To see the other types of publications on this topic, follow the link: Stacked Bi-LSTM.
Journal articles on the topic 'Stacked Bi-LSTM'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Stacked Bi-LSTM.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Raut, Supriya. "Analysis & Stock Price Prediction and Forecasting Using Different LSTM Models." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 04 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem30115.
Full textAbstract:
The objective of this research is to develop a Deep Learning model to forecast the stock price, by using the variant of Long Short-Term Memory. This model predicts the close price of the stock for the future selected date, choosing as inputs the following data: open, high, low, adj close and close prices. This model shows a comparative analysis between three different LSTM networks: Long Short-Term Memory (LSTM), Stacked Long Short-Term Memory (Stacked LSTM), and Stacked Bi-directional Long Short-Term Memory (Stacked Bidirectional LSTM) concluding which one is the best and implementing the model using that variant. We have used the historical stock prices data from yahoo’s financial website over 5 years, by choosing multiple datasets: Apple, Amazon, Google, Meta, Microsoft and Tesla (daily values). In order to get effective in the forecasting model, we have tested the network with different iterations and epochs. The model represents Multiple Graphs for data visualization in different comparisons. We have estimated the effectiveness of our proposed model by using the following performance indicators: the Mean Square Error (MSE), the Root Mean Square Error (RMSE), and the R-Squared of the model. The experimental results clearly show that our Stacked Bi-LSTM model has the highest accuracy values when comparing with the LSTM and Stacked LSTM Models. Hence, we can conclude that our Stacked Bi-LSTM Model is suitable for accurate prediction of the stock market time series. Key Words: stock price prediction, Machine Learning, stacked LSTM, Bi-directional LSTM, Deep Learning, Data pre-processing techniques, Data normalization, Data Visualization, Training and Testing Set, Financial Time Series, Future prediction
2
Gunawan, Akbar Rikzy, and Rifda Faticha Alfa Aziza. "Sentiment Analysis Using LSTM Algorithm Regarding Grab Application Services in Indonesia." Journal of Applied Informatics and Computing 9, no. 2 (2025): 322–32. https://doi.org/10.30871/jaic.v9i2.8696.
Full textAbstract:
This study aims to analyze the sentiment of user reviews for the Grab Indonesia application using Long Short-Term Memory (LSTM) algorithms. Two variants of LSTM, namely Stacked LSTM and Bi-Directional LSTM, were compared to determine the most effective model in classifying user review sentiments. Both models were enhanced with Multi-Head Attention mechanisms to capture more complex contextual relationships in sequential data. The data used consists of 2,000 user reviews collected through scraping from the Google Play Store, with sentiment labels of positive and negative. Data preprocessing included labeling, case folding, stopword removal, tokenization, stemming, and the application of the SMOTE technique to address class imbalance. The results show that the Bi-Directional LSTM model achieved the highest validation accuracy of 87%, with an F1-score of 0.90 for the negative class and 0.82 for the positive class, while the Stacked LSTM recorded an accuracy of 84%, with an F1-score of 0.87 for the negative class and 0.78 for the positive class. Overall, the Bi-Directional LSTM demonstrated better performance in identifying both negative and positive sentiments, providing a good balance between precision and recall. This study proves that Bi-Directional LSTM with Multi-Head Attention can improve sentiment analysis performance on user reviews of digital applications, with potential applications in various other platforms.
3
Li, Jianyao. "A Comparative Study of LSTM Variants in Prediction for Tesla’s Stock Price." BCP Business & Management 34 (December 14, 2022): 30–38. http://dx.doi.org/10.54691/bcpbm.v34i.2861.
Full textAbstract:
Long short-term memory (LSTM) is widely used in the stock market to train the prediction model and forecast future stock prices. Applying the LSTM method to research may incur some problems and facilitate the improvement of the method. Therefore, many LSTM variants are put forward under different circumstances. This paper surveys four LSTM variants, including Vanilla, Stacked, Bi-directional, and CNN LSTM on two different data sets regarding Tesla's stock price. Two data sets mentioned in this paper represent different stock types. To be more specific, data set 1 refers to stocks with a single long-term trend, while data set 2 can be seen as an example of stocks with more complexity. The result shows that the Vanilla LSTM reaches the highest prediction accuracy on the data set without any irregular shift in the long-term trend. CNN LSTM also provides decent predictions for the stock price. Otherwise, the Stacked LSTM performs the best for stock prediction. Bi-LSTM and CNN LSTM are also suitable for stock forecasting in more complicated situations. The change in preference for model selection proves that a company's operation situation and market circumstances also influence the prediction performance of LSTM variants.
4
Venkatesan, Saravanakumar, and Yongyun Cho. "Multi-Timeframe Forecasting Using Deep Learning Models for Solar Energy Efficiency in Smart Agriculture." Energies 17, no. 17 (2024): 4322. http://dx.doi.org/10.3390/en17174322.
Full textAbstract:
Since the advent of smart agriculture, technological advancements in solar energy have significantly improved farming practices, resulting in a substantial revival of different crop yields. However, the smart agriculture industry is currently facing challenges posed by climate change. This involves multi-timeframe forecasts for greenhouse operators covering short-, medium-, and long-term intervals. Solar energy not only reduces our reliance on non-renewable electricity but also plays a pivotal role in addressing climate change by lowering carbon emissions. This study aims to find a method to support consistently optimal solar energy use regardless of changes in greenhouse conditions by predicting solar energy (kWh) usage on various time steps. In this paper, we conducted solar energy usage prediction experiments on time steps using traditional Tensorflow Keras models (TF Keras), including a linear model (LM), Convolutional Neural Network (CNN), stacked—Long Short Term Memory (LSTM), stacked-Gated recurrent unit (GRU), and stacked-Bidirectional—Long Short —Term Memory (Bi-LSTM), as well as Tensor-Flow-based models for solar energy usage data from a smart farm. The stacked-Bi-LSTM outperformed the other DL models with Root Mean Squared Error (RMSE) of 0.0048, a Mean Absolute Error (MAE) of 0.0431, and R-Squared (R2) of 0.9243 in short-term prediction (2-h intervals). For mid-term (2-day) and long-term (2-week) forecasting, the stacked Bi-LSTM model also exhibited superior performance compared to other deep learning models, with RMSE values of 0.0257 and 0.0382, MAE values of 0.1103 and 0.1490, and R2 values of 0.5980 and 0.3974, respectively. The integration of multi-timeframe forecasting is expected to avoid conventional solar energy use forecasting, reduce the complexity of greenhouse energy management, and increase energy use efficiency compared to single-timeframe forecasting models.
5
Rupapara, Vaibhav, Furqan Rustam, Aashir Amaar, Patrick Bernard Washington, Ernesto Lee, and Imran Ashraf. "Deepfake tweets classification using stacked Bi-LSTM and words embedding." PeerJ Computer Science 7 (October 21, 2021): e745. http://dx.doi.org/10.7717/peerj-cs.745.
Full textAbstract:
The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make their way to social platforms. The polarity of such tweets is significant to determine the sentiment of people about deep fakes. This paper presents a deep learning model to predict the polarity of deep fake tweets. For this purpose, a stacked bi-directional long short-term memory (SBi-LSTM) network is proposed to classify the sentiment of deep fake tweets. Several well-known machine learning classifiers are investigated as well such as support vector machine, logistic regression, Gaussian Naive Bayes, extra tree classifier, and AdaBoost classifier. These classifiers are utilized with term frequency-inverse document frequency and a bag of words feature extraction approaches. Besides, the performance of deep learning models is analyzed including long short-term memory network, gated recurrent unit, bi-direction LSTM, and convolutional neural network+LSTM. Experimental results indicate that the proposed SBi-LSTM outperforms both machine and deep learning models and achieves an accuracy of 0.92.
6
Murugesan, R., Eva Mishra, and Akash Hari Krishnan. "Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM." International Journal of Sustainable Agricultural Management and Informatics 8, no. 3 (2022): 242. http://dx.doi.org/10.1504/ijsami.2022.125757.
Full text
7
Krishnan, Akash Hari, R. Murugesan, and Eva Mishra. "Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM." International Journal of Sustainable Agricultural Management and Informatics 8, no. 3 (2022): 1. http://dx.doi.org/10.1504/ijsami.2022.10048228.
