检索结果-内蒙古大学图书馆

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Tripathi, Tripti Kumar, Rakesh Mmmut Dept. of Computer Science and Engineering Gorakhpur India

ISBN: (纸本)9798350383522

Alzheimer's disease (AD) is a type of neurological disorder that progresses over a period and affects a significant number of people worldwide. Early detection of AD is necessary for rapid intervention and improved outcomes for patients. In this paper, we compare the performance of four widely used Deep Convolutional Neural Network (DCNN) architectures: CNN, VGG16, InceptionV3, and DenseNet121. The study focuses on the use of DCNNs for AD identification. Our dataset is collected from the Kaggle website and preprocessed such that the inputs are identical for every model. Several criteria are used to assess the DCNN architecture's performance, including recall, accuracy, precision, and f1-score. By looking at individual architecture's predictive capabilities, we may discover further the benefits and drawbacks of AD detection jobs. Also, transfer learning techniques employ pre-trained weights from large neuroimaging datasets to enhance model performance and generalization abilities. This study contributes to the increasing body of knowledge in AD research by identifying the ideal DCNN architecture for fast and accurate AD diagnosis. © 2024 IEEE.

关键词： AD detection Alzheimer's disease CNN computational efficiency Deep Convolutional Neural Networks DenseNet121 InceptionV3 performance evaluation transfer learning VGG16

来源：评论

学校读者我要写书评

暂无评论

Identifying Influential Users in Social Networks with an Extended Hybrid Global Structure Model 10

Identifying Influential Users in Social Networks with an Ext...

引用

10th International Conference on Web Research, ICWR 2024

作者： Esfandiari, Shima Fakhrahmad, Seyed Mostafa Shiraz University Dept. of Computer Engineering and IT Shiraz Iran

ISBN: (纸本)9798350394986

With the widespread use of social media, communication, and news dissemination have become faster and more extensive. Therefore, identifying key individuals in controlling rumors is of great importance. Researchers have employed various methods to identify these individuals, each with its advantages and disadvantages. Some methods lack accuracy and do not adequately identify the influence of each individual. Others have low resolution, meaning they consider many individuals to be equally influential and do not differentiate between them. In this paper, we propose a comprehensive method based on the Degree and K-shell, which improves upon the Hybrid global structure model (HGSM) method. According to the evaluations performed on five social networks, the proposed method has higher accuracy and resolution compared to recent methods, while also having a suitable time complexity. The real influence of each individual is calculated using the Susceptible-Infected-Recovered (SIR) model and the evaluation criteria are Kendall's Tau, Monotonicity index, and Time complexity. © 2024 IEEE.

关键词： Degree HGSM Influential Nodes K-Shell SIR Social Networks

来源：评论

学校读者我要写书评

暂无评论

A Faster R-CNN Model for Multi-Class Classification and Detection of Land, Air, and Sea Vehicles 9

A Faster R-CNN Model for Multi-Class Classification and Dete...

引用

9th International Conference on computer Science and engineering, UBMK 2024

作者： Güvelioǧlu, Enes Aci, Çiǧdem Inan Mersin University Dept. of Computer Engineering Mersin Turkey

ISBN: (纸本)9798350365887

Automatic vehicle detection and classification systems have recently been utilized in various fields. Although the applications in this field generally focus on civilian land vehicles (mostly automobiles), relatively few studies address civil and military land, air, and sea vehicles together. This study developed a multi-class vehicle detection model using faster region-based convolutional neural networks (Faster R-CNN) on a tailored dataset. The dataset includes 13,577 images, with a total of 21,070 objects identified. Among these, 8,194 objects are classified as land, 7,203 as sea, and 5,674 as air. The faster R-CNN model yielded an F1-score value of 0.869 for air, 0.838 for land, and 0.894 for sea vehicles. The results showed that the developed model is a promising approach for identifying civil and military vehicles on land, at sea, or in the air. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced ConvLSTM with Hierarchical Attention Scheme for Unusual Activity Detection in Classrooms or Laboratories

Enhanced ConvLSTM with Hierarchical Attention Scheme for Unu...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Shrivas, Ansh Mahendra Kumar Singh, Dushyant Jain, Rishabh Chandel, Shreyansh Singh Sahu, Abhimanyu Mnnit Computer Science and Engineering Dept. Allahabad India

