Siga este link para ver outros tipos de publicações sobre o tema: Time-Aware LSTM.
Artigos de revistas sobre o tema "Time-Aware LSTM"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "Time-Aware LSTM".
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
Cheng, Lin, Yuliang Shi, Kun Zhang, Xinjun Wang e Zhiyong Chen. "GGATB-LSTM: Grouping and Global Attention-based Time-aware Bidirectional LSTM Medical Treatment Behavior Prediction". ACM Transactions on Knowledge Discovery from Data 15, n.º 3 (maio de 2021): 1–16. http://dx.doi.org/10.1145/3441454.
Texto completo da fonteResumo:
In China, with the continuous development of national health insurance policies, more and more people have joined the health insurance. How to accurately predict patients future medical treatment behavior becomes a hotspot issue. The biggest challenge in this issue is how to improve the prediction performance by modeling health insurance data with high-dimensional time characteristics. At present, most of the research is to solve this issue by using Recurrent Neural Networks (RNNs) to construct an overall prediction model for the medical visit sequences. However, RNNs can not effectively solve the long-term dependence, and RNNs ignores the importance of time interval of the medical visit sequence. Additionally, the global model may lose some important content to different groups. In order to solve these problems, we propose a Grouping and Global Attention based Time-aware Bidirectional Long Short-Term Memory (GGATB-LSTM) model to achieve medical treatment behavior prediction. The model first constructs a heterogeneous information network based on health insurance data, and uses a tensor CANDECOMP/PARAFAC decomposition method to achieve similarity grouping. In terms of group prediction, a global attention and time factor are introduced to extend the bidirectional LSTM. Finally, the proposed model is evaluated by using real dataset, and conclude that GGATB-LSTM is better than other methods.
2
Wiessner, Paul, Grigor Bezirganyan, Sana Sellami, Richard Chbeir e Hans-Joachim Bungartz. "Uncertainty-Aware Time Series Anomaly Detection". Future Internet 16, n.º 11 (31 de outubro de 2024): 403. http://dx.doi.org/10.3390/fi16110403.
Texto completo da fonteResumo:
Traditional anomaly detection methods in time series data often struggle with inherent uncertainties like noise and missing values. Indeed, current approaches mostly focus on quantifying epistemic uncertainty and ignore data-dependent uncertainty. However, consideration of noise in data is important as it may have the potential to lead to more robust detection of anomalies and a better capability of distinguishing between real anomalies and anomalous patterns provoked by noise. In this paper, we propose LSTMAE-UQ (Long Short-Term Memory Autoencoder with Aleatoric and Epistemic Uncertainty Quantification), a novel approach that incorporates both aleatoric (data noise) and epistemic (model uncertainty) uncertainties for more robust anomaly detection. The model combines the strengths of LSTM networks for capturing complex time series relationships and autoencoders for unsupervised anomaly detection and quantifies uncertainties based on the Bayesian posterior approximation method Monte Carlo (MC) Dropout, enabling a deeper understanding of noise recognition. Our experimental results across different real-world datasets show that consideration of uncertainty effectively increases the robustness to noise and point outliers, making predictions more reliable for longer periodic sequential data.
3
Yadulla, Akhila Reddy, Mounica Yenugula, Vinay Kumar Kasula, Bhargavi Konda, Santosh Reddy Addula e Sarath Babu Rakki. "A time-aware LSTM model for detecting criminal activities in blockchain transactions". International Journal of Communication and Information Technology 4, n.º 2 (1 de julho de 2023): 33–39. https://doi.org/10.33545/2707661x.2023.v4.i2a.108.
Texto completo da fonte
4
Yang, Xuan, e James A. Esquivel. "Time-Aware LSTM Neural Networks for Dynamic Personalized Recommendation on Business Intelligence". Tsinghua Science and Technology 29, n.º 1 (fevereiro de 2024): 185–96. http://dx.doi.org/10.26599/tst.2023.9010025.
Texto completo da fonte
5
Chen, Long, Zhiyao Tian, Shunhua Zhou, Quanmei Gong e Honggui Di. "Attitude deviation prediction of shield tunneling machine using Time-Aware LSTM networks". Transportation Geotechnics 45 (março de 2024): 101195. http://dx.doi.org/10.1016/j.trgeo.2024.101195.
Texto completo da fonte
6
Chen, Jie, Chang Liu, Jiawu Xie, Jie An e Nan Huang. "Time–Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation". Sensors 22, n.º 15 (26 de julho de 2022): 5598. http://dx.doi.org/10.3390/s22155598.
Texto completo da fonteResumo:
Underwater acoustic signal separation is a key technique for underwater communications. The existing methods are mostly model-based, and cannot accurately characterize the practical underwater acoustic communication environment. They are only suitable for binary signal separation and cannot handle multivariate signal separation. However, recurrent neural networks (RNNs) show a powerful ability to extract the features of temporal sequences. Inspired by this, in this paper, we present a data-driven approach for underwater acoustic signal separation using deep learning technology. We use a bidirectional long short-term memory (Bi-LSTM) approach to explore the features of a time–frequency (T-F) mask, and propose a T-F-mask-aware Bi-LSTM for signal separation. Taking advantage of the sparseness of the T-F image, the designed Bi-LSTM network is able to extract the discriminative features for separation, which further improves the separation performance. In particular, this method breaks through the limitations of the existing methods and not only achieves good results in multivariate separation but also effectively separates signals when they are mixed with 40 dB Gaussian noise signals. The experimental results show that this method can achieve a 97% guarantee ratio (PSR), and the average similarity coefficient of the multivariate signal separation is stable above 0.8 under high noise conditions. It should be noted that our model can only handle known signals such as test signals for calibration.
7
Zhang, Jinkai, Wenming Ma, En Zhang e Xuchen Xia. "Time-Aware Dual LSTM Neural Network with Similarity Graph Learning for Remote Sensing Service Recommendation". Sensors 24, n.º 4 (11 de fevereiro de 2024): 1185. http://dx.doi.org/10.3390/s24041185.
Texto completo da fonteResumo:
Technological progress has led to significant advancements in Earth observation and satellite systems. However, some services associated with remote sensing face issues related to timeliness and relevance, which affect the application of remote sensing resources in various fields and disciplines. The challenge now is to help end-users make precise decisions and recommendations for relevant resources that meet the demands of their specific domains from the vast array of remote sensing resources available. In this study, we propose a remote sensing resource service recommendation model that incorporates a time-aware dual LSTM neural network with similarity graph learning. We further use the stream push technology to enhance the model. We first construct interaction history behavior sequences based on users’ resource search history. Then, we establish a category similarity relationship graph structure based on the cosine similarity matrix between remote sensing resource categories. Next, we use LSTM to represent historical sequences and Graph Convolutional Networks (GCN) to represent graph structures. We construct similarity relationship sequences by combining historical sequences to explore exact similarity relationships using LSTM. We embed user IDs to model users’ unique characteristics. By implementing three modeling approaches, we can achieve precise recommendations for remote sensing services. Finally, we conduct experiments to evaluate our methods using three datasets, and the experimental results show that our method outperforms the state-of-the-art algorithms.
8
Zheng, Ruixuan, Yanping Bao, Lihua Zhao e Lidong Xing. "Prediction of steelmaking process variables using K-medoids and a time-aware LSTM network". Heliyon 10, n.º 12 (junho de 2024): e32901. http://dx.doi.org/10.1016/j.heliyon.2024.e32901.
Texto completo da fonte
9
Subapriya Vijayakumar e Rajaprakash Singaravelu. "Time Aware Long Short-Term Memory and Kronecker Gated Intelligent Transportation for Smart Car Parking". Journal of Advanced Research in Applied Sciences and Engineering Technology 44, n.º 1 (26 de abril de 2024): 134–50. http://dx.doi.org/10.37934/araset.44.1.134150.
Texto completo da fonteResumo:
Technology desires to improve quality of life and impart citizen’s health as well as happiness. The concept of Internet of Things (IoT) refers to smart world where prevailing objects are said to be embedded and hence interact with each other (i.e., between objects and human beings) to achieve an objective. In the period of IoT as well as smart city, there is requirement for Intelligent Transport System-based (ITS) ingenious smart parking or car parking space prediction (CPSP) for more feasible cities. With the increase in population and mushroom growth in vehicles are bringing about several distinct economic as well as environmental issues. One of pivotal ones is optimal parking space identification. To address on this problem, in this work, Time-aware Long Short-Term Memory and Kronecker product Gated Recurrent Unit (TLSTM-KGRU) for smart parking in internet of transportation things is proposed. The TLSTM-KGRU method is split into two sections. In the first section, smart parking occupancy is derived using Time-aware Long Short-Term Memory (Time-aware LSTM) for Kuala Lumpur Convention Centre car parking sensor dataset. Following which the resultant smart car occupancy results are subjected to Linear Interpolations and Kronecker product Gated Recurrent Unit for predicting smart parking. When compared against other predictive methods such as SGRU-LSTM and CPSP using DELM, our experimental outcomes denote that TLSTM-KGRU method has improved performance for smart parking occupancy forecast as it not only enhances sensitivity and specificity but also reduces prediction time with minimum delay.
