检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ahire, Vrushank Shah, Kunal Khan, Mudasir Nazir Pakhale, Nikhil Sookha, Lownish Rai Ganaie, M.A. Dhall, Abhinav Department of Computer Science and Engineering Indian Institute of Technology Punjab Ropar India Faculty of Information Technology Monash University Melbourne Australia

—This paper introduces MAVEN (Multi-modal Attention for Valence-Arousal Emotion Network), a novel architecture for dynamic emotion recognition through dimensional modeling of affect. The model uniquely integrates visual, audio, and textual modalities via a bi-directional cross-modal attention mechanism with six distinct attention pathways, enabling comprehensive interactions between all modality pairs. Our proposed approach employs modality-specific encoders to extract rich feature representations from synchronized video frames, audio segments, and transcripts. The architecture’s novelty lies in its cross-modal enhancement strategy, where each modality representation is refined through weighted attention from other modalities, followed by self-attention refinement through modality-specific encoders. Rather than directly predicting valence-arousal values, MAVEN predicts emotions in a polar coordinate form, aligning with psychological models of the emotion circumplex. Experimental evaluation on the Aff-Wild2 dataset demonstrates the effectiveness of our approach, with performance measured using Concordance Correlation Coefficient (CCC). The multistage architecture demonstrates superior ability to capture the complex, nuanced nature of emotional expressions in conversational videos, advancing the state-of-the-art (SOTA) in continuous emotion recognition in-the-wild. Code can be found at: https://***/Vrushank-Ahire/MAVEN_8th_ABAW. © 2025, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Multiplex Graph Neural Networks for Recommendation

arXiv

引用

arXiv 2024年

作者： Li, Xiang Fu, Chaofan Zhao, Zhongying Zheng, Guanjie Huang, Chao Yu, Yanwei Dong, Junyu Faculty of Information Science and Engineering Ocean University of China China College of Computer Science and Engineering Shandong University of Science and Technology China Department of Computer Science and Engineering Shanghai Jiao Tong University China Department of Computer Science The University of Hong Kong Hong Kong

Effective recommender systems play a crucial role in accurately capturing user and item attributes that mirror individual preferences. Some existing recommendation techniques have started to shift their focus towards modeling various types of interactive relations between users and items in real-world recommendation scenarios, such as clicks, marking favorites, and purchases on online shopping platforms. Nevertheless, these approaches still grapple with two significant challenges: (1) Insufficient modeling and exploitation of the impact of various behavior patterns formed by multiplex relations between users and items on representation learning, and (2) ignoring the effect of different relations within behavior patterns on the target relation in recommender system scenarios. In this work, we introduce a novel recommendation framework, Dual-Channel Multiplex Graph Neural Network (DCMGNN), which addresses the aforementioned challenges. It incorporates an explicit behavior pattern representation learner to capture the behavior patterns composed of multiplex user-item interactive relations, and includes a relation chain representation learner and a relation chain-aware encoder to discover the impact of various auxiliary relations on the target relation, the dependencies between different relations, and mine the appropriate order of relations in a behavior pattern. Extensive experiments on three real-world datasets demonstrate that our DCMGNN surpasses various state-of-the-art recommendation methods. It outperforms the best baselines by 10.06% and 12.15% on average across all datasets in terms of Recall@10 and NDCG@10 respectively. The source code of our paper is available at https://***/lx970414/TKDE-DCMGNN. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Malware Traffic Classification Via Consistency Regularization and Pseudo-Labeling 23

Semi-Supervised Malware Traffic Classification Via Consisten...