Full text
8
Nayak, G. H. Harish, A. Varalakshmi, M. G. Manjunath, Veershetty, G. Avinash, and Moumita Baishya. "Trend Analysis and Prediction of Rainfall Using Deep Learning Models in Three Sub-Divisions of Karnataka." Journal of Experimental Agriculture International 45, no. 4 (2023): 36–48. http://dx.doi.org/10.9734/jeai/2023/v45i42114.
Full textAbstract:
Precise estimation of rainfall is a crucial and challenging task in environmental science. It involves the use of advanced and powerful models to forecast non-linear and dynamic changes in rainfall. Deep learning, a recently developed method for handling vast amounts of data and resolving complex problems, has proven to be an effective tool for rainfall forecasting. In this study, we applied various deep learning models such as Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Stacked LSTM, Gated Recurrent Units (GRUs), and a traditional model called Autoregressive Integrated Moving Average (ARIMA), to forecast monthly rainfall data (mm) for three regions of Karnataka: Coastal Karnataka, North Interior Karnataka (NIK), and South Interior Karnataka (SIK). Trend analysis was conducted using the Mann-Kendall trend test (MK test) and the Seasonal Mann-Kendall trend test, along with Sen's Slope Estimator, to determine trends and slope magnitudes. The results showed that deep learning models perform better than traditional methods in forecasting rainfall. The performance of different models was evaluated using forecasting evaluation criteria and found that the LSTM model performed best for Coastal Karnataka, with an RMSE value of 149.45, while the Bi-LSTM model performed best for NIK, with an RMSE value of 32.57, and the Stacked LSTM model performed best for SIK, with an RMSE value of 45.33. Therefore, deep learning models can be effectively used to predict rainfall data with greater accuracy.
9
Adib, Arash, Mohammad Pourghasemzadeh, and Morteza Lotfirad. "RNN-Based Monthly Inflow Prediction for Dez Dam in Iran Considering the Effect of Wavelet Pre-Processing and Uncertainty Analysis." Hydrology 11, no. 9 (2024): 155. http://dx.doi.org/10.3390/hydrology11090155.
Full textAbstract:
In recent years, deep learning (DL) methods, such as recurrent neural networks (RNN). have been used for streamflow prediction. In this study, the monthly inflow into the Dez Dam reservoir from 1955 to 2018 in southwestern Iran was simulated using various types of RNNs, including long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), and stacked long short-term memory (Stacked LSTM). It was observed that considering flow discharge, temperature, and precipitation as inputs to the models yields the best results. Additionally, wavelet transform was employed to enhance the accuracy of the RNNs. Among the RNNs, the GRU model exhibited the best performance in simulating monthly streamflow without using wavelet transform, with RMSE, MAE, NSE, and R2 values of 0.061 m3/s, 0.038 m3/s, 0.556, and 0.642, respectively. Moreover, in the case of using wavelet transform, the Bi-LSTM model with db5 mother wavelet and decomposition level 5 was able to simulate the monthly streamflow with high accuracy, yielding RMSE, MAE, NSE, and R2 values of 0.014 m3/s, 0.008 m3/s, 0.9983, and 0.9981, respectively. Uncertainty analysis was conducted for the two mentioned superior models. To quantify the uncertainty, the concept of the 95 percent prediction uncertainty (95PPU) and the p-factor and r-factor criteria were utilized. For the GRU, the p-factor and r-factor values were 82% and 1.28, respectively. For the Bi-LSTM model, the p-factor and r-factor values were 94% and 1.06, respectively. The obtained p-factor and r-factor values for both models are within the acceptable and reliable range.
10
Ravinder, Paspula, and Saravanan Srinivasan. "Hybrid Attention-Based Stacked Bi-LSTM Model for Automated MultiImage Captioning." Journal of Computer Science 21, no. 4 (2025): 883–904. https://doi.org/10.3844/jcssp.2025.883.904.
Full text
11
Ali Khan, Mehmood, Iftikhar Ahmed Khan, Sajid Shah, Mohammed EL-Affendi, and Waqas Jadoon. "Short-term wind power forecasting through stacked and bi directional LSTM techniques." PeerJ Computer Science 10 (March 29, 2024): e1949. http://dx.doi.org/10.7717/peerj-cs.1949.
Full textAbstract:
Background Computational intelligence (CI) based prediction models increase the efficient and effective utilization of resources for wind prediction. However, the traditional recurrent neural networks (RNN) are difficult to train on data having long-term temporal dependencies, thus susceptible to an inherent problem of vanishing gradient. This work proposed a method based on an advanced version of RNN known as long short-term memory (LSTM) architecture, which updates recurrent weights to overcome the vanishing gradient problem. This, in turn, improves training performance. Methods The RNN model is developed based on stack LSTM and bidirectional LSTM. The parameters like mean absolute error (MAE), standard deviation error (SDE), and root mean squared error (RMSE) are utilized as performance measures for comparison with recent state-of-the-art techniques. Results Results showed that the proposed technique outperformed the existing techniques in terms of RMSE and MAE against all the used wind farm datasets. Whereas, a reduction in SDE is observed for larger wind farm datasets. The proposed RNN approach performed better than the existing models despite fewer parameters. In addition, the approach requires minimum processing power to achieve compatible results.
12
Horng, Gwo-Jiun, Yu-Chin Huang, and Zong-Xian Yin. "Using Bidirectional Long-Term Memory Neural Network for Trajectory Prediction of Large Inner Wheel Routes." Sustainability 14, no. 10 (2022): 5935. http://dx.doi.org/10.3390/su14105935.
Full textAbstract:
When a large car turns at an intersection, it often leads to tragedy because the driver does not pay attention to the incoming car or the dead corner of the line of sight of the car body. On the market, the wheel difference warning system used in large cars generally adds sensors or lenses to confirm whether there are incoming vehicles in the dead corner of the line of sight. However, the accident rate of large vehicles has not been reduced due to the installation of a vision subsidy system. The main reason is that motorcycle and bicycle drivers often neglect to pay attention to the inner wheel difference formed when large vehicles turn, resulting in accidents with large vehicles at intersections. This paper proposes a bidirectional long-term memory neural network for the prediction of the inner wheel path trajectory of large cars, mainly from the perspective of motorcycle riders, through the combination of YOLOv4 and the stacked Bi-LSTM model used in this study to analyze the motion of large cars and predict the inner wheel path trajectory. In this study, the turning trajectory of large vehicles at the intersection is predicted by using an object detection algorithm and cyclic neural network model. Finally, the experiment shows that this study uses the stacked Bi-LSTM trajectory prediction model to predict the next second trajectory with one second trajectory data, and the prediction accuracy is 87.77%; it has an accuracy of 75.75% when predicting the trajectory data of two seconds. In terms of prediction error, the system has a better prediction error than LSTM and Bi-LSTM models.
13
Guangliang, Pan, Li Jie, and Li Minglei. "Multi-channel multi-step spectrum prediction using transformer and stacked Bi-LSTM." China Communications 22, no. 5 (2025): 1–13. https://doi.org/10.23919/jcc.ja.2022-0667.
Full text
14
Bijal U. Gadhia. "LSTM-Based Soccer Video Summarization Via Event Classification for Highlighting Key Moments." Journal of Electrical Systems 20, no. 9s (2024): 1677–84. http://dx.doi.org/10.52783/jes.4677.
Full textAbstract:
Video summarization creates brief synopses of video content by selecting the most informative segments, either as key-frames or key-fragments. This study introduces an advanced method for event classification in soccer videos using a modified stacked Long Short-Term Memory (LSTM) model. By utilizing the Soccer Action Detection Compilation (SADC) dataset, which includes detailed annotations of football events, our method combines VGG16 for feature extraction with LSTM for event classification. The model efficiently identifies crucial events such as goals, goal attempts, and yellow cards, while also filtering out non-essential segments labelled as "No Events." When compared to the Bi-LSTM model, the modified LSTM demonstrates superior performance in terms of precision, recall, and F1-score for several key event classes. Specifically, at epoch 150, the modified LSTM achieves an F1-score of 0.87 for "No Event" segments and perfect precision for "Goal" events, surpassing the Bi-LSTM. These findings underscore the model's stability and accuracy, which ensure the production of high-quality highlight reels by emphasizing important events and minimizing irrelevant content. In the future, by removing non-essential segments recognized as "No Events" from any football match, one can generate perfect highlight reels that capture all crucial moments, providing viewers with a more focused and enjoyable experience.
