Siga este link para ver outros tipos de publicações sobre o tema: LSTM Temporel.
Artigos de revistas sobre o tema "LSTM Temporel"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "LSTM Temporel".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja os artigos de revistas das mais diversas áreas científicas e compile uma bibliografia correta.
1
Liu, Jun, Tong Zhang, Guangjie Han e Yu Gou. "TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature Prediction". Sensors 18, n.º 11 (6 de novembro de 2018): 3797. http://dx.doi.org/10.3390/s18113797.
Texto completo da fonteResumo:
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.
2
Baddar, Wissam J., e Yong Man Ro. "Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition". Proceedings of the AAAI Conference on Artificial Intelligence 33 (17 de julho de 2019): 3215–23. http://dx.doi.org/10.1609/aaai.v33i01.33013215.
Texto completo da fonteResumo:
Spatio-temporal feature encoding is essential for encoding the dynamics in video sequences. Recurrent neural networks, particularly long short-term memory (LSTM) units, have been popular as an efficient tool for encoding spatio-temporal features in sequences. In this work, we investigate the effect of mode variations on the encoded spatio-temporal features using LSTMs. We show that the LSTM retains information related to the mode variation in the sequence, which is irrelevant to the task at hand (e.g. classification facial expressions). Actually, the LSTM forget mechanism is not robust enough to mode variations and preserves information that could negatively affect the encoded spatio-temporal features. We propose the mode variational LSTM to encode spatio-temporal features robust to unseen modes of variation. The mode variational LSTM modifies the original LSTM structure by adding an additional cell state that focuses on encoding the mode variation in the input sequence. To efficiently regulate what features should be stored in the additional cell state, additional gating functionality is also introduced. The effectiveness of the proposed mode variational LSTM is verified using the facial expression recognition task. Comparative experiments on publicly available datasets verified that the proposed mode variational LSTM outperforms existing methods. Moreover, a new dynamic facial expression dataset with different modes of variation, including various modes like pose and illumination variations, was collected to comprehensively evaluate the proposed mode variational LSTM. Experimental results verified that the proposed mode variational LSTM encodes spatio-temporal features robust to unseen modes of variation.
3
D, Usha, Jesmalar L, Noorbasha Nagoor Meeravali, Mihirkumar B.Suthar, Rajeswari J, Pothumarthi Sridevi e Vengatesh T. "Enhanced Dengue Fever Prediction in India through Deep Learning with Spatially Attentive LSTMs". Cuestiones de Fisioterapia 54, n.º 2 (10 de janeiro de 2025): 3804–12. https://doi.org/10.48047/v3dm7y10.
Texto completo da fonteResumo:
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.
4
Tao, Hong, Yue Deng, Yunqiu Xiang e Long Liu. "Performance of long short-term memory networks in predicting athlete injury risk". Journal of Computational Methods in Sciences and Engineering 24, n.º 4-5 (14 de agosto de 2024): 3155–71. http://dx.doi.org/10.3233/jcm-247563.
Texto completo da fonteResumo:
Conventional approaches to forecasting the risk of athlete injuries are constrained by their narrow scope in feature extraction, often failing to adequately account for temporal dependencies and the effects of long-term memory. This paper enhances the Long Short-Term Memory (LSTM) network, specifically tailoring it to harness temporal data pertaining to athletes. This advancement significantly boosts the accuracy and effectiveness of predicting the risk of injuries among athletes. The network structure of the LSTM model was improved, and the collected data was converted into the temporal data form of the LSTM input. Finally, historical data labeled with injury labels were used to train the improved LSTM model, and gradient descent iterative optimization was used to adjust the parameters of the improved LSTM model. The improved LSTM network model was compared with the traditional athlete injury risk prediction model in terms of performance. The incorporation of enhanced LSTM networks for the analysis of temporal athlete data holds significant research significance. This approach has the potential to substantially enhance the accuracy and effectiveness of athlete injury risk prediction, contributing to a deeper understanding of the temporal dynamics influencing injuries in sports.
5
Majeed, Mokhalad A., Helmi Zulhaidi Mohd Shafri, Zed Zulkafli e 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, n.º 5 (25 de fevereiro de 2023): 4130. http://dx.doi.org/10.3390/ijerph20054130.
Texto completo da fonteResumo:
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.
6
Lin, Fei, Yudi Xu, Yang Yang e Hong Ma. "A Spatial-Temporal Hybrid Model for Short-Term Traffic Prediction". Mathematical Problems in Engineering 2019 (14 de janeiro de 2019): 1–12. http://dx.doi.org/10.1155/2019/4858546.
Texto completo da fonteResumo:
Accurate and timely short-term traffic prediction is important for Intelligent Transportation System (ITS) to solve the traffic problem. This paper presents a hybrid model called SpAE-LSTM. This model considers the temporal and spatial features of traffic flow and it consists of sparse autoencoder and long short-term memory (LSTM) network based on memory units. Sparse autoencoder extracts the spatial features within the spatial-temporal matrix via full connected layers. It cooperates with the LSTM network to capture the spatial-temporal features of traffic flow evolution and make prediction. To validate the performance of the SpAE-LSTM, we implement it on the real-world traffic data from Qingyang District of Chengdu city, China, and compare it with advanced traffic prediction models, such as models only based on LSTM or SAE. The results demonstrate that the proposed model reduces the mean absolute percent error by more than 15%. The robustness of the proposed model is also validated and the mean absolute percent error on more than 86% road segments is below 20%. This research provides strong evidence suggesting that the proposed SpAE-LSTM effectively captures the spatial-temporal features of the traffic flow and achieves promising results.
7
Chen, Wantong, Hailong Wu e Shiyu Ren. "CM-LSTM Based Spectrum Sensing". Sensors 22, n.º 6 (16 de março de 2022): 2286. http://dx.doi.org/10.3390/s22062286.
Texto completo da fonteResumo:
This paper presents spectrum sensing as a classification problem, and uses a spectrum-sensing algorithm based on a signal covariance matrix and long short-term memory network (CM-LSTM). We jointly exploited the spatial cross-correlation of multiple signals received by the antenna array and the temporal autocorrelation of single signals; we used the long short-term memory network (LSTM), which is good at extracting temporal correlation features, as the classification model; we then input the covariance matrix of the signals received by the array into the LSTM classification model to achieve the fusion learning of spatial correlation features and temporal correlation features of the signals, thus significantly improving the performance of spectrum sensing. Simulation analysis shows that the CM-LSTM-based spectrum-sensing algorithm shows better performance compared with support vector machine (SVM), gradient boosting machine (GBM), random forest (RF), and energy detection (ED) algorithm-based spectrum-sensing algorithms for different signal-to-noise ratios (SNRs) and different numbers of secondary users (SUs). Among them, SVM is a classical machine-learning algorithm, GBM and RF are two integrated learning methods with better generalization capability, and ED is a classical, traditional, and spectrum-sensing algorithm.
8
Tang, Qicheng, Mengning Yang e Ying Yang. "ST-LSTM: A Deep Learning Approach Combined Spatio-Temporal Features for Short-Term Forecast in Rail Transit". Journal of Advanced Transportation 2019 (6 de fevereiro de 2019): 1–8. http://dx.doi.org/10.1155/2019/8392592.
Texto completo da fonteResumo:
The short-term forecast of rail transit is one of the most essential issues in urban intelligent transportation system (ITS). Accurate forecast result can provide support for the forewarning of flow outburst and enables passengers to make an appropriate travel plan. Therefore, it is significant to develop a more accurate forecast model. Long short-term memory (LSTM) network has been proved to be effective on data with temporal features. However, it cannot process the correlation between time and space in rail transit. As a result, a novel forecast model combining spatio-temporal features based on LSTM network (ST-LSTM) is proposed. Different from other forecast methods, ST-LSTM network uses a new method to extract spatio-temporal features from the data and combines them together as the input. Compared with other conventional models, ST-LSTM network can achieve a better performance in experiments.
9
Geng, Yue, Lingling Su, Yunhong Jia e Ce Han. "Seismic Events Prediction Using Deep Temporal Convolution Networks". Journal of Electrical and Computer Engineering 2019 (2 de abril de 2019): 1–14. http://dx.doi.org/10.1155/2019/7343784.
