Segui questo link per vedere altri tipi di pubblicazioni sul tema: Robust Long-Short Term Memory (RoLSTM).
Articoli di riviste sul tema "Robust Long-Short Term Memory (RoLSTM)"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Vedi i top-50 articoli di riviste per l'attività di ricerca sul tema "Robust Long-Short Term Memory (RoLSTM)".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Vedi gli articoli di riviste di molte aree scientifiche e compila una bibliografia corretta.
1
Javid, Gelareh, Djaffar Ould Abdeslam e Michel Basset. "Adaptive Online State of Charge Estimation of EVs Lithium-Ion Batteries with Deep Recurrent Neural Networks". Energies 14, n. 3 (1 febbraio 2021): 758. http://dx.doi.org/10.3390/en14030758.
Testo completoAbstract (sommario):
The State of Charge (SOC) estimation is a significant issue for safe performance and the lifespan of Lithium-ion (Li-ion) batteries. In this paper, a Robust Adaptive Online Long Short-Term Memory (RoLSTM) method is proposed to extract SOC estimation for Li-ion Batteries in Electric Vehicles (EVs). This real-time, as its name suggests, method is based on a Recurrent Neural Network (RNN) containing Long Short-Term Memory (LSTM) units and using the Robust and Adaptive online gradient learning method (RoAdam) for optimization. In the proposed architecture, one sequential model is defined for each of the three inputs: voltage, current, and temperature of the battery. Therefore, the three networks work in parallel. With this approach, the number of LSTM units are reduced. Using this suggested method, one is not dependent on precise battery models and can avoid complicated mathematical methods. In addition, unlike the traditional recursive neural network where content is re-written at any time, the LSTM network can decide on preserving the current memory through the proposed gateways. In that case, it can easily transfer this information over long paths to receive and maintain long-term dependencies. Using real databases, the experiment results illustrate the better performance of RoLSTM applied to SOC estimation of Li-Ion batteries in comparison with a neural network modeling and unscented Kalman filter method that have been used thus far.
2
Fister, Dušan, Matjaž Perc e Timotej Jagrič. "Two robust long short-term memory frameworks for trading stocks". Applied Intelligence 51, n. 10 (27 febbraio 2021): 7177–95. http://dx.doi.org/10.1007/s10489-021-02249-x.
Testo completo
3
Liu, Yong, Xin Hao, Biling Zhang e Yuyan Zhang. "Simplified long short-term memory model for robust and fast prediction". Pattern Recognition Letters 136 (agosto 2020): 81–86. http://dx.doi.org/10.1016/j.patrec.2020.05.033.
Testo completo
4
Yang, Haimin, Zhisong Pan e Qing Tao. "Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory". Computational Intelligence and Neuroscience 2017 (2017): 1–9. http://dx.doi.org/10.1155/2017/9478952.
Testo completoAbstract (sommario):
Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam), for long short-term memory (LSTM) to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM.
5
Son, Namrye, Seunghak Yang e Jeongseung Na. "Hybrid Forecasting Model for Short-Term Wind Power Prediction Using Modified Long Short-Term Memory". Energies 12, n. 20 (15 ottobre 2019): 3901. http://dx.doi.org/10.3390/en12203901.
Testo completoAbstract (sommario):
Renewable energy has recently gained considerable attention. In particular, the interest in wind energy is rapidly growing globally. However, the characteristics of instability and volatility in wind energy systems also affect power systems significantly. To address these issues, many studies have been carried out to predict wind speed and power. Methods of predicting wind energy are divided into four categories: physical methods, statistical methods, artificial intelligence methods, and hybrid methods. In this study, we proposed a hybrid model using modified LSTM (Long short-term Memory) to predict short-term wind power. The data adopted by modified LSTM use the current observation data (wind power, wind direction, and wind speed) rather than previous data, which are prediction factors of wind power. The performance of modified LSTM was compared among four multivariate models, which are derived from combining the current observation data. Among multivariable models, the proposed hybrid method showed good performance in the initial stage with Model 1 (wind power) and excellent performance in the middle to late stages with Model 3 (wind power, wind speed) in the estimation of short-term wind power. The experiment results showed that the proposed model is more robust and accurate in forecasting short-term wind power than the other models.
6
Ngoc-Lan Huynh, Anh, Ravinesh C. Deo, Mumtaz Ali, Shahab Abdulla e Nawin Raj. "Novel short-term solar radiation hybrid model: Long short-term memory network integrated with robust local mean decomposition". Applied Energy 298 (settembre 2021): 117193. http://dx.doi.org/10.1016/j.apenergy.2021.117193.
Testo completo
7
Darling, Stephen, Richard J. Allen e Jelena Havelka. "Visuospatial Bootstrapping". Current Directions in Psychological Science 26, n. 1 (febbraio 2017): 3–9. http://dx.doi.org/10.1177/0963721416665342.
Testo completoAbstract (sommario):
Visuospatial bootstrapping is the name given to a phenomenon whereby performance on visually presented verbal serial-recall tasks is better when stimuli are presented in a spatial array rather than a single location. However, the display used has to be a familiar one. This phenomenon implies communication between cognitive systems involved in storing short-term memory for verbal and visual information, alongside connections to and from knowledge held in long-term memory. Bootstrapping is a robust, replicable phenomenon that should be incorporated in theories of working memory and its interaction with long-term memory. This article provides an overview of bootstrapping, contextualizes it within research on links between long-term knowledge and short-term memory, and addresses how it can help inform current working memory theory.
8
Avci, Gunes, Steven P. Woods, Marizela Verduzco, David P. Sheppard, James F. Sumowski, Nancy D. Chiaravalloti e John DeLuca. "Effect of Retrieval Practice on Short-Term and Long-Term Retention in HIV+ Individuals". Journal of the International Neuropsychological Society 23, n. 3 (9 gennaio 2017): 214–22. http://dx.doi.org/10.1017/s1355617716001089.
Testo completoAbstract (sommario):
AbstractObjectives: Episodic memory deficits are both common and impactful among persons infected with HIV; however, we know little about how to improve such deficits in the laboratory or in real life. Retrieval practice, by which retrieval of newly learned material improves subsequent recall more than simple restudy, is a robust memory boosting strategy that is effective in both healthy and clinical populations. In this study, we investigated the benefits of retrieval practice in 52 people living with HIV and 21 seronegatives. Methods: In a within-subjects design, all participants studied 48 verbal paired associates in 3 learning conditions: Massed-Restudy, Spaced-Restudy, and Spaced-Testing. Retention of verbal paired associates was assessed after short- (30 min) and long- (30 days) delay intervals. Results: After a short delay, both HIV+ persons and seronegatives benefited from retrieval practice more so than massed and spaced restudy. The same pattern of results was observed specifically for HIV+ persons with clinical levels of memory impairment. The long-term retention interval data evidenced a floor effect that precluded further analysis. Conclusions: This study provides evidence that retrieval practice improves verbal episodic memory more than some other mnemonic strategies among HIV+ persons. (JINS, 2017, 23, 214–222)
9
Bukhari, Syed Basit Ali, Khawaja Khalid Mehmood, Abdul Wadood e Herie Park. "Intelligent Islanding Detection of Microgrids Using Long Short-Term Memory Networks". Energies 14, n. 18 (13 settembre 2021): 5762. http://dx.doi.org/10.3390/en14185762.
