Narrow Results

With the advancement of smart grid technology, the issue of power system network security has become increasingly critical. To fully utilize the power grid’s vast data resources and enhance the efficiency of anomaly detection, this paper proposes an improved decision tree (DT)-based automatic identification approach for anomalies in electric power big data. The method employs six-dimensional features extracted from the dimensions of volatility, trend, and variability to characterize the time series of power data. These features are integrated into a hybrid DT-SVM-LSTM framework, combining the strengths of DTs, support vector machines, and long short-term memory networks. Experimental results demonstrate that the proposed method achieves an accuracy of 96.8%, a precision of 95.3%, a recall of 94.8%, and an F1-score of 95.0%, outperforming several state-of-the-art methods cited in the literature. Moreover, the approach exhibits strong robustness to noise, maintaining high detection accuracy even under low signal-to-noise ratio conditions. These findings highlight the effectiveness of the method in efficiently detecting anomalies and addressing noise interference.

Emotion recognition plays an essential role in human–human interaction since it is a key to understanding the emotional states and reactions of human beings when they are subject to events and engagements in everyday life. Moving towards human–computer interaction, the study of emotions becomes fundamental because it is at the basis of the design of advanced systems to support a broad spectrum of application areas, including forensic, rehabilitative, educational, and many others. An effective method for discriminating emotions is based on ElectroEncephaloGraphy (EEG) data analysis, which is used as input for classification systems. Collecting brain signals on several channels and for a wide range of emotions produces cumbersome datasets that are hard to manage, transmit, and use in varied applications. In this context, the paper introduces the Empátheia system, which explores a different EEG representation by encoding EEG signals into images prior to their classification. In particular, the proposed system extracts spatio-temporal image encodings, or atlases, from EEG data through the Processing and transfeR of Interaction States and Mappings through Image-based eNcoding (PRISMIN) framework, thus obtaining a compact representation of the input signals. The atlases are then classified through the Empátheia architecture, which comprises branches based on convolutional, recurrent, and transformer models designed and tuned to capture the spatial and temporal aspects of emotions. Extensive experiments were conducted on the Shanghai Jiao Tong University (SJTU) Emotion EEG Dataset (SEED) public dataset, where the proposed system significantly reduced its size while retaining high performance. The results obtained highlight the effectiveness of the proposed approach and suggest new avenues for data representation in emotion recognition from EEG signals.

In recent years, deep learning-based networks have been able to achieve state-of-the-art performance in medical image segmentation. U-Net, one of the currently available networks, has proven to be effective when applied to the segmentation of medical images. A Convolutional Neural Network’s (CNN) performance is heavily dependent on the network’s architecture and associated parameters. There are many layers and parameters that need to be set up in order to manually create a CNN, making it a complex procedure. Designing a network is made more difficult by using a variety of connections to increase the network’s complexity. Evolutionary computation can be used to set the parameters of CNN and/or organize the CNN layers as an optimization strategy. This paper proposes an automatic evolutionary method for detecting an optimal network topology and its parameters for the segmentation of clinical image using Grey Wolf Optimization algorithm. Also, Bi-Directional LSTM integrated in the skip connection to extract dense feature characteristics of image by combining feature maps extracted from encoded and previous decoded path in nonlinear way (MIS-GW-U-Net-BiDCLSTM) is proposed. The experimental results demonstrate that the proposed method attains 98.49% accuracy with minimal parameters, which is much better than that of the other methods.

This paper has the aim of solving problems in research studies on the analysis tasks of text emotion; the problems are the low utilization of text, the difficulty of effective information extraction, the failure of recognizing word polysemy with effectiveness. Thus, based on LSTM and Bert, the method of sentiment analysis on text is adopted. To be precise, word embedding of dataset in view of the skip-gram model is used for training course. In each sample, the word embeddings combine matric with the two-dimensional feature to be neural network input. Next, construction of analysis model for text sentiment combines Bert pre-training language model and long short-term memory (LSTM) network, using the word vector pre-trained by Bert instead of that trained in the traditional way to dynamically generate the semantic vector according to the word context. Finally, the semantic representation of words from text is improved by effectively identifying the polysemy of words, and the semantic vector is input into the LSTM to capture the semantic dependencies, thereby enhancing the ability to extract valid information. The Accuracy, Precision, Recall and F-Measure for the method of Bert–LSTM based on analysis of text sentiment are 0.89, 0.9, 0.84 and 0.87, indicating high value than the compared ones. Thus, the proposed method significantly outperforms the comparison methods in text sentiment analysis.

