Unravelling emotions: exploring deep learning approaches for EEG-based emotionrecognition with current challenges and future recommendations.

Sentiment Analysis of Self Driving Car Dataset: A comparative study of Deep Learning approaches

COVID-19 is highly infectious and causes acute respiratory disease. Machine learning (ML) and deep learning (DL) models are vital in detecting disease from computerized chest tomography (CT) scans. The DL models outperformed the ML models. For COVID-19 detection from CT scan images, DL models are used as end-to-end models. Thus, the performance of the model is evaluated for the quality of the extracted feature and classification accuracy. There are four contributions included in this work. First, this research is motivated by studying the quality of the extracted feature from the DL by feeding these extracted to an ML model. In other words, we proposed comparing the end-to-end DL model performance against the approach of using DL for feature extraction and ML for the classification of COVID-19 CT scan images. Second, we proposed studying the effect of fusing extracted features from image descriptors, e.g., Scale-Invariant Feature Transform (SIFT), with extracted features from DL models. Third, we proposed a new Convolutional Neural Network (CNN) to be trained from scratch and then compared to the deep transfer learning on the same classification problem. Finally, we studied the performance gap between classic ML models against ensemble learning models. The proposed framework is evaluated using a CT dataset, where the obtained results are evaluated using five different metrics The obtained results revealed that using the proposed CNN model is better than using the well-known DL model for the purpose of feature extraction. Moreover, using a DL model for feature extraction and an ML model for the classification task achieved better results in comparison to using an end-to-end DL model for detecting COVID-19 CT scan images. Of note, the accuracy rate of the former method improved by using ensemble learning models instead of the classic ML models. The proposed method achieved the best accuracy rate of 99.39%.

Individual investors often struggle to predict stock prices due to the limitations imposed by the computational capacities of personal laptop Graphics Processing Units (GPUs) when running intensive deep learning models. This study proposes solving these GPU constraints by integrating deep learning models with technical analysis methods. This integration significantly reduces analysis time and equips individual investors with the ability to identify stocks that may yield potential gains or losses in an efficient manner. Thus, a comprehensive buy and sell algorithm, compatible with average laptop GPU performance, is introduced in this study. This algorithm offers a lightweight analysis method that emphasizes factors identified by technical analysis methods, thereby providing a more accessible and efficient approach for individual investors. To evaluate the efficacy of this approach, we assessed the performance of eight deep learning models: long short-term memory (LSTM), a convolutional neural network (CNN), bidirectional LSTM (BiLSTM), CNN Attention, a bidirectional gated recurrent unit (BiGRU) CNN BiLSTM Attention, BiLSTM Attention CNN, CNN BiLSTM Attention, and CNN Attention BiLSTM. These models were used to predict stock prices for Samsung Electronics and Celltrion Healthcare. The CNN Attention BiLSTM model displayed superior performance among these models, with the lowest validation mean absolute error value. In addition, an experiment was conducted using WandB Sweep to determine the optimal hyperparameters for four individual hybrid models. These optimal parameters were then implemented in each model to validate their back-testing rate of return. The CNN Attention BiLSTM hybrid model emerged as the highest-performing model, achieving an approximate rate of return of 5 percent. Overall, this study offers valuable insights into the performance of various deep learning and hybrid models in predicting stock prices. These findings can assist individual investors in selecting appropriate models that align with their investment strategies, thereby increasing their likelihood of success in the stock market.

To develop a deep learning (DL) model for predicting axillary lymph node (ALN) metastasis using dynamic ultrasound (US) videos in breast cancer patients. A total of 271 US videos from 271 early breast cancer patients collected from Xiang'an Hospital of Xiamen University andShantou Central Hospitabetween September 2019 and June 2021 were used as the training, validation, and internal testing set (testing set A). Additionally, an independent dataset of 49 US videos from 49 patients with breast cancer, collected from Shanghai 10th Hospital of Tongji University from July 2021 to May 2022, was used as an external testing set (testing set B). All ALN metastases were confirmed using pathological examination. Three different convolutional neural networks (CNNs) with R2+1D, TIN, and ResNet-3D architectures were used to build the models. The performance of the US video DL models was compared with that of US static image DL models and axillary US examination performed by ultra-sonographers. The performances of the DL models and ultra-sonographers were evaluated based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Additionally, gradient class activation mapping (Grad-CAM) technology was also used to enhance the interpretability of the models. Among the three US video DL models, TIN showed the best performance, achieving an AUC of 0.914 (95% CI: 0.843-0.985) in predicting ALN metastasis in testing set A. The model achieved an accuracy of 85.25% (52/61), with a sensitivity of 76.19% (16/21) and a specificity of 90.00% (36/40). The AUC of the US video DL model was superior to that of the US static image DL model (0.856, 95% CI: 0.753-0.959, P<0.05). The Grad-CAM technology confirmed the heatmap of the model, which highlighted important subregions of the keyframe for ultra-sonographers' review. A feasible and improved DL model to predict ALN metastasis from breast cancer US video images was developed. The DL model in this study with reliable interpretability would provide an early diagnostic strategy for the appropriate management of axillary in the early breast cancer patients.

