To see the other types of publications on this topic, follow the link: LSTM.
Journal articles on the topic 'LSTM'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'LSTM.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Murugesan, R., Eva Mishra, and Akash Hari Krishnan. "Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM." International Journal of Sustainable Agricultural Management and Informatics 8, no. 3 (2022): 242. http://dx.doi.org/10.1504/ijsami.2022.125757.
Full text
2
Krishnan, Akash Hari, R. Murugesan, and Eva Mishra. "Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM." International Journal of Sustainable Agricultural Management and Informatics 8, no. 3 (2022): 1. http://dx.doi.org/10.1504/ijsami.2022.10048228.
Full text
3
Roberg, Kevin J., Stephen Bickel, Neil Rowley, and Chris A. Kaiser. "Control of Amino Acid Permease Sorting in the Late Secretory Pathway of Saccharomyces cerevisiae by SEC13, LST4, LST7 and LST78." Genetics 147, no. 4 (December 1, 1997): 1569–84. http://dx.doi.org/10.1093/genetics/147.4.1569.
Full textAbstract:
Abstract The SEC13 gene was originally identified by temperature-sensitive mutations that block all protein transport from the ER to the Golgi. We have found that at a permissive temperature for growth, the sec13-1 mutation selectively blocks transport of the nitrogen-regulated amino acid permease, Gaplp, from the Golgi to the plasma membrane, but does not affect the activity of constitutive permeases such as Hip1p, Can1p, or Lyp1p. Different alleles of SEC13 exhibit different relative effects on protein transport from the ER to the Golgi, or on Gap1p activity, indicating distinct requirements for SEC13 function at two different steps in the secretory pathway. Three new genes, LST4, LST7, and LSTB, were identified that are also required for amino acid permease transport from the Golgi to the cell surface. Mutations in LST4 and LST7 reduce the activity of the nitrogen-regulated permeases Gap1p and Put4p, whereas mutations in LST8 impair the activities of a broader set of amino acid permeases. The LST8 gene encodes a protein composed of WD-repeats and has a close human homologue. The LST7 gene encodes a novel protein. Together, these data indicate that SEC13, LST4, LST7, and LST8 function in the regulated delivery of Gap1p to the cell surface, perhaps as components of a post-Golgi secretory-vesicle coat.
4
Victor, Nancy, and Daphne Lopez. "sl-LSTM." International Journal of Grid and High Performance Computing 12, no. 3 (July 2020): 1–16. http://dx.doi.org/10.4018/ijghpc.2020070101.
Full textAbstract:
The volume of data in diverse data formats from various data sources has led the way for a new drift in the digital world, Big Data. This article proposes sl-LSTM (sequence labelling LSTM), a neural network architecture that combines the effectiveness of typical LSTM models to perform sequence labeling tasks. This is a bi-directional LSTM which uses stochastic gradient descent optimization and combines two features of the existing LSTM variants: coupled input-forget gates for reducing the computational complexity and peephole connections that allow all gates to inspect the current cell state. The model is tested on different datasets and the results show that the integration of various neural network models can further improve the efficiency of approach for identifying sensitive information in Big data.
5
Liu, Zhandong, Wengang Zhou, and Houqiang Li. "AB-LSTM." ACM Transactions on Multimedia Computing, Communications, and Applications 15, no. 4 (January 10, 2020): 1–23. http://dx.doi.org/10.1145/3356728.
Full text
6
Suebsombut, Paweena, Aicha Sekhari, Pradorn Sureephong, Abdelhak Belhi, and Abdelaziz Bouras. "Field Data Forecasting Using LSTM and Bi-LSTM Approaches." Applied Sciences 11, no. 24 (December 13, 2021): 11820. http://dx.doi.org/10.3390/app112411820.
Full textAbstract:
Water, an essential resource for crop production, is becoming increasingly scarce, while cropland continues to expand due to the world’s population growth. Proper irrigation scheduling has been shown to help farmers improve crop yield and quality, resulting in more sustainable water consumption. Soil Moisture (SM), which indicates the amount of water in the soil, is one of the most important crop irrigation parameters. In terms of water usage optimization and crop yield, estimating future soil moisture (forecasting) is an essentially valuable task for crop irrigation. As a result, farmers can base crop irrigation decisions on this parameter. Sensors can be used to estimate this value in real time, which may assist farmers in deciding whether or not to irrigate. The soil moisture value provided by the sensors, on the other hand, is instantaneous and cannot be used to directly compute irrigation parameters such as the best timing or the required water quantity to irrigate. The soil moisture value can, in fact, vary greatly depending on factors such as humidity, weather, and time. Using machine learning methods, these parameters can be used to predict soil moisture levels in the near future. This paper proposes a new Long-Short Term Memory (LSTM)-based model to forecast soil moisture values in the future based on parameters collected from various sensors as a potential solution. To train and validate this model, a real-world dataset containing a set of parameters related to weather forecasting, soil moisture, and other related parameters was collected using smart sensors installed in a greenhouse in Chiang Mai province, Thailand. Preliminary results show that our LSTM-based model performs well in predicting soil moisture with a 0.72% RMSE error and a 0.52% cross-validation error (LSTM), and our Bi-LSTM model with a 0.76% RMSE error and a 0.57% cross-validation error. In the future, we aim to test and validate this model on other similar datasets.
7
Liang, Xinyue. "Stock Market Prediction with RNN-LSTM and GA-LSTM." SHS Web of Conferences 196 (2024): 02006. http://dx.doi.org/10.1051/shsconf/202419602006.
Full textAbstract:
The stock price reflects various factors such as the rate of economic growth, inflation, overall economy, trade balance, and monetary system, all of which impact the stock market as a whole. Investors often find the principle of stock price trends unclear because of the many important variables involved. When creating an investment strategy or determining the timing for buying or selling stocks, forecasting stock market trends plays a critical role. It is difficult to estimate the value of the stock market due to the non-linear and dynamic nature of the stock index. Numerous studies using deep learning techniques have been successful in making such predictions. The Long Short Term Memory (LSTM) has become popular for predicting stock market prices. This paper thoroughly examines methods for predicting stock market performance using RNN-LSTM and GA-LSTM, provides explanations of these methods, and performs a comparative analysis. We will discuss future directions and outline the significance of using RNN-LSTM and GA-LSTM for forecasting stock market trends, based on the papers we have reviewed.
8
Song, Jun, Siliang Tang, Jun Xiao, Fei Wu, and Zhongfei Zhang. "LSTM-in-LSTM for generating long descriptions of images." Computational Visual Media 2, no. 4 (November 15, 2016): 379–88. http://dx.doi.org/10.1007/s41095-016-0059-z.
Full text
9
Nilasari, Ni Ketut Novia, Made Sudarma, and Nyoman Gunantara. "Prediksi Nilai Cryptocurrency Dengan Metode Bi-LSTM dan LSTM." Majalah Ilmiah Teknologi Elektro 22, no. 2 (December 19, 2023): 221. http://dx.doi.org/10.24843/mite.2023.v22i02.p09.
Full textAbstract:
Semakin pesatnya perkembangan teknologi saat ini, dapat memudahkan seluruh kegiatan manusia, sehingga mengakibatkan seluruh aspek tidak bisa lepas dari teknologi tanpa terkecuali bidang keuangan. Dengan berkembangnya teknologi diiringi juga dengan dikenalnya berbagai instrument investasi. Setiap melaksanakan investasi tentu akan selalu ada berbagai resiko yang menyertainya termasuk investasi cryptocurrency salah satunya bitcoin. Tidak seperti mata uang konvensional, bitcoin bersifat tidak desentralisasi sehingga perkembangan harganya tidak dalam pengawasan atau kontrol pihak manapun, dimana jika uang konvensional ada lembaga tertentu yang mengawasi dan mengontrol pergerakannya. Hal tersebut mengakibatkan harga nilai tukar dari bitcoin menjadi tidak konsisten atau tidak stabil. Dengan terdapatnya metode prediksi, pengguna bitcoin bisa menetapkan waktu yang pas untuk menjalankan transaksi. Penelitian ini memiliki tujuan guna memprediksi harga bitcoin dengan menggunakan metode LSTM serta Bi-LSTM. Berdasarkan hasil penelitian diperoleh hasil prediksi terbaik menggunakan metode Bi-LSTM dengan RMSE 1482.73 sedangkan dengan LSTM menghasilkan RMSE sebesar 1768.69 sehingga dapat disimpulkan dari sisi akurasi Bi-LSTM memberikan hasil yang lebih akurat hanya saja dengan Bi-LSTM membutuhkan resourse yang lebih banyak.
