To see the other types of publications on this topic, follow the link: Deep residual bidirectional long short-term memory fusion.
Journal articles on the topic 'Deep residual bidirectional long short-term memory fusion'
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 'Deep residual bidirectional long short-term memory fusion.'
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
Munsarif, Muhammad, and Ku Ruhana Ku-Mahamud. "Deep residual bidirectional long short-term memory fusion: achieving superior accuracy in facial emotion recognition." Bulletin of Electrical Engineering and Informatics 14, no. 3 (2025): 2143–55. https://doi.org/10.11591/eei.v14i3.9090.
Full textAbstract:
Facial emotion recognition (FER) is a crucial task in human communication. Various face emotion recognition models were introduced but often struggle with generalization across different datasets and handling subtle variations in expressions. This study aims to develop the deep residual bidirectional long short-term memory (Bi-LSTM) fusion method to improve FER accuracy. This method combines the strengths of convolutional neural networks (CNN) for spatial feature extraction and Bi-LSTM for capturing temporal dynamics, using residual layers to address the vanishing gradient problem. Testing was performed on three face emotion datasets, and a comparison was made with seventeen models. The results show perfect accuracy on the extended Cohn-Kanade (CK+) and the real-world affective faces database (RAF-DB) datasets and almost perfect accuracy on the face expression recognition plus (FERPlus) dataset. However, the receiver operating characteristic (ROC) curve for the CK+ dataset shows some inconsistencies, indicating potential overfitting. In contrast, the ROC curves for the RAF-DB and FERPlus datasets are consistent with the high accuracy achieved. The proposed method has proven highly efficient and reliable in classifying various facial expressions, making it a robust solution for FER applications.
2
Fan, Jiaxing, Lin Dong, Gang Sun, and Zhize Zhou. "A Deep Learning Approach for Mental Fatigue State Assessment." Sensors 25, no. 2 (2025): 555. https://doi.org/10.3390/s25020555.
Full textAbstract:
This study investigates mental fatigue in sports activities by leveraging deep learning techniques, deviating from the conventional use of heart rate variability (HRV) feature analysis found in previous research. The study utilizes a hybrid deep neural network model, which integrates Residual Networks (ResNet) and Bidirectional Long Short-Term Memory (Bi-LSTM) for feature extraction, and a transformer for feature fusion. The model achieves an impressive accuracy of 95.29% in identifying fatigue from original ECG data, 2D spectral characteristics and physiological information of subjects. In comparison to traditional methods, such as Support Vector Machines (SVMs) and Random Forests (RFs), as well as other deep learning methods, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), the proposed approach demonstrates significantly improved experimental outcomes. Overall, this study offers a promising solution for accurately recognizing fatigue through the analysis of physiological signals, with potential applications in sports and physical fitness training contexts.
3
Kang, Junhyuk, Jieun Shin, Jaewon Shin, Daeho Lee, and Ahyoung Choi. "Robust Human Activity Recognition by Integrating Image and Accelerometer Sensor Data Using Deep Fusion Network." Sensors 22, no. 1 (2021): 174. http://dx.doi.org/10.3390/s22010174.
Full textAbstract:
Studies on deep-learning-based behavioral pattern recognition have recently received considerable attention. However, if there are insufficient data and the activity to be identified is changed, a robust deep learning model cannot be created. This work contributes a generalized deep learning model that is robust to noise not dependent on input signals by extracting features through a deep learning model for each heterogeneous input signal that can maintain performance while minimizing preprocessing of the input signal. We propose a hybrid deep learning model that takes heterogeneous sensor data, an acceleration sensor, and an image as inputs. For accelerometer data, we use a convolutional neural network (CNN) and convolutional block attention module models (CBAM), and apply bidirectional long short-term memory and a residual neural network. The overall accuracy was 94.8% with a skeleton image and accelerometer data, and 93.1% with a skeleton image, coordinates, and accelerometer data after evaluating nine behaviors using the Berkeley Multimodal Human Action Database (MHAD). Furthermore, the accuracy of the investigation was revealed to be 93.4% with inverted images and 93.2% with white noise added to the accelerometer data. Testing with data that included inversion and noise data indicated that the suggested model was robust, with a performance deterioration of approximately 1%.
4
Song, Xudong, Qi Zhang, Rui Sun, et al. "A Hybrid Deep Learning Prediction Method of Remaining Useful Life for Rolling Bearings Using Multiscale Stacking Deep Residual Shrinkage Network." International Journal of Intelligent Systems 2023 (November 17, 2023): 1–15. http://dx.doi.org/10.1155/2023/6665534.
Full textAbstract:
The vibration signal is easily interfered by noise due to the influence of environment and other factors, which can lead to the poor adaptability, low accuracy of remaining useful life (RUL) prediction, and other problems. To solve this problem, this paper proposes a novel RUL prediction method, which is based on multiscale stacking deep residual shrinkage network (MSDRSN). MSDRSN combines the ability of stacking in improving prediction accuracy and the advantages of deep residual shrinkage network (DRSN) in denoising. First, cumulative sum (CUSUM) from statistics is used to divide the full life cycle of the rolling bearings and discover the points of failure. Second, stacking is used for feature learning on the raw data, multiple convolutional kernels of different scales are selected as base-learners, and fully connected neural networks are selected as meta-learners for feature fusion and learning. Then, DRSN is used to do prediction, and the acquired results are fitted with Savitzky–Golay (SG) smoothing. Finally, the effectiveness of the proposed method is proved by the IEEE PHM 2012 data challenge dataset. Compared with the multiscale convolutional neural network with fully connected layer (MSCNN-FC) and the bidirectional long short-term memory (BiLSTM) for RUL prediction under the noise. Using the proposed method, the mean absolute error (MSE) of the best result is 0.002 and the mean square error (MSE) is 0.014; meanwhile, the coefficient of determination (R2) of the best prediction result can reach 97.6%. It is also compared with other machine learning methods, and all the results prove the accuracy and effectiveness of the proposed method for RUL prediction applications.
5
Wang, Lei, Dongrun Chang, and Zongshuai Li. "MSCNN-BLSTM based Prediction of the Remaining Useful Life of Aeroengine." Journal of Physics: Conference Series 2361, no. 1 (2022): 012019. http://dx.doi.org/10.1088/1742-6596/2361/1/012019.
Full textAbstract:
Accurate prediction of the aeroengine remaining useful life (RUL) is essential to improve engine availability and reliability. Aiming at the reliable prediction of residual life of aeroengine system, an engine residual life prediction model based on the fusion of multiscale fusion two-dimensional convolutional neural network and bidirectional long and short term memory (MSCNN-BLSTM) is proposed. Based on the fusion of two-dimensional convolutional neural network and bidirectional long and short time memory (BLSTM) network, the engine medium and advanced features extracted by the convolutional neural network are integrated to make residual life prediction. Finally, C-MAPSS dataset provided by NASA was used for validation. It is shown that the proposed multiscale hybrid model, compared with other model predictions, reduces the performance index score and root mean square error by 32.2% and 14.7% respectively. It can be seen that the data-driven model can effectively extract the information from the degradation data, which improves the prediction performance of aeroengine remaining life.
6
Zhao, Yu, Rennong Yang, Guillaume Chevalier, Ximeng Xu, and Zhenxing Zhang. "Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors." Mathematical Problems in Engineering 2018 (December 30, 2018): 1–13. http://dx.doi.org/10.1155/2018/7316954.
Full textAbstract:
Human activity recognition (HAR) has become a popular topic in research because of its wide application. With the development of deep learning, new ideas have appeared to address HAR problems. Here, a deep network architecture using residual bidirectional long short-term memory (LSTM) is proposed. The advantages of the new network include that a bidirectional connection can concatenate the positive time direction (forward state) and the negative time direction (backward state). Second, residual connections between stacked cells act as shortcut for gradients, effectively avoiding the gradient vanishing problem. Generally, the proposed network shows improvements on both the temporal (using bidirectional cells) and the spatial (residual connections stacked) dimensions, aiming to enhance the recognition rate. When testing with the Opportunity dataset and the public domain UCI dataset, the accuracy is significantly improved compared with previous results.
7
Asadullaev, R. G., and M. A. Sitnikova. "INTELLIGENT MODEL FOR CLASSIFYING HEMODYNAMIC PATTERNS OF BRAIN ACTIVATION TO IDENTIFY NEUROCOGNITIVE MECHANISMS OF SPATIAL-NUMERICAL ASSOCIATIONS." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 235 (January 2024): 38–45. http://dx.doi.org/10.14489/vkit.2024.01.pp.038-045.
Full textAbstract:
The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.
