检索结果-内蒙古大学图书馆

Attention-Driven Emotion Recognition in EEG: A Transformer-Based Approach With Cross-Dataset Fine-Tuning

IEEE Access 2025年 13卷 69369-69394页

作者： Ghous, Ghulam Najam, Shaheryar Alshehri, Mohammed Alshahrani, Abdulmonem AlQahtani, Yahya Jalal, Ahmad Liu, Hui Riphah International University Department of Electrical and Computer Engineering Islamabad44000 Pakistan Bahria University Department of Electrical Engineering Islamabad44000 Pakistan King Khalid University Department of Computer Science Abha61421 Saudi Arabia King Khalid University Department of Informatics and Computer Systems Abha61421 Saudi Arabia Air University Faculty of Computer Science and AI Islamabad44000 Pakistan Korea University College of Informatics Department of Computer Science and Engineering Seoul02841 Korea Republic of University of Bremen Cognitive Systems Laboratory Bremen28359 Germany Guodian Nanjing Automation Company Ltd. Nanjing210032 China

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

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Near-Field 3D Parameter Estimation Method Based on a Symmetric Enhanced Nested Array

A Near-Field 3D Parameter Estimation Method Based on a Symme...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yu, Linke Chen, Hua Xue, Dingfan Liu, Wei Tian, Ye Wang, Gang Faculty of Electrical Engineering and Computer Science Ningbo University China Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9798350368741

In this paper, a high-precision three-dimensional (3-D) near-field (NF) localization method is proposed under an underdetermined case based on a symmetric enhanced nested array (SENA). Firstly, the symmetry of the array and the fourth-order cumulant (FOC) are utilized to construct the equivalent virtual far-field (FF) reception data. Then, a gridless sparse and parametric approach (SPA), combined with an l1-SVD based pairing procedure, is used to obtain estimates for two paired angles. Finally, a one-dimensional (1-D) spectral estimator is applied to obtain the estimate of range parameter. Simulation results show the effectiveness of the proposed method. © 2025 IEEE.

关键词： cross array near-field source localization spatial-temporal underdetermine estimation

来源：评论

学校读者我要写书评

暂无评论

The Power of PDF-to-Audio Summaries in Modern Learning 4

The Power of PDF-to-Audio Summaries in Modern Learning

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kawde, Dhanshri Mendhe, Sameer Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Maharashtra Sawangi Wardha442001 India

ISBN: (纸本)9798331523923

PDF -to-audio based summarization technology is designed to enhance information accessibility and efficiency by transforming long written reports into short, audible summaries. AI, NLP, and TTS technologies that have developed recently have made it possible to extract main points without losing context. Yet, current systems have various shortcomings such as inability to process intricate PDF layouts like tables, charts, and annotations, contextual summarization inaccuracies, robotic or unhuman speech synthesis, and limited customization. Furthermore, the absence of multilingual support and easy integration into various platforms hinders wider adoption. These issues are addressed in this paper with a better approach that employs sophisticated NLP methods, context-sensitive summarization algorithms, and adaptive TTS systems. Our goal is to create a strong, user-oriented solution that provides greater summarization accuracy, personalized speech output, and improved accessibility for a variety of users, such as professionals, students, and the disabled. © 2025 IEEE.

关键词： Web Design

来源：评论

学校读者我要写书评

暂无评论

Beyond Playlists: AI-Driven Emotion-Based Music Recommendation Systems 2

Beyond Playlists: AI-Driven Emotion-Based Music Recommendati...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Shiralaskar, Hrishikesh Mendhe, Sameer Datta Meghe Institute of Higher Education md Research Department of Computer Science & Engineering Faculty of Engineering & Technology Maharashtra Wardha India Datta Meghe Institute of Higher Education and Research Department of Computer Science & Design Faculty of Engineering & Technology Maharashtra India