10
Zhang, Xinchen, Linghao Zhang, Qincheng Zhou, and Xu Jin. "A Novel Bitcoin and Gold Prices Prediction Method Using an LSTM-P Neural Network Model." Computational Intelligence and Neuroscience 2022 (May 5, 2022): 1–12. http://dx.doi.org/10.1155/2022/1643413.
Full textAbstract:
As a result of the fast growth of financial technology and artificial intelligence around the world, quantitative algorithms are now being employed in many classic futures and stock trading, as well as hot digital currency trades, among other applications today. Using the historical price series of Bitcoin and gold from 9/11/2016 to 9/10/2021, we investigate an LSTM-P neural network model for predicting the values of Bitcoin and gold in this research. We first employ a noise reduction approach based on the wavelet transform to smooth the fluctuations of the price data, which has been shown to increase the accuracy of subsequent predictions. Second, we apply a wavelet transform to diminish the influence of high-frequency noise components on prices. Third, in the price prediction model, we develop an optimized LSTM prediction model (LSPM-P) and train it using historical price data for gold and Bitcoin to make accurate predictions. As a consequence of our model, we have a high degree of accuracy when projecting future pricing. In addition, our LSTM-P model outperforms both the conventional LSTM models and other time series forecasting models in terms of accuracy and precision.
11
Abbas, Thekra. "Finger Vein Recognition with Hybrid Deep Learning Approach." Journal La Multiapp 4, no. 1 (July 24, 2023): 23–33. http://dx.doi.org/10.37899/journallamultiapp.v4i1.788.
Full textAbstract:
Finger vein biometrics is an identification technique based on the vein patterns in fingers, and it has the benefit of being difficult to counterfeit. Due to its high level of security, durability, and performance history, finger vein recognition captures our attention as one of the most significant authentication methods available today. Using a mixed deep learning approach, we investigate the challenge of identifying the finger vein sensor model. Thus far, we use Traditional LSTM architectures for this biometric modality. This work also suggests a brand-new hybrid architecture that shines due to its compactness and a merging with the LSMT layer to be taught. In the experiment, original samples as well as the region of interest data from eight freely available FV-USM datasets are employed. The standard LSTM-based strategy is preferable and produced better outcomes, as seen by the comparison with the earlier approaches. Moreover, the results show that the hybrid CNN and LSTM networks may be used to improve vein detection performance.
12
Song, Kyungwoo, JoonHo Jang, Seung jae Shin, and Il-Chul Moon. "Bivariate Beta-LSTM." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 5818–25. http://dx.doi.org/10.1609/aaai.v34i04.6039.
Full textAbstract:
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function. However, due to the graduality of the sigmoid function, the sigmoid gate is not flexible in representing multi-modality or skewness. Besides, the previous models lack modeling on the correlation between the gates, which would be a new method to adopt inductive bias for a relationship between previous and current input. This paper proposes a new gate structure with the bivariate Beta distribution. The proposed gate structure enables probabilistic modeling on the gates within the LSTM cell so that the modelers can customize the cell state flow with priors and distributions. Moreover, we theoretically show the higher upper bound of the gradient compared to the sigmoid function, and we empirically observed that the bivariate Beta distribution gate structure provides higher gradient values in training. We demonstrate the effectiveness of the bivariate Beta gate structure on the sentence classification, image classification, polyphonic music modeling, and image caption generation.
13
Karyadi, Yadi. "Prediksi Kualitas Udara Dengan Metoda LSTM, Bidirectional LSTM, dan GRU." JATISI (Jurnal Teknik Informatika dan Sistem Informasi) 9, no. 1 (March 17, 2022): 671–84. http://dx.doi.org/10.35957/jatisi.v9i1.1588.
Full textAbstract:
Kualitas udara menjadi salah satu masalah utama di kota besar. Salah satu cara pengendalian kualitas udara adalah dengan cara memprediksi beberapa parameter utama dengan menggunakan algoritma deep learning. Penelitian ini menggunakan metoda deep learning yang merupakan bagian dari Recurrent Neural network yaitu Long Short Term Memory, Bidirectional Long Short Term Memory, dan Gated Recurrent Unit yang diterapkan pada permasalahan memprediksi data time series kualitas udara dengan parameter suhu, kelembaban, particular matter PM10, dan Indeks Standar Pencemar Udara (ISPU). Dari hasil pengujian 3 jenis model prediksi terhadap 4 variabel berdasarkan kreteria penilain menggunakan RMSE dari data testing dan dibandingkan dengan standard deviasi, maka model LSTM dan LSTM Bidirectional telah menunjukan hasil yang bagus untuk permasalahan data yang bersifat time series kualitas udara, Sedangkan model Gated Recurrent Unit (GRU) menampilkan hasil yang kurang bagus.
14
Li, Youru, Zhenfeng Zhu, Deqiang Kong, Hua Han, and Yao Zhao. "EA-LSTM: Evolutionary attention-based LSTM for time series prediction." Knowledge-Based Systems 181 (October 2019): 104785. http://dx.doi.org/10.1016/j.knosys.2019.05.028.
Full text
15
Wan, Huaiyu, Shengnan Guo, Kang Yin, Xiaohui Liang, and Youfang Lin. "CTS-LSTM: LSTM-based neural networks for correlatedtime series prediction." Knowledge-Based Systems 191 (March 2020): 105239. http://dx.doi.org/10.1016/j.knosys.2019.105239.
Full text
16
Sang, Shuai, and Lu Li. "A Novel Variant of LSTM Stock Prediction Method Incorporating Attention Mechanism." Mathematics 12, no. 7 (March 22, 2024): 945. http://dx.doi.org/10.3390/math12070945.
Full textAbstract:
Long Short-Term Memory (LSTM) is an effective method for stock price prediction. However, due to the nonlinear and highly random nature of stock price fluctuations over time, LSTM exhibits poor stability and is prone to overfitting, resulting in low prediction accuracy. To address this issue, this paper proposes a novel variant of LSTM that couples the forget gate and input gate in the LSTM structure, and adds a “simple” forget gate to the long-term cell state. In order to enhance the generalization ability and robustness of the variant LSTM, the paper introduces an attention mechanism and combines it with the variant LSTM, presenting the Attention Mechanism Variant LSTM (AMV-LSTM) model along with the corresponding backpropagation algorithm. The parameters in AMV-LSTM are updated using the Adam gradient descent method. Experimental results demonstrate that the variant LSTM alleviates the instability and overfitting issues of LSTM, effectively improving prediction accuracy. AMV-LSTM further enhances accuracy compared to the variant LSTM, and compared to AM-LSTM, it exhibits superior generalization ability, accuracy, and convergence capability.
17
D, Usha, Jesmalar L, Noorbasha Nagoor Meeravali, Mihirkumar B.Suthar, Rajeswari J, Pothumarthi Sridevi, and Vengatesh T. "Enhanced Dengue Fever Prediction in India through Deep Learning with Spatially Attentive LSTMs." Cuestiones de Fisioterapia 54, no. 2 (January 10, 2025): 3804–12. https://doi.org/10.48047/v3dm7y10.