引用

23rd IEEE International Conference on Communication technology, ICCT 2023

作者： Jiao, Qianlong Zhang, Xixi Zhang, Weijie Miao, Fucheng Ohtsuki, Tomoaki Adebisi, Bamidele Wang, Yu Gui, Guan College of Telecommunications and Information Engineering Njupt Nanjing China Reading Academy Nanjing University of Information Science and Technology Nanjing China Nanjing Great Information Technology Co. Ltd Nanjing China Keio University Department of Information and Computer Science Yokohama Japan Manchester Metropolitan University Faculty of Science and Engineering Manchester United Kingdom

ISBN: (纸本)9798350325959

Malware traffic classification (MTC) technology plays a crucial role in cyber security by serving as the first step of network intrusion detection system. Recently, deep learning has been successfully introduced into the field of network intrusion detection. However, its performance relies heavily on the quantity and quality of labeled samples, which are often difficult to obtain in real-world applications. To address these challenges, we propose semi-supervised MTC method based on consistency regularization and pseudo-labeling. This method utilizes unlabeled malware traffic data to improve the classification performance of the model. Specifically, we train the model using labeled malware traffic data. Then, weak data augmentation is performed on unlabeled traffic data and pseudo labels are generated through the model. Finally, the model predicts unlabeled data after strong data augmentation and compares it with pseudo labels. Model parameters are updated using losses from labeled and unlabeled samples. Experimental results demonstrate that our proposed method outperforms other classical classification approaches, including ladder networks, virtual adversarial training (VAT), convolutional neural network (CNN), and support vector machine (SVM), when the ratios of labeled samples range from 1% to 5%. © 2023 IEEE.

关键词： data augmentation deep learning Malware traffic classification semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Detection in Text-Based Communication Using Fine-Tuned BERT Model

Emotion Detection in Text-Based Communication Using Fine-Tun...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： Urva Dave Om Desai Nisarg Chaudhari Dweepna Garg Kashyap Patel Parth Goel Department of Computer Engineering Faculty of Technology and Engineering (FTE) Devang Patel Institute of Advance Technology and Research (DEPSTAR) Charotar University of Science and Technology (CHARUSAT) Gujarat

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

To detect emotions in text-based communication, the study investigates the use of BERT (Bidirectional Encoder Representations from Transformers). In digital contexts like social media or messaging platforms, where non-verbal cues are lacking, accurately identifying emotions is a challenge that requires careful attention. This study used an uncased BERT model that was pretrained on large corpora such as the English Wikipedia. It was then refined on a dataset of more than 10,000 entries that were categorized into 13 different emotions, such as surprise, happiness, and sadness. Training and validation accuracy of the model improved steadily over the course of eight epochs, stabilizing at 99.4% by the end of the process. The model performed well in forecasting emotions like love and happiness, but it had trouble with more nuanced feelings like surprise and worry, according to a confusion matrix that was created. This study highlights how BERT can be used to improve emotion detection, particularly in chat platforms and other applications where real-time emotion recognition could enhance the emotional accuracy and clarity of digital conversations.

关键词： Training Emotion recognition Accuracy Social networking (online) Bidirectional control Predictive models Transformers Encoding Real-time systems Overfitting

来源：评论

学校读者我要写书评

暂无评论

Robust Transmission design in Multiobjective RIS-Aided SWIPT IoT Communications

引用

IEEE Internet of Things Journal 2024年第10期11卷 18605-18618页

作者： Sharma, Vaibhav Allu, Raviteja Singh, Sandeep Kumar Singh, Keshav Duong, Trung Q. Tsiftsis, Theodoros A. Institute of Communications Engineering National Sun Yat-sen University Kaohsiung804 Taiwan Motilal Nehru National Institute of Technology Allahabad Electronics and Communication Engineering Department Prayagraj211004 India Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John'sNLA1B 3X5 Canada Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom University of Thessaly Department of Informatics and Telecommunications Lamia35100 Greece

This work investigates the performance of simultaneous wireless information and power transfer (SWIPT) in a reconfigurable intelligent surface (RIS)-aided Internet of Things (IoT) communications under imperfect channel state information (CSI). We formulate a multiobjective optimization problem (MOOP) to design a transmit precoding vector (TPV) at the base station (BS) and phase shift matrix (PSM) at the RIS that jointly maximizes energy efficiency (EE) and harvested power (HP) under the norm-bounded CSI error model. Due to the conflicting objective functions and nonconvex nature of the above optimization problem, the MOOP is simplified using the ϵ-constraint method and subsequently adopting advanced optimization tools, such as the Dinkelbach method, S-procedure, general sign-definiteness, semidefinite programming and convex-concave procedure. Thereafter, we propose an alternating optimization-based algorithm which determines optimal TPV and PSM iteratively that jointly maximizes the EE and HP of the considered system. Through numerical simulations, we validate the robustness, optimality, convergence, accuracy, and effectiveness of our proposed algorithm. Furthermore, we assess the impact of several key parameters, such as the number of RIS elements, available transmit power at BS, and the minimum HP on the performance of the considered system. © 2014 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Effect of radiofrequency coil and primary magnetic field on radiolucent composite plates