15
Li, Hui, Jiankang Lou, Fan Li, Guang Yang, and Yibo Ouyang. "A Deep Learning Framework for Deformation Monitoring of Hydraulic Structures with Long-Sequence Hydrostatic and Thermal Time Series." Water 17, no. 12 (2025): 1814. https://doi.org/10.3390/w17121814.
Full textAbstract:
As hydraulic buildings are constantly subjected to complex interactions with water, particularly variations in hydrostatic pressure and temperature, deformation structural behavior is inherently sensitive to environmental fluctuations. Monitoring dam deformation with high accuracy and robustness is critical for ensuring the long-term safety and operational integrity of hydraulic structures. However, traditional physics-based models often struggle to fully capture the nonlinear and time-dependent deformation responses in hydraulic structures driven by such coupled environmental influences. To address these limitations, this study presents an advanced deep learning (DL)-based deformation monitoring for hydraulic buildings using long-sequence monitoring data of hydrostatic pressure and temperature. Specifically, the Bidirectional Stacked Long Short-Term Memory (Bi-Stacked-LSTM) is proposed to capture intricate temporal dependencies and directional dynamics within long-sequence hydrostatic and thermal time series. Then, hyperparameters, including the number of LSTM layers, neuron counts in each layer, dropout rate, and time steps, are efficiently fine-tuned using the Gaussian Process-based surrogate model optimization (GP-SMO) algorithm. Multiple deformation monitoring points from hydraulic buildings and a variety of advanced machine-learning methods are utilized for analysis. Experimental results indicate that the developed GP-SMO-optimized Bi-Stacked-LSTM dam deformation monitoring model shows better comprehensive representation capability of both past and future deformation-related sequences compared with benchmark methods. By approximating the behavior of the target function, the GP-SMO algorithms allow for the optimization of critical parameters in DL models while minimizing the high computational costs typically associated with direct evaluations. This novel DL-based approach significantly improves the extraction of deformation-relevant features from long-term monitoring data, enabling more accurate modeling of temporal dynamics. As a result, the developed method offers a promising new tool for safety monitoring and intelligent management of large-scale hydraulic structures.
16
Moazzen, Farid, and M. J. Hossain. "Multivariate Deep Learning Long Short-Term Memory-Based Forecasting for Microgrid Energy Management Systems." Energies 17, no. 17 (2024): 4360. http://dx.doi.org/10.3390/en17174360.
Full textAbstract:
In the scope of energy management systems (EMSs) for microgrids, the forecasting module stands out as an essential element, significantly influencing the efficacy of optimal solution policies. Forecasts for consumption, generation, and market prices play a crucial role in both day-ahead and real-time decision-making processes within EMSs. This paper aims to develop a machine learning-based multivariate forecasting methodology to account for the intricate interplay pertaining to these variables from the perspective of day-ahead energy management. Specifically, our approach delves into the dynamic relationship between load demand variations and electricity price fluctuations within the microgrid EMSs. The investigation involves a comparative analysis and evaluation of recurrent neural networks’ performance to recognize the most effective technique for the forecasting module of microgrid EMSs. This study includes approaches based on Long Short-Term Memory Neural Networks (LSTMs), with architectures ranging from Vanilla LSTM, Stacked LSTM, Bi-directional LSTM, and Convolution LSTM to attention-based models. The empirical study involves analyzing real-world time-series data sourced from the Australian Energy Market (AEM), specifically focusing on historical data from the NSW state. The findings indicate that while the Triple-Stacked LSTM demonstrates superior performance for this application, it does not necessarily lead to more optimal operational costs, with forecast inaccuracies potentially causing deviations of up to forty percent from the optimal cost.
17
Akshita, Anu Bajaj, and Vikas Sharma. "EEG-Based Epileptic Seizure Prediction Using Variants of the Long Short Term Memory Algorithm." International Journal of Computer Information Systems and Industrial Management Applications 17 (January 6, 2025): 13. https://doi.org/10.70917/ijcisim-2025-0001.
Full textAbstract:
One of the most widespread neurological disorders worldwide is epilepsy. Seizures that are caused by sudden aberrant electrical activity in the patient’s brain, causing unpredictable episodes, are called epileptic seizures. Epileptic seizure patient’s life can be significantly impacted by early detection of seizure. For the prediction of seizures based on zero-crossing intervals of examination of the scalp, an approach known as electroencephalograms (EEGs) is introduced. EEG signals are examined to anticipate seizures and prevent unwarranted life risks. Deep Learning (DL) has been used in this research as it can automatically generate hierarchical representation from unprocessed EEG data, making it possible to quickly uncover complicated patterns and information associated with brain activity. This required preprocessing EEG scalp recordings, automatic feature extraction, and classification. In this paper, we proposed the Long Short Term Memory (LSTM) variants, Bi-LTSM, vanilla LSTM, and stacked LSTM, and compared the results with GRU, MLP, and DCNN for epileptic seizure prediction. We compared these models using the CHB-MIT dataset to improve accuracy, sensitivity, and specificity for predicting epileptic seizures. The results show that the Bi-LSTM algorithm performed better than the other proposed algorithms in terms of evaluation metrics.
18
Tang, Xingyu, Peijie Zheng, Yuewu Liu, Yuhua Yao, and Guohua Huang. "LangMoDHS: A deep learning language model for predicting DNase I hypersensitive sites in mouse genome." Mathematical Biosciences and Engineering 20, no. 1 (2022): 1037–57. http://dx.doi.org/10.3934/mbe.2023048.
Full textAbstract:
<abstract> <p>DNase I hypersensitive sites (DHSs) are a specific genomic region, which is critical to detect or understand cis-regulatory elements. Although there are many methods developed to detect DHSs, there is a big gap in practice. We presented a deep learning-based language model for predicting DHSs, named LangMoDHS. The LangMoDHS mainly comprised the convolutional neural network (CNN), the bi-directional long short-term memory (Bi-LSTM) and the feed-forward attention. The CNN and the Bi-LSTM were stacked in a parallel manner, which was helpful to accumulate multiple-view representations from primary DNA sequences. We conducted 5-fold cross-validations and independent tests over 14 tissues and 4 developmental stages. The empirical experiments showed that the LangMoDHS is competitive with or slightly better than the iDHS-Deep, which is the latest method for predicting DHSs. The empirical experiments also implied substantial contribution of the CNN, Bi-LSTM, and attention to DHSs prediction. We implemented the LangMoDHS as a user-friendly web server which is accessible at <a href="http:/www.biolscience.cn/LangMoDHS/" target="_blank">http:/www.biolscience.cn/LangMoDHS/</a>. We used indices related to information entropy to explore the sequence motif of DHSs. The analysis provided a certain insight into the DHSs.</p> </abstract>
19
Tello-Leal, Edgar, Ulises Manuel Ramirez-Alcocer, Bárbara A. Macías-Hernández, and Jaciel David Hernandez-Resendiz. "Evaluation of Deep Learning Models for Predicting the Concentration of Air Pollutants in Urban Environments." Sustainability 16, no. 16 (2024): 7062. http://dx.doi.org/10.3390/su16167062.
Full textAbstract:
Air pollution is an issue of great concern globally due to the risks to the health of humanity, animals, and ecosystems. On the one hand, air quality monitoring systems allow for determining the concentration level of air pollutants and health risks through an air quality index (AQI). On the other hand, accurate future predictions of air pollutant concentration levels can provide valuable information for data-driven decision-making to reduce health risks from short- and long-term exposure when indicators exceed permissible limits. In this paper, five deep learning architectures are evaluated to predict the concentration of particulate matter pollutants (in their fractions PM2.5 and PM10) and carbon monoxide (CO) in consecutive hours. The proposed prediction models are based on recurrent neural networks (RNNs), long short-term memory (LSTM), vanilla LSTM, Stacked LSTM, Bi-LSTM, and encoder–decoder LSTM networks. Moreover, a methodology is presented to guide the construction of the prediction model, encompassing raw data processing, model design and optimization, and neural network training, testing, and evaluation. The results underscore the precision and reliability of the Stacked LSTM model in predicting the hourly concentration level for PM2.5, with an RMSE of 3.4538 μg/m3. Similarly, the encoder–decoder LSTM model accurately predicts the concentration level for PM10 and CO, with an RMSE of 3.2606 μg/m3 and 2.1510 ppm, respectively. These evaluations, with their minimal differences in error metrics and coefficient of determination, validate the effectiveness and superiority of the deep learning models over other reference models, instilling confidence in their potential.