ISBN: (纸本)9798331505745

Music recommendation systems have evolved from simple playlist curation techniques to sophisticated AI-driven models capable of analyzing human emotions for personalized song suggestions. Emotion-based music recommendation systems integrate advanced machine learning, deep learning, and artificial intelligence techniques to detect users' emotional states through various input modes, including facial expressions, speech tone, text analysis, and physiological signals. These systems aim to enhance user experience by dynamically selecting music that aligns with real-time emotions, thereby improving mood regulation and mental well-being. This review explores the methodologies employed in emotion-based music recommendation systems, including deep learning architectures, facial recognition techniques, and sentiment analysis models. It also discusses the challenges associated with real-time emotion detection, data privacy concerns, cross-cultural differences in music perception, and system adaptability. Furthermore, the paper highlights emerging trends and future research directions, such as multimodal emotion detection, hybrid AI models, reinforcement learning, and ethical AI frameworks. Addressing these challenges and advancements will be crucial in developing more robust, accurate, and user-centric emotion-based music recommendation systems. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach on Advanced Fruit Disease Identification Using RCNN

A Novel Approach on Advanced Fruit Disease Identification Us...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Kumar, R. Boopathi, P. Rajan, M. Sundar Bangalore India Shri Nehru College of Arts and Science Department of Computer Science Tamil Nadu Coimbatore India Arba Minch Institute of Technology Arba Minch University Faculty of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798331509828

The early diagnosis of diseases in fruits holds immense importance for agricultural industries, as it directly impacts production quality and quantity. This study introduces a novel approach utilizing Recursive Convolutional Neural Network (RCNN) for automated citrus plant disease detection. Through a comprehensive methodology involving data collection, image pre-processing, segmentation, feature extraction using Linear Principal Component Analysis (LPCA), and classification, the proposed RCNN algorithm showcases promising results. Experimental evaluation demonstrates the efficacy of the RCNN-based approach, with precision averaging at 0.929, recall at 0.946, accuracy at 0.945, F-measure at 0.943, and minimal time complexity. Compared to traditional manual inspection methods, RCNN offers a more accurate and efficient solution, significantly reducing the burden on farmers and experts while enhancing fruit disease detection capabilities. Overall, the proposed RCNN-based approach presents a significant advancement in fruit disease identification, offering precise and timely detection to mitigate agricultural losses. With its superior performance metrics and streamlined process, RCNN stands as a promising tool for revolutionizing fruit disease diagnosis and improving agricultural productivity. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A modified grey wolf optimizer with multi-solution crossover integration algorithm for feature selection

引用

Journal of Ambient Intelligence and Humanized Computing 2025年第1期16卷 329-345页

作者： Ihsan, Muhammad Din, Fakhrud Zamli, Kamal Z. Ghadi, Yazeed Yasin Alahmadi, Tahani Jaser Innab, Nisreen Faculty of IT Department of Computer Science and IT University of Malakand Khyber Pakhtunkhwa Chakdara18800 Pakistan Faculty of Computing College of Computing and Applied Sciences Universiti Malaysia Pahang Pahang Pekan26600 Malaysia Department of computer science and software engineering Al Ain University Abu Dhabi12555 United Arab Emirates Department of Information SystemsCollege of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh84428 Saudi Arabia Department of Computer Science and Information SystemsCollege of Applied Sciences Al-Maarefa University Diriyah Riyadh13713 Saudi Arabia