引用

Noise and Vibration Worldwide 2023年第1期54卷 44-58页

作者： Gawande, Atul S Mukka Ramachanra, Shreyas Kamyab, Hesam Trung, Nguyen-Thoi Kattimani, Subhaschandra Department of Mechanical Engineering National Institute of Technology Karnataka Surathkal India Malaysia-Japan International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur Malaysia Laboratory for Applied and Industrial Mathematics Institute of Computational Science and Artificial Intelligence Ho Chi Minh City Viet Nam Faculty of Mechanical-Electrical and Computer Engineering Van Lang University Ho Chi Minh City Viet Nam

Magnetic Resonance Imaging (MRI) systems need a material compatible with the imaging technique with lesser attenuation and provide accurate images without distortion. Carbon fibers are the best-suited materials for x-ray applications because of their radiolucent properties and reduced attenuation characteristics. However, carbon fiber produces images with distortion in the MRI system by absorbing electromagnetic energy because of its conductive nature. In the present study, five different fiber-reinforced radiolucent composite plates are analyzed to predict their suitability for a radio frequency coil and the effect of a primary magnetic field of 1.5 T and 3.0 T on mechanical responses. Simulation models are built to explore the impact of electromagnetic waves and birdcage coil configurations on composite material and quantify the temperature changes caused due to energy absorption. A multiphysics coupling simulation is being used to understand the effect of stacking sequence, ply orientation, and boundary conditions on the response of composite plates under an electro-magneto-mechanical environment. © The Author(s) 2022.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Management in IoTs Using Evolutionary and Swarm Intelligence Algorithms 7

Efficient Resource Management in IoTs Using Evolutionary and...

引用

7th International Symposium on Innovative Approaches in Smart Technologies, ISAS 2023

作者： Gupta, Keshav Dev Cengiz, Korhan Awasthi, Charu Ramini, Siva Akash Chatterjee, Shyamapriya Pavithra, M. Poornima College of Engineering Department of Computer Science Engineering Jaipur India University of Fujairah College of Information Technology United Arab Emirates Istinye University Department of Computer Engineering Istanbul Turkey University of Hradec Kralove Faculty of Informatics and Management Department of Information Technologies Hradec Kralove500 03 Czech Republic JSS Academy of Technical Education Department of Information Technology Noida India Andhra Pradesh Amaravati India Narula Institute of Technology Department of Information Technology West Bengal Kolkata India Jansons Institute of Technology Karumathampatti Department of Computer Science and Engineering Coimbatore641659 India

ISBN: (纸本)9798350383065

The proliferation of the Internet of Things (IoT) has ushered in a transformative era of connected devices, emphasizing the critical need for effective resource management. This study introduces an innovative approach that harnesses Evolutionary and Swarm Intelligence algorithms for IoT Task Scheduling, addressing resource optimization challenges. The approach offers superior resource utilization through advanced optimization techniques, reducing energy consumption and enhancing efficiency. Furthermore, it significantly reduces task scheduling execution time, enabling prompt decision-making in dynamic IoT environments. This results in improved task allocation quality, meeting application-specific requirements, and prioritizing critical tasks. Notably, the approach excels in minimizing completion time, making it particularly advantageous for real-time IoT applications. This research contributes to the advancement of IoT resource management, offering an adaptive, efficient, and intelligent solution with broad applicability. In the evolving landscape of IoT, the findings presented here lay a solid foundation for future research and practical implementations, ultimately promoting more responsive, sustainable, and intelligent IoT ecosystems. © 2023 IEEE.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

Abnormality Detection of Retinal Images Using Dual Autoencoder 21

Abnormality Detection of Retinal Images Using Dual Autoencod...