20
Qi, Jiakang, and Na Luo. "Using Stacked Auto-Encoder and Bi-Directional LSTM For Batch Process Quality Prediction." JOURNAL OF CHEMICAL ENGINEERING OF JAPAN 54, no. 4 (2021): 144–51. http://dx.doi.org/10.1252/jcej.19we235.
Full text
21
Dai, Tao, Li Zhu, Yaxiong Wang, and Kathleen M. Carley. "Attentive Stacked Denoising Autoencoder With Bi-LSTM for Personalized Context-Aware Citation Recommendation." IEEE/ACM Transactions on Audio, Speech, and Language Processing 28 (2020): 553–68. http://dx.doi.org/10.1109/taslp.2019.2949925.
Full text
22
Mengara Mengara, Axel Gedeon, Younghak Kim, Younghwan Yoo, and Jaehun Ahn. "Distributed Deep Features Extraction Model for Air Quality Forecasting." Sustainability 12, no. 19 (2020): 8014. http://dx.doi.org/10.3390/su12198014.
Full textAbstract:
Several studies in environmental engineering emphasize the importance of air quality forecasting for sustainable development around the world. In this paper, we studied a new approach for air quality forecasting in Busan metropolitan city. We proposed a convolutional Bi-Directional Long-Short Term Memory (Bi-LSTM) autoencoder model trained using a distributed architecture to predict the concentration of the air quality particles (PM2.5 and PM10). The proposed deep learning model can automatically learn the intrinsic correlation among the pollutants in different location. Also, the meteorological and the pollution gas information at each location are fully utilized, which is beneficial for the performance of the model. We used multiple one-dimension convolutional neural network (CNN) layers to extract the local spatial features and a stacked Bi-LSTM layer to learn the spatiotemporal correlation of air quality particles. In addition, we used a stacked deep autoencoder to encode the essential transformation patterns of the pollution gas and the meteorological data, since they are very important for providing useful information that can significantly improve the prediction of the air quality particles. Finally, in order to reduce the training time and the resource consumption, we used a distributed deep leaning approach called data parallelism, which has never been used to tackle the problem of air quality forecasting. We evaluated our approach with extensive experiments based on the data collected in Busan metropolitan city. The results reveal the superiority of our framework over ten baseline models and display how the distributed deep learning model can significantly improve the training time and even the prediction accuracy.
23
Chen, Lei, Mengyao Zheng, Zhaohua Liu, Mingyang Lv, Lv Zhao, and Ziyao Wang. "SDAE+Bi-LSTM-Based Situation Awareness Algorithm for the CAN Bus of Intelligent Connected Vehicles." Electronics 11, no. 1 (2021): 110. http://dx.doi.org/10.3390/electronics11010110.
Full textAbstract:
With a deep connection to the internet, the controller area network (CAN) bus of intelligent connected vehicles (ICVs) has suffered many network attacks. A deep situation awareness method is urgently needed to judge whether network attacks will occur in the future. However, traditional shallow methods cannot extract deep features from CAN data with noise to accurately detect attacks. To solve these problems, we developed a SDAE+Bi-LSTM based situation awareness algorithm for the CAN bus of ICVs, simply called SDBL. Firstly, the stacked denoising auto-encoder (SDAE) model was used to compress the CAN data with noise and extract the deep spatial features at a certain time, to reduce the impact of noise. Secondly, a bidirectional long short-term memory (Bi-LSTM) model was further built to capture the periodic features from two directions to enhance the accuracy of the future situation prediction. Finally, a threat assessment model was constructed to evaluate the risk level of the CAN bus. Extensive experiments also verified the improved performance of our SDBL algorithm.
24
Bandyopadhyay, Samir Kumar. "Stacked Bi-directional LSTM Layer Based Model for Prediction of Possible Heart Disease during Lockdown Period of COVID-19." Journal of Advanced Research in Medical Science & Technology 07, no. 02 (2020): 10–14. http://dx.doi.org/10.24321/2394.6539.202006.
Full text
25
Thakur, Ujwala, Ankit Vidyarthi, and Amarjeet Prajapati. "Recognition of Real-Time Video Activities Using Stacked Bi-GRU with Fusion-based Deep Architecture." JUCS - Journal of Universal Computer Science 30, no. 10 (2024): 1423–52. http://dx.doi.org/10.3897/jucs.113095.
Full textAbstract:
Recognizing and understanding human activities in real-time videos is a challenging task due to the complex nature of video data and the need for efficient and accurate analysis. This research pioneers a breakthrough in video activity recognition by introducing a robust framework leveraging the power of a stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architecture, harmonized within a fusion-based deep model. The stacked Bi-LSTM-GRU model capitalizes on its dual recurrent architecture, capturing nuanced temporal dependencies within video sequences. The fusion-based deep architecture synergizes spatial and temporal features, enabling the model to discern intricate patterns in human activities. To further enhance the discriminative power of the model, we introduce a fusion module in the proposed deep architecture. The fusion module integrates multi-modal features extracted from different levels of the network hierarchy, allowing for a more comprehensive representation of video activities. We demonstrate the efficacy of our approach through rigorous experimentation on UCF50, UCF101, and HMDB51 datasets. In experiments on the UCF50 dataset, our model achieves an accuracy of 97.01% and 95.86% on training and validation sets respectively, showcasing its proficiency in discerning activities across a diverse range of scenarios. The evaluation extends to the UCF101 dataset, where the proposed approach achieves a competitive accuracy of 97.62% and 96.93% on training and validation sets, surpassing previous benchmarks by a margin of approx 1%. Further-more, on the challenging HMDB51 dataset, the model demonstrates a robust accuracy of 89.71%and 88.88% on training and validation sets, solidifying its efficacy in intricate action recognition tasks.
26
Thakur, Ujwala, Ankit Vidyarthi, and Amarjeet Prajapati. "Recognition of Real-Time Video Activities Using Stacked Bi-GRU with Fusion-based Deep Architecture." JUCS - Journal of Universal Computer Science 30, no. (10) (2024): 1424–52. https://doi.org/10.3897/jucs.113095.
Full textAbstract:
Recognizing and understanding human activities in real-time videos is a challenging task due to the complex nature of video data and the need for efficient and accurate analysis. This research pioneers a breakthrough in video activity recognition by introducing a robust framework leveraging the power of a stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architecture, harmonized within a fusion-based deep model. The stacked Bi-LSTM-GRU model capitalizes on its dual recurrent architecture, capturing nuanced temporal dependencies within video sequences. The fusion-based deep architecture synergizes spatial and temporal features, enabling the model to discern intricate patterns in human activities. To further enhance the discriminative power of the model, we introduce a fusion module in the proposed deep architecture. The fusion module integrates multi-modal features extracted from different levels of the network hierarchy, allowing for a more comprehensive representation of video activities. We demonstrate the efficacy of our approach through rigorous experimentation on UCF50, UCF101, and HMDB51 datasets. In experiments on the UCF50 dataset, our model achieves an accuracy of 97.01% and 95.86% on training and validation sets respectively, showcasing its proficiency in discerning activities across a diverse range of scenarios. The evaluation extends to the UCF101 dataset, where the proposed approach achieves a competitive accuracy of 97.62% and 96.93% on training and validation sets, surpassing previous benchmarks by a margin of approx 1%. Further-more, on the challenging HMDB51 dataset, the model demonstrates a robust accuracy of 89.71%and 88.88% on training and validation sets, solidifying its efficacy in intricate action recognition tasks.
27
Yadav, Shweta, Asif Ekbal, Sriparna Saha, Ankit Kumar, and Pushpak Bhattacharyya. "Feature assisted stacked attentive shortest dependency path based Bi-LSTM model for protein–protein interaction." Knowledge-Based Systems 166 (February 2019): 18–29. http://dx.doi.org/10.1016/j.knosys.2018.11.020.
Full text
28
Shuxin, Shi, Han Bing, Wu Zhongdai, Han Dezhi, Wu Huafeng, and Mei Xiaojun. "BLSAE-SNIDS: A Bi-LSTM sparse autoencoder framework for satellite network intrusion detection." Computer Science and Information Systems, no. 00 (2024): 41. http://dx.doi.org/10.2298/csis240401041s.