Full textAbstract:
This research intends to forecast dengue fever occurrences in India using machine learningmethods. A dataset comprising weekly dengue occurrences at the state level in India from 2017 to2024 was sourced from the India Open Data website and contains factors such as climate, geography,and demographics. Six distinct long short-term memory (LSTM) models were created and assessedfor dengue forecasting in India: LSTM, stacked LSTM (S-LSTM), LSTM with temporal attention(TA-LSTM), S-LSTM with temporal attention (STA-LSTM), LSTM with spatial attention (SALSTM), and S-LSTM with spatial attention (SSA-LSTM). The models were trained and tested on adataset of monthly dengue occurrences in India from 2017 to 2024, aiming to predict the number ofdengue cases using various climate, topographic, demographic, and land-use factors.
18
Majeed, Mokhalad A., Helmi Zulhaidi Mohd Shafri, Zed Zulkafli, and Aimrun Wayayok. "A Deep Learning Approach for Dengue Fever Prediction in Malaysia Using LSTM with Spatial Attention." International Journal of Environmental Research and Public Health 20, no. 5 (February 25, 2023): 4130. http://dx.doi.org/10.3390/ijerph20054130.
Full textAbstract:
This research aims to predict dengue fever cases in Malaysia using machine learning techniques. A dataset consisting of weekly dengue cases at the state level in Malaysia from 2010 to 2016 was obtained from the Malaysia Open Data website and includes variables such as climate, geography, and demographics. Six different long short-term memory (LSTM) models were developed and compared for dengue prediction in Malaysia: LSTM, stacked LSTM (S-LSTM), LSTM with temporal attention (TA-LSTM), S-LSTM with temporal attention (STA-LSTM), LSTM with spatial attention (SA-LSTM), and S-LSTM with spatial attention (SSA-LSTM). The models were trained and evaluated on a dataset of monthly dengue cases in Malaysia from 2010 to 2016, with the task of predicting the number of dengue cases based on various climate, topographic, demographic, and land-use variables. The SSA-LSTM model, which used both stacked LSTM layers and spatial attention, performed the best, with an average root mean squared error (RMSE) of 3.17 across all lookback periods. When compared to three benchmark models (SVM, DT, ANN), the SSA-LSTM model had a significantly lower average RMSE. The SSA-LSTM model also performed well in different states in Malaysia, with RMSE values ranging from 2.91 to 4.55. When comparing temporal and spatial attention models, the spatial models generally performed better at predicting dengue cases. The SSA-LSTM model was also found to perform well at different prediction horizons, with the lowest RMSE at 4- and 5-month lookback periods. Overall, the results suggest that the SSA-LSTM model is effective at predicting dengue cases in Malaysia.
19
N. Laxmi, Et al. "Hybrid Deep Learning Algorithm for Insulin Dosage Prediction Using Blockchain and IOT." International Journal on Recent and Innovation Trends in Computing and Communication 11, no. 10 (November 2, 2023): 1077–86. http://dx.doi.org/10.17762/ijritcc.v11i10.8627.
Full textAbstract:
This paper addresses the problem of predicting insulin dosage in diabetes patients using the PSO-LSTM, COA-LSTM, and LOA-LSTM algorithms. Accurate insulin dosage prediction is crucial in effectively managing Diabetes and maintaining blood glucose levels within the desired range. The study proposes a novel approach that combines particle swarm optimization (PSO) with the long short-term memory (LSTM) model. PSO is used to optimize the LSTM's parameters, enhancing its prediction capabilities specifically for insulin dosage. Additionally, two other techniques, COA-LSTM and LOA-LSTM, are introduced for comparison purposes. The algorithms utilize a dataset comprising relevant features such as past insulin dosages, blood glucose levels, carbohydrate intake, and physical activity. These features are fed into the PSO-LSTM, COA-LSTM, and LOA-LSTM models to predict the appropriate insulin dosage for future time points. The results demonstrate the effectiveness of the proposed PSO-LSTM algorithm in accurately predicting insulin dosage, surpassing the performance of COA-LSTM and LOA-LSTM. The PSO-LSTM model achieves a high level of accuracy, aiding in personalized and precise insulin administration for diabetes patients. By leveraging the power of PSO optimization and LSTM modeling, this research improves the accuracy and reliability of insulin dosage prediction. The findings highlight the potential of the PSO-LSTM algorithm as a valuable tool for healthcare professionals in optimizing diabetes management and enhancing patient outcomes.
20
Chen, Yiqing, Zongzhu Chen, Kang Li, Tiezhu Shi, Xiaohua Chen, Jinrui Lei, Tingtian Wu, et al. "Research of Carbon Emission Prediction: An Oscillatory Particle Swarm Optimization for Long Short-Term Memory." Processes 11, no. 10 (October 19, 2023): 3011. http://dx.doi.org/10.3390/pr11103011.
Full textAbstract:
Carbon emissions play a significant role in shaping social policy-making, industrial planning, and other critical areas. Recurrent neural networks (RNNs) serve as the major choice for carbon emission prediction. However, year-frequency carbon emission data always results in overfitting during RNN training. To address this issue, we propose a novel model that combines oscillatory particle swarm optimization (OPSO) with long short-term memory (LSTM). OPSO is employed to fine-tune the hyperparameters of LSTM, utilizing an oscillatory strategy to effectively mitigate overfitting and consequently improve the accuracy of the LSTM model. In validation tests, real data from Hainan Province, encompassing diverse dimensions such as gross domestic product, forest area, and ten other relevant factors, are used. Standard LSTM and PSO-LSTM are selected in the control group. The mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are used to evaluate the performance of these methods. In the test dataset, the MAE of OPSO-LSTM is 117.708, 65.72% better than LSTM and 29.48% better than PSO-LSTM. The RMSE of OPSO-LSTM is 149.939, 68.52% better than LSTM and 41.90% better than PSO-LSTM. The MAPE of OPSO-LSTM is 0.017, 65.31% better than LSTM, 29.17% better than PSO-LSTM. The experimental results prove that OPSO-LSTM can provide reliable predictions for carbon emissions.
21
Khataei Maragheh, Hamed, Farhad Soleimanian Gharehchopogh, Kambiz Majidzadeh, and Amin Babazadeh Sangar. "A New Hybrid Based on Long Short-Term Memory Network with Spotted Hyena Optimization Algorithm for Multi-Label Text Classification." Mathematics 10, no. 3 (February 2, 2022): 488. http://dx.doi.org/10.3390/math10030488.
Full textAbstract:
An essential work in natural language processing is the Multi-Label Text Classification (MLTC). The purpose of the MLTC is to assign multiple labels to each document. Traditional text classification methods, such as machine learning usually involve data scattering and failure to discover relationships between data. With the development of deep learning algorithms, many authors have used deep learning in MLTC. In this paper, a novel model called Spotted Hyena Optimizer (SHO)-Long Short-Term Memory (SHO-LSTM) for MLTC based on LSTM network and SHO algorithm is proposed. In the LSTM network, the Skip-gram method is used to embed words into the vector space. The new model uses the SHO algorithm to optimize the initial weight of the LSTM network. Adjusting the weight matrix in LSTM is a major challenge. If the weight of the neurons to be accurate, then the accuracy of the output will be higher. The SHO algorithm is a population-based meta-heuristic algorithm that works based on the mass hunting behavior of spotted hyenas. In this algorithm, each solution of the problem is coded as a hyena. Then the hyenas are approached to the optimal answer by following the hyena of the leader. Four datasets are used (RCV1-v2, EUR-Lex, Reuters-21578, and Bookmarks) to evaluate the proposed model. The assessments demonstrate that the proposed model has a higher accuracy rate than LSTM, Genetic Algorithm-LSTM (GA-LSTM), Particle Swarm Optimization-LSTM (PSO-LSTM), Artificial Bee Colony-LSTM (ABC-LSTM), Harmony Algorithm Search-LSTM (HAS-LSTM), and Differential Evolution-LSTM (DE-LSTM). The improvement of SHO-LSTM model accuracy for four datasets compared to LSTM is 7.52%, 7.12%, 1.92%, and 4.90%, respectively.