Feature selection helps eradicate redundant features which is essential to mitigate the curse of dimensionality when a machine-learning model deals with high-dimensional datasets. Grey Wolf Optimizer (GWO) is a swarm-based algorithm that simulates the wolves’ hunting behavior. Although very efficient, GWO faces some limitations which may cause premature convergence and/or local optima trapping. Moreover, GWO relies mainly on the three best wolves, limiting its potential for diverse exploration and exploitation. This work proposes an improved version of GWO namely, a modified grey wolf optimizer with multi-solution crossover integration (MGWO-MCI) algorithm. MGWO-MCI algorithm incorporates a multi-solution strategy that evolves new potential solutions in the optimization process. A crossover operation is performed between the new wolves and the existing hierarchy, reforming the position-updating process. MGWO-MCI utilizes this position-updating process using two different approaches. The first approach named MGWO-MCI-I expands the additional wolves’ role to both exploration and exploitation whereas the second approach named MGWO-MCI-II incorporates their role to exploration only. These approaches are evaluated and tested using 18 datasets and an Intrusion detection dataset NSL-KDD for feature selection. Statistically, the results are analyzed through the Wilcoxon test, which shows the superiority of MGWO-MCI-II. MGWO-MCI-II outperforms others with an accuracy of 98.6% on NSL-KDD and achieves 55.5% overall best outcomes on other datasets. Moreover, the MGWO-MCI was evaluated on two constrained optimization problems, the pressure vessel and welded beam design validating its effectiveness and adaptability in solving different optimization problems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid-Optimized Model for Deepfake Detection

引用

International Journal of Advanced computer science and Applications 2025年第4期16卷 148-160页

作者： Mancy, H. Elpeltagy, Marwa Eldahshan, Kamal Ismail, Aya Department of Computer Science College of Engineering and Computer Sciences Prince Sattam Bin Abdulaziz University Alkharj11942 Saudi Arabia Al-Azhar University Cairo Egypt Systems and Computers Department Al-Azhar University Egypt Mathematics Department Faculty of Science Al-Azhar University Egypt Mathematics Department Tanta University Egypt

The advancement of deep learning models has led to the creation of novel techniques for image and video synthesis. One such technique is the deepfake, which swaps faces among persons and then produces hyper-realistic videos of individuals saying or doing things that they never said or done. These deepfake videos pose a serious risk to everyone and countries if they are exploited for extortion, scamming, political disinformation, or identity theft. This work presents a new methodology based on a hybrid-optimized model for detecting deepfake videos. A Mask Region-based Convolutional Neural Network (Mask R-CNN) is employed to detect human faces from video frames. Then, the optimal bounding box representing the face region per frame is selected, which could help to discover many artifacts. An improved Xception-Network is proposed to extract informative and deep hierarchical representations of the produced face frames. The Bayesian optimization (BO) algorithm is employed to search for the optimal hyperparameters' values in the extreme gradient boosting (XGBoost) classifier model to properly discriminate the deepfake videos from the genuine ones. The proposed method is trained and validated on two different datasets;CelebDF-FaceForencics++ (c23) and FakeAVCeleb, and tested also on various datasets;CelebDF, DeepfakeTIMIT, and FakeAVCeleb. The experimental study proves the superiority of the proposed method over the state-of-the-art methods. The proposed method yielded %97.88 accuracy and %97.65 AUROC on the trained CelebDF-FaceForencics++ (c23) and tested CelebDF datasets. Additionally, it achieved %98.44 accuracy and %98.44 AUROC on the trained CelebDF-FaceForencics++ (c23) and tested DeepfakeTIMIT datasets. Moreover, it yielded %99.50 accuracy and %99.21 AUROC on the FakeAVCeleb visual dataset. © (2025), (science and Information Organization). All Rights Reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Proposal of a Document Layout Analysis Method Adopting Pre-processing Based on Document Image Classification 16th

Proposal of a Document Layout Analysis Method Adopting Pre...

引用

16th International Conference on Genetic and Evolutionary Computing, ICGEC 2024

作者： Kakinoki, Kanta Katayama, Tetsuro Department of Computer Science and Systems Engineering Faculty of Engineering University of Miyazaki 1-1 Gakuen-Kibanadai Nishi Miyazaki889-2192 Japan

ISBN: (纸本)9789819615346

To extract important information from the document images, document layout analysis research has been carried out. Previous research analyzes document layouts only for specific document formats. This paper proposes a document layout analysis method that adopts pre-processing based on document image classification to analyze document layouts for various document formats. From the application examples, we have confirmed that the proposed method can correctly analyze document layout by using training models trained for each document format. Furthermore, to evaluate the usefulness of the proposed method, we have compared the F score of the proposed method for document layout analysis using a single training model covering various document formats and using a training model generated for each document format. As a result, we have confirmed that our proposed method is useful in document layout analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： document image classification document layout analysis rule-based correction

