Siga este enlace para ver otros tipos de publicaciones sobre el tema: LSTM.
Tesis sobre el tema "LSTM"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "LSTM".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
1
Edholm, Gustav y Xuechen Zuo. "A comparison between aconventional LSTM network and agrid LSTM network applied onspeech recognition". Thesis, KTH, Skolan för teknikvetenskap (SCI), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-230173.
Texto completoResumen
In this paper, a comparision between the conventional LSTM network and the one-dimensionalgrid LSTM network applied on single word speech recognition is conducted. The performanceof the networks are measured in terms of accuracy and training time. The conventional LSTMmodel is the current state of the art method to model speech recognition. However, thegrid LSTM architecture has proven to be successful in solving other emperical tasks such astranslation and handwriting recognition. When implementing the two networks in the sametraining framework with the same training data of single word audio files, the conventionalLSTM network yielded an accuracy rate of 64.8 % while the grid LSTM network yielded anaccuracy rate of 65.2 %. Statistically, there was no difference in the accuracy rate betweenthe models. In addition, the conventional LSTM network took 2 % longer to train. However,this difference in training time is considered to be of little significance when tralnslating it toabsolute time. Thus, it can be concluded that the one-dimensional grid LSTM model performsjust as well as the conventional one.
2
Fu, Reid J. "CCG Realization with LSTM Hypertagging". The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1534236955413883.
Texto completo
3
Nordin, Stensö Isak. "Predicting Tropical Thunderstorm Trajectories Using LSTM". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231613.
Texto completoResumen
Thunderstorms are both dangerous as well as important rain-bearing structures for large parts of the world. The prediction of thunderstorm trajectories is however difficult, especially in tropical regions. This is largely due to their smaller size and shorter lifespan. To overcome this issue, this thesis investigates how well a neural network composed of long short-term memory (LSTM) units can predict the trajectories of thunderstorms, based on several years of lightning strike data. The data is first clustered, and important features are extracted from it. These are used to predict the mean position of the thunderstorms using an LSTM network. A random search is then carried out to identify optimal parameters for the LSTM model. It is shown that the trajectories predicted by the LSTM are much closer to the true trajectories than what a linear model predicts. This is especially true for predictions of more than 1 hour. Scores commonly used to measure forecast accuracy are applied to compare the LSTM and linear model. It is found that the LSTM significantly improves forecast accuracy compared to the linear model.Åskväder är både farliga och livsviktiga bärare av vatten för stora delar av världen. Det är dock svårt att förutsäga åskcellernas banor, främst i tropiska områden. Detta beror till större delen på deras mindre storlek och kortare livslängd. Detta examensarbete undersöker hur väl ett neuralt nätverk, bestående av long short-term memory-lager (LSTM) kan förutsäga åskväders banor baserat på flera års blixtnedlslagsdata. Först klustras datan, och viktiga karaktärsdrag hämtas ut från den. Dessa används för att förutspå åskvädrens genomsnittliga position med hjälp av ett LSTMnätverk. En slumpmässig sökning genomförs sedan för att identifiera optimala parametrar för LSTM-modellen. Det fastslås att de banor som förutspås av LSTM-modellen är mycket närmare de sanna banorna, än de som förutspås av en linjär modell. Detta gäller i synnerhet för förutsägelser mer än 1 timme framåt. Värden som är vanliga för att bedöma prognosers träffsäkerhet beräknas för att jämföra LSTM-modellen och den linjära. Det visas att LSTM-modellen klart förbättrar förutsägelsernas träffsäkerhet jämfört med den linjära modellen.
4
Rogers, Joseph. "Effects of an LSTM Composite Prefetcher". Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-396842.
Texto completoResumen
Recent work in computer architecture and machine learning has seen various groups begin exploring the viability of using neural networks to augment conventional processor designs. Of particular interest is using the predictive capabilities of techniques in natural language processing to assist traditional CPU memory prefetching methods. This work demonstrates one of these proposed techniques, and examines some of the challenges associated with producing satisfactory and consistently reproducible results. Special attention is given to data acquisition and preprocessing as different methods. This is important since the handling training data can enormously influence on the final prediction accuracy of the network. Finally, a number of changes to improve these methods are suggested. These include ways to raise accuracy, reduce network overhead, and to improve the consistency of results. This work shows that augmenting an LSTM prefetcher with a simple stream prefetcher leads to moderate improvements in prediction accuracy. This could be a way to start reducing the size of neural networks so they are usable in real hardware.
5
Schelhaas, Wietze. "Predicting network performancein IoT environments using LSTM". Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-454062.
Texto completoResumen
There are still many problems that need to be solved with Internet of Things (IoT) technology, one of them being performance assurance. To ensure a certain quality of service in an IoT environment, the network has to be monitored and actively measured. However, Due to the limited computational recourses Internet of things nodes have, active measurement is difficult to achieve without also inducing energy and network overhead. A potential solution to this problem is to apply a machine-learning algorithm to predict network performance metrics such as round- trip time or packet loss. By substituting active performance measurements with a machine-learning algorithm, you reduce the overhead created by active performance measurements Previous research has revolved around applying traditional machine learning algorithms to wireless sensor network features such as packet statistics and topological information of the network to predict round-trip time. The purpose of this thesis is to use a more advanced deep learning algorithm namely Long short-term memory (LSTM) to try and exploit time dependencies in the data Three different datasets containing network statistics are used in three different experiments. In every experiment, LSTM models with different configurations are created, and their predictioncapabilities are compared to traditional neural networks with equivalent configurations. In all experiments, both the LSTM model and its corresponding equivalent neural network model produced similar results, meaning that a time dependency in the data could not be proven.
6
Nilson, Erik y Arvid Renström. "LSTM-nätverk för generellt Atari 2600 spelande". Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17174.
Texto completoResumen
I detta arbete jämfördes ett LSTM-nätverk med ett feedforward-nätverk för generellt Atari 2600 spelande. Prestandan definierades som poängen agenten får för ett visst spel. Hypotesen var att LSTM skulle prestera minst lika bra som feedforward och förhoppningsvis mycket bättre. För att svara på frågeställningen skapades två olika agenter, en med ett LSTM-nätverk och en med ett feedforward-nätverk. Experimenten utfördes på Stella emulatorn med hjälp av ramverket the Arcade Learning Environment (ALE). Hänsyn togs till Machado råd om inställningar för användning av ALE och hur agenter borde tränas och evalueras samtidigt. Agenterna utvecklades med hjälp av en genetisk algoritm. Resultaten visade att LSTM var minst lika bra som feedforward men båda metoderna blev slagna av Machados metoder. Toppoängen i varje spel jämfördes med Granfelts arbete som har varit en utgångspunkt för detta arbete.
7
Paschou, Michail. "ASIC implementation of LSTM neural network algorithm". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254290.
Texto completoResumen
LSTM neural networks have been used for speech recognition, image recognition and other artificial intelligence applications for many years. Most applications perform the LSTM algorithm and the required calculations on cloud computers. Off-line solutions include the use of FPGAs and GPUs but the most promising solutions include ASIC accelerators designed for this purpose only. This report presents an ASIC design capable of performing the multiple iterations of the LSTM algorithm on a unidirectional and without peepholes neural network architecture. The proposed design provides arithmetic level parallelism options as blocks are instantiated based on parameters. The internal structure of the design implements pipelined, parallel or serial solutions depending on which is optimal in every case. The implications concerning these decisions are discussed in detail in the report. The design process is described in detail and the evaluation of the design is also presented to measure accuracy and error of the design output.This thesis work resulted in a complete synthesizable ASIC design implementing an LSTM layer, a Fully Connected layer and a Softmax layer which can perform classification of data based on trained weight matrices and bias vectors. The design primarily uses 16-bit fixed point format with 5 integer and 11 fractional bits but increased precision representations are used in some blocks to reduce error output. Additionally, a verification environment has also been designed and is capable of performing simulations, evaluating the design output by comparing it with results produced from performing the same operations with 64-bit floating point precision on a SystemVerilog testbench and measuring the encountered error. The results concerning the accuracy and the design output error margin are presented in this thesis report. The design went through Logic and Physical synthesis and successfully resulted in a functional netlist for every tested configuration. Timing, area and power measurements on the generated netlists of various configurations of the design show consistency and are reported in this report.LSTM neurala nätverk har använts för taligenkänning, bildigenkänning och andra artificiella intelligensapplikationer i många år. De flesta applikationer utför LSTM-algoritmen och de nödvändiga beräkningarna i digitala moln. Offline lösningar inkluderar användningen av FPGA och GPU men de mest lovande lösningarna inkluderar ASIC-acceleratorer utformade för endast dettaändamål. Denna rapport presenterar en ASIC-design som kan utföra multipla iterationer av LSTM-algoritmen på en enkelriktad neural nätverksarkitetur utan peepholes. Den föreslagna designed ger aritmetrisk nivå-parallellismalternativ som block som är instansierat baserat på parametrar. Designens inre konstruktion implementerar pipelinerade, parallella, eller seriella lösningar beroende på vilket anternativ som är optimalt till alla fall. Konsekvenserna för dessa beslut diskuteras i detalj i rapporten. Designprocessen beskrivs i detalj och utvärderingen av designen presenteras också för att mäta noggrannheten och felmarginal i designutgången. Resultatet av arbetet från denna rapport är en fullständig syntetiserbar ASIC design som har implementerat ett LSTM-lager, ett fullständigt anslutet lager och ett Softmax-lager som kan utföra klassificering av data baserat på tränade viktmatriser och biasvektorer. Designen använder huvudsakligen 16bitars fast flytpunktsformat med 5 heltal och 11 fraktions bitar men ökade precisionsrepresentationer används i vissa block för att minska felmarginal. Till detta har även en verifieringsmiljö utformats som kan utföra simuleringar, utvärdera designresultatet genom att jämföra det med resultatet som produceras från att utföra samma operationer med 64-bitars flytpunktsprecision på en SystemVerilog testbänk och mäta uppstådda felmarginal. Resultaten avseende noggrannheten och designutgångens felmarginal presenteras i denna rapport.Designen gick genom Logisk och Fysisk syntes och framgångsrikt resulterade i en funktionell nätlista för varje testad konfiguration. Timing, area och effektmätningar på den genererade nätlistorna av olika konfigurationer av designen visar konsistens och rapporteras i denna rapport.