Testo completoAbstract (sommario):
This paper presents a new intelligent islanding detection scheme (IIDS) based on empirical wavelet transform (EWT) and long short-term memory (LSTM) network to identify islanding events in microgrids. The concept of EWT is extended to extract features from three-phase signals. First, the three-phase voltage signals sampled at the terminal of targeted distributed energy resource (DER) or point of common coupling (PCC) are decomposed into empirical modes/frequency subbands using EWT. Then, instantaneous amplitudes and instantaneous frequencies of the three-phases at different frequency subbands are combined, and various statistical features are calculated. Finally, the EWT-based features along with the three-phase voltage signals are input to the LSTM network to differentiate between non-islanding and islanding events. To assess the efficacy of the proposed IIDS, extensive simulations are performed on an IEC microgrid and an IEEE 34-node system. The simulation results verify the effectiveness of the proposed IIDS in terms of non-detection zone (NDZ), computational time, detection accuracy, and robustness against noisy measurement. Furthermore, comparisons with existing intelligent methods and different LSTM architectures demonstrate that the proposed IIDS offers higher reliability by significantly reducing the NDZ and stands robust against measurements uncertainty.
10
Baddar, Wissam J., e Yong Man Ro. "Encoding features robust to unseen modes of variation with attentive long short-term memory". Pattern Recognition 100 (aprile 2020): 107159. http://dx.doi.org/10.1016/j.patcog.2019.107159.
Testo completo
11
Lee, Byung-Jun, e Kee-Eung Kim. "Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking". Dialogue & Discourse 7, n. 3 (15 aprile 2016): 47–64. http://dx.doi.org/10.5087/dad.2016.302.
Testo completoAbstract (sommario):
One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges.
12
Zhou, Zhiyu, Ruoxi Zhang e Zefei Zhu. "Robust Kalman filtering with long short-term memory for image-based visual servo control". Multimedia Tools and Applications 78, n. 18 (10 giugno 2019): 26341–71. http://dx.doi.org/10.1007/s11042-019-07773-0.
Testo completo
13
Lees, Thomas, Steven Reece, Frederik Kratzert, Daniel Klotz, Martin Gauch, Jens De Bruijn, Reetik Kumar Sahu, Peter Greve, Louise Slater e Simon J. Dadson. "Hydrological concept formation inside long short-term memory (LSTM) networks". Hydrology and Earth System Sciences 26, n. 12 (20 giugno 2022): 3079–101. http://dx.doi.org/10.5194/hess-26-3079-2022.
Testo completoAbstract (sommario):
Abstract. Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains: what have these models learned? Is it possible to extract information about the learned relationships that map inputs to outputs, and do these mappings represent known hydrological concepts? Small-scale experiments have demonstrated that the internal states of long short-term memory networks (LSTMs), a particular neural network architecture predisposed to hydrological modelling, can be interpreted. By extracting the tensors which represent the learned translation from inputs (precipitation, temperature, and potential evapotranspiration) to outputs (discharge), this research seeks to understand what information the LSTM captures about the hydrological system. We assess the hypothesis that the LSTM replicates real-world processes and that we can extract information about these processes from the internal states of the LSTM. We examine the cell-state vector, which represents the memory of the LSTM, and explore the ways in which the LSTM learns to reproduce stores of water, such as soil moisture and snow cover. We use a simple regression approach to map the LSTM state vector to our target stores (soil moisture and snow). Good correlations (R2>0.8) between the probe outputs and the target variables of interest provide evidence that the LSTM contains information that reflects known hydrological processes comparable with the concept of variable-capacity soil moisture stores. The implications of this study are threefold: (1) LSTMs reproduce known hydrological processes. (2) While conceptual models have theoretical assumptions embedded in the model a priori, the LSTM derives these from the data. These learned representations are interpretable by scientists. (3) LSTMs can be used to gain an estimate of intermediate stores of water such as soil moisture. While machine learning interpretability is still a nascent field and our approach reflects a simple technique for exploring what the model has learned, the results are robust to different initial conditions and to a variety of benchmarking experiments. We therefore argue that deep learning approaches can be used to advance our scientific goals as well as our predictive goals.
14
Haynes, James T., Emily Frith, Eveleen Sng e Paul D. Loprinzi. "Experimental Effects of Acute Exercise on Episodic Memory Function: Considerations for the Timing of Exercise". Psychological Reports 122, n. 5 (5 luglio 2018): 1744–54. http://dx.doi.org/10.1177/0033294118786688.
Testo completoAbstract (sommario):
Our previous work employing a between-subject randomized controlled trial design suggests that exercising prior to memory encoding is more advantageous in enhancing retrospective episodic memory function when compared to exercise occurring during or after memory encoding. The present experiment evaluates this potential temporal effect of acute exercise on memory function while employing a within-subject, counterbalanced design. In a counterbalanced order (via Latin squares), 24 participants completed four visits including (1) exercising (moderate-intensity walking) prior to memory encoding, (2) exercising during memory encoding, (3) exercising after memory encoding, and (4) a control visit (no exercise). Retrospective memory function (short term and long term; 24-hour follow-up) was assessed from a multitrial word list. Prospective memory was assessed from a time-based task. Compared to all other visits, short-term memory was greater in the visit that involved exercising prior to memory encoding (F = 3.76; P = .01; η2 = .79). Similar results occurred for long-term memory, with no significant effects for prospective memory performance. We provide robust evidence demonstrating that acute moderate-intensity exercise prior to memory encoding is optimal in enhancing short-term and long-term memory function when compared to no exercise as well as exercising during and after memory encoding.
15
Deng, Lu. "Short-Term Noise and the Robustness of Two Log-Periodogram Estimators in Long Memory Series". Applied Mechanics and Materials 313-314 (marzo 2013): 1235–38. http://dx.doi.org/10.4028/www.scientific.net/amm.313-314.1235.
Testo completoAbstract (sommario):
This paper focuses on the robustness of estimates and its mechanism with presence of short-term noise. Simulation results show that although AG estimator derives lower bias and better robustness than the GPH in most situations, the modification effects are evident only when the short noise has small negative roots. The problem of over-modification on larger negative roots and the under-modification on the positive roots are still lack of advanced study. The standard deviation it is not sensitive to short-term noise but the mean square errors increase sharply with short-term noise. Besides, the power and practical size of the test was affected too. Larger sample size is suggested to gain more robust finite sample properties.
16
Tan, Truong-Ngoc, Ali Khenchaf, Fabrice Comblet, Pierre Franck, Jean-Marc Champeyroux e Olivier Reichert. "Robust-Extended Kalman Filter and Long Short-Term Memory Combination to Enhance the Quality of Single Point Positioning". Applied Sciences 10, n. 12 (24 giugno 2020): 4335. http://dx.doi.org/10.3390/app10124335.
Testo completoAbstract (sommario):
In the recent years, multi-constellation and multi-frequency have improved the positioning precision in GNSS applications and significantly expanded the range of applications to new areas and services. However, the use of multiple signals presents advantages as well as disadvantages, since they may contain poor quality signals that negatively impact the position precision. The objective of this study is to improve the Single Point Positioning (SPP) accuracy using multi-GNSS data fusion. We propose the use of robust-Extended Kalman Filter (referred to as robust-EKF hereafter) to eliminate outliers. The robust-EKF used in the present work combines the Extended Kalman Filter with the Iterative ReWeighted Least Squares (IRWLS) and the Receiver Autonomous Integrity Monitoring (RAIM). The weight matrix in IRWLS is defined by the MM Estimation method which is a robust statistics approach for more efficient statistical data analysis with high breaking point. The RAIM algorithm is used to check the accuracy of the protection zone of the user. We apply the robust-EKF method along with the robust combination of GPS, Galileo and GLONASS data from ABMF base station, which significantly improves the position accuracy by about 84% compared to the non-robust data combination. ABMF station is a GNSS reception station managed by Météo-France in Guadeloupe. Thereafter, ABMF will refer to the acronym used to designate this station. Although robust-EKF demonstrates improvement in the position accuracy, its outputs might contain errors that are difficult to estimate. Therefore, an algorithm that can predetermine the error produced by robust-EKF is needed. For this purpose, the long short-term memory (LSTM) method is proposed as an adapted Deep Learning-Based approach. In this paper, LSTM is considered as a de-noising filter and the new method is proposed as a hybrid combination of robust-EKF and LSTM which is denoted rEKF-LSTM. The position precision greatly improves by about 95% compared to the non-robust combination of data from ABMF base station. In order to assess the rEKF-LSTM method, data from other base stations are tested. The position precision is enhanced by about 87%, 77% and 93% using the rEKF-LSTM compared to the non-robust combination of data from three other base stations AJAC, GRAC and LMMF in France, respectively.