Texto completo da fonteResumo:
Seismic events prediction is a crucial task for preventing coal mine rock burst hazards. Currently, this task attracts increasing research enthusiasms from many mining experts. Considering the temporal characteristics of monitoring data, seismic events prediction can be abstracted as a time series prediction task. This paper contributes to address the problem of long-term historical dependence on seismic time series prediction with deep temporal convolution neural networks (CNN). We propose a dilated causal temporal convolution network (DCTCNN) and a CNN long short-term memory hybrid model (CNN-LSTM) to forecast seismic events. In particular, DCTCNN is designed with dilated CNN kernels, causal strategy, and residual connections; CNN-LSTM is established in a hybrid modeling way by utilizing advantage of CNN and LSTM. Based on these manners, both of DCTCNN and CNN-LSTM can extract long-term historical features from the monitoring seismic data. The proposed models are experimentally tested on two real-life coal mine seismic datasets. Furthermore, they are also compared with one traditional time series prediction method, two classic machine learning algorithms, and two standard deep learning networks. Results show that DCTCNN and CNN-LSTM are superior than the other five algorithms, and they successfully complete the seismic prediction task.
10
Vaseekaran S, Pragadeeswaran S e Mrs S Janani. "Brain Tumour Prediction Using Temporal Memory". International Research Journal on Advanced Engineering Hub (IRJAEH) 3, n.º 02 (20 de fevereiro de 2025): 235–39. https://doi.org/10.47392/irjaeh.2025.0033.
Texto completo da fonteResumo:
Brain tumor prediction plays a critical role in advancing early diagnosis and effective treatment planning, directly impacting patient survival rates. Traditional methods for detecting brain tumors involve extensive image processing and manual feature extraction, which can be time-consuming and prone to errors. Recent advancements in deep learning have introduced neural networks, specifically Long Short-Term Memory (LSTM) networks, as effective tools for handling the sequential nature of medical imaging data. This study presents an approach leveraging LSTM-based models for brain tumor prediction, focusing on capturing temporal dependencies in MRI scans. By utilizing a time-sequence approach to model variations in patient data, the LSTM model effectively identifies and classifies tumor presence with improved accuracy. Through extensive training on labeled MRI datasets, the proposed method demonstrates high predictive performance, reducing the need for manual feature engineering and setting a new standard in automated brain tumor detection.
11
Bhandare, Yash. "Deepfake Detection Using Keyframe Extraction, Global Feature Enhancement, and Temporal Analysis". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, n.º 02 (22 de fevereiro de 2025): 1–9. https://doi.org/10.55041/ijsrem41765.
Texto completo da fonteResumo:
This paper presents a novel deepfake detection approach that combines spatial and temporal analysis, leveraging keyframe extraction, global feature enhancement, and a dual network system integrating ResNeXt-50 and LSTM. This hybrid approach aims to detect AI-synthesized media by enhancing subtle artifacts in manipulated frames. Initial observations indi cate that spatial enhancements improve artifact detection while the LSTM effectively identifies temporal inconsistencies. This methodology, outlined with expected performance outcomes, contributes a robust solution for deepfake detection that is adaptable to future real-time applications. Key Words: Deepfake Detection, Global feature Enhancement, ResNeXt-50, LSTM, Temporal Analysis, Keyframe Extraction, GAN, AI-Synthesized Media
12
Mekouar, Youssef, Imad Saleh e Mohammed Karim. "GreenNav: Spatiotemporal Prediction of CO2 Emissions in Paris Road Traffic Using a Hybrid CNN-LSTM Model". Network 5, n.º 1 (10 de janeiro de 2025): 2. https://doi.org/10.3390/network5010002.
Texto completo da fonteResumo:
In a global context where reducing the carbon footprint has become an urgent necessity, this article presents a hybrid CNN-LSTM prediction model to estimate CO2 emission rates of Paris road traffic using spatio-temporal data. Our hybrid prediction model relies on a real-time road traffic database that we built by fusing several APIs and datasets. In particular, we trained two specialized models: a CNN to extract spatial patterns and an LSTM to capture temporal dynamics. By merging their outputs, we leverage both spatial and temporal dependencies, ensuring more accurate predictions. Thus, this article aims to compare various strategies and configurations, allowing us to identify the optimal architecture and parameters for our CNN-LSTM model. Moreover, to refine the predictive learning evolution of our hybrid model, we used optimization techniques like gradient descent to monitor the learning progress. The results show that our hybrid CNN-LSTM model achieved an R2 value of 0.91 and an RMSE of 0.086, outperforming conventional models regarding CO2 emission rate prediction accuracy. These results validate the efficiency and relevance of using hybrid CNN-LSTM models for the spatio-temporal modelling of CO2 emissions in the context of road traffic.
13
Hashemi, Seyed Mohammad, Ruxandra Mihaela Botez e Georges Ghazi. "Bidirectional Long Short-Term Memory Development for Aircraft Trajectory Prediction Applications to the UAS-S4 Ehécatl". Aerospace 11, n.º 8 (31 de julho de 2024): 625. http://dx.doi.org/10.3390/aerospace11080625.
Texto completo da fonteResumo:
The rapid advancement of unmanned aerial systems in various civilian roles necessitates improved safety measures during their operation. A key aspect of enhancing safety is effective collision avoidance, which is based on conflict detection and is greatly aided by accurate trajectory prediction. This paper represents a novel data-driven trajectory prediction methodology based on applying the Long Short-Term Memory (LSTM) prediction algorithm to the UAS-S4 Ehécatl. An LSTM model was designed as the baseline and then developed into a Staked LSTM to better capture complex and hierarchical temporal trajectory patterns. Next, the Bidirectional LSTM was developed for a better understanding of the contextual trajectories from both its past and future data points, and to provide a more comprehensive temporal perspective that could enhance its accuracy. LSTM-based models were evaluated in terms of mean absolute percentage errors. The results reveal the superiority of the Bidirectional LSTM, as it could predict UAS-S4 trajectories more accurately than the Stacked LSTM. Moreover, the developed Bidirectional LSTM was compared with other state-of-the-art deep neural networks aimed at aircraft trajectory prediction. Promising results confirmed that Bidirectional LSTM exhibits the most stable MAPE across all prediction horizons.
14
Bagherian, Kamand, Edna G. Fernández-Figueroa, Stephanie R. Rogers, Alan E. Wilson e Yin Bao. "Predicting Chlorophyll-a Concentration and Harmful Algal Blooms in Lake Okeechobee Using Time-Series MODIS Satellite Imagery and Long Short-Term Memory". Journal of the ASABE 67, n.º 5 (2024): 1191–202. http://dx.doi.org/10.13031/ja.15995.
Texto completo da fonteResumo:
Highlights A 10-year dataset of time-series MODIS imagery and in situ Chl-a concentration were curated for Lake Okeechobee. LSTM significantly outperformed KNN, SVR, and RF for Chl-a prediction and subsequent HAB detection. The optimal window length was found to be 13 days with a 4-day temporal resolution for the LSTM model. KNN, SVR, and RF models were not effective at utilizing the temporal dynamics of the input features. Abstract. Harmful algal blooms (HABs) in inland waterbodies are a global concern due to their negative impact on human, animal, and ecosystem health. Chlorophyll-a (Chl-a) concentration is an important water quality parameter for monitoring HABs. While statistical and machine learning (ML) models have been widely studied to predict Chl-a concentration and HABs based on single-time-point satellite data, this work assessed whether long short-term memory (LSTM) can improve both tasks by leveraging temporal features in time-series MODIS satellite images compared to three classical ML models, including k-nearest neighbor (KNN), support vector regression (SVR), and random forest (RF). A dataset of daily MODIS images and monthly in situ Chl-a concentration measurements from 2011 to 2020 was curated for Lake Okeechobee, Florida. A window size of 13 days with a temporal resolution of four days was found to produce the optimal performance for LSTM, which significantly outperformed KNN, SVR, and RF for Chl-a prediction with a root mean square error of 11.95 µg/L, a mean absolute error of 8.55 µg/L, and a R2 value of 0.43. The superior performance of LSTM for Chl-a prediction was likely due to its ability to leverage the temporal dynamics in the features associated with HAB development. The Chl-a predictions were further used to determine HAB events, showing better accuracy and a significantly higher F1 score for LSTM over the other models. The study suggested that combining LSTM with high-temporal-resolution time-series data should be preferred over applying common ML models on time-series or single-time-point remote sensing data for Chl-a and HAB monitoring. Keywords: Cyanobacteria, LSTM, Machine Learning, Remote Sensing, Water Quality.