10
Gui, Zhipeng, Yunzeng Sun, Le Yang, Dehua Peng, Fa Li, Huayi Wu, Chi Guo, Wenfei Guo e Jianya Gong. "LSI-LSTM: An attention-aware LSTM for real-time driving destination prediction by considering location semantics and location importance of trajectory points". Neurocomputing 440 (junho de 2021): 72–88. http://dx.doi.org/10.1016/j.neucom.2021.01.067.
Texto completo da fonte
11
Lees, Thomas, Marcus Buechel, Bailey Anderson, Louise Slater, Steven Reece, Gemma Coxon e Simon J. Dadson. "Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual models". Hydrology and Earth System Sciences 25, n.º 10 (21 de outubro de 2021): 5517–34. http://dx.doi.org/10.5194/hess-25-5517-2021.
Texto completo da fonteResumo:
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have demonstrated the applicability of LSTM-based models for rainfall–runoff modelling; however, LSTMs have not been tested on catchments in Great Britain (GB). Moreover, opportunities exist to use spatial and seasonal patterns in model performances to improve our understanding of hydrological processes and to examine the advantages and disadvantages of LSTM-based models for hydrological simulation. By training two LSTM architectures across a large sample of 669 catchments in GB, we demonstrate that the LSTM and the Entity Aware LSTM (EA LSTM) models simulate discharge with median Nash–Sutcliffe efficiency (NSE) scores of 0.88 and 0.86 respectively. We find that the LSTM-based models outperform a suite of benchmark conceptual models, suggesting an opportunity to use additional data to refine conceptual models. In summary, the LSTM-based models show the largest performance improvements in the north-east of Scotland and in south-east of England. The south-east of England remained difficult to model, however, in part due to the inability of the LSTMs configured in this study to learn groundwater processes, human abstractions and complex percolation properties from the hydro-meteorological variables typically employed for hydrological modelling.
12
Anan, Muhammad, Khalid Kanaan, Driss Benhaddou, Nidal Nasser, Basheer Qolomany, Hanaa Talei e Ahmad Sawalmeh. "Occupant-Aware Energy Consumption Prediction in Smart Buildings Using a LSTM Model and Time Series Data". Energies 17, n.º 24 (21 de dezembro de 2024): 6451. https://doi.org/10.3390/en17246451.
Texto completo da fonteResumo:
Accurate energy consumption prediction in commercial buildings is a challenging research task. Energy prediction plays a crucial role in energy efficiency, management, planning, sustainability, risk management, diagnosis, and demand response. Although many studies have been conducted on building energy predictions, the impact of occupancy on energy prediction models for office-type commercial buildings remains insufficiently explored, despite its potential to improve energy efficiency by 20%. This study investigates energy prediction using a Long Short-Term Memory (LSTM) model that incorporates time-series power consumption data and considers occupancy. A real-world dataset containing the per-minute electricity consumption of various appliances in an office building in Houston, TX, USA, is utilized. The proposed machine learning models forecast future energy consumption based on hourly, 3-hourly, daily, and quarterly predictions for individual appliances and total energy usage. The model’s performance is evaluated using the following three metrics: Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The results demonstrate the superiority of the proposed system.
13
Park, Hyun Joon, Min Seok Lee, Dong Il Park e Sung Won Han. "Time-Aware and Feature Similarity Self-Attention in Vessel Fuel Consumption Prediction". Applied Sciences 11, n.º 23 (4 de dezembro de 2021): 11514. http://dx.doi.org/10.3390/app112311514.
Texto completo da fonteResumo:
An accurate vessel fuel consumption prediction is essential for constructing a ship route network and vessel management, leading to efficient sailings. Besides, ship data from monitoring and sensing systems accelerate fuel consumption prediction research. However, the ship data consist of three properties: sequential, irregular time interval, and feature importance, making the predicting problem challenging. In this paper, we propose Time-aware Attention (TA) and Feature-similarity Attention (FA) applied to bi-directional Long Short-Term Memory (LSTM). TA acquires time importance by nonlinear function from irregular time intervals in each sequence and emphasizes data depending on the importance. FA emphasizes data based on similarities of features in the sequence by estimating feature importance with learnable parameters. Finally, we propose the ensemble model of TA and FA-based BiLSTM. The ensemble model, which consists of fully connected layers, is capable of simultaneously capturing different properties of ship data. The experimental results on ship data showed that the proposed model improves the performance in predicting fuel consumption. In addition to model performance, visualization results of attention maps and feature importance help to understand data properties and model characteristics.
14
Zhang, Jiangnan, Hai Wang, Fengjuan Cui, Yongshuo Liu, Zhenxing Liu e Junyu Dong. "Research into Ship Trajectory Prediction Based on An Improved LSTM Network". Journal of Marine Science and Engineering 11, n.º 7 (22 de junho de 2023): 1268. http://dx.doi.org/10.3390/jmse11071268.
Texto completo da fonteResumo:
The establishment of ship trajectory prediction is critical in analyzing trajectory data. It serves as a critical reference point for identifying abnormal behavior and potential collision risks for ships. Accurate and real-time ship trajectory prediction is essential during navigation. Since the timing of automatic identification system (AIS) data is irregular, traditional methods usually use time calibration to simulate the data of uniform sequencing before analysis. Inevitably, this increases the chances of error and time delays. To address this issue, we propose a time-aware LSTM (T-LSTM) single-ship trajectory model combined with the generative adversarial network (GAN) to predict multiple ship trajectories. These analysis methods are capable of directly analyzing AIS data and have demonstrated better performance in both single-ship and multi-ship trajectories. Our experimental results show that the proposed method achieves high accuracy and can meet the practical navigation requirements of ships.
15
Kim, Jonghong, Inchul Choi e Minho Lee. "Context Aware Video Caption Generation with Consecutive Differentiable Neural Computer". Electronics 9, n.º 7 (17 de julho de 2020): 1162. http://dx.doi.org/10.3390/electronics9071162.
Texto completo da fonteResumo:
Recent video captioning models aim at describing all events in a long video. However, their event descriptions do not fully exploit the contextual information included in a video because they lack the ability to remember information changes over time. To address this problem, we propose a novel context-aware video captioning model that generates natural language descriptions based on the improved video context understanding. We introduce an external memory, differential neural computer (DNC), to improve video context understanding. DNC naturally learns to use its internal memory for context understanding and also provides contents of its memory as an output for additional connection. By sequentially connecting DNC-based caption models (DNC augmented LSTM) through this memory information, our consecutively connected DNC architecture can understand the context in a video without explicitly searching for event-wise correlation. Our consecutive DNC is sequentially trained with its language model (LSTM) for each video clip to generate context-aware captions with superior quality. In experiments, we demonstrate that our model provides more natural and coherent captions which reflect previous contextual information. Our model also shows superior quantitative performance on video captioning in terms of BLEU (BLEU@4 4.37), METEOR (9.57), and CIDEr-D (28.08).
16
Ng, Yu Nie, Han Ying Lim, Ying Chyi Cham, Mohd Aftar Abu Bakar e Noratiqah Mohd Ariff. "Comparison Between LSTM, GRU and VARIMA in Forecasting of Air Quality Time Series Data". Malaysian Journal of Fundamental and Applied Sciences 20, n.º 6 (16 de dezembro de 2024): 1248–60. https://doi.org/10.11113/mjfas.v20n6.3411.
Texto completo da fonteResumo:
Air quality forecast is essential in alerting the public, especially those who have respiratory diseases, to take necessary precautions beforehand. The public can be forewarned of any worsening of air quality and be aware of the importance of reducing air pollution. In recent years, forecasting techniques based on deep learning algorithms such as recurrent neural network (RNN) have seen improvements in both accuracy and execution speed. Long short-term memory (LSTM) network and gated recurrent unit (GRU) are among the most popular variants of RNN. In this study, the hourly PM2.5 concentrations at five selected air quality monitoring stations, provided by the Department of Environment Malaysia, are forecasted using LSTM, GRU and vector autoregressive integrated moving average (VARIMA) models respectively. Data containing missing, negative and zero values are pre-processed using an interpolation technique before being split into training and test sets on an 80:20 ratio basis. Optimal combinations of hyperparameter values are selected via manual tuning based on the 10-fold growing window cross-validation results. The model performance is evaluated based on RMSE, MAE and MAPE. The results demonstrate that neural network models significantly outperform the multivariate time series model in which the LSTM and GRU models have comparable performance in forecasting the hourly PM2.5 concentration, with a slightly better prediction in the west coast region for LSTM and the east coast region for GRU. However, due to the complex architecture of neural networks, the computational time to train both LSTM and GRU models is three times longer than that for VARIMA. Additionally, it is observed that a higher percentage of interpolated values leads to lower prediction errors.