8
Valluru, Aravind-Deshikh. "Realization of LSTM Based Cognitive Radio Network". Thesis, University of North Texas, 2019. https://digital.library.unt.edu/ark:/67531/metadc1538697/.
Texto completoResumen
This thesis presents the realization of an intelligent cognitive radio network that uses long short term memory (LSTM) neural network for sensing and predicting the spectrum activity at each instant of time. The simulation is done using Python and GNU Radio. The implementation is done using GNU Radio and Universal Software Radio Peripherals (USRP). Simulation results show that the confidence factor of opportunistic users not causing interference to licensed users of the spectrum is 98.75%. The implementation results demonstrate high reliability of the LSTM based cognitive radio network.
9
Li, Edwin. "LSTM Neural Network Models for Market Movement Prediction". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231627.
Texto completoResumen
Interpreting time varying phenomena is a key challenge in the capital markets. Time series analysis using autoregressive methods has been carried out over the last couple of decades, often with reassuring results. However, such methods sometimes fail to explain trends and cyclical fluctuations, which may be characterized by long-range dependencies or even dependencies between the input features. The purpose of this thesis is to investigate whether recurrent neural networks with LSTM-cells can be used to capture these dependencies, and ultimately be used as a complement for index trading decisions. Experiments are made on different setups of the S&P-500 stock index, and two distinct models are built, each one being an improvement of the previous model. The first model is a multivariate regression model, and the second model is a multivariate binary classifier. The output of each model is used to reason about the future behavior of the index. The experiment shows for the configuration provided that LSTM RNNs are unsuitable for predicting exact values of daily returns, but gives satisfactory results when used to predict the direction of the movement.Att förstå och kunna förutsäga hur index varierar med tiden och andra parametrar är ett viktigt problem inom kapitalmarknader. Tidsserieanalys med autoregressiva metoder har funnits sedan årtionden tillbaka, och har oftast gett goda resultat. Dessa metoder saknar dock möjligheten att förklara trender och cykliska variationer i tidsserien, något som kan karaktäriseras av tidsvarierande samband, men även samband mellan parametrar som indexet beror utav. Syftet med denna studie är att undersöka om recurrent neural networks (RNN) med long short-term memory-celler (LSTM) kan användas för att fånga dessa samband, för att slutligen användas som en modell för att komplettera indexhandel. Experimenten är gjorda mot en modifierad S&P-500 datamängd, och två distinkta modeller har tagits fram. Den ena är en multivariat regressionsmodell för att förutspå exakta värden, och den andra modellen är en multivariat klassifierare som förutspår riktningen på nästa dags indexrörelse. Experimenten visar för den konfiguration som presenteras i rapporten att LSTM RNN inte passar för att förutspå exakta värden för indexet, men ger tillfredsställande resultat när modellen ska förutsäga indexets framtida riktning.
10
Wang, Nancy. "Spectral Portfolio Optimisation with LSTM Stock Price Prediction". Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273611.
Texto completoResumen
Nobel Prize-winning modern portfolio theory (MPT) has been considered to be one of the most important and influential economic theories within finance and investment management. MPT assumes investors to be riskaverse and uses the variance of asset returns as a proxy of risk to maximise the performance of a portfolio. Successful portfolio management reply, thus on accurate risk estimate and asset return prediction. Risk estimates are commonly obtained through traditional asset pricing factor models, which allow the systematic risk to vary over time domain but not in the frequency space. This approach can impose limitations in, for instance, risk estimation. To tackle this shortcoming, interest in applications of spectral analysis to financial time series has increased lately. Among others, the novel spectral portfolio theory and the spectral factor model which demonstrate enhancement in portfolio performance through spectral risk estimation [1][11]. Moreover, stock price prediction has always been a challenging task due to its non-linearity and non-stationarity. Meanwhile, Machine learning has been successfully implemented in a wide range of applications where it is infeasible to accomplish the needed tasks traditionally. Recent research has demonstrated significant results in single stock price prediction by artificial LSTM neural network [6][34]. This study aims to evaluate the combined effect of these two advancements in a portfolio optimisation problem and optimise a spectral portfolio with stock prices predicted by LSTM neural networks. To do so, we began with mathematical derivation and theoretical presentation and then evaluated the portfolio performance generated by the spectral risk estimates and the LSTM stock price predictions, as well as the combination of the two. The result demonstrates that the LSTM predictions alone performed better than the combination, which in term performed better than the spectral risk alone.Den nobelprisvinnande moderna portföjlteorin (MPT) är utan tvekan en av de mest framgångsrika investeringsmodellerna inom finansvärlden och investeringsstrategier. MPT antar att investerarna är mindre benägna till risktagande och approximerar riskexponering med variansen av tillgångarnasränteavkastningar. Nyckeln till en lyckad portföljförvaltning är därmed goda riskestimat och goda förutsägelser av tillgångspris. Riskestimering görs vanligtvis genom traditionella prissättningsmodellerna som tillåter risken att variera i tiden, dock inte i frekvensrummet. Denna begränsning utgör bland annat ett större fel i riskestimering. För att tackla med detta har intresset för tillämpningar av spektraanalys på finansiella tidsserier ökat de senast åren. Bland annat är ett nytt tillvägagångssätt för att behandla detta den nyintroducerade spektralportföljteorin och spektralfak- tormodellen som påvisade ökad portföljenprestanda genom spektralriskskattning [1][11]. Samtidigt har prediktering av aktierpriser länge varit en stor utmaning på grund av dess icke-linjära och icke-stationära egenskaper medan maskininlärning har kunnat använts för att lösa annars omöjliga uppgifter. Färska studier har påvisat signifikant resultat i aktieprisprediktering med hjälp av artificiella LSTM neurala nätverk [6][34]. Detta arbete undersöker kombinerade effekten av dessa två framsteg i ett portföljoptimeringsproblem genom att optimera en spektral portfölj med framtida avkastningar predikterade av ett LSTM neuralt nätverk. Arbetet börjar med matematisk härledningar och teoretisk introduktion och sedan studera portföljprestation som genereras av spektra risk, LSTM aktieprispredikteringen samt en kombination av dessa två. Resultaten visar på att LSTM-predikteringen ensam presterade bättre än kombinationen, vilket i sin tur presterade bättre än enbart spektralriskskattningen.
11
Tang, Hao. "Bidirectional LSTM-CNNs-CRF Models for POS Tagging". Thesis, Uppsala universitet, Institutionen för lingvistik och filologi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-362823.
Texto completoResumen
In order to achieve state-of-the-art performance for part-of-speech(POS) tagging, the traditional systems require a significant amount of hand-crafted features and data pre-processing. In this thesis, we present a discriminative word embedding, character embedding and byte pair encoding (BPE) hybrid neural network architecture to implement a true end-to-end system without feature engineering and data pre-processing. The neural network architecture is a combination of bidirectional LSTM, CNNs, and CRF, which can achieve a state-of-the-art performance for a wide range of sequence labeling tasks. We evaluate our model on Universal Dependencies (UD) dataset for English, Spanish, and German POS tagging. It outperforms other models with 95.1%, 98.15%, and 93.43% accuracy on testing datasets respectively. Moreover, the largest improvements of our model appear on out-of-vocabulary corpora for Spanish and German. According to statistical significance testing, the improvements of English on testing and out-of-vocabulary corpora are not statistically significant. However, the improvements of the other more morphological languages are statistically significant on their corresponding corpora.
12
Andréasson, David y Blomquist Jesper Mortensen. "Forecasting the OMXS30 - a comparison between ARIMA and LSTM". Thesis, Uppsala universitet, Statistiska institutionen, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-413793.
Texto completoResumen
Machine learning is a rapidly growing field with more and more applications being proposed every year, including but not limited to the financial sector. In this thesis, historical adjusted closing prices from the OMXS30 index are used to forecast the corresponding future values using two different approaches; one using an ARIMA model and the other using an LSTM neural network. The forecasts are made on three different time intervals: 90, 30 and 7 days ahead. The results showed that the LSTM model performs slightly better when forecasting 90 and 30 days ahead, whereas the ARIMA model has comparable accuracy on the seven day forecast.
13
Cavallie, Mester Jon William. "Using LSTM Neural Networks To Predict Daily Stock Returns". Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-106124.
Texto completoResumen
Long short-term memory (LSTM) neural networks have been proven to be effective for time series prediction, even in some instances where the data is non-stationary. This lead us to examine their predictive ability of stock market returns, as the development of stock prices and returns tend to be a non-stationary time series. We used daily stock trading data to let an LSTM train models at predicting daily returns for 60 stocks from the OMX30 and Nasdaq-100 indices. Subsequently, we measured their accuracy, precision, and recall. The mean accuracy was 49.75 percent, meaning that the observed accuracy was close to the accuracy one would observe by randomly selecting a prediction for each day and lower than the accuracy achieved by blindly predicting all days to be positive. Finally, we concluded that further improvements need to be made for models trained by LSTMs to have any notable predictive ability in the area of stock returns.
