检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wewelwala, Sahan Hewage Sumanathilaka, T.G.D.K. School of Computing Informatics Institute of Technology 06 Colombo Sri Lanka Department of Computer Science Swansea University Wales Swansea United Kingdom

This research presents a hybrid emotion recognition system integrating advanced Deep Learning, Natural Language Processing (NLP), and Large Language Models (LLMs) to analyze audio and textual data for enhancing customer interactions in contact centers. By combining acoustic features with textual sentiment analysis, the system achieves nuanced emotion detection, addressing the limitations of traditional approaches in understanding complex emotional states. Leveraging LSTM and CNN models for audio analysis and DistilBERT for textual evaluation, the methodology accommodates linguistic and cultural variations while ensuring real-time processing. Rigorous testing on diverse datasets demonstrates the system's robustness and accuracy, highlighting its potential to transform customer service by enabling personalized, empathetic interactions and improving operational efficiency. This research establishes a foundation for more intelligent and human-centric digital communication, redefining customer service standards. © 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

Designing Quantum-Resilient Blockchain Frameworks: Enhancing Transactional Security with Quantum Algorithms in Decentralized Ledgers

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 618-628页

作者： Kale, Meenal R. Baker El-Ebiary, Yousef A. Sathiya, L. Burugari, Vijay Kumar Yulduz, Erkiniy Muniyandy, Elangovan Alanazi, Rakan Department of Humanities Yeshwantrao Chavan College of Engineering Hingna Nagpur India Faculty of Informatics and Computing UniSZA University Malaysia Department of CSE Panimalar Engineering College Chennai India Dept of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Automatic Control and Computer Engineering Department Turin Polytechnic University in Tashkent Tashkent Uzbekistan Department of Biosciences-Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Applied Science Research Center Applied Science Private University Amman Jordan Department of Information Technology Faculty of Computing and Information Technology Northern Border University Rafha Saudi Arabia

Quantum computing is progressing at a fast rate and there is a real threat that classical cryptographic methods can be compromised and therefore impact the security of blockchain networks. All of the ways used to secure blockchain like Rivest–Shamir–Adleman (RSA), Elliptic Curve Cryptography (ECC) and Secure Hash Algorithm 256-bit (SHA256) are the characteristic of the traditional cryptographic techniques vulnerable to attack by quantum algorithms: Shor’s and Grover’s algorithms: can efficiently break asymmetric encryption and speed up brute force attacks. Because of this vulnerability, there exists a need to develop an advance quantum resilient blockchain framework to protect the decentralized ledgers from the future threats of the quantum. This research proposes Post-Quantum Cryptography (PQC), Quantum Key Distribution (QKD) and Quantum Random Number Generation (QRNG) as a formidable architectural integration, to fortify security of blockchain. Classical encryption is replaced with PQC, QKD with secure key exchange by detecting eavesdropping, and QRNG with improving cryptographic randomness to remove the predictable key vulnerability. Only with a small loss of transaction efficiency, we increase transaction encryption accuracy, key exchange security, and resistance to quantum attacks. In this quantum enhanced blockchain design, the idea is to preserve the decentralization, transparency and security and at the same time overcome the future quantum threat. By going through rigorous analysis and comparative evaluation, we demonstrate that the approach saves blockchain networks from the emerging quantum risks to make sure that the decentralized finance, smart contracts and cross chain transactions. © (2025), (Science and Information Organization). All rights reserved.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

ActivityMamba: A CNN-Mamba hybrid neural network for efficient human activity recognition

引用

IEEE Transactions on Mobile computing 2025年

作者： Luo, Fei Li, Anna Jiang, Bin Khan, Salabat Wu, Kaishun Wang, Lu Great Bay University School of Computing and Information Technology Dongguan China Lancaster University School of Computing & Communications United Kingdom University of Petroleum College of Oceanography and Space Informatics Qingdao China Shenzhen University College of Computer Science and Software Engineering Shenzhen China Guangzhou China