22
Pranolo, Andri, Xiaofeng Zhou, Yingchi Mao, Bambang Widi Pratolo, Aji Prasetya Wibawa, Agung Bella Putra Utama, Abdoul Fatakhou Ba, and Abdullahi Uwaisu Muhammad. "Exploring LSTM-based Attention Mechanisms with PSO and Grid Search under Different Normalization Techniques for Energy demands Time Series Forecasting." Knowledge Engineering and Data Science 7, no. 1 (April 16, 2024): 1. http://dx.doi.org/10.17977/um018v7i12024p1-12.
Full textAbstract:
Advanced analytical approaches are required to accurately forecast the energy sector's rising complexity and volume of time series data. This research aims to forecast the energy demand utilizing sophisticated Long Short-Term Memory (LSTM) configurations with Attention mechanisms (Att), Grid search, and Particle Swarm Optimization (PSO). In addition, the study also examines the influence of Min-Max and Z-Score normalization approaches in the preprocessing stage on the accuracy performances of the baselines and the proposed models. PSO and Grid Search techniques are used to select the best hyperparameters for LSTM models, while the attention mechanism selects the important input for the LSTM. The research compares the performance of baselines (LSTM, Grid-search-LSTM, and PSO-LSTM) and proposes models (Att-LSTM, Att-Grid-search-LSTM, and Att-PSO-LSTM) based on MAPE, RMSE, and R2 metrics into two scenarios normalization: Min-Max, and Z-Score. The results show that all models with Min-Max normalization have better MAPE, RMSE, and R2 than those with Z-Score. The best model performance is shown in Att-PSO-LSTM MAPE 3.1135, RMSE 0.0551, and R2 0.9233, followed by Att-Grid-search-LSTM, Att-LSTM, PSO-LSTM, Grid-search-LSTM, and LSTM. These findings emphasize the effectiveness of attention mechanisms in improving model predictions and the influence of normalization methods on model performance. This study's novel approach provides valuable insights into time series forecasting in energy demands.
23
Yang, Tianyi, Quanming Zhao, and Yifan Meng. "Ultra-short-term Photovoltaic Power Prediction Based on Multi-head ProbSparse Self-attention and Long Short-term Memory." Journal of Physics: Conference Series 2558, no. 1 (August 1, 2023): 012007. http://dx.doi.org/10.1088/1742-6596/2558/1/012007.
Full textAbstract:
Abstract To provide accurate predictions of photovoltaic (PV) power generation, an MHPSA-LSTM ultra-short-term multipoint PV power prediction model combining Multi-head ProbSparse self-attention (MHPSA) and long short-term memory (LSTM) network is posited. The MHPSA is first used to capture information dependencies at a distance. Secondly, the LSTM is used to enhance the local correlation. At last, a pooling layer is added after LSTM to reduce the parameters of the fully-connected layer and alleviate overfitting, thus improving the prediction accuracy. The MHPSA-LSTM model is validated on a PV plant at the Desert Knowledge Australia Solar Centre as an example, and the RMSE, MAE, and R2 of MHPSA-LSTM are 0.527, 0.264, and 0.917, respectively. MHPSA-LSTM has higher prediction accuracy compared with BP, LSTM, GRU, and CNN-LSTM.
24
Ismail, Mohammad Hafiz, and Tajul Rosli Razak. "Predicting the Kijang Emas Bullion Price using LSTM Networks." Journal of Entrepreneurship and Business 8, no. 2 (June 1, 2022): 11–18. http://dx.doi.org/10.17687/jeb.v8i2.849.
Full textAbstract:
This study investigates the potential of Deep Learning techniques, specifically LSTM networks, in forecasting Kijang Emas future value over a long period. Six LSTM models comprising of Simple LSTM, Bidirectional LSTM, and Stacked LSTM architecture were built and trained against a 15-year historical price data for Kijang Emas. The models’ performance was then measured against ARIMA (5,1,0) as a baseline reference and evaluated against the RAE, MSE and RMSE metric. The results revealed that LSTM networks models performed well in forecasting Kijang Emas price based on the test dataset where the average RMSE was between 49.9 to 50.3 while the Bidirectional LSTM was found to exhibit better performance as compared to the other LSTM models.
25
Ismail, Mohammad Hafiz, and Tajul Rosli Razak. "Predicting the Kijang Emas Bullion Price using LSTM Networks." Journal of Entrepreneurship and Business 8, no. 2 (December 31, 2020): 11–18. http://dx.doi.org/10.17687/jeb.0802.02.
Full textAbstract:
This study investigates the potential of Deep Learning techniques, specifically LSTM networks, in forecasting Kijang Emas future value over a long period. Six LSTM models comprising of Simple LSTM, Bidirectional LSTM, and Stacked LSTM architecture were built and trained against a 15-year historical price data for Kijang Emas. The models’ performance was then measured against ARIMA (5,1,0) as a baseline reference and evaluated against the RAE, MSE and RMSE metric. The results revealed that LSTM networks models performed well in forecasting Kijang Emas price based on the test dataset where the average RMSE was between 49.9 to 50.3 while the Bidirectional LSTM was found to exhibit better performance as compared to the other LSTM models.
26
Chen, Qili, Bofan Liang, and Jiuhe Wang. "A Comparative Study of LSTM and Phased LSTM for Gait Prediction." International Journal of Artificial Intelligence & Applications 10, no. 4 (July 31, 2019): 57–66. http://dx.doi.org/10.5121/ijaia.2019.10405.
Full text
27
Tajalsir, ohammed, Susana Mu˜noz Hern´andez, and Fatima Abdalbagi Mohammed. "ASERS-LSTM: Arabic Speech Emotion Recognition System Based on LSTM Model." Signal & Image Processing : An International Journal 13, no. 1 (February 28, 2022): 19–27. http://dx.doi.org/10.5121/sipij.2022.13102.
Full textAbstract:
The swift progress in the study field of human-computer interaction (HCI) causes to increase in the interest in systems for Speech emotion recognition (SER). The speech Emotion Recognition System is the system that can identify the emotional states of human beings from their voice. There are well works in Speech Emotion Recognition for different language but few researches have implemented for Arabic SER systems and that because of the shortage of available Arabic speech emotion databases. The most commonly considered languages for SER is English and other European and Asian languages. Several machine learning-based classifiers that have been used by researchers to distinguish emotional classes: SVMs, RFs, and the KNN algorithm, hidden Markov models (HMMs), MLPs and deep learning. In this paper we propose ASERS-LSTM model for Arabic Speech Emotion Recognition based on LSTM model. We extracted five features from the speech: Mel-Frequency Cepstral Coefficients (MFCC) features, chromagram, Melscaled spectrogram, spectral contrast and tonal centroid features (tonnetz). We evaluated our model using Arabic speech dataset named Basic Arabic Expressive Speech corpus (BAES-DB). In addition of that we also construct a DNN for classify the Emotion and compare the accuracy between LSTM and DNN model. For DNN the accuracy is 93.34% and for LSTM is 96.81%.
28
Liu, Jun, Tong Zhang, Guangjie Han, and Yu Gou. "TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction." Sensors 18, no. 11 (November 6, 2018): 3797. http://dx.doi.org/10.3390/s18113797.
Full textAbstract:
Changes in ocean temperature over time have important implications for marine ecosystems and global climate change. Marine temperature changes with time and has the features of closeness, period, and trend. This paper analyzes the temporal dependence of marine temperature variation at multiple depths and proposes a new ocean-temperature time-series prediction method based on the temporal dependence parameter matrix fusion of historical observation data. The Temporal Dependence-Based Long Short-Term Memory (LSTM) Networks for Marine Temperature Prediction (TD-LSTM) proves better than other methods while predicting sea-surface temperature (SST) by using Argo data. The performances were good at various depths and different regions.
29
Park, KyoungJong. "Prediction of Tier in Supply Chain Using LSTM and Conv1D-LSTM." Journal of Society of Korea Industrial and Systems Engineering 43, no. 2 (June 30, 2020): 120–25. http://dx.doi.org/10.11627/jkise.2020.43.2.120.
Full text
30
Wang, Hao. "Enhancing Stock Price Forecasting Accuracy Using LSTM and Bi-LSTM Models." ITM Web of Conferences 70 (2025): 04008. https://doi.org/10.1051/itmconf/20257004008.