17
Yuan, Xiaofeng, Lin Li, Kai Wang e Yalin Wang. "Sampling-Interval-Aware LSTM for Industrial Process Soft Sensing of Dynamic Time Sequences With Irregular Sampling Measurements". IEEE Sensors Journal 21, n.º 9 (1 de maio de 2021): 10787–95. http://dx.doi.org/10.1109/jsen.2021.3056210.
Texto completo da fonte
18
Ozpinar, Alper, e Arma Deger Mut. "Multidimensional Next-Generation Time and Transition-Aware Product Recommendation System". European Journal of Research and Development 4, n.º 2 (31 de maio de 2024): 229–46. http://dx.doi.org/10.56038/ejrnd.v4i2.458.
Texto completo da fonteResumo:
In the dynamic landscape of e-commerce, the proliferation of products has immensely complicated the process of effective product discovery. With over 14 million items listed on platforms such as Pazarama.com, consumers often struggle to navigate through extensive catalogs to find products that genuinely meet their evolving needs. This challenge is exacerbated in categories requiring sequential consumption, such as baby products, where the progression from one product stage to another is not only inevitable but critical. Traditional recommendation systems primarily rely on static historical data. While these systems provide baseline suggestions based on past purchases or general popularity, they often fail to capture the nuanced and immediate requirements of consumers. For instance, a parent purchasing size one diapers will soon need to transition to size two, and a static system might continue to recommend size one, ignoring the child's growth. Moreover, these systems are not equipped to handle anomalies or data inconsistencies, often stemming from privacy regulations like the General Data Protection Regulation (GDPR), which can skew the effectiveness of the recommendations provided. This paper proposes a novel approach that integrates Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks to develop a multidimensional, next-generation product recommendation system. This system accommodates time-sensitive needs and transitions in consumer product stages, predicting future product requirements based on evolving consumer stages while handling anomalies and data inconsistencies due to privacy concerns. Furthermore, it offers real-time updates and integrates seamlessly with social media and online platforms to enhance user engagement and satisfaction. By employing time series analysis and advanced AI techniques, this model aims to improve the accuracy of personalized recommendations, support the introduction and marketing of new or rare products, and ultimately enhance the overall user experience on platforms like Pazarama.com. Through this approach, the paper demonstrates the potential for advanced recommendation systems to transform online retail environments by increasing sales, enhancing customer interaction, and expanding the technological repertoire of e-commerce platforms.
19
Kratzert, Frederik, Daniel Klotz, Guy Shalev, Günter Klambauer, Sepp Hochreiter e Grey Nearing. "Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets". Hydrology and Earth System Sciences 23, n.º 12 (17 de dezembro de 2019): 5089–110. http://dx.doi.org/10.5194/hess-23-5089-2019.
Texto completo da fonteResumo:
Abstract. Regional rainfall–runoff modeling is an old but still mostly outstanding problem in the hydrological sciences. The problem currently is that traditional hydrological models degrade significantly in performance when calibrated for multiple basins together instead of for a single basin alone. In this paper, we propose a novel, data-driven approach using Long Short-Term Memory networks (LSTMs) and demonstrate that under a “big data” paradigm, this is not necessarily the case. By training a single LSTM model on 531 basins from the CAMELS dataset using meteorological time series data and static catchment attributes, we were able to significantly improve performance compared to a set of several different hydrological benchmark models. Our proposed approach not only significantly outperforms hydrological models that were calibrated regionally, but also achieves better performance than hydrological models that were calibrated for each basin individually. Furthermore, we propose an adaption to the standard LSTM architecture, which we call an Entity-Aware-LSTM (EA-LSTM), that allows for learning catchment similarities as a feature layer in a deep learning model. We show that these learned catchment similarities correspond well to what we would expect from prior hydrological understanding.
20
Zhang, Jiajun. "Time Series Analysis of Greenhouse Gas Emission Based on ARIMA and LSTM". Highlights in Science, Engineering and Technology 76 (31 de dezembro de 2023): 378–84. http://dx.doi.org/10.54097/zy49qb44.
Texto completo da fonteResumo:
Greenhouse gas emissions have become a topic of great concern, and research on the prediction of greenhouse gas emissions is urgently needed. In this paper, based on the GHG emission data from 1990-2018, it applied ARIMA model and LSTM model to predict future GHG emissions, and evaluated their prediction performance using MAE. According to the analysis, the results show that the ARIMA model can more accurately capture the trend and seasonal characteristics in the greenhouse gas emission data, and generate prediction results that match the actual observations. Moreover, this study confirmed the effectiveness and feasibility of ARIMA and LSTM models in greenhouse gas emission prediction. At the same time, one must also be aware that greenhouse gas emission forecasts still face limitations such as data reliability, model assumptions, and policy uncertainties. Future research can further improve model performance and explore more comprehensive predictive models to improve accuracy. Overall, these results shed light on guiding further exploration of gas emission analysis.
21
Palanichamy, Indurani, e Firdaus Begam Basheer Ahamed. "Prediction of Seizure in the EEG Signal with Time Aware Recurrent Neural Network". Revue d'Intelligence Artificielle 36, n.º 5 (23 de dezembro de 2022): 717–24. http://dx.doi.org/10.18280/ria.360508.
Texto completo da fonteResumo:
The human brain's actions are reflected by the significant physiological data relying on the Electroencephalogram (EEG), which is utilized in the detection of epileptic seizures and the diagnosis of epilepsy. The visual inspection process of a vast quantity of EEG data by any human expert is time-consuming and the judgemental process may vary or be inconsistent among the physician. Hence, an automated process in detection and diagnosis is initiated by utilizing deep learning approaches. The Convolutional Neural Network (CNN) is incorporated to correctly recognize the irregular inter-ictal discharges as non-seizures, but could not detect the ictal state and slower oscillations. To improve the performance of CNN for detecting seizures' ictal state and slower oscillations, Recurrent Neural Network (RNN) is combined with the CNN model. An RNN evokes every processed information via time and it assists in the prediction of time series data. The processed feature in RNN remembers the preceding input information which is Long Short Term Memory (LSTM). The investigational outcome of the proposed Time Aware CNN and Recurrent Neural Network (TA-CNN-RNN) attained effective classification accuracy. The experiments analysis exhibits that the TA-CNN-RNN achieves an accuracy of 89%, 88.6%, and 88.7% on CHB-MIT-EEG, Bonn-iEEG, and VIRGO-EEG databases, respectively compared to the Entropy+LSSVM, LBP+KNN and P-one-class SVM methods for epilepsy detection.
22
Yuan, Yuan, Yuying Zhou, Xuanyou Chen, Qi Xiong e Hector Chimeremeze Okere. "Enhancing Recommendation Diversity and Novelty with Bi-LSTM and Mean Shift Clustering". Electronics 13, n.º 19 (28 de setembro de 2024): 3841. http://dx.doi.org/10.3390/electronics13193841.
Texto completo da fonteResumo:
In the digital age, personalized recommendation systems have become crucial for information dissemination and user experience. While traditional systems focus on accuracy, they often overlook diversity, novelty, and serendipity. This study introduces an innovative recommendation system model, Time-based Outlier Aware Recommender (TOAR), designed to address the challenges of content homogenization and information bubbles in personalized recommendations. TOAR integrates Neural Matrix Factorization (NeuMF), Bidirectional Long Short-Term Memory Networks (Bi-LSTM), and Mean Shift clustering to enhance recommendation accuracy, novelty, and diversity. The model analyzes temporal dynamics of user behavior and facilitates cross-domain knowledge exchange through feature sharing and transfer learning mechanisms. By incorporating an attention mechanism and unsupervised clustering, TOAR effectively captures important time-series information and ensures recommendation diversity. Experimental results on a news recommendation dataset demonstrate TOAR’s superior performance across multiple metrics, including AUC, precision, NDCG, and novelty, compared to traditional and deep learning-based recommendation models. This research provides a foundation for developing more intelligent and personalized recommendation services that balance accuracy with content diversity.
23
Mehta, Amiben Maheshbhai, e Kajal S. Patel. "LSTM-based Forecasting of Dengue Cases in Gujarat: A Machine Learning Approach". Indian Journal Of Science And Technology 17, n.º 7 (15 de fevereiro de 2024): 635–42. http://dx.doi.org/10.17485/ijst/v17i7.2748.