17
Chherawala, Youssouf, Partha Pratim Roy e Mohamed Cheriet. "Combination of context-dependent bidirectional long short-term memory classifiers for robust offline handwriting recognition". Pattern Recognition Letters 90 (aprile 2017): 58–64. http://dx.doi.org/10.1016/j.patrec.2017.03.012.
Testo completo
18
Wöllmer, Martin, Felix Weninger, Jürgen Geiger, Björn Schuller e Gerhard Rigoll. "Noise robust ASR in reverberated multisource environments applying convolutive NMF and Long Short-Term Memory". Computer Speech & Language 27, n. 3 (maggio 2013): 780–97. http://dx.doi.org/10.1016/j.csl.2012.05.002.
Testo completo
19
Jadid Abdulkadir, Said, Hitham Alhussian, Muhammad Nazmi e Asim A Elsheikh. "Long Short Term Memory Recurrent Network for Standard and Poor’s 500 Index Modelling". International Journal of Engineering & Technology 7, n. 4.15 (7 ottobre 2018): 25. http://dx.doi.org/10.14419/ijet.v7i4.15.21365.
Testo completoAbstract (sommario):
Forecasting time-series data are imperative especially when planning is required through modelling using uncertain knowledge of future events. Recurrent neural network models have been applied in the industry and outperform standard artificial neural networks in forecasting, but fail in long term time-series forecasting due to the vanishing gradient problem. This study offers a robust solution that can be implemented for long-term forecasting using a special architecture of recurrent neural network known as Long Short Term Memory (LSTM) model to overcome the vanishing gradient problem. LSTM is specially designed to avoid the long-term dependency problem as their default behavior. Empirical analysis is performed using quantitative forecasting metrics and comparative model performance on the forecasted outputs. An evaluation analysis is performed to validate that the LSTM model provides better forecasted outputs on Standard & Poor’s 500 Index (S&P 500) in terms of error metrics as compared to other forecasting models.
20
Bing, Qichun, Fuxin Shen, Xiufeng Chen, Weijian Zhang, Yanran Hu e Dayi Qu. "A Hybrid Short-Term Traffic Flow Multistep Prediction Method Based on Variational Mode Decomposition and Long Short-Term Memory Model". Discrete Dynamics in Nature and Society 2021 (12 ottobre 2021): 1–13. http://dx.doi.org/10.1155/2021/4097149.
Testo completoAbstract (sommario):
Timely and accurate traffic prediction information is essential for advanced traffic management system (ATMS) and advanced traveler information system (ATIS). Because of the characteristics of nonlinearity, nonstationarity, and randomness, short-term traffic flow prediction could be still a challenging task. In this study, a hybrid short-term traffic flow multistep prediction method is proposed by combining the variational mode decomposition (VMD) algorithm and long short-term memory (LSTM) model. Firstly, the VMD algorithm is employed to decompose the original traffic flow data into a series of intrinsic mode function (IMF) components. Secondly, different LSTM models are established to predict different IMF components. For each prediction model, one-step to three-step predictions are carried out. Finally, the component prediction results are aggregated to obtain the final traffic flow multistep prediction values. The prediction performance of the proposed hybrid model is investigated using inductive loop data measured from the north-south viaduct expressway in Shanghai. The experiment results show that (1) VMD algorithm could effectively avoid the problems of endpoint effects and modal aliasing, and the decomposition effect is better than empirical mode decomposition algorithm and wavelet decomposition algorithm; (2) among all the involved methods, the proposed hybrid model is more effective and robust in extracting the trend information, which has the best multistep prediction performance.
21
Valada, Abhinav, e Wolfram Burgard. "Deep spatiotemporal models for robust proprioceptive terrain classification". International Journal of Robotics Research 36, n. 13-14 (31 agosto 2017): 1521–39. http://dx.doi.org/10.1177/0278364917727062.
Testo completoAbstract (sommario):
Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep long-short term memory based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new convolution neural network architecture that learns deep spatial features, complemented with long-short term memory units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high-ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.
22
Wu, Jianqing, Qiang Wu, Jun Shen e Chen Cai. "Towards Attention-Based Convolutional Long Short-Term Memory for Travel Time Prediction of Bus Journeys". Sensors 20, n. 12 (12 giugno 2020): 3354. http://dx.doi.org/10.3390/s20123354.
Testo completoAbstract (sommario):
Travel time prediction is critical for advanced traveler information systems (ATISs), which provides valuable information for enhancing the efficiency and effectiveness of the urban transportation systems. However, in the area of bus trips, existing studies have focused on directly using the structured data to predict travel time for a single bus trip. For state-of-the-art public transportation information systems, a bus journey generally has multiple bus trips. Additionally, due to the lack of study on data fusion, it is even inadequate for the development of underlying intelligent transportation systems. In this paper, we propose a novel framework for a hybrid data-driven travel time prediction model for bus journeys based on open data. We explore a convolutional long short-term memory (ConvLSTM) model with a self-attention mechanism that accurately predicts the running time of each segment of the trips and the waiting time at each station. The model is more robust to capture long-range dependence in time series data as well.
23
Deva Hema, D., J. Tharun, G. Arun Dev e N. Sateesh. "A Robust False Spam Review Detection Using Deep Long Short-Term Memory (LSTM) Based Recurrent Neural Network". Journal of Computational and Theoretical Nanoscience 17, n. 8 (1 agosto 2020): 3421–26. http://dx.doi.org/10.1166/jctn.2020.9198.
Testo completoAbstract (sommario):
Our day-to-day activity is highly influenced by development of Internet. One of the rapid growing area in Internet is E-commerce. People are eager to buy products from online sites like Amazon, embay, Flipkart etc. Customers can write reviews about the products purchased online. The purchasing of good through online has been increasing exponentially since last few years. As there is no physical contact with goods before purchasing through online, people totally rely on reviews about the product before purchasing it. Hence review plays an important role in deciding the quality of the product. There are many customers who give online reviews about the product after using it. Hence the quality of the product is decided by the reviews of the customers. Thus, detection of fake reviews has become one of the important task. The proposed system will help in finding such fake reviews about the product, so that the fake reviews can be eliminated. Therefore, the purchasing of the products will be totally based on the genuine reviews. The proposed system uses Deep Recurrent Neural Network (DRNN) to predict the fake reviews and the performance of the proposed method has compared with Naïve Bayes Algorithm. The proposed model shows good accuracy and can handle huge amount of data over the existing system.
24
Hattinger, E., S. Scheiblhofer, E. Roesler, T. Thalhamer, J. Thalhamer e R. Weiss. "Prophylactic mRNA Vaccination against Allergy Confers Long-Term Memory Responses and Persistent Protection in Mice". Journal of Immunology Research 2015 (2015): 1–12. http://dx.doi.org/10.1155/2015/797421.