8
Li, Xin, Hong Huang, Guotao Yuan, Zhaolian Wang, and Rui Du. "An Intrusion Detection Method based on Fusion Neural Network." Frontiers in Computing and Intelligent Systems 4, no. 2 (2023): 124–30. http://dx.doi.org/10.54097/fcis.v4i2.10369.
Full textAbstract:
Aiming at the problems of class imbalance, insufficient feature learning, weak generalization ability, and representation capability in existing intrusion detection models, we propose a multi-scale feature fusion Intrusion Detection Model (MSFF). This model combines multi-scale one-dimensional convolution and bidirectional long short-term memory (LSTM) networks, and incorporates residual connections with identity mappings to address the problem of network degradation. The multi-scale convolution captures feature representations at different levels, thereby improving the expressive power of the model. The WGAN-GP algorithm is employed to augment the minority samples and balance the dataset. By performing convolution operations and extracting local window features and global features using bidirectional LSTM units, the model effectively captures temporal information and long-term dependencies. Experimental results demonstrate significant performance improvement compared to a single model. The MSFF model achieves an accuracy of 99.50% and 94.73% in binary classification experiments on the NSL-KDD and UNSW-NB15 datasets, respectively, and an accuracy of 99.50% and 83.78% in multi-class classification experiments.
9
Xie, Jialing, Weifeng Shi, and Yuqi Shi. "Research on Fault Diagnosis of Six-Phase Propulsion Motor Drive Inverter for Marine Electric Propulsion System Based on Res-BiLSTM." Machines 10, no. 9 (2022): 736. http://dx.doi.org/10.3390/machines10090736.
Full textAbstract:
To ensure the implementation of the marine electric propulsion self-healing strategy after faults, it is necessary to diagnose and accurately classify the faults. Considering the characteristics of the residual network (ResNet) and bidirectional long short-term memory (BiLSTM), the Res-BiLSTM deep learning algorithm is used to establish a fault diagnosis model to distinguish the types of electric drive faults. First, the powerful fault feature extraction ability of the residual network is used to deeply mine the fault features in the signals. Then, perform time-series learning through a bidirectional long short-term memory network, and further excavate the transient time-series features in the fault features so as to achieve the accurate classification of drive inverter faults. The effectiveness of the method is verified using noise-free fault data, and the robustness of the method is verified using data with varying degrees of noise. The results show that compared with conventional deep learning algorithms, Res-BiLSTM has the fastest and most stable training process, the diagnostic performance is improved, and the accuracy can be maintained over 95% under 25–19 dB. It has certain robustness and can be applied to marine electric propulsion systems drive inverter fault diagnosis, and its results can provide data support for the implementation of self-healing control strategies.
10
Ma, Yahong, Zhentao Huang, Yuyao Yang, et al. "MSBiLSTM-Attention: EEG Emotion Recognition Model Based on Spatiotemporal Feature Fusion." Biomimetics 10, no. 3 (2025): 178. https://doi.org/10.3390/biomimetics10030178.
Full textAbstract:
Emotional states play a crucial role in shaping decision-making and social interactions, with sentiment analysis becoming an essential technology in human–computer emotional engagement, garnering increasing interest in artificial intelligence research. In EEG-based emotion analysis, the main challenges are feature extraction and classifier design, making the extraction of spatiotemporal information from EEG signals vital for effective emotion classification. Current methods largely depend on machine learning with manual feature extraction, while deep learning offers the advantage of automatic feature extraction and classification. Nonetheless, many deep learning approaches still necessitate manual preprocessing, which hampers accuracy and convenience. This paper introduces a novel deep learning technique that integrates multi-scale convolution and bidirectional long short-term memory networks with an attention mechanism for automatic EEG feature extraction and classification. By using raw EEG data, the method applies multi-scale convolutional neural networks and bidirectional long short-term memory networks to extract and merge features, selects key features via an attention mechanism, and classifies emotional EEG signals through a fully connected layer. The proposed model was evaluated on the SEED dataset for emotion classification. Experimental results demonstrate that this method effectively classifies EEG-based emotions, achieving classification accuracies of 99.44% for the three-class task and 99.85% for the four-class task in single validation, with average 10-fold-cross-validation accuracies of 99.49% and 99.70%, respectively. These findings suggest that the MSBiLSTM-Attention model is a powerful approach for emotion recognition.
11
Tong, Yizhi, Ping Wu, Jiajun He, Xujie Zhang, and Xinlong Zhao. "Bearing fault diagnosis by combining a deep residual shrinkage network and bidirectional LSTM." Measurement Science and Technology 33, no. 3 (2021): 034001. http://dx.doi.org/10.1088/1361-6501/ac37eb.
Full textAbstract:
Abstract Bearings are indispensable and key components in rotating machinery. To ensure the safe and reliable operation of rotating machinery, bearing fault diagnosis plays a crucial role. To explore the spatial and temporal information in vibration signals, a novel bearing fault diagnosis method is proposed by combining a deep residual shrinkage network (DRSN) and bidirectional long short-term memory (Bi-LSTM) network in this study. Firstly, a DRSN is employed to extract the spatial features from noise-related vibration signals. Then, a Bi-LSTM network is adopted to further address the long-term dependencies problem in vibration signals, where the temporal information is exploited. By integrating DRSN and Bi-LSTM, the spatial and temporal information of vibration signals is fully extracted. Finally, a fully connected layer with Softmax is used to offer the diagnostic results. Experimental results using two case studies demonstrate the effectiveness of the proposed method by comparison with other state-of-the-art methods.
12
He, Zhiqian, Qingzheng Liu, Anxu Chen, et al. "Metal Temperature Prediction Model based on Attention-Enhanced CNN-BiLSTM for Pulverized Coal Boiler Reheat Wall." Journal of Physics: Conference Series 3001, no. 1 (2025): 012018. https://doi.org/10.1088/1742-6596/3001/1/012018.
Full textAbstract:
Abstract The overheating of heat transfer wall is a primary contributor to boiler tube failures in coal-fired boilers. A fusion model that integrates sparse self-attention (SSA), convolutional neural networks (CNN), and bidirectional long short-term memory networks (BiLSTM) is proposed to predict the wall temperature of the final reheater, based on their dynamic characteristics. Firstly, the original candidate variables are subjected to filtering and dimensionality reduction through the KPCA algorithm, resulting in the selection of the top 26 principal component variables as the final input for the model. Secondly, leveraging the strengths of convolutional neural networks (CNN) in capturing local correlations and bidirectional long short-term memory networks (BiLSTM) in modeling long-term sequential dependencies, a CNN-BiLSTM architecture is employed to effectively capture both short-term and long-term dependencies within time series data. Additionally, a sparse self-attention mechanism (SSA) is incorporated to enhance CNN-BiLSTM’s performance by assigning varying weights to different components based on their significance. Simulations are performed utilizing historical data from an operational 1000MW ultra-supercritical boiler. The results indicate that the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) for the CNN-BiLSTM-SSA model are 4.92°C, 3.81°C, and 0.624%, respectively, demonstrating superior performance compared to CNN, LSTM, BiLSTM, CNN-LSTM, and CNN-BiLSTM models. The presented deep learning fusion model effectively predicts high-temperature reheater wall temperatures and holds significant theoretical and engineering value for addressing overheating issues in advance.
13
Zhang, Ke, and Yaming Guo. "Attention-Based Residual Dilated Network for Traffic Accident Prediction." Mathematics 11, no. 9 (2023): 2011. http://dx.doi.org/10.3390/math11092011.
Full textAbstract:
Traffic accidents directly influence public safety and economic development; thus, the prevention of traffic accidents is of great importance in urban transportation. The accurate prediction of traffic accidents can assist traffic departments to better control and prevent accidents. Thus, this paper proposes a deep learning method named attention-based residual dilated network (ARDN), to extract essential information from multi-source datasets and enhance accident prediction accuracy. The method utilizes bidirectional long short-term memory to model sequential information and incorporates an attention mechanism to recalibrate weights. Furthermore, a dilated residual layer is adopted to capture long term information effectively. Feature encoding is also employed to incorporate natural language descriptions and point-of-interest data. Experimental evaluations of datasets collected from Austin and Houston demonstrate that ARDN outperforms a range of machine learning methods, such as logistic regression, gradient boosting, Xgboost, and deep learning methods. The ablation experiments further confirm the indispensability of each component in the proposed method.
14
Cruz-Victoria, Juan Crescenciano, Alma Rosa Netzahuatl-Muñoz, and Eliseo Cristiani-Urbina. "Long Short-Term Memory and Bidirectional Long Short-Term Memory Modeling and Prediction of Hexavalent and Total Chromium Removal Capacity Kinetics of Cupressus lusitanica Bark." Sustainability 16, no. 7 (2024): 2874. http://dx.doi.org/10.3390/su16072874.