New advancements in deep learning issues, motivated by real-world use cases, frequently contribute to this growth. Still, it’s not easy to recognize the speaker’s emotions from what they want to say. The proposed technique combines a deep learning-based brain-inspired prediction-making artificial neural network (ANN) through social ski-driver (SSD) optimization techniques. When assessing speaker emotion recognition (SER), the recognition results are compared with the existing convolutional neural network (CNN) and long short-term memory (LSTM)-based emotion recognition methods. The proposed method for classification based on ANN decreases the computational costs. The SER algorithm allows for a more in-depth classification of different emotions because of its relationship to ANN and LSTM. The SER model is based on ANN and the recognition impact of the feature reduction. The SER in this proposed research work is based on the ANN emotion classification system. Speaker recognition accuracy values of 96.46%, recall values of 95.39%, precision values of 95.21%, and F-Score values of 96.10% are obtained in this proposed result, which is higher than the existing result. The average accuracy results by using the proposed ANN classification technique are 4.38% and 2.89%, better than the existing CNN and LSTM techniques, respectively. The average precision results by using the proposed ANN classification technique are 4.67% and 2.49%, better than the existing CNN and LSTM techniques, respectively. The average recall results by using the proposed ANN classification technique are 2.90% and 1.42%, better than the existing CNN and LSTM techniques, respectively. The average precision results using the proposed ANN classification technique are 3.80% and 3.10%, better than the existing CNN and LSTM techniques, respectively.

Long short-term memory (LSTM) with significantly increased complexity and a large number of parameters have a bottleneck in computing power resulting from limited memory capacity. Hardware acceleration of LSTM using memristor circuit is an effective solution. This paper presents a complete design of memristive LSTM network system. Both the LSTM cell and the fully connected layer circuit are implemented through memristor crossbars, and the 1T1R design avoids the influence of the sneak current which helps to improve the accuracy of network calculation. To reduce the power consumption, the word embedding dimensionality was reduced using the GloVe model, and the number of features in the hidden layer was reduced. The effectiveness of the proposed scheme is verified by performing the text classification task on the IMDB dataset and the hardware training accuracy reached as high as 88.58%.

With the accelerated construction of 5G and IoT, more and more 5G base stations are erected. However, with the increase of 5G base stations, the power management of 5G base stations becomes progressively a bottleneck. In this paper, we solve the problem of 5G base station power management by designing a 5G base station lithium battery cloud monitoring system. In this paper, first, the lithium battery acquisition hardware is designed. Second, a new communication protocol is established based on Modbus. Third, the windows desktop upper computer software and the cloud-based monitoring system are designed. Finally, this paper designs the improved ResLSTM algorithm which is fused with ResNet algorithm based on Stacked LSTM. The algorithm designed in this paper is tested in comparison with SVM and LSTM. The performance of the algorithm designed in this paper is better than SVM and LSTM. Furthermore, the communication test, as well as the training and testing of the ResLSTM algorithm are outstanding. The 5G base station lithium-ion battery cloud monitoring system designed in this paper can meet the requirements. It has great significance for engineering promotion. More importantly, the ResLSTM algorithm designed in this paper can better guide the method of lithium-ion battery SOC estimation.

In this study, AdaBoost-Bi-LSTM ensemble models are developed to predict the number of COVID-19 confirmed cases by effectively learning volatile and unstable data using a nonparametric method. The performance of the developed models in terms of prediction accuracy is compared with those of existing deep learning models such as GRU, LSTM, and Bi-LSTM. The COVID-19 outbreak in 2019 has resulted in a global pandemic with a significant number of deaths worldwide. There have long been ongoing efforts to prevent the spread of infectious diseases, and a number of prediction models have been developed for the number of confirmed cases. However, there are many variables that continuously mutate the virus and therefore affect the number of confirmed cases, which makes it difficult to accurately predict the number of COVID-19 confirmed cases. The goal of this study is to develop a model with a lower error rate and higher predictive accuracy than existing models to more effectively monitor and handle endemic diseases. To this end, this study predicts COVID-19 confirmed cases from April to October 2022 based on the analysis of COVID-19 confirmed cases data from 16 December 2020 to 27 September 2022 using the developed models. As a result, the AdaBoost-Bi-LSTM model shows the best performance, even though the data from the period of high variability in the number of confirmed cases was used for model training. The AdaBoost-Bi-LSTM model achieved improved predictive power and shows an increased performance of 17.41% over the simple GRU/LSTM model and of 15.62% over the Bi-LSTM model.

This study was conducted to evaluate the effect of computer vision-based respiratory rehabilitation. Chronic obstructive pulmonary disease (COPD) is one of the primary respiratory diseases worldwide. Recently, image-capturing devices are increasingly used for physical therapy during rehabilitation treatment. Among these technologies, Action recognition plays a critical role in physical exercise and rehabilitation evaluation. This study aimed to propose an action series of a respiratory training program consisting of six actions. A video camera was placed in front of the participants to record their movements. Then, a hybrid algorithm combined with a convolution neural network and long short-term memory models was employed for action recognition from a video recording. The results indicated that the model achieved a reliable classification level of 82.35% on six actions. This demonstrated the validity of the proposed approach for multi-category action recognition. It was effective for action evaluation without medical guidance under home-based rehabilitation. Furthermore, the model for weight estimation was light-weight, with no need to consider the processing time.