Full textAbstract:
Due to disparities in tolerance, resource availability, and acquisition of labeled training data between satellite-terrestrial integrated networks (STINs) and terrestrial networks, the application of traditional terrestrial network intrusion detection techniques to satellite networks poses significant challenges. This paper presents a satellite network intrusion detection system named Bi-LSTM sparse selfencoder (BLSAE-SNIDS) to address this issue. Through the development of an innovative unsupervised training Bi-LSTM stacked self-encoder, BLSAE-SNIDS facilitates feature extraction from satellite network traffic, diminishes dimensionality, considerably reduces training and testing durations, and enhances the attack pre diction accuracy of the classifier. To assess the efficacy of the proposed model, we conduct comprehensive experiments utilizing STIN and UNSW-NB15 datasets. The results obtained from the STIN dataset demonstrate that BLSAE-SNIDS achieves 99.99% accuracy with reduced computational and transmission overheads alongside enhanced flexibility. Furthermore, results from the UNSW-NB15 dataset exhibit BLSAE-SNIDS? proficiency in detecting various network intrusion attacks efficiently. These findings indicate that BLSAE-SNIDS suits general satellite security networks and offers a novel approach to designing security systems for polar satellite networks, thus exhibiting practical utility.
29
El Maazoui, Q., A. Retbi, and S. Bennani. "AUTOMATISATION HYPERPARAMETERS TUNING PROCESS FOR TIMES SERIES FORECASTING: APPLICATION TO PASSENGER’S FLOW PREDICTION ON A RAILWAY NETWORK." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVIII-4/W3-2022 (December 2, 2022): 53–60. http://dx.doi.org/10.5194/isprs-archives-xlviii-4-w3-2022-53-2022.
Full textAbstract:
Abstract. Many industries and companies in various fields are interested in time series analysis to predict the future. However, in time series modeling, precision is lacking as time progress. In this paper, an architecture is proposed, allowing on the one hand keep the prediction accurate over time using the Walk Forward Optimization (WFO); On the other hand, automate the choice of parameters of the statistical models (ARIMA) introducing “AutoArima”; The RNN models, especially LSTM architectures (LSTM, Bi-LSTM, Stacked LSTM) using the function Optuna. Moreover, to avoid overfitting the LSTM models, an automatic function is implemented in the presented architecture. To demonstrate the validity of this research, a comparison of three models applied to a railway company to predict the flow of passengers is made. In particular, the naive model constitutes a reference base, the ARIMA model which had demonstrated its performances in several research, and finally, following the last progress in the neural networks the LSTM architecture is introduced in the paper. According to the results, the implemented architecture has great potential and more accurate predictions by using WFO. Through the comparisons of the models made, Each model has proven its performance according to the case of study. More concretely the mean absolute error obtained by LSTM for the railway stations is 0,13 compared to 0,15 obtained by ARIMA and 0,16 for the naive model, showing a small superiority for LSTM over ARIMA. On the other side, ARIMA excels on the Train lines.
30
Li, You, Xueyong Li, Yuewu Liu, Yuhua Yao, and Guohua Huang. "MPMABP: A CNN and Bi-LSTM-Based Method for Predicting Multi-Activities of Bioactive Peptides." Pharmaceuticals 15, no. 6 (2022): 707. http://dx.doi.org/10.3390/ph15060707.
Full textAbstract:
Bioactive peptides are typically small functional peptides with 2–20 amino acid residues and play versatile roles in metabolic and biological processes. Bioactive peptides are multi-functional, so it is vastly challenging to accurately detect all their functions simultaneously. We proposed a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM)-based deep learning method (called MPMABP) for recognizing multi-activities of bioactive peptides. The MPMABP stacked five CNNs at different scales, and used the residual network to preserve the information from loss. The empirical results showed that the MPMABP is superior to the state-of-the-art methods. Analysis on the distribution of amino acids indicated that the lysine preferred to appear in the anti-cancer peptide, the leucine in the anti-diabetic peptide, and the proline in the anti-hypertensive peptide. The method and analysis are beneficial to recognize multi-activities of bioactive peptides.
31
Terala, Pranaya K., Ayodeji S. Ogundana, Simon Y. Foo, Migara Y. Amarasinghe, and Huanyu Zang. "State of Charge Estimation of Lithium-Ion Batteries Using Stacked Encoder–Decoder Bi-Directional LSTM for EV and HEV Applications." Micromachines 13, no. 9 (2022): 1397. http://dx.doi.org/10.3390/mi13091397.
Full textAbstract:
Energy storage technologies are being used excessively in industrial applications and in automobiles. Battery state of charge (SOC) is an important metric to be monitored in these applications to ensure proper and safe functionality. Since SOC cannot be measured directly, this paper puts forth a novel machine learning architecture to improve on the existing methods of SOC estimation. This method consists of using combined stacked bi-directional LSTM and encoder–decoder bi-directional long short-term memory architecture. This architecture henceforth represented as SED is implemented to overcome the nonparallel functionality observed in traditional RNN algorithms. Estimations were made utilizing different open-source datasets such as urban dynamometer driving schedule (UDDS), highway fuel efficiency test (HWFET), LA92 and US06. The least Mean Absolute Error observed was 0.62% at 25 °C for the HWFET condition, which confirms the good functionality of the proposed architecture.
32
Paul, M. Robin Raj, and Dr K. Santhi Sree. "Ensemble Based Detection of Phishing URLs Using Hybrid, Deep Learning and Machine Learning Models." International Journal for Research in Applied Science and Engineering Technology 13, no. 5 (2025): 6402–15. https://doi.org/10.22214/ijraset.2025.71708.
Full textAbstract:
Abstract: Phishing attacks pose a serious cybersecurity threat, requiring advanced detection mechanisms. This study proposes an ensemble-based phishing Uniform Resource Locator(URL) detection framework integrating both machine learning and deep learning models. The first phase employs Adaboost, Naïve Bayes(NB), Random Forest(RF), Logistic Regression(LR), Support Vector Machine(SVM), Artificial Neural Network(ANN), Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Long Short TermMemory(LSTM) and Stacked Gated Recurrent Unit(Stacked GRU), combined using voting ensemble. The second phase includes detection with hybrid deep learning models, including Neural Network -Long Short Term Memory(NN_LSTM), StackedGated Recurrent Unit-Convolutional Neural Network-Long Short Term Memory(StackedGRU_CNN_LSTM), Deep Belief Network -StackedGated Recurrent UnitTransformer(DBN_StackedGRU_Transformer), Autoencoder+Convolutional Neural Network-Long Short Term Memory+BiGated Recurrent Unit(AutoencoderCNNLSTMBiGRU), and Multi LayerPerceptron-Bi-Long Short Term MemoryConvolutional Neural Network-Gated Recurrent Unit(MLP_BiLSTM_CNN_GRU), utilizing stacking and a host of other ensemble methods like Voting,Weighted Averaging, Confidence-Based Stacking, Gated Mixture of Experts, Neural Greedy Selector, Stacked with Featuresfor improved classification. Performance evaluation using accuracy, precision, recall, and F1- score shows that ensemble learning significantly enhances phishing detection accuracy, making it a robust cybersecurity solution.
33
Swarnalata Rath, Nilima R. Das, and Binod Kumar Pattanayak. "Stacked BI-LSTM and E-Optimized CNN-A Hybrid Deep Learning Model for Stock Price Prediction." Optical Memory and Neural Networks 33, no. 2 (2024): 102–20. http://dx.doi.org/10.3103/s1060992x24700024.
Full text
34
Mughees, Neelam, Mujtaba Hussain Jaffery, Abdullah Mughees, Anam Mughees, and Krzysztof Ejsmont. "Bi-LSTM-Based Deep Stacked Sequence-to-Sequence Autoencoder for Forecasting Solar Irradiation and Wind Speed." Computers, Materials & Continua 75, no. 3 (2023): 6375–93. http://dx.doi.org/10.32604/cmc.2023.038564.
Full text
35
Guo, Fusen, Huadong Mo, Jianzhang Wu, et al. "A Hybrid Stacking Model for Enhanced Short-Term Load Forecasting." Electronics 13, no. 14 (2024): 2719. http://dx.doi.org/10.3390/electronics13142719.