Testo completoAbstract (sommario):
Recently, mRNA vaccines have been introduced as a safety-optimized alternative to plasmid DNA-based vaccines for protection against allergy. However, it remained unclear whether the short persistence of this vaccine type would limit memory responses and whether the protective immune response type would be maintained during recurrent exposure to allergen. We tested the duration of protective memory responses in mice vaccinated with mRNA encoding the grass pollen allergen Phl p 5 by challenging them with recombinant allergen, 3.5, 6, and 9 months after vaccination. In a second experiment, vaccinated mice were repeatedly challenged monthly with aerosolized allergen over a period of 7 months. Antibody and cytokine responses as well as lung inflammation and airway hyperresponsiveness were assessed. mRNA vaccination induced robust TH1 memory responses for at least 9 months. Vaccination efficiently suppressed TH2 cytokines, IgE responses, and lung eosinophilia. Protection was maintained after repeated exposure to aerosolized allergen and no TH1 associated pathology was observed. Lung function remained improved compared to nonvaccinated controls. Our data clearly indicate that mRNA vaccination against Phl p 5 induces robust, long-lived memory responses, which can be recalled by allergen exposure without side effects. mRNA vaccines fulfill the requirements for safe prophylactic vaccination without the need for booster immunizations.
25
Shen, Jing, Chao Tao, Ji Qi e Hao Wang. "Semi-Supervised Convolutional Long Short-Term Memory Neural Networks for Time Series Land Cover Classification". Remote Sensing 13, n. 17 (3 settembre 2021): 3504. http://dx.doi.org/10.3390/rs13173504.
Testo completoAbstract (sommario):
Time series images with temporal features are beneficial to improve the classification accuracy. For abstract temporal and spatial contextual information, deep neural networks have become an effective method. However, there is usually a lack of sufficient samples in network training: one is the loss of images or the discontinuous distribution of time series data because of the inevitable cloud cover, and the other is the lack of known labeled data. In this paper, we proposed a Semi-supervised convolutional Long Short-Term Memory neural network (SemiLSTM) for time series remote sensing images, which was validated on three data sets with different time distributions. It achieves an accurate and automated land cover classification via a small number of labeled samples and a large number of unlabeled samples. Besides, it is a robust classification algorithm for time series optical images with cloud coverage, which reduces the requirements for cloudless remote sensing images and can be widely used in areas that are often obscured by clouds, such as subtropical areas. In conclusion, this method makes full advantage of spectral-spatial-temporal characteristics under the condition of limited training samples, especially expanding time context information to enhance classification accuracy.
26
Loprinzi, Paul D., Sierra Day, Rebecca Hendry, Sara Hoffman, Alexis Love, Sarah Marable, Elizabeth McKee, Sydney Stec, Hanna Watson e Brittney Gilliland. "The effects of acute exercise on short- and long-term memory: Considerations for the timing of exercise and phases of memory". Europe’s Journal of Psychology 17, n. 1 (26 febbraio 2021): 85–103. http://dx.doi.org/10.5964/ejop.2955.
Testo completoAbstract (sommario):
The specific questions addressed from this research include: (1) Does high-intensity acute exercise improve memory?, (2) If so, do the mechanisms occur via encoding, consolidation, or retrieval? and (3) If acute exercise occurs in multiple phases of memory (e.g., before encoding and during consolidation), does this have an additive effect on memory? Three experimental, within-subject, counterbalanced studies were conducted among young adults. High-intensity exercise involved a 20-minutes bout of exercise at 75% of heart rate reserve. Memory was evaluated from a word-list task, including multiple evaluations out to 24-hours post-encoding. The timing of the exercise and memory assessments were carefully positioned to evaluate whether any improvements in memory were driven by mechanisms related to encoding, consolidation, and/or retrieval. We demonstrated that high-intensity acute exercise enhanced memory. This effect was robust (repeatable) and occurred through encoding, consolidation and retrieval-based mechanisms. Further, incorporating acute exercise into multiple phases of memory additively enhanced memory function.
27
Betsch, Tilmann, Nancy Quittenbaum e Manfred Lüders. "On the Robustness of the Quizzing Effect under Real Teaching Conditions". Zeitschrift für Pädagogische Psychologie 29, n. 2 (18 maggio 2015): 109–14. http://dx.doi.org/10.1024/1010-0652/a000149.
Testo completoAbstract (sommario):
Lab experiments and field studies showed that studying improves short-term memory, whereas active retrieval improves long-term memory – a phenomenon known as the quizzing (or testing) effect. In a quasi-experimental field study with four elementary school classes (18 < n < 22) and a pretest – posttest (5 min after the intervention) – posttest (6 weeks later) design, we tested the robustness of the quizzing effect under real conditions involving verbal teacher-student interactions in geometry lessons on symmetry in elementary schoolers. Results showed that re-studying compared to active retrieval (quizzing) enhanced learning more when measured directly after the lessons. This pattern revered when knowledge was measured six weeks later, demonstrating that the quizzing effect was robust. Moreover, long-term memory generally increased after six weeks. Limitations of the quasi-experimental approach are discussed.
28
Lee, Jungshin, e Hyochoong Bang. "A Robust Terrain Aided Navigation Using the Rao-Blackwellized Particle Filter Trained by Long Short-Term Memory Networks". Sensors 18, n. 9 (31 agosto 2018): 2886. http://dx.doi.org/10.3390/s18092886.
Testo completoAbstract (sommario):
Terrain-aided navigation (TAN) is a technology that estimates the position of the vehicle by comparing the altitude measured by an altimeter and height from the digital elevation model (DEM). The particle filter (PF)-based TAN has been commonly used to obtain stable real-time navigation solutions in cases where the unmanned aerial vehicle (UAV) operates at a high altitude. Even though TAN performs well on rough and unique terrains, its performance degrades in flat and repetitive terrains. In particular, in the case of PF-based TAN, there has been no verified technique for deciding its terrain validity. Therefore, this study designed a Rao-Blackwellized PF (RBPF)-based TAN, used long short-term memory (LSTM) networks to endure flat and repetitive terrains, and trained the noise covariances and measurement model of RBPF. LSTM is a modified recurrent neural network (RNN), which is an artificial neural network that recognizes patterns from time series data. Using this, this study tuned the noise covariances and measurement model of RBPF to minimize the navigation errors in various flight trajectories. This paper designed a TAN algorithm based on combining RBPF and LSTM and confirmed that it can enable a more precise navigation performance than conventional RBPF based TAN through simulations.
29
Jing, S., e T. Chao. "TIME SERIES LAND COVER CLASSIFICATION BASED ON SEMI-SUPERVISED CONVOLUTIONAL LONG SHORT-TERM MEMORY NEURAL NETWORKS". ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2020 (14 agosto 2020): 1521–28. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2020-1521-2020.
Testo completoAbstract (sommario):
Abstract. Time series imagery containing high-dimensional temporal features are conducive to improving classification accuracy. With the plenty accumulation of historical images, the inclusion of time series data becomes available to utilize, but it is difficult to avoid missing values caused by cloud cover. Meanwhile, seeking a large amount of training labels for long time series also makes data collection troublesome. In this study, we proposed a semi-supervised convolutional long short-term memory neural network (Semi-LSTM) in long time series which achieves an accurate and automated land cover classification with a small proportion of labels. Three main contributions of this work are summarized as follows: i) the proposed method achieve an excellent classification via a small group of labels in long time series data, and reducing dependence of training labels; ii) it is a robust algorithm in accuracy for the influence of noise, and reduces the requirements of sequential data for cloudless and lossless images; and iii) it makes full advantage of spectral-spatial-temporal features, especially expanding time context information to enhance classification accuracy. Finally, the proposed network is validated on time series imagery from Landsat 8. All quantitative analyses and evaluation indicators of the experimental results demonstrate competitive performance in the suggested modes.
30
Aldhyani, Theyazn H. H., e Hasan Alkahtani. "A Bidirectional Long Short-Term Memory Model Algorithm for Predicting COVID-19 in Gulf Countries". Life 11, n. 11 (21 ottobre 2021): 1118. http://dx.doi.org/10.3390/life11111118.
