检索结果-内蒙古大学图书馆

Software, Systems and Information Technology (SSITCON), International Conference on

作者： Tushar Dhar Shukla Diana Vanyan Qaim Mehdi Rizvi Geogen George Aryaraj Dattatraya Bhosale V. Bhoopathy Department of Physical Education University Institute of Physical Education & Sports Chandigarh University Mohali India Kuban State University Krasnodar Russia Department of Computer Science and Engineering (Data Science) Brainware University Kolkata India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Middle East Sultanate of Oman Indian Institute of Information Technology Pune India Department of Computer Science and Engineering Sree Rama Engineering College Tirupathi India

ISBN: (数字)9798350352931

ISBN: (纸本)9798350352948

This study focusses on the crucial matter of identifying student sadness by analysing patterns of cyberactivity. The technology utilizes Heterogeneous Graph Attention Networks (HGATs) to represent and examine intricate connections within the data. The dataset used for training and testing the model was obtained from Kaggle. The model achieved an accuracy of $\mathbf{9 6 . 8 \%}$, a precision of $\mathbf{9 5 . 4 \%}$, a recall of $94.7 \%$, and an AUC-ROC of $98.3 \%$. The findings of this study demonstrate a substantial improvement over current models, indicating the high efficacy of HGATs in accurately capturing complex patterns in cyber-activity data. The results indicate that this method can function as a potent instrument for identifying depression at an early stage, with wide-ranging implications for monitoring the mental health of students and implementing intervention techniques.

关键词： Training Accuracy Instruments Mental health Depression Software systems data models Information technology Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Accelerating convergence of score-based diffusion models, provably 24

Accelerating convergence of score-based diffusion models, pr...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Gen Li Yu Huang Timofey Efimov Yuting Wei Yuejie Chi Yuxin Chen Department of Statistics The Chinese University of Hong Kong Hong Kong Department of Statistics and Data Science Wharton School University of Pennsylvania Philadelphia PA Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh PA

Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. Despite a flurry of recent activities towards speeding up diffusion generative modeling in practice, theoretical underpinnings for acceleration techniques remain severely limited. In this paper, we design novel training-free algorithms to accelerate popular deterministic (i.e., DDIM) and stochastic (i.e., DDPM) samplers. Our accelerated deterministic sampler converges at a rate O(1/T2) with T the number of steps, improving upon the O(1/T) rate for the DDIM sampler; and our accelerated stochastic sampler converges at a rate O(1/T), outperforming the rate O(1/√T) for the DDPM sampler. The design of our algorithms leverages insights from higher-order approximation, and shares similar intuitions as popular highorder ODE solvers like the DPM-Solver-2. Our theory accommodates ℓ2-accurate score estimates, and does not require log-concavity or smoothness on the target distribution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Foundation Models in Electrocardiogram: A Review

arXiv

引用

arXiv 2024年

作者： Han, Yu Liu, Xiaofeng Zhang, Xiang Ding, Cheng University of Chinese Academy of Sciences Beijing China Department of Biomedical Informatics and Data Science Yale University Connecticut United States Department of Computer Science University of North Carolina at Charlotte Charlotte United States Department of Biomedical Engineering Georgia Institute of Technology Atlanta United States

The electrocardiogram (ECG) is ubiquitous across various healthcare domains, such as cardiac arrhythmia detection and sleep monitoring, making ECG analysis critically essential. Traditional deep learning models for ECG are task-specific, with a narrow scope of functionality and limited generalization capabilities. Recently, foundation models (FMs), also known as large pre-training models, have fundamentally reshaped the scheme of model design and representation learning, enhancing the performance across a variety of downstream tasks. This success has drawn interest in the exploration of FMs to address ECG-based medical challenges concurrently. This survey provides a timely, comprehensive and up-to-date overview of FMs for large-scale ECG-FMs. First, we offer a brief background introduction to FMs. Then, we discuss the model architectures, pre-training methods, and adaptation approaches of ECG-FMs from a methodology perspective. Despite the promising opportunities of ECG-FMs, we also outline the challenges and potential future directions. Overall, this survey aims to provide researchers and practitioners with insights into the research of ECG-FMs on theoretical underpinnings, domain-specific applications, and avenues for future exploration. © 2024, CC BY.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Precision and Safety in Minimally Invasive Surgery: The Role of AI and Robotics Integration