14
Pokhrel, Abhishek <1996>. "Stock Returns Prediction using Recurrent Neural Networks with LSTM". Master's Degree Thesis, Università Ca' Foscari Venezia, 2022. http://hdl.handle.net/10579/22038.
Texto completoResumen
Research in asset pricing has, until recently, side-stepped the high dimensionality problem by focusing on low-dimensional models. Work on cross-sectional stock return prediction, for example, has focused on regressions with a small number of characteristics. Given the background of an enormously large number of variables that could potentially be relevant for predicting returns, focusing on such a small number of factors effectively means that the researchers are imposing a very high degree of sparsity on these models. This research studies the use of the recurrent neural network (RNN) method to deal with the “curse of dimensionality” challenge in the cross-section of stock returns. The purpose is to predict the daily stock returns. Compared with the traditional method of returns, namely the CAPM model, the focus will be on using the LSTM model to do the prediction. LSTM is very powerful in sequence prediction problems because they’re able to store past information. Thus, we compare the forecast of returns from the LSTM model with the traditional CAPM model. The comparison will be made using the out-of-sample R2 along with the Sharpe Ratio and Sortino Ratio. Finally, we conclude with the further improvements that need to be made for models trained by LSTMs to have any notable predictive ability in the area of stock returns.
15
Gualandi, Giacomo. "Analisi di dataset in campo finanziario mediante reti neurali LSTM". Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19623/.
Texto completoResumen
Con il presente elaborato si è esplorato il campo della data analytics.
È stato analizzato un dataset relativo all' andamento storico del titolo di borsa di una società, i cui dati sono stati manipolati in modo tale da renderli compatibili per un loro utilizzo in una applicazione di Machine Learning. Si sono approfondite le reti neurali artificiali LSTM e con esse si è creato un modello che permettesse di effettuare delle predizioni sui valori futuri del titolo. Infine sono state valutate le differenze tra i valori predetti e quelli reali assunti dal titolo di borsa.
16
Larsson, Joel. "Optimizing text-independent speaker recognition using an LSTM neural network". Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-26312.
Texto completoResumen
In this paper a novel speaker recognition system is introduced. Automated speaker recognition has become increasingly popular to aid in crime investigations and authorization processes with the advances in computer science. Here, a recurrent neural network approach is used to learn to identify ten speakers within a set of 21 audio books. Audio signals are processed via spectral analysis into Mel Frequency Cepstral Coefficients that serve as speaker specific features, which are input to the neural network. The Long Short-Term Memory algorithm is examined for the first time within this area, with interesting results. Experiments are made as to find the optimum network model for the problem. These show that the network learns to identify the speakers well, text-independently, when the recording situation is the same. However the system has problems to recognize speakers from different recordings, which is probably due to noise sensitivity of the speech processing algorithm in use.
17
Wolpher, Maxim. "Anomaly Detection in Unstructured Time Series Datausing an LSTM Autoencoder". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231368.
Texto completoResumen
An exploration of anomaly detection. Much work has been done on the topic of anomalyd etection, but what seems to be lacking is a dive into anomaly detection of unstructuredand unlabeled data. This thesis aims to determine the efctiveness of combining recurrentneural networks with autoencoder structures for sequential anomaly detection. The use of an LSTM autoencoder will be detailed, but along the way there will also be backgroundon time-independent anomaly detection using Isolation Forests and Replicator Neural Networks on the benchmark DARPA dataset. The empirical results in this thesis show that Isolation Forests and Replicator Neural Networks both reach an F1-score of 0.98. The RNN reached a ROC AUC score of 0.90 while the Isolation Forest reached a ROC AUC of 0.99. The results for the LSTM Autoencoder show that with 137 features extracted from the unstructured data, it can reach an F1 score of 0.8 and a ROC AUC score of 0.86En undersökning av anomalitetsdetektering. Mycket arbete har gjorts inom ämnet anomalitetsdetektering, men det som verkar saknas är en fördjupning i anomalitetsdetektering av ostrukturerad och omärktdata. Denna avhandling syftar till att bestämma effektiviteten av att kombinera Recurrent Neural Networks med Autoencoder strukturer för sekventiell anomalitetsdetektion. Användningen av en LSTM autoencoder kommeratt beskrivas i detalj, men bakgrund till tidsoberoende anomalitetsdetektering med hjälp av Isolation Forests och Replicator Neural Networks på referens DARPA dataset kommer också att täckas. De empiriska resultaten i denna avhandling visar att Isolation Forestsoch Replicator Neural Networks (RNN) båda når en F1-score på 0,98. RNN nådde en ROC AUC-score på 0,90 medan Isolation Forest nådde en ROC-AUC på 0,99. Resultaten för LSTM Autoencoder visar att med 137 features extraherade från ostrukturerad data kan den nå en F1-score på 0,80 och en ROC AUC-score på 0,86.
18
Berenji, Ardestani Sarah. "Time Series Anomaly Detection and Uncertainty Estimation using LSTM Autoencoders". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281354.
Texto completoResumen
The goal of this thesis is to implement an anomaly detection tool using LSTM autoencoder and apply a novel method for uncertainty estimation using Bayesian NeuralNetworks (BNNs) based on a paper from Uber research group [1]. Having a reliable anomaly detection tool and accurate uncertainty estimation is critical in many fields. At Telia, such a tool can be used in many different data domains like device logs to detect abnormal behaviours. Our method uses an autoencoder to extract important features and learn the encoded representation of the time series. This approach helps to capture testing data points coming from a different population. We then train a prediction model based on this encoder’s representation of data. An uncertainty estimation algorithm is used to estimate the model’s uncertainty, which breaks it down to three different sources: model uncertainty, model misspecification, and inherent noise. To get the first two, a Monte Carlo dropout approach is used which is simple to implement and easy to scale. For the third part, a bootstrap approach that estimates the noise level via the residual sum of squares on validation data is used. As a result, we could see that our proposed model can make a better prediction in comparison to our benchmarks. Although the difference is not big, yet it shows that making prediction based on encoding representation is more accurate. The anomaly detection results based on these predictions also show that our proposed model has a better performance than the benchmarks. This means that using autoencoder can improve both prediction and anomaly detection tasks. Additionally, we conclude that using deep neutral networks would show bigger improvement if the data has more complexity.Målet med den här uppsatsen är att implentera ett verktyg för anomaliupptäckande med hjälp av LSTM autoencoders och applicera en ny metod för osäkerhetsestimering med hjälp av Bayesian Neural Networks (BNN) baserat på en artikel från Uber research group [1]. Pålitliga verktyg för att upptäcka anomalier och att göra precisa osäkerhetsestimeringar är kritiskt i många fält. På Telia kan ett sådant verktyg användas för många olika datadomäner, som i enhetsloggar för att upptäcka abnormalt beteende. Vår metod använder en autoencoder för att extrahera viktiga egenskaper och lära sig den kodade representationen av tidsserierna. Detta tillvägagångssätt hjälper till med att ta in testdatapunker som kommer in från olika grundmängder. Sedan tränas en förutsägelsemodell baserad på encoderns representation av datan. För att uppskatta modellens osäkerhet används en uppskattningsalgoritm som delar upp osäkerheten till tre olika källor. Dessa tre källor är: modellosäkerhet, felspeciferad model, och naturligt brus. För att få de första två används en Monte Carlo dropout approach som är lätt att implementera och enkel att skala. För den tredje delen används en enkel anfallsvikel som uppskattar brusnivån med hjälp av felkvadratsumman av valideringsdatan. Som ett resultat kunde vi se att vår föreslagna model kan göra bättre förutsägelser än våra benchmarks. Även om skillnaden inte är stor så visar det att att använda autoencoderrepresentation för att göra förutsägelser är mer noggrant. Resulaten för anomaliupptäckanden baserat på dessa förutsägelser visar också att vår föreslagna modell har bättre prestanda än benchmarken. Det betyder att användning av autoencoders kan förbättra både förutsägelser och anomaliupptäckande. Utöver det kan vi dra slutsatsen att användning av djupa neurala nätverk skulle visa en större förbättring om datan hade mer komplexitet.
19
Singh, J. P., A. Kumar, Nripendra P. Rana y Y. K. Dwivedi. "Attention-based LSTM network for rumor veracity estimation of tweets". Springer, 2020. http://hdl.handle.net/10454/17942.
Texto completoResumen
YesTwitter has become a fertile place for rumors, as information can spread to a large number of people immediately. Rumors can mislead public opinion, weaken social order, decrease the legitimacy of government, and lead to a significant threat to social stability. Therefore, timely detection and debunking rumor are urgently needed. In this work, we proposed an Attention-based Long-Short Term Memory (LSTM) network that uses tweet text with thirteen different linguistic and user features to distinguish rumor and non-rumor tweets. The performance of the proposed Attention-based LSTM model is compared with several conventional machine and deep learning models. The proposed Attention-based LSTM model achieved an F1-score of 0.88 in classifying rumor and non-rumor tweets, which is better than the state-of-the-art results. The proposed system can reduce the impact of rumors on society and weaken the loss of life, money, and build the firm trust of users with social media platforms.
20
Backer-Meurke, Henrik y Marcus Polland. "Predicting Road Rut with a Multi-time-series LSTM Model". Thesis, Högskolan Dalarna, Institutionen för information och teknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:du-37599.