Emotion recognition from textual data has become increasingly vital in domains such as sentiment-aware systems, conversational agents, and mental health analysis. Despite significant progress, accurately detecting emotions from text remains a challenging task due to the lack of prosodic and visual cues, contextual ambiguity, and imbalanced datasets. This study presents a comprehensive evaluation of traditional Machine Learning (ML) and advanced Deep Learning (DL) models on four diverse emotion-labeled datasets: DailyDialog, ISEAR, Emotion-Stimulus, and CrowdFlower. Various feature extraction techniques—TF-IDF and Count Vectorizer for ML models, and semantic embeddings (Word2Vec and GloVe) for DL models—were employed to assess their impact on model performance. The models compared include Logistic Regression, Random Forest, Stochastic Gradient Descent, and Multinomial Naïve Bayes for ML, and LSTM, BiLSTM, and CNN for DL. Evaluation metrics such as accuracy, precision, recall, F1-score, and MCC were used for performance assessment. Results reveal that DL models, particularly CNN and BiLSTM, outperform ML models in terms of accuracy and contextual understanding, especially on structured datasets. Conversely, Logistic Regression with TF-IDF demonstrates robustness on noisy and imbalanced data. Word2Vec embeddings consistently enhance DL model performance, highlighting the importance of contextual semantics. This work underscores the significance of dataset characteristics, model architecture, and feature representation in achieving effective emotion classification. Future directions include integrating transformer-based models, addressing class imbalance, and exploring multimodal emotion recognition to improve generalization and real-world applicability.

Sentiment analysis using stemmed Twitter data from various languages is an emerging research topic. In this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis. The performance of these DL models has been compared with the existing traditional machine learning (TML) models. The performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques. Based on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time ( TTM ) and runtime ( RTM ) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.

Abstract. This study aims to enhance lung cancer patient screening by developing and evaluating bidirectional Long Short-Term Memory (LSTM) and bidirectional Gated Recurrent Unit (GRU) models using the Lung Cancer dataset from Kaggle. The dataset includes 16 features related to patient symptoms and lung cancer status, providing a broad spectrum of symptoms to improve model accuracy. The research advances Artificial Intelligence (AI)-driven healthcare by integrating these sophisticated machine learning techniques into diagnostic processes. The methodology involves four main steps: preprocessing the dataset for model compatibility, defining the model architecture with bidirectional LSTM and GRU layers and evaluating its performance. The results show an overall accuracy of 52.17%, with accuracy, recall, and F1 scores for both cancerous and non-cancerous categories around 50%. Despite the hybrid model's average performance, it establishes a basis for future enhancements. Optimizing model parameters and exploring additional other techniques to improve prediction accuracy and clinical applicability will be done in the future.

Introduction: Forecasting electrical energy demand is crucial for predicting future energy consumption patterns, which aids in effective energy management and distribution. Various forecasting methods have been developed, yet this study explores univariate time series analysis using Bidirectional Long Short-Term Memory (BiLSTM) and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model. These deep learning techniques are designed to capture both temporal dependencies and spatial patterns, improving predictive performance in energy forecasting. Objectives: This study aims to evaluate the forecasting performance of deep learning models in univariate time series energy demand prediction. Specifically, it seeks to: Implement and compare the forecasting performance of Bidirectional LSTM and hybrid CNN-LSTM models using a publicly available dataset from Transmission Service Operators (TSO). Preprocess the dataset using appropriate data preparation techniques, such as normalization, handling missing values, and feature selection, before training the models. Assess predictive accuracy by evaluating both models using key performance metrics, including Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R-Squared (R²). Methods: The dataset used in this study was obtained from a public portal for Transmission Service Operators (TSO). Before training, the data underwent preprocessing techniques such as normalization, handling missing values, and feature selection to improve model performance. Two deep learning models—BiLSTM and CNN-LSTM—were implemented and trained on the dataset. The performance of each model was evaluated using four key metrics: Mean Absolute Error (MAE) – measures the average magnitude of errors, Mean Absolute Percentage Error (MAPE) – represents error as a percentage of actual values, Root Mean Squared Error (RMSE) – penalizes larger errors more heavily than MAE, R-Squared (R²) – indicates how well predictions align with actual data. Results: Experimental findings reveal that the hybrid CNN-LSTM model outperformed the BiLSTM model across all evaluation metrics. The CNN-LSTM model achieved a lower MAE of 499.08 compared to 780.56 in BiLSTM, a lower MAPE of 1.80% versus 2.52%, and a reduced RMSE of 671.37 compared to 1,042.20. Additionally, the CNN-LSTM model obtained a slightly higher R² score of 0.97 compared to 0.94 in BiLSTM, indicating a better fit for the data. Conclusion: The results demonstrate that integrating CNN with LSTM significantly improves predictive accuracy in univariate time series energy demand forecasting. The CNN component enhances feature extraction, allowing the LSTM layers to capture complex temporal dependencies more effectively. Consequently, the hybrid CNN-LSTM model emerges as a more robust approach compared to BiLSTM alone, making it a valuable tool for accurate energy demand forecasting. Further research can explore additional deep learning architectures or hybrid models to optimize forecasting performance further.

