Adverse Drug Event Detection Using a Weakly Supervised Convolutional Neural Network and Recurrent Neural Network Model

Emotion recognition (ER) is crucial for understanding human behaviours, social interactions, and psychological well-being. Electroencephalography (EEG) has emerged as a promising tool for capturing the neural correlates of emotions. This work is a systematic review of articles in ER using EEG signals. A total of 120 articles from 1041 articles were selected based on PRISMA guidelines using defined inclusion and exclusion criteria, published between 2018 and 2024. This article aims to provide an in-depth understanding of the current landscape of ER from EEG signals utilizing deep learning (DL). This review offers valuable guidance for researchers and practitioners seeking more refined and reliable emotion classification systems. To explore the effectiveness of DL models in EEG-based ER, several potential DL models, such as convolutional neural network, long short-term memory (LSTM), gated recurrent unit (GRU), hybrid bidirectional LSTM (BiLSTM), bidirectional GRU, and advanced DL models such as convolutional recurrent neural network and EEG-Conformer models are applied to two popular datasets, SEED and GAMEEMO, respectively, to depict the full process of ER. Additionally, the performance of DL models is also compared with the performance of basic machine learning (ML) models such as SVM, k-nearest neighbors, logistic regression, and boosting algorithms such as AdaBoost, XGBoost and LightGBM. Through extensive experiments and performance evaluations, the performance of different models when applied to the datasets mentioned above is compared. The accuracy, precision, recall, and F1-scores are analysed to determine the most effective model for EEG-based ER. The findings of this study demonstrate that the performance of hybrid DL models is more efficacious than that of ML models. The best-performing model (BiLSTM) classified the emotions, with an accuracy of 90.54% when applied to the GAMEEMO dataset. This research contributes to the growing body of literature on ER and provides insights into the feasibility of using EEG signals to understand emotional states, and presents a structured roadmap for future exploration. The findings can aid in the development of more accurate and reliable ER systems, which can have wide-ranging applications in psychology, social sciences, and human-computer interactions.

Liquefaction susceptibility using machine learning based on SPT data

The presented paper proposes a new speech command recognition model for novel engineering applications with limited resources. We built the proposed model with the help of a Convolutional Recurrent Neural Network (CRNN). The use of CRNN instead of Convolutional Neural Network (CNN) helps us to reduce the model parameters and memory requirement as per resource constraints. Furthermore, we insert transmute and curtailment layer between the layers of CRNN. By doing this we further reduce model parameters and float number of operations to half of the CRNN requirement. The proposed model is tested on Google’s speech command dataset. The obtained result shows that the proposed CRNN model requires 1/3 parameters as compared to the CNN model. The number of parameters of the CRNN model is further reduced by 45% and the float numbers of operations between 2% to 12 % in different recognition tasks. The recognition accuracy of the proposed model is 96% on Google’s speech command dataset, and on laboratory recording, its recognition accuracy is 89%.

This paper proposes a multi-layered anomaly detection scheme to train feature extraction and to test anomaly prediction by using Convolutional Neural Networks (CNNs) layer, Bidirectional and Unidirectional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs), which is one of a novel deep architecture named stacked convolutional bidirectional LSTM network (SCB-LSTM). In the proposed model, the stacked CNNs perform feature extraction of vibration sensor signal patterns, and the result is used to feature learning with the stacked bidirectional LSTMs (SB-LSTMs). After this procedure, the stacked unidirectional LSTMs (SU-LSTMs) enhance the feature learning, and a regression layer finally predicts anomaly detections. The experimental results of bearing data not only show the accuracy of the proposed model in anomaly detection for rotating machinery diagnostics, but also suggest the better performance than other state-of-the-art algorithms such as a plain uni-LSTM or Bi-LSTM.

Deep learning models for short-term travel speed prediction on urban expressways, such as the convolutional neural network (CNN), still present several limitations in multiscale spatiotemporal feature extraction. Hence, in this paper, three hybrid CNN models are proposed to improve the basic CNN model with regard to three target aspects for short-term (i.e., 5 min) travel speed prediction on urban expressways. More specifically, long short-term memory (LSTM), AutoEncoder (AE), and Inception module are incorporated into the basic CNN model to capture multiscale spatiotemporal features of travel speed data effectively and improve the accuracy and robustness of the basic CNN model. Based on loop detector data collected on the Yan’an expressway in Shanghai, the proposed hybrid CNN models are trained and tuned. To validate the improvements on the target aspects, a comprehensive comparison is conducted using a classical statistical model (i.e., autoregressive integrated moving average), a typical shallow neural network model (i.e., artificial neural network), and two basic deep learning models (i.e., recurrent neural network and CNN). Results show that the prediction accuracies of all the proposed hybrid CNN models exceed 96% and the mean absolute errors are less than 2.5 km/h, which are superior to other models. In terms of target improving aspects, two new metrics were introduced, and the proposed models, especially the AE–CNN model, showed better robustness under various input data structures and traffic states. The LSTM–CNN model outperformed the other models in learning time-series features, and the Inception–CNN model is superior in reproducing the dynamics of traffic congestion patterns on urban expressways.

