检索结果-内蒙古大学图书馆

Multi-Feature Fusion-Based Speech Disorder Classification Using MobileNetV3-EfficientNetB7, Linformer-Performer, and SHAP-Aware XGBoost

引用

IEEE Access 2025年 13卷 83348-83360页

作者： Sait, Abdul Rahaman Wahab Sankaranarayanan, Suresh Gouthaman, P. King Faisal University Center of Documentation and Administrative Communication Department of Archives and Communication Al-Ahsa Al Hofuf31982 Saudi Arabia Department of Computer Science Al-Ahsa Al Hofuf31982 Saudi Arabia SRM Institute of Science and Technology Faculty of Engineering & Technology Department of Networking and Communications Kattankulathur Chennai603203 India

Traditional speech disorders (SD) detection relies on subjective analysis, resulting in inconsistent outcome. Direct voice classification lacks effective approaches to capture temporal dependencies. Machine learning (ML) models face challenges in extracting the complex temporal and spectral variations in speech signals. Advanced deep learning (DL) and transfer learning techniques offer a foundation for early screening of SD. However, the lack of interpretability reduces the generalization capabilities of these models. Addressing these shortcomings is essential in order to improve the accuracy of SD detection and clinical trustworthiness. Thus, the proposed study introduces a novel image-based SD classification model to classify healthy and pathological speech with high accuracy and robustness. The raw speech signals are transformed into Mel-Spectrograms to overcome the limitations of direct voice classification. To facilitate the model’s interpretability, the statistical and handcrafted acoustic features are extracted from the raw speech signals. Hybrid MobileNet V3-EfficientNet B7and Linformer-Performer are employed to extract diverse features from the Mel-Spectrograms. An attention-based feature fusion is used to identify critical features indicating the SD patterns from the extracted features. The XGBoost classifier is optimized using Bayesian Optimization and HyperBand (BOHB) to classify the healthy and pathological speech. SHapley Additive exPlanations (SHAP) values is employed to offer valuable insights into the model’s decisions. The proposed model obtains an exceptional performance on two benchmark datasets. On the Saarbruecken Voice Database (SVD), it achieves an accuracy of 98.1% with loss of 0.13. It yields a remarkable generalization accuracy of 98.2% on the VOICE dataset, outperforming the state-of-the-art models. In addition, it contributes a significant advancement in SD detection, setting the stage for future research endeavors. © 2013 IEEE.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

The Role of Generative AI in Deepfake Detection: A Systematic Literature Review

The Role of Generative AI in Deepfake Detection: A Systemati...

引用

International Conference on Smart Business and technology, ICSBT 2024

作者： Acim, Btissam Kharmoum, Nassim Lagmiri, Souad Najoua Ziti, Soumia Department of Computer Science Intelligent Processing & Security of Systems Faculty of Sciences Mohammed V University in Rabat Rabat Morocco Rabat Morocco IT Networking Security and Management Laboratory Higher Institute of Management Administration and Computer Engineering Rabat Morocco

ISBN: (纸本)9783031866975

There is a possibility that deepfakes will increase a great deal of false information in a very realistic way, but it seems that today such technology appears to be extremely dangerous. While generative Artificial Intelligence (AI) does expand possibilities and give an opportunity to achieve terrific outcomes and has innumerable potential uses. This systematic literature review focuses on the role of generative AI in the improvement of deepfake detection technologies, providing a comparison between different methods and assessing their effectiveness. By analyzing recent studies, it depicts the techniques employed most frequently in deepfake detection, such as the ones concentrating on the intricacies between the visual and auditory elements, the temporal domains, as well as any minor signs of alteration. Due to the fact that generative AI is rapidly improving, the methods that are used to detect its use are often inadequate, which calls for more studies on the subject matter. Besides, by combining audio and visual elements when performing the analysis, calling it as a method that can be useful in focusing the detection growth potential with diverse and unstructured data. Also, this study evaluates the advantages and limitations of the techniques existing today and demonstrates their relative effectiveness in controlled and real conditions. Clarifying that measures aimed at detecting AI generated content should be preoccupied with a technique that is able to keep pace with changes in generative AI. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Energy-Free Sensing and Context Recognition Using Photovoltaic Cells