Recently, deep learning (DL) models, especially those based on long short-term memory (LSTM), have demonstrated their superior ability in resolving sequential data problems. This study investigated the performance of six models that belong to the supervised learning category to evaluate the performance of DL models in terms of streamflow forecasting. They include a feed-forward neural network (FFNN), a convolutional neural network (CNN), and four LSTM-based models. Two standard models with just one hidden layer—LSTM and gated recurrent unit (GRU)—are used against two more complex models—the stacked LSTM (StackedLSTM) model and the Bidirectional LSTM (BiLSTM) model. The Red River basin—the largest river basin in the north of Vietnam—was adopted as a case study because of its geographic relevance since Hanoi city—the capital of Vietnam—is located downstream of the Red River. Besides, the input data of these models are the observed data at seven hydrological stations on the three main river branches of the Red River system. This study indicates that the four LSTM-based models exhibited considerably better performance and maintained stability than the FFNN and CNN models. However, the complexity of the StackedLSTM and BiLSTM models is not accompanied by performance improvement because the results of the comparison illustrate that their respective performance is not higher than the two standard models—LSTM and GRU. The findings of this study present that LSTM-based models can reach impressive forecasts even in the presence of upstream dams and reservoirs. For the streamflow-forecasting problem, the LSTM and GRU models with a simple architecture (one hidden layer) are sufficient to produce highly reliable forecasts while minimizing the computation time.

Human-induced global warming, primarily attributed to the rise in atmospheric CO2, poses a substantial risk to the survival of humanity. While most research focuses on predicting annual CO2 emissions, which are crucial for setting long-term emission mitigation targets, the precise prediction of daily CO2 emissions is equally vital for setting short-term targets. This study examines the performance of 14 models in predicting daily CO2 emissions data from 1/1/2022 to 30/9/2023 across the top four polluting regions (China, India, the USA, and the EU27&UK). The 14 models used in the study include four statistical models (ARMA, ARIMA, SARMA, and SARIMA), three machine learning models (support vector machine (SVM), random forest (RF), and gradient boosting (GB)), and seven deep learning models (artificial neural network (ANN), recurrent neural network variations such as gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional-LSTM (BILSTM), and three hybrid combinations of CNN-RNN). Performance evaluation employs four metrics (R2, MAE, RMSE, and MAPE). The results show that the machine learning (ML) and deep learning (DL) models, with higher R2 (0.714–0.932) and lower RMSE (0.480–0.247) values, respectively, outperformed the statistical model, which had R2 (− 0.060–0.719) and RMSE (1.695–0.537) values, in predicting daily CO2 emissions across all four regions. The performance of the ML and DL models was further enhanced by differencing, a technique that improves accuracy by ensuring stationarity and creating additional features and patterns from which the model can learn. Additionally, applying ensemble techniques such as bagging and voting improved the performance of the ML models by approximately 9.6%, whereas hybrid combinations of CNN-RNN enhanced the performance of the RNN models. In summary, the performance of both the ML and DL models was relatively similar. However, due to the high computational requirements associated with DL models, the recommended models for daily CO2 emission prediction are ML models using the ensemble technique of voting and bagging. This model can assist in accurately forecasting daily emissions, aiding authorities in setting targets for CO2 emission reduction.

