检索结果-内蒙古大学图书馆

9th International Conference on Information, Communication and Computing Technology, ICICCT 2024

作者： Akshaya, M. Joy, Emmanuel Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9783031724824

Parkinson’s disease (PD) is a brain dysfunction condition that affects thousands of people across the globe. Early detection of Parkinson’s disease is crucial for effective treatment and control of symptoms. This study employs a multi-modal methodology coded as ParkinSense that combines spiral drawings, gait analysis, and Magnetic Resonance Imaging (MRI) analysis for timely Parkinson’s disease identification. MRI analysis provides insight into structural and functional changes in the brain, revealing potential anomalies. GAIT analysis assesses alterations in walking patterns, such as reduced arm swing and slow gait velocity. Spiral drawings, serve as a surrogate for motor dexterity and fine motor control, both of which are compromised in Parkinson’s disease. In this study, data from Parkinson’s patients and healthy candidates are collected and analyzed using advanced machine-learning techniques to create models for accurate disease prediction and classification. Specifically, the gait analysis is conducted using a Support Vector Machine and XGBoost algorithm. The spiral drawings are analyzed using a Convolutional Neural Network. The MRI data is processed using a MobileNet-based neural network. These algorithms are integrated to create models for accurate disease prediction and classification. The results demonstrate that this multimodal technique is equipped to identify Parkinson’s disease with an accuracy rate of more than 90%. Early detection using speech analysis, gait analysis, and spiral drawings can lead to earlier intervention and treatment, resulting in a better excellence of life for those affected. This study adds to the expanding body of knowledge about non-invasive, cost-effective approaches for the timely identification of Parkinson’s disease. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Sophia S Getzi Jeba Leelipushpam Paulraj Yuvarajan D Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance; however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. This research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. The proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. The proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios.

关键词： Protocols Heuristic algorithms Clustering algorithms Autonomous aerial vehicles Routing Elliptic curve cryptography Real-time systems Security Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: A Systematic Survey on Implementation of Fuzzy Regression Models for Real Life Applications

引用

Archives of Computational Methods in engineering 2025年 1-2页

作者： Khan, Mufala Kumar, Rakesh Aledaily, Arwa N. Kariri, Elham Viriyasitavat, Wattana Yadav, Kusum Dhiman, Gaurav Kaur, Amandeep Sharma, Ashutosh Vimal, S. Department of Mathematics Lovely Professional University Phagwara India College of Computer Science and Engineering University of Ha’il Hail Saudi Arabia College of Computer Science and Engineering Prince Sattam Bin Abdulaziz University Al‑Kharj Saudi Arabia Business Information Technology Division Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand Department of Computer Science Government Bikram College of Commerce Patiala India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon University Centre for Research and Development Department of Computer Science and Engineering Chandigarh University Gharuan India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajaplayam India

来源：评论

学校读者我要写书评

暂无评论

QMix: Quality-aware Learning with Mixed Noise for Robust Retinal Disease Diagnosis

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Hou, Junlin Xu, Jilan Feng, Rui Chen, Hao Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China HKUST Department of Chemical and Biological Engineering Division of Life Science Hong Kong HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen China

Due to the complex nature of medical image acquisition and annotation, medical datasets inevitably contain noise. This adversely affects the robustness and generalization of deep neural networks. Previous noise learning methods mainly considered noise arising from images being mislabeled, i.e., label noise, assuming all mislabeled images were of high quality. However, medical images can also suffer from severe data quality issues, i.e., data noise, where discriminative visual features for disease diagnosis are missing. In this paper, we propose QMix, a noise learning framework that learns a robust disease diagnosis model under mixed noise scenarios. QMix alternates between sample separation and quality-aware semisupervised training in each epoch. The sample separation phase uses a joint uncertainty-loss criterion to effectively separate (1) correctly labeled images, (2) mislabeled high-quality images, and (3) mislabeled low-quality images. The semi-supervised training phase then learns a robust disease diagnosis model from the separated samples. Specifically, we propose a sample-reweighing loss to mitigate the effect of mislabeled low-quality images during training, and a contrastive enhancement loss to further distinguish them from correctly labeled images. QMix achieved state-of-the-art performance on six public retinal image datasets and exhibited significant improvements in robustness against mixed noise. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Rapid Amplification of Single-Stranded DNA by On-Bead Plasmonic PCR in an Automated Microfluidic System

Rapid Amplification of Single-Stranded DNA by On-Bead Plasmo...