Full textAbstract:
Hexavalent chromium [Cr(VI)] is a high-priority environmental pollutant because of its toxicity and potential to contaminate water sources. Biosorption, using low-cost biomaterials, is an emerging technology for removing pollutants from water. In this study, Long Short-Term Memory (LSTM) and bidirectional LSTM (Bi-LSTM) neural networks were used to model and predict the kinetics of the removal capacity of Cr(VI) and total chromium [Cr(T)] using Cupressus lusitanica bark (CLB) particles. The models were developed using 34 experimental kinetics datasets under various temperature, pH, particle size, and initial Cr(VI) concentration conditions. Data preprocessing via interpolation was implemented to augment the sparse time-series data. Early stopping regularization prevented overfitting, and dropout techniques enhanced model robustness. The Bi-LSTM models demonstrated a superior performance compared to the LSTM models. The inherent complexities of the process and data limitations resulted in a heavy-tailed and left-skewed residual distribution, indicating occasional deviations in the predictions of capacities obtained under extreme conditions. K-fold cross-validation demonstrated the stability of Bi-LSTM models 38 and 43, while response surfaces and validation with unseen datasets assessed their predictive accuracy and generalization capabilities. Shapley additive explanations analysis (SHAP) identified the initial Cr(VI) concentration and time as the most influential input features for the models. This study highlights the capabilities of deep recurrent neural networks in comprehending and predicting complex pollutant removal kinetic phenomena for environmental applications.
15
Cui, Ziti, Wei Wang, Wei Jiang, Jun Guo, and Yang Liu. "High-precision identification and prediction of low-voltage load characteristics in smart grids based on hybrid deep learning framework." International Journal of Low-Carbon Technologies 19 (2024): 2656–66. http://dx.doi.org/10.1093/ijlct/ctae221.
Full textAbstract:
Abstract This paper proposes a hybrid deep learning framework (HDLF) that combines improved convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and transformer models. First, feature selection and dimensionality reduction are performed using XGBoost and principal component analysis, respectively. Secondly, CNN is enhanced by multiscale convolution, residual connection, and attention mechanism. Then, the bidirectional LSTM is combined with temporal convolutional network to improve the LSTM. Then, an improved dynamic focusing mechanism of transformer is introduced. The experimental results show that the HDLF has an accuracy of 0.945 in identifying low-pressure load characteristics.
16
Malki, Zohair, Elsayed Atlam, Guesh Dagnew, Ahmad Reda Alzighaibi, Elmarhomy Ghada, and Ibrahim Gad. "Bidirectional Residual LSTM-based Human Activity Recognition." Computer and Information Science 13, no. 3 (2020): 40. http://dx.doi.org/10.5539/cis.v13n3p40.
Full textAbstract:
The Residual Long Short Term Memory (LSTM) deep learning approach is attracting attension of many researchers due to its efficiency when trained on high dimensional datasets. Nowadays, Human Activity Recognition (HAR) has come with enormous challenges that have to be addressed. In addressing such a problem, one can think of developing an application that can help the elderly people as an assistant when it works in collaboration with other timely technologies such as wearable devices with the help of IoT. Many research works are using a standard dataset in evaluating their proposed method in this regard. The dataset comes with its own challenge such as imbalanced classes. In this work, we propose to apply different machine learning techniques to address the specified problems and the method is validated on a standard dataset. To validate the proposed method, we evaluated using different standard metrics such as classification accuracy, precision, recall, f1-score, and Receiver Operating Characteristic (ROC) curve. The proposed method achieves an Area Under Curve (AUC) of 100%, 97.66% of accuracy, 91.59% precision,  93.75% of recall and 92.66% of F1-score respectively.
17
Nguyen, Huu Khoa Minh, Quoc-Dung Phan, Yuan-Kang Wu, and Quoc-Thang Phan. "Multi-Step Wind Power Forecasting with Stacked Temporal Convolutional Network (S-TCN)." Energies 16, no. 9 (2023): 3792. http://dx.doi.org/10.3390/en16093792.
Full textAbstract:
Nowadays, wind power generation has become vital thanks to its advantages in cost, ecological friendliness, enormousness, and sustainability. However, the erratic and intermittent nature of this energy poses significant operational and management difficulties for power systems. Currently, the methods of wind power forecasting (WPF) are various and numerous. An accurate forecasting method of WPF can help system dispatchers plan unit commitment and reduce the risk of the unreliability of electricity supply. In order to improve the accuracy of short-term prediction for wind power and address the multi-step ahead forecasting, this research presents a Stacked Temporal Convolutional Network (S-TCN) model. By using dilated causal convolutions and residual connections, the suggested solution addresses the issue of long-term dependencies and performance degradation of deep convolutional models in sequence prediction. The simulation outcomes demonstrate that the S-TCN model’s training procedure is extremely stable and has a powerful capacity for generalization. Besides, the performance of the proposed model shows a higher forecasting accuracy compared to other existing neural networks like the Vanilla Long Short-Term Memory model or the Bidirectional Long Short-Term Memory model.
18
Jamatia, Anupam, Amitava Das, and Björn Gambäck. "Deep Learning-Based Language Identification in English-Hindi-Bengali Code-Mixed Social Media Corpora." Journal of Intelligent Systems 28, no. 3 (2019): 399–408. http://dx.doi.org/10.1515/jisys-2017-0440.
Full textAbstract:
Abstract This article addresses language identification at the word level in Indian social media corpora taken from Facebook, Twitter and WhatsApp posts that exhibit code-mixing between English-Hindi, English-Bengali, as well as a blend of both language pairs. Code-mixing is a fusion of multiple languages previously mainly associated with spoken language, but which social media users also deploy when communicating in ways that tend to be rather casual. The coarse nature of code-mixed social media text makes language identification challenging. Here, the performance of deep learning on this task is compared to feature-based learning, with two Recursive Neural Network techniques, Long Short Term Memory (LSTM) and bidirectional LSTM, being contrasted to a Conditional Random Fields (CRF) classifier. The results show the deep learners outscoring the CRF, with the bidirectional LSTM demonstrating the best language identification performance.
19
Yen, Chih-Ta, Sheng-Nan Chang, and Cheng-Hong Liao. "Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions." Measurement and Control 54, no. 3-4 (2021): 439–45. http://dx.doi.org/10.1177/00202940211001904.
Full textAbstract:
This study used photoplethysmography signals to classify hypertensive into no hypertension, prehypertension, stage I hypertension, and stage II hypertension. There are four deep learning models are compared in the study. The difficulties in the study are how to find the optimal parameters such as kernel, kernel size, and layers in less photoplethysmographyt (PPG) training data condition. PPG signals were used to train deep residual network convolutional neural network (ResNetCNN) and bidirectional long short-term memory (BILSTM) to determine the optimal operating parameters when each dataset consisted of 2100 data points. During the experiment, the proportion of training and testing datasets was 8:2. The model demonstrated an optimal classification accuracy of 76% when the testing dataset was used.
20
Wu, Yiqi, Mei Liu, Zhaoyuan Peng, Meiqi Liu, Miao Wang, and Yingqi Peng. "Recognising Cattle Behaviour with Deep Residual Bidirectional LSTM Model Using a Wearable Movement Monitoring Collar." Agriculture 12, no. 8 (2022): 1237. http://dx.doi.org/10.3390/agriculture12081237.
Full textAbstract:
Cattle behaviour is a significant indicator of cattle welfare. With the advancements in electronic equipment, monitoring and classifying multiple cattle behaviour patterns is becoming increasingly important in precision livestock management. The aim of this study was to detect important cattle physiological states using a neural network model and wearable electronic sensors. A novel long short-term memory (LSTM) recurrent neural network model that uses two-way information was developed to accurately classify cattle behaviour and compared with baseline LSTM. Deep residual bidirectional LSTM and baseline LSTM were used to classify six behavioural patterns of cows with window sizes of 64, 128 and 256 (6.4 s, 12.8 s and 25.6 s, respectively). The results showed that when using deep residual bidirectional LSTM with window size 128, four classification performance indicators, namely, accuracy, precision, recall, and F1-score, achieved the best results of 94.9%, 95.1%, 94.9%, and 94.9%, respectively. The results showed that the deep residual bidirectional LSTM model can be used to classify time-series data collected from twelve cows using inertial measurement unit collars. Six aim cattle behaviour patterns can be classified with high accuracy. This method can be used to quickly detect whether a cow is suffering from bovine dermatomycosis. Furthermore, this method can be used to implement automated and precise cattle behaviour classification techniques for precision livestock farming.
21
Cai, Linqin, Yaxin Hu, Jiangong Dong, and Sitong Zhou. "Audio-Textual Emotion Recognition Based on Improved Neural Networks." Mathematical Problems in Engineering 2019 (December 31, 2019): 1–9. http://dx.doi.org/10.1155/2019/2593036.
