检索结果-内蒙古大学图书馆

2023 IEEE technology and engineering Management Conference - Asia Pacific, TEMSCON-ASPAC 2023

作者： Priya, K. Maanesh, M. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Cse School of Computing Tamilnadu Chennai India Sri Venkateswara College of Engineering Sriperumbathur Department of Cse Tamilnadu Chennai India

ISBN: (纸本)9798350384659

In today's digital age, the demand for online video content is skyrocketing. However, reaching a diverse, multilingual audience poses a significant challenge due to language barriers. To overcome this obstacle and maximize outreach, our project introduces an innovative solution: automated real-time video dubbing into various Indian regional languages. Leveraging advanced AI-powered technology, this initiative seamlessly translates audio, ensures precise lip synchronization, incorporates voice cloning, and preserves the cultural authenticity of the content. What sets our platform apart is its ability to allow content creators to maintain their unique vocal identity while speaking in a different language. This personal touch enhances the localized content's authenticity, resonating more deeply with viewers and significantly contributing to *** innovative software not only generates voiceovers in human-like tones for languages such as Hindi, Marathi, Bengali, Gujarati, Tamil, Telugu, and more but also ensures that these translations are presented in a simple, clear, and non-colloquial manner, ensuring easy comprehension. © 2023 IEEE.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

XIFBench: Evaluating Large Language Models on Multilingual Instruction Following

arXiv

引用

arXiv 2025年

作者： Li, Zhenyu Chen, Kehai Long, Yunfei Bai, Xuefeng Zhang, Yaoyin Wei, Xuchen Li, Juntao Zhang, Min Institute of Computing and Intelligence Harbin Institute of Technology Shenzhen China School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Soochow University China

Large Language Models (LLMs) have demonstrated remarkable instruction-following capabilities across various applications. However, their performance in multilingual settings remains poorly understood, as existing evaluations lack fine-grained constraint analysis. We introduce XIFBench, a comprehensive constraint-based benchmark for assessing multilingual instruction-following abilities of LLMs, featuring a novel taxonomy of five constraint categories and