15
Yang, Binlin, Lu Chen, Bin Yi, Siming Li e Zhiyuan Leng. "Local Weather and Global Climate Data-Driven Long-Term Runoff Forecasting Based on Local–Global–Temporal Attention Mechanisms and Graph Attention Networks". Remote Sensing 16, n.º 19 (30 de setembro de 2024): 3659. http://dx.doi.org/10.3390/rs16193659.
Texto completo da fonteResumo:
The accuracy of long-term runoff models can be increased through the input of local weather variables and global climate indices. However, existing methods do not effectively extract important information from complex input factors across various temporal and spatial dimensions, thereby contributing to inaccurate predictions of long-term runoff. In this study, local–global–temporal attention mechanisms (LGTA) were proposed for capturing crucial information on global climate indices on monthly, annual, and interannual time scales. The graph attention network (GAT) was employed to extract geographical topological information of meteorological stations, based on remotely sensed elevation data. A long-term runoff prediction model was established based on long-short-term memory (LSTM) integrated with GAT and LGTA, referred to as GAT–LGTA–LSTM. The proposed model was compared to five comparative models (LGTA–LSTM, GAT–GTA–LSTM, GTA–LSTM, GAT–GA–LSTM, GA–LSTM). The models were applied to forecast the long-term runoff at Luning and Pingshan stations in China. The results indicated that the GAT–LGTA–LSTM model demonstrated the best forecasting performance among the comparative models. The Nash–Sutcliffe Efficiency (NSE) of GAT–LGTA–LSTM at the Luning and Pingshan stations reached 0.87 and 0.89, respectively. Compared to the GA–LSTM benchmark model, the GAT–LGTA–LSTM model demonstrated an average increase in NSE of 0.07, an average increase in Kling–Gupta Efficiency (KGE) of 0.08, and an average reduction in mean absolute percent error (MAPE) of 0.12. The excellent performance of the proposed model is attributed to the following: (1) local attention mechanism assigns a higher weight to key global climate indices at a monthly scale, enhancing the ability of global and temporal attention mechanisms to capture the critical information at annual and interannual scales and (2) the global attention mechanism integrated with GAT effectively extracts crucial temporal and spatial information from precipitation and remotely-sensed elevation data. Furthermore, attention visualization reveals that various global climate indices contribute differently to runoff predictions across distinct months. The global climate indices corresponding to specific seasons or months should be selected to forecast the respective monthly runoff.
16
Verianto, Eko. "Penerapan LSTM Dengan Regularisasi Untuk Mencegah Overfitting Pada Model Prediksi Tingkat Inflasi di Indonesia". Simkom 9, n.º 2 (21 de julho de 2024): 195–204. http://dx.doi.org/10.51717/simkom.v9i2.460.
Texto completo da fonteResumo:
Permasalahan inflasi dapat mempengaruhi pengembangan strategi, keputusan dan kebijakan pemerintah, sehingga diperlukan pemahaman mendalam mengenai tren inflasi di masa yang akan datang. Dalam menghadapi situasi ini diperlukan model prediksi yang dapat memodelkan tren inflasi di masa yang akan datang dengan tepat. Salah satu pendekatan yang dapat digunakan adalah backpropagation, namun penerapan backpropagation pada permasalahan prediksi seperti pada penelitian sebelumnya mendapatkan tantangan tersendiri, terutama pada data runtun waktu yang biasanya menghadirkan ketergantungan temporal. Penggunaan backpropagation dalam penelitian sebelumnya juga menunjukan perilaku overfitting. Tujuan dari penelitian ini adalah mengatasi ketergantungan temporal pada data runtun waktu menggunakan Long-Short Term Memory (LSTM) dan penerapan dropout dalam arsitektur LSTM untuk mencegah terjadinya overfitting pada model prediksi tingkat inflasi di Indonesia. Hasil dari penelitian ini menunjukan bahwa penerapan LSTM untuk mengatasi data dengan ketergantungan temporal menghasilkan kinerja yang cukup baik dan juga penggunaan dropout pada LSTM dapat mengatasi permasalahan overfitting pada prediksi tingkat inflasi di Indonesia.
17
Ji, Shengfei, Wei Li, Yong Wang, Bo Zhang e See-Kiong Ng. "A Soft Sensor Model for Predicting the Flow of a Hydraulic Pump Based on Graph Convolutional Network–Long Short-Term Memory". Actuators 13, n.º 1 (17 de janeiro de 2024): 38. http://dx.doi.org/10.3390/act13010038.
Texto completo da fonteResumo:
The hydraulic pump plays a pivotal role in engineering machinery, and it is essential to continuously monitor its operating status. However, many vital signals for monitoring cannot be directly obtained in practical applications. To address this, we propose a soft sensor approach for predicting the flow signal of the hydraulic pump based on a graph convolutional network (GCN) and long short-term memory (LSTM). Our innovative GCN-LSTM model is intricately designed to capture both spatial and temporal interdependencies inherent in complex machinery, such as hydraulic pumps. We used the GCN to extract spatial features and LSTM to extract temporal features of the process variables. To evaluate the performance of GCN-LSTM in predicting the flow of a hydraulic pump, we construct a real-world experimental dataset with an actual hydraulic shovel. We further evaluated GCN-LSTM on two public datasets, showing the effectiveness of GCN-LSTM for predicting the flow of hydraulic pumps and other complex engineering operations.
18
Jiang, Rui, Hongyun Xu, Gelian Gong, Yong Kuang e Zhikang Liu. "Spatial-Temporal Attentive LSTM for Vehicle-Trajectory Prediction". ISPRS International Journal of Geo-Information 11, n.º 7 (21 de junho de 2022): 354. http://dx.doi.org/10.3390/ijgi11070354.
Texto completo da fonteResumo:
Vehicle-trajectory prediction is essential for intelligent traffic systems (ITS), as it can help autonomous vehicles to plan a safe and efficient path. However, it is still a challenging task because existing studies have mainly focused on the spatial interactions of adjacent vehicles regardless of the temporal dependencies. In this paper, we propose a spatial-temporal attentive LSTM encoder–decoder model (STAM-LSTM) to predict vehicle trajectories. Specifically, the spatial attention mechanism is used to capture the spatial relationships among neighboring vehicles and then obtain the global spatial feature. Meanwhile, the temporal attention mechanism is designed to distinguish the effects of different historical time steps on future trajectory prediction. In addition, the motion feature of vehicles is extracted to reveal the influence of dynamic information on vehicle-trajectory prediction, and is combined with the local and global spatial features to represent the integrated features of the target vehicle at each historical moment. The experiments were conducted on public highway trajectory datasets—US-101 and I-80 in NGSIM—and the results demonstrate that our model achieves state-of-the-art prediction performance.
19
Wang, Changyuan, Ting Yan e Hongbo Jia. "Spatial-Temporal Feature Representation Learning for Facial Fatigue Detection". International Journal of Pattern Recognition and Artificial Intelligence 32, n.º 12 (27 de agosto de 2018): 1856018. http://dx.doi.org/10.1142/s0218001418560189.
Texto completo da fonteResumo:
In order to reduce the serious problems caused by the operators’ fatigue, we propose a novel network model Convolutional Neural Network and Long Short-Term Memory Network (CNN-LSTM) — for fatigue detection in the inter-frame images of video sequences, which mainly consists of CNN and LSTM network. Firstly, in order to improve the accuracy of the deep network structure, the Viola–Jones detection algorithm and the Kernelized Correlation Filter (KCF) tracking algorithm are used in the face detection to normalize the size of the inter-frame images of video sequences. Secondly, we use the CNN and the LSTM network to detect the fatigue state in real time and efficiently. The fatigue-related facial features are extracted by the CNN. Then, the temporal symptoms of the whole fatigue process can be extracted by LSTM networks, the input data which is the facial feature vector can be obtained by the CNN. Thirdly, we train and test the network in a step-by-step approach. Finally, we experiment with the proposed network model. The experimental results demonstrate that the network structure can effectively detect the fatigue state, and the overall accuracy rate can rise to 82.8%.