Current research in human activity recognition primarily emphasizes enhancing accuracy, with limited exploration into computational efficiency and hardware compatibility. Recently, Mamba has sparked substantial interest within the realm of deep learning. Mamba is a hardware-aware algorithm enabling very efficient training and inference. Researchers are applying Mamba to various tasks, demonstrating significant promise in both language and vision tasks. It is worthwhile to investigate the use of Mamba for efficient human activity recognition. In this paper, we proposed a hybrid neural network that integrates CNN and visual Mamba, called ActivityMamba. The SE-Mamba block in ActivityMamba utilizes both CNN's local and Mamba's global context modeling while keeping computation and memory efficiency. We evaluated the ActivityMamba on five public benchmark datasets collected by using three different sensing techniques. ActivityMamba achieved higher performance than vision transformers, vision Mamba, and CNNs with fewer FLOPs and parameters. It sets a new SOTA on all five datasets, which are 91.78% OA and 89.13% F1 on the USC-HAD dataset, 99.19% OA and 98.64% F1 on the UT-HAR dataset, 99.82% OA and F1 on the DIAT dataset, 98.59% OA and 98.65% F1 on the UCI-HAR dataset, and 95.41% OA and 93.14% F1 on the UniMib dataset. Our work is the first to investigate the CNN-Mamba hybrid network for efficient human activity recognition. © 2002-2012 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

LiteLSTM architecture based on weights sharing for recurrent neural networks

引用

International Journal of Computers and Applications 2025年

作者： Elsayed, Nelly ElSayed, Zag Maida, Anthony S. School of Information Technology University of Cincinnati CincinnatiOH United States School of Computing and Informatics University of Louisiana at Lafayette LafayetteLA United States

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This paper proposed a novel LiteLSTM architecture based on reducing the LSTM computation components via the weights sharing concept to reduce the overall architecture computation cost and maintain the architecture performance. The proposed LiteLSTM can be significant for processing large data at different domains where time-consuming is crucial while hardware resources are limited, such as the security of Internet of Things (IoT) devices and medical data processing. The proposed model was evaluated and tested empirically on three different datasets from the computer vision, cybersecurity, and speech emotion recognition domains. The proposed LiteLSTM has comparable accuracy to the other state-of-the-art recurrent architecture while using a smaller computation budget. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Organising unstructured data using Double Net Self-Organising Map (DNSOM) model

引用

Soft computing 2025年 1-22页

作者： You, Cheng Chun Lim, Seng Poh Lee, Chen Kang Tan, Joi San Lim, Seng Chee Department of Computer Science Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Jalan University Bandar Barat Perak Kampar31900 Malaysia Department of Computing Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Jalan Sungai Long Bandar Sungai Long Cheras Selangor Kajang43000 Malaysia School of Computing and Informatics ViTrox College 746 Persiaran Cassia Selatan 3 Batu Kawan Industrial Park Penang Bandar Cassia14110 Malaysia

Surface reconstruction is the process of representing surfaces using the data obtained from scanning devices. When the data obtained is unstructured during data collection, it can cause problems in presenting the surface due to the lack of connectivity information for the data. It shows that data collection is a crucial task in surface reconstruction. Previous works have proved that Self-Organising Map (SOM) models can be used to organise unstructured data. However, the 2-D SOM model will generate a surface with holes for the closed surfaces. Besides, the 3-D SOM model will generate an incorrect surface due to the connectivity of the internal neurons. In addition, the Cube Kohonen SOM (CKSOM) model is limited to the same grid size. Hence, a SOM model known as Double Net SOM (DNSOM) is proposed via the merging of two 2-D SOMs to overcome the issues. Three data sets (cube, sphere, and talus bone) with different grid sizes are applied to test the models. When the grid size of all the models increases, the surface becomes smoother. The DNSOM contains a lower quantisation error than the 2-D SOM and the lowest topographic error among the other SOM models. It performs faster than the 3-D SOM and CKSOM. It presents the correct closed surface with a smaller number of neurons and different grid sizes. Microsoft Visual Studio 2022 with the C++ programming language is used to develop the models, while GNUPlot is used to visualise the results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Go-X: Gain Ratio and Optuna Driven Optimization for Extreme Gradient Boosting (Xgboost) in Malware Detection