Testo completoAbstract (sommario):
Accurate prediction models have become the first goal for aiding pandemic-related decisions. Modeling and predicting the number of new active cases and deaths are important steps for anticipating and controlling COVID-19 outbreaks. The aim of this research was to develop an accurate prediction system for the COVID-19 pandemic that can predict the numbers of active cases and deaths in the Gulf countries of Saudi Arabia, Oman, the United Arab Emirates (UAE), Kuwait, Bahrain, and Qatar. The novelty of the proposed approach is that it uses an advanced prediction model—the bidirectional long short-term memory (Bi-LSTM) network deep learning model. The datasets were collected from an available repository containing updated registered cases of COVID-19 and showing the global numbers of active COVID-19 cases and deaths. Statistical analyses (e.g., mean square error, root mean square error, mean absolute error, and Spearman’s correlation coefficient) were employed to evaluate the results of the adopted Bi-LSTM model. The Bi-LSTM results based on the correlation metric gave predicted confirmed COVID-19 cases of 99.67%, 99.34%, 99.94%, 99.64%, 98.95%, and 99.91% for Saudi Arabia, Oman, the UAE, Kuwait, Bahrain, and Qatar, respectively, while testing the Bi-LSTM model for predicting COVID-19 mortality gave accuracies of 99.87%, 97.09%, 99.53%, 98.71%, 95.62%, and 99%, respectively. The Bi-LSTM model showed significant results using the correlation metric. Overall, the Bi-LSTM model demonstrated significant success in predicting COVID-19. The Bi-LSTM-based deep learning network achieves optimal prediction results and is effective and robust for predicting the numbers of active cases and deaths from COVID-19 in the studied Gulf countries.
31
Asch, Anna, Ethan J. Brady, Hugo Gallardo, John Hood, Bryan Chu e Mohammad Farazmand. "Model-assisted deep learning of rare extreme events from partial observations". Chaos: An Interdisciplinary Journal of Nonlinear Science 32, n. 4 (aprile 2022): 043112. http://dx.doi.org/10.1063/5.0077646.
Testo completoAbstract (sommario):
To predict rare extreme events using deep neural networks, one encounters the so-called small data problem because even long-term observations often contain few extreme events. Here, we investigate a model-assisted framework where the training data are obtained from numerical simulations, as opposed to observations, with adequate samples from extreme events. However, to ensure the trained networks are applicable in practice, the training is not performed on the full simulation data; instead, we only use a small subset of observable quantities, which can be measured in practice. We investigate the feasibility of this model-assisted framework on three different dynamical systems (Rössler attractor, FitzHugh–Nagumo model, and a turbulent fluid flow) and three different deep neural network architectures (feedforward, long short-term memory, and reservoir computing). In each case, we study the prediction accuracy, robustness to noise, reproducibility under repeated training, and sensitivity to the type of input data. In particular, we find long short-term memory networks to be most robust to noise and to yield relatively accurate predictions, while requiring minimal fine-tuning of the hyperparameters.
32
Zhang, Xinxin, Ying Zhang, Xiaoyan Lu, Lu Bai, Liangfu Chen, Jinhua Tao, Zhibao Wang e Lili Zhu. "Estimation of Lower-Stratosphere-to-Troposphere Ozone Profile Using Long Short-Term Memory (LSTM)". Remote Sensing 13, n. 7 (2 aprile 2021): 1374. http://dx.doi.org/10.3390/rs13071374.
Testo completoAbstract (sommario):
Climate change and air pollution are emerging topics due to their possible enormous implications for health and social perspectives. In recent years, tropospheric ozone has been recognized as an important greenhouse gas and pollutant that is detrimental to human health, agriculture, and natural ecosystems, and has shown a trend of increasing interest. Machine-learning-based approaches have been widely applied to the estimation of tropospheric ozone concentrations, but few studies have included tropospheric ozone profiles. This study aimed to predict the Northern Hemisphere distribution of Lower-Stratosphere-to-Troposphere (LST) ozone at a pressure of 100 hPa to the near surface by employing a deep learning Long Short-Term Memory (LSTM) model. We referred to a history of all the observed parameters (meteorological data of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5), satellite data, and the ozone profiles of the World Ozone and Ultraviolet Data Center (WOUDC)) between 2014 and 2018 for training the predictive models. Model–measurement comparisons for the monitoring sites of WOUDC for the period 2019–2020 show that the mean correlation coefficients (R2) in the Northern Hemisphere at high latitude (NH), Northern Hemisphere at middle latitude (NM), and Northern Hemisphere at low latitude (NL) are 0.928, 0.885, and 0.590, respectively, indicating reasonable performance for the LSTM forecasting model. To improve the performance of the model, we applied the LSTM migration models to the Civil Aircraft for the Regular Investigation of the Atmosphere Based on an Instrument Container (CARIBIC) flights in the Northern Hemisphere from 2018 to 2019 and three urban agglomerations (the Sichuan Basin (SCB), North China Plain (NCP), and Yangtze River Delta region (YRD)) between 2018 and 2019. The results show that our models performed well on the CARIBIC data set, with a high R2 equal to 0.754. The daily and monthly surface ozone concentrations for 2018–2019 in the three urban agglomerations were estimated from meteorological and ancillary variables. Our results suggest that the LSTM models can accurately estimate the monthly surface ozone concentrations in the three clusters, with relatively high coefficients of 0.815–0.889, root mean square errors (RMSEs) of 7.769–8.729 ppb, and mean absolute errors (MAEs) of 6.111–6.930 ppb. The daily scale performance was not as high as the monthly scale performance, with the accuracy of R2 = 0.636~0.737, RMSE = 14.543–16.916 ppb, MAE = 11.130–12.687 ppb. In general, the trained module based on LSTM is robust and can capture the variation of the atmospheric ozone distribution. Moreover, it also contributes to our understanding of the mechanism of air pollution, especially increasing our comprehension of pollutant areas.
33
Kim, Byoungjun, e Joonwhoan Lee. "A Bayesian Network-Based Information Fusion Combined with DNNs for Robust Video Fire Detection". Applied Sciences 11, n. 16 (19 agosto 2021): 7624. http://dx.doi.org/10.3390/app11167624.
Testo completoAbstract (sommario):
Fire is an abnormal event that can cause significant damage to lives and property. Deep learning approach has made large progress in vision-based fire detection. However, there is still the problem of false detections due to the objects which have similar fire-like visual properties such as colors or textures. In the previous video-based approach, Faster Region-based Convolutional Neural Network (R-CNN) is used to detect the suspected regions of fire (SRoFs), and long short-term memory (LSTM) accumulates the local features within the bounding boxes to decide a fire in a short-term period. Then, majority voting of the short-term decisions is taken to make the decision reliable in a long-term period. To ensure that the final fire decision is more robust, however, this paper proposes to use a Bayesian network to fuse various types of information. Because there are so many types of Bayesian network according to the situations or domains where the fire detection is needed, we construct a simple Bayesian network as an example which combines environmental information (e.g., humidity) with visual information including the results of location recognition and smoke detection, and long-term video-based majority voting. Our experiments show that the Bayesian network successfully improves the fire detection accuracy when compared against the previous video-based method and the state of art performance has been achieved with a public dataset. The proposed method also reduces the latency for perfect fire decisions, as compared with the previous video-based method.
34
Dhabhar, Firdaus S., e Kavitha Viswanathan. "Short-term stress experienced at time of immunization induces a long-lasting increase in immunologic memory". American Journal of Physiology-Regulatory, Integrative and Comparative Physiology 289, n. 3 (settembre 2005): R738—R744. http://dx.doi.org/10.1152/ajpregu.00145.2005.