Full textAbstract:
The high penetration of distributed energy resources poses significant challenges to the dispatch and operation of power systems. Improving the accuracy of short-term load forecasting (STLF) can optimize grid management, thus leading to increased economic and social benefits. Currently, some simple AI and hybrid models have issues to deal with and struggle with multivariate dependencies, long-term dependencies, and nonlinear relationships. This paper proposes a novel hybrid model for short-term load forecasting (STLF) that integrates multiple AI models with Lasso regression using the stacking technique. The base learners include ANN, XgBoost, LSTM, Stacked LSTM, and Bi-LSTM, while lasso regression serves as the metalearner. By considering factors such as temperature, rainfall, and daily electricity prices, the model aims to more accurately reflect real-world conditions and enhance predictive accuracy. Empirical analyses on real-world datasets from Australia and Spain show significant improvements in the forecasting accuracy, with a substantial reduction in the mean absolute percentage error (MAPE) compared to existing hybrid models and individual AI models. This research highlights the efficiency of the stacking technique in improving STLF accuracy, thus suggesting potential operational efficiency benefits for the power industry.
36
Wegayehu, Eyob Betru, and Fiseha Behulu Muluneh. "Short-Term Daily Univariate Streamflow Forecasting Using Deep Learning Models." Advances in Meteorology 2022 (February 10, 2022): 1–21. http://dx.doi.org/10.1155/2022/1860460.
Full textAbstract:
Hydrological forecasting is one of the key research areas in hydrology. Innovative forecasting tools will reform water resources management systems, flood early warning mechanisms, and agricultural and hydropower management schemes. Hence, in this study, we compared Stacked Long Short-Term Memory (S-LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Gated Recurrent Unit (GRU) with the classical Multilayer Perceptron (MLP) network for one-step daily streamflow forecasting. The analysis used daily time series data collected from Borkena (in Awash river basin) and Gummera (in Abay river basin) streamflow stations. All data sets passed through rigorous quality control processes, and null values were filled using linear interpolation. A partial autocorrelation was also applied to select the appropriate time lag for input series generation. Then, the data is split into training and testing datasets using a ratio of 80 : 20, respectively. Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R2) were used to evaluate the performance of the proposed models. Finally, the findings are summarized in model variability, lag time variability, and time series characteristic themes. As a result, time series characteristics (climatic variability) had a more significant impact on streamflow forecasting performance than input lagged time steps and deep learning model architecture variations. Thus, Borkena’s river catchment forecasting result is more accurate than Gummera’s catchment forecasting result, with RMSE, MAE, MAPE, and R2 values ranging between (0.81 to 1.53, 0.29 to 0.96, 0.16 to 1.72, 0.96 to 0.99) and (17.43 to 17.99, 7.76 to 10.54, 0.16 to 1.03, 0.89 to 0.90) for both catchments, respectively. Although the performance is dependent on lag time variations, MLP and GRU outperform S-LSTM and Bi-LSTM on a nearly equal basis.
37
T., Mathu, and Raimond Kumudha. "A novel deep learning architecture for drug named entity recognition." TELKOMNIKA (Telecommunication, Computing, Electronics and Control) 19, no. 6 (2021): 1884–91. https://doi.org/10.12928/telkomnika.v19i6.21667.
Full textAbstract:
Drug named entity recognition (DNER) becomes the prerequisite of other medical relation extraction systems. Existing approaches to automatically recognize drug names includes rule-based, machine learning (ML) and deep learning (DL) techniques. DL techniques have been verified to be the state-of-the-art as it is independent of handcrafted features. The previous DL methods based on word embedding input representation uses the same vector representation for an entity irrespective of its context in different sentences and hence could not capture the context properly. Also, identification of the n-gram entity is a challenge. In this paper, a novel architecture is proposed that includes a sentence embedding layer that works on the entire sentence to efficiently capture the context of an entity. A hybrid model that comprises a stacked bidirectional long short-term memory (Bi-LSTM) with residual LSTM has been designed to overcome the limitations and to upgrade the performance of the model. We have contrasted the achievement of our proposed approach with other DNER models and the percentage of improvements of the proposed model over LSTM-conditional random field (CRF), LIU and WBI with respect to micro-average F1-score are 11.17, 8.8 and 17.64 respectively. The proposed model has also shown promising result in recognizing 2- and 3-gram entities.
38
Hu, Jennifer, Rushikesh Jagtap, Rishikumar Ravichandran, et al. "Data-Driven Air Quality and Environmental Evaluation for Cattle Farms." Atmosphere 14, no. 5 (2023): 771. http://dx.doi.org/10.3390/atmos14050771.
Full textAbstract:
The expansion of agricultural practices and the raising of animals are key contributors to air pollution. Cattle farms contain hazardous gases, so we developed a cattle farm air pollution analyzer to count the number of cattle and provide comprehensive statistics on different air pollutant concentrations based on severity over various time periods. The modeling was performed in two parts: the first stage focused on object detection using satellite data of farm images to identify and count the number of cattle; the second stage predicted the next hour air pollutant concentration of the seven cattle farm air pollutants considered. The output from the second stage was then visualized based on severity, and analytics were performed on the historical data. The visualization illustrates the relationship between cattle count and air pollutants, an important factor for analyzing the pollutant concentration trend. We proposed the models Detectron2, YOLOv4, RetinaNet, and YOLOv5 for the first stage, and LSTM (single/multi lag), CNN-LSTM, and Bi-LSTM for the second stage. YOLOv5 performed best in stage one with an average precision of 0.916 and recall of 0.912, with the average precision and recall for all models being above 0.87. For stage two, CNN-LSTM performed well with an MAE of 3.511 and an MAPE of 0.016, while a stacked model had an MAE of 5.010 and an MAPE of 0.023.
39
Algarni, Mona, Faisal Saeed, Tawfik Al-Hadhrami, Fahad Ghabban, and Mohammed Al-Sarem. "Deep Learning-Based Approach for Emotion Recognition Using Electroencephalography (EEG) Signals Using Bi-Directional Long Short-Term Memory (Bi-LSTM)." Sensors 22, no. 8 (2022): 2976. http://dx.doi.org/10.3390/s22082976.
Full textAbstract:
Emotions are an essential part of daily human communication. The emotional states and dynamics of the brain can be linked by electroencephalography (EEG) signals that can be used by the Brain–Computer Interface (BCI), to provide better human–machine interactions. Several studies have been conducted in the field of emotion recognition. However, one of the most important issues facing the emotion recognition process, using EEG signals, is the accuracy of recognition. This paper proposes a deep learning-based approach for emotion recognition through EEG signals, which includes data selection, feature extraction, feature selection and classification phases. This research serves the medical field, as the emotion recognition model helps diagnose psychological and behavioral disorders. The research contributes to improving the performance of the emotion recognition model to obtain more accurate results, which, in turn, aids in making the correct medical decisions. A standard pre-processed Database of Emotion Analysis using Physiological signaling (DEAP) was used in this work. The statistical features, wavelet features, and Hurst exponent were extracted from the dataset. The feature selection task was implemented through the Binary Gray Wolf Optimizer. At the classification stage, the stacked bi-directional Long Short-Term Memory (Bi-LSTM) Model was used to recognize human emotions. In this paper, emotions are classified into three main classes: arousal, valence and liking. The proposed approach achieved high accuracy compared to the methods used in past studies, with an average accuracy of 99.45%, 96.87% and 99.68% of valence, arousal, and liking, respectively, which is considered a high performance for the emotion recognition model.
40
Abdulameer, Yahya Hafedh. "Forecasting of Electrical Energy Consumption Using Hybrid Models of GRU, CNN, LSTM, And ML Regressors." Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications 16, no. 1 (2025): 560–75. https://doi.org/10.58346/jowua.2025.i1.033.
Full textAbstract:
Electricity consumption predictions for a long period are critical in the institutions that distribute the electricity and governmental or private entities that supply the electricity. It guarantees optimum energy utilization and aids in making strategic decisions for improving the energy production quality. This need is especially important in nations like Iraq, which has suffered from energy crises for many years. This study uses daily household electricity consumption data acquired from the Ministry of Electricity in Iraq, namely the Rusafa area of Baghdad, from 2022 to 2024. Weather data for the same years was also included, which contains external weather factors such as temperature, humidity, and solar radiation that directly influence consumption patterns. This paper proposes a hybrid forecasting model that utilizes advanced deep learning architectures LSTM and CNN-based deep learning architectures for forecasting along with an upgraded stacked hybrid model that employs CNN, GRU, Stacked Bi-LSTM, and machine learning regressors, such as XGBoost Regressor, and LightGBM Regressor. These models are being trained to improve accuracy in the forecast and to improve energy acoustic production strategies. The 30 epochs were trained and evaluated on the proposed model using the mean relative absolute error (MAPE) and mean root mean square error (RMSE) to examine the prediction quality. Among all models tested, the best performance was achieved using LightGBM regressor in our hybrid model with MAPE and RMSE of periodic forecasts for the next spilled of time being 0.185155 and 0.094603, respectively. The results show the potential of hybrid modeling techniques for energy forecasts and electricity distribution systems optimization.