来源：评论

学校读者我要写书评

暂无评论

Data Processing and Pattern Recognition for Electronic Nose 3

Data Processing and Pattern Recognition for Electronic Nose

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Raymond, David Chaudhri, Shivnath Shaikh, Kahkasha Datta Meghe Institute of Higher Education and Research Faculty of Enfineering and Technology Department of Computer Science and Medical Engineering Wardha India Datta Meghe Institute of Higher Education and Research Faculty of Enfineering and Technology Depertment of Computer Science and Design Wardha India

ISBN: (纸本)9798331509675

Electronic nose (e-nose) technology has become a powerful tool for identifying and evaluating complex scents in a variety of contexts, such as environmental monitoring, medical diagnostics, and food quality control. This review study looks at how important pattern recognition and data processing are to improving e-nose system performance. This study covered challenges, including data complexity, cross-sensitivity and interference, sensor drift, and a lack of standardization. The article covers several future directions, such as the use of artificial intelligence (AI) and machine learning to advance pattern recognition and predictive analytics, integration with the Internet of Things (IoT) and big data for real-time monitoring, and advancements in sensor technology for improved sensitivity and *** research work is underway towards the development of low power flexible sensors, improved multi sensor fusion Methodologies, smart adaptive algorithms, Application for personalized health monitoring and diagnostics as well to make it green technologies. To move forward with emerging technologies and for e-nose technology to be applicable, it will have to overcome these weaknesses. © 2025 IEEE.

关键词： Electronic nose

来源：评论

学校读者我要写书评

暂无评论

Enhanced Position-Aided Beam Prediction Using Real-World Data and Enhanced-Convolutional Neural Networks

引用

IEEE Access 2025年 13卷 74913-74925页

作者： Abd El Moaty Mohamed Gouda, Ahmed Hamad, Ehab K. I. Hussein, Aziza I. Mabrook, M. Mourad Donkol, A.A. Nahda University Faculty of Engineering Electrical Engineering Department Beni Suef62764 Egypt Aswan University Faculty of Engineering Department of Electrical Engineering Aswan81542 Egypt Effat University Department of Electrical and Computer Engineering Jeddah22332 Saudi Arabia Beni-Suef University Faculty of Navigation Science and Space Technology Space Communication Department Beni Suef62511 Egypt South Valley University Faculty of Engineering Electrical Engineering Communication and Electronics Department Qena83523 Egypt

Millimeter-wave (mmWave) communication systems utilize narrow beamforming to ensure adequate signal power. However, beam alignment requires significant training overhead, especially in high mobility scenarios. Previous research has utilized synthetic data for position-aided beam prediction, which does not fully capture real-world complexities. In this work, an Enhanced Convolutional Neural Network model (E-CNN) is proposed for optimal prediction of beam indices with the aid of real-world GPS position data. The proposed E-CNN model has been investigated across nine different scenarios from the DeepSense 6G dataset and compared against the conventional algorithms. For 64-beams Scenario 1, the E-CNN model showed an increase in average top-1 accuracy from 55.57% to 63.92%, and in case of 32-beams, the accuracy increased from 71.34 % to 82.06%. For 16-beams, the accuracy increased from 86.17% to 94.64 %, while for 8-beams, the accuracy increased from 90.24% to 97.11%. In addition, besides showing significant power loss reduction in various scenarios, the proposed E-CNN model has demonstrated robustness regarding real-word conditions and adaptability for various beam setups. The model realized as high as a 50% power loss reduction in arguably the most challenging graphs, which is an exercise in reliability. This research fills the existing gap between the simulated aid beam alignment and real-world position beam aided alignment, which can be useful in improving beamforming in the upcoming wireless networks. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：