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.

In this paper, a software comparative analysis of two neural network models is presented, namely, Convolutional Neural Network (CNN), and Long Short Term Memory (LSTM) neural network. The evaluation is performed using the famous deep learning database the “MNIST” to check the accuracy, model size, speed and complexity of the two models for future digital realization on reconfigurable hardware. In addition to that, we optimize the size of the two models by quantizing the weights width to 8-bits instead of 32-bits. The results show an extensive reduction in the size of each model (by 10X) with a slight drop in the accuracy. The results also show that the CNN is more accurate and much faster than LSTMs making it the best model to be implemented on reconfigurable hardware.

Multimodal emotion recognition has become a hot topic in human-computer interaction and intelligent healthcare fields. However, combining information from different human different modalities for emotion computation is still challenging. In this paper, we propose a three-dimensional convolutional recurrent neural network model (referred to as 3FACRNN network) based on multimodal fusion and attention mechanism. The 3FACRNN network model consists of a visual network and an EEG network. The visual network is composed of a cascaded convolutional neural network-time convolutional network (CNN-TCN). In the EEG network, the 3D feature building module was added to integrate band information, spatial information and temporal information of the EEG signal, and the band attention and self-attention modules were added to the convolutional recurrent neural network (CRNN). The former explores the effect of different frequency bands on network recognition performance, while the latter is to obtain the intrinsic similarity of different EEG samples. To investigate the effect of different frequency bands on the experiment, we obtained the average attention mask for all subjects in different frequency bands. The distribution of the attention masks across the different frequency bands suggests that signals more relevant to human emotions may be active in the high frequency bands γ (31-50 Hz). Finally, we try to use the multi-task loss function Lc to force the approximation of the intermediate feature vectors of the visual and EEG modalities, with the aim of using the knowledge of the visual modalities to improve the performance of the EEG network model. The mean recognition accuracy and standard deviation of the proposed method on the two multimodal sentiment datasets DEAP and MAHNOB-HCI (arousal, valence) were 96.75 ± 1.75, 96.86 ± 1.33; 97.55 ± 1.51, 98.37 ± 1.07, better than those of the state-of-the-art multimodal recognition approaches. The experimental results show that starting from the multimodal information, the facial video frames and electroencephalogram (EEG) signals of the subjects are used as inputs to the emotion recognition network, which can enhance the stability of the emotion network and improve the recognition accuracy of the emotion network. In addition, in future work, we will try to utilize sparse matrix methods and deep convolutional networks to improve the performance of multimodal emotion networks.

To develop and evaluate deep learning models for cardiac arrest rhythm classification during cardiopulmonary resuscitation (CPR), we analyzed 508 electrocardiogram (ECG) segments (each 4 s in duration, recorded at 250 Hz) from 131 cardiac arrest patients. Compression-affected segments were recorded during chest compressions, while non-compression segments were extracted during compression pauses or immediately after return of spontaneous circulation (ROSC) declaration. One-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) models were employed for four binary classification tasks: (1) shockable rhythms (VF and pVT) versus non-shockable rhythms (asystole and PEA) in all ECG segments; (2) the same classification in compression-affected ECG segments; (3) pulse-generating rhythms (ROSC rhythm) versus non-pulse-generating rhythms (asystole, PEA, VF and pVT) in all ECG segments; and (4) the same classification in compression-affected ECG segments. The 1D-CNN model consistently outperformed the RNN model across all classification tasks. For shockable versus non-shockable rhythm classification, the 1D-CNN achieved accuracies of 91.3% and 89.8% for all ECG segments and compression-affected ECG segments, respectively, compared to 50.6% and 54.5% for the RNN. In detecting pulse-generating rhythms, the 1D-CNN demonstrated accuracies of 90.9% and 85.7% for all ECG segments and compression-affected ECG segments, respectively, while the RNN achieved 92.2% and 84.4%. The 1D-CNN model demonstrated superior performance in cardiac arrest rhythm classification, maintaining high accuracy even with compression-affected ECG data.