Full textAbstract:
Accurately predicting stock price trends is of critical importance in the financial sector, enabling both individuals and enterprises to make informed and profitable decisions. In recent years, researchers have employed a variety’ of techniques to forecast stock market trends, yet the challenge of improving accuracy remains. This research introduces an innovative approach to predicting stock prices, employing two sophisticated models: Long Short-Tenn Memory (LSTM) and Bidirectional Long Short-Tenn Memory (Bi-LSTM) networks. Through rigorous analysis, the research demonstrates that, with proper hypeiparameter tuning. LSTM models are capable of making highly accurate predictions of future stock trends, a capability’ that is also exhibited by Bi-LSTM models. The study’ evaluates the models by’ measuring the Root Mean Square Error (RMSE) while varying key factors. Publicly available stock market information. such as the highest and lowest prices, and opening and closing prices, is utilized for evaluating model effectiveness. The results indicate that the Bi-LSTM model is superior to the LSTM model in terms of RMSE. making it a more effective methodology for stock price forecasting and aiding in strategic decision-making.
31
Jiang, Longquan, Xuan Sun, Francesco Mercaldo, and Antonella Santone. "DECAB-LSTM: Deep Contextualized Attentional Bidirectional LSTM for cancer hallmark classification." Knowledge-Based Systems 210 (December 2020): 106486. http://dx.doi.org/10.1016/j.knosys.2020.106486.
Full text
32
Roy, Sanjiban Sekhar, Ali Ismail Awad, Lamesgen Adugnaw Amare, Mabrie Tesfaye Erkihun, and Mohd Anas. "Multimodel Phishing URL Detection Using LSTM, Bidirectional LSTM, and GRU Models." Future Internet 14, no. 11 (November 21, 2022): 340. http://dx.doi.org/10.3390/fi14110340.
Full textAbstract:
In today’s world, phishing attacks are gradually increasing, resulting in individuals losing valuables, assets, personal information, etc., to unauthorized parties. In phishing, attackers craft malicious websites disguised as well-known, legitimate sites and send them to individuals to steal personal information and other related private details. Therefore, an efficient and accurate method is required to determine whether a website is malicious. Numerous methods have been proposed for detecting malicious uniform resource locators (URLs) using deep learning, machine learning, and other approaches. In this study, we have used malicious and benign URLs datasets and have proposed a detection mechanism for detecting malicious URLs using recurrent neural network models such as long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), and the gated recurrent unit (GRU). Experimental results have shown that the proposed mechanism achieved an accuracy of 97.0% for LSTM, 99.0% for Bi-LSTM, and 97.5% for GRU, respectively.
33
Riyadi, Willy, and Jasmir Jasmir. "Performance Prediction of Airport Traffic Using LSTM and CNN-LSTM Models." MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 22, no. 3 (July 28, 2023): 627–38. http://dx.doi.org/10.30812/matrik.v22i3.3032.
Full textAbstract:
During the COVID-19 pandemic, airports faced a significant drop in passenger numbers, impacting the vital hub of the aircraft transportation industry. This study aimed to evaluate whether Long Short-Term Memory Network (LSTM) and Convolutional Neural Network - Long Short-Term Memory Network (CNN-LSTM) offer more accurate predictions for airport traffic during the COVID-19 pandemic from March to December 2020. The studies involved data filtering, applying min-max scaling, and dividing the dataset into 80% training and 20% testing sets. Parameter adjustment was performed with different optimizers such as RMSProp, Stochastic Gradient Descent (SGD), Adam, Nadam, and Adamax. Performance evaluation uses metrics that include Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and R-squared (R2). The best LSTM model achieved an impressive MAPE score of 0.0932, while the CNN-LSTM model had a slightly higher score of 0.0960. In particular, the inclusion of a balanced data set representing a percentage of the base period for each airport had a significant impact on improving prediction accuracy. This research contributes to providing stakeholders with valuable insights into the effectiveness of predicting airport traffic patterns during these unprecedented times.
34
Yadav, Hemant, and Amit Thakkar. "NOA-LSTM: An efficient LSTM cell architecture for time series forecasting." Expert Systems with Applications 238 (March 2024): 122333. http://dx.doi.org/10.1016/j.eswa.2023.122333.
Full text
35
Li, Jianyao. "A Comparative Study of LSTM Variants in Prediction for Tesla’s Stock Price." BCP Business & Management 34 (December 14, 2022): 30–38. http://dx.doi.org/10.54691/bcpbm.v34i.2861.
Full textAbstract:
Long short-term memory (LSTM) is widely used in the stock market to train the prediction model and forecast future stock prices. Applying the LSTM method to research may incur some problems and facilitate the improvement of the method. Therefore, many LSTM variants are put forward under different circumstances. This paper surveys four LSTM variants, including Vanilla, Stacked, Bi-directional, and CNN LSTM on two different data sets regarding Tesla's stock price. Two data sets mentioned in this paper represent different stock types. To be more specific, data set 1 refers to stocks with a single long-term trend, while data set 2 can be seen as an example of stocks with more complexity. The result shows that the Vanilla LSTM reaches the highest prediction accuracy on the data set without any irregular shift in the long-term trend. CNN LSTM also provides decent predictions for the stock price. Otherwise, the Stacked LSTM performs the best for stock prediction. Bi-LSTM and CNN LSTM are also suitable for stock forecasting in more complicated situations. The change in preference for model selection proves that a company's operation situation and market circumstances also influence the prediction performance of LSTM variants.
36
Chen, Xingyu, Haijian Bai, Heng Ding, Jianshe Gao, and Wenjuan Huang. "A Safety Control Method of Car-Following Trajectory Planning Based on LSTM." Promet - Traffic&Transportation 35, no. 3 (June 28, 2023): 380–94. http://dx.doi.org/10.7307/ptt.v35i3.118.
Full textAbstract:
This paper focuses on the potential safety hazards of collision in car-following behaviour generated by deep learning models. Based on an intelligent LSTM model, combined with a Gipps model of safe collision avoidance, a new, Gipps-LSTM model is constructed, which can not only learn the intelligent behaviour of people but also ensure the safety of vehicles. The idea of the Gipps-LSTM model combination is as follows: the concept of a potential collision point (PCP) is introduced, and the LSTM model or Gipps model is controlled and started through a risk judgment algorithm. Dataset 1 and dataset 2 are used to train and simulate the LSTM model and Gipps-LSTM model. The simulation results show that the Gipps-LSTM can solve the problem of partial trajectory collision in the LSTM model simulation. Moreover, the risk level of all trajectories is lower than that of the LSTM model. The safety and stability of the model are verified by multi-vehicle loop simulation and multi-vehicle linear simulation. Compared with the LSTM model, the safety of the Gipps-LSTM model is improved by 42.02%, and the convergence time is reduced by 25 seconds.
37
Lu, Yi-Xiang, Xiao-Bo Jin, Dong-Jie Liu, Xin-Chang Zhang, and Guang-Gang Geng. "Anomaly Detection Using Multiscale C-LSTM for Univariate Time-Series." Security and Communication Networks 2023 (January 23, 2023): 1–12. http://dx.doi.org/10.1155/2023/6597623.
Full textAbstract:
Computers generate network traffic data when people go online, and devices generate sensor data when they communicate with each other. When events such as network intrusion or equipment failure occur, the corresponding time-series will show abnormal trends. By detecting these time-series, anomalous events can be detected instantly, ensuring the security of network communication. However, existing time-series anomaly detection methods are difficult to deal with sequences with different degrees of correlation in complex scenes. In this paper, we propose three multiscale C-LSTM deep learning models to efficiently detect abnormal time-series: independent multiscale C-LSTM (IMC-LSTM), where each LSTM has an independent scale CNN; combined multiscale C-LSTM (CMC-LSTM), that is, the output of multiple scales of CNN is combined as an LSTM input; and shared multiscale C-LSTM (SMC-LSTM), that is, the output of multiple scales of CNN shares an LSTM model. Comparative experiments on multiple data sets show that the proposed three models have achieved excellent performance on the famous Yahoo Webscope S5 dataset and Numenta Anomaly Benchmark dataset, even better than the existing C-LSTM based latest model.