20
Ng, Jia Hui, Ying Han Pang, Sarmela Raja Sekaran, Shih Yin Ooi e Lillian Yee Kiaw Wang. "Temporal Convolutional Recurrent Neural Network for Elderly Activity Recognition". Journal of Engineering Technology and Applied Physics 6, n.º 2 (15 de setembro de 2024): 84–91. http://dx.doi.org/10.33093/jetap.2024.6.2.12.
Texto completo da fonteResumo:
Research on smartphone-based human activity recognition (HAR) is prevalent in the field of healthcare, especially for elderly activity monitoring. Researchers usually propose to use of accelerometers, gyroscopes or magnetometers that are equipped in smartphones as an individual sensing modality for human activity recognition. However, any of these alone is limited in capturing comprehensive movement information for accurate human activity analysis. Thus, we propose a smartphone-based HAR approach by leveraging the inertial signals captured by these three sensors to classify human activities. These heterogeneous sensors deliver information on various aspects of nature, motion and orientation, offering a richer set of features for more accurate representations of the activities. Hence, a deep learning approach that amalgamates long short-term memory (LSTM) in temporal convolutional network (TCN) is proposed. We use independent temporal convolutional networks, coined as temporal convolutional streams, to independently analyse the temporal data of each sensing modality. We name this architecture multi-stream TC-LSTM. The performance of multi-stream TC-LSTM is assessed on the self-collected elderly activity database. Empirical results exhibit that multi-stream TC-LSTM outperforms the existing machine learning and deep learning models, with an F1 score of 98.3 %
21
Gauch, Martin, Frederik Kratzert, Daniel Klotz, Grey Nearing, Jimmy Lin e Sepp Hochreiter. "Rainfall–runoff prediction at multiple timescales with a single Long Short-Term Memory network". Hydrology and Earth System Sciences 25, n.º 4 (19 de abril de 2021): 2045–62. http://dx.doi.org/10.5194/hess-25-2045-2021.
Texto completo da fonteResumo:
Abstract. Long Short-Term Memory (LSTM) networks have been applied to daily discharge prediction with remarkable success. Many practical applications, however, require predictions at more granular timescales. For instance, accurate prediction of short but extreme flood peaks can make a lifesaving difference, yet such peaks may escape the coarse temporal resolution of daily predictions. Naively training an LSTM on hourly data, however, entails very long input sequences that make learning difficult and computationally expensive. In this study, we propose two multi-timescale LSTM (MTS-LSTM) architectures that jointly predict multiple timescales within one model, as they process long-past inputs at a different temporal resolution than more recent inputs. In a benchmark on 516 basins across the continental United States, these models achieved significantly higher Nash–Sutcliffe efficiency (NSE) values than the US National Water Model. Compared to naive prediction with distinct LSTMs per timescale, the multi-timescale architectures are computationally more efficient with no loss in accuracy. Beyond prediction quality, the multi-timescale LSTM can process different input variables at different timescales, which is especially relevant to operational applications where the lead time of meteorological forcings depends on their temporal resolution.
22
Dai, Hongbin, Guangqiu Huang, Jingjing Wang, Huibin Zeng e Fangyu Zhou. "Prediction of Air Pollutant Concentration Based on One-Dimensional Multi-Scale CNN-LSTM Considering Spatial-Temporal Characteristics: A Case Study of Xi’an, China". Atmosphere 12, n.º 12 (6 de dezembro de 2021): 1626. http://dx.doi.org/10.3390/atmos12121626.
Texto completo da fonteResumo:
Air pollution has become a serious problem threatening human health. Effective prediction models can help reduce the adverse effects of air pollutants. Accurate predictions of air pollutant concentration can provide a scientific basis for air pollution prevention and control. However, the previous air pollution-related prediction models mainly processed air quality prediction, or the prediction of a single or two air pollutants. Meanwhile, the temporal and spatial characteristics and multiple factors of pollutants were not fully considered. Herein, we establish a deep learning model for an atmospheric pollutant memory network (LSTM) by both applying the one-dimensional multi-scale convolution kernel (ODMSCNN) and a long-short-term memory network (LSTM) on the basis of temporal and spatial characteristics. The temporal and spatial characteristics combine the respective advantages of CNN and LSTM networks. First, ODMSCNN is utilized to extract the temporal and spatial characteristics of air pollutant-related data to form a feature vector, and then the feature vector is input into the LSTM network to predict the concentration of air pollutants. The data set comes from the daily concentration data and hourly concentration data of six atmospheric pollutants (PM2.5, PM10, NO2, CO, O3, SO2) and 17 types of meteorological data in Xi’an. Daily concentration data prediction, hourly concentration data prediction, group data prediction and multi-factor prediction were used to verify the effectiveness of the model. In general, the air pollutant concentration prediction model based on ODMSCNN-LSTM shows a better prediction effect compared with multi-layer perceptron (MLP), CNN, and LSTM models.
23
Varma, Danthuluru Sri Datta Manikanta. "ActiWise: Insight on Human Activity Recognition Using Deep Learning Approaches". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, n.º 05 (2 de maio de 2024): 1–5. http://dx.doi.org/10.55041/ijsrem32830.
Texto completo da fonteResumo:
In this study, we investigate the fusion of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks for human activity recognition (HAR). By integrating hierarchical spatial features extracted by CNNs with LSTM networks' temporal modelling capabilities, our approach excels in discerning nuanced patterns from raw sensor data collected via wearable devices. Through rigorous experimentation and validation, our CNN+LSTM model demonstrates robust performance in accurately classifying a spectrum of human activities. This research advances HAR methodologies, shedding light on the synergistic interplay between spatial and temporal modelling in activity recognition, with implications across healthcare, sports analytics, and human-computer interaction domains. Index Terms- Human activity recognition, deep learning, Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM).
24
van Duynhoven, Alysha, e Suzana Dragićević. "Analyzing the Effects of Temporal Resolution and Classification Confidence for Modeling Land Cover Change with Long Short-Term Memory Networks". Remote Sensing 11, n.º 23 (26 de novembro de 2019): 2784. http://dx.doi.org/10.3390/rs11232784.
Texto completo da fonteResumo:
Land cover change (LCC) is typically characterized by infrequent changes over space and time. Data-driven methods such as deep learning (DL) approaches have proven effective in many domains for predictive and classification tasks. When applied to geospatial data, sequential DL methods such as long short-term memory (LSTM) have yielded promising results in remote sensing and GIScience studies. However, the characteristics of geospatial datasets selected for use with these methods have demonstrated important implications on method performance. The number of data layers available, the rate of LCC, and inherent errors resulting from classification procedures are expected to influence model performance. Yet, it is unknown how these can affect compatibility with the LSTM method. As such, the main objective of this study is to explore the capacity of LSTM to forecast patterns that have emerged from LCC dynamics given varying temporal resolutions, persistent land cover classes, and auxiliary data layers pertaining to classification confidence. Stacked LSTM modeling approaches are applied to 17-year MODIS land cover datasets focused on the province of British Columbia, Canada. This geospatial data is reclassified to four major land cover (LC) classes during pre-processing procedures. The evaluation considers the dataset at variable temporal resolutions to demonstrate the significance of geospatial data characteristics on LSTM method performance in several scenarios. Results indicate that LSTM can be utilized for forecasting LCC patterns when there are few limitations on temporal intervals of the datasets provided. Likewise, this study demonstrates improved performance measures when there are classes that do not change. Furthermore, providing classification confidence data as ancillary input also demonstrated improved results when the number of timesteps or temporal resolution is limited. This study contributes to future applications of DL and LSTM methods for forecasting LCC.
25
Mei, Jinlong, Chengqun Wang, Shuyun Luo, Weiqiang Xu e Zhijiang Deng. "Short-Term Wind Power Prediction Based on Encoder–Decoder Network and Multi-Point Focused Linear Attention Mechanism". Sensors 24, n.º 17 (25 de agosto de 2024): 5501. http://dx.doi.org/10.3390/s24175501.