引用

IEEE Sensors Journal 2025年第9期25卷 15598-15611页

作者： Shintani, Kaede Rizk, Hamada Yamaguchi, Hirozumi Osaka University Graduate School of Information Science and Technology Department of Information Networking Suita565-0871 Japan Tanta University Tanta31733 Egypt RIKEN Center for Computational Science Kobe650-0047 Japan RIKEN Center for Computational Science Department of Computer and Control Engineering Kobe650-0047 Japan

The field of energy-free sensing and context recognition has recently gained significant attention as it allows operating systems without external power sources. Photovoltaic cells can convert light energy into electrical energy to power sensing devices, but their power may not be sufficient to ensure energy-free sensing due to the varying power needs of sensors and high computational demands. In this article, we propose the use of photovoltaic cells as a standalone sensor for the recognition of different contexts, including user identification, step counting, and location tracking. The system utilizes the photocurrent readings generated by the photovoltaic cells to capture the unique mobility patterns of different users. By analyzing these patterns, the system can accurately identify the user, count the number of steps taken, and track the user’s location. We propose a computationally efficient dynamic time warping (DTW) to match the variable length sequences of photocurrent readings to a database of known patterns and identify the closest subject and location matches. The system was rigorously evaluated in a realistic environment, and the results indicate that it can accurately estimate step count, identify subjects, and localize them with an accuracy of 88%, 90%, and 43 cm, respectively. This is achieved while the proposed system is nonintrusive and can operate without external power sources, making it a promising technology for energy-free sensing and context recognition. © 2001-2012 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration 31

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Chen, Yuzong Abouelhamayed, Ahmed F. Dai, Xilai Wang, Yang Andronic, Marta Constantinides, George A. Abdelfattah, Mohamed S. Cornell University Computer Systems Lab United States Systems and Networking Research Group Microsoft Research United States Imperial College London Department of Electrical and Electronic Engineering United Kingdom

ISBN: (纸本)9798331506476

Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of LLMs through BitMoD1, an algorithm-hardware co-design solution that enables efficient LLM acceleration at low weight precision. On the algorithm side, BitMoD introduces fine-grained data type adaptation that uses a different numerical data type to quantize a group of (e.g., 128) weights. Through the careful design of these new data types, BitMoD is able to quantize LLM weights to very low precision (e.g., 4 bits and 3 bits) while maintaining high accuracy. On the hardware side, BitMoD employs a bitserial processing element to easily support multiple numerical precisions and data types;our hardware design includes two key innovations: First, it employs a unified representation to process different weight data types, thus reducing the hardware cost. Second, it adopts a bit-serial dequantization unit to rescale the per-group partial sum with minimal hardware overhead. Our evaluation on six representative LLMs demonstrates that BitMoD significantly outperforms state-of-the-art LLM quantization and acceleration methods. For discriminative tasks, BitMoD can quantize LLM weights to 4 -bit with © 2025 IEEE.

关键词： Integrated circuit design

来源：评论

学校读者我要写书评

暂无评论

Decentralized Unlearning for Trustworthy AI-Generated Content (AIGC) Services

引用

IEEE Network 2025年第3期39卷 285-292页

作者： Lin, Yijing Du, Hongyang Gao, Zhipeng Yao, Jing Jiang, Bingting Niyato, Dusit Li, Ruidong Zhang, Ping Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong Central South University School of Computer Science and Engineering Changsha410083 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore Kanazawa University Institute of Science and Engineering Kanazawa920-1192 Japan