Texto completo da fonteResumo:
Objectives: Dengue fever, a mosquito-borne viral disease, is particularly prevalent in tropical regions like India. Gujarat State is also one of them. Forecasting outbreaks of diseases such as dengue can prove important for public health management. The purpose of this study is to predict dengue cases in ten districts of Gujarat using the LSTM machine learning model. And if people are aware of this from the beginning, the spread of dengue can be prevented. Methods: This approach uses LSTM models to predict dengue cases using a total of 10 years (2010 to 2019) of data. From this data, data from 2010 to 2016 is used for training and data from 2017 to 2019 is used for testing. To predict dengue cases, population density, average temperature, average humidity, monthly rainfall, dengue cases with lag of one, two and twelve months. Findings: The LSTM model was applied with different parameter configurations, showing the following results: The root mean square error value is 0.04, and the R-squared (R2) score is 0.84. Many machine learning methods, like ANN, linear regression, random forest, etc., have been used to predict dengue cases in different states and countries. LSTM model gives the best results in terms of accuracy. Previously reported dengue cases, population density, and total monthly rainfall proved to be the most effective predictors of dengue in the state of Gujarat. Novelty: Models have been developed to predict dengue outbreaks in many other countries and states. The LSTM model is developed for the first time in this study for the state of Gujarat. 84% accuracy is obtained from the model. This model has been prepared by collecting environmental data and registered dengue cases in Gujarat state. Keywords: Dengue Cases Predictions, Artificial Intelligence in Healthcare, LSTM Algorithm, Disease Outbreaks, Public Health Management
24
Yaprakdal, Fatma, e Merve Varol Arısoy. "A Multivariate Time Series Analysis of Electrical Load Forecasting Based on a Hybrid Feature Selection Approach and Explainable Deep Learning". Applied Sciences 13, n.º 23 (4 de dezembro de 2023): 12946. http://dx.doi.org/10.3390/app132312946.
Texto completo da fonteResumo:
In the smart grid paradigm, precise electrical load forecasting (ELF) offers significant advantages for enhancing grid reliability and informing energy planning decisions. Specifically, mid-term ELF is a key priority for power system planning and operation. Although statistical methods were primarily used because ELF is a time series problem, deep learning (DL)-based forecasting approaches are more commonly employed and successful in achieving precise predictions. However, these DL-based techniques, known as black box models, lack interpretability. When interpreting the DL model, employing explainable artificial intelligence (XAI) yields significant advantages by extracting meaningful information from the DL model outputs and the causal relationships among various factors. On the contrary, precise load forecasting necessitates employing feature engineering to identify pertinent input features and determine optimal time lags. This research study strives to accomplish a mid-term forecast of ELF study load utilizing aggregated electrical load consumption data, while considering the aforementioned critical aspects. A hybrid framework for feature selection and extraction is proposed for electric load forecasting. Technical term abbreviations are explained upon first use. The feature selection phase employs a combination of filter, Pearson correlation (PC), embedded random forest regressor (RFR) and decision tree regressor (DTR) methods to determine the correlation and significance of each feature. In the feature extraction phase, we utilized a wrapper-based technique called recursive feature elimination cross-validation (RFECV) to eliminate redundant features. Multi-step-ahead time series forecasting is conducted utilizing three distinct long-short term memory (LSTM) models: basic LSTM, bi-directional LSTM (Bi-LSTM) and attention-based LSTM models to accurately predict electrical load consumption thirty days in advance. Through numerous studies, a reduction in forecasting errors of nearly 50% has been attained. Additionally, the local interpretable model-agnostic explanations (LIME) methodology, which is an explainable artificial intelligence (XAI) technique, is utilized for explaining the mid-term ELF model. As far as the authors are aware, XAI has not yet been implemented in mid-term aggregated energy forecasting studies utilizing the ELF method. Quantitative and detailed evaluations have been conducted, with the experimental results indicating that this comprehensive approach is entirely successful in forecasting multivariate mid-term loads.
25
Wang, Yakun, Yajun Du, Jinrong Hu, Xianyong Li e Xiaoliang Chen. "SAEP: A Surrounding-Aware Individual Emotion Prediction Model Combined with T-LSTM and Memory Attention Mechanism". Applied Sciences 11, n.º 23 (23 de novembro de 2021): 11111. http://dx.doi.org/10.3390/app112311111.
Texto completo da fonteResumo:
The future emotion prediction of users on social media has been attracting increasing attention from academics. Previous studies on predicting future emotion have focused on the characteristics of individuals’ emotion changes; however, the role of the individual’s neighbors has not yet been thoroughly researched. To fill this gap, a surrounding-aware individual emotion prediction model (SAEP) based on a deep encoder–decoder architecture is proposed to predict individuals’ future emotions. In particular, two memory-based attention networks are constructed: The time-evolving attention network and the surrounding attention network to extract the features of the emotional changes of users and neighbors, respectively. Then, these features are incorporated into the emotion prediction task. In addition, a novel variant LSTM is introduced as the encoder of the proposed model, which can effectively extract complex patterns of users’ emotional changes from irregular time series. Extensive experimental results show that the proposed approach outperforms five alternative methods. The SAEP approach has improved by approximately 4.21–14.84% micro F1 on a dataset built from Twitter and 7.30–13.41% on a dataset built from Microblog. Further analyses validate the effectiveness of the proposed time-evolving context and surrounding context, as well as the factors that may affect the prediction results.
26
Pan, Feng, Bingyao Huang, Chunhong Zhang, Xinning Zhu, Zhenyu Wu, Moyu Zhang, Yang Ji, Zhanfei Ma e Zhengchen Li. "A survival analysis based volatility and sparsity modeling network for student dropout prediction". PLOS ONE 17, n.º 5 (5 de maio de 2022): e0267138. http://dx.doi.org/10.1371/journal.pone.0267138.
Texto completo da fonteResumo:
Student Dropout Prediction (SDP) is pivotal in mitigating withdrawals in Massive Open Online Courses. Previous studies generally modeled the SDP problem as a binary classification task, providing a single prediction outcome. Accordingly, some attempts introduce survival analysis methods to achieve continuous and consistent predictions over time. However, the volatility and sparsity of data always weaken the models’ performance. Prevailing solutions rely heavily on data pre-processing independent of predictive models, which are labor-intensive and may contaminate authentic data. This paper proposes a Survival Analysis based Volatility and Sparsity Modeling Network (SAVSNet) to address these issues in an end-to-end deep learning framework. Specifically, SAVSNet smooths the volatile time series by convolution network while preserving the original data information using Long-Short Term Memory Network (LSTM). Furthermore, we propose a Time-Missing-Aware LSTM unit to mitigate the impact of data sparsity by integrating informative missingness patterns into the model. A survival analysis loss function is adopted for parameter estimation, and the model outputs monotonically decreasing survival probabilities. In the experiments, we compare the proposed method with state-of-the-art methods in two real-world MOOC datasets, and the experiment results show the effectiveness of our proposed model.
27
Puchała, Sebastian, Włodzimierz Kasprzak e Paweł Piwowarski. "Human Interaction Classification in Sliding Video Windows Using Skeleton Data Tracking and Feature Extraction". Sensors 23, n.º 14 (10 de julho de 2023): 6279. http://dx.doi.org/10.3390/s23146279.
Texto completo da fonteResumo:
A “long short-term memory” (LSTM)-based human activity classifier is presented for skeleton data estimated in video frames. A strong feature engineering step precedes the deep neural network processing. The video was analyzed in short-time chunks created by a sliding window. A fixed number of video frames was selected for every chunk and human skeletons were estimated using dedicated software, such as OpenPose or HRNet. The skeleton data for a given window were collected, analyzed, and eventually corrected. A knowledge-aware feature extraction from the corrected skeletons was performed. A deep network model was trained and applied for two-person interaction classification. Three network architectures were developed—single-, double- and triple-channel LSTM networks—and were experimentally evaluated on the interaction subset of the ”NTU RGB+D” data set. The most efficient model achieved an interaction classification accuracy of 96%. This performance was compared with the best reported solutions for this set, based on “adaptive graph convolutional networks” (AGCN) and “3D convolutional networks” (e.g., OpenConv3D). The sliding-window strategy was cross-validated on the ”UT-Interaction” data set, containing long video clips with many changing interactions. We concluded that a two-step approach to skeleton-based human activity classification (a skeleton feature engineering step followed by a deep neural network model) represents a practical tradeoff between accuracy and computational complexity, due to an early correction of imperfect skeleton data and a knowledge-aware extraction of relational features from the skeletons.
28
Alam, Kazi Nabiul, Md Shakib Khan, Abdur Rab Dhruba, Mohammad Monirujjaman Khan, Jehad F. Al-Amri, Mehedi Masud e Majdi Rawashdeh. "Deep Learning-Based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter Data". Computational and Mathematical Methods in Medicine 2021 (2 de dezembro de 2021): 1–15. http://dx.doi.org/10.1155/2021/4321131.