Enhanced Precision and Safety in Minimally Invasive Surgery:...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Rani Sunil Kedar Chetan G Puri Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Sawangi Meghe Wardha Maharashtra Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research(DU) Sawangi (Meghe) Wardha Maharashtra

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

A revolutionary development in surgical practice, the incorporation of robotics and artificial intelligence (AI) into minimally invasive surgery (MIS) improves patient outcomes, safety, and precision. This review article examines the development of minimally invasive surgery (MIS) and highlights its notable advantages over open surgery, including shorter recovery periods, less discomfort following surgery, and a decreased rate of complications. The article explores the function of robotic systems, in particular the da Vinci Surgical System, which has transformed surgical operations by giving doctors more dexterity and visualization using robotic arms and high-definition 3D imagery. Additionally, the application of AI technology is explored, demonstrating how it enhances real-time decision-making, intraoperative assistance, and preoperative planning, ultimately improving surgical results. The paper also discusses the ethical and regulatory issues raised by surgical robots' growing autonomy, highlighting the necessity of strong frameworks to guarantee patient safety and fair access to these cutting-edge technologies. This study highlights how artificial intelligence (AI) and robotics have the ability to change the surgical medicine landscape by combining the most recent research and clinical practices. It also calls for continued communication among stakeholders to effectively traverse the complexity of this rapidly developing sector.

关键词： Ethics Visualization Minimally invasive surgery Medical robotics Ubiquitous computing Safety Planning Complexity theory Artificial intelligence Robots

来源：评论

学校读者我要写书评

暂无评论

Modeling Path Importance for E_ective Alzheimer's Disease Drug Repurposing

Modeling Path Importance for E_ective Alzheimer's Disease Dr...

引用

29th Pacific Symposium on Biocomputing, PSB 2024

作者： Xiang, Shunian Lawrence, Patrick J. Peng, Bo Chiang, Chienwei Kim, Dokyoon Shen, Li Ning, Xia Biomedical Informatics Department The Ohio State University ColumbusOH43210 United States Computer Science and Engineering Department The Ohio State University ColumbusOH43210 United States Department of Biostatistics Epidemiology and Informatics University of Pennsylvania PhiladelphiaPA19104 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

ISBN: (纸本)9789811286414

Recently, drug repurposing has emerged as an effective and resource-efficient paradigm for AD drug discovery. Among various methods for drug repurposing, network-based methods have shown promising results as they are capable of leveraging complex networks that integrate multiple interaction types, such as protein-protein interactions, to more effectively identify candidate drugs. However, existing approaches typically assume paths of the same length in the network have equal importance in identifying the therapeutic effect of drugs. Other domains have found that same length paths do not necessarily have the same importance. Thus, relying on this assumption may be deleterious to drug repurposing attempts. In this work, we propose MPI (Modeling Path Importance), a novel network-based method for AD drug repurposing. MPI is unique in that it prioritizes important paths via learned node embeddings, which can effectively capture a networks rich structural information. Thus, leveraging learned embeddings allows MPI to effectively differentiate the importance among paths. We evaluate MPI against a commonly used baseline method that identifies anti-AD drug candidates primarily based on the shortest paths between drugs and AD in the network. We observe that among the top-50 ranked drugs, MPI prioritizes 20.0% more drugs with anti-AD evidence compared to the baseline. Finally, Cox proportional-hazard models produced from insurance claims data aid us in identifying the use of etodolac, nicotine, and BBB-crossing ACE-INHs as having a reduced risk of AD, suggesting such drugs may be viable candidates for repurposing and should be explored further in future studies. © 2023 The Authors.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

From 5G to 6G: The Role of AI, Machine Learning, and Deep Learning in Wireless Systems

From 5G to 6G: The Role of AI, Machine Learning, and Deep Le...