One of the areas where artificial intelligence (AI) technologies are used is the detection and diagnosis of mental disorders. AI approaches, including machine learning and deep learning models, can identify early signs of bipolar disorder, schizophrenia, autism spectrum disorder, depression, suicidality, and dementia by analyzing speech patterns, behaviors, and physiological data. These approaches increase diagnostic accuracy and enable timely intervention, which is crucial for effective treatment. This paper presents a comprehensive literature review of AI approaches applied to mental disorder detection using various data sources, such as survey, Electroencephalography (EEG) signal, text and image. Applications include predicting anxiety and depression levels in online games, detecting schizophrenia from EEG signals, detecting autism spectrum disorder, analyzing text-based indicators of suicidality and depression, and diagnosing dementia from magnetic resonance imaging images. eXtreme Gradient Boosting (XGBoost), light gradient-boosting machine (LightGBM), random forest (RF), support vector machine (SVM), K-nearest neighbor were designed as machine learning models, and convolutional neural networks (CNN), long short-term memory (LSTM) and gated recurrent unit (GRU) models suitable for the dataset were designed as deep learning models. Data preprocessing techniques such as wavelet transforms, normalization, clustering were used to optimize model performances, and hyperparameter optimization and feature extraction were performed. While the LightGBM technique had the highest performance with 96% accuracy for anxiety and depression prediction, the optimized SVM stood out with 97% accuracy. Autism spectrum disorder classification reached 98% accuracy with XGBoost, RF and LightGBM. The LSTM model achieved a high accuracy of 83% in schizophrenia diagnosis. The GRU model showed the best performance with 93% accuracy in text-based suicide and depression detection. In the detection of dementia, LSTM and GRU models have demonstrated their effectiveness in data analysis by reaching 99% accuracy. The findings of the study highlight the effectiveness of LSTM and GRU for sequential data analysis and their applicability in medical imaging or natural language processing. XGBoost and LightGBM are noted to be highly accurate ML tools for clinical diagnoses. In addition, hyperparameter optimization and advanced data pre-processing approaches are confirmed to significantly improve model performance. The results obtained with this study have revealed the potential to improve clinical decision support systems for mental disorders with AI, facilitating early diagnosis and personalized treatment strategies.

Disease prediction based on modeling the correlations between compounded indicator factors is a widely used technique in high incidence chronic disease prevention diagnosis. Predictive models based on personal health information have been developed historically by using simple regression fitting over relatively few factors. Regression approaches have been favored in previous prediction modeling approaches because they are simplest and do not assume any non-linearity in the model for contributions of the chosen factors. In practice, many factors are correlated and have underlying non-linear relationships to the predicted outcome. Deep learning offers a means to construct a more complex modeling approach, along with automation and adaptation. The aim of this paper is to assess the ability of a deep learning model to predict the heart disease incidence using a common benchmark dataset (University of California, Irvine (UCI) dataset). The performance of deep learning model has been compared with four popular machine learning models (two linear and two nonlinear) in predicting the incidence of heart disease using data from 567 participants from two cohorts taken from UCI database. The deep learning model was able to achieve the best accuracy of 94% and an AUC score of 0.964 when compared to other models. The performance of deep learning and nonlinear machine learning models was significantly better compared to the linear machine learning models with increase in the dataset size.

Aims: This study aimed to explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy. Methods: Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models, convolutional neural network (CNN) 1, CNN 2 and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3, respectively), were constructed, and their performances on each test set were respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real time. Results: On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp) and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052) and 94.60%, respectively. The Acc, Sn, Sp and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71) and 90.93% respectively. The Acc, Sn, Sp and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123) and 94.89%, respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138) and 94.44% (17/18), respectively. Conclusions: The deep learning model with the most diverse training data has the best diagnostic effect.

Abstract—Sentiment analysis (also known as opinion mining or emotion AI) is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly. Sentiment analysis aims to extract opinion automatically from data and classify them as positive and negative. Twitter widely used social media tools, been seen as an important source of information for acquiring people’s attitudes, emotions, views, and feedbacks. Within this context, Twitter sentiment analysis techniques were developed to decide whether textual tweets express a positive or negative opinion. In contrast to lower classification performance of traditional algorithms, deep learning models, including Convolution Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM), have achieved a significant result in sentiment analysis. Keras is a Deep Learning (DL) framework that provides an embedding layer to produce the vector representation of words present in the document. The objective of this work is to analyze the performance of deep learning models namely Convolutional Neural Network (CNN), Simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM), bidirectional Long Short-Term Memory (Bi-LSTM), BERT and RoBERTa for classifying the twitter reviews. From the experiments conducted, it is found that RoBERTa model performs better than CNN and simple RNN for sentiment classification. Keywords—Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Deep Learning, Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Encoder Representations from Transformers (BERT), Robustly Optimized BERT Pre-training Approach (RoBERTa).

Effective forecasting of key features in hospital emergency department: Hybrid deep learning-driven methods