The widespread adoption of AI-Generated Content (AIGC) has captured remarkable interests from academia and industry. However, this advancement brings forth challenges in data ownership, as emphasized by the General Data Protection Regulation’s right to be forgotten. The right to be forgotten allows participants to erase their data contributions from well-trained AIGC models. Training AIGC models demands an extensive amount of data and computations, often surpassing the capabilities of individual participants. As a solution, Federated Learning (FL) is employed to collaboratively train an AIGC model without sharing raw data directly. To protect the right to be forgotten in FL, "federated unlearning" has been introduced to eradicate the data contributions of unlearning participants from fully trained AIGC models, achieved by deleting historical model updates. However, given that historical updates are distributed among various participants, they may still hold contributions from the unlearning participants. This presents a challenge to the trustworthiness of federated unlearning. In this paper, we first provide an overview of both centralized and federated learning and unlearning methods. We survey relevant works and classify four main categories for federated unlearning. Subsequently, we introduce a comprehensive decentralized unlearning architecture designed for trustworthy AIGC services. To address the challenge of participants retaining historical contributions from unlearning participants, we integrate a coded computing-based interaction mechanism, ensuring both scalability and security. We further present a case study using NanoGPT to demonstrate the effectiveness of the proposed framework for decentralized unlearning. We conclude by identifying potential future research directions. © 1986-2012 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Edge-Driven Industrial Computing Power Networks: Digital Twin-Empowered Service Provisioning by Hybrid Soft Actor-Critic

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8095-8109页

作者： Zhang, Long Song, Deng-Ao Zhang, Hongliang Tian, Ni Zhuang, Zirui Niyato, Dusit Han, Zhu Hebei University of Engineering School of Information and Electrical Engineering Handan056038 China Peking University State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University College of Computing and Data Science 639798 Singapore University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

With the proliferation of data-intensive industrial applications, the collaboration of computing powers among standalone edge servers is vital to provision such services for smart devices. In this paper, we propose an edge-driven industrial computing power network (CPN) by orchestrating the computing and network resources of edge servers through the centralized resource scheduling and decentralized task computing. However, efficient task offloading and collaborative processing is challenging, which requires higher degrees of network automation and intelligence. Therefore, we incorporate digital twins (DTs) into the edge-driven CPN architecture, where the DTs are created as the digital replicas to assist both the computation offloading and collaborative processing. A joint optimization problem of the computing power assignment, service association, task partition, and transmit power control is formulated for maximizing the system average weighted utility. Due to the temporal-spatial variability of tasks and the resulted dynamic environment, we transform the original problem as a Markov decision process aiming at maximizing the long-term average weighted utility. To efficiently handle the high-dimensional discrete-continuous action space, a hybrid soft actor-critic based deep reinforcement learning algorithm is developed for optimizing the joint design. Simulation results validate the superiority of our proposed algorithm over the benchmarks, showing the significant gains obtained by integrating DTs into the edge-driven CPN. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Detecting the symptoms of COVID-19 during pandemic environment using smart spectacle thermal images and deep capsule networks

引用

Multimedia Tools and Applications 2025年第8期84卷 4475-4501页

作者： Dwarakanath, B. Pandimurugan, V. Mohandas, R. Sambath, M. Baiju, B.V. Chinnasamy, A. SRM Institute of Science and Technology Ramapuram Chennai India Networking and Communications School of Computing SRMIST kattankulathur Chennai India Computational Intelligence School of Computing SRMIST kattankulathur Chennai India Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Data Science and Business Systems School of Computing SRMIST kattankulathur Chennai India