SSRN

引用

SSRN 2025年

作者： Rizal, Randi Fadilah, Haris Fikri Selamat, Siti Rahayu Rahmatulloh, Alam Bramantoro, Arif Department of Informatics Faculty of Engineering Universitas Siliwangi Tasikmalaya Indonesia Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka Malaysia School of Computing and Informatics Universiti Teknologi Brunei Brunei Universitas Negeri Yogyakarta Indonesia

The rapid expansion of the Internet of Things (IoT) has revolutionized industries by enabling seamless connectivity and automation, yet it has also exposed critical vulnerabilities to cyberattacks. IoT devices, often lacking robust security mechanisms, present easy targets for hackers, and their interconnected nature amplifies the risks of malware proliferation, potentially disrupting entire networks. To address these issues, this research aims to develop an eXtreme Gradient Boosting (XGBoost) algorithm integrated with Gain Ratio for feature selection and Optuna for hyperparameter optimization. This approach focuses on improving malware detection accuracy while reducing computational overhead by prioritizing the most relevant features and fine-tuning model configurations. The research method used is experimental research with several stages, starting from data collection, model design, model optimization, and finally model evaluation. The experiments showed that using Gain Ratio reduced model execution time by 5 seconds and Optuna optimization time by 1899.33 seconds. The final model achieved outstanding performance, with precision, recall, accuracy, and F1-score all at 99.99%. When compared to previous research using the same dataset, this model outperformed with an accuracy improvement of 5.99%. This research demonstrates the effectiveness of feature selection in reducing Optuna optimization time and highlights the successful implementation of the XGBoost model. While the model achieves good accuracy and reduces execution time slightly, it remains resource-intensive, making it more suitable for deployment on edge servers rather than direct integration into IoT devices. Future research should explore methods to reduce resource requirements, such as implementing quantization techniques or utilizing lighter models like LightGBM. © 2025, The Authors. All rights reserved.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

SEAFL: Enhancing Efficiency in Semi-Asynchronous Federated Learning through Adaptive Aggregation and Selective Training

arXiv

引用

arXiv 2025年

作者： Islam, Md Sirajul Panta, Sanjeev Xu, Fei Yuan, Xu Chen, Li Tzeng, Nian-Feng School of Computing and Informatics University of Louisiana Lafayette United States School of Computer Science and Technology East China Normal University China Department of Computer and Information Sciences University of Delaware United States

Federated Learning (FL) is a promising distributed machine learning framework that allows collaborative learning of a global model across decentralized devices without uploading their local data. However, in real-world FL scenarios, the conventional synchronous FL mechanism suffers from inefficient training caused by slow-speed devices, commonly known as stragglers, especially in heterogeneous communication environments. Though asynchronous FL effectively tackles the efficiency challenge, it induces substantial system overheads and model degradation. Striking for a balance, semi-asynchronous FL has gained increasing attention, while still suffering from the open challenge of stale models, where newly arrived updates are calculated based on outdated weights that easily hurt the convergence of the global model. In this paper, we present SEAFL, a novel FL framework designed to mitigate both the straggler and the stale model challenges in semi-asynchronous FL. SEAFL dynamically assigns weights to uploaded models during aggregation based on their staleness and importance to the current global model. We theoretically analyze the convergence rate of SEAFL and further enhance the training efficiency with an extended variant that allows partial training on slower devices, enabling them to contribute to global aggregation while reducing excessive waiting times. We evaluate the effectiveness of SEAFL through extensive experiments on three benchmark datasets. The experimental results demonstrate that SEAFL outperforms its closest counterpart by up to ∼22% in terms of the wall-clock training time required to achieve target accuracy. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