Texto completoResumen
Road ruts are depressions or grooves worn into a road. Increases in rut depth are highly undesirable due to the heightened risk of hydroplaning. Accurately predicting increases in road rut depth is important for maintenance planning within the Swedish Transport Administration. At the time of writing this paper, the agency utilizes a linear regression model and is developing a feed-forward neural network for road rut predictions. The aim of the study was to evaluate the possibility of using a Recurrent Neural Network to predict road rut. Through design science research, an artefact in the form of a LSTM model was designed, developed, and evaluated.The dataset consisted of multiple-multivariate short time series where research was limited. Case studies were conducted which inspired the conceptual design of the model. The baseline LSTM model proposed in this paper utilizes the full dataset in combination with time-series individualization through an added index feature. Additional features thought to correlate with rut depth was also studied through multiple training set variations. The model was evaluated by calculating the Root Mean Squared Error (RMSE) and the Mean Absolute Error (MAE) for each training set variation. The baseline model predicted rut depth with a MAE of 0.8110 (mm) and a RMSE of 1.124 (mm) outperforming a control set without the added index. The feature with the highest correlation to rut depth was curvature with a MAEof 0.8031 and a RMSE of 1.1093. Initial finding shows that there is a possibility of utilizing an LSTM model trained on multiple-multivariate time series to predict rut depth. Time series individualization through an added index feature yielded better results than control, indicating that it had the desired effect on model performance.
21
Ärlemalm, Filip. "Harbour Porpoise Click Train Classification with LSTM Recurrent Neural Networks". Thesis, KTH, Teknisk informationsvetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-215088.
Texto completoResumen
The harbour porpoise is a toothed whale whose presence is threatened in Scandinavia. Onestep towards preserving the species in critical areas is to study and observe the harbourporpoise population growth or decline in these areas. Today this is done by using underwateraudio recorders, so called hydrophones, and manual analyzing tools. This report describes amethod that modernizes the process of harbour porpoise detection with machine learning. Thedetection method is based on data collected by the hydrophone AQUAclick 100. The data isprocessed and classified automatically with a stacked long short-term memory recurrent neuralnetwork designed specifically for this purpose.Vanlig tumlare är en tandval vars närvaro i Skandinavien är hotad. Ett steg mot att kunnabevara arten i utsatta områden är att studera och observera tumlarbeståndets tillväxt ellertillbakagång i dessa områden. Detta görs idag med hjälp av ljudinspelare för undervattensbruk,så kallade hydrofoner, samt manuella analysverktyg. Den här rapporten beskriver enmetod som moderniserar processen för detektering av vanlig tumlare genom maskininlärning.Detekteringen är baserad på insamlad data från hydrofonen AQUAclick 100. Bearbetning ochklassificering av data har automatiserats genom att använda ett staplat återkopplande neuraltnätverk med långt korttidsminne utarbetat specifikt för detta ändamål.
22
Bergström, Carl y Oscar Hjelm. "Impact of Time Steps on Stock Market Prediction with LSTM". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-262221.
Texto completoResumen
Machine learning models as tools for predicting time series have in recent years proven to perform exceptionally well. With financial time series in the form of stock indices being inherently complex and subject to noise and volatility, the prediction of stock market movements has proven to be especially difficult throughout extensive research. The objective of this study is to thoroughly analyze the LSTM architecture for neural networks and its performance when applied to the S&P 500 stock index. The main research question revolves around quantifying the impact of varying the number of time steps in the LSTM model on predictive performance when applied to the S&P 500 index. The data used in the model is of high reliability downloaded from the Bloomberg Terminal, where the closing price has been used as feature in the model. Other constituents of the model have been based in previous research, where satisfactory results have been reached. The results indicate that among the evaluated time steps, ten steps provided the superior performance. However, the impact of varying time steps is not all too significant for the overall performance of the model. Finally, the implications of the results for the field of research present themselves as good basis for future research, where parameters are varied and fine-tuned in pursuit of optimal performance.Maskininlärningsmodeller som redskap för att förutspå tidsserier har de senaste åren visat sig prestera exceptionellt bra. Vad gäller finansiella tidsserier i formen av aktieindex, som har en inneboende komplexitet, och är föremål för störningar och volatilitet, har förutsägelse av aktiemarknadsrörelser visat sig vara särskilt svårt igenom omfattande forskning. Målet med denna studie är att grundligt undersöka LSTM-arkitekturen för neurala nätverk och dess prestanda när den appliceras på aktieindexet S&P 500. Huvudfrågan kretsar kring att kvantifiera inverkan som varierande av antal tidssteg i LTSM-modellen har på prediktivprestanda när den appliceras på aktieindexet S&P 500. Data som använts i modellen är av hög pålitlighet, nedladdad frånBloomberg-terminalen, där stängningskurs har använts som feature i modellen. Andra beståndsdelar av modellen har baserats i tidigare forskning, där tillfredsställande resultat har uppnåtts. Resultaten indikerar att bland de testade tidsstegen så producerartio tidssteg bäst resultat. Dock verkar inte påverkan av antalet tidssteg vara särskilt signifikant för modellens övergripandeprestanda. Slutligen så presenterar sig implikationerna av resultaten för forskningsområdet som god grund för framtida forskning, där parametrar kan varieras och finjusteras i strävan efter optimal prestanda.
23
Khaghani, Farnaz. "A Deep Learning Approach to Predict Accident Occurrence Based on Traffic Dynamics". Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/98801.
Texto completoResumen
Traffic accidents are of concern for traffic safety; 1.25 million deaths are reported each year. Hence, it is crucial to have access to real-time data and rapidly detect or predict accidents. Predicting the occurrence of a highway car accident accurately any significant length of time into the future is not feasible since the vast majority of crashes occur due to unpredictable human negligence and/or error. However, rapid traffic incident detection could reduce incident-related congestion and secondary crashes, alleviate the waste of vehicles’ fuel and passengers’ time, and provide appropriate information for emergency response and field operation. While the focus of most previously proposed techniques is predicting the number of accidents in a certain region, the problem of predicting the accident occurrence or fast detection of the accident has been little studied. To address this gap, we propose a deep learning approach and build a deep neural network model based on long short term memory (LSTM). We apply it to forecast the expected speed values on freeways’ links and identify the anomalies as potential accident occurrences. Several detailed features such as weather, traffic speed, and traffic flow of upstream and downstream points are extracted from big datasets. We assess the proposed approach on a traffic dataset from Sacramento, California. The experimental results demonstrate the potential of the proposed approach in identifying the anomalies in speed value and matching them with accidents in the same area. We show that this approach can handle a high rate of rapid accident detection and be implemented in real-time travelers’ information or emergency management systems.M.S.
Rapid traffic accident detection/prediction is essential for scaling down non-recurrent conges- tion caused by traffic accidents, avoiding secondary accidents, and accelerating emergency system responses. In this study, we propose a framework that uses large-scale historical traffic speed and traffic flow data along with the relevant weather information to obtain robust traffic patterns. The predicted traffic patterns can be coupled with the real traffic data to detect anomalous behavior that often results in traffic incidents in the roadways. Our framework consists of two major steps. First, we estimate the speed values of traffic at each point based on the historical speed and flow values of locations before and after each point on the roadway. Second, we compare the estimated values with the actual ones and introduce the ones that are significantly different as an anomaly. The anomaly points are the potential points and times that an accident occurs and causes a change in the normal behavior of the roadways. Our study shows the potential of the approach in detecting the accidents while exhibiting promising performance in detecting the accident occurrence at a time close to the actual time of occurrence.
24
Poormehdi, Ghaemmaghami Masoumeh. "Tracking of Humans in Video Stream Using LSTM Recurrent Neural Network". Thesis, KTH, Teoretisk datalogi, TCS, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-217495.
Texto completoResumen
In this master thesis, the problem of tracking humans in video streams by using Deep Learning is examined. We use spatially supervised recurrent convolutional neural networks for visual human tracking. In this method, the recurrent convolutional network uses both the history of locations and the visual features from the deep neural networks. This method is used for tracking, based on the detection results. We concatenate the location of detected bounding boxes with high-level visual features produced by convolutional networks and then predict the tracking bounding box for next frames. Because a video contain continuous frames, we decide to have a method which uses the information from history of frames to have a robust tracking in different visually challenging cases such as occlusion, motion blur, fast movement, etc. Long Short-Term Memory (LSTM) is a kind of recurrent convolutional neural network and useful for our purpose. Instead of using binary classification which is commonly used in deep learning based tracking methods, we use a regression for direct prediction of the tracking locations. Our purpose is to test our method on real videos which is recorded by head-mounted camera. So our test videos are very challenging and contain different cases of fast movements, motion blur, occlusions, etc. Considering the limitation of the training data-set which is spatially imbalanced, we have a problem for tracking the humans who are in the corners of the image but in other challenging cases, the proposed tracking method worked well.I detta examensarbete undersöks problemet att spåra människor i videoströmmar genom att använda deep learning. Spårningen utförs genom att använda ett recurrent convolutional neural network. Input till nätverket består av visuella features extraherade med hjälp av ett convolutional neural network, samt av detektionsresultat från tidigare frames. Vi väljer att använda oss av historiska detektioner för att skapa en metod som är robust mot olika utmanande situationer, som t.ex. snabba rörelser, rörelseoskärpa och ocklusion. Long Short- Term Memory (LSTM) är ett recurrent convolutional neural network som är användbart för detta ändamål. Istället för att använda binära klassificering, vilket är vanligt i många deep learning-baserade tracking-metoder, så använder vi oss av regression för att direkt förutse positionen av de spårade subjekten. Vårt syfte är att testa vår metod på videor som spelats in med hjälp av en huvudmonterad kamera. På grund av begränsningar i våra träningsdataset som är spatiellt oblanserade har vi problem att spåra människor som befinner sig i utkanten av bildområdet, men i andra utmanande fall lyckades spårningen bra.