Texto completo da fonteResumo:
The COVID-19 pandemic has had a devastating effect on many people, creating severe anxiety, fear, and complicated feelings or emotions. After the initiation of vaccinations against coronavirus, people’s feelings have become more diverse and complex. Our aim is to understand and unravel their sentiments in this research using deep learning techniques. Social media is currently the best way to express feelings and emotions, and with the help of Twitter, one can have a better idea of what is trending and going on in people’s minds. Our motivation for this research was to understand the diverse sentiments of people regarding the vaccination process. In this research, the timeline of the collected tweets was from December 21 to July21. The tweets contained information about the most common vaccines available recently from across the world. The sentiments of people regarding vaccines of all sorts were assessed using the natural language processing (NLP) tool, Valence Aware Dictionary for sEntiment Reasoner (VADER). Initializing the polarities of the obtained sentiments into three groups (positive, negative, and neutral) helped us visualize the overall scenario; our findings included 33.96% positive, 17.55% negative, and 48.49% neutral responses. In addition, we included our analysis of the timeline of the tweets in this research, as sentiments fluctuated over time. A recurrent neural network- (RNN-) oriented architecture, including long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM), was used to assess the performance of the predictive models, with LSTM achieving an accuracy of 90.59% and Bi-LSTM achieving 90.83%. Other performance metrics such as precision,, F1-score, and a confusion matrix were also used to validate our models and findings more effectively. This study improves understanding of the public’s opinion on COVID-19 vaccines and supports the aim of eradicating coronavirus from the world.
29
Faudzi, A. A. M., M. M. Raslan e N. E. Alias. "IoT based real-time monitoring system of rainfall and water level for flood prediction using LSTM Network". IOP Conference Series: Earth and Environmental Science 1143, n.º 1 (1 de fevereiro de 2023): 012015. http://dx.doi.org/10.1088/1755-1315/1143/1/012015.
Texto completo da fonteResumo:
Abstract Floods in recent years have frequently resulted in environmental, economic, as well as loss of human life. People are less aware of incoming floods if there is no early warning system. This proposal outlines the design of a monitoring system to obtain real-time data on rain gauge and water level. The monitoring system is based on IoT via a GSM network to provide real-time data cloud and dashboard display on Grafana platform. The rainfall forecasting model used Long Short-Term Memory (LSTM) networks to predict future rainfall and water level values which could cause floods. The result was experimented with using historical data since the current data of the monitoring system is insufficient yet to make an accurate prediction. The main findings of the research are the predicted values of streamflow and rainfall for historical data, also water level and rain gauge for new data. The primary result was experimented with using historical data on two rainfall stations and one streamflow. Also, the primary result was experimented with using new data on two water level stations and one rainfall. The forecasting method that applied LSTM showed high accuracy of the result reaching more than 90%. Based on these results, the system can be used as a non-structural solution to alleviate the damage caused by urban floods.
30
Ni, Xiang, Jing Li, Mo Yu, Wang Zhou e Kun-Lung Wu. "Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning". Proceedings of the AAAI Conference on Artificial Intelligence 34, n.º 01 (3 de abril de 2020): 857–64. http://dx.doi.org/10.1609/aaai.v34i01.5431.
Texto completo da fonteResumo:
This paper considers the problem of resource allocation in stream processing, where continuous data flows must be processed in real time in a large distributed system. To maximize system throughput, the resource allocation strategy that partitions the computation tasks of a stream processing graph onto computing devices must simultaneously balance workload distribution and minimize communication. Since this problem of graph partitioning is known to be NP-complete yet crucial to practical streaming systems, many heuristic-based algorithms have been developed to find reasonably good solutions. In this paper, we present a graph-aware encoder-decoder framework to learn a generalizable resource allocation strategy that can properly distribute computation tasks of stream processing graphs unobserved from training data. We, for the first time, propose to leverage graph embedding to learn the structural information of the stream processing graphs. Jointly trained with the graph-aware decoder using deep reinforcement learning, our approach can effectively find optimized solutions for unseen graphs. Our experiments show that the proposed model outperforms both METIS, a state-of-the-art graph partitioning algorithm, and an LSTM-based encoder-decoder model, in about 70% of the test cases.
31
Alsaedi, Faisal, e Sara Masoud. "Condition-Based Maintenance for Degradation-Aware Control Systems in Continuous Manufacturing". Machines 13, n.º 2 (12 de fevereiro de 2025): 141. https://doi.org/10.3390/machines13020141.
Texto completo da fonteResumo:
To enhance maintenance endeavors, it is imperative to gain a deep understanding of system degradation. In systems with degradation-aware control, observing degradation becomes particularly challenging. Even with sensors, such controllers continuously mitigate deviations to ensure the system operates within optimal limits. Here, we propose a framework explicitly tailored for degradation-aware control systems, built upon two main components: (1) degradation modeling to estimate and track hidden degradation over time and (2) a Long Short-Term Memory Autoencoder-Degradation Stage Detector (A-LSTMA-DSD) to define alarm and failure thresholds for enabling condition-based maintenance. In degradation modeling, the framework utilizes actuator measurements to model hidden degradation. Next, an A-LSTMA-DSD model is developed to flag anomalies, based on which alarm and failure thresholds are assigned. These dynamic thresholds are defined to ensure sufficient time for addressing maintenance requirements. Working with real data from a boiler unit in an oil refinery and focusing on steam leakages, our proposed framework successfully identified all failures and on average triggered alarm and failure thresholds 15 and 8 days in advance of failures, respectively. In addition to triggering these thresholds, our system outperforms baseline models, such as CNN, LSTM, ANN, ARIMA, and Facebook Profit, in identifying failures by 60% and 95%, respectively.
32
Tam, Prohim, Seungwoo Kang, Seyha Ros e Seokhoon Kim. "Enhancing QoS with LSTM-Based Prediction for Congestion-Aware Aggregation Scheduling in Edge Federated Learning". Electronics 12, n.º 17 (27 de agosto de 2023): 3615. http://dx.doi.org/10.3390/electronics12173615.
Texto completo da fonteResumo:
The advancement of the sensing capabilities of end devices drives a variety of data-intensive insights, yielding valuable information for modelling intelligent industrial applications. To apply intelligent models in 5G and beyond, edge intelligence integrates edge computing systems and deep learning solutions, which enables distributed model training and inference. Edge federated learning (EFL) offers collaborative edge intelligence learning with distributed aggregation capabilities, promoting resource efficiency, participant inclusivity, and privacy preservation. However, the quality of service (QoS) faces challenges due to congestion problems that arise from the diverse models and data in practical architectures. In this paper, we develop a modified long short-term memory (LSTM)-based congestion-aware EFL (MLSTM-CEFL) approach that aims to enhance QoS in the final model convergence between end devices, edge aggregators, and the global server. Given the diversity of service types, MLSTM-CEFL proactively detects the congestion rates, adequately schedules the edge aggregations, and effectively prioritizes high mission-critical serving resources. The proposed system is formulated to handle time series analysis from local/edge model parameter loading, weighing the configuration of resource pooling properties at specific congestion intervals. The MLSTM-CEFL policy orchestrates the establishment of long-term paths for participant-aggregator scheduling and follows the expected QoS metrics after final averaging in multiple industrial application classes.
33
Abdullah, Hazem salim. "A comparison of several intrusion detection methods using the NSL-KDD dataset". Wasit Journal of Computer and Mathematics Science 3, n.º 2 (30 de junho de 2024): 32–41. http://dx.doi.org/10.31185/wjcms.251.
Texto completo da fonteResumo:
The increasing significance of cybersecurity underscores the critical necessity of addressing evolving methods of hackers. This research investigates the way to classify and predict cyber-attacks on the NSL-KDD dataset using intrusion detection methods the investigation contrasts the capabilities of various algorithms, including RNN, MLP, CNN-LSTM, and ANN, in recognizing attacks. The results indicate that both MLP and RNN have the greatest efficiency and effectiveness for different time frames. these findings demonstrate the necessity of Constant evaluation and enhancement of intrusion detection systems in order to remain aware of the dynamic nature of the cyber threat landscape. Addressing cybersecurity issues necessitates a comprehensive approach that combines computational enhancements, human talent, organizational policies, and regulatory frameworks in order to create a powerful and stable cybersecurity system.
34
Yang, Hui, e Changchun Yang. "TIGNN-RL: Enabling time-sensitive and context-aware intelligent decision-making with dynamic graphs in recommender systems and biomechanics knowledge". Molecular & Cellular Biomechanics 22, n.º 3 (13 de fevereiro de 2025): 1339. https://doi.org/10.62617/mcb1339.