Texto completo da fonteResumo:
Wind energy is a clean energy source that is characterised by significant uncertainty. The electricity generated from wind power also exhibits strong unpredictability, which when integrated can have a substantial impact on the security of the power grid. In the context of integrating wind power into the grid, accurate prediction of wind power generation is crucial in order to minimise damage to the grid system. This paper proposes a novel composite model (MLL-MPFLA) that combines a multilayer perceptron (MLP) and an LSTM-based encoder–decoder network for short-term prediction of wind power generation. In this model, the MLP first extracts multidimensional features from wind power data. Subsequently, an LSTM-based encoder-decoder network explores the temporal characteristics of the data in depth, combining multidimensional features and temporal features for effective prediction. During decoding, an improved focused linear attention mechanism called multi-point focused linear attention is employed. This mechanism enhances prediction accuracy by weighting predictions from different subspaces. A comparative analysis against the MLP, LSTM, LSTM–Attention–LSTM, LSTM–Self_Attention–LSTM, and CNN–LSTM–Attention models demonstrates that the proposed MLL-MPFLA model outperforms the others in terms of MAE, RMSE, MAPE, and R2, thereby validating its predictive performance.
26
Ge, Shaojia, Weimin Su, Hong Gu, Yrjö Rauste, Jaan Praks e Oleg Antropov. "Improved LSTM Model for Boreal Forest Height Mapping Using Sentinel-1 Time Series". Remote Sensing 14, n.º 21 (4 de novembro de 2022): 5560. http://dx.doi.org/10.3390/rs14215560.
Texto completo da fonteResumo:
Time series of SAR imagery combined with reference ground data can be suitable for producing forest inventories. Copernicus Sentinel-1 imagery is particularly interesting for forest mapping because of its free availability to data users; however, temporal dependencies within SAR time series that can potentially improve mapping accuracy are rarely explored. In this study, we introduce a novel semi-supervised Long Short-Term Memory (LSTM) model, CrsHelix-LSTM, and demonstrate its utility for predicting forest tree height using time series of Sentinel-1 images. The model brings three important modifications to the conventional LSTM model. Firstly, it uses a Helix-Elapse (HE) projection to capture the relationship between forest temporal patterns and Sentinel-1 time series, when time intervals between datatakes are irregular. A skip-link based LSTM block is introduced and a novel backbone network, Helix-LSTM, is proposed to retrieve temporal features at different receptive scales. Finally, a novel semisupervised strategy, Cross-Pseudo Regression, is employed to achieve better model performance when reference training data are limited. CrsHelix-LSTM model is demonstrated over a representative boreal forest site located in Central Finland. A time series of 96 Sentinel-1 images are used in the study. The developed model is compared with basic LSTM model, attention-based bidirectional LSTM and several other established regression approaches used in forest variable mapping, demonstrating consistent improvement of forest height prediction accuracy. At best, the achieved accuracy of forest height mapping was 28.3% relative root mean squared error (rRMSE) for pixel-level predictions and 18.0% rRMSE on stand level. We expect that the developed model can also be used for modeling relationships between other forest variables and satellite image time series.
27
Shelke, Shivani Shelke, e Dr Sheshang Degadwala Degadwala. "Multi-Class Recognition of Soybean Leaf Diseases using a Conv-LSTM Model". International Journal of Scientific Research in Computer Science, Engineering and Information Technology 10, n.º 2 (27 de março de 2024): 249–57. http://dx.doi.org/10.32628/cseit2410217.
Texto completo da fonteResumo:
This research presents an innovative approach for multi-class recognition of soybean leaf diseases using a Convolutional Long Short-Term Memory (Conv-LSTM) model. The model integrates the spatial learning capabilities of convolutional layers with the temporal dependencies of LSTM units, addressing the critical need for accurate disease detection in agriculture, particularly in soybean cultivation where leaf diseases significantly impact crop yield and quality. Through comparative experiments with established deep learning models such as AlexNet, VGG16, and ResNet50, the Conv-LSTM model demonstrates superior performance in terms of accuracy, precision, recall, and F1 score. By effectively capturing both spatial and temporal features in soybean leaf images, the Conv-LSTM model showcases its potential to enhance disease detection accuracy, supporting precision agriculture practices and enabling timely interventions to mitigate crop losses caused by diseases.
28
Zhen, Hao, Dongxiao Niu, Min Yu, Keke Wang, Yi Liang e Xiaomin Xu. "A Hybrid Deep Learning Model and Comparison for Wind Power Forecasting Considering Temporal-Spatial Feature Extraction". Sustainability 12, n.º 22 (15 de novembro de 2020): 9490. http://dx.doi.org/10.3390/su12229490.
Texto completo da fonteResumo:
The inherent intermittency and uncertainty of wind power have brought challenges in accurate wind power output forecasting, which also cause tricky problems in the integration of wind power to the grid. In this paper, a hybrid deep learning model bidirectional long short term memory-convolutional neural network (BiLSTM-CNN) is proposed for short-term wind power forecasting. First, the grey correlation analysis is utilized to select the inputs for forecasting model; Then, the proposed hybrid model extracts multi-dimension features of inputs to predict the wind power from the temporal-spatial perspective, where the Bi-LSTM model is utilized to mine the bidirectional temporal characteristics while the convolution and pooling operations of CNN are utilized to extract the spatial characteristics from multiple input time series. Lastly, a case study is conducted to verify the superiority of the proposed model. Other deep learning models (Bi-LSTM, LSTM, CNN, LSTM-CNN, CNN-BiLSTM, CNN-LSTM) are also simulated to conduct comparison from three aspects. The results show that the BiLSTM-CNN model has the best accuracy with the lowest RMSE of 2.5492, MSE of 6.4984, MAE of 1.7344 and highest R2 of 0.9929. CNN has the fastest speed with an average computational time of 0.0741s. The hybrid model that mines the spatial feature based on the extracted temporal feature has a better performance than the model mines the temporal feature based on the extracted spatial feature.
29
Hu, Chunsheng, Fangjuan Cheng, Liang Ma e Bohao Li. "State of Charge Estimation for Lithium-Ion Batteries Based on TCN-LSTM Neural Networks". Journal of The Electrochemical Society 169, n.º 3 (1 de março de 2022): 030544. http://dx.doi.org/10.1149/1945-7111/ac5cf2.
Texto completo da fonteResumo:
Accurately estimating the state of charge (SOC) of lithium-ion batteries is critical for developing more reliable and efficient operation of electric vehicles. However, the commonly used models cannot simultaneously extract effective spatial and temporal features from the original data, leading to an inefficient SOC estimation. This paper proposes a novel neural network method for accurate and robust battery SOC estimation, which incorporates the temporal convolutional network (TCN) and the long short-term memory (LSTM), namely TCN-LSTM model. Specifically, the TCN is employed to extract more advanced spatial features among multivariate variables, and the LSTM captures long-term dependencies from time-series data and maps battery temporal information into current SOC and historical inputs. The proposed model performs well in various estimation conditions. The average value of mean absolute error, root mean square error, and maximum error of SOC estimation achieve 0.48%, 0.60%, and 2.3% at multiple temperature conditions, respectively, and reach 0.70%, 0.81%, and 2.7% for a different battery, respectively. In addition, the proposed method has better accuracy than the LSTM or TCN used independently and the CNN-LSTM network. The computational burden with varying length of input is also investigated. In summary, experiment results show that the proposed method has excellent generalization and robustness.
30
Huang, Feini, Yongkun Zhang, Ye Zhang, Wei Shangguan, Qingliang Li, Lu Li e Shijie Jiang. "Interpreting Conv-LSTM for Spatio-Temporal Soil Moisture Prediction in China". Agriculture 13, n.º 5 (27 de abril de 2023): 971. http://dx.doi.org/10.3390/agriculture13050971.
Texto completo da fonteResumo:
Soil moisture (SM) is a key variable in Earth system science that affects various hydrological and agricultural processes. Convolutional long short-term memory (Conv-LSTM) networks are widely used deep learning models for spatio-temporal SM prediction, but they are often regarded as black boxes that lack interpretability and transparency. This study aims to interpret Conv-LSTM for spatio-temporal SM prediction in China, using the permutation importance and smooth gradient methods for global and local interpretation, respectively. The trained Conv-LSTM model achieved a high R2 of 0.92. The global interpretation revealed that precipitation and soil properties are the most important factors affecting SM prediction. Furthermore, the local interpretation showed that the seasonality of variables was more evident in the high-latitude regions, but their effects were stronger in low-latitude regions. Overall, this study provides a novel approach to enhance the trust-building for Conv-LSTM models and to demonstrate the potential of artificial intelligence-assisted Earth system modeling and understanding element prediction in the future.