Testo completoAbstract (sommario):
It would be extremely beneficial if one could harness natural, endogenous, health-promoting defense mechanisms to fight disease and restore health. The psychophysiological stress response is the most underappreciated of nature's survival mechanisms. We show that acute stress experienced before primary immunization induces a long-lasting increase in immunity. Compared with controls, mice restrained for 2.5 h before primary immunization with keyhole limpet hemocyanin (KLH) show a significantly enhanced immune response when reexposed to KLH 9 mo later. This immunoenhancement is mediated by an increase in numbers of memory and effector helper T cells in sentinel lymph nodes at the time of primary immunization. Further analyses show that the early stress-induced increase in T cell memory may stimulate the robust increase in infiltrating lymphocyte and macrophage numbers observed months later at a novel site of antigen reexposure. Enhanced leukocyte infiltration may be driven by increased levels of the type 1 cytokines, IL-2 and IFN-γ, and TNF-α, observed at the site of antigen reexposure in animals that had been stressed at the time of primary immunization. In contrast, no differences were observed in type 2 cytokines, IL-4 or IL-5. Given the importance of inducing long-lasting increases in immunologic memory during vaccination, we suggest that the neuroendocrine stress response is nature's adjuvant that could be psychologically and/or pharmacologically manipulated to safely increase vaccine efficacy. These studies introduce the novel concept that a psychophysiological stress response is nature's fundamental survival mechanism that could be therapeutically harnessed to augment immune function during vaccination, wound healing, or infection.
35
McBride, Dawn M., Jennifer H. Coane, Shuofeng Xu, Yi Feng e Zhichun Yu. "Short-term false memories vary as a function of list type". Quarterly Journal of Experimental Psychology 72, n. 12 (29 giugno 2019): 2726–41. http://dx.doi.org/10.1177/1747021819859880.
Testo completoAbstract (sommario):
False memories have primarily been investigated at long-term delays in the Deese–Roediger–McDermott (DRM) procedure, but a few studies have reported meaning-based false memories at delays as short as 1–4 s. The current study further investigated the processes that contribute to short-term false memories with semantic and phonological lists (Experiment 1) and hybrid lists containing items of each type (Experiment 2). In Experiment 1, more false memories were found for phonological than for semantic lists. In Experiment 2, an asymmetrical hyper-additive effect was found such that including one or two phonological associates in pure semantic lists yielded a robust increase in false alarms, whereas including semantic associates in pure phonological lists did not affect false alarms. These results are more consistent with the activation–monitoring account of false memory creation than with fuzzy trace theory that has not typically been referenced when describing phonological false memories.
36
Kong, Longteng, Mengxiao Zhu, Nan Ran, Qingjie Liu e Rui He. "Online Multiple Athlete Tracking with Pose-Based Long-Term Temporal Dependencies". Sensors 21, n. 1 (30 dicembre 2020): 197. http://dx.doi.org/10.3390/s21010197.
Testo completoAbstract (sommario):
This paper addresses the Multi-Athlete Tracking (MAT) problem, which plays a crucial role in sports video analysis. There exist specific challenges in MAT, e.g., athletes share a high similarity in appearance and frequently occlude with each other, making existing approaches not applicable for this task. To address this problem, we propose a novel online multiple athlete tracking approach which make use of long-term temporal pose dynamics for better distinguishing different athletes. Firstly, we design a Pose-based Triple Stream Network (PTSN) based on Long Short-Term Memory (LSTM) networks, capable of modeling long-term temporal pose dynamics of athletes, including pose-based appearance, motion and athletes’ interaction clues. Secondly, we propose a multi-state online matching algorithm based on bipartite graph matching and similarity scores produced by PTSN. It is robust to noisy detections and occlusions due to the reliable transitions of multiple detection states. We evaluate our method on the APIDIS, NCAA Basketball and VolleyTrack databases, and the experiment results demonstrate its effectiveness.
37
Shao, Xiaorui, Chang-Soo Kim e Palash Sontakke. "Accurate Deep Model for Electricity Consumption Forecasting Using Multi-channel and Multi-Scale Feature Fusion CNN–LSTM". Energies 13, n. 8 (12 aprile 2020): 1881. http://dx.doi.org/10.3390/en13081881.
Testo completoAbstract (sommario):
Electricity consumption forecasting is a vital task for smart grid building regarding the supply and demand of electric power. Many pieces of research focused on the factors of weather, holidays, and temperatures for electricity forecasting that requires to collect those data by using kinds of sensors, which raises the cost of time and resources. Besides, most of the existing methods only focused on one or two types of forecasts, which cannot satisfy the actual needs of decision-making. This paper proposes a novel hybrid deep model for multiple forecasts by combining Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) algorithm without additional sensor data, and also considers the corresponding statistics. Different from the conventional stacked CNN–LSTM, in the proposed hybrid model, CNN and LSTM extracted features in parallel, which can obtain more robust features with less loss of original information. Chiefly, CNN extracts multi-scale robust features by various filters at three levels and wide convolution technology. LSTM extracts the features which think about the impact of different time-steps. The features extracted by CNN and LSTM are combined with six statistical components as comprehensive features. Therefore, comprehensive features are the fusion of multi-scale, multi-domain (time and statistic domain) and robust due to the utilization of wide convolution technology. We validate the effectiveness of the proposed method on three natural subsets associated with electricity consumption. The comparative study shows the state-of-the-art performance of the proposed hybrid deep model with good robustness for very short-term, short-term, medium-term, and long-term electricity consumption forecasting.
38
Jamil, Ramish, Imran Ashraf, Furqan Rustam, Eysha Saad, Arif Mehmood e Gyu Sang Choi. "Detecting sarcasm in multi-domain datasets using convolutional neural networks and long short term memory network model". PeerJ Computer Science 7 (25 agosto 2021): e645. http://dx.doi.org/10.7717/peerj-cs.645.
Testo completoAbstract (sommario):
Sarcasm emerges as a common phenomenon across social networking sites because people express their negative thoughts, hatred and opinions using positive vocabulary which makes it a challenging task to detect sarcasm. Although various studies have investigated the sarcasm detection on baseline datasets, this work is the first to detect sarcasm from a multi-domain dataset that is constructed by combining Twitter and News Headlines datasets. This study proposes a hybrid approach where the convolutional neural networks (CNN) are used for feature extraction while the long short-term memory (LSTM) is trained and tested on those features. For performance analysis, several machine learning algorithms such as random forest, support vector classifier, extra tree classifier and decision tree are used. The performance of both the proposed model and machine learning algorithms is analyzed using the term frequency-inverse document frequency, bag of words approach, and global vectors for word representations. Experimental results indicate that the proposed model surpasses the performance of the traditional machine learning algorithms with an accuracy of 91.60%. Several state-of-the-art approaches for sarcasm detection are compared with the proposed model and results suggest that the proposed model outperforms these approaches concerning the precision, recall and F1 scores. The proposed model is accurate, robust, and performs sarcasm detection on a multi-domain dataset.
39
Ma, Liang, Meng Liu, Na Wang, Lu Wang, Yang Yang e Hongjun Wang. "Room-Level Fall Detection Based on Ultra-Wideband (UWB) Monostatic Radar and Convolutional Long Short-Term Memory (LSTM)". Sensors 20, n. 4 (18 febbraio 2020): 1105. http://dx.doi.org/10.3390/s20041105.