25
Singh, Akash. "Anomaly Detection for Temporal Data using Long Short-Term Memory (LSTM)". Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-215723.
Texto completoResumen
We explore the use of Long short-term memory (LSTM) for anomaly detection in temporal data. Due to the challenges in obtaining labeled anomaly datasets, an unsupervised approach is employed. We train recurrent neural networks (RNNs) with LSTM units to learn the normal time series patterns and predict future values. The resulting prediction errors are modeled to give anomaly scores. We investigate different ways of maintaining LSTM state, and the effect of using a fixed number of time steps on LSTM prediction and detection performance. LSTMs are also compared to feed-forward neural networks with fixed size time windows over inputs. Our experiments, with three real-world datasets, show that while LSTM RNNs are suitable for general purpose time series modeling and anomaly detection, maintaining LSTM state is crucial for getting desired results. Moreover, LSTMs may not be required at all for simple time series.Vi undersöker Long short-term memory (LSTM) för avvikelsedetektion i tidsseriedata. På grund av svårigheterna i att hitta data med etiketter så har ett oövervakat an-greppssätt använts. Vi tränar rekursiva neuronnät (RNN) med LSTM-noder för att lära modellen det normala tidsseriemönstret och prediktera framtida värden. Vi undersö-ker olika sätt av att behålla LSTM-tillståndet och effekter av att använda ett konstant antal tidssteg på LSTM-prediktionen och avvikelsedetektionsprestandan. LSTM är också jämförda med vanliga neuronnät med fasta tidsfönster över indata. Våra experiment med tre verkliga datasetvisar att även om LSTM RNN är tillämpbara för generell tidsseriemodellering och avvikelsedetektion så är det avgörande att behålla LSTM-tillståndet för att få de önskaderesultaten. Dessutom är det inte nödvändigt att använda LSTM för enkla tidsserier.
26
Zambezi, Samantha. "Predicting social unrest events in South Africa using LSTM neural networks". Master's thesis, Faculty of Science, 2021. http://hdl.handle.net/11427/33986.
Texto completoResumen
This thesis demonstrates an approach to predict the count of social unrest events in South Africa. A comparison is made between traditional forecasting approaches and neural networks; the traditional forecast method selected being the Autoregressive Integrated Moving Average (ARIMA model). The type of neural network implemented was the Long Short-Term Memory (LSTM) neural network. The basic theoretical concepts of ARIMA and LSTM neural networks are explained and subsequently, the patterns of the social unrest time series were analysed using time series exploratory techniques. The social unrest time series contained a significant number of irregular fluctuations with a non-linear trend. The structure of the social unrest time series suggested that traditional linear approaches would fail to model the non-linear behaviour of the time series. This thesis confirms this finding. Twelve experiments were conducted, and in these experiments, features, scaling procedures and model configurations are varied (i.e. univariate and multivariate models). Multivariate LSTM achieved the lowest forecast errors and performance improved as more explanatory features were introduced. The ARIMA model's performance deteriorated with added complexity and the univariate ARIMA produced lower forecast errors compared to the multivariate ARIMA. In conclusion, it can be claimed that multivariate LSTM neural networks are useful for predicting social unrest events.
27
Holm, Noah y Emil Plynning. "Spatio-temporal prediction of residential burglaries using convolutional LSTM neural networks". Thesis, KTH, Geoinformatik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-229952.
Texto completoResumen
The low amount solved residential burglary crimes calls for new and innovative methods in the prevention and investigation of the cases. There were 22 600 reported residential burglaries in Sweden 2017 but only four to five percent of these will ever be solved. There are many initiatives in both Sweden and abroad for decreasing the amount of occurring residential burglaries and one of the areas that are being tested is the use of prediction methods for more efficient preventive actions. This thesis is an investigation of a potential method of prediction by using neural networks to identify areas that have a higher risk of burglaries on a daily basis. The model use reported burglaries to learn patterns in both space and time. The rationale for the existence of patterns is based on near repeat theories in criminology which states that after a burglary both the burgled victim and an area around that victim has an increased risk of additional burglaries. The work has been conducted in cooperation with the Swedish Police authority. The machine learning is implemented with convolutional long short-term memory (LSTM) neural networks with max pooling in three dimensions that learn from ten years of residential burglary data (2007-2016) in a study area in Stockholm, Sweden. The model's accuracy is measured by performing predictions of burglaries during 2017 on a daily basis. It classifies cells in a 36x36 grid with 600 meter square grid cells as areas with elevated risk or not. By classifying 4% of all grid cells during the year as risk areas, 43% of all burglaries are correctly predicted. The performance of the model could potentially be improved by further configuration of the parameters of the neural network, along with a use of more data with factors that are correlated to burglaries, for instance weather. Consequently, further work in these areas could increase the accuracy. The conclusion is that neural networks or machine learning in general could be a powerful and innovative tool for the Swedish Police authority to predict and moreover prevent certain crime. This thesis serves as a first prototype of how such a system could be implemented and used.
28
Sarika, Pawan Kumar. "Comparing LSTM and GRU for Multiclass Sentiment Analysis of Movie Reviews". Thesis, Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-20213.
Texto completoResumen
Today, we are living in a data-driven world. Due to a surge in data generation, there is a need for efficient and accurate techniques to analyze data. One such kind of data which is needed to be analyzed are text reviews given for movies. Rather than classifying the reviews as positive or negative, we will classify the sentiment of the reviews on the scale of one to ten. In doing so, we will compare two recurrent neural network algorithms Long short term memory(LSTM) and Gated recurrent unit(GRU). The main objective of this study is to compare the accuracies of LSTM and GRU models. For training models, we collected data from two different sources. For filtering data, we used porter stemming and stop words. We coupled LSTM and GRU with the convolutional neural networks to increase the performance. After conducting experiments, we have observed that LSTM performed better in predicting border values. Whereas, GRU predicted every class equally. Overall GRU was able to predict multiclass text data of movie reviews slightly better than LSTM. GRU was computationally expansive when compared to LSTM.
29
Kindbom, Hannes. "LSTM vs Random Forest for Binary Classification of Insurance Related Text". Thesis, KTH, Matematisk statistik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-252748.
Texto completoResumen
The field of natural language processing has received increased attention lately, but less focus is put on comparing models, which differ in complexity. This thesis compares Random Forest to LSTM, for the task of classifying a message as question or non-question. The comparison was done by training and optimizing the models on historic chat data from the Swedish insurance company Hedvig. Different types of word embedding were also tested, such as Word2vec and Bag of Words. The results demonstrated that LSTM achieved slightly higher scores than Random Forest, in terms of F1 and accuracy. The models’ performance were not significantly improved after optimization and it was also dependent on which corpus the models were trained on. An investigation of how a chatbot would affect Hedvig’s adoption rate was also conducted, mainly by reviewing previous studies about chatbots’ effects on user experience. The potential effects on the innovation’s five attributes, relative advantage, compatibility, complexity, trialability and observability were analyzed to answer the problem statement. The results showed that the adoption rate of Hedvig could be positively affected, by improving the first two attributes. The effects a chatbot would have on complexity, trialability and observability were however suggested to be negligible, if not negative.Det vetenskapliga området språkteknologi har fått ökad uppmärksamhet den senaste tiden, men mindre fokus riktas på att jämföra modeller som skiljer sig i komplexitet. Den här kandidatuppsatsen jämför Random Forest med LSTM, genom att undersöka hur väl modellerna kan användas för att klassificera ett meddelande som fråga eller icke-fråga. Jämförelsen gjordes genom att träna och optimera modellerna på historisk chattdata från det svenska försäkringsbolaget Hedvig. Olika typer av word embedding, så som Word2vec och Bag of Words, testades också. Resultaten visade att LSTM uppnådde något högre F1 och accuracy än Random Forest. Modellernas prestanda förbättrades inte signifikant efter optimering och resultatet var också beroende av vilket korpus modellerna tränades på. En undersökning av hur en chattbot skulle påverka Hedvigs adoption rate genomfördes också, huvudsakligen genom att granska tidigare studier om chattbotars effekt på användarupplevelsen. De potentiella effekterna på en innovations fem attribut, relativ fördel, kompatibilitet, komplexitet, prövbarhet and observerbarhet analyserades för att kunna svara på frågeställningen. Resultaten visade att Hedvigs adoption rate kan påverkas positivt, genom att förbättra de två första attributen. Effekterna en chattbot skulle ha på komplexitet, prövbarhet och observerbarhet ansågs dock vara försumbar, om inte negativ.
30
Gessle, Gabriel y Simon Åkesson. "A comparative analysis of CNN and LSTM for music genre classification". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-260138.
