Machine learning algorithms face important implementation difficulties due to imbalanced learning since the Synthetic Minority Oversampling Technique (SMOTE) helps improve performance through the creation of new minor...
详细信息
Predicting the outcomes of Formula 1 (F1) races presents a significant challenge due to the complex interplay of numerous factors, including driver skill, vehicle performance, team strategy, and unpredictable race-day...
详细信息
Emotion recognition from EEG (electroencephalogram) signals is crucial in mental health diagnostics and human-computer interaction but is often hindered by high dimensionality, noise, and complex temporal dependencies...
详细信息
Emotion recognition from EEG (electroencephalogram) signals is crucial in mental health diagnostics and human-computer interaction but is often hindered by high dimensionality, noise, and complex temporal dependencies in the data. This paper presents a novel approach that integrates transformer models, attention mechanisms, and transfer learning to enhance emotion recognition accuracy from EEG signals. The proposed methodology consists of two phases: Attention Enhanced Base Model Development (AE-BMD) and Cross-Dataset Fine Tuning Adaptation (CD-FTA). In the AE-BMD phase, the base model is developed and trained on the SEED-IV dataset (15 participants, 62 EEG channels), achieving an accuracy of 84%, with an average precision of 84.75%, recall of 84% and F1-score of 84%. This phase employs optimized feature extraction from key EEG frequency bands (Delta, Theta, Alpha, Beta, Gamma) using techniques such as MFCC, GFCC, power spectral density, and Hjorth parameters. A transformer encoder with integrated spectral and temporal attention mechanisms captures intricate patterns and long-range dependencies within the EEG signals. In the CD-FTA phase, the model undergoes fine-tuning on the SEED-V dataset (20 participants, 62 channels) leading to an improved accuracy of 90%, with an average precision of 90.6%, recall of 90.6%, and F1-score of 90.6%. The model’s generalization is further validated on the MPED dataset (23 participants, 62 channels, seven emotion classes), achieving 79%, with an average precision of 79.3%, recall of 79.3% and F1-score of 79.1% across diverse emotional states. This cross-dataset adaptation leverages transfer learning to enhance the model’s generalization across different emotional states and EEG datasets. Experimental results show that the proposed approach outperforms traditional methods, achieving superior accuracy and robustness in emotion recognition tasks. This work advances emotion recognition systems by addressing challenges in EEG signal proc
Surveillance drones equipped with video transmission capabilities play a crucial role in modern security systems, with the integration of OpenCV for object detection marking a significant advancement. This study evalu...
详细信息
Depression is a major public health concern, affecting millions worldwide, and necessitates early, accurate detection for timely intervention. This study focuses on enhancing machine learning (ML) and deep learning (D...
详细信息
Text-based person retrieval aims to identify specific individuals within an image database using textual descriptions. Due to the high cost of annotation and privacy protection, researchers resort to synthesized data ...
详细信息
Multi-access edge computing (MEC) plays a crucial role in providing low-latency and high-data transmission services to Internet of Things (IoT) devices. However, in remote areas where deploying edge devices is challen...
详细信息
Ample profits of GPU cryptojacking attract hackers to recklessly invade victims’ devices, for completing specific cryptocurrency mining tasks. Such malicious invasion undoubtedly obstructs normal device usage and was...
详细信息
作者:
Gote, Pradnyawant M.Kumar, PraveenVerma, PrateekYesankar, PrajyotPawar, AdeshSaratkar, Saniya
Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India
Faculty of Engineering and Technology Department of Computer Science & Medical Engineering Maharashtra Wardha442001 India
Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India
Faculty of Engineering and Technology Department of Artificial Intelligence & Data Science Maharashtra Wardha442001 India
The swift progression of wireless communication technologies-specifically from 5G to 6G is an approach that could be the most significant revolutionary leap towards changing connectivity and data transmission forever....
详细信息
作者:
Wanjari, KetanVerma, Prateek
Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Wardha442001 India
Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India
Skin cancer is the most commonly reported type of cancer globally and one of the few cancers that can be effectively treated if detected in its early stages. Recent advancements in artificial intelligence (AI) have si...
详细信息
暂无评论