Full textAbstract:
With the rapid development in social media, single-modal emotion recognition is hard to satisfy the demands of the current emotional recognition system. Aiming to optimize the performance of the emotional recognition system, a multimodal emotion recognition model from speech and text was proposed in this paper. Considering the complementarity between different modes, CNN (convolutional neural network) and LSTM (long short-term memory) were combined in a form of binary channels to learn acoustic emotion features; meanwhile, an effective Bi-LSTM (bidirectional long short-term memory) network was resorted to capture the textual features. Furthermore, we applied a deep neural network to learn and classify the fusion features. The final emotional state was determined by the output of both speech and text emotion analysis. Finally, the multimodal fusion experiments were carried out to validate the proposed model on the IEMOCAP database. In comparison with the single modal, the overall recognition accuracy of text increased 6.70%, and that of speech emotion recognition soared 13.85%. Experimental results show that the recognition accuracy of our multimodal is higher than that of the single modal and outperforms other published multimodal models on the test datasets.
22
Yang, Chengjin, Yanzhong Zhai, and Zehua Liu. "Enhancing corn industry sustainability through deep learning hybrid models for price volatility forecasting." PLOS One 20, no. 6 (2025): e0323714. https://doi.org/10.1371/journal.pone.0323714.
Full textAbstract:
The fluctuations in corn prices not only increase uncertainty in the market but also affect farmers’ planting decisions and income stability, while also impeding crucial investments in sustainable agricultural practices. Collectively, these factors jeopardize the long-term sustainability of the corn sector. In order to address the challenges posed by maize price volatility to the sustainability of the industry, this study proposes a multi-module wavelet transform-based fusion forecasting model: the TLDCF-TSD-BiTCEN-BiLSTM-FECAM (TLDCF-TSD-BBF) model, which is capable of accurately predicting short-term maize price volatility, thereby enhancing the sustainability of the industry. The model integrates a three-layer decomposition combined dual-filter time-series denoising method (TLDCF-TSD), a bidirectional time-convolutional enhancement network (BiTCEN), a bidirectional long- and short-term memory network (BiLSTM), and a frequency-enhanced channel attention mechanism (FECAM) to improve prediction accuracy and robustness. First, TLDCF-TSD is used to decompose the corn price time series into multiple scales, effectively separating the frequency components, extracting the signal details and trend information, and reducing the data complexity and non-stationarity. Secondly, BiTCEN designed in this paper effectively captures the short-term dependencies in the corn price data through the unique bidirectional structure and the special hybrid convolutional structure, and then accurately extracts the local features of the data, while BiLSTM mines the long-term trends and complex dependencies in the data by exploiting its bidirectional processing and long-term memory capabilities. Finally, FECAM enhances the focus on key temporal features in the frequency domain by grouping the input features along the channel dimensions and applying discrete cosine transform to generate attention vectors, improving the prediction accuracy and robustness of the model. The dataset utilized in this study was sourced from the BREC Agricultural Big Data platform, ensuring the reliability and accuracy of the corn price data for our analysis. This study utilizes price data from China’s five major corn-producing regions as a case study to demonstrate the efficacy of the proposed model in corn price forecasting. Through extensive experimentation, it has been established that the model significantly outperforms existing baseline models across various evaluation metrics. To be more specific, when dealing with different datasets, its MAE values are 0.0093, 0.0137, 0.0081, 0.0055, and 0.0101 respectively; the MSE values are 0.0002, 0.0002, 0.0001, 0.0001, and 0.0002 respectively; the MAPE values are 1.3630, 1.7456, 1.1905, 0.8456, and 1.7567 respectively; and the R2 values are 0.9891, 0.9888, 0.9943, 0.9955, and 0.9933 respectively. These data fully demonstrate the excellent performance of this model.
23
Charles, Pranob Kumar, Habibulla Khan, and K. S. Rao. "Adaptive Video Coding Framework with Spatial-Temporal Fusion for Optimized Streaming in Next-Generation Networks." Intelligent Communication and Computing for Next Generation Wireless Communication Networks 11, NGWCN (2023): 20–24. http://dx.doi.org/10.37391/ijeer.11ngwcn04.
Full textAbstract:
Predicting future frames and improving inter-frame prediction are ongoing challenges in the field of video streaming. By creating a novel framework called STreamNet (Spatial-Temporal Video Coding), fusing bidirectional long short-term memory with temporal convolutional networks, this work aims to address the issue at hand. The development of STreamNet, which combines spatial hierarchies with local and global temporal dependencies in a seamless manner, along with sophisticated preprocessing, attention mechanisms, residual learning, and effective compression techniques, is the main contribution. Significantly, STreamNet claims to provide improved video coding quality and efficiency, making it suitable for next-generation networks. STreamNet has the potential to provide reliable and optimal streaming in high-demand network environments, as shown by preliminary tests that show a performance advantage over existing methods.
24
Choi, Kanghae, Hokyoung Ryu, and Jieun Kim. "Deep Residual Networks for User Authentication via Hand-Object Manipulations." Sensors 21, no. 9 (2021): 2981. http://dx.doi.org/10.3390/s21092981.
Full textAbstract:
With the ubiquity of wearable devices, various behavioural biometrics have been exploited for continuous user authentication during daily activities. However, biometric authentication using complex hand behaviours have not been sufficiently investigated. This paper presents an implicit and continuous user authentication model based on hand-object manipulation behaviour, using a finger-and hand-mounted inertial measurement unit (IMU)-based system and state-of-the-art deep learning models. We employed three convolutional neural network (CNN)-based deep residual networks (ResNets) with multiple depths (i.e., 50, 101, and 152 layers) and two recurrent neural network (RNN)-based long short-term memory (LSTMs): simple and bidirectional. To increase ecological validity, data collection of hand-object manipulation behaviours was based on three different age groups and simple and complex daily object manipulation scenarios. As a result, both the ResNets and LSTMs models acceptably identified users’ hand behaviour patterns, with the best average accuracy of 96.31% and F1-score of 88.08%. Specifically, in the simple hand behaviour authentication scenarios, more layers in residual networks tended to show better performance without showing conventional degradation problems (the ResNet-152 > ResNet-101 > ResNet-50). In a complex hand behaviour scenario, the ResNet models outperformed user authentication compared to the LSTMs. The 152-layered ResNet and bidirectional LSTM showed an average false rejection rate of 8.34% and 16.67% and an equal error rate of 1.62% and 9.95%, respectively.
25
Guo, Longfei, Yunwei Pu, and Wenxiang Zhao. "CNN-BiLSTM Daily Precipitation Prediction Based on Attention Mechanism." Atmosphere 16, no. 3 (2025): 333. https://doi.org/10.3390/atmos16030333.
Full textAbstract:
Accurate daily precipitation forecasting is crucial for the rational utilization of water resources and the prediction of flood disasters. To address the low reliability and low prediction accuracy of existing daily precipitation prediction models based on deep learning which arise from the nonlinear and non-stationary characteristics of surface precipitation data, this paper first employs the principal component analysis (PCA) method to extract the principal components of the original data. Given that the convolutional neural network (CNN) is adept at capturing spatial dependencies, bidirectional long short-term memory (Bi-LSTM, a variant of long short-term memory (LSTM)) can capture the long-term dependence of time-series data, and the attention mechanism allows the model to focus on the more important features of the input data. A PCA-CNN-BiLSTM-Attention fusion neural network was constructed. Taking Kunming, China as the study area, the experimental results demonstrate that the Nash efficiency coefficient of the proposed model reaches 0.993, which is 15.3% and 12.6% higher than that of the CNN-LSTM and CNN-BiLSTM models, respectively. This indicates high prediction accuracy and provides an effective and feasible method for daily precipitation prediction.
26
Khan, Gulista, Sanjeev Kumar Mandal, and Sunil Sharma. "Deployment of the deep learning fusion method to emotional semantic evaluation of natural language." Multidisciplinary Science Journal 5 (August 10, 2023): 2023ss0114. http://dx.doi.org/10.31893/multiscience.2023ss0114.
Full textAbstract:
The emotional semantic evaluation of natural language plays a crucial role in sentiment analysis. Deep learning methods have shown great potential in capturing the complex relationships between words and emotions. This paper proposes a deep learning fusion method for deploying emotional semantic evaluation. The technique combines multiple deep learning architectures to capture local and global contextual information, including Bidirectional Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) networks, and Self-Attention mechanisms. Pretrained GloVe word embedding’s utilized to enhance word representation. A novel fusion layer combines the outputs of individual models; employing self-attention means to assign weights dynamically. This allows the model to weigh the importance of different representations in the final prediction. Benchmark movie review (MR) for sentiment analysis and emotion classification tasks are used to evaluate the proposed method. Experimental results demonstrate superior performance compared to individual deep learning models and traditional feature-based approaches. The proposed fusion method effectively captures the nuances of emotional semantics in natural language, leading to more accurate and nuanced evaluations.