Texto completoResumen
The music industry has seen a great influx of new channels to browse and distribute music. This does not come without drawbacks. As the data rapidly increases, manual curation becomes a much more difficult task. Audio files have a plethora of features that could be used to make parts of this process a lot easier. It is possible to extract these features, but the best way to handle these for different tasks is not always known. This thesis compares the two deep learning models, convolutional neural network (CNN) and long short-term memory (LSTM), for music genre classification when trained using mel-frequency cepstral coefficients (MFCCs) in hopes of making audio data as useful as possible for future usage. These models were tested on two different datasets, GTZAN and FMA, and the results show that the CNN had a 56.0% and 50.5% prediction accuracy, respectively. This outperformed the LSTM model that instead achieved a 42.0% and 33.5% prediction accuracy.Musikindustrin har sett en stor ökning i antalet sätt att hitta och distribuera musik. Det kommer däremot med sina nackdelar, då mängden data ökar fort så blir det svårare att hantera den på ett bra sätt. Ljudfiler har mängder av information man kan extrahera och därmed göra den här processen enklare. Det är möjligt att använda sig av de olika typer av information som finns i filen, men bästa sättet att hantera dessa är inte alltid känt. Den här rapporten jämför två olika djupinlärningsmetoder, convolutional neural network (CNN) och long short-term memory (LSTM), tränade med mel-frequency cepstral coefficients (MFCCs) för klassificering av musikgenre i hopp om att göra ljuddata lättare att hantera inför framtida användning. Modellerna testades på två olika dataset, GTZAN och FMA, där resultaten visade att CNN:et fick en träffsäkerhet på 56.0% och 50.5% tränat på respektive dataset. Denna utpresterade LSTM modellen som istället uppnådde en träffsäkerhet på 42.0% och 33.5%.
31
Vitali, Greta <1995>. "“Forecasting Stock Index Volatility: A comparison between GARCH and LSTM models”". Master's Degree Thesis, Università Ca' Foscari Venezia, 2019. http://hdl.handle.net/10579/15933.
Texto completoResumen
The financial world is characterized by the uncertainty of events and this phenomenon can expose operators to huge financial risks. Thus, there is a need to measure this uncertainty, with the aim to predict it and to make adequate plans of action. The concept of uncertainty is often associated with the definition of volatility, which is a measure of the variation of stock prices of a financial instrument during the time. But modelling volatility is not a trivial task, because of the essence of financial stock prices, which usually present volatility clusters, fat tails, nonnormality and structural breaks in the distribution. A popular class of models able to capture many of these stylized facts is the ARCH/GARCH family. As a matter of fact, a GARCH model is able to explain the time-varying variance and the presence of clusters in the series of the returns. Nevertheless, it requires some constraints on both parameters and distributions of returns to obtain satisfactory results. An attractive solution is given by some mathematical models based on artificial intelligence. Indeed, the artificial neural networks, resembling the human brain, are able to make predictions of future volatility due to their ability to be self-adaptive and to be a universal approximator of any underlying nonlinear function of financial data. The aim of this thesis is to make a comparison between the forecasting capabilities of a GARCH(1,1) model and a Long Short-Term Memory network. In particular, the objective is to predict the volatility of the Dow Jones Industrial Average Index, demonstrating the superiority of the neural network with respect to the well-established GARCH model.
32
Graffi, Giacomo. "A novel approach for Credit Scoring using Deep Neural Networks with bank transaction data". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Buscar texto completoResumen
With the PSD2 open banking revolution FinTechs obtained a key role in the financial industry. This role implies the inquiry and development of new techniques, products and solutions to compete with other players in this area.
The aim of this thesis is to investigate the applicability of the state-of-the-art Deep Learning techniques for Credit Risk Modeling. In order to accomplish it, a PSD2-related synthetic and anonymized dataset has been used to simulate an application process with only one account per user. Firstly, a machine-readable representation of the bank accounts has been created, starting from the raw transactions’ data and scaling the variables using the quantile function.
Afterwards, a Deep Neural Network has been created in order to capture the complex relations between the input variables and to extract information from the accounts’ representations. The proposed architecture accomplished the assigned tasks with a Gini index of 0.55, exploiting a Convolutional encoder to extract features from the inputs and a Recurrent decoder to analyze them.
33
Elmasdotter, Ajla y Carl Nyströmer. "A comparative study between LSTM and ARIMA for sales forecasting in retail". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-229747.
Texto completoResumen
Food waste is a major environmental issue. Expired products are thrown away, implying that too much food is ordered compared to what is sold and that a more accurate prediction model is required within grocery stores. In this study the two prediction models Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA) were compared on their prediction accuracy in two scenarios, given sales data for different products, to observe if LSTM is a model that can compete against the ARIMA model in the field of sales forecasting in retail. In the first scenario the models predict sales for one day ahead using given data, while they in the second scenario predict each day for a week ahead. Using the evaluation measures RMSE and MAE together with a t-test the results show that the difference between the LSTM and ARIMA model is not of statistical significance in the scenario of predicting one day ahead. However when predicting seven days ahead, the results show that there is a statistical significance in the difference indicating that the LSTM model has higher accuracy. This study therefore concludes that the LSTM model is promising in the field of sales forecasting in retail and able to compete against the ARIMA model.Matsvinn är ett stort problem för miljön. Utgångna produkter slängs, vilket implicerar att för mycket mat beställs jämfört med hur mycket butikerna säljer. En mer precis modell för att förutsäga försäljningssiffrorna kan minska matsvinnet. Denna studie jämför modellerna Long Short-Term Memory (LSTM) och Autoregressive Integrated Moving Average (ARIMA) i deras precision i två scenarion. Givet försäljningssiffror för olika matvaruprodukter, undersöks ifall LSTM är en modell som kan konkurrera mot ARIMA-modellen när modellerna ska förutsäga försäljningssiffror för matvaruprodukter. Det första scenariot var att förutse försäljningen en dag i framtiden baserat på given data, medan det andra scenariot var att förutse försäljningen varje dag under en vecka i framtiden baserat på given data. Genom att använda måtten RMSE och MAE tillsammans med ett T-Test visade resultaten av studien att skillnaden mellan LSTM- och ARIMA-modellen inte var av statistik signifikans i fallet då modellerna skulle förutsäga försäljningen en dag i framtiden. Däremot visar resultaten på att skillnaden mellan modellerna är av signifikans när modellerna skulle förutsäga försäljningen under en vecka, vilken implicerar att LSTM-modellen har en högre precision i detta scenario. Denna studie drar därmed slutsatsen att LSTM-modellen är lovande och kan konkurrera mot ARIMA-modellen när det kommer till försäljningssiffror av matvaruprodukter.
34
Farahani, Marzieh. "Anomaly Detection on Gas Turbine Time-series’ Data Using Deep LSTM-Autoencoder". Thesis, Umeå universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-179863.
Texto completoResumen
Anomaly detection with the aim of identifying outliers plays a very important role in various applications (e.g., online spam, manufacturing, finance etc.). An automatic and reliable anomaly detection tool with accurate prediction is essential in many domains. This thesis proposes an anomaly detection method by applying deep LSTM (long short-term memory) especially on time-series data. By validating on real-worlddata at Siemens Industrial Turbomachinery (SIT), the proposed methods hows promising performance, and can be employed in different data domains like device logs of turbine machines to provide useful information on abnormal behaviors. In detail, our proposed method applies an auto encoder to have feature selection by keeping vital features, and learn the time series’s encoded representation. This approach reduces the extensive input data by pulling out the auto encoder’s latent layer output. For prediction, we then train a deep LSTM model with three hidden layers based on the encoder’s latent layer output. Afterwards, given the output from the prediction model, we detect the anomaly sensors related to the specific gas turbine by using a threshold approach. Our experimental results show that our proposed methods perform well on noisy and real-world data set in order to detect anomalies. Moreover, it confirmed that making predictions based on encoding representation, which is under reduction, is more accurate. We could say applying autoencoder can improve both anomaly detection and prediction tasks. Additionally, the performance of deep neural networks would be significantly improved for data with high complexity.
35
Stark, Love. "Outlier detection with ensembled LSTM auto-encoders on PCA transformed financial data". Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-296161.
Texto completoResumen
Financial institutions today generate a large amount of data, data that can contain interesting information to investigate to further the economic growth of said institution. There exists an interest in analyzing these points of information, especially if they are anomalous from the normal day-to-day work. However, to find these outliers is not an easy task and not possible to do manually due to the massive amounts of data being generated daily. Previous work to solve this has explored the usage of machine learning to find outliers in these financial datasets. Previous studies have shown that the pre-processing of data usually stands for a big part in information loss. This work aims to study if there is a proper balance in how the pre-processing is carried out to retain the highest amount of information while simultaneously not letting the data remain too complex for the machine learning models. The dataset used consisted of Foreign exchange transactions supplied by the host company and was pre-processed through the use of Principal Component Analysis (PCA). The main purpose of this work is to test if an ensemble of Long Short-Term Memory Recurrent Neural Networks (LSTM), configured as autoencoders, can be used to detect outliers in the data and if the ensemble is more accurate than a single LSTM autoencoder. Previous studies have shown that Ensemble autoencoders can prove more accurate than a single autoencoder, especially when SkipCells have been implemented (a configuration that skips over LSTM cells to make the model perform with more variation). A datapoint will be considered an outlier if the LSTM model has trouble properly recreating it, i.e. a pattern that is hard to classify, making it available for further investigations done manually. The results show that the ensembled LSTM model proved to be more accurate than that of a single LSTM model in regards to reconstructing the dataset, and by our definition of an outlier, more accurate in outlier detection. The results from the pre-processing experiments reveal different methods of obtaining an optimal number of components for your data. One of those is by studying retained variance and accuracy of PCA transformation compared to model performance for a certain number of components. One of the conclusions from the work is that ensembled LSTM networks can prove very powerful, but that alternatives to pre-processing should be explored such as categorical embedding instead of PCA.Finansinstitut genererar idag en stor mängd data, data som kan innehålla intressant information värd att undersöka för att främja den ekonomiska tillväxten för nämnda institution. Det finns ett intresse för att analysera dessa informationspunkter, särskilt om de är avvikande från det normala dagliga arbetet. Att upptäcka dessa avvikelser är dock inte en lätt uppgift och ej möjligt att göra manuellt på grund av de stora mängderna data som genereras dagligen. Tidigare arbete för att lösa detta har undersökt användningen av maskininlärning för att upptäcka avvikelser i finansiell data. Tidigare studier har visat på att förbehandlingen av datan vanligtvis står för en stor del i förlust av emphinformation från datan. Detta arbete syftar till att studera om det finns en korrekt balans i hur förbehandlingen utförs för att behålla den högsta mängden information samtidigt som datan inte förblir för komplex för maskininlärnings-modellerna. Det emphdataset som användes bestod av valutatransaktioner som tillhandahölls av värdföretaget och förbehandlades genom användning av Principal Component Analysis (PCA). Huvudsyftet med detta arbete är att undersöka om en ensemble av Long Short-Term Memory Recurrent Neural Networks (LSTM), konfigurerad som autoenkodare, kan användas för att upptäcka avvikelser i data och om ensemblen är mer precis i sina predikteringar än en ensam LSTM-autoenkodare. Tidigare studier har visat att en ensembel avautoenkodare kan visa sig vara mer precisa än en singel autokodare, särskilt när SkipCells har implementerats (en konfiguration som hoppar över vissa av LSTM-cellerna för att göra modellerna mer varierade). En datapunkt kommer att betraktas som en avvikelse om LSTM-modellen har problem med att återskapa den väl, dvs ett mönster som nätverket har svårt att återskapa, vilket gör datapunkten tillgänglig för vidare undersökningar. Resultaten visar att en ensemble av LSTM-modeller predikterade mer precist än en singel LSTM-modell när det gäller att återskapa datasetet, och då enligt vår definition av avvikelser, mer precis avvikelse detektering. Resultaten från förbehandlingen visar olika metoder för att uppnå ett optimalt antal komponenter för dina data genom att studera bibehållen varians och precision för PCA-transformation jämfört med modellprestanda. En av slutsatserna från arbetet är att en ensembel av LSTM-nätverk kan visa sig vara mycket kraftfulla, men att alternativ till förbehandling bör undersökas, såsom categorical embedding istället för PCA.