引用

21st IEEE India Council International Conference, INDICON 2024

作者： Karthikayan Nagarajan, P. Bairwa, Sachin Kumar Lakshmi Priya, A. Jayaraman, Umarani Indian Institute of Information Technology Design and Manufacturing Department of Computer Science and Engineering Kancheepuram Chennai India Psg College of Technology Department of Biomedical Engineering Coimbatore India

ISBN: (纸本)9798350391282

This paper presents a dual autoencoder model for abnormality detection from retinal fundus images. In this paper, the dual autoencoder along with (Kernal Density Estimation) KDE is used to improve the result as compared to a single autoencoder with MSE for disease classification. The proposed model makes use of an autoencoder because it can be trained on unlabeled data. It is a good fit for abnormality detection scenarios in which access to labeled data may be limited or costly. It is useful to have a model that does not require labeled examples of abnormalities because abnormalities are usually rare and diverse. Dual autoencoders combined with Kernel Density Estimation (KDE) offer a powerful framework for abnormality detection by leveraging the complementary strengths of both techniques. The dataset used in this research is the Ocular Disease Intelligent Recognition (ODIR) which is a structured ophthalmic database with seven classes of abnormal covering most of the common retinal eye diseases. The evaluation criteria used in this work include MSE for reconstruction error and accuracy for abnormality detection. © 2024 IEEE.

关键词： Abnormality Detection Disease Classification Dual Autoencoder Eye Disease ODIR Dataset Retinal Images

来源：评论

学校读者我要写书评

暂无评论

Exploring the Benefits of DNS-Based Authentication for Wireless Network Security 3

Exploring the Benefits of DNS-Based Authentication for Wirel...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Swarup, Lakshya Jayadurga, R. Borade, Monali R. Ramachandran, T. Singh, Akhilendra Pratap Prabha, Savita Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Master of Business Administration Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9798350319125

Wi-wireless networks are becoming more pervasive and are frequently the primary goal of malicious attackers. Therefore, it is miles crucial that wireless networks are nicely secured to defend their users from malicious moves. DNS-based total authentication is a promising answer for attaining ease of authentication of wi-wireless customers in an open Wi-Fi community. This paper surveys numerous current works that discover the wi-fits wireless of DNS-based total authentication for Wi-Fi wireless community safety. especially this paper opinions three one-of-a-kindwireless strategies of using DNS for authentication purposes: making use of DNS's cache for identifying windows-primarily based Wi-Fi wireless clients;Open Mobile Alliance (OMA)'s tool control (DM) projects to relaxed get right of entry to;and a modern scheme for protecting the use of the DNS-based techniques. Wi-finally, this paper discusses a few safety-demanding situations and future studies directions. © 2023 IEEE.

关键词： authentication initiatives management protecting secured

来源：评论

学校读者我要写书评

暂无评论

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Real-Time Detection 18

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Rea...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Ahmed, Tafreed Maaz, Ahmad Mahmood, Danyaal Abideen, Zain Ul Arshad, Usama Ali, Raja Hashim BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany

ISBN: (纸本)9798350328172

YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. Developing a custom object detection solution that can detect specific objects in real-time video streams has the potential to revolutionize various fields and has been the subject of extensive research. Although there have been advances in object detection, there is still a gap in the research for real-time detection of custom objects with high accuracy and speed. This research addresses this gap by training a YOLOv8 detector on a custom dataset of objects and evaluating its performance on real-time video streams which is by far the latest model and thus is faster and more accurate. Our experimental results demonstrate that our custom-trained YOLOv8 detector achieves high accuracy and real-time performance on a custom dataset of objects. The detector achieved an overall mAP50 of 0.864 and a mAP50-95 of 0.758, with individual class results ranging from 0.47 to 0.995. These findings show that custom training data and YOLOv8 are effective in real-time object detection, which has practical applications in various fields. The significance of the results and our contribution lies in demonstrating the effectiveness of custom training data for improving object detection accuracy and speed using YOLO, which has implications for a wide range of real-world applications. © 2023 IEEE.

关键词： Object detection

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：