41
Jadkar, Vinayak, Mayur Khandate, Vedant Gampawar, Pritesh Bhutada, and Prof Leena Deshpande. "Robotic Process Automation for Stock Selection Process and Price Prediction Model using Machine Learning Techniques." International Journal on Recent and Innovation Trends in Computing and Communication 10, no. 7 (2022): 50–57. http://dx.doi.org/10.17762/ijritcc.v10i7.5569.
Full textAbstract:
Among these last few years, we have seen a tremendous increase in the participation in financial markets as well as there are more robotic process automation jobs emerging in recent years. We can clearly see the scope and increased requirement in both these domains. In the stock market, predicting the stock prices/direction and making profits is the main goal whereas in rpa, tasks which are done on a regular basis are converted into automated or semi-automated form. In this paper we have tried to apply both things into the picture such as developing a price prediction model using machine learning techniques and automating the stock selecting process through technical screeners depending on user requirements. Stacked LSTM and Bi-directional LSTM ML techniques are used and for automation part powerful rpa tool Automation Anywhere has been used. Factors such as evaluation metrics and graph plots are compared for models and advantages, and disadvantages are discussed for using systems with RPA and without RPA practices. Price prediction plots have been analyzed for stocks of different sectors with highest market capitalization and results/analysis and inferences have been stated.
 
 
 
 
 
 
42
Lu, Guanyu, and Xiuxia Tian. "An Efficient Communication Intrusion Detection Scheme in AMI Combining Feature Dimensionality Reduction and Improved LSTM." Security and Communication Networks 2021 (April 20, 2021): 1–21. http://dx.doi.org/10.1155/2021/6631075.
Full textAbstract:
Communication intrusion detection in Advanced Metering Infrastructure (AMI) is an eminent security technology to ensure the stable operation of the Smart Grid. However, methods based on traditional machine learning are not appropriate for learning high-dimensional features and dealing with the data imbalance of communication traffic in AMI. To solve the above problems, we propose an intrusion detection scheme by combining feature dimensionality reduction and improved Long Short-Term Memory (LSTM). The Stacked Autoencoder (SAE) has shown excellent performance in feature dimensionality reduction. We compress high-dimensional feature input into low-dimensional feature output through SAE, narrowing the complexity of the model. Methods based on LSTM have a superior ability to detect abnormal traffic but cannot extract bidirectional structural features. We designed a Bi-directional Long Short-Term Memory (BiLSTM) model that added an Attention Mechanism. It can determine the criticality of the dimensionality and improve the accuracy of the classification model. Finally, we conduct experiments on the UNSW-NB15 dataset and the NSL-KDD dataset. The proposed scheme has obvious advantages in performance metrics such as accuracy and False Alarm Rate (FAR). The experimental results demonstrate that it can effectively identify the intrusion attack of communication in AMI.
43
Fu, Yanfang, Yishuai Du, Zijian Cao, Qiang Li, and Wei Xiang. "A Deep Learning Model for Network Intrusion Detection with Imbalanced Data." Electronics 11, no. 6 (2022): 898. http://dx.doi.org/10.3390/electronics11060898.
Full textAbstract:
With an increase in the number and types of network attacks, traditional firewalls and data encryption methods can no longer meet the needs of current network security. As a result, intrusion detection systems have been proposed to deal with network threats. The current mainstream intrusion detection algorithms are aided with machine learning but have problems of low detection rates and the need for extensive feature engineering. To address the issue of low detection accuracy, this paper proposes a model for traffic anomaly detection named a deep learning model for network intrusion detection (DLNID), which combines an attention mechanism and the bidirectional long short-term memory (Bi-LSTM) network, first extracting sequence features of data traffic through a convolutional neural network (CNN) network, then reassigning the weights of each channel through the attention mechanism, and finally using Bi-LSTM to learn the network of sequence features. In intrusion detection public data sets, there are serious imbalance data generally. To address data imbalance issues, this paper employs the method of adaptive synthetic sampling (ADASYN) for sample expansion of minority class samples, to eventually form a relatively symmetric dataset, and uses a modified stacked autoencoder for data dimensionality reduction with the objective of enhancing information fusion. DLNID is an end-to-end model, so it does not need to undergo the process of manual feature extraction. After being tested on the public benchmark dataset on network intrusion detection NSL-KDD, experimental results show that the accuracy and F1 score of this model are better than those of other comparison methods, reaching 90.73% and 89.65%, respectively.
44
Jalli, Ravi Kumar, Lipsa Priyadarshini, P. K. Dash, and Ranjeeta Bisoi. "Identification of multiple power quality disturbances in hybrid microgrid using deep stacked auto-encoder based bi-directional LSTM classifier." e-Prime - Advances in Electrical Engineering, Electronics and Energy 11 (March 2025): 100919. https://doi.org/10.1016/j.prime.2025.100919.
Full text
45
Aljebreen, Mohammed, Fatma S. Alrayes, Sumayh S. Aljameel, and Muhammad Kashif Saeed. "Political Optimization Algorithm with a Hybrid Deep Learning Assisted Malicious URL Detection Model." Sustainability 15, no. 24 (2023): 16811. http://dx.doi.org/10.3390/su152416811.
Full textAbstract:
With the enhancement of the Internet of Things (IoT), smart cities have developed the idea of conventional urbanization. IoT networks permit distributed smart devices to collect and process data in smart city structures utilizing an open channel, the Internet. Accordingly, challenges like security, centralization, privacy (i.e., execution data poisoning and inference attacks), scalability, transparency, and verifiability restrict faster variations of smart cities. Detecting malicious URLs in an IoT environment is crucial to protect devices and the network from potential security threats. Malicious URL detection is an essential element of cybersecurity. It is established that malicious URL attacks mean large risks in smart cities, comprising financial damages, losses of personal identifications, online banking, losing data, and loss of user confidentiality in online businesses, namely e-commerce and employment of social media. Therefore, this paper concentrates on the proposal of a Political Optimization Algorithm by a Hybrid Deep Learning Assisted Malicious URL Detection and Classification for Cybersecurity (POAHDL-MDC) technique. The presented POAHDL-MDC technique identifies whether malicious URLs occur. To accomplish this, the POAHDL-MDC technique performs pre-processing to transform the data to a compatible format, and a Fast Text word embedding process is involved. For malicious URL recognition, a Hybrid Deep Learning (HDL) model integrates the features of stacked autoencoder (SAE) and bi-directional long short-term memory (Bi-LSTM). Finally, POA is exploited for optimum hyperparameter tuning of the HDL technique. The simulation values of the POAHDL-MDC approach are tested on a Malicious URL database, and the outcome exhibits an improvement of the POAHDL-MDC technique with a maximal accuracy of 99.31%.
46
Uddin, Md Azher, Joolekha Bibi Joolee, Young-Koo Lee, and Kyung-Ah Sohn. "A Novel Multi-Modal Network-Based Dynamic Scene Understanding." ACM Transactions on Multimedia Computing, Communications, and Applications 18, no. 1 (2022): 1–19. http://dx.doi.org/10.1145/3462218.
Full textAbstract:
In recent years, dynamic scene understanding has gained attention from researchers because of its widespread applications. The main important factor in successfully understanding the dynamic scenes lies in jointly representing the appearance and motion features to obtain an informative description. Numerous methods have been introduced to solve dynamic scene recognition problem, nevertheless, a few concerns still need to be investigated. In this article, we introduce a novel multi-modal network for dynamic scene understanding from video data, which captures both spatial appearance and temporal dynamics effectively. Furthermore, two-level joint tuning layers are proposed to integrate the global and local spatial features as well as spatial and temporal stream deep features. In order to extract the temporal information, we present a novel dynamic descriptor, namely, Volume Symmetric Gradient Local Graph Structure ( VSGLGS ), which generates temporal feature maps similar to optical flow maps. However, this approach overcomes the issues of optical flow maps. Additionally, Volume Local Directional Transition Pattern ( VLDTP ) based handcrafted spatiotemporal feature descriptor is also introduced, which extracts the directional information through exploiting edge responses. Lastly, a stacked Bidirectional Long Short-Term Memory ( Bi-LSTM ) network along with a temporal mixed pooling scheme is designed to achieve the dynamic information without noise interference. The extensive experimental investigation proves that the proposed multi-modal network outperforms most of the state-of-the-art approaches for dynamic scene understanding.