引用

IEEE International Conference on Micro Electro Mechanical Systems

作者： Anni Hu Yang Bu Yuze Liu Yung Ching Lee Levent Yobas Division of Bioengineering The Hong Kong University of Science and Technology Hong Kong Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798331508890

ISBN: (纸本)9798331508906

This paper presents a novel automated microfluidic system for rapid plasmonic on-beads polymerase chain reaction (PCR). The highly integrated system automates essential PCR workflows, including sample loading, thermal cycling, purification washes, and elution utilizing pneumatic valves. Additionally, gold nanorods are introduced into the PCR system to leverage their efficient photothermal conversion properties to accelerate the PCR reaction. The platform completes 20 PCR cycles within 12 minutes to amplify single-stranded DNA (ssDNA), demonstrating potential for various rapid ssDNA PCR applications, such as aptamer selection and generation.

关键词： Gold Purification Loading DNA System integration Plasmons Valves Thermal loading Microfluidics Nanorods

来源：评论

学校读者我要写书评

暂无评论

Weave defect detection in jute manufacturing value chain using artificial intelligence and computer vision

引用

International Journal of System Assurance engineering and Management 2025年 1-9页

作者： Vadivel, S. M. Madhumitha, R. Nair, Yash Aniruddha, P. Manish Mithun, S. P. Sarathy, Yashwanth VIT Business School Operations and Quantitative Techniques Division Vellore Institute of Technology Chennai Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

This study aims to introduce a cutting-edge method for weave defect detection using Artificial intelligence (AI) and computer vision (CV) technologies. By employing a Convolutional neural network (CNN) trained on a comprehensive dataset (Python programming codes mentioned in appendix) of textile images with annotated defects, the system automates the identification and classification of fabric irregularities, such as stains and tears. Testing in an industrial setting has shown that this AI-driven approach significantly outperforms traditional manual inspections, enhancing defect detection accuracy and production efficiency. The research highlights the potential of AI and CV to revolutionize Quality control (QC) processes in jute manufacturing industries and beyond.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shaping Connectivity: Channel Modeling and Performance Analysis of Reconfigurable Intelligent Surfaces for IoV Visible Light Communication

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Eldeeb, Hossien B. Qaraqe, Marwa Muhaidat, Sami Ghrayeb, Ali Tavakkolnia, Iman Haas, Harald University of Cambridge Electrical Engineering Division Department of Engineering Cambridge United Kingdom Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering United Kingdom Qatar Foundation Doha Qatar Khalifa University Computer and Communication Engineering Abu Dhabi United Arab Emirates

This paper presents a promising solution for enhancing the reliability and data rate of Internet-of-vehicles (IoV) visible light communication (VLC) systems through the utilization of optical reconfigurable intelligent surfaces (RISs). The focus is on the infrastructure-to-vehicle (I2V) scenario, where streetlights serve as internet access points. The IoV-VLC system is modeled using an advanced non-sequential raytracing approach. A novel closed-form channel model expression is proposed, incorporating transceiver, RIS, and infrastructure parameters. The proposed model is then validated against broadband raytracing simulation results considering different combinations of system parameters, including, receiver aperture size, streetlight pole height, spacing between the poles, and RIS height. Moreover, based on the derived channel model, the error rate and data rate performances of the system are analyzed. The required numbers of RIS elements allocated to each vehicle's location, to achieve a target error rate and data rate values, are further derived. Finally, this paper demonstrates the impact of various transceiver, RIS, and infrastructure parameters on the system performance. The obtained results reveal that the proposed IoV-VLC system with optimal RIS deployment effectively addresses system outage issues and meets reliability and data speed requirements regardless of the vehicle's location. The results also shed light on the influence of various factors on system performance. Notably, the total number of required RIS elements is significantly affected by factors such as receiver aperture size, space between the poles, and transmit power budget. For instance, when considering the same power budget and error rate target, the required number of RIS elements for spacing distances of 20 m, 22 m, and 24 m are determined as 132, 244, and 428 elements, respectively. Conversely, the impact of pole height is found to be minimal as long as the space between the poles remains

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud

arXiv

引用

arXiv 2025年

作者： Jiang, Junkun Chen, Jie Au, Ho Yin Chen, Mingyuan Xue, Wei Guo, Yike Department of Computer Science Hong Kong Baptist University Hong Kong Division of Emerging Interdisciplinary Areas The Hong Kong University of Science and Technology Hong Kong Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