38
Han, Shipeng, Zhen Meng, Xingcheng Zhang, and Yuepeng Yan. "Hybrid Deep Recurrent Neural Networks for Noise Reduction of MEMS-IMU with Static and Dynamic Conditions." Micromachines 12, no. 2 (February 20, 2021): 214. http://dx.doi.org/10.3390/mi12020214.
Full textAbstract:
Micro-electro-mechanical system inertial measurement unit (MEMS-IMU), a core component in many navigation systems, directly determines the accuracy of inertial navigation system; however, MEMS-IMU system is often affected by various factors such as environmental noise, electronic noise, mechanical noise and manufacturing error. These can seriously affect the application of MEMS-IMU used in different fields. Focus has been on MEMS gyro since it is an essential and, yet, complex sensor in MEMS-IMU which is very sensitive to noises and errors from the random sources. In this study, recurrent neural networks are hybridized in four different ways for noise reduction and accuracy improvement in MEMS gyro. These are two-layer homogenous recurrent networks built on long short term memory (LSTM-LSTM) and gated recurrent unit (GRU-GRU), respectively; and another two-layer but heterogeneous deep networks built on long short term memory-gated recurrent unit (LSTM-GRU) and a gated recurrent unit-long short term memory (GRU-LSTM). Practical implementation with static and dynamic experiments was carried out for a custom MEMS-IMU to validate the proposed networks, and the results show that GRU-LSTM seems to be overfitting large amount data testing for three-dimensional axis gyro in the static test. However, for X-axis and Y-axis gyro, LSTM-GRU had the best noise reduction effect with over 90% improvement in the three axes. For Z-axis gyroscope, LSTM-GRU performed better than LSTM-LSTM and GRU-GRU in quantization noise and angular random walk, while LSTM-LSTM shows better improvement than both GRU-GRU and LSTM-GRU networks in terms of zero bias stability. In the dynamic experiments, the Hilbert spectrum carried out revealed that time-frequency energy of the LSTM-LSTM, GRU-GRU, and GRU-LSTM denoising are higher compared to LSTM-GRU in terms of the whole frequency domain. Similarly, Allan variance analysis also shows that LSTM-GRU has a better denoising effect than the other networks in the dynamic experiments. Overall, the experimental results demonstrate the effectiveness of deep learning algorithms in MEMS gyro noise reduction, among which LSTM-GRU network shows the best noise reduction effect and great potential for application in the MEMS gyroscope area.
39
Poetra, Chandra Kirana, Syafrial Fachri Pane, and Nuraini Siti Fatonah. "Meningkatkan Akurasi Long-Short Term Memory (LSTM) pada Analisis Sentimen Vaksin Covid-19 di Twitter dengan Glove." Jurnal Telematika 16, no. 2 (January 19, 2022): 85–90. http://dx.doi.org/10.61769/telematika.v16i2.400.
Full textAbstract:
Covid-19 began to appear in early 2020. The spread of this outbreak is often discussed on Twitter, especially about vaccine procurement. For this reason, it is necessary to have a sentiment analysis on the opinion on vaccine procurement. Sentiment analysis will use the Long Short Term Memory (LSTM) method. However, the level of accuracy of LSTM itself is not accurate enough compared to another method, such as Bi-LSTM. Therefore, it is necessary to optimize so that the LSTM model can predict accurately and compete with the accuracy of Bi-LSTM. Optimization is done by using the Glove method. The Glove method works by counting the occurrences of one word with another and then converting it to a vector. Words that often appear together will have vector values that are close to each other. This vector value is then used as a reference and inserted into the embedding layer of the LSTM model. The application of LSTM coupled with the Glove method resulted in an accuracy of 89% (87% for LSTM and 88% for Bi-LSTM). In this study, the Glove method could increase the accuracy of the used model by 2%. Covid-19 mulai muncul di awal tahun 2020. Penyebaran wabah ini sering dibicarakan di Twitter, terutama tentang pengadaan vaksin. Untuk itu, perlu adanya analisis sentimen terhadap opini pengadaan vaksin. Analisis sentimen akan menggunakan metode Long Short Term Memory (LSTM). Namun, tingkat akurasi LSTM sendiri belum cukup akurat dibandingkan dengan metode lainnya, seperti Bi-LSTM. Oleh karena itu, perlu dilakukan optimalisasi agar model LSTM dapat memprediksi secara akurat dan dapat menyaingi akurasi Bi-LSTM. Optimalisasi dilakukan dengan menggunakan metode Glove. Metode Glove bekerja dengan menghitung kemunculan satu kata dengan kata lainnya lalu mengonversinya menjadi vektor. Kata yang sering muncul secara bersamaan akan memiliki nilai vektor yang saling mendekati. Nilai vektor ini kemudian dijadikan referensi dan dimasukkan ke lapisan embedding pada model LSTM. Penerapan LSTM yang ditambah dengan metode Glove menghasilkan akurasi sebesar 89% (87% untuk LSTM dan 88% untuk Bi-LSTM). Dalam penelitian ini penerapan metode Glove dapat meningkatkan akurasi model sebesar 2%.
40
Zhao, Ziquan, and Jing Bai. "Ultra-Short-Term Wind Power Forecasting Based on the MSADBO-LSTM Model." Energies 17, no. 22 (November 14, 2024): 5689. http://dx.doi.org/10.3390/en17225689.
Full textAbstract:
To address the challenges of the strong randomness and intermittency of wind power generation that affect wind power grid integration, power system scheduling, and the safe and stable operation of the system, an improved Dung Beetle Optimization Algorithm (MSADBO) is proposed to optimize the hyperparameters of the Long Short-Term Memory neural network (LSTM) for ultra-short-term wind power forecasting. By applying Bernoulli mapping for population initialization, the model’s sensitivity to wind power fluctuations is reduced, which accelerates the algorithm’s convergence speed. Incorporating an improved Sine Algorithm (MSA) into the forecasting model for this nonlinear problem significantly improves the position update strategy of the Dung Beetle Optimization Algorithm (DBO), which tends to be overly random and prone to local optima. This enhancement boosts the algorithm’s exploration capabilities both locally and globally, improving the rapid responsiveness of ultra-short-term wind power forecasting. Furthermore, an adaptive Gaussian–Cauchy mixture perturbation is introduced to interfere with individuals, increasing population diversity, escaping local optima, and enabling the continued exploration of other areas of the solution space until the global optimum is ultimately found. By optimizing three hyperparameters of the LSTM using the MSADBO algorithm, the prediction accuracy of the model is greatly enhanced. After simulation validation, taking winter as an example, the MSADBO-LSTM predictive model achieved a reduction in the MAE metric of 40.6% compared to LSTM, 20.12% compared to PSO-LSTM, and 3.82% compared to DBO-LSTM. The MSE decreased by 45.4% compared to LSTM, 40.78% compared to PSO-LSTM, and 16.62% compared to DBO-LSTM. The RMSE was reduced by 26.11% compared to LSTM, 23.05% compared to PSO-LSTM, and 8.69% compared to DBO-LSTM. Finally, the MAPE declined by 79.83% compared to LSTM, 31.88% compared to PSO-LSTM, and 29.62% compared to DBO-LSTM. This indicates that the predictive model can effectively enhance the accuracy of wind power forecasting.
41
Yu, Yong, Xiaosheng Si, Changhua Hu, and Jianxun Zhang. "A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures." Neural Computation 31, no. 7 (July 2019): 1235–70. http://dx.doi.org/10.1162/neco_a_01199.
Full textAbstract:
Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.