Texto completo da fonteResumo:
Intelligent decision-making in dynamic recommender systems is crucial for capturing temporal user preferences and optimizing long-term user satisfaction. Traditional recommender systems often rely on static modeling, neglecting the temporal dynamics of user-item interactions. To address this limitation, we propose a novel framework, Temporal Interpretability Graph Neural Network with Reinforcement Learning (TIGNN-RL), which integrates dynamic graph neural networks (DGNNs) and Proximal Policy Optimization (PPO) to optimize personalized recommendations. Specifically, our method models user-item interactions as dynamic graphs and utilizes temporal interpretability modules to encode both temporal features and node-specific static features. The temporal interpretability module assigns time-aware and interactions weights to user-item, enabling more time-sensitive and explainable dynamic embeddings. This TIGNN dynamic graph sequential embedding is processed by some LSTM modules to be used as the state of the deep reinforcement learning agent and states. We take a joint approach to training, earn graph embeddings that enable better PPO policy. To evaluate the proposed framework, we conduct experiments on three benchmark datasets: Last.fm 1K, MovieLens 1M, and Amazon Product Review. Results show that TIGNN-RL outperforms state-of-the-art baselines, which use GNNs for augmenting DRL-based RS, in terms of accuracy (NDCG@K) and diversity (ILD@K@K), demonstrating its effectiveness in dynamic and interpretable recommendation scenarios. In this research, some biomechanics knowledge is integrated to further enhance the understanding and application of the proposed framework in scenarios where user behavior is influenced by physical factors.
35
Ibnu Sina, Muhammad Noer, e Erwin Budi Setiawan. "Stock Price Correlation Analysis with Twitter Sentiment Analysis Using The CNN-LSTM Method". sinkron 8, n.º 4 (1 de outubro de 2023): 2190–202. http://dx.doi.org/10.33395/sinkron.v8i4.12855.
Texto completo da fonteResumo:
The intricate interplay between stock prices, reflecting a company's intrinsic value, and multifaceted factors like economic conditions, corporate performance, and market sentiment, constitutes a vital research domain. Grounded in sentiment analysis, our study deciphers public opinions from vast textual data to gauge sentiment, leveraging Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. We focus on Bank Central Asia (BBCA), a prominent Indonesian banking institution, aiming to forecast stock price fluctuations by analyzing sentiment trends extracted from social media, especially Twitter. Meticulous experimentation, encompassing data segmentation, feature extraction, augmentation, and model refinement, yields significant enhancements in prediction accuracy. The CNN-LSTM model's performance improves from 73.41% to a robust 77.75% accuracy, with F1-scores rising from 73.00% to 75.42%. Importantly, strong correlations emerge between sentiment predictions and actual stock price movements, validated by Spearman correlation coefficients. Positive sentiment exhibits a substantial correlation of 0.745 with stock price changes, while negative sentiment exerts notable influence with a correlation coefficient of 0.691. In summary, our study advances the field of sentiment-driven stock price prediction, showcasing deep learning's effectiveness in extracting sentiment from social media narratives. The implications extend to understanding market dynamics and potentially integrating sentiment-aware strategies into financial decision-making. Future research directions could explore model transferability across financial contexts, real-time sentiment data integration, and interpretability techniques for enhanced practicality in sentiment-driven predictions.
36
Cayme, Karl Jensen, Vince Andrei Retutal, Miguel Edwin Salubre, Philip Virgil Astillo, Luis Gerardo Cañete e Gaurav Choudhary. "Gesture Recognition of Filipino Sign Language Using Convolutional and Long Short-Term Memory Deep Neural Networks". Knowledge 4, n.º 3 (8 de julho de 2024): 358–81. http://dx.doi.org/10.3390/knowledge4030020.
Texto completo da fonteResumo:
In response to the recent formalization of Filipino Sign Language (FSL) and the lack of comprehensive studies, this paper introduces a real-time FSL gesture recognition system. Unlike existing systems, which are often limited to static signs and asynchronous recognition, it offers dynamic gesture capturing and recognition of 10 common expressions and five transactional inquiries. To this end, the system sequentially employs cropping, contrast adjustment, grayscale conversion, resizing, and normalization of input image streams. These steps serve to extract the region of interest, reduce the computational load, ensure uniform input size, and maintain consistent pixel value distribution. Subsequently, a Convolutional Neural Network and Long-Short Term Memory (CNN-LSTM) model was employed to recognize nuances of real-time FSL gestures. The results demonstrate the superiority of the proposed technique over existing FSL recognition systems, achieving an impressive average accuracy, recall, and precision rate of 98%, marking an 11.3% improvement in accuracy. Furthermore, this article also explores lightweight conversion methods, including post-quantization and quantization-aware training, to facilitate the deployment of the model on resource-constrained platforms. The lightweight models show a significant reduction in model size and memory utilization with respect to the base model when executed in a Raspberry Pi minicomputer. Lastly, the lightweight model trained with the quantization-aware technique (99%) outperforms the post-quantization approach (97%), showing a notable 2% improvement in accuracy.
37
Islam, Muhammad Zubair, A. S. M. Sharifuzzaman Sagar e Hyung Seok Kim. "Enabling Pandemic-Resilient Healthcare: Edge-Computing-Assisted Real-Time Elderly Caring Monitoring System". Applied Sciences 14, n.º 18 (20 de setembro de 2024): 8486. http://dx.doi.org/10.3390/app14188486.
Texto completo da fonteResumo:
Over the past few years, life expectancy has increased significantly. However, elderly individuals living independently often require assistance due to mobility issues, symptoms of dementia, or other health-related challenges. In these situations, high-quality elderly care systems for the aging population require innovative approaches to guarantee Quality of Service (QoS) and Quality of Experience (QoE). Traditional remote elderly care methods face several challenges, including high latency and poor service quality, which affect their transparency and stability. This paper proposes an Edge Computational Intelligence (ECI)-based haptic-driven ECI-TeleCaring system for the remote caring and monitoring of elderly people. It utilizes a Software-Defined Network (SDN) and Mobile Edge Computing (MEC) to reduce latency and enhance responsiveness. Dual Long Short-Term Memory (LSTM) models are deployed at the edge to enable real-time location-aware activity prediction to ensure QoS and QoE. The results from the simulation demonstrate that the proposed system is proficient in managing the transmission of data in real time without and with an activity recognition and location-aware model by communication latency under 2.5 ms (more than 60%) and from 11∼12 ms (60∼95%) for 10 to 1000 data packets, respectively. The results also show that the proposed system ensures a trade-off between the transparency and stability of the system from the QoS and QoE perspectives. Moreover, the proposed system serves as a testbed for implementing, investigating, and managing elder telecaring services for QoS/QoE provisioning. It facilitates real-time monitoring of the deployed technological parameters along with network delay and packet loss, and it oversees data exchange between the master domain (human operator) and slave domain (telerobot).
38
Li, Bing, Wei Cui, Wei Wang, Le Zhang, Zhenghua Chen e Min Wu. "Two-Stream Convolution Augmented Transformer for Human Activity Recognition". Proceedings of the AAAI Conference on Artificial Intelligence 35, n.º 1 (18 de maio de 2021): 286–93. http://dx.doi.org/10.1609/aaai.v35i1.16103.
Texto completo da fonteResumo:
Recognition of human activities is an important task due to its far-reaching applications such as healthcare system, context-aware applications, and security monitoring. Recently, WiFi based human activity recognition (HAR) is becoming ubiquitous due to its non-invasiveness. Existing WiFi-based HAR methods regard WiFi signals as a temporal sequence of channel state information (CSI), and employ deep sequential models (e.g., RNN, LSTM) to automatically capture channel-over-time features. Although being remarkably effective, they suffer from two major drawbacks. Firstly, the granularity of a single temporal point is blindly elementary for representing meaningful CSI patterns. Secondly, the time-over-channel features are also important, and could be a natural data augmentation. To address the drawbacks, we propose a novel Two-stream Convolution Augmented Human Activity Transformer (THAT) model. Our model proposes to utilize a two-stream structure to capture both time-over-channel and channel-over-time features, and use the multi-scale convolution augmented transformer to capture range-based patterns. Extensive experiments on four real experiment datasets demonstrate that our model outperforms state-of-the-art models in terms of both effectiveness and efficiency.
39
Nam, Seung-Joo, Gwiseong Moon, Jung-Hwan Park, Yoon Kim, Yun Jeong Lim e Hyun-Soo Choi. "Deep Learning-Based Real-Time Organ Localization and Transit Time Estimation in Wireless Capsule Endoscopy". Biomedicines 12, n.º 8 (31 de julho de 2024): 1704. http://dx.doi.org/10.3390/biomedicines12081704.