Based on electroencephalography (EEG) and video data, we propose a multimodal affective analysis approach in this study to examine the affective states of university students. This method is based on the findings of this investigation. The EEG signals and video data were obtained from 50 college students experiencing various emotional states, and then they were processed in great detail. The EEG signals are pre-processed to extract their multi-view characteristics. Additionally, the video data were processed by frame extraction, face detection, and convolutional neural network (CNN) operations to extract features. We take a feature splicing strategy to merge EEG and video data to produce a time series input to realize the fusion of multimodal features. This allows us to realize the fusion of multimodal features. In addition, we developed and trained a model for the classification of emotional states based on a long short-term memory network (LSTM). With the help of cross-validation, the experiments were carried out by dividing the dataset into a training set and a test set. The model’s performance was evaluated with the help of four metrics: accuracy, precision, recall, and F1-score. When compared to the single-modal method of sentiment analysis, the results demonstrate that the multimodal approach, which combines EEG and video, demonstrates considerable advantages in terms of sentiment detection. Specifically, the accuracy obtained from the multimodal approach is significantly higher. As part of its investigation, the study also investigates the respective contributions of EEG and video aspects to emotion detection. It discovers that these features complement each other in a variety of emotional states and have the potential to improve the overall recognition results. The multimodal sentiment analysis method that is based on LSTM offers a high level of accuracy and robustness when it comes to recognizing the affective states of college students. This is especially essential for enhancing the quality of education and providing support for mental health.

To meet carbon peak and neutrality targets, accurate carbon trading price forecasting is very important for enterprises making emission reduction decisions. By fusing convolutional neural network (CNN) and long short-term memory network (LSTM), the CNN–LSTM model is constructed. After variational mode decomposition (VMD), several intrinsic mode functions (IMFs) components are obtained and input into the CNN–LSTM model, thus constructing the combined sooty tern optimization algorithm (STOA)–VMD–CNN–LSTM forecasting model. To test this model, the carbon trading prices of the carbon emission trading markets of Hubei, Guangdong and Shenzhen were forecast. The prediction performance of the STOA–VMD–CNN–LSTM model is compared with ARIMA, BP, CNN and LSTM benchmark models and models combining different decomposition technologies. The international carbon trading price (EUR and CER) is used for prediction. Compared with other methods, the developed model makes fewer errors and achieves superior performance. Several important implications are provided for investors and risk managers involved in carbon financial products.

Traffic prediction is challenging due to the stochastic nonlinear dependencies in spatiotemporal traffic characteristics. We introduce a Graph Convolutional Gated Recurrent Unit Network (GC-GRU-N) to capture the critical spatiotemporal dynamics. Using 15-min aggregated Seattle loop detector data, we recontextualize the prediction challenge across space and time. We benchmark our model against Historical Average, LSTM, and Transformers. While Transformers outperformed other models, our GC-GRU-N came in a close second with notably faster inference time — six times quicker than Transformers. We offer a comprehensive comparison of all models based on training and inference times, MAPE, MAE, and RMSE. Furthermore, we delve into the spatial and temporal characteristics of each model’s performance.

Assessing the impacts of climate change on hydrological systems requires accurate downscaled climate projections. In the past two decades, various statistical and machine-learning techniques have been developed and tested for climate downscaling; however, there is no consensus regarding which technique is the most reliable for climate downscaling and hydrological impact assessment. In this study, an advanced machine-learning technique, Long Short-Term Memory (LSTM) neural network, is used to build multi-model ensembles for downscaling climate projections from a wide ranges of global and regional climate models, and its performance is compared with a number of traditional statistical and machine-learning methods, such as ensemble average, linear regression, Multi-layer Perceptron, Time-lagged Feed-forward Neural Network, and Nonlinear Auto-regression Network with exogenous inputs. The downscaling input consists of temperature and precipitation projections provided by regional climate models, such as CanRCM4, CRCM5, RCA4, and HIRHAM5, and the output is observation data collected from meteorological stations. Performance of the developed LSTM ensemble is evaluated for two case studies in Canada and China. The downscaled climate projections are further used to assess the hydrological impacts in the southwestern mountainous area in China, with the assist of a fully distributed hydrological model, MIKE SHE. The results can support future applications of LSTM neural networks and other similar data-driven techniques for climate downscaling and hydrological impact assessment.

Protein domain boundary prediction is usually an early step to understand protein function and structure. Most of the current computational domain boundary prediction methods suffer from low accuracy and limitation in handling multi-domain types, or even cannot be applied on certain targets such as proteins with discontinuous domain. We developed an ab-initio protein domain predictor using a stacked bidirectional LSTM model in deep learning. Our model is trained by a large amount of protein sequences without using feature engineering such as sequence profiles. Hence, the predictions using our method is much faster than others, and the trained model can be applied to any type of target proteins without constraint. We evaluated DeepDom by a 10-fold cross validation and also by applying it on targets in different categories from CASP 8 and CASP 9. The comparison with other methods has shown that DeepDom outperforms most of the current ab-initio methods and even achieves better results than the top-level template-based method in certain cases. The code of DeepDom and the test data we used in CASP 8, 9 can be accessed through GitHub at https://github.com/yuexujiang/DeepDom.