42
Roy, Dilip Kumar, Tapash Kumar Sarkar, Sheikh Shamshul Alam Kamar, Torsha Goswami, Md Abdul Muktadir, Hussein M. Al-Ghobari, Abed Alataway, Ahmed Z. Dewidar, Ahmed A. El-Shafei, and Mohamed A. Mattar. "Daily Prediction and Multi-Step Forward Forecasting of Reference Evapotranspiration Using LSTM and Bi-LSTM Models." Agronomy 12, no. 3 (February 27, 2022): 594. http://dx.doi.org/10.3390/agronomy12030594.
Full textAbstract:
Precise forecasting of reference evapotranspiration (ET0) is one of the critical initial steps in determining crop water requirements, which contributes to the reliable management and long-term planning of the world’s scarce water sources. This study provides daily prediction and multi-step forward forecasting of ET0 utilizing a long short-term memory network (LSTM) and a bi-directional LSTM (Bi-LSTM) model. For daily predictions, the LSTM model’s accuracy was compared to that of other artificial intelligence-based models commonly used in ET0 forecasting, including support vector regression (SVR), M5 model tree (M5Tree), multivariate adaptive regression spline (MARS), probabilistic linear regression (PLR), adaptive neuro-fuzzy inference system (ANFIS), and Gaussian process regression (GPR). The LSTM model outperformed the other models in a comparison based on Shannon’s entropy-based decision theory, while the M5 tree and PLR models proved to be the lowest performers. Prior to performing a multi-step-ahead forecasting, ANFIS, sequence-to-sequence regression LSTM network (SSR-LSTM), LSTM, and Bi-LSTM approaches were used for one-step-ahead forecasting utilizing the past values of the ET0 time series. The results showed that the Bi-LSTM model outperformed other models and that the sequence of models in ascending order in terms of accuracies was Bi-LSTM > SSR-LSTM > ANFIS > LSTM. The Bi-LSTM model provided multi-step (5 day)-ahead ET0 forecasting in the next step. According to the results, the Bi-LSTM provided reasonably accurate and acceptable forecasting of multi-step-forward ET0 with relatively lower levels of forecasting errors. In the final step, the generalization capability of the proposed best models (LSTM for daily predictions and Bi-LSTM for multi-step-ahead forecasting) was evaluated on new unseen data obtained from a test station, Ishurdi. The model’s performance was assessed on three distinct datasets (the entire dataset and the first and the second halves of the entire dataset) derived from the test dataset between 1 January 2015 and 31 December 2020. The results indicated that the deep learning techniques (LSTM and Bi-LSTM) achieved equally good performances as the training station dataset, for which the models were developed. The research outcomes demonstrated the ability of the developed deep learning models to generalize the prediction capabilities outside the training station.
43
Kostyra, Tomasz Piotr. "Forecasting the yield curve for Poland with the PCA and machine learning." Bank i Kredyt Vol. 55, No. 4 (August 31, 2024): 459–78. http://dx.doi.org/10.5604/01.3001.0054.8580.
Full textAbstract:
The article examines the application of the Principal Component Analysis (PCA) and machine learning method, the Long Short-Term Memory (LSTM), in the prediction of the yield curve for Poland. The PCA was applied to decompose the yield curve, forecast its components using the LSTM, and obtain the yield curve predictions upon recomposition. The results from the PCA-LSTM model were compared to predictions generated directly by the LSTM model, simple autoregression and random walk, which serves as a benchmark. Overall, LSTM predictions are the most accurate with PCA-LSTM being a close second, nonetheless PCA-LSTM is more accurate in short-term forecasting of interest rates at long maturities. Both methods outperform the benchmark, while autoregression usually underperforms. For these reasons, the PCA-LSTM as well as the LSTM can be useful in interest rate management or building trading strategies. The PCA-LSTM has the advantage that it can focus on particular components of the yield curve, such as variability of the yield curve’s level or steepness.
44
Xiong, Ying, Xue Shi, Shuai Chen, Dehuan Jiang, Buzhou Tang, Xiaolong Wang, Qingcai Chen, and Jun Yan. "Cohort selection for clinical trials using hierarchical neural network." Journal of the American Medical Informatics Association 26, no. 11 (July 15, 2019): 1203–8. http://dx.doi.org/10.1093/jamia/ocz099.
Full textAbstract:
Abstract Objective Cohort selection for clinical trials is a key step for clinical research. We proposed a hierarchical neural network to determine whether a patient satisfied selection criteria or not. Materials and Methods We designed a hierarchical neural network (denoted as CNN-Highway-LSTM or LSTM-Highway-LSTM) for the track 1 of the national natural language processing (NLP) clinical challenge (n2c2) on cohort selection for clinical trials in 2018. The neural network is composed of 5 components: (1) sentence representation using convolutional neural network (CNN) or long short-term memory (LSTM) network; (2) a highway network to adjust information flow; (3) a self-attention neural network to reweight sentences; (4) document representation using LSTM, which takes sentence representations in chronological order as input; (5) a fully connected neural network to determine whether each criterion is met or not. We compared the proposed method with its variants, including the methods only using the first component to represent documents directly and the fully connected neural network for classification (denoted as CNN-only or LSTM-only) and the methods without using the highway network (denoted as CNN-LSTM or LSTM-LSTM). The performance of all methods was measured by micro-averaged precision, recall, and F1 score. Results The micro-averaged F1 scores of CNN-only, LSTM-only, CNN-LSTM, LSTM-LSTM, CNN-Highway-LSTM, and LSTM-Highway-LSTM were 85.24%, 84.25%, 87.27%, 88.68%, 88.48%, and 90.21%, respectively. The highest micro-averaged F1 score is higher than our submitted 1 of 88.55%, which is 1 of the top-ranked results in the challenge. The results indicate that the proposed method is effective for cohort selection for clinical trials. Discussion Although the proposed method achieved promising results, some mistakes were caused by word ambiguity, negation, number analysis and incomplete dictionary. Moreover, imbalanced data was another challenge that needs to be tackled in the future. Conclusion In this article, we proposed a hierarchical neural network for cohort selection. Experimental results show that this method is good at selecting cohort.
45
Liang, Bushun, Siye Wang, Yeqin Huang, Yiling Liu, and Linpeng Ma. "F-LSTM: FPGA-Based Heterogeneous Computing Framework for Deploying LSTM-Based Algorithms." Electronics 12, no. 5 (February 26, 2023): 1139. http://dx.doi.org/10.3390/electronics12051139.
Full textAbstract:
Long Short-Term Memory (LSTM) networks have been widely used to solve sequence modeling problems. For researchers, using LSTM networks as the core and combining it with pre-processing and post-processing to build complete algorithms is a general solution for solving sequence problems. As an ideal hardware platform for LSTM network inference, Field Programmable Gate Array (FPGA) with low power consumption and low latency characteristics can accelerate the execution of algorithms. However, implementing LSTM networks on FPGA requires specialized hardware and software knowledge and optimization skills, which is a challenge for researchers. To reduce the difficulty of deploying LSTM networks on FPGAs, we propose F-LSTM, an FPGA-based framework for heterogeneous computing. With the help of F-LSTM, researchers can quickly deploy LSTM-based algorithms to heterogeneous computing platforms. FPGA in the platform will automatically take up the computation of the LSTM network in the algorithm. At the same time, the CPU will perform the pre-processing and post-processing in the algorithm. To better design the algorithm, compress the model, and deploy the algorithm, we also propose a framework based on F-LSTM. The framework also integrates Pytorch to increase usability. Experimental results on sentiment analysis tasks show that deploying algorithms to the F-LSTM hardware platform can achieve a 1.8× performance improvement and a 5.4× energy efficiency improvement compared to GPU. Experimental results also validate the need to build heterogeneous computing systems. In conclusion, our work reduces the difficulty of deploying LSTM on FPGAs while guaranteeing algorithm performance compared to traditional work.
46
Pal, Subarno, Soumadip Ghosh, and Amitava Nag. "Sentiment Analysis in the Light of LSTM Recurrent Neural Networks." International Journal of Synthetic Emotions 9, no. 1 (January 2018): 33–39. http://dx.doi.org/10.4018/ijse.2018010103.