31
Cao, Wenzhi, Houdun Liu, Xiangzhi Zhang e Yangyan Zeng. "Residential Load Forecasting Based on Long Short-Term Memory, Considering Temporal Local Attention". Sustainability 16, n.º 24 (22 de dezembro de 2024): 11252. https://doi.org/10.3390/su162411252.
Texto completo da fonteResumo:
Accurate residential load forecasting is crucial for the stable operation of the energy internet, which plays a significant role in advancing sustainable development. As the construction of the energy internet progresses, the proportion of residential electricity consumption in end-use energy consumption is increasing, the peak load on the grid is growing year on year, and seasonal and regional peak power supply tensions, mainly for household electricity consumption, grow into common problems across countries. Residential load forecasting can assist utility companies in determining effective electricity pricing structures and demand response operations, thereby improving renewable energy utilization efficiency and reducing the share of thermal power generation. However, due to the randomness and uncertainty of user load data, forecasting residential load remains challenging. According to prior research, the accuracy of residential load forecasting using machine learning and deep learning methods still has room for improvement. This paper proposes an improved load-forecasting model based on a time-localized attention (TLA) mechanism integrated with LSTM, named TLA-LSTM. The model is composed of a full-text regression network, a date-attention network, and a time-point attention network. The full-text regression network consists of a traditional LSTM, while the date-attention and time-point attention networks are based on a local attention model constructed with CNN and LSTM. Experimental results on real-world datasets show that compared to standard LSTM models, the proposed method improves R2 by 14.2%, reduces MSE by 15.2%, and decreases RMSE by 8.5%. These enhancements demonstrate the robustness and efficiency of the TLA-LSTM model in load forecasting tasks, effectively addressing the limitations of traditional LSTM models in focusing on specific dates and time-points in user load data.
32
Noor, Fahima, Sanaulla Haq, Mohammed Rakib, Tarik Ahmed, Zeeshan Jamal, Zakaria Shams Siam, Rubyat Tasnuva Hasan, Mohammed Sarfaraz Gani Adnan, Ashraf Dewan e Rashedur M. Rahman. "Water Level Forecasting Using Spatiotemporal Attention-Based Long Short-Term Memory Network". Water 14, n.º 4 (17 de fevereiro de 2022): 612. http://dx.doi.org/10.3390/w14040612.
Texto completo da fonteResumo:
Bangladesh is in the floodplains of the Ganges, Brahmaputra, and Meghna River delta, crisscrossed by an intricate web of rivers. Although the country is highly prone to flooding, the use of state-of-the-art deep learning models in predicting river water levels to aid flood forecasting is underexplored. Deep learning and attention-based models have shown high potential for accurately forecasting floods over space and time. The present study aims to develop a long short-term memory (LSTM) network and its attention-based architectures to predict flood water levels in the rivers of Bangladesh. The models developed in this study incorporated gauge-based water level data over 7 days for flood prediction at Dhaka and Sylhet stations. This study developed five models: artificial neural network (ANN), LSTM, spatial attention LSTM (SALSTM), temporal attention LSTM (TALSTM), and spatiotemporal attention LSTM (STALSTM). The multiple imputation by chained equations (MICE) method was applied to address missing data in the time series analysis. The results showed that the use of both spatial and temporal attention together increases the predictive performance of the LSTM model, which outperforms other attention-based LSTM models. The STALSTM-based flood forecasting system, developed in this study, could inform flood management plans to accurately predict floods in Bangladesh and elsewhere.
33
Zhang, Yue, Zhaohui Gu, Jesse Van Griensven Thé, Simon X. Yang e Bahram Gharabaghi. "The Discharge Forecasting of Multiple Monitoring Station for Humber River by Hybrid LSTM Models". Water 14, n.º 11 (2 de junho de 2022): 1794. http://dx.doi.org/10.3390/w14111794.
Texto completo da fonteResumo:
An early warning flood forecasting system that uses machine-learning models can be utilized for saving lives from floods, which are now exacerbated due to climate change. Flood forecasting is carried out by determining the river discharge and water level using hydrologic models at the target sites. If the water level and discharge are forecasted to reach dangerous levels, the flood forecasting system sends warning messages to residents in flood-prone areas. In the past, hybrid Long Short-Term Memory (LSTM) models have been successfully used for the time series forecasting. However, the prediction errors grow exponentially with the forecasting period, making the forecast unreliable as an early warning tool with enough lead time. Therefore, this research aimed to improve the accuracy of flood forecasting models by employing real-time monitoring network datasets and establishing temporal and spatial links between adjacent monitoring stations. We evaluated the performance of the Long Short-Term Memory (LSTM), the Convolutional Neural Networks LSTM (CNN-LSTM), the Convolutional LSTM (ConvLSTM), and the Spatio-Temporal Attention LSTM (STA-LSTM) models for flood forecasting. The dataset, employed for validation, includes hourly discharge records, from 2012 to 2017, on six stations of the Humber River in the City of Toronto, Canada. Experiments included forecasting for both 6 and 12 h ahead, using discharge data as input for the past 24 h. The STA-LSTM model’s performance was superior to the CNN-LSTM, the ConvLSTM, and the basic LSTM models when the forecast time was longer than 6 h.
34
Xu, Gengchen, Jingyun Xu e Yifan Zhu. "LSTM-based estimation of lithium-ion battery SOH using data characteristics and spatio-temporal attention". PLOS ONE 19, n.º 12 (26 de dezembro de 2024): e0312856. https://doi.org/10.1371/journal.pone.0312856.
Texto completo da fonteResumo:
As the primary power source for electric vehicles, the accurate estimation of the State of Health (SOH) of lithium-ion batteries is crucial for ensuring the reliable operation of the power system. Long Short-Term Memory (LSTM), a special type of recurrent neural network, achieves sequence information estimation through a gating mechanism. However, traditional LSTM-based SOH estimation methods do not account for the fact that the degradation sequence of battery SOH exhibits trend-like nonlinearity and significant dynamic variations between samples. Therefore, this paper proposes an LSTM-based lithium-ion SOH estimation method incorporating data characteristics and spatio-temporal attention. First, considering the trend-like nonlinearity of the degradation sequence, which is initially gradual and then rapid, input features are filtered and divided into trend and non-trend features. Then, to address the significant dynamic variations between samples, especially for capacity regeneration,a spatio-temporal attention mechanism is designed to extract spatio-temporal features from multidimensional non-trend features. Subsequently, an LSTM model is built with trend features, spatio-temporal features, and actual capacity as inputs to estimate capacity. Finally, the model is trained and tested on different datasets. Experimental results demonstrate that the proposed method outperforms traditional methods in terms of SOH estimation accuracy and robustness.
35
Eun, Hyunjun, Jinyoung Moon, Jongyoul Park, Chanho Jung e Changick Kim. "Learning Snippet Relatedness Based on LSTM for Temporal Action Proposal Generation". Journal of Korean Institute of Communications and Information Sciences 45, n.º 6 (30 de junho de 2020): 975–78. http://dx.doi.org/10.7840/kics.2020.45.6.975.
Texto completo da fonte
36
Wanzhen Wang, Sze Song Ngu, Miaomiao Xin, Rong Liu, Qian Wang, Man Qiu e Shengqun Zhang. "Tool Wear Prediction Based on Adaptive Feature and Temporal Attention with Long Short-Term Memory Model". International Journal of Engineering and Technology Innovation 14, n.º 3 (1 de maio de 2024): 271–84. http://dx.doi.org/10.46604/ijeti.2024.13387.
Texto completo da fonteResumo:
Effective monitoring of tool wear status can improve productivity and reduce losses. In previous studies, extensive feature selection was required when using the traditional machine learning method. The gating mechanism in the traditional long short-term memory (LSTM) model may incur information loss and a weaker representation of global sequential dependencies in handling long sequences. This paper aims to enhance the performance of the LSTM model in tool wear prediction by combining feature and temporal attention. Firstly, the original vibration signal is divided into sub-sequences and related features extracted. Secondly, the ability to capture global sequential dependencies using the LSTM model is improved by feature and temporal attention. Finally, a fully connected layer is used to predict tool wear values. Compared to traditional LSTM, the proposed method performs best in three evaluation metrics, RMSE, MAE, and the coefficient of determination.
37
Chieu Hanh Vu, Duc Hong Nguyen e Trinh Hieu Tran. "Investigating the effectiveness of LSTM and deep LSTM architectures in solar energy forecasting". International Journal of Science and Research Archive 13, n.º 1 (30 de outubro de 2024): 2519–29. http://dx.doi.org/10.30574/ijsra.2024.13.1.1950.