36
Verner, Alexander. "LSTM Networks for Detection and Classification of Anomalies in Raw Sensor Data". Diss., NSUWorks, 2019. https://nsuworks.nova.edu/gscis_etd/1074.
Texto completoResumen
In order to ensure the validity of sensor data, it must be thoroughly analyzed for various types of anomalies. Traditional machine learning methods of anomaly detections in sensor data are based on domain-specific feature engineering. A typical approach is to use domain knowledge to analyze sensor data and manually create statistics-based features, which are then used to train the machine learning models to detect and classify the anomalies. Although this methodology is used in practice, it has a significant drawback due to the fact that feature extraction is usually labor intensive and requires considerable effort from domain experts.
An alternative approach is to use deep learning algorithms. Research has shown that modern deep neural networks are very effective in automated extraction of abstract features from raw data in classification tasks. Long short-term memory networks, or LSTMs in short, are a special kind of recurrent neural networks that are capable of learning long-term dependencies. These networks have proved to be especially effective in the classification of raw time-series data in various domains. This dissertation systematically investigates the effectiveness of the LSTM model for anomaly detection and classification in raw time-series sensor data.
As a proof of concept, this work used time-series data of sensors that measure blood glucose levels. A large number of time-series sequences was created based on a genuine medical diabetes dataset. Anomalous series were constructed by six methods that interspersed patterns of common anomaly types in the data. An LSTM network model was trained with k-fold cross-validation on both anomalous and valid series to classify raw time-series sequences into one of seven classes: non-anomalous, and classes corresponding to each of the six anomaly types.
As a control, the accuracy of detection and classification of the LSTM was compared to that of four traditional machine learning classifiers: support vector machines, Random Forests, naive Bayes, and shallow neural networks. The performance of all the classifiers was evaluated based on nine metrics: precision, recall, and the F1-score, each measured in micro, macro and weighted perspective.
While the traditional models were trained on vectors of features, derived from the raw data, that were based on knowledge of common sources of anomaly, the LSTM was trained on raw time-series data. Experimental results indicate that the performance of the LSTM was comparable to the best traditional classifiers by achieving 99% accuracy in all 9 metrics. The model requires no labor-intensive feature engineering, and the fine-tuning of its architecture and hyper-parameters can be made in a fully automated way. This study, therefore, finds LSTM networks an effective solution to anomaly detection and classification in sensor data.
37
Pavai, Arumugam Thendramil. "SENSOR-BASED HUMAN ACTIVITY RECOGNITION USING BIDIRECTIONAL LSTM FOR CLOSELY RELATED ACTIVITIES". CSUSB ScholarWorks, 2018. https://scholarworks.lib.csusb.edu/etd/776.
Texto completoResumen
Recognizing human activities using deep learning methods has significance in many fields such as sports, motion tracking, surveillance, healthcare and robotics. Inertial sensors comprising of accelerometers and gyroscopes are commonly used for sensor based HAR. In this study, a Bidirectional Long Short-Term Memory (BLSTM) approach is explored for human activity recognition and classification for closely related activities on a body worn inertial sensor data that is provided by the UTD-MHAD dataset. The BLSTM model of this study could achieve an overall accuracy of 98.05% for 15 different activities and 90.87% for 27 different activities performed by 8 persons with 4 trials per activity per person. A comparison of this BLSTM model is made with the Unidirectional LSTM model. It is observed that there is a significant improvement in the accuracy for recognition of all 27 activities in the case of BLSTM than LSTM.
38
Xiang, Wenliang. "Anomaly detection by prediction for health monitoring of satellites using LSTM neural networks". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24695/.
Texto completoResumen
Anomaly detection in satellite has not been well-documented due to the unavailability of satellite data, while it becomes more and more important with the increasing popularity of satellite applications. Our work focus on the anomaly detection by prediction on the dataset from the satellite, where we try and compare performance among recurrent neural network (RNN), Long Short-Term Memory (LSTM) and conventional neural network (NN). We conclude that LSTM with input length p=16, dimensionality n=32, output length q=2, 128 neurons and without maximum overlap is the best in terms of balanced accuracy. And LSTM with p=128, n=32, q=16, 128 and without maximum overlap outperforms most with respect to AUC metric. We also invent award function as a new performance metric trying to capture not only the correctness of decisions that NN made but also the amount of confidence in making its decisions, and we propose two candidates of award function. Regrettably, they partially meet our expectation as they possess a fatal defect which has been proved both from practical and theoretical viewpoints.
39
Silfver, Anton. "Short-Term Forecasting of Taxi Demand using a two Channelled Convolutional LSTM network". Thesis, Linköpings universitet, Artificiell intelligens och integrerade datorsystem, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-165743.
Texto completoResumen
In this thesis a model capable of predicting taxidemand with high accuracy across five different real world single company datasets is presented. The model uses historical drop off and arrival information to make accurate shortterm predictions about future taxi demand. The model is compared to and outperforms both LSTM and statistical baselines. This thesis uniquely uses a different tessellation strategy which makes the results directly applicable to smaller taxi companies. This paper shows that accurate short term predictions of taxi demand can be made using real world data available to taxi companies. MSE is also shown to be a more robust to uneven demand distributions across cities than MAE. Adding drop offs to the input had provided only marginal improvements in the performance of the model.
40
Mussumeci, Elisa. "A machine learning approach to dengue forecasting: comparing LSTM, Random Forest and Lasso". reponame:Repositório Institucional do FGV, 2018. http://hdl.handle.net/10438/24093.
Texto completoResumen
Submitted by Elisa Mussumeci (elisamussumeci@gmail.com) on 2018-05-29T18:53:58Z
No. of bitstreams: 1
machine-learning-aproach (4).pdf: 11272802 bytes, checksum: 52b25abf2711fdd6d1a338316c15c154 (MD5)Approved for entry into archive by ÁUREA CORRÊA DA FONSECA CORRÊA DA FONSECA (aurea.fonseca@fgv.br) on 2018-05-29T19:15:35Z (GMT) No. of bitstreams: 1 machine-learning-aproach (4).pdf: 11272802 bytes, checksum: 52b25abf2711fdd6d1a338316c15c154 (MD5)
Made available in DSpace on 2018-06-14T19:45:29Z (GMT). No. of bitstreams: 1 machine-learning-aproach (4).pdf: 11272802 bytes, checksum: 52b25abf2711fdd6d1a338316c15c154 (MD5) Previous issue date: 2018-04-12
We used the Infodengue database of incidence and weather time-series, to train predictive models for the weekly number of cases of dengue in 790 cities of Brazil. To overcome a limitation in the length of time-series available to train the model, we proposed using the time series of epidemiologically similar cities as predictors for the incidence of each city. As Machine Learning-based forecasting models have been used in recent years with reasonable success, in this work we compare three machine learning models: Random Forest, lasso and Long-short term memory neural network in their forecasting performance for all cities monitored by the Infodengue Project.
41
Kuo, Shih-Chun y 郭士鈞. "LSTM-Based Vehicle Trajectory Prediction". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/q7qwdc.