MVideoRec: Micro Video Recommendations through Modality Decomposition and Contrastive Learning

引用

ACM Transactions on Information Systems 2025年第3期43卷 1-27页

作者： Yu, Li Hu, Jianyong Du, Qihan Niu, Xi School of Information Renmin University of China Beijing China Suzhou Key Laboratory of Artificial Intelligence and Social Governance Technology Suzhou China College of Computing and Informatics The University of North Carolina at Charlotte CharlotteNC United States

Personalized micro video recommendation aims to recommend the micro videos tailored to user preference based on the user’s interaction history with the micro videos, which has drawn increasing attention from both the academic and industrial communities. Existing solutions primarily concentrate on video-level interactions between users and micro videos to model their preferences, and cannot distinguish the finer-grained users’ interactions with various modalities. Ignoring modality-level interactions prevents the full understanding of the user’s true and subtle preferences on micro videos. To this end, in this article, we propose a Contrastive Multimodal Interaction Graph Learning (MVideoRec) model to automatically and explicitly learn the modality-level interaction between users and micro videos for recommendations. Specifically, we designed a graph structure learning module with a sparsification strategy to infer modality-level interaction graph, which will be dynamically and iteratively updated based on the node representations obtained from the node representation learning module. Furthermore, to address the lack of ground truth labels, we propose to generate teacher view from video-level interaction graph and student view from modality-level interaction graph, as well as construct intra-modality and inter-modality contrastive pairwise instances to provide self-supervised signals. Extensive experiments on three real-world micro video datasets validate the effectiveness of MVideoRec. © 2025 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generative AI, IoT, and blockchain in healthcare: application, issues, and solutions

引用

Discover Internet of Things 2025年第1期5卷 1-23页

作者： Mazhar, Tehseen khan, Sunawar Shahzad, Tariq khan, Muhammad Amir Saeed, Mamoon M. Awotunde, Joseph Bamidele Hamam, Habib School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Science International Islamic University Islamabad44000 Pakistan Department of Computer Science COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia Sana’a Yemen Department of Computer Science Faculty of Communication and Information Sciences University of Ilorin Ilorin Nigeria Faculty of Engineering Uni de Moncton MonctonNBE1A3E9 Canada Department of Computer Science and Information Technology School Education Department Government of Punjab 31200 Layyah Pakistan School of Electrical Engineering University of Johannesburg Johannesburg2006 South Africa Av. Grandes Ecoles LibrevilleBP 1989 Gabon Bridges for Academic Excellence Spectrum Tunis Tunisia

This article discusses Blockchain and Generative AI in healthcare, including their uses, difficulties, and solutions. Blockchain technology improves EHR security, privacy, and interoperability, while smart contracts streamline supply chain management and administrative procedures. Blockchain verifies and secures IoT data, improving medical care and treatment, according to case studies. Generative AI systems like ChatGPT have transformed healthcare by personalizing therapy, diagnostics, and predictive analytics. AI systems can examine massive databases to diagnose diseases early, anticipate dangers, and personalize therapies. By providing timely information, boosting treatment adherence, and giving continuous support, AI-powered virtual health assistants have enhanced patient involvement. Generative AI has additionally enhanced medical research and drug development, cutting the time and expense of introducing new medicines. Generative AI and Blockchain provide safe patient data storage, high-quality AI training datasets, and efficient healthcare operations. Scalability, energy usage, and interoperability issues remain. Scalable Blockchain designs and standardized data integration and exchange protocols are suggested by this study. These technologies could improve medical research and therapy by making them safer, more effective, and more individualized. © The Author(s) 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

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

作者： Gao, Shihao Li, Caoshuo Mao, Cunli Zhang, Xulong Qu, Xiaoyang Jin, Taisong Wang, Jianzong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China Ping An Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350368741

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph's semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches. © 2025 IEEE.

关键词： Contrastive learning Graph representation Self-supervised learning

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：