Texto completo da fonteResumo:
This study investigates the effectiveness of Long Short-Term Memory (LSTM) and Deep LSTM architectures in solar energy forecasting using real-world data. We compare these models based on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) metrics to assess their predictive performance. While Deep LSTM models show higher accuracy by capturing complex temporal patterns, they also demand greater computational resources. Hybrid models integrating LSTM with techniques like CNNs and Transformers demonstrate further improvements, achieving lower error rates. The findings highlight the trade-offs between model complexity and computational efficiency, providing insights into selecting suitable architectures for solar power forecasting. This research contributes to advancing deep learning techniques for renewable energy systems, enhancing their role in modern energy management.
38
ZHAO, Yongpeng, Yongcang LI, Changxi MA, Ke WANG e Xuecai XU. "Optimised LSTM Neural Network for Traffic Speed Prediction with Multi-Source Data Fusion". Promet - Traffic&Transportation 36, n.º 4 (27 de agosto de 2024): 765–78. http://dx.doi.org/10.7307/ptt.v36i4.592.
Texto completo da fonteResumo:
Predicting traffic speed accurately and in real-time is crucial for the development of smart transportation systems. Given the nonlinear and stochastic nature of vehicle data, integrating diverse spatio-temporal data sources with the Improved Particle Swarm Optimisation (IPSO) offers a promising approach to optimise the Long Short-Term Memory Neural Network (LSTM). Firstly, we enhance the optimisation capabilities of PSO by implementing nonlinear inertial weight and adaptive variation. Secondly, addressing the challenge of selecting the LSTM hyperparameters, the PSO algorithm effectively identifies global optimal solutions for hyperparameter optimisation, ensuring appropriate settings through iterative training. Subsequently, we conduct a case study using multi-source spatio-temporal traffic speed data, comparing our proposed IPSO-LSTM model with traditional neural network prediction models and advanced models. Results from the experiment demonstrate that the IPSO-LSTM model presented in this study addresses issues of parameter selection and inaccurate prediction encountered by traditional LSTM models in traffic state prediction. Moreover, it enhances the model’s ability to capture speed time series dynamics. Notably, in processing complex speed data, our model exhibits superior accuracy and stability in prediction.
39
Hwang, Bor-Jiunn, Hui-Hui Chen, Chaur-Heh Hsieh e Deng-Yu Huang. "Gaze Tracking Based on Concatenating Spatial-Temporal Features". Sensors 22, n.º 2 (11 de janeiro de 2022): 545. http://dx.doi.org/10.3390/s22020545.
Texto completo da fonteResumo:
Based on experimental observations, there is a correlation between time and consecutive gaze positions in visual behaviors. Previous studies on gaze point estimation usually use images as the input for model trainings without taking into account the sequence relationship between image data. In addition to the spatial features, the temporal features are considered to improve the accuracy in this paper by using videos instead of images as the input data. To be able to capture spatial and temporal features at the same time, the convolutional neural network (CNN) and long short-term memory (LSTM) network are introduced to build a training model. In this way, CNN is used to extract the spatial features, and LSTM correlates temporal features. This paper presents a CNN Concatenating LSTM network (CCLN) that concatenates spatial and temporal features to improve the performance of gaze estimation in the case of time-series videos as the input training data. In addition, the proposed model can be optimized by exploring the numbers of LSTM layers, the influence of batch normalization (BN) and global average pooling layer (GAP) on CCLN. It is generally believed that larger amounts of training data will lead to better models. To provide data for training and prediction, we propose a method for constructing datasets of video for gaze point estimation. The issues are studied, including the effectiveness of different commonly used general models and the impact of transfer learning. Through exhaustive evaluation, it has been proved that the proposed method achieves a better prediction accuracy than the existing CNN-based methods. Finally, 93.1% of the best model and 92.6% of the general model MobileNet are obtained.
40
Du, Jiale, Zunyi Liu, Wenyuan Dong, Weifeng Zhang e Zhonghua Miao. "A Novel TCN-LSTM Hybrid Model for sEMG-Based Continuous Estimation of Wrist Joint Angles". Sensors 24, n.º 17 (30 de agosto de 2024): 5631. http://dx.doi.org/10.3390/s24175631.
Texto completo da fonteResumo:
Surface electromyography (sEMG) offers a novel method in human–machine interactions (HMIs) since it is a distinct physiological electrical signal that conceals human movement intention and muscle information. Unfortunately, the nonlinear and non-smooth features of sEMG signals often make joint angle estimation difficult. This paper proposes a joint angle prediction model for the continuous estimation of wrist motion angle changes based on sEMG signals. The proposed model combines a temporal convolutional network (TCN) with a long short-term memory (LSTM) network, where the TCN can sense local information and mine the deeper information of the sEMG signals, while LSTM, with its excellent temporal memory capability, can make up for the lack of the ability of the TCN to capture the long-term dependence of the sEMG signals, resulting in a better prediction. We validated the proposed method in the publicly available Ninapro DB1 dataset by selecting the first eight subjects and picking three types of wrist-dependent movements: wrist flexion (WF), wrist ulnar deviation (WUD), and wrist extension and closed hand (WECH). Finally, the proposed TCN-LSTM model was compared with the TCN and LSTM models. The proposed TCN-LSTM outperformed the TCN and LSTM models in terms of the root mean square error (RMSE) and average coefficient of determination (R2). The TCN-LSTM model achieved an average RMSE of 0.064, representing a 41% reduction compared to the TCN model and a 52% reduction compared to the LSTM model. The TCN-LSTM also achieved an average R2 of 0.93, indicating an 11% improvement over the TCN model and an 18% improvement over the LSTM model.
41
Wang, Li, Qianhui Tang, Xiaoyi Wang, Jiping Xu, Zhiyao Zhao, Huiyan Zhang, Jiabin Yu et al. "Spatio-temporal data prediction of multiple air pollutants in multi-cities based on 4D digraph convolutional neural network". PLOS ONE 18, n.º 12 (22 de dezembro de 2023): e0287781. http://dx.doi.org/10.1371/journal.pone.0287781.
Texto completo da fonteResumo:
In response to the problem that current multi-city multi-pollutant prediction methods based on one-dimensional undirected graph neural network models cannot accurately reflect the two-dimensional spatial correlations and directedness, this study proposes a four-dimensional directed graph model that can capture the two-dimensional spatial directed information and node correlation information related to multiple factors, as well as extract temporal correlation information at different times. Firstly, A four-dimensional directed GCN model with directed information graph in two-dimensional space was established based on the geographical location of the city. Secondly, Spectral decomposition and tensor operations were then applied to the two-dimensional directed information graph to obtain the graph Fourier coefficients and graph Fourier basis. Thirdly, the graph filter of the four-dimensional directed GCN model was further improved and optimized. Finally, an LSTM network architecture was introduced to construct the four-dimensional directed GCN-LSTM model for synchronous extraction of spatio-temporal information and prediction of atmospheric pollutant concentrations. The study uses the 2020 atmospheric six-parameter data of the Taihu Lake city cluster and applies canonical correlation analysis to confirm the data’s temporal, spatial, and multi-factor correlations. Through experimentation, it is verified that the proposed 4D-DGCN-LSTM model achieves a MAE reduction of 1.12%, 4.91%, 5.62%, and 11.67% compared with the 4D-DGCN, GCN-LSTM, GCN, and LSTM models, respectively, indicating the good performance of the 4D-DGCN-LSTM model in predicting multiple types of atmospheric pollutants in various cities.
42
Garima Pandey, Abhishek Kumar Karn e Manish Jha. "Human Activity Recognition Using CNN-LSTM-GRU Model". International Research Journal on Advanced Engineering Hub (IRJAEH) 2, n.º 04 (20 de abril de 2024): 889–94. http://dx.doi.org/10.47392/irjaeh.2024.0125.