27
Geetha Paranjothi, Arunachalam A.S. "Lung Cancer Detection: Advancing CT Image Analysis Through Hybrid Bidirectional Long Short-Term Memory and Recurrent Neural Network." Journal of Information Systems Engineering and Management 10, no. 18s (2025): 29–46. https://doi.org/10.52783/jisem.v10i18s.2880.
Full textAbstract:
Globally, lung cancer (LC) is the leading cause of death from cancer. Medical image analysis based on deep learning (DL) has strong potential for detecting and diagnosing lung cancer by identifying early symptoms with image aid from positron emission tomography (PET) and computed tomography (CT). The majority of DL models created for LC detection are very resource-intensive, requiring a great deal of computational capacity; hence, they pose a challenge to deployment on a standard clinical system and are therefore significantly less accessible in resource-constrained settings. This additional computational load may delay diagnosis and treatment, thus affecting the outcome of the patients. Therein lies the critical need for developing more lightweight and efficient deep learning models that ensure high accuracy while reducing computational requirements. This manuscript presents a Lung Cancer Detection technique, LCD-CT-BiLSTM-RNN, based on advanced CT image analysis. First, noise reduction in the lung CT images by anisotropic guided filtering (AGF) is performed. Then, adaptive fuzzy K-means clustering (AFKMC) separates the affected areas of cancer, and Synchroextracting Transform (SET) adds the spectral features. Finally, a hybrid BiLSTM and RNN architecture runs the classification task with an improved overall accuracy. Hybrid optimization using Slime Mould Optimization (SMO) and Golden Eagle Optimization (GEO) fine-tunes the model. The performance of the methods is assessed using MATLAB's accuracy, precision, recall, F1-score, specificity, Matthews Correlation Coefficient (MCC), and ROC to compare the acquired findings with the existing approaches. The performance of the proposed method provides 2.03%, 3.45%, and 2.36% higher accuracy compared with existing techniques like Fuzzy Particle Swarm Optimization with Convolutional Neural Network for Detection of LC (FPSO-CNN), Deep learning Instantaneously Accomplished Neural Network with Improved Profuse Clustering Technique for LC detection (DITNN-IPCT), and Residual Learning Denoising Model with Convolutional Neural Network (DR-Net-CNN) for the Detection of LC.
28
Abid, Fazeel, Muhammad Alam, Faten S. Alamri, and Imran Siddique. "Multi-directional gated recurrent unit and convolutional neural network for load and energy forecasting: A novel hybridization." AIMS Mathematics 8, no. 9 (2023): 19993–20017. http://dx.doi.org/10.3934/math.20231019.
Full textAbstract:
<abstract> <p>Energy operations and schedules are significantly impacted by load and energy forecasting systems. An effective system is a requirement for a sustainable and equitable environment. Additionally, a trustworthy forecasting management system enhances the resilience of power systems by cutting power and load-forecast flaws. However, due to the numerous inherent nonlinear properties of huge and diverse data, the classical statistical methodology cannot appropriately learn this non-linearity in data. Energy systems can appropriately evaluate data and regulate energy consumption because of advanced techniques. In comparison to machine learning, deep learning techniques have lately been used to predict energy consumption as well as to learn long-term dependencies. In this work, a fusion of novel multi-directional gated recurrent unit (MD-GRU) with convolutional neural network (CNN) using global average pooling (GAP) as hybridization is being proposed for load and energy forecasting. The spatial and temporal aspects, along with the high dimensionality of the data, are addressed by employing the capabilities of MD-GRU and CNN integration. The obtained results are compared to baseline algorithms including CNN, Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), Gated Recurrent Unit (GRU), and Bidirectional Gated Recurrent Unit (Bi-GRU). The experimental findings indicate that the proposed approach surpasses conventional approaches in terms of accuracy, Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RSME).</p> </abstract>
29
Fang, Yifan, Shanshan Jiang, Shengxuan Fang, Zhenxi Gong, Min Xia, and Xiaodong Zhang. "Non-Intrusive Load Disaggregation Based on a Feature Reused Long Short-Term Memory Multiple Output Network." Buildings 12, no. 7 (2022): 1048. http://dx.doi.org/10.3390/buildings12071048.
Full textAbstract:
Load decomposition technology is an important aspect of power intelligence. At present, there are mainly machine learning methods based on artificial features and deep learning methods for load decomposition. The method based on artificial features has a difficult time obtaining effective load features, leading to low accuracy. The method based on deep learning can automatically extract load characteristics, which improves the accuracy of load decomposition. However, with the deepening of the model structure, the number of parameters becomes too large, the training speed is slow, and the computing cost is high, which leads to the reduction of redundant features and the learning ability in some shallow networks, and the traditional deep learning model has a difficult time obtaining effective features on the time scale. To address these problems, a feature reused long short-term memory multiple output network (M-LSTM) is proposed and used for non-invasive load decomposition tasks. The network proposes an improved multiscale fusion residual module to extract basic load features and proposes the use of LSTM cyclic units to extract time series information. Feature reuse is achieved by combining it with the reorganization of the input data into multiple branches. The proposed structure reduces the difficulty of network optimization, and multi-scale fusion can obtain features on multiple time scales, which improves the ability of model feature extraction. Compared with common network models that tend to train network models for a single target load, the structure can simultaneously decompose the target load power while ensuring the accuracy of load decomposition, thus reducing computational costs, avoiding repetitive model training, and improving training efficiency.
30
Setiadi, De Rosal Ignatius Moses, Kristiawan Nugroho, Ahmad Rofiqul Muslikh, Syahroni Wahyu Iriananda, and Arnold Adimabua Ojugo. "Integrating SMOTE-Tomek and Fusion Learning with XGBoost Meta-Learner for Robust Diabetes Recognition." Journal of Future Artificial Intelligence and Technologies 1, no. 1 (2024): 23–38. http://dx.doi.org/10.62411/faith.2024-11.
Full textAbstract:
This research aims to develop a robust diabetes classification method by integrating the Synthetic Minority Over-sampling Technique (SMOTE)-Tomek technique for data balancing and using a machine learning ensemble led by eXtreme Gradient Boosting (XGB) as a meta-learner. We propose an ensemble model that combines deep learning techniques such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU) with XGB classifier as the base learner. The data used included the Pima Indians Diabetes and Iraqi Society Diabetes datasets, which were processed by missing value handling, duplication, normalization, and the application of SMOTE-Tomek to resolve data imbalances. XGB, as a meta-learner, successfully improves the model's predictive ability by reducing bias and variance, resulting in more accurate and robust classification. The proposed ensemble model achieves perfect accuracy, precision, recall, specificity, and F1 score of 100% on all tested datasets. This method shows that combining ensemble learning techniques with a rigorous preprocessing approach can significantly improve diabetes classification performance.
31
Ge, Ming, and Yongbo Yuan. "Evaluation model design of project construction safety level based on bidirectional recurrent neural network (BiRNN) and bidirectional long short-term memory (BiLSTM)." PeerJ Computer Science 10 (October 18, 2024): e2351. http://dx.doi.org/10.7717/peerj-cs.2351.
Full textAbstract:
Integrating deep learning methods for multi-element regression analysis poses a challenge in constructing safety evaluations for building construction. To address this challenge, this paper evaluates the integration of construction safety by quantitatively analyzing practitioners’ information and on-site construction conditions. The analytic hierarchy process (AHP) method quantifies construction safety capabilities, considering four key aspects: operators’ primary conditions, organizational personnel’s working conditions, on-site management conditions, and analysis of unsafe behaviors. A comprehensive set of 19 secondary causal factors is constructed. Furthermore, a hybrid model based on bidirectional recurrent neural network (BiRNN) and bidirectional long short-term memory (BiLSTM) is developed for construction safety evaluation, enhancing the model’s generalization ability by introducing the Dropout mechanism. Experimental results demonstrate that the fusion of BiRNN and BiLSTM methods outperforms traditional methods in construction safety evaluation, yielding mean squared error (MSE) and root mean squared error (RMSE) values of 0.48 and 0.69 and mean absolute error (MAE) and mean absolute percentage error (MAPE) values of 0.54 and 3.36%, respectively. The case study affirms that BiRNN-BiLSTM can accurately identify potential safety risks, providing reliable decision support for project management.