Full textAbstract:
Long short-term memory (LSTM) is a special type of recurrent neural network (RNN) architecture that was designed over simple RNNs for modeling temporal sequences and their long-range dependencies more accurately. In this article, the authors work with different types of LSTM architectures for sentiment analysis of movie reviews. It has been showed that LSTM RNNs are more effective than deep neural networks and conventional RNNs for sentiment analysis. Here, the authors explore different architectures associated with LSTM models to study their relative performance on sentiment analysis. A simple LSTM is first constructed and its performance is studied. On subsequent stages, the LSTM layer is stacked one upon another which shows an increase in accuracy. Later the LSTM layers were made bidirectional to convey data both forward and backward in the network. The authors hereby show that a layered deep LSTM with bidirectional connections has better performance in terms of accuracy compared to the simpler versions of LSTM used here.
47
Bo, Yanping, Chunlei Zhang, Xiaoyu Fang, Yidi Sun, Changjiang Li, Meiyun An, Yun Peng, and Yixin Lu. "Application of HP-LSTM Models for Groundwater Level Prediction in Karst Regions: A Case Study in Qingzhen City." Water 17, no. 3 (January 27, 2025): 362. https://doi.org/10.3390/w17030362.
Full textAbstract:
Groundwater serves as an indispensable global resource, essential for agriculture, industry, and the urban water supply. Predicting the groundwater level in karst regions presents notable challenges due to the intricate geological structures and fluctuating climatic conditions. This study examines Qingzhen City, China, introducing an innovative hybrid model, the Hodrick–Prescott (HP) filter–Long Short-Term Memory (LSTM) network (HP-LSTM), which integrates the HP filter with the LSTM network to enhance the precision of groundwater level forecasting. By attenuating short-term noise, the HP-LSTM model improves the long-term trend prediction accuracy. Findings reveal that the HP-LSTM model significantly outperformed the conventional LSTM, attaining R2 values of 0.99, 0.96, and 0.98 on the training, validation, and test datasets, respectively, in contrast to LSTM values of 0.92, 0.76, and 0.95. The HP-LSTM model achieved an RMSE of 0.0276 and a MAPE of 2.92% on the test set, significantly outperforming the LSTM model (RMSE: 0.1149; MAPE: 9.14%) in capturing long-term patterns and reducing short-term fluctuations. While the LSTM model is effective at modeling short-term dynamics, it is more prone to noise, resulting in greater prediction errors. Overall, the HP-LSTM model demonstrates superior robustness for long-term groundwater level prediction, whereas the LSTM model may be better suited for scenarios requiring rapid adaptation to short-term variations. Selecting an appropriate model tailored to specific predictive needs can thus optimize groundwater management strategies.
48
Yang, Guangyu, Quanjie Zhu, Dacang Wang, Yu Feng, Xuexi Chen, and Qingsong Li. "Method and Validation of Coal Mine Gas Concentration Prediction by Integrating PSO Algorithm and LSTM Network." Processes 12, no. 5 (April 28, 2024): 898. http://dx.doi.org/10.3390/pr12050898.
Full textAbstract:
: Gas concentration monitoring is an effective method for predicting gas disasters in mines. In response to the shortcomings of low efficiency and accuracy in conventional gas concentration prediction, a new method for gas concentration prediction based on Particle Swarm Optimization and Long Short-Term Memory Network (PSO-LSTM) is proposed. First, the principle of the PSO-LSTM fusion model is analyzed, and the PSO-LSTM gas concentration analysis and prediction model is constructed. Second, the gas concentration data are normalized and preprocessed. The PSO algorithm is utilized to optimize the training set of the LSTM model, facilitating the selection of the training data set for the LSTM model. Finally, the MAE, RMSE, and coefficient of determination R2 evaluation indicators are proposed to verify and analyze the prediction results. Gas concentration prediction comparison and verification research was conducted using gas concentration data measured in a mine as the sample data. The experimental results show that: (1) The maximum RMSE predicted using the PSO-LSTM model is 0.0029, and the minimum RMSE is 0.0010 when the sample size changes. This verifies the reliability of the prediction effect of the PSO-LSTM model. (2) The predictive performance of all models ranks as follows: PSO-LSTM > SVR-LSTM > LSTM > PSO-GRU. Comparative analysis with the LSTM model demonstrates that the PSO-LSTM model is more effective in predicting gas concentration, further confirming the superiority of this model in gas concentration prediction.
49
Yudi Widhiyasana, Transmissia Semiawan, Ilham Gibran Achmad Mudzakir, and Muhammad Randi Noor. "Penerapan Convolutional Long Short-Term Memory untuk Klasifikasi Teks Berita Bahasa Indonesia." Jurnal Nasional Teknik Elektro dan Teknologi Informasi 10, no. 4 (November 29, 2021): 354–61. http://dx.doi.org/10.22146/jnteti.v10i4.2438.
Full textAbstract:
Klasifikasi teks saat ini telah menjadi sebuah bidang yang banyak diteliti, khususnya terkait Natural Language Processing (NLP). Terdapat banyak metode yang dapat dimanfaatkan untuk melakukan klasifikasi teks, salah satunya adalah metode deep learning. RNN, CNN, dan LSTM merupakan beberapa metode deep learning yang umum digunakan untuk mengklasifikasikan teks. Makalah ini bertujuan menganalisis penerapan kombinasi dua buah metode deep learning, yaitu CNN dan LSTM (C-LSTM). Kombinasi kedua metode tersebut dimanfaatkan untuk melakukan klasifikasi teks berita bahasa Indonesia. Data yang digunakan adalah teks berita bahasa Indonesia yang dikumpulkan dari portal-portal berita berbahasa Indonesia. Data yang dikumpulkan dikelompokkan menjadi tiga kategori berita berdasarkan lingkupnya, yaitu “Nasional”, “Internasional”, dan “Regional”. Dalam makalah ini dilakukan eksperimen pada tiga buah variabel penelitian, yaitu jumlah dokumen, ukuran batch, dan nilai learning rate dari C-LSTM yang dibangun. Hasil eksperimen menunjukkan bahwa nilai F1-score yang diperoleh dari hasil klasifikasi menggunakan metode C-LSTM adalah sebesar 93,27%. Nilai F1-score yang dihasilkan oleh metode C-LSTM lebih besar dibandingkan dengan CNN, dengan nilai 89,85%, dan LSTM, dengan nilai 90,87%. Dengan demikian, dapat disimpulkan bahwa kombinasi dua metode deep learning, yaitu CNN dan LSTM (C-LSTM),memiliki kinerja yang lebih baik dibandingkan dengan CNN dan LSTM.
50
Zhou, Shuyi, Brandon J. Bethel, Wenjin Sun, Yang Zhao, Wenhong Xie, and Changming Dong. "Improving Significant Wave Height Forecasts Using a Joint Empirical Mode Decomposition–Long Short-Term Memory Network." Journal of Marine Science and Engineering 9, no. 7 (July 5, 2021): 744. http://dx.doi.org/10.3390/jmse9070744.
Full textAbstract:
Wave forecasts, though integral to ocean engineering activities, are often conducted using computationally expensive and time-consuming numerical models with accuracies that are blunted by numerical-model-inherent limitations. Additionally, artificial neural networks, though significantly computationally cheaper, faster, and effective, also experience difficulties with nonlinearities in the wave generation and evolution processes. To solve both problems, this study employs and couples empirical mode decomposition (EMD) and a long short-term memory (LSTM) network in a joint model for significant wave height forecasting, a method widely used in wind speed forecasting, but not yet for wave heights. Following a comparative analysis, the results demonstrate that EMD-LSTM significantly outperforms LSTM at every forecast horizon (3, 6, 12, 24, 48, and 72 h), considerably improving forecasting accuracy, especially for forecasts exceeding 24 h. Additionally, EMD-LSTM responds faster than LSTM to large waves. An error analysis comparing LSTM and EMD-LSTM demonstrates that LSTM errors are more systematic. This study also identifies that LSTM is not able to adequately predict high-frequency significant wave height intrinsic mode functions, which leaves room for further improvements.