ISBN: (纸本)9798350364866

Surveillance camera systems have been essential in enhancing security protocols, serving as crucial tools for monitoring and deterring unauthorized or unusual activities across various settings. This paper addresses the significant vulnerability of educational spaces to numerous security threats, such as unauthorized access, theft, vandalism, and risks to the safety of students and staff. In an age where both physical and digital security are critically important, there is an increasing demand for proactive surveillance solutions that can quickly and accurately identify anomalies and potential security breaches. Deep learning techniques have demonstrated remarkable effectiveness in identifying patterns, anomalies, and subtle deviations in behavior within real-time video feeds. We have developed an enhanced ConvLSTM model incorporating spatial and temporal attention mechanisms to extract essential features from raw video footage, which are then processed by the backbone network. The architecture is designed to selectively focus on the most valuable features, thereby reducing computational complexity and enhancing the model's detection performance. The model is fine-tuned to detect and classify activities into usual and unusual categories. The proposed design is trained on videos from the UCF-Crime dataset and fine-tuned on a custom dataset created from YouTube videos, which includes videos of actions that are unusual or anomalous in educational environments. Our approach achieved approximately 99% accuracy on the UCF-Crime dataset, surpassing detection baselines (85.53% to 88.56%) and outperforming other architectures such as C3D, ConvLSTM, and CNN+RNN models with and without attention mechanisms. Evaluation on a custom YouTube dataset yielded a detection accuracy of 82.66%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Study on the Analysis and Reduction Method for AC Copper Loss in Electric Vehicle Traction Motor

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第2期74卷 295-301页

作者： Wang, Chang-Hyeon Kim, Nam-Ho Choi, Ho-Yong Jung, Sang-Yong Dept. of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of Special Motor Engineering 1 Team Hyosung Heavy Industies Korea Republic of

The advancements in electrified drive systems have enabled the design of high-power density electric vehicle (EV) motors. However, the increased operating frequency necessary for achieving high-power density amplifies AC copper losses, primarily due to skin and proximity effects. This study focuses on reducing AC copper losses in an 8-pole, 48-slot Interior Permanent Magnet Synchronous Motor (IPMSM) using 2D finite element analysis (FEA). The analysis evaluates the contributions of skin and proximity effects to total copper losses and investigates the influence of slot leakage flux. Additionally, the impact of slot and conductor geometries on leakage flux, its variation over time, and the resulting AC copper losses were systematically analyzed. By balancing manufacturability and performance, optimal design parameters were derived to minimize AC copper losses. The results demonstrate that adjustments in slot width, slot dept., and conductor placement significantly affect leakage flux and copper losses. The proposed design strategies improve motor efficiency and thermal performance under high-speed operating conditions, contributing to the development of high-performance EV motors. Copyright © The Korean Institute of Electrical Engineers.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Exploring The Use of Advanced Machine Learning to Detect Fraudulent Crypto Platforms 9

Exploring The Use of Advanced Machine Learning to Detect Fra...

引用

9th IEEE International Conference on Adaptive Science and Technology, ICAST 2024

作者： Manful, John Terence Hasford, Adelle Yeluripati, Govindha Ramaiah Ashesi University Dept. of Computer Science & Information Systems Berekuso Ghana

ISBN: (纸本)9798350385403

The decentralized nature, self-regulation, and rapid transaction speeds of the cryptocurrency landscape foster both innovation and fraud. As crypto gains attention, fraudulent exchanges posing as legitimate platforms present significant financial risks. Traditional reporting methods, like those of CryptoScamDB, are becoming less effective. This study addresses the need for automated techniques to identify and classify fraudulent exchanges. We found that features related to domain information, website security, and user reviews are crucial for detection. A comparative experiment using machine learning models - random forest, support vector machine, k-nearest neighbour, light gradient boosting machine, and multi-layer perceptron - showed that the light gradient boosting machine (95.9%) and random forest (95.5%) had the highest accuracy. An ensemble model using soft voting achieved a higher accuracy of 96.2%, outperforming its base models. These results demonstrate that machine learning is a viable approach for automating the classification of fraudulent exchanges. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach to Song Popularity Forecasting 2

A Comprehensive Approach to Song Popularity Forecasting

引用

2nd International Conference on Artificial Intelligence and Machine Learning Applications, AIMLA 2024

作者： Kishore, N. Santhiya, P. Mohamed Askar Asib, M. Kirubaaharan, S. Kongu Engineering College Dept. Computer Science India

