检索结果-内蒙古大学图书馆

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

作者： Chandrasekaran, R. Vijayaraj, S. Balakumaran, M. Arul Stephen, C. Abhijjit, D. Soundarya, M.K. Vels Institute of Science Technology & Advanced Studies Department of Biomedical Engineering Chennai India Vels Institute of Science Technology & Advanced Studies Department of Electrical and Electronics Engineering Chennai India Vels Institute of Science Technology & Advanced Studies Department of Electronics and Communication Engineering Chennai India Vels Institute of Science Technology & Advanced Studies Department of Civil Engineering Chennai India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523923

The Interactive Sign Language Learning System is a ground breaking application designed to provide a comprehensive and interactive learning experience for sign language alphabet and word recognition. Built on advanced technologies, this system aims to bridge the gap between individuals with hearing impairments and non-sign language users, enabling effective communication and inclusion. The application offers a user-friendly interface, where learners can easily navigate through various sign language alphabets and individual words, receiving real-time visual feedback and guidance. With a vast library of sign language gestures and clear video demonstrations, learners can practice their signing skills with confidence and accuracy. The system utilizes computer vision and machine learning algorithms to recognize and interpret users' sign language gestures, providing immediate feedback to ensure proper hand movements and positioning. Additionally, the system offers interactive exercises and quizzes, allowing learners to test their knowledge and track their progress over time. The application also incorporates gaming elements, making the learning process engaging and enjoyable. Whether used by individuals wanting to learn sign language or organizations looking to enhance accessibility, this comprehensive learning system is an invaluable tool that empowers users to communicate effectively and inclusively with the deaf community. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Cyber Attack Detection Using Deep Multi-agent Reinforcement Learning with Beth Dataset

引用

SN Computer Science 2025年第5期6卷 1-16页

作者： Manikandan, A. Rajan, S. Deepa Department of Computer Science and Engineering Vels Institute of Science Technology and Advanced Studies VISTAS Tamil Nadu Chennai India

The Internet of Things (IoT) transforms connectivity, enabling devices to share data seamlessly via the cloud or wireless networks. However, IoT systems remain vulnerable to sophisticated cyberattacks, and traditional detection methods often fail due to inadequate fine-tuning and ineffective feature extraction. This study addresses these challenges by proposing a novel cyberattack detection framework based on deep multi-agent reinforcement learning (MARL). The framework employs the deep deterministic policy gradient (DDPG) algorithm to enhance the adaptive capabilities of multiple agents within an IoT network environment. A newly curated dataset, BETH, is introduced, encompassing diverse cyberattack scenarios specifically designed for training and evaluating MARL-based systems. Through deep reinforcement learning, the framework autonomously learns to detect and mitigate known and emerging threats. To assess the robustness and generalizability of the proposed model, a fivefold cross-validation process was conducted. Experimental results reveal that the proposed approach achieves an exceptional detection accuracy of 99.95%, demonstrating its ability to adapt to dynamic attack patterns while minimizing error rates. The findings highlight the framework’s potential to improve network security significantly, advancing the field of intelligent, autonomous cyber defence for IoT systems. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anomaly detection agents (ADA) BETH dataset Collaboration and communication buffer (CCB) Cyber-attack detection Deep deterministic policy gradient algorithm Internet of Things (IoT) Intrusion detection agents (IDA) Multi-agent reinforcement learning (MARL)

来源：评论

学校读者我要写书评

暂无评论

Convolutional and Graph Neural Networks for the prediction of Papulosquamous Diseases (PSDs) 3

Convolutional and Graph Neural Networks for the prediction o...

引用

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

作者： Nagarajan, G. Raaza, Arun Vels Institute of Science Technology and Advanced Studies Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

The precise identification of papulosquamous diseases (PSDs), including psoriasis and seborrheic dermatitis, is a challenge for dermatologists due to their complicated and heterogeneous clinical presentations. In the discipline of dermatology, artificial intelligence (AI) has recently made major advancements in image classification and malignancy prediction. Deep learning is becoming increasingly popular for treating a variety of diseases. This study proposes a CNN (Convolutional Neural Networks)+GNN (Graph Neural Networks) architecture and evaluates and compares the performance of multiple deep learning models, including LSTM (Long Short-Term Memory), Autoencoders (AEs), and Recurrent Neural Networks (RNNs), for the automatic categorization of Papulosquamous Diseases(PSDs).. A hybrid strategy combining CNN and GNN was selected as the most efficient model, achieving the maximum performance across all measures with 93% accuracy, 92% precision, 94% recall, and 93% F1-Score. © 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

Intelligent computational ensemble model for predicting cerebral aneurysm using the concept of region localization in multi-section CT angiography