Testo completoAbstract (sommario):
Timely calls for help can really make a difference for elders who suffer from falls, particularly in private locations. Considering privacy protection and convenience for the users, in this paper, we approach the problem by using impulse–radio ultra-wideband (IR-UWB) monostatic radar and propose a learning model that combines convolutional layers and convolutional long short term memory (ConvLSTM) to extract robust spatiotemporal features for fall detection. The performance of the proposed scheme was evaluated in terms of accuracy, sensitivity, and specificity. The results show that the proposed method outperforms convolutional neural network (CNN)-based methods. Of the six activities we investigated, the proposed method can achieve a sensitivity of 95% and a specificity of 92.6% at a range of 8 meters. Further tests in a heavily furnished lounge environment showed that the model can detect falls with more than 90% sensitivity, even without re-training effort. The proposed method can detect falls without exposing the identity of the users. Thus, the proposed method is ideal for room-level fall detection in privacy-prioritized scenarios.
40
Grobelny, Piotr, e Adam Narbudowicz. "MM-Wave Radar-Based Recognition of Multiple Hand Gestures Using Long Short-Term Memory (LSTM) Neural Network". Electronics 11, n. 5 (3 marzo 2022): 787. http://dx.doi.org/10.3390/electronics11050787.
Testo completoAbstract (sommario):
The paper proposes a simple machine learning solution for hand-gesture classification, based on processed MM-wave radar signal. It investigates the classification up to 12 different intuitive and ergonomic gestures, which are intended to serve as a contactless user interface. The system is based on AWR1642 boost Frequency-Modulated Continuous-Wave (FMCW) radar, which allows capturing standardized data to support the scalability of the proposed solution. More than 4000 samples were collected from 4 different people, with all signatures extracted from the radar hardware available in open-access database accompanying the publication. Collected data were processed and used to train Long short-term memory (LSTM) and artificial recurrent neural network (RNN) architecture. The work studies the impact of different input parameters, the number of hidden layers, and the number of neurons in those layers. The proposed LSTM network allows for classification of different gestures, with the total accuracy ranging from 94.4% to 100% depending on use-case scenario, with a relatively small architecture of only 2 hidden layers with 32 neurons in each. The solution is also tested with additional data recorded from subjects not involved in the original training set, resulting in an accuracy drop of no more than 2.24%. This demonstrates that the proposed solution is robust and scalable, allowing quick and reliable creation of larger databases of gestures to expand the use of machine learning with radar technologies.
41
Colettis, Natalia Claudia, Martín Habif, María Victoria Oberholzer, Federico Filippin e Diana Alicia Jerusalinsky. "Differences in learning and memory between middle-aged female and male rats". Learning & Memory 29, n. 5 (15 aprile 2022): 120–25. http://dx.doi.org/10.1101/lm.053578.122.
Testo completoAbstract (sommario):
We observed differences in cognitive functions between middle-aged female and male Wistar rats. Both (like youngsters) discriminated new versus familiar objects, showing similar short- and long-term memory (STM and LTM, respectively). Only females show robust LTM for new location of an object. Both successfully form LTM of inhibitory avoidance, though males appeared to be amnesic for memory persistence. Habituation, locomotion, horizontal exploration, “stereotypies,” fear, and anxiety-like behavior were similar for both, while vertical exploration was significantly higher in middle-aged and younger females. Therefore, sex-dependent differences in some cognitive functions and behaviors must be considered when designing and interpreting learning and memory studies.
42
Elliott, Terry. "Dynamic Integrative Synaptic Plasticity Explains the Spacing Effect in the Transition from Short- to Long-Term Memory". Neural Computation 31, n. 11 (novembre 2019): 2212–51. http://dx.doi.org/10.1162/neco_a_01227.
Testo completoAbstract (sommario):
Repeated stimuli that are spaced apart in time promote the transition from short- to long-term memory, while massing repetitions together does not. Previously, we showed that a model of integrative synaptic plasticity, in which plasticity induction signals are integrated by a low-pass filter before plasticity is expressed, gives rise to a natural timescale at which to repeat stimuli, hinting at a partial account of this spacing effect. The account was only partial because the important role of neuromodulation was not considered. We now show that by extending the model to allow dynamic integrative synaptic plasticity, the model permits synapses to robustly discriminate between spaced and massed repetition protocols, suppressing the response to massed stimuli while maintaining that to spaced stimuli. This is achieved by dynamically coupling the filter decay rate to neuromodulatory signaling in a very simple model of the signaling cascades downstream from cAMP production. In particular, the model's parameters may be interpreted as corresponding to the duration and amplitude of the waves of activity in the MAPK pathway. We identify choices of parameters and repetition times for stimuli in this model that optimize the ability of synapses to discriminate between spaced and massed repetition protocols. The model is very robust to reasonable changes around these optimal parameters and times, but for large changes in parameters, the model predicts that massed and spaced stimuli cannot be distinguished or that the responses to both patterns are suppressed. A model of dynamic integrative synaptic plasticity therefore explains the spacing effect under normal conditions and also predicts its breakdown under abnormal conditions.
43
Qiu, Yibin, Qi Li, Yuru Pan, Lanjia Huang, Cai Sun, Hanqing Yang, Jiawei Liu e Weirong Chen. "Modeling the Adaptive Uncertainty Sets of Robust Optimization Based on Long Short-Term Memory Network and Modified Fuzzy Information Granulation". IEEE Access 8 (2020): 56072–80. http://dx.doi.org/10.1109/access.2020.2964652.
Testo completo
44
Mwaura, Anselim M., e Yong-Kuo Liu. "Prediction of the Loss of Feed Water Fault Signatures Using Machine Learning Techniques". Science and Technology of Nuclear Installations 2021 (9 agosto 2021): 1–13. http://dx.doi.org/10.1155/2021/5511735.
Testo completoAbstract (sommario):
Fault diagnosis occurrence and its precise prediction in nuclear power plants are extremely important in avoiding disastrous consequences. The inherent limitations of the current fault diagnosis methods make machine learning techniques and their hybrid methodologies possible solutions to remedy this challenge. This study sought to develop, examine, compare, and contrast three robust machine learning methodologies of adaptive neurofuzzy inference system, long short-term memory, and radial basis function network by modeling the loss of feed water event using RELAP5. The performance indices of residual plots, mean absolute percentage error, root mean squared error, and coefficient of determination were used to determine the most suitable algorithms for accurately diagnosing the loss of feed water transient signatures. The study found out that the adaptive neurofuzzy inference system model outperformed the other schemes when predicting the temperature of the steam generator tubes, the radial basis function network scheme was best suited in forecasting the mass flow rate at the core inlet, while the long short-term memory algorithm was best suited for the estimation of the severities of the loss of the feed water fault.
45
Nguyen, Lam Van, Hoese Michel Tornyeviadzi, Dieu Tien Bui e Razak Seidu. "Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework". Water 14, n. 3 (19 gennaio 2022): 300. http://dx.doi.org/10.3390/w14030300.
Testo completoAbstract (sommario):
Predicting discharges in sewage systems play an essential role in reducing sewer overflows and impacts on the environment and public health. Choosing a suitable model to predict discharges in these systems is essential to realizing these aforementioned goals. Long Short-Term Memory (LSTM) has been proposed as a robust technique for predicting discharges in wastewater networks. This study explored the potential application of an LSTM model to predict discharges using 3-month data set in a sewer network in Ålesund city, Norway. Different sequence-to-sequence LSTMs were investigated using various input and output datasets. The impact of data aggregation (10-min and 30-min intervals) was examined and compared to original sensor data (5-min intervals) to evaluate the performance of the LSTM model. The results show that 50-neuron LSTM architecture performed better (MAPE = 0.09, RMSE = 0.0008, R2 = 0.8) in predicting discharges for the study area. The study indicates that using the same sequence length for the prior and the forecast can improve the effectiveness of the LSTM model. Based on the results, using a 10-min aggregated discharge dataset reduces energy consumption, transmission bandwidth, and storage capacity. Additionally, it improves prediction performance compared to an original 5-min interval data in Ålesund city.