In this modern world, we are accustomed to a constant stream of data. Major social media sites like Twitter, Facebook, or Quora face a huge dilemma as a lot of these sites fall victim to spam accounts. These accounts are made to trap unsuspecting genuine users by making them click on malicious links or keep posting redundant posts by using bots. This can greatly impact the experiences that users have on these sites. A lot of time and research has gone into effective ways to detect these forms of spam. Performing sentiment analysis on these posts can help us in solving this problem effectively. The main purpose of this proposed work is to develop a system that can determine whether a tweet is “spam” or “ham” and evaluate the emotion of the tweet. The extracted features after preprocessing the tweets are classified using various classifiers, namely, decision tree, logistic regression, multinomial naïve Bayes, support vector machine, random forest, and Bernoulli naïve Bayes for spam detection. The stochastic gradient descent, support vector machine, logistic regression, random forest, naïve Bayes, and deep learning methods, namely, simple recurrent neural network (RNN) model, long short-term memory (LSTM) model, bidirectional long short-term memory (BiLSTM) model, and 1D convolutional neural network (CNN) model are used for sentiment analysis. The performance of each classifier is analyzed. The classification results showed that the features extracted from the tweets can be satisfactorily used to identify if a certain tweet is spam or not and create a learning model that will associate tweets with a particular sentiment.

Problems like image recognition, object detection, image segmentation need efficacious solution for computer vision. Traditionally, these problems are being solved by Deep Learning. Convolutional Neural Network(CNN) and Recurrent Neural Network models are used for computer vision tasks. However, CNNs have some drawbacks. They cannot recognize objects if same object is viewed from different viewpoints and deformed objects. Besides, CNNs require an immense amount of training data. Capsule networks are viewed as a new solution for computer vision problems. They are capable of solving the above-mentioned problems better than CNNs. Capsule networks have shown better accuracy in many computer vision applications. In this paper, we review the methodologies and architectures of existing implementations of capsule networks.KeywordsDeep learningCNNDynamic routingCapsule networkExpectation maximization

The terahertz spectrum has the characteristics of a fingerprint spectrum, which can realize the identification of antibiotics. Antibiotic identification based on traditional learning methods has achieved certain results. Models based on deep learning can automatically extract kernel features, and convolutional neural network (CNN) models rely on a convolution layer to extract features. In view of the high characteristic dimension of antibiotic spectrum sequences, we propose a new CNN model and attention bidirectional long short-term memory (BiLSTM). We use CNN to reduce the dimension of an antibiotic sequence. However, the convolution kernel limits a CNN's long-term dependence in processing time-series signal data. BiLSTM can effectively solve this problem and capture the dependence before and after the timing signal. The attention mechanism is added to BiLSTM to further extract the subtle features of the antibiotic spectrum, and can better capture the most important local information. A full connection network achieves the purpose of antibiotic identification. In experiments, the F1 score of the proposed model is 0.98, confirming its strong recognition ability and good interpretability.

Prediction of PM2.5 concentration in urban agglomeration of China by hybrid network model

People counting and pedestrian flow statistics are challenging tasks because of the perspective distortions, appearance changes and occlusion. In this paper, we address the two tasks: people counting in images of highly dense crowds and pedestrian flow statistics in a place over a period of time. Our first contribution is to propose a new convolution neural network (CNN) model which is composed of a deep and shallow fully convolution network to fulfill the task of people counting. We extract different layer features from the deep fully convolution network and the last layer features from the shallow fully convolution network, and concatenate them together. After that we add two deconvolution layers to make the output image have the same resolution with the input image. Our second contribution is to combine pedestrian flow statistics task with people counting task. According to the density maps that CNN model generates, we can calculate the number of people crossing a place based on the recurrent neural network (RNN). Besides, we also have collected two datasets and labelled them. Extensive experiments have been implemented, our people counting method outperforms other existing methods, and our pedestrian flow statistics method combined with CNN model also outperforms the model which only uses long-short term memory (LSTM).

In this paper, alternative direction finding methods have been proposed using deep learning techniques. Firstly, Regeression and Classification models have created by using Convolutional Neural Networks (CNNs). In the second Convolutional Neural Networks and Recurrent Neural Networks (RNNs) have been utilized in the proposed methods. Despite having vast amount of direction finding studies, utilization of neural networks is scarce in literature and past works mostly only includes usage of CNNs. In this study, direction finding is performed by learning signals reaching multiple antenna arrays by networks. Created neural networks have been fed with different data formats and their performances against noisy and no-noise data have been shown. In addition, comparative analysis of the developed models were made in the similar Signal-to-Noise Ratio (SNR) range with the subspace based MUSIC algorithm, which is frequently used in direction finding.