引用

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

作者： Pradnyawant M. Gote Praveen Kumar Prateek Verma Prajyot Yesankar Adesh Pawar Saniya Saratkar Department of Computer Science & Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Department of Computer Science & Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Department of Artificial Intelligence & Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Department of Artificial Intelligence & Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The swift progression of wireless communication technologies-specifically from 5G to 6G is an approach that could be the most significant revolutionary leap towards changing connectivity and data transmission forever. Additionally, algorithms of machine learning (ML) and deep learning (DL) in 5G and 6G can offer promising advancements toward predictive maintenance, dynamic spectrum management, and enhanced security. The review of the potentially transformative nature of these technologies underlines the need for future directions of research efforts called for in circumventing challenges towards making full capability exploitation of 6G possible.

关键词： 6G mobile communication Wireless communication Deep learning Tactile Internet Technological innovation Sentiment analysis 5G mobile communication Reviews Heuristic algorithms Security

来源：评论

学校读者我要写书评

暂无评论

The Influence of Human Factors in Ensuring Cybersecurity in Organizations: Effectiveness of PDPA and GDPR Implementation

The Influence of Human Factors in Ensuring Cybersecurity in ...

引用

Delhi Section Conference (DELCON), IEEE

作者： Ahmad Zia Sharifi Md. Abul Ala Walid Mohammad Dawood Momand Ihsan Ul Haq Safi Hamidullah Khanzai Safi Sadia Hossain Department of Networking and Communication Faculty of Computer Science Nangarhar University Afghanistan Department of Data Science and Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur Bangladesh Lautsprecher Teufel GMbH Berlin Germany Department of Internet of Things and Robotics Engineering Bangabandhu Sheikh Mujibur Rahman Digital University Gazipur Bangladesh

ISBN: (数字)9798331518592

ISBN: (纸本)9798331518608

Modern organizations face rising levels of cyber risks, making cybersecurity a top priority for safeguarding sensitive data and maintaining operational continuity. Recent studies find human factors as the most critical contributors to cyber risks. These human-related risks include user misuse, user mistakes, and user malice. A large proportion of cyber risks arise when hackers use social engineering or phishing techniques to manipulate employees into disclosing confidential information. While some employees knowingly engage in these actions, some incidents occur accidentally due to a lack of awareness about cybersecurity protocols. As a result, governments around the world are enacting data protection legislation aimed at enhancing employees' cyber risk. This study explores the perception of US employees on the effectiveness of data protection legislation in countering cyber threats. It surveyed 30 randomly selected employees from various industries. The results showed that employees perceive data protection legislation as effective in mitigating employeerelated cyber risks.

关键词： Industries Protocols computer hacking Phishing Legislation data protection Human factors computer crime Faces

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Convolutional Neural Network for Wheat Rust Disease Classification

Three-Dimensional Convolutional Neural Network for Wheat Rus...

引用

Distributed Computing and Optimization Techniques (ICDCOT), International Conference on

作者： N Jagadeeshan Y Nagendar Swarnalatha K Kassem Al-Attabi Ramachandra A C Electronics and Communication Engineering Department Mallareddy Engineering College for Women (Autonomous) Hyderabad Telangana India School of Computer Science and Engineering SR University Warangal Telangana India Department of Artificial intelligence and Data Science Maharaja Institute of Technology Thandavapura India The Islamic university Najaf Iraq Department of ECE Nitte Meenakshi Institute of Technology Bengaluru India

In worldwide, the wheat is a significant crop which generates main source of food for numerous peoples. Through, the development of crop productions is vulnerable through various diseases such as bacterial, viral and fungal infections. These type of disease can cause important damage in crops which leads to diminish the yield production and grain quality. This paper proposed a Three-Dimensional Convolutional Neural Network (3D-CNN) for wheat rust disease classification that learns to recognize the pattern and structure of rust disease using convolution filter layers. The CGIAR dataset is used which contains 1486 images and it is pre-processed by gaussian filter which reduces the noise and smoothens the image. Then, the Discrete Wavelet Transform (DWT) is used for feature extraction which works in discrete timespan that outputs in low computational cost. Then, 3D-CNN is used for the classification of wheat rust disease. The performance of 3D-CNN is estimated by accuracy, recall, f1score and precision. The 3D-CNN attains accuracy 99.83%, recall 98.89%, f1score 98.81 % and precision 98.79 % when compared to existing techniques like GNet+FERSPNET-50 and Few-shot learning based EfficientNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative AI Empowered Semantic Feature Multiple Access (SFMA) Over Wireless Networks