47
Eslamieh, Pegah, Mehdi Shajari, and Ahmad Nickabadi. "User2Vec: A Novel Representation for the Information of the Social Networks for Stock Market Prediction Using Convolutional and Recurrent Neural Networks." Mathematics 11, no. 13 (2023): 2950. http://dx.doi.org/10.3390/math11132950.
Full textAbstract:
Predicting stock market trends is an intriguing and complex problem, which has drawn considerable attention from the research community. In recent years, researchers have employed machine learning techniques to develop prediction models by using numerical market data and textual messages on social networks as their primary sources of information. In this article, we propose User2Vec, a novel approach to improve stock market prediction accuracy, which contributes to more informed investment decision making. User2Vec is a unique method that recognizes the unequal impact of different user opinions on specific stocks, and it assigns weights to these opinions based on the accuracy of their associated social metrics. The User2Vec model begins by encoding each message as a vector. These vectors are then fed into a convolutional neural network (CNN) to generate an aggregated feature vector. Following this, a stacked bi-directional long short-term memory (LSTM) model provides the final representation of the input data over a period. LSTM-based models have shown promising results by effectively capturing the temporal patterns in time series market data. Finally, the output is fed into a classifier that predicts the trend of the target stock price for the next day. In contrast to previous attempts, User2Vec considers not only the sentiment of the messages, but also the social information associated with the users and the text content of the messages. It has been empirically proven that this inclusion provides valuable information for predicting stock direction, thereby significantly enhancing prediction accuracy. The proposed model was rigorously evaluated using various combinations of market data, encoded messages, and social features. The empirical studies conducted on the Dow Jones 30 stock market showed the model’s superiority over existing state-of-the-art models. The findings of these experiments reveal that including social information about users and their tweets, in addition to the sentiment and textual content of their messages, significantly improves the accuracy of stock market prediction.
48
Serrano, Salvatore, Luca Patanè, Omar Serghini, and Marco Scarpa. "Detection and Classification of Obstructive Sleep Apnea Using Audio Spectrogram Analysis." Electronics 13, no. 13 (2024): 2567. http://dx.doi.org/10.3390/electronics13132567.
Full textAbstract:
Sleep disorders are steadily increasing in the population and can significantly affect daily life. Low-cost and noninvasive systems that can assist the diagnostic process will become increasingly widespread in the coming years. This work aims to investigate and compare the performance of machine learning-based classifiers for the identification of obstructive sleep apnea–hypopnea (OSAH) events, including apnea/non-apnea status classification, apnea–hypopnea index (AHI) prediction, and AHI severity classification. The dataset considered contains recordings from 192 patients. It is derived from a recently released dataset which contains, amongst others, audio signals recorded with an ambient microphone placed ∼1 m above the studied subjects and apnea/hypopnea accurate events annotations performed by specialized medical doctors. We employ mel spectrogram images extracted from the environmental audio signals as input of a machine-learning-based classifier for apnea/hypopnea events classification. The proposed approach involves a stacked model which utilizes a combination of a pretrained VGG-like audio classification (VGGish) network and a bidirectional long short-term memory (bi-LSTM) network. Performance analysis was conducted using a 5-fold cross-validation approach, leaving out patients used for training and validation of the models in the testing step. Comparative evaluations with recently presented methods from the literature demonstrate the advantages of the proposed approach. The proposed architecture can be considered a useful tool for supporting OSAHS diagnoses by means of low-cost devices such as smartphones.
49
Zhang, Like, Chaowei Zhang, Zewei Zhang, and Yuchao Huang. "SAFE-GTA: Semantic Augmentation-Based Multimodal Fake News Detection via Global-Token Attention." Symmetry 17, no. 6 (2025): 961. https://doi.org/10.3390/sym17060961.
Full textAbstract:
Large pre-trained models (PLMs) have provided tremendous opportunities and potentialities for multimodal fake news detection. However, existing multimodal fake news detection methods never manipulate the token-wise hierarchical semantics of news yielded from PLMs and extremely rely on contrastive learning but ignore the symmetry between text and image in terms of the abstract level. This paper proposes a novel multimodal fake news detection method that helps to balance the understanding between text and image via (1) designing a global-token across-attention mechanism to capture the correlations between global text and tokenwise image representations (or tokenwise text and global image representations) obtained from BERT and ViT; (2) proposing a QK-sharing strategy within cross-attention to enforce model symmetry that reduces information redundancy and accelerates fusion without sacrificing representational power; (3) deploying a semantic augmentation module that systematically extracts token-wise multilayered text semantics from stacked BERT blocks via CNN and Bi-LSTM layers, thereby rebalancing abstract-level disparities by symmetrically enriching shallow and deep textual signals. We also prove the effectiveness of our approach by comparing it with four state-of-the-art baselines. All the comparisons were conducted using three widely adopted multimodal fake news datasets. The results show that our approach outperforms the benchmarks by 0.8% in accuracy and 2.2% in F1-score on average across the three datasets, which demonstrates a symmetric, token-centric fusion of fine-grained semantic fusion, thereby driving more robust fake news detection.
50
Gütl, Christian. "Editorial." JUCS - Journal of Universal Computer Science 30, no. 10 (2024): 1284–85. http://dx.doi.org/10.3897/jucs.137611.
Full textAbstract:
Dear Readers,&nbsp; Following the publication of the J.UCS special issue &lsquo;Fighting Cybersecurity Risks from a Multidisciplinary Perspective&rdquo; by our esteemed guest editors Steffen Wendzel, Aleksandra Mileva, Virginia N. L. Franqueira and Martin Gilje in mid-September, I am very pleased to announce today the ninth J.UCS regular issue of 2024. In this issue, various topical aspects of computer science are covered by 26 authors from 8 countries (Algeria, Brazil, India, Indonesia, Ireland, Israel, Serbia, Sri Lanka) in 6 articles. As always, I would like to thank all the authors for their sound research and the editorial board for their highly valuable review effort and suggestions for improvement. These contributions, together with the generous support of the consortium members, sustain the quality of our journal.&nbsp; As we want to secure the financial support also for the years to come, we are looking for institutions and libraries to financially support our diamond open access journal as part of the KOALA initiative. Please think about the possibility of such financial participation by your institution in the computer science and mathematics cluster of the KOALA initiative together with a lot of other active members, we would be very grateful for any kind of support.&nbsp; In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in receiving high-quality proposals for special issues on new topics and trends. Please consider yourself and encourage your colleagues to submit high-quality articles or special issue proposals for our journal.&nbsp; In this regular issue, I am very pleased to introduce the following 6 accepted articles: Panji Bintoro, Zulkifli Zulkifli, Yaya Heryadi, Fitriana Fitriana, Nopi Anggista Putri, and Dwi Yana Ayu Andini introduce their research on the automatic detection of systemic diseases to recognize Mpox virus using GPLNet based on skin lesions. In their research, Farhad Lotfi, Branka Rodi&#263;, Aleksandra Labus, and Zorica Bogdanovi&#263; from Serbia are looking at predicting university students&#39; anxiety by using supervised learning algorithms with providing pertinent feedback. Michele dos Santos Soares, C&aacute;ssio Andrade Furukawa, Maria Istela Cagnin, and D&eacute;bora Maria Barroso Paiva from Brazil discuss their research findings on identifying the accessibility barriers faced by the community of blind students and highlighting the main factors that hinder this community from accessing learning objects. Houda Tadjer, Zohra Mehenaoui, Yacine Lafif, Amira Chemmakh, and Asanka P. Sayakkara from Algeria discuss their research on time management for effective learning based on students&#39; temporal traces and the production of automatic feedback in an online learning environment. In a collaborative&nbsp;research effort between Sri Lanka, Ireland and Israel, Lojenaa Navanesan, Nhien-An Le-Khac, Yossi Oren, and Asanka P. Sayakkara cover in their research cross-device portability of machine learning models in electromagnetic side-channel analysis for forensics. Last but not least, Ujjwala Thakur, Ankit Vidyarthi, and Amarjeet Prajapati from India cover the latest research on video activity recognition by introducing a robust framework that leverages the power of a stacked Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architecture, harmonized within a fusion-based deep model.&nbsp; Enjoy Reading!&nbsp; Best regards,&nbsp; Christian G&uuml;tl, Managing Editor&nbsp;