Texto completo da fonteResumo:
Human Activity Recognition (HAR) is a fundamental task in the field of computer vision and machine learning, with applications spanning from healthcare monitoring to human- computer interaction. This research paper presents a novel approach to HAR utilizing a hybrid model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, referred to as the VGG-LSTM model. The proposed VGG-LSTM model leverages the power of deep learning to address the challenges associated with HAR, including capturing spatial features and modeling temporal dependencies in complex human activities. In this research, we employ the VGG architecture as the feature extractor to capture discriminative spatial information from input sensor data, such as images or videos. Furthermore, the LSTM layer is integrated to model the temporal dynamics of human activities. This enables the model to effectively recognize and differentiate between a wide range of human activities, such as walking, running, sitting, and more, in real-world scenarios. The research demonstrates the effectiveness of the VGG-LSTM model on benchmark datasets, achieving state-of-the-art performance in human activity recognition tasks. The model’s accuracy, robustness, and ability to generalize to diverse scenarios make it a promising solution for applications in healthcare, sports analytics, security, and beyond. The contributions of this paper lie in the development of a powerful hybrid model that combines spatial and temporal information seamlessly, improving the accuracy and applicability of HAR systems. The results underscore the potential of the VGG-LSTM model in advancing human activity recognition technology, with implications for improving the quality of life and safety in various domains.
43
Kolipaka, Venkata Rama Rao, e Anupama Namburu. "Integrating Temporal Fluctuations in Crop Growth with Stacked Bidirectional LSTM and 3D CNN Fusion for Enhanced Crop Yield Prediction". International Journal on Recent and Innovation Trends in Computing and Communication 11, n.º 9 (27 de outubro de 2023): 376–83. http://dx.doi.org/10.17762/ijritcc.v11i9.8543.
Texto completo da fonteResumo:
Optimizing farming methods and guaranteeing a steady supply of food depend critically on accurate predictions of crop yields. The dynamic temporal changes that occur during crop growth are generally ignored by conventional crop growth models, resulting in less precise projections. Using a stacked bidirectional Long Short-Term Memory (LSTM) structure and a 3D Convolutional Neural Network (CNN) fusion, we offer a novel neural network model that accounts for temporal oscillations in the crop growth process. The 3D CNN efficiently recovers spatial and temporal features from the crop development data, while the bidirectional LSTM cells capture the sequential dependencies and allow the model to learn from both past and future temporal information. Our model's prediction accuracy is improved by combining the LSTM and 3D CNN layers at the top, which better captures temporal and spatial patterns. We also provide a novel label-related loss function that is optimized for agricultural yield forecasting. Because of the relevance of temporal oscillations in crop development and the dynamic character of crop growth, a new loss function has been developed. This loss function encourages our model to learn and take advantage of the temporal trends, which improves our ability to estimate crop yield. We perform comprehensive experiments on real-world crop growth datasets to verify the efficacy of our suggested approach. The outcomes prove that our unified strategy performs far better than both baseline crop growth prediction algorithms and cutting-edge applications of deep learning. Improved crop yield prediction accuracy is achieved with the integration of temporal variations via the merging of bidirectional LSTM and 3D CNN and a unique loss function. This study helps move the science of estimating crop yields forward, which is important for informing agricultural policy and ensuring a steady supply of food.
44
Zhen, Peining, Hai-Bao Chen, Yuan Cheng, Zhigang Ji, Bin Liu e Hao Yu. "Fast Video Facial Expression Recognition by a Deeply Tensor-Compressed LSTM Neural Network for Mobile Devices". ACM Transactions on Internet of Things 2, n.º 4 (30 de novembro de 2021): 1–26. http://dx.doi.org/10.1145/3464941.
Texto completo da fonteResumo:
Mobile devices usually suffer from limited computation and storage resources, which seriously hinders them from deep neural network applications. In this article, we introduce a deeply tensor-compressed long short-term memory (LSTM) neural network for fast video-based facial expression recognition on mobile devices. First, a spatio-temporal facial expression recognition LSTM model is built by extracting time-series feature maps from facial clips. The LSTM-based spatio-temporal model is further deeply compressed by means of quantization and tensorization for mobile device implementation. Based on datasets of Extended Cohn-Kanade (CK+), MMI, and Acted Facial Expression in Wild 7.0, experimental results show that the proposed method achieves 97.96%, 97.33%, and 55.60% classification accuracy and significantly compresses the size of network model up to 221× with reduced training time per epoch by 60%. Our work is further implemented on the RK3399Pro mobile device with a Neural Process Engine. The latency of the feature extractor and LSTM predictor can be reduced 30.20× and 6.62× , respectively, on board with the leveraged compression methods. Furthermore, the spatio-temporal model costs only 57.19 MB of DRAM and 5.67W of power when running on the board.
45
Vaish, Rohan Kumar. "Stock Price Prediction Using LSTM Algorithm". INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, n.º 05 (28 de maio de 2024): 1–5. http://dx.doi.org/10.55041/ijsrem34831.
Texto completo da fonteResumo:
ock price prediction is a challenging task due to the volatile and non-linear nature of the financial markets. This paper explores the application of the Long Short-Term Memory (LSTM) neural network, a type of Recurrent Neural Network (RNN), for predicting stock prices. The study demonstrates the effectiveness of LSTM in capturing the temporal dependencies in stock price data, comparing its performance with traditional models.
46
Wang, Weilin, Wenjing Mao, Xueli Tong e Gang Xu. "A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction". Remote Sensing 13, n.º 7 (27 de março de 2021): 1284. http://dx.doi.org/10.3390/rs13071284.
Texto completo da fonteResumo:
Deep learning provides a promising approach for air pollution prediction. The existing deep learning-based predicted models generally consider either the temporal correlations of air quality monitoring stations or the nonlinear relationship between the PM2.5 (particulate matter with an aerodynamic diameter of less than 2.5 μm) concentrations and explanatory variables. Spatial correlation has not been effectively incorporated into prediction models, therefore exhibiting poor performance in PM2.5 prediction tasks. Additionally, determining the manner by which to expand longer-term prediction tasks is still challenging. In this paper, to allow for spatiotemporal correlations, a spatiotemporal convolutional recursive long short-term memory (CR-LSTM) neural network model is proposed for predicting the PM2.5 concentrations in long-term prediction tasks by combining a convolutional long short-term memory (ConvLSTM) neural network and a recursive strategy. Herein, the ConvLSTM network was used to capture the complex spatiotemporal correlations and to predict the future PM2.5 concentrations; the recursive strategy was used for expanding the long-term prediction tasks. The CR-LSTM model was used to realize the prediction of the future 24 h of PM2.5 concentrations for 12 air quality monitoring stations in Beijing by configuring both the appropriate time lag derived from the temporal correlations and the spatial neighborhood, including the hourly historical PM2.5 concentrations, the daily mean meteorological data, and the annual nighttime light and normalized difference vegetation index (NDVI). The results showed that the proposed CR-LSTM model achieved better performance (coefficient of determination (R2) = 0.74; root mean square error (RMSE) = 18.96 μg/m3) than other common models, such as multiple linear regression (MLR), support vector regression (SVR), the conventional LSTM model, the LSTM extended (LSTME) model, and the temporal sliding LSTM extended (TS-LSTME) model. The proposed CR-LSTM model, implementing a combination of geographical rules, recursive strategy, and deep learning, shows improved performance in longer-term prediction tasks.
47
Wang, Bowen, Liangzhi Li, Yuta Nakashima, Ryo Kawasaki, Hajime Nagahara e Yasushi Yagi. "Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation". IEEE Access 9 (2021): 46810–20. http://dx.doi.org/10.1109/access.2021.3067928.
Texto completo da fonte
48
Zhang, Bingbing, Qilong Wang, Zilin Gao, Ruiren Zeng e Peihua Li. "Temporal grafter network: Rethinking LSTM for effective video recognition". Neurocomputing 505 (setembro de 2022): 276–88. http://dx.doi.org/10.1016/j.neucom.2022.07.040.
Texto completo da fonte
49
Zhang, Wanruo, Guan Yao, Bo Yang, Wenfeng Zheng e Chao Liu. "Motion Prediction of Beating Heart Using Spatio-Temporal LSTM". IEEE Signal Processing Letters 29 (2022): 787–91. http://dx.doi.org/10.1109/lsp.2022.3154317.
Texto completo da fonte
50
Zhao, Zhen, Ze Li, Fuxin Li e Yang Liu. "CNN-LSTM Based Traffic Prediction Using Spatial-temporal Features". Journal of Physics: Conference Series 2037, n.º 1 (1 de setembro de 2021): 012065. http://dx.doi.org/10.1088/1742-6596/2037/1/012065.
Texto completo da fonte