The pandemic creates a more complicated providence of medical assistance and diagnosis procedures. In the world, Covid-19, Severe Acute Respiratory Syndrome Coronavirus-2 (SARS Cov-2), and plague are widely known pandemic disease desperations. Due to the recent COVID-19 pandemic tragedies, various medical diagnosis models and intelligent computing solutions are proposed for medical applications. In this era of computer-based medical environment, conventional clinical solutions are surpassed by many Machine Learning and Deep Learning-based COVID-19 diagnosis models. Anyhow, many existing models are developing lab-based diagnosis environments. Notably, the Gated Recurrent Unit-based Respiratory Data Analysis (GRU-RE), Intelligent Unmanned Aerial Vehicle-based Covid Data Analysis (Thermal Images) (I-UVAC), and Convolutional Neural Network-based computer Tomography Image Analysis (CNN-CT) are enriched with lightweight image data analysis techniques for obtaining mass pandemic data at real-time conditions. However, the existing models directly deal with bulk images (thermal data and respiratory data) to diagnose the symptoms of COVID-19. Against these works, the proposed spectacle thermal image data analysis model creates an easy and effective way of disease diagnosis deployment strategies. Particularly, the mass detection of disease symptoms needs a more lightweight equipment setup. In this proposed model, each patient's thermal data is collected via the spectacles of medical staff, and the data are analyzed with the help of a complex set of capsule network functions. Comparatively, the conventional capsule network functions are enriched in this proposed model using adequate sampling and data reduction solutions. In this way, the proposed model works effectively for mass thermal data diagnosis applications. In the experimental platform, the proposed and existing models are analyzed in various dimensions (metrics). The comparative results obtained in the experiments just

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Multi-Controller Architecture Design and Features in Software - Defined networking (SDN) 6

Multi-Controller Architecture Design and Features in Softwar...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Prabhu, V. Balamurugan, P. Department of Computer Science and Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603 203 India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603 203 India

ISBN: (纸本)9798331522667

networking paradigm known as "Software-Defined networking" (SDN) offers more flexibility with network management and is fast gaining popularity. Separating the control plane from the data plane is largely responsible for this success. In SDN-enabled networks, a centralized controller is used to translate high-level network application requirements into low-level directives that are issued to the forwarding devices. Such the controller requires limited ability to react to the request for flow processing generated by forwarding devices. Whenever an SDN-enabled network expands in terms of size or as a network traffic rises, flow processing demands can’t be able to fulfill by a single centralized controller. This causes a controller's performance to decline, which eventually results in a malfunctioning SDN-enabled network. Implementing a multi-controller architecture, in which a number of controllers cooperate to manage a sizable amount of network traffic and flow processing requirements, would be a successful strategy. The introduction of a multi-controller architecture and a consideration of the problems with its scalability, coherence as well as accessibility make up the core contribution of this study. Additionally, it identifies areas where study in this area could still be done. © 2025 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

Detection of Perfect Stealthy Attacks on Cyber-Physical Systems Subject to Measurement Quantizations: A Watermark-Based Strategy

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 114-125页

作者： Yu-Ang Wang Zidong Wang Lei Zou Bo Shen Hongli Dong the College of Information Science and Technology Donghua University the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education IEEE the College of Electrical Engineering and Automation Shandong University of Science and Technology the Department of Computer Science Brunel University London Uxbridge the Sanya Offshore Oil and Gas Research Institute Northeast Petroleum University the Artificial Intelligence Energy Research Institute Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University

In this paper, the attack detection problem is investigated for a class of closed-loop systems subjected to unknownbutbounded noises in the presence of stealthy attacks. The measurement outputs from the sensors are quantized before transmission.A specific type of perfect stealthy attack, which meets certain rather stringent conditions, is taken into account. Such attacks could be injected by adversaries into both the sensor-toestimator and controller-to-actuator channels, with the aim of disrupting the normal data flow. For the purpose of defending against these perfect stealthy attacks, a novel scheme based on watermarks is developed. This scheme includes the injection of watermarks(applied to data prior to quantization) and the recovery of data(implemented before the data reaches the estimator).The watermark-based scheme is designed to be both timevarying and hidden from adversaries through incorporating a time-varying and bounded watermark signal. Subsequently, a watermark-based attack detection strategy is proposed which thoroughly considers the characteristics of perfect stealthy attacks,thereby ensuring that an alarm is activated upon the occurrence of such attacks. An example is provided to demonstrate the efficacy of the proposed mechanism for detecting attacks.

关键词： Attack detection cyber-physical systems (CPSs) perfect stealthy attacks watermark-based strategy

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：