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 1957-1963页

作者： Khan, Zabiha Kanna, R. Kishore Parthasarathy, K. Vijayaraj, S. Chandrasekaran, R. Jawla, Shashi Nitte Meenakshi Institute of Technology Bengaluru India Department of Biomedical Engineering Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Tamil Nadu Chennai India Electrical and Electronics Engineering Indian Naval Academy Kannur India Electrical and Electronics Engineering Vels Institute of Science Technology & Advanced Studies Tamil Nadu Chennai India Biomedical Engineering Vels Institute of Science Technology & Advanced Studies Tamil Nadu Chennai India Swami Vivekanand Institute of Engineering and Technology Banur Chandigarh India

Intracranial aneurysms and hemorrhage, also known as cerebral or brain aneurysms, are abnormal bulges or ballooning in the walls of blood vessels in the brain. When intracranial aneurysm leaks or ruptures, it results in bleeding within the brain, referred to as a hemorrhagic stroke. Multi-section computed tomography angiography (CTA) data is used to study because it is an effective technique for identifying cerebral atherosclerosis, arterial and intracranial hemorrhage. The hybrid model RID_Net is proposed that integrates ResNet15, InceptionV3, and DenseNet201 architectures in collectively, optimizing for precision through individual efficacy testing of each model. This ensemble model enhances feature extraction and classification performance, demonstrating the effectiveness of combining multiple transfer learning paradigms in biomedical image analysis. The performance is validated by comparing the proposed model with existing studies based on metrics such as accuracy (%), precision (%), recall (%) and f1-score (%). © Bharati Vidyapeeth's institute of Computer Applications and Management 2024.

关键词： Computed tomography angiography (CTA) Densenet201 Intracranial aneurysms (IA) Intracranial hemorrhage (IH) RID_Net Stochastic gradient descent (SGD)

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Detection System of Autism Spectrum Disorder Using Thermal Imaging and Deep Learning

引用

SN Computer Science 2025年第2期6卷 1-11页

作者： Jegan Amarnath, J. Meera, S. Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Pallavaram Tamil Nadu Chennai 600117 India

Autism Spectrum Disorder (ASD) is a brain-based condition characterized by social difficulties and repetitive behaviors. Traditional diagnostic methods can be subjective and time-consuming. Current diagnostic techniques for ASD often rely on behavioral assessments and clinical observations, which can be inconsistent and prone to subjectivity. Additionally, there is a need for more reliable and objective methods to differentiate between autistic and non-autistic individuals. Existing imaging techniques require further refinement to improve accuracy and efficiency in detecting ASD. The primary objective of this research is to develop and evaluate an enhanced detection system for ASD using thermal imaging and Improved Mask Faster Recurrent Convolutional Neural Network (IMFRCNN). This research focuses on enhancing the detection of ASD using Deep Learning (DL) methods and thermal imaging. Traditional diagnostic techniques for ASD often rely on subjective behavioral assessments, highlighting the need for more reliable methods. By examining cerebral imaging data from the thermal face image datasets collect facial thermal images using thermal cameras. Ensure the dataset is diverse, including varying expressions and environmental conditions. The study compares the effectiveness of IMFRCNN and the ResNet 50 system in classifying thermal images of 50 autistic and 50 non-autistic individuals. Emotions were evoked using audio-visual stimuli, and temperature variations in facial areas such as the nose, forehead, cheek, and eyes were measured. Anger showed the greatest temperature differences, with a 12.6% variation between autistic and non-autistic individuals. The IMFRCNN achieved a reliability of 96%, while the ResNet 50 achieved 90%. These findings indicate that computer-aided assessment techniques utilizing thermal imaging and DL can provide a consistent and objective method for identifying individuals with ASD. © The Author(s), under exclusive licence to Springer Nature Sing

关键词： Deep learning algorithms Diagnostic tool Improved mask faster recurrent convolutional neural network Performance measures

来源：评论

学校读者我要写书评

暂无评论

Advancing Object Discovery: Unveiling the Power of YOLO in Computer Vision Applications 6th

Advancing Object Discovery: Unveiling the Power of YOLO in C...

引用

6th International Conference on Intelligent Communication, Control and Devices, ICICCD 2024

作者： Vijayalakshmi, A. Ebenezer Abishek, B. Arul Stephen, C. Mohith, K. Sri Niranjan Raja, C.A. Department of Electronics and Communication Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Electronics and Communication Engineering KCG College of Technology Chennai India

ISBN: (纸本)9789819783281

The practical implementations and technological advances of the YOLO method in computer vision for object detection are examined in this article. Santosh Divvala and Joseph Redmon’s YOLO artificial intelligence system can accurately and quickly detect objects in videos and images, eliminating the need for network iterations. Instead of using traditional methods, YOLO directly generates bounding boxes and class probabilities for each object, optimising the procedure. After reading this, the process is clearer. This study examines YOLO’s effectiveness in various situations. This technology has many applications in industrial automation, AR/VR, autonomous vehicles, healthcare, and retail. This article examines YOLO model training and data preparation. COCO datasets are used in this study. The architectural components of YOLO versions 7 and 8 are also examined. The findings show that YOLO v8 is highly accurate in identifying a wide range of objects in real time. This study shows YOLO’s revolutionary potential as object detection software for BV applications, highlighting its outstanding features. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

Science China(Information Sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models 3

Hyperspectral Images for Crop Prediction using Machine and D...