Texto completo da fonteResumo:
Background: Wireless capsule endoscopy (WCE) has significantly advanced the diagnosis of gastrointestinal (GI) diseases by allowing for the non-invasive visualization of the entire small intestine. However, machine learning-based methods for organ classification in WCE often rely on color information, leading to decreased performance when obstacles such as food debris are present. This study proposes a novel model that integrates convolutional neural networks (CNNs) and long short-term memory (LSTM) networks to analyze multiple frames and incorporate temporal information, ensuring that it performs well even when visual information is limited. Methods: We collected data from 126 patients using PillCam™ SB3 (Medtronic, Minneapolis, MN, USA), which comprised 2,395,932 images. Our deep learning model was trained to identify organs (stomach, small intestine, and colon) using data from 44 training and 10 validation cases. We applied calibration using a Gaussian filter to enhance the accuracy of detecting organ boundaries. Additionally, we estimated the transit time of the capsule in the gastric and small intestine regions using a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) designed to be aware of the sequence information of continuous videos. Finally, we evaluated the model’s performance using WCE videos from 72 patients. Results: Our model demonstrated high performance in organ classification, achieving an accuracy, sensitivity, and specificity of over 95% for each organ (stomach, small intestine, and colon), with an overall accuracy and F1-score of 97.1%. The Matthews Correlation Coefficient (MCC) and Geometric Mean (G-mean) were used to evaluate the model’s performance on imbalanced datasets, achieving MCC values of 0.93 for the stomach, 0.91 for the small intestine, and 0.94 for the colon, and G-mean values of 0.96 for the stomach, 0.95 for the small intestine, and 0.97 for the colon. Regarding the estimation of gastric and small intestine transit times, the mean time differences between the model predictions and ground truth were 4.3 ± 9.7 min for the stomach and 24.7 ± 33.8 min for the small intestine. Notably, the model’s predictions for gastric transit times were within 15 min of the ground truth for 95.8% of the test dataset (69 out of 72 cases). The proposed model shows overall superior performance compared to a model using only CNN. Conclusions: The combination of CNN and LSTM proves to be both accurate and clinically effective for organ classification and transit time estimation in WCE. Our model’s ability to integrate temporal information allows it to maintain high performance even in challenging conditions where color information alone is insufficient. Including MCC and G-mean metrics further validates the robustness of our approach in handling imbalanced datasets. These findings suggest that the proposed method can significantly improve the diagnostic accuracy and efficiency of WCE, making it a valuable tool in clinical practice for diagnosing and managing GI diseases.
40
Wang, Ziteng, Junfeng Li e Yonghong Yan. "Target Speaker Localization Based on the Complex Watson Mixture Model and Time-Frequency Selection Neural Network". Applied Sciences 8, n.º 11 (21 de novembro de 2018): 2326. http://dx.doi.org/10.3390/app8112326.
Texto completo da fonteResumo:
Common sound source localization algorithms focus on localizing all the active sources in the environment. While the source identities are generally unknown, retrieving the location of a speaker of interest requires extra effort. This paper addresses the problem of localizing a speaker of interest from a novel perspective by first performing time-frequency selection before localization. The speaker of interest, namely the target speaker, is assumed to be sparsely active in the signal spectra. The target speaker-dominant time-frequency regions are separated by a speaker-aware Long Short-Term Memory (LSTM) neural network, and they are sufficient to determine the Direction of Arrival (DoA) of the target speaker. Speaker-awareness is achieved by utilizing a short target utterance to adapt the hidden layer outputs of the neural network. The instantaneous DoA estimator is based on the probabilistic complex Watson Mixture Model (cWMM), and a weighted maximum likelihood estimation of the model parameters is accordingly derived. Simulative experiments show that the proposed algorithm works well in various noisy conditions and remains robust when the signal-to-noise ratio is low and when a competing speaker exists.
41
Nair, Biji, e S. Mary Saira Bhanu. "Task Scheduling in Fog Node within the Tactical Cloud". Defence Science Journal 72, n.º 1 (5 de janeiro de 2022): 49–55. http://dx.doi.org/10.14429/dsj.72.17039.
Texto completo da fonteResumo:
Fog computing architecture competent to support the mission-oriented network-centric warfare provides the framework for a tactical cloud in this work. The tactical cloud becomes situation-aware of the war from the information relayed by fog nodes (FNs) on the battlefield. This work aims to sustain the network of FNs by maintaining the operational efficiency of the FNs on the battlefield at the tactical edge. The proposed solution monitors and predicts the likely overloading of an FN using the long short-term memory model through a buddy FN at the fog server (FS). This paper also proposes randomised task scheduling (RTS) algorithm to avert the likely overloading of an FN by pre-empting tasks from the FN and scheduling them to another FN. The experimental results demonstrate that RTS with linear complexity has a schedulability measure 8% - 26% higher than that of other base scheduling algorithms. The results show that the LSTM model has low mean absolute error compared to other time-series forecasting models.
42
Lu, Tong, Sizu Hou e Yan Xu. "Ultra-Short-Term Load Forecasting for Customer-Level Integrated Energy Systems Based on Composite VTDS Models". Processes 11, n.º 8 (16 de agosto de 2023): 2461. http://dx.doi.org/10.3390/pr11082461.
Texto completo da fonteResumo:
A method is proposed to address the challenging issue of load prediction in user-level integrated energy systems (IESs) using a composite VTDS model. Firstly, an IES multi-dimensional load time series is decomposed into multiple intrinsic mode functions (IMFs) using variational mode decomposition (VMD). Then, each IMF, along with other influential features, is subjected to data dimensionality reduction and clustering denoising using t-distributed stochastic neighbor embedding (t-SNE) and fast density-based spatial clustering of applications with noise (FDBSCAN) to perform major feature selection. Subsequently, the reduced and denoised data are reconstructed, and a time-aware long short-term memory (T-LSTM) artificial neural network is employed to fill in missing data by incorporating time interval information. Finally, the selected multi-factor load time series is used as input into a support vector regression (SVR) model optimized using the quantum particle swarm optimization (QPSO) algorithm for load prediction. Using measured load data from a specific user-level IES at the Tempe campus of Arizona State University, USA, as a case study, a comparative analysis between the VTDS method and other approaches is conducted. The results demonstrate that the method proposed in this study achieved higher accuracy in short-term forecasting of the IES’s multiple loads.
43
Pandey, Neeraj Kumar, Manoj Diwakar, Achyut Shankar, Prabhishek Singh, Mohammad R. Khosravi e Vivek Kumar. "Energy Efficiency Strategy for Big Data in Cloud Environment Using Deep Reinforcement Learning". Mobile Information Systems 2022 (11 de agosto de 2022): 1–11. http://dx.doi.org/10.1155/2022/8716132.
Texto completo da fonteResumo:
Big data entails massive cloud resources for data processing and analysis, which consumes more energy to run. The resources and tasks are increasing exponentially in the cloud environment for the processing of big data, which results in an increment in power consumption to run the cloud data center. So, there is always a scope for optimizing the energy utilization in cloud data centers. This paper presents a visionary architecture in a cloud environment for big data with a proposed energy-efficient strategy based on LSTM-DQN (long-short-term memory-deep Q network) using reinforcement learning (RL). The traditional techniques are not so efficient when the tasks are allocated dynamically, and the generic RL strategies are not able to store the data iterated in the last cycles of processing, so the LSTM is considered for this purpose. In the proposed model, integration of DPSO and DQN is used for better estimation and rectification of the curse of dimensionality. The proposed strategy is compared with different variants of PSO (particle swarm optimization) such as DPSO and QoS-PSO. The improvement in results through proposed model is recoded over the algorithm such as load aware (8.01%), DQN (13.36%), EA-DQN (34.16%), L-No-DEAF (15.62%), DPSO (62.68%), QoS-PSO (72.69%), FFO-EVSM (75.42%), and MIMT (76.39%) on the parameter of energy efficiency, tasks completion time, and energy consumption over the timeline. So, the proposed model is encouraging in the energy-efficient cloud environment for big data with the challenges that the technological world is facing and the emergence of deep learning as one propitious field.
44
Xue, Mingfu, Junyu Zhu, Rusheng Wu, Xiayiwei Zhang e Yuan Chen. "BRP-Net: A discrete-aware network based on attention mechanisms and LSTM for birth rate prediction in prefecture-level cities". PLOS ONE 19, n.º 9 (12 de setembro de 2024): e0307721. http://dx.doi.org/10.1371/journal.pone.0307721.
Texto completo da fonteResumo:
The continuous decline in the birth rate can lead to a series of social and economic problems. Accurately predicting the birth rate of a region will help national and local governments to formulate more scientifically sound development policies. This paper proposes a discrete-aware model BRP-Net based on attention mechanism and LSTM, for effectively predicting the birth rate of prefecture-level cities. BRP-Net is trained using multiple variables related to comprehensive development of prefecture-level cities, covering factors such as economy, education and population structure that can influence the birth rate. Additionally, the comprehensive data of China’s prefecture-level cities exhibits strong spatiotemporal specificity. Our model leverages the advantages of attention mechanism to identify the feature correlation and temporal relationships of these multi-variable time series input data. Extensive experimental results demonstrate that the proposed BRP-Net has higher accuracy and better generalization performance compared to other mainstream methods, while being able to adapt to the spatiotemporal specificity of variables between prefecture-level cities. Using BRP-Net to achieve precise and robust prediction estimates of the birth rate in prefecture-level cities can provide more effective decision-making references for local governments to formulate more accurate and reasonable fertility encouragement policies.