arXiv

引用

arXiv 2024年

作者： Wang, Jiaxiang Yang, Yinchao Yang, Zhaohui Huang, Chongwen Chen, Mingzhe Zhang, Zhaoyang Shikh-Bahaei, Mohammad Department of Engineering King’s College London London United Kingdom College of Information Science and Electronic Engineering Zhejiang University Zhejiang Hangzhou310027 China Zhejiang Hangzhou310007 China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States

This paper investigates a novel generative artificial intelligence (GAI) empowered multi-user semantic communication system called semantic feature multiple access (SFMA) for video transmission, which comprises a base station (BS) and paired users. The BS generates and combines semantic information of several frames simultaneously requested by paired users into a signal. Users recover their frames from this combined signal and input the recovered frames into a GAI-based video frame interpolation model to generate the intermediate frame. To optimize transmission rates and temporal gaps between simultaneously transmitted frames, we formulate an optimization problem to maximize the system sum rate while minimizing temporal gaps. We observe that the standard signal-to-interference-plus-noise ratio (SINR) equation does not accurately capture the performance of our semantic communication system. Therefore, we introduce a weight parameter into the SINR equation to better represent the system’s performance. Due to the complexity introduced by the weight parameter’s dependence on transmit power, we propose a three-step solution. First, we develop a user pairing algorithm that pairs two users with the highest preference value, a weighted combination of semantic transmission rate and temporal gap. Second, we optimize inter-group power allocation by formulating an optimization problem that allocates proper transmit power across all user groups to maximize system sum rates while satisfying each user’s minimum rate requirement. Third, we address intra-group power allocation to enhance the performance of each user. Simulation results demonstrate that our method improves transmission rates by up to 24.8%, 45.8%, and 66.1% compared to fixed-power non-orthogonal multiple access (F-NOMA), orthogonal joint source-channel Coding (O-JSCC), and orthogonal frequency division multiple access (OFDMA) schemes, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Monitoring the Student's Entry and Exit Time in the Classroom

Monitoring the Student's Entry and Exit Time in the Classroo...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： S. Usharani K. Vijayaragavan A. Balachandar P. Manju Bala Department of Artificial Intelligence and Machine Learning IFET College of Engineering (An Autonomous Institution) Villupuram India Department of Computer Science and Engineering IFET College of Engineering (An Autonomous Institution) Villupuram India Department of Artificial Intelligence amd Data Science IFET College of Engineering (An Autonomous Institution) Villupuram India

Monitoring the student's entry and exit time into a classroom is a crucial task. This system will be a solution for performing that crucial task. In this system, for face detection and face recognition, two pre-trained models were imported and utilized to create face embeddings for a collection of photographs kept in a file directory. The face embeddings and corresponding labels are then used to train an SVM classifier using the scikit-learn library's SVC class. To detect and recognize the students, the pre-trained face detection and recognition models were loaded using OpenCV's dnn module. Then the saved face embeddings and labels were also loaded using pickle, which was previously generated by a face recognition model. Face detection is performed using a Caffe model trained on the SSD framework, while face recognition is done using OpenFace. The system identifies the student's faces using embeddings that were generated by pre-processing the images and were saved in the face_*** file. It then matches these embeddings to the corresponding labels that were saved in the *** file. Then the input is captured from the webcam and the optical flow analysis is applied to detect motion in the video stream. After that, it initializes the input image with a blurred, grayscale image and sets the starting points for the motion tracking. It then loops over the captured frames, blurs and converts them to grayscale, and uses calcOpticalFlowPyrLK to calculate the new points based on the old ones. If the new points are within a certain range, it draws a line between them on the input image and displays it. If the points move outside a certain threshold, it triggers an event to log the entry or exit of a student from a classroom and appends these details into a text file accordingly. Finally, this text file is sent through email to a specified list of recipients (faculties) on a daily basis.

关键词：

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：