引用

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

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

In-situ growth of cross-link NiAl-LDH nanosheets on the inner/outer surfaces of carbon microtubes for anti-corrosive electromagnetic wave absorption

引用

Journal of Materials Science and technology 2025年 238卷 109-118页

作者： Liu, Rui Liu, Xiao Wu, Lihong Du, Changlong Lv, Haiming Wan, Gengping Xiong, Hualin Yuan, Xiang Wang, Jieping Wang, Guizhen Institute of Electromagnetic Protection Materials and Spectral Innovation Technology State Key Laboratory of Tropic Ocean Engineering Materials and Materials Evaluation School of Materials Science and Engineering Hainan University Haikou570228 China Center for New Pharmaceutical Development and Testing of Haikou Center for Advanced Studies in Precision Instruments Haikou570228 China Key Laboratory of Pico Electron Microscopy of Hainan Province Center for Advanced Studies in Precision Instruments Haikou570228 China

Electromagnetic wave (EMW) absorbers with anti-corrosion property are highly desired to enhance the durability of military targets in harsh condition. Herein, cross-link NiAl-layered double hydroxide (NiAl-LDH) nanosheets on the inner/outer surfaces of carbon microtubes (CMTs) are ingeniously constructed through the combination of atomic layer deposition technique and a hydrothermal method. The obtained NiAl-LDH/CMT composite exhibits excellent EMW absorption and corrosion resistance performance. The large internal cavity of CMT significantly enhances impedance matching. The uniform distribution of NiAl-LDH nanosheets on both the inner and outer surfaces of CMT generates numerous heterogeneous interfaces that induce substantial polarization loss. Consequently, at a filler rate of only 5 wt.%, the NiAl-LDH/CMT composite exhibits a minimum reflection loss of −60.2 dB and a maximum effective absorption bandwidth of 5.9 GHz. In addition, the combined high impermeability of CMT and the effective Cl−-trapping ability of NiAl-LDH endows NiAl-LDH/CMT composite with outstanding corrosion protection property in simulated seawater environment. Furthermore, the PO43− anions are effectively incorporated into the NiAl-LDH interlayer via anion exchange, which can further enhance corrosion protection capacity through surface inactivation from slow-release PO43− anions without reducing their EMW absorption performance. In summary, this work can give guidance for the development of efficient anti-corrosion EMW absorption materials. © 2025

关键词： Anodic protection

来源：评论

学校读者我要写书评

暂无评论

Hydrothermal pretreatment of food waste enhances performance of anaerobic co-digestion with sludge

引用

Environmental Science and Pollution Research 2025年第9期32卷 5259-5275页

作者： Johnravindar, Davidraj Zhao, Jun Manu, Mathikere Krishnegowda Wong, Jonathan Woon Chung Research Centre for Eco-Environmental Engineering Dongguan University of Technology Guangdong Dongguan523830 China Department of Biology Hong Kong Baptist University Kowloon Tong Hong Kong Department of Nanobiotechnology PSG Institute of Advanced Studies Coimbatore641 004 India

Food waste (FW) presents a significant opportunity for renewable energy production through anaerobic digestion (AD) when subjected to appropriate treatment. This study investigates the impact of thermal hydrolysis pretreatment (THP) on FW at varying temperature levels (90 °C, 120 °C, and 140 °C) prior to mesophilic anaerobic co-digestion with sewage sludge (SS). Results demonstrate enhanced FW hydrolysis at 120 °C, leading to a cumulative methane yield of 324.39 ± 4.5 mL/gVSadd, representing a 41.75% increase over untreated FW (228.83 ± 1.13 mL/gVSadd). Shifts in microbial communities, particularly Methanosarcina, Methanobactrium, and Methanobrevibacter, support efficient methanogenesis. Co-digestion of FW pretreated at 120 °C yields maximum energy production of 11.48 MJ/t, a 49.47% improvement compared to untreated processes. The economic analysis underscores the profitability of co-digestion with FW pretreated at 120 °C. These findings highlight the potential for enhanced methane production and energy conversion efficiency with hydrothermally pretreated FW and SS co-digestion. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Anaerobic digestion

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：