32
Adil, Mohd, Jei-Zheng Wu, Ripon K. Chakrabortty, Ahmad Alahmadi, Mohd Faizan Ansari, and Michael J. Ryan. "Attention-Based STL-BiLSTM Network to Forecast Tourist Arrival." Processes 9, no. 10 (2021): 1759. http://dx.doi.org/10.3390/pr9101759.
Full textAbstract:
Tourism makes a significant contribution to the economy of almost every country, so accurate demand forecasting can help in better planning for the government and a range of stakeholders involved in the tourism industry and can aid economic sustainability. Machine learning models, and in particular, deep neural networks, can perform better than traditional forecasting models which depend mainly on past observations (e.g., past data) to forecast future tourist arrivals. However, search intensities indices (SII) indicators have recently been included as a forecasting model, which significantly enhances forecasting accuracy. In this study, we propose a bidirectional long short-term memory (BiLSTM) neural network to forecast the arrival of tourists along with SII indicators. The proposed BiLSTM network can remember information from left to right and right to left, which further adds more context for forecasting in memory as compared to a simple long short- term memory (LSTM) network that can remember information only from left to right. A seasonal and trend decomposition using the Loess (STL) approach is utilized to decompose time series tourist arrival data suggested by previous studies. The resultant approach, called STL-BiLSTM, decomposes time series into trend, seasonality, and residual. The trend provides the general direction of the overall data. Seasonality is a regular and predictable pattern which re-occurs at fixed time intervals, and residual is a random fluctuation that is something which cannot be forecast. The proposed BiLSTM network achieves better accuracy than the other methods considered under the current study.
33
Zhang, Hao, Qiang Zhang, Siyu Shao, Tianlin Niu, Xinyu Yang, and Haibin Ding. "Sequential Network with Residual Neural Network for Rotatory Machine Remaining Useful Life Prediction Using Deep Transfer Learning." Shock and Vibration 2020 (September 14, 2020): 1–16. http://dx.doi.org/10.1155/2020/8888627.
Full textAbstract:
Deep learning has a strong feature learning ability, which has proved its effectiveness in fault prediction and remaining useful life prediction of rotatory machine. However, training a deep network from scratch requires a large amount of training data and is time-consuming. In the practical model training process, it is difficult for the deep model to converge when the parameter initialization is inappropriate, which results in poor prediction performance. In this paper, a novel deep learning framework is proposed to predict the remaining useful life of rotatory machine with high accuracy. Firstly, model parameters and feature learning ability of the pretrained model are transferred to the new network by means of transfer learning to achieve reasonable initialization. Then, the specific sensor signals are converted to RGB image as the specific task data to fine-tune the parameters of the high-level network structure. The features extracted from the pretrained network are the input into the Bidirectional Long Short-Term Memory to obtain the RUL prediction results. The ability of LSTM to model sequence signals and the dynamic learning ability of bidirectional propagation to time information contribute to accurate RUL prediction. Finally, the deep model proposed in this paper is tested on the sensor signal dataset of bearing and gearbox. The high accuracy prediction results show the superiority of the transfer learning-based sequential network in RUL prediction.
34
Xiao, Xiaqiu, Buyun Sheng, Gaocai Fu, and Yingkang Lu. "Construction of Knowledge Graph for Air Compressor Fault Diagnosis Based on a Feature-Fusion RoBERTa-BiLSTM-CRF Model." Actuators 13, no. 9 (2024): 339. http://dx.doi.org/10.3390/act13090339.
Full textAbstract:
Diagnosing complex air compressor systems with traditional data-driven deep learning models often results in isolated fault diagnosis, ignoring correlations between concurrent faults. This paper introduces a knowledge graph construction approach for the air compressor fault diagnosis field, using after-sales business data as the source. We propose a model based on Robustly Optimized Bidirectional Encoder Representations from Transformers (RoBERTa), specifically tailored for constructing a knowledge graph for air compressor fault diagnosis. By integrating Whole Word Masking (WWM) technology, Bidirectional Long Short-Term Memory (BiLSTM), and Conditional Random Fields (CRFs), our approach effectively extracts specific entities from unstructured data. On our dataset, the model achieved an average accuracy of 0.7962 and an F1 score of 0.7956, demonstrating notable improvements in both accuracy and recall for entity recognition tasks. The extracted entities were subsequently stored in a Neo4j graph database, facilitating the construction of a domain-specific knowledge graph for air compressor fault diagnosis.
35
Dhaka, Priyanka, and Ruchi Sehrawat. "Adaptive Ensembled Fusion Based Deep CNN-Bilstm Model For Heart Disease Prediction In IoT." Fusion: Practice and Applications 14, no. 1 (2024): 40–55. http://dx.doi.org/10.54216/fpa.140104.
Full textAbstract:
Internet-of-Things (IoT)-based heart disease prediction is a complex task and processing the real collected data directly for remote patient monitoring suffers from the limitations due to the irrelevant data features, affecting the prediction accuracy and raising the security concerns. Hence, the efficient Adaptive ensembled deep Convolution neural network –Bidirectional Long Short Term Memory (Adaptive ensembled deep CNN-BiLSTM ) classifier model is proposed via the fusion of interactive hunt-based CNN and Whale on Marine optimization (WoM)-based deep BiLSTM. The Adaptive optimization developed from the standard hybrid characteristics such as random searching, seeking, attack prohibition, following, and waiting characteristics optimized the fusion parameters of the developed classifier for attaining high detection accuracy. Additionally, the modified Elliptic Curve Cryptography (ECC) based Diffi-Huffman encryption algorithm provides the authentication and security of sensitive patient data in heart disease prediction. The developed model is evaluated with other competent methods in terms of accuracy, sensitivity, specificity as well as F-measure, which are reported as 97.573%, 98.012%, 97.592%, and 97.705% respectively.
36
Parivendan, Sibi Chakravathy, Kashfia Sailunaz, and Suresh Neethirajan. "Socializing AI: Integrating Social Network Analysis and Deep Learning for Precision Dairy Cow Monitoring—A Critical Review." Animals 15, no. 13 (2025): 1835. https://doi.org/10.3390/ani15131835.
Full textAbstract:
This review critically analyzes recent advancements in dairy cow behavior recognition, highlighting novel methodological contributions through the integration of advanced artificial intelligence (AI) techniques such as transformer models and multi-view tracking with social network analysis (SNA). Such integration offers transformative opportunities for improving dairy cattle welfare, but current applications remain limited. We describe the transition from manual, observer-based assessments to automated, scalable methods using convolutional neural networks (CNNs), spatio-temporal models, and attention mechanisms. Although object detection models, including You Only Look Once (YOLO), EfficientDet, and sequence models, such as Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Long Short-Term Memory (convLSTM), have improved detection and classification, significant challenges remain, including occlusions, annotation bottlenecks, dataset diversity, and limited generalizability. Existing interaction inference methods rely heavily on distance-based approximations (i.e., assuming that proximity implies social interaction), lacking the semantic depth essential for comprehensive SNA. To address this, we propose innovative methodological intersections such as pose-aware SNA frameworks and multi-camera fusion techniques. Moreover, we explicitly discuss ethical challenges and data governance issues, emphasizing data transparency and animal welfare concerns within precision livestock contexts. We clarify how these methodological innovations directly impact practical farming by enhancing monitoring precision, herd management, and welfare outcomes. Ultimately, this synthesis advocates for strategic, empathetic, and ethically responsible precision dairy farming practices, significantly advancing both dairy cow welfare and operational effectiveness.
37
Liu, Yong, Jiaqi Liu, Han Wang, Mingshun Yang, Xinqin Gao, and Shujuan Li. "A Remaining Useful Life Prediction Method of Mechanical Equipment Based on Particle Swarm Optimization-Convolutional Neural Network-Bidirectional Long Short-Term Memory." Machines 12, no. 5 (2024): 342. http://dx.doi.org/10.3390/machines12050342.
Full textAbstract:
In industry, forecast prediction and health management (PHM) is used to improve system reliability and efficiency. In PHM, remaining useful life (RUL) prediction plays a key role in preventing machine failures and reducing operating costs, especially for reliability requirements such as critical components in aviation as well as for costly equipment. With the development of deep learning techniques, many RUL prediction methods employ convolutional neural network (CNN) and long short-term memory (LSTM) networks and demonstrate superior performance. In this paper, a novel two-stream network based on a bidirectional long short-term memory neural network (BiLSTM) is proposed to establish a two-stage residual life prediction model for mechanical devices using CNN as the feature extractor and BiLSTM as the timing processor, and finally, a particle swarm optimization (PSO) algorithm is used to adjust and optimize the network structural parameters for the initial data. Under the condition of lack of professional knowledge, the adaptive extraction of the features of the data accumulated by the enterprise and the effective processing of a large amount of timing data are achieved. Comparing the prediction results with other models through examples, it shows that the model established in this paper significantly improves the accuracy and efficiency of equipment remaining life prediction.