45
Dash, Debadatta, Paul Ferrari, Satwik Dutta e Jun Wang. "NeuroVAD: Real-Time Voice Activity Detection from Non-Invasive Neuromagnetic Signals". Sensors 20, n.º 8 (16 de abril de 2020): 2248. http://dx.doi.org/10.3390/s20082248.
Texto completo da fonteResumo:
Neural speech decoding-driven brain-computer interface (BCI) or speech-BCI is a novel paradigm for exploring communication restoration for locked-in (fully paralyzed but aware) patients. Speech-BCIs aim to map a direct transformation from neural signals to text or speech, which has the potential for a higher communication rate than the current BCIs. Although recent progress has demonstrated the potential of speech-BCIs from either invasive or non-invasive neural signals, the majority of the systems developed so far still assume knowing the onset and offset of the speech utterances within the continuous neural recordings. This lack of real-time voice/speech activity detection (VAD) is a current obstacle for future applications of neural speech decoding wherein BCI users can have a continuous conversation with other speakers. To address this issue, in this study, we attempted to automatically detect the voice/speech activity directly from the neural signals recorded using magnetoencephalography (MEG). First, we classified the whole segments of pre-speech, speech, and post-speech in the neural signals using a support vector machine (SVM). Second, for continuous prediction, we used a long short-term memory-recurrent neural network (LSTM-RNN) to efficiently decode the voice activity at each time point via its sequential pattern-learning mechanism. Experimental results demonstrated the possibility of real-time VAD directly from the non-invasive neural signals with about 88% accuracy.
46
Sidhu, Kamaljeet Kaur, Habeeb Balogun e Kazeem Oluwakemi Oseni. ""Predictive Modelling of Air Quality Index (AQI) Across Diverse Cities and States of India using Machine Learning: Investigating the Influence of Punjab's Stubble Burning on AQI Variability"". International Journal of Managing Information Technology 16, n.º 1 (28 de fevereiro de 2024): 15–35. http://dx.doi.org/10.5121/ijmit.2024.16102.
Texto completo da fonteResumo:
Air pollution is a common and serious problem nowadays and it cannot be ignored as it has harmful impacts on human health. To address this issue proactively, people should be aware of their surroundings, which means the environment where they survive. With this motive, this research has predicted the AQI based on different air pollutant concentrations in the atmosphere. The dataset used for this research has been taken from the official website of CPCB. The dataset has the air pollutant concentration from 22 different monitoring stations in different cities of Delhi, Haryana, and Punjab. This data is checked for null values and outliers. But, the most important thing to note is the correct understanding and imputation of such values rather than ignoring or doing wrong imputation. The time series data has been used in this research which is tested for stationarity using The Dickey-Fuller test. Further different ML models like CatBoost, XGBoost, Random Forest, SVM regressor, time series model SARIMAX, and deep learning model LSTM have been used to predict AQI. For the performance evaluation of different models, I used MSE, RMSE, MAE, and R2. It is observed that Random Forest performed better as compared to other models.
47
Tariq, Usman. "Optimized Feature Selection for DDoS Attack Recognition and Mitigation in SD-VANETs". World Electric Vehicle Journal 15, n.º 9 (28 de agosto de 2024): 395. http://dx.doi.org/10.3390/wevj15090395.
Texto completo da fonteResumo:
Vehicular Ad-Hoc Networks (VANETs) are pivotal to the advancement of intelligent transportation systems (ITS), enhancing safety and efficiency on the road through secure communication networks. However, the integrity of these systems is severely threatened by Distributed Denial-of-Service (DDoS) attacks, which can disrupt the transmission of safety-critical messages and put lives at risk. This research paper focuses on developing robust detection methods and countermeasures to mitigate the impact of DDoS attacks in VANETs. Utilizing a combination of statistical analysis and machine learning techniques (i.e., Autoencoder with Long Short-Term Memory (LSTM), and Clustering with Classification), the study introduces innovative approaches for real-time anomaly detection and system resilience enhancement. Emulation results confirm the effectiveness of the proposed methods in identifying and countering DDoS threats, significantly improving (i.e., 94 percent anomaly detection rate) the security posture of a high mobility-aware ad hoc network. This research not only contributes to the ongoing efforts to secure VANETs against DDoS attacks but also lays the groundwork for more resilient intelligent transportation systems architectures.
48
Wang, Chunli, Linming Xu, Hongxin Zhu e Xiaoyang Cheng. "Robustness study of speaker recognition based on ECAPA-TDNN-CIFG". Journal of Computational Methods in Sciences and Engineering 24, n.º 4-5 (14 de agosto de 2024): 3287–96. http://dx.doi.org/10.3233/jcm-247581.
Texto completo da fonteResumo:
This paper describes a study on speaker recognition using the ECAPA-TDNN architecture, which stands for Extended Context-Aware Parallel Aggregations Time-Delay Neural Network. It utilizes X-vectors, a method for extracting speaker features by converting speech into fixed-length vectors, and introduces a squeeze-and-excitation block to model dependencies between channels. In order to better explore temporal relationships in the context of speaker recognition and improve the algorithm’s generalization performance in complex acoustic scenarios, this study adds input gates and forget gates to the ECAPA-TDNN architecture, combining them with CIFG (Convolutional LSTM with Input and Forget Gates) modules. These are embedded into a residual structure of multi-layer aggregated features. A sub-center Arcface, an improved loss function based on Arcface, is used for selecting sub-centers for subclass discrimination, retaining advantageous sub-centers to enhance intra-class compactness and strengthen the robustness of the network. Experimental results demonstrate that the improved ECAPA-TDNN-CIFG in this study outperforms the baseline model, yielding more accurate and efficient recognition results.
49
Kamal, Saurabh, Sahil Sharma, Vijay Kumar, Hammam Alshazly, Hany S. Hussein e Thomas Martinetz. "Trading Stocks Based on Financial News Using Attention Mechanism". Mathematics 10, n.º 12 (10 de junho de 2022): 2001. http://dx.doi.org/10.3390/math10122001.
Texto completo da fonteResumo:
Sentiment analysis of news headlines is an important factor that investors consider when making investing decisions. We claim that the sentiment analysis of financial news headlines impacts stock market values. Hence financial news headline data are collected along with the stock market investment data for a period of time. Using Valence Aware Dictionary and Sentiment Reasoning (VADER) for sentiment analysis, the correlation between the stock market values and sentiments in news headlines is established. In our experiments, the data on stock market prices are collected from Yahoo Finance and Kaggle. Financial news headlines are collected from the Wall Street Journal, Washington Post, and Business-Standard website. To cope with such a massive volume of data and extract useful information, various embedding methods, such as Bag-of-words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF), are employed. These are then fed into machine learning models such as Naive Bayes and XGBoost as well as deep learning models such as Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). Various natural language processing, andmachine and deep learning algorithms are considered in our study to achieve the desired outcomes and to attain superior accuracy than the current state-of-the-art. Our experimental study has shown that CNN (80.86%) and LSTM (84%) are the best performing models in relation to machine learning models, such as Support Vector Machine (SVM) (50.3%), Random Forest (67.93%), and Naive Bayes (59.79%). Moreover, two novel methods, BERT and RoBERTa, were applied with the expectation of better performance than all the other models, and they did exceptionally well by achieving an accuracy of 90% and 88%, respectively.
50
Do, Nhu-Tai, Soo-Hyung Kim, Hyung-Jeong Yang, Guee-Sang Lee e Soonja Yeom. "Context-Aware Emotion Recognition in the Wild Using Spatio-Temporal and Temporal-Pyramid Models". Sensors 21, n.º 7 (27 de março de 2021): 2344. http://dx.doi.org/10.3390/s21072344.
Texto completo da fonteResumo:
Emotion recognition plays an important role in human–computer interactions. Recent studies have focused on video emotion recognition in the wild and have run into difficulties related to occlusion, illumination, complex behavior over time, and auditory cues. State-of-the-art methods use multiple modalities, such as frame-level, spatiotemporal, and audio approaches. However, such methods have difficulties in exploiting long-term dependencies in temporal information, capturing contextual information, and integrating multi-modal information. In this paper, we introduce a multi-modal flexible system for video-based emotion recognition in the wild. Our system tracks and votes on significant faces corresponding to persons of interest in a video to classify seven basic emotions. The key contribution of this study is that it proposes the use of face feature extraction with context-aware and statistical information for emotion recognition. We also build two model architectures to effectively exploit long-term dependencies in temporal information with a temporal-pyramid model and a spatiotemporal model with “Conv2D+LSTM+3DCNN+Classify” architecture. Finally, we propose the best selection ensemble to improve the accuracy of multi-modal fusion. The best selection ensemble selects the best combination from spatiotemporal and temporal-pyramid models to achieve the best accuracy for classifying the seven basic emotions. In our experiment, we take benchmark measurement on the AFEW dataset with high accuracy.