46
Huang, Lin, Jianjun Yan, Shiyu Cai, Rui Guo, Haixia Yan e Yiqin Wang. "Automated Segmentation of the Systolic and Diastolic Phases in Wrist Pulse Signal Using Long Short-Term Memory Network". BioMed Research International 2022 (21 agosto 2022): 1–9. http://dx.doi.org/10.1155/2022/2766321.
Testo completoAbstract (sommario):
Purpose. Single-period segmentation is one of the important steps in time-domain analysis of pulse signals, which is the basis of time-domain feature extraction. The existing single-period segmentation methods have the disadvantages of generalization, reliability, and robustness. Method. This paper proposed a period segmentation method of pulse signals based on long short-term memory (LSTM) network. The preprocessing was performed to remove noises and baseline drift of pulse signals. Thus, LabelMe was used to label each period of the pulse signals into two parts according to the location of the starting point of main wave and the dicrotic notch, and the dataset of the pulse signal period segmentation was established. Consequently, the labeled dataset was input into the LSTM for training and testing, and the results were compared with sum slope function method. Result. The remarkable result with the whole period segmentation accuracy of 92.8% was achieved for the segmentation of seven types of pulse signals. And the segmentation accuracies of the systolic phase, diastolic phase, and whole period using this method were higher than those of the sum slope function method. Conclusion. LSTM-based pulse signal segmentation method can achieve outstanding, robust, and reliable segmentation effects of the systolic phase, diastolic phase, and whole period of pulse signals. The research provides a new idea and method for the segmentation of pulse signals.
47
Khadka, Shauharda, Jen Jen Chung e Kagan Tumer. "Neuroevolution of a Modular Memory-Augmented Neural Network for Deep Memory Problems". Evolutionary Computation 27, n. 4 (dicembre 2019): 639–64. http://dx.doi.org/10.1162/evco_a_00239.
Testo completoAbstract (sommario):
We present Modular Memory Units (MMUs), a new class of memory-augmented neural network. MMU builds on the gated neural architecture of Gated Recurrent Units (GRUs) and Long Short Term Memory (LSTMs), to incorporate an external memory block, similar to a Neural Turing Machine (NTM). MMU interacts with the memory block using independent read and write gates that serve to decouple the memory from the central feedforward operation. This allows for regimented memory access and update, giving our network the ability to choose when to read from memory, update it, or simply ignore it. This capacity to act in detachment allows the network to shield the memory from noise and other distractions, while simultaneously using it to effectively retain and propagate information over an extended period of time. We train MMU using both neuroevolution and gradient descent, and perform experiments on two deep memory benchmarks. Results demonstrate that MMU performs significantly faster and more accurately than traditional LSTM-based methods, and is robust to dramatic increases in the sequence depth of these memory benchmarks.
48
Huynh, Anh Ngoc-Lan, Ravinesh C. Deo, Duc-Anh An-Vo, Mumtaz Ali, Nawin Raj e Shahab Abdulla. "Near Real-Time Global Solar Radiation Forecasting at Multiple Time-Step Horizons Using the Long Short-Term Memory Network". Energies 13, n. 14 (8 luglio 2020): 3517. http://dx.doi.org/10.3390/en13143517.
Testo completoAbstract (sommario):
This paper aims to develop the long short-term memory (LSTM) network modelling strategy based on deep learning principles, tailored for the very short-term, near-real-time global solar radiation (GSR) forecasting. To build the prescribed LSTM model, the partial autocorrelation function is applied to the high resolution, 1 min scaled solar radiation dataset that generates statistically significant lagged predictor variables describing the antecedent behaviour of GSR. The LSTM algorithm is adopted to capture the short- and the long-term dependencies within the GSR data series patterns to accurately predict the future GSR at 1, 5, 10, 15, and 30 min forecasting horizons. This objective model is benchmarked at a solar energy resource rich study site (Bac-Ninh, Vietnam) against the competing counterpart methods employing other deep learning, a statistical model, a single hidden layer and a machine learning-based model. The LSTM model generates satisfactory predictions at multiple-time step horizons, achieving a correlation coefficient exceeding 0.90, outperforming all of the counterparts. In accordance with robust statistical metrics and visual analysis of all tested data, the study ascertains the practicality of the proposed LSTM approach to generate reliable GSR forecasts. The Diebold–Mariano statistic test also shows LSTM outperforms the counterparts in most cases. The study confirms the practical utility of LSTM in renewable energy studies, and broadly in energy-monitoring devices tailored for other energy variables (e.g., hydro and wind energy).
49
Ramaraj, P. "A Neural Network in Convolution with Constant Error Carousel Based Long Short Term Memory for Better Face Recognition". Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, n. 2 (11 aprile 2021): 2042–52. http://dx.doi.org/10.17762/turcomat.v12i2.1808.
Testo completoAbstract (sommario):
Unconstrained face identification, facial periocular recognition, facial land marking and pose prediction, facial expression recognition, 3D facial model design, and other facial-related problems require robust face detection in the wild. Despite the fact that the face recognition issue has been researched intensively for decades with different commercial implementations, it nevertheless faces problems in certain real-world scenarios due to multiple obstacles, such as severe facial occlusions, incredibly low resolutions, intense lighting, exceptionally pose inconsistencies, picture or video compression artefacts, and so on. To solve the problems described above, a face detection technique called Convolution Neural Network with Constant Error Carousel dependent Long Short Term Memory (CNN-CEC-LSTM) is proposed in this paper. This research implemented a novel network structure and designed a special feature extraction that employs a self-channel attention (SCA) block and a self-spatial attention (SSA) block that adaptively aggregates the feature maps in both channel and spatial domains to learn the inter-channel and inter-spatial connection matrices; additionally, matrix multiplications are conducted for a This approach first smoothed the initial image with a Gaussian filter before measuring the gradient image. The Canny-Kirsch Method edge detection algorithm was then used to identify human face edges. The proposed method is evaluated against two recent difficult face detection databases, including the IIT Kanpur Dataset. The experimental findings indicate that the proposed approach outperforms the most current cutting-edge face recognition approaches.
50
Tran, Trung Duc, Vinh Ngoc Tran e Jongho Kim. "Improving the Accuracy of Dam Inflow Predictions Using a Long Short-Term Memory Network Coupled with Wavelet Transform and Predictor Selection". Mathematics 9, n. 5 (5 marzo 2021): 551. http://dx.doi.org/10.3390/math9050551.
Testo completoAbstract (sommario):
Accurate and reliable dam inflow prediction models are essential for effective reservoir operation and management. This study presents a data-driven model that couples a long short-term memory (LSTM) network with robust input predictor selection, input reconstruction by wavelet transformation, and efficient hyper-parameter optimization by K-fold cross-validation and the random search. First, a robust analysis using a “correlation threshold” for partial autocorrelation and cross-correlation functions is proposed, and only variables greater than this threshold are selected as input predictors and their time lags. This analysis indicates that a model trained on a threshold of 0.4 returns the highest Nash–Sutcliffe efficiency value; as a result, six principal inputs are selected. Second, using additional subseries reconstructed by the wavelet transform improves predictability, particularly for flow peak. The peak error values of LSTM with the transform are approximately one-half to one-quarter the size of those without the transform. Third, for a K of 5 as determined by the Silhouette coefficients and the distortion score, the wavelet-transformed LSTMs require a larger number of hidden units, epochs, dropout, and batch size. This complex configuration is needed because the amount of inputs used by these LSTMs is five times greater than that of other models. Last, an evaluation of accuracy performance reveals that the model proposed in this study, called SWLSTM, provides superior predictions of the daily inflow of the Hwacheon dam in South Korea compared with three other LSTM models by 84%, 78%, and 65%. These results strengthen the potential of data-driven models for efficient and effective reservoir inflow predictions, and should help policy-makers and operators better manage their reservoir operations.