38
Zhao, Jianjun, Wenying Yan, and Yang Yang. "DeepTP: A Deep Learning Model for Thermophilic Protein Prediction." International Journal of Molecular Sciences 24, no. 3 (2023): 2217. http://dx.doi.org/10.3390/ijms24032217.
Full textAbstract:
Thermophilic proteins have important value in the fields of biopharmaceuticals and enzyme engineering. Most existing thermophilic protein prediction models are based on traditional machine learning algorithms and do not fully utilize protein sequence information. To solve this problem, a deep learning model based on self-attention and multiple-channel feature fusion was proposed to predict thermophilic proteins, called DeepTP. First, a large new dataset consisting of 20,842 proteins was constructed. Second, a convolutional neural network and bidirectional long short-term memory network were used to extract the hidden features in protein sequences. Different weights were then assigned to features through self-attention, and finally, biological features were integrated to build a prediction model. In a performance comparison with existing methods, DeepTP had better performance and scalability in an independent balanced test set and validation set, with AUC values of 0.944 and 0.801, respectively. In the unbalanced test set, DeepTP had an average precision (AP) of 0.536. The tool is freely available.
39
Huang, Songtao, Jun Shen, Qingquan Lv, Qingguo Zhou, and Binbin Yong. "A Novel NODE Approach Combined with LSTM for Short-Term Electricity Load Forecasting." Future Internet 15, no. 1 (2022): 22. http://dx.doi.org/10.3390/fi15010022.
Full textAbstract:
Electricity load forecasting has seen increasing importance recently, especially with the effectiveness of deep learning methods growing. Improving the accuracy of electricity load forecasting is vital for public resources management departments. Traditional neural network methods such as long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) have been widely used in electricity load forecasting. However, LSTM and its variants are not sensitive to the dynamic change of inputs and miss the internal nonperiodic rules of series, due to their discrete observation interval. In this paper, a novel neural ordinary differential equation (NODE) method, which can be seen as a continuous version of residual network (ResNet), is applied to electricity load forecasting to learn dynamics of time series. We design three groups of models based on LSTM and BiLSTM and compare the accuracy between models using NODE and without NODE. The experimental results show that NODE can improve the prediction accuracy of LSTM and BiLSTM. It indicates that NODE is an effective approach to improving the accuracy of electricity load forecasting.
40
Saddozai, Furqan Khan, Sahar K. Badri, Daniyal Alghazzawi, Asad Khattak, and Muhammad Zubair Asghar. "Multimodal hate speech detection: a novel deep learning framework for multilingual text and images." PeerJ Computer Science 11 (April 16, 2025): e2801. https://doi.org/10.7717/peerj-cs.2801.
Full textAbstract:
The rapid proliferation of social media platforms has facilitated the expression of opinions but also enabled the spread of hate speech. Detecting multimodal hate speech in low-resource multilingual contexts poses significant challenges. This study presents a deep learning framework that integrates bidirectional long short-term memory (BiLSTM) and EfficientNetB1 to classify hate speech in Urdu-English tweets, leveraging both text and image modalities. We introduce multimodal multilingual hate speech (MMHS11K), a manually annotated dataset comprising 11,000 multimodal tweets. Using an early fusion strategy, text and image features were combined for classification. Experimental results demonstrate that the BiLSTM+EfficientNetB1 model outperforms unimodal and baseline multimodal approaches, achieving an F1-score of 81.2% for Urdu tweets and 75.5% for English tweets. This research addresses critical gaps in multilingual and multimodal hate speech detection, offering a foundation for future advancements.
41
Zheng, Tianwei, Mei Wang, Yuan Guo, and Zheng Wang. "The Bidirectional Information Fusion Using an Improved LSTM Model." Mobile Information Systems 2021 (April 20, 2021): 1–15. http://dx.doi.org/10.1155/2021/5595898.
Full textAbstract:
The information fusion technology is of great significance in intelligent systems. At present, the modern coal-fired power plant has the fully functional sensor network. However, many data that are important for the operation of a power plant, such as the coal quality, cannot be directly obtained. Therefore, the information fusion technology needs to be introduced to obtain the implied information of the power plant. As a practical application, the soft measurement of coal quality is taken as the research object. This paper proposes an improved LSTM model combined with the bidirectional deep fusion, alertness mechanism, and parameter self-learning (DFAS-LSTM) to realize online soft computing for the coal quality analyses of industries and elements. First, a latent structure model is established to preprocess the noisy and redundant sensor network data. Second, an alertness mechanism is proposed and the self-learning method of the activation function parameters is used for the data feature extraction. Third, a deeply bidirectional fusion layer is added to the long short-term memory neural network model to solve the problem of the insufficient accuracy and the weak generalization. Using the historical data of the sensor network, the DFAS-LSTM model is established. Then, the online data of the sensor network is input to the DFAS-LSTM model to implement the online coal quality analyses. Experiment shows that the accuracy of the coal quality analyses is increased by 1%–2.42% compared to the traditionally bidirectional LSTM.
42
Chen, Kangen, Xiuhong Lin, Tao Xia, and Rushan Bai. "Research on Park Perception and Understanding Methods Based on Multimodal Text–Image Data and Bidirectional Attention Mechanism." Buildings 15, no. 9 (2025): 1552. https://doi.org/10.3390/buildings15091552.
Full textAbstract:
Parks are an important component of urban ecosystems, yet traditional research often relies on single-modal data, such as text or images alone, making it difficult to comprehensively and accurately capture the complex emotional experiences of visitors and their relationships with the environment. This study proposes a park perception and understanding model based on multimodal text–image data and a bidirectional attention mechanism. By integrating text and image data, the model incorporates a bidirectional encoder representations from transformers (BERT)-based text feature extraction module, a Swin Transformer-based image feature extraction module, and a bidirectional cross-attention fusion module, enabling a more precise assessment of visitors’ emotional experiences in parks. Experimental results show that compared to traditional methods such as residual network (ResNet), recurrent neural network (RNN), and long short-term memory (LSTM), the proposed model achieves significant advantages across multiple evaluation metrics, including mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R2). Furthermore, using the SHapley Additive exPlanations (SHAP) method, this study identified the key factors influencing visitors’ emotional experiences, such as “water”, “green”, and “sky”, providing a scientific basis for park management and optimization.
43
Zhang, Chen, Qingxu Li, and Xue Cheng. "Text Sentiment Classification Based on Feature Fusion." Revue d'Intelligence Artificielle 34, no. 4 (2020): 515–20. http://dx.doi.org/10.18280/ria.340418.
Full textAbstract:
The convolutional neural network (CNN) and long short-term memory (LSTM) network are adept at extracting local and global features, respectively. Both can achieve excellent classification effects. However, the CNN performs poorly in extracting the global contextual information of the text, while LSTM often overlooks the features hidden between words. For text sentiment classification, this paper combines the CNN with bidirectional LSTM (BiLSTM) into a parallel hybrid model called CNN_BiLSTM. Firstly, the CNN was adopted to extract the local features of the text quickly. Next, the BiLSTM was employed to obtain the global text features containing contextual semantics. After that, the features extracted by the two neural networks (NNs) were fused, and processed by Softmax classifier for text sentiment classification. To verify its performance, the CNN_BiLSTM was compared with single NNs like CNN and LSTM, as well as other deep learning (DL) NNs through experiments. The experimental results show that the proposed parallel hybrid model outperformed the contrastive methods in F1-score and accuracy. Therefore, our model can solve text sentiment classification tasks effectively, and boast better practical value than other NNs.
44
Zhao, Yonghong, Xiumei Fan, and Jisong Liu. "Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion." Sensors 25, no. 10 (2025): 3142. https://doi.org/10.3390/s25103142.
Full textAbstract:
In this paper, we propose a robust deep learning (DL)-based method for Direction-of-Arrival (DOA) estimation. Specifically, we develop a novel CRDCNN-LSTM network architecture, which integrates a Cross-Residual Depthwise Convolutional Neural Network (CRDCNN) with a Long Short-Term Memory (LSTM) module for effective capture of both spatial and temporal features. The CRDCNN employs multi-level cross-residual connections and depthwise separable convolutions to enhance feature diversity while mitigating issues such as gradient vanishing and overfitting. Furthermore, a customized FD loss function, combining Focal Loss and Dice Loss, is introduced to emphasize low-confidence samples and promote sparsity in the spatial spectrum, thereby improving the precision and overall effectiveness of DOA estimation. A post-processing strategy based on peak detection and quadratic interpolation is also employed to refine DOA estimations and reduce quantization errors. Simulation results demonstrate that the proposed approach achieves significantly higher estimation accuracy and resolution than conventional methods and current DL models under varying SNR and snapshot conditions. In addition, it offers distinct advantages in terms of generalization and computational efficiency.