Texto completoResumen
碩士國立清華大學
通訊工程研究所
107
Future trajectory prediction of objects is a very important technical link for self-driving cars and navigation systems. In order to be safe, efficient, and to avoid collisions, self-driving cars should be able to anticipate what will happen in a changeable environment and predict the future location of surrounding objects in advance. There have been many significant technical advances in autonomous cars, such as Google’s self-driving cars and Tesla’s Autopilot. In the past research of object trajectory prediction, the interaction between objects was simulated by considering the object distances and learning functions using the Long Short-Term Memory model. However, the results of future predictions should not only depend on the distance of the surrounding objects but also related to their own inertial trajectories and the relative importance between target and other objects. The forecasting system should look at all past trajectories and establish an important relationship between the input trajectories and the prediction results. The forecasting system also needs to aware which surrounding objects is important to target, thereby improving the prediction performance. In addition, considering more object information, such as heading, how fast, and object class will improve the prediction results. In this paper, our main goal is to improve the effectiveness of object trajectory prediction in dashcam videos. First, a temporal attention model is built to focus on the motion characteristics of moving objects from past trajectories. Our approach is to calculate the importance relationship value between future position and all past trajectories. Furthermore, we build a spatial attention model to understand the relative importance relationship between itself and surrounding objects information, thereby reducing errors and error propagation of predicted results. Finally, combining the direction, speed information and object class of the input trajectory will provide more object information and reduce the misjudgment of prediction. We apply the experimental results to the Kitti tracking database of real driving dashcam videos and New York Grand Central of pedestrian trajectory prediction database. The results show that our method still has quite good results compared to the previous method.
42
XIAO, HUNG-JIE y 蕭宏杰. "LSTM-based Parking Space Detection". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/z88u44.
Texto completoResumen
碩士國立中正大學
電機工程研究所
107
In this research, we propose the LSTM-based parking lot detection method architecture. This framework divides to two parts, one is “Status ConvNet”, and another is “Action ConvNet”. Frist, we will separate individual frame from sequence of image to become the spatial stream. And then, we will calculate optical flow to be moving information to become the temporal stream. For spatial stream, we input an image to Convolutional Neural Network (CNN) to detect the status of parking space, called the network “Status ConvNet”. At the same time, input extracted high-level feature to LSTM that could consider the information of historical status to avoid wrong detection from single frame. The classes of space status are “Occupy” and “Vacant”. For temporal stream, we stack multiple images of optical flow, and input them to 3-dimension CNN to detection parking status of driver. The network is similar as Status ConvNet called “Action ConvNet”. Action ConvNet uses optical flow as short-term information to detect parking status of driver. In order to increase the accuracy, we also introduce LSTM in network to consider historical information of optical flow as long-term moving information. The classes of parking status are “Drop off”, “Pick up”, and “No action”. Finally, we design the two-stream architecture to fuse spatial and temporal information.
43
Mendes, João Filipe Batista. "Forecasting bitcoin prices: ARIMA vs LSTM". Master's thesis, 2019. http://hdl.handle.net/10071/19724.
Texto completoResumen
Bitcoin has recently received special attention in economics and finance as the most popular blockchain technology. This dissertation aims to discuss whether newly machine-leaning models perform better than traditional models in forecasting. Particularly, this study compares the accuracy of the prediction of bitcoin prices using two different models: Long-Short Term Memory (LSTM) versus Auto Regressive Integrated Moving Average (ARIMA), in terms of forecasting errors, and Python routines were used for such purpose. Bitcoin price time series ranges from 2017-06-18 to 2019-08-07, in a daily basis, sourced from the Federal Reserve Economic Data. To compare the results of both models, data was divided into two subsets: training (83.5%) and testing (16.5%). The literature usually indicates that LSTM outperforms ARIMA. In this dissertation, the results do confirm that LSTM forecasts of bitcoin prices improve on average ARIMA predictions by 92% and 94%, according to RMSE and MAE.A Bitcoin tem recebido recentemente especial atenção em áreas como a economia e finanças por ser a mais popular tecnologia de blockchain. Esta dissertação tem como objetivo verificar se os novos modelos de machine-learning apresentam melhores resultados que os modelos tradicionais em previsões. Este estudo compara, em particular, a precisão da previsão do preço da Bitcoin usando dois modelos diferentes: Long-Short Term Memory (LSTM) versus Auto Regressive Integrated Moving Average (ARIMA), em termos de erros de previsão e aplicando rotinas do Python. A análise teve como base os preços diários da Bitcoin entre 18 de junho de 2016 e 7 de agosto de 2019, retirados da base de dados da Reserva Federal. Para comparar os resultados dos dois modelos, os dados foram divididos em duas secções: o treino (83.5%) e o teste (16.5%). A literatura indica que o modelo LSTM tem uma melhor precisão que o ARIMA e nesta dissertação os resultados confirmam que o modelo LSTM melhora em média 92% e 94% a previsão do ARIMA, de acordo com o RMSE e o MAE.
44
Chen, Wei-Rui y 陳維睿. "Applying LSTM to Bitcoin price prediction". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/67y8s7.
Texto completoResumen
碩士國立政治大學
資訊科學系
106
This thesis focuses on applying Long Short-Term Memory (LSTM) technique to predict Bitcoin price direction. Features including internal and external features are extracted from Bitcoin blockchain and exchange center respectively. Cryptocurrency is a new type of currency that is traded over the infrastructure of Internet. Bitcoin (BTC) is the first cryptocurrency and ranks first in the market capitalization among all the other cryptocurrencies. Predicting Bitcoin price is a novel topic because of its differences with traditional financial assets and its volatility. As contributions, this thesis provides a guide of processing Bitcoin blockchain data and serves as an empirical study on applying LSTM to Bitcoin price prediction.
45
Fonseca, José Pedro Castro. "FPGA implementation of a LSTM Neural Network". Master's thesis, 2016. https://repositorio-aberto.up.pt/handle/10216/90359.
Texto completoResumen
Este trabalho pretende fazer uma implementação customizada, em Hardware, duma Rede Neuronal Long Short-Term Memory. O modelo python, assim como a descrição Verilog, e síntese RTL, encontram-se terminadas. Falta apenas fazer o benchmarking e a integração de um sistema de aprendizagem.
46
Yen-LiangLin y 林彥良. "PM 2.5 Prediction based on LSTM Model". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/8gayas.
Texto completoResumen
碩士國立成功大學
工程科學系
106
Recently, pollution conditions of particulate matter 2.5 in Taiwan have become more severe day by day. Several other cities in Asia such as Beijing and Delhi are also facing the same pollution problem, which draws attention to government and experts. Due to the human activities in Asia such as industrialization and animal husbandry, air pollution condition has been getting worse, increases the possibility of population suffering from cardiovascular disease. Particular matter pollution has become a problem we cannot ignore in modern society. Currently, official meteorological department applies traditional statistic model to predict meteorology trend. Traditional statistic model such like ARIMA has certain accuracy on time series data. However, nowadays along with the calculate ability of computer and chips progressing, application field of neural network and deep learning has become much more extensive. Recurrent neural network had been developed to deal with time sequence data. Long short term memory model has a longer time range memorize ability than recurrent neural network, meanwhile has been frequently applied on forecasting and analyzation. This thesis utilizes the long short term memory model to predict future particular matter hourly average concentration, in hope that government and the departments concerned could take actions on the pollution phenomenon, improve the air pollution problem.
47
Kuo, Chen-Yu y 郭鎮宇. "LSTM-Based Taiwan Stock Index Futures Prediction". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/xam4d3.
Texto completoResumen
碩士國立臺灣大學
經濟學研究所
107
This study uses the price data of Taiwan stock index futures and several common technical indicators to create RNN and LSTM model to predict futures’ price data. LSTM model is a RNN model for processing time series data. Due to its special structural design, LSTM models are more suitable for data with long time periods or long delays, and are mostly used in image recognition and speech recognition. The price data in the financial market also has similar characteristics. This study attempts to apply deep learning models on futures price market to predict future futures prices.
48
Fonseca, José Pedro Castro. "FPGA implementation of a LSTM Neural Network". Dissertação, 2016. https://repositorio-aberto.up.pt/handle/10216/90359.
Texto completoResumen
Este trabalho pretende fazer uma implementação customizada, em Hardware, duma Rede Neuronal Long Short-Term Memory. O modelo python, assim como a descrição Verilog, e síntese RTL, encontram-se terminadas. Falta apenas fazer o benchmarking e a integração de um sistema de aprendizagem.
49
Kau, Wei-Hao y 高偉豪. "Time series prediction using LSTM Network Models". Thesis, 2018. http://ndltd.ncl.edu.tw/handle/ey3638.
Texto completoResumen
碩士國立中山大學
應用數學系研究所
106
As recent computing hardware technology has undergone rapid and significant advances, complex methods that require a lot of computing power have been realized, which has led to the development of more machine learning methods and neural network models. This paper discusses the Long short-term memory (LSTM) network model of recurrent neural networks. The first part of this paper introduces the basic concept of LSTM and its training method. The second part discusses short- and long-term prediction, and compares their differences with the conventional time series model. The third part compares the prediction performance of the conventional time series model and LSTM by analysing simulated data. In the empirical study, a Long short-term memory network model is fitted for bicycle rental data in Kaohsiung, and predictive analysis is performed.
50
CHU, WEI-TAO y 朱韋濤. "Exchange Rate Prediction Using LSTM Neural Networks". Thesis, 2019. http://ndltd.ncl.edu.tw/handle/zwzv47.
Texto completoResumen
碩士國立勤益科技大學
資訊工程系
107
Foreign exchange market is not only a global place that doing foreign trade, but also the best flowing market in the world. Foreign exchange prediction or accuracy of future exchange trend are very important for future investments. Foreign exchange trend of each country has been deeply learned and used in the thesis. Most signals in our lives are belong to unstable signals. However, financial’s timeline is different from normal. Nonlinear model is a prediction method for this time. Recurrent Neural Network (RNN) can depict dynamic time results, so exchange rate prediction uses it to handle sequence-changing data. When the amount of computation is large in a feedforward network or a cyclic network, the neural network will face the long term dependent problem. In order to improve traditional long term dependent question of RNN, the solution is using LSTM to improve prediction accuracy by backpropagation over time.