ISBN: (数字)9798350349221

ISBN: (纸本)9798350349221

Assessing the potential success of a song based on its acoustic characteristics is a crucial task within the music industry. Traditionally, this has been approached by leveraging audio features independently. In this study, we take a novel approach by jointly exploiting audio features, framing as a regression on prediction task. Our methodology employs a wide architecture, enabling a comprehensive analysis. Additionally, we enhance feature sets by incorporating information about track release years. Evaluation on the Million Song Dataset, using Billboard Hot 100 inclusion as a metric for song success, reveals that our approach surpasses baseline methods and those utilizing low- or high-level features in isolation. Notably, the inclusion of release year alongside mood and vocal features further enhances predictive accuracy, highlighting the efficacy of our comprehensive model in gauging song popularity. © 2024 IEEE.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Parallelized 0/1 Knapsack Algorithm Optimization in CPU-GPU-Based Heterogeneous System with Algorithm-based Fault Tolerance 18

Parallelized 0/1 Knapsack Algorithm Optimization in CPU-GPU-...

引用

18th International Conference on Ubiquitous Information Management and Communication, IMCOM 2024

作者： Abid, Marzan Binte Shaha, Shuvo Kabir, Upama Arefin, Md. Fahim University of Dhaka Dept. of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350331011

A heterogeneous high-performance computing (HPC) system is an aggregation of CPUs and GPUs through high-speed interconnection. As graphics processing units (GPUs) can conduct rapid mathematical and vector operations due to their hardware properties, GPU-based heterogeneous systems can optimize algorithms that show data parallelism. Since the dynamic programming (DP) solution of the 0/1 knapsack algorithm is inherently data-parallel, this paper optimized the algorithm to maximize the advantages of a GPU-based parallel environment. Furthermore, this research identified that the algorithm was well suited to four distinct GPU-launch approaches. Among them, the "single-cell calculation by single thread with a single kernel launch"approach outperforms others by reducing the complexity from O(n∗w) to O(n). Besides, these HPC systems are susceptible to the slightest of errors. Checkpoint recovery (CP/R) is the most commonly used fault tolerance and recovery system, which suffers from huge checkpoint and recovery overhead. To reduce this overhead in CPU-GPU-based heterogeneous systems, an algorithm-based fault tolerance (ABFT) technique has been proposed for a particular class of algorithm: 0/1 knapsack. The experimental results verify the feasibility of the proposed ABFT technique and demonstrate that the system can recover from failures with minimal overhead. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Cyberbullying Detection using Deep Learning Algorithms 3

Cyberbullying Detection using Deep Learning Algorithms

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Nirmala Devi, K. Jayanthi, P. Rajasekar, Vani Rathinasamy, Rahul Dhandapani, Pradeep Rasil Risam, F. Dept. of Computer Science Kongu Engineering College Erode India

ISBN: (纸本)9798331527549

Social media's widespread use has made it easier for people to communicate openly, but it has also fuelled the growth of cyberbullying, which has seriously harmed victims' emotional and mental health. The intricacy of human language and the variety of abusive behaviours make it difficult to detect cyberbullying. To solve this problem, numerous studies have used deep learning (DL) and machine learning (ML) algorithms over time. However, deep learning (DL) algorithms have transformed text analysis by automatically extracting features and comprehending contextual dependencies in language, while machine learning (ML) techniques are limited in their ability to handle complex and contextual linguistic patterns. Building upon this framework, this study investigates the use of transformer-based models—more especially, BERT—for the detection of cyberbullying. Out of the proposed models, DistlBERT gives the best accuracy, precision, recall, and F1-score of 98.87%,98.87%, 98.87 and 98.86% respectively. © 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

Rethinking Machine Ethics - Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?

Rethinking Machine Ethics - Can LLMs Perform Moral Reasoning...

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Zhou, Jingyan Hu, Minda Li, Junan Zhang, Xiaoying Wu, Xixin King, Irwin Meng, Helen Dept. of Systems Engineering & Engineering Management The Chinese University of Hong Kong Hong Kong Dept. of Computer Science & Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798891761193

Making moral judgments is an essential step toward developing ethical AI systems. Prevalent approaches are mostly implemented in a bottom-up manner, which uses a large set of annotated data to train models based on crowd-sourced opinions about morality. These approaches have been criticized for overgeneralizing the moral stances of a limited group of annotators and lacking explainability. This work proposes a flexible top-down framework to steer (Large) Language Models (LMs) to perform moral reasoning with well-established moral theories from interdisciplinary research. The theory-guided top-down framework can incorporate various moral theories. Our experiments demonstrate the effectiveness of the proposed framework on datasets derived from moral theories. Furthermore, we show the alignment between different moral theories and existing morality datasets. Our analysis exhibits the potential and flaws in existing resources (models and datasets) in developing explainable moral judgment-making systems. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

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：