45
Yang, Chuanli, Huawang Qin, and Siyuan Hu. "A 3D-ResNet Combined with BRNN: Application in the Auxiliary Diagnosis of ADHD." Advances in Computer and Engineering Technology Research 1, no. 3 (2024): 452. http://dx.doi.org/10.61935/acetr.3.1.2024.p452.
Full textAbstract:
Attention Deficit/Hyperactivity Disorder (ADHD) is a common mental disorder that exhibits a high incidence rate in children and adolescents, and it is also observed in adults. Currently, there is a lack of objective diagnostic methods for ADHD. Therefore, a three-dimensional residual network (3D-ResNet) deep learning method based on feature extraction from rs-fMRI images for assisting in the diagnosis of ADHD based on resting-state functional magnetic resonance imaging (rs-fMRI) and deep learning models was proposed in this paper. Taking into consideration the temporal characteristics of rs-fMRI, we constructed a 3D-ResNet model based on four-dimensional image. The model utilized TimeDistributed to encapsulate residual blocks which allowed the model to extract spatial features from rs-fMRI while preserving its temporal sequence information. We constructed four different hierarchical structures of 3D-ResNet which are subsequently combined with two different bidirectional recurrent neural networks (BRNNs) to extract sequence features. And BRNNs includes bidirectional long short-term memory (Bi-LSTM) and bidirectional gated recurrent unit (Bi-GRU). The proposed method utilized the ADHD-200 Consortium's public dataset for training and was validated by 5-fold cross-validation. The experimental results indicated that the proposed method in this study demonstrated superior performance on the dataset compared to traditional methods (Accuracy: 76.56%, Sensitivity: 80.16%, Specificity: 90.22%). Therefore, adopting this method can further enhance the accuracy of assisting in the diagnosis of ADHD.
46
Yang, Chao, Xingli Gan, Antao Peng, and Xiaoyu Yuan. "ResNet Based on Multi-Feature Attention Mechanism for Sound Classification in Noisy Environments." Sustainability 15, no. 14 (2023): 10762. http://dx.doi.org/10.3390/su151410762.
Full textAbstract:
Environmental noise affects people’s lives and poses challenges for urban sound classification. Traditional algorithms such as Mel frequency cepstral coefficients (MFCCs) struggle due to audio signal complexity. This study applied an attention mechanism to a deep residual network (ResNet) deep learning network to overcome the structural impact of urban noise on audio signals and improve classification accuracy. We propose a three-feature fusion ResNet + attention method (Net50_SE) to maximize information representation in environmental sound signals. This method uses residual structured convolutional neural networks (CNNs) for feature extraction in sound classification tasks. Additionally, an attention module is added to suppress environmental noise impact and focus on different feature map channels. The experimental results demonstrate the effectiveness of our method, achieving 93.2% accuracy compared with 82.87% with CNN and 84.77% with long short-term memory (LSTM). Our model provides higher accuracy and confidence in urban sound classification.
47
Lou, Yongjun, Meng Gao, Shuo Zhang, et al. "Chinese Named Entity Recognition for Dairy Cow Diseases by Fusion of Multi-Semantic Features Using Self-Attention-Based Deep Learning." Animals 15, no. 6 (2025): 822. https://doi.org/10.3390/ani15060822.
Full textAbstract:
Named entity recognition (NER) is the basic task of constructing a high-quality knowledge graph, which can provide reliable knowledge in the auxiliary diagnosis of dairy cow disease, thus alleviating problems of missed diagnosis and misdiagnosis due to the lack of professional veterinarians in China. Targeting the characteristics of the Chinese dairy cow diseases corpus, we propose an ensemble Chinese NER model incorporating character-level, pinyin-level, glyph-level, and lexical-level features of Chinese characters. These multi-level features were concatenated and fed into the bidirectional long short-term memory (Bi-LSTM) network based on the multi-head self-attention mechanism to learn long-distance dependencies while focusing on important features. Finally, the globally optimal label sequence was obtained by the conditional random field (CRF) model. Experimental results showed that our proposed model outperformed baselines and related works with an F1 score of 92.18%, which is suitable and effective for named entity recognition for the dairy cow disease corpus.
48
Li, Zhongyu, Xu Liu, Yu Lin, Xiaohua Xu, and Xiangfa Wang. "Energy Efficiency Prediction of Energy Storage Virtual Synchronous Machine Based on Long Short-Term Memory Network." Journal of Physics: Conference Series 2665, no. 1 (2023): 012014. http://dx.doi.org/10.1088/1742-6596/2665/1/012014.
Full textAbstract:
Abstract The integration of renewable energy sources in the power grid has led to an increased demand for energy storage systems to manage the intermittency and variability of these sources. Among various energy storage technologies, Energy Storage Virtual Synchronous Machines (ESVSMs) have emerged as a promising solution for enhancing grid stability and energy efficiency. However, optimizing the performance of ESVSMs requires accurate energy efficiency predictions. This paper proposes a energy efficiency prediction network (EEPNet) to achieve energy efficiency prediction of ESVSMs. Firstly, considering the peculiarity of storing virtual synchronous machine efficiency fluctuations, this paper improves the traditional Inception structure. This allows for the extraction of information at different scales and its fusion to obtain a better representation. Secondly, this paper introduces residual connections in the structure. This not only avoids the difficulties in model training caused by deep networks but also helps to integrate the original information with the extracted information. Thirdly, building upon the improved Inception structure, this work combines long short-term memory (LSTM) and attention mechanisms to construct a complete network architecture, further enhancing the performance of the entire model. Finally, the effectiveness and validity of the model are validated through comprehensive experiments.
49
Sun, Mingwei, Haoyuan Hu, Wei Pang, and You Zhou. "ACP-BC: A Model for Accurate Identification of Anticancer Peptides Based on Fusion Features of Bidirectional Long Short-Term Memory and Chemically Derived Information." International Journal of Molecular Sciences 24, no. 20 (2023): 15447. http://dx.doi.org/10.3390/ijms242015447.
Full textAbstract:
Anticancer peptides (ACPs) have been proven to possess potent anticancer activities. Although computational methods have emerged for rapid ACPs identification, their accuracy still needs improvement. In this study, we propose a model called ACP-BC, a three-channel end-to-end model that utilizes various combinations of data augmentation techniques. In the first channel, features are extracted from the raw sequence using a bidirectional long short-term memory network. In the second channel, the entire sequence is converted into a chemical molecular formula, which is further simplified using Simplified Molecular Input Line Entry System notation to obtain deep abstract features through a bidirectional encoder representation transformer (BERT). In the third channel, we manually selected four effective features according to dipeptide composition, binary profile feature, k-mer sparse matrix, and pseudo amino acid composition. Notably, the application of chemical BERT in predicting ACPs is novel and successfully integrated into our model. To validate the performance of our model, we selected two benchmark datasets, ACPs740 and ACPs240. ACP-BC achieved prediction accuracy with 87% and 90% on these two datasets, respectively, representing improvements of 1.3% and 7% compared to existing state-of-the-art methods on these datasets. Therefore, systematic comparative experiments have shown that the ACP-BC can effectively identify anticancer peptides.
50
Zou, Yingyong, Tao Liu, and Xingkui Zhang. "A Three-Channel Feature Fusion Approach Using Symmetric ResNet-BiLSTM Model for Bearing Fault Diagnosis." Symmetry 17, no. 3 (2025): 427. https://doi.org/10.3390/sym17030427.
Full textAbstract:
For mechanical equipment to operate normally, rolling bearings—which are crucial parts of rotating machinery—need to have their faults diagnosed. This work introduces a bearing defect diagnosis technique that incorporates three-channel feature fusion and is based on enhanced Residual Networks and Bidirectional long- and short-term memory networks (ResNet-BiLSTM) model. The technique can effectively establish spatial-temporal relationships and better capture complex features in data by combining the powerful spatial feature extraction capability of ResNet and the bidirectional temporal modeling capability of BiLSTM. Specifically, the one-dimensional vibration signals are first transformed into two-dimensional images using the Continuous Wavelet Transform (CWT) and Markov Transition Field (MTF). The upgraded ResNet-BiLSTM network is then used to extract and combine the original one-dimensional vibration signal along with features from the two types of two-dimensional images. Finally, experimental validation is performed on two bearing datasets. The results show that compared with other state-of-the-art models, the computing cost is greatly reduced, with params and flops at 15.4 MB and 715.24 MB, respectively, and the running time of a single batch becomes 5.19 s. The fault diagnosis accuracy reaches 99.53% and 99.28% for the two datasets, respectively, successfully realizing the classification task.