Multi-person motion capture over sparse angular observations is a challenging problem under interference from both self- and mutual-occlusions. Existing works produce accurate 2D joint detection, however, when these are triangulated and lifted into 3D, available solutions all struggle in selecting the most accurate candidates and associating them to the correct joint type and target identity. As such, in order to fully utilize all accurate 2D joint location information, we propose to independently triangulate between all same-typed 2D joints from all camera views regardless of their target ID, forming the Joint Cloud. Joint Cloud consist of both valid joints lifted from the same joint type and target ID, as well as falsely constructed ones that are from different 2D sources. These redundant and inaccurate candidates are processed over the proposed Joint Cloud Selection and Aggregation Transformer (JCSAT) involving three cascaded encoders which deeply explore the trajectile, skeletal structural, and view-dependent correlations among all 3D point candidates in the cross-embedding space. An Optimal Token Attention Path (OTAP) module is proposed which subsequently selects and aggregates informative features from these redundant observations for the final prediction of human motion. To demonstrate the effectiveness of JCSAT, we build and publish a new multi-person motion capture dataset BUMocap-X with complex interactions and severe occlusions. Comprehensive experiments over the newly presented as well as benchmark datasets validate the effectiveness of the proposed framework, which outperforms all existing state-of-the-art methods, especially under challenging occlusion scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Micro-LED-based quantum random number generators

引用

Optics Express 2025年第11期33卷 22154-22164页

作者： Heming Lin Hang Lu Matthew S Wong Abdullah Almogbel Ahmed Alyamani Tien Khee Ng Osman Bakr Shuji Nakamura Steven P Denbaars Boon S Ooi Photonics Laboratory Electrical and Computer Engineering Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia Solid State Lighting & Energy Electronics Center University of California Santa Barbara California 93106 USA King Abdulaziz City for Science and Technology (KACST) Riyadh 12354 Saudi Arabia Division of Physical Science and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia boon.ooi@kaust.edu.sa

Quantum random number generators (QRNGs) leverage the inherent unpredictability of quantum mechanical phenomena to produce random numbers. However, the performance of many QRNGs is hindered by limitations such as low generation rates and the bulkiness of systems utilizing single-photon detectors (SPDs). In this study, we present a QRNG that addresses these challenges by using a micro-LED as an entropy source, utilizing the intensity fluctuations of spontaneous emissions. By applying post-processing techniques, our 5 × 5 µm 2 micro-LED-based system achieves a PD bandwidth-limited generation rate of 9.375 Gbit/s while successfully passing the required randomness tests outlined by the National Institute of Standards and Technology (NIST). Importantly, systematic testing across micro-LEDs of varying sizes demonstrates consistently high performance, highlighting the robustness of this approach. The compact, small footprint, scalable design, and surface emission characteristics of micro-LEDs pave the way for the development of parallel QRNG-integrated chips, which hold the potential to deliver ultra-high random number generation rates in practical, miniaturized platforms.

关键词： Atomic layer deposition Detectors Quantum communications Quantum computation Quantum key distribution Random number generation

来源：评论

学校读者我要写书评

暂无评论

CPM-Based Tunable Phase-Attached Radar–Communications (PARC)

IEEE Transactions on Radar Systems

引用

IEEE Transactions on Radar Systems 2025年 3卷 520-538页

作者： Sahin, Cenk McCormick, Patrick M. Metcalf, Justin G. Jakabosky, John Blunt, Shannon D. Perrins, Erik S. Owen, Jonathan Johns Hopkins University Applied Physics Laboratory LaurelMD20723 United States The University of Kansas Department of Electrical Engineering and Computer Science LawrenceKS66045 United States The University of Oklahoma Advanced Radar Research Center NormanOK73019 United States Naval Research Laboratory Radar Division WashingtonDC20375 United States

Motivated by the increasing need for efficient use of the electromagnetic spectrum (EMS) in congested and contested environments, a codesigned dual-function radar-communication (DFRC) waveform framework was introduced, which combines the desirable features of a pulsed radar transmission (i.e., constant amplitude and continuous phase) with the ability to embed information in the phase of the waveform via continuous-phase modulation (CPM). This CPM-based phase-attached radar-communication (PARC) waveform operates in a pulse-agile mode, which introduces a coupling of the fast- and slow-time dimensions through what is known as range-sidelobe modulation (RSM). The flexibility of CPM-based PARC via its multiple tunable parameters provides the ability to control this radar performance degradation at the expense of bit error rate (BER) and/or data throughput. Furthermore, the severity of RSM can likewise be mitigated via mismatched filter pulse compression on receive to reduce the variance of the pulse compression responses. Here, we evaluate the radar and communication performance trade space as a function of the CPM-based PARC parameters when assuming both matched and mismatched filter pulse compression at the radar receiver. The efficacy of the CPM-based PARC framework for both radar and communications is experimentally validated in an open-air environment using a radar in a quasi-monostatic configuration and a communication receiver in the field of view of the radar. © 2023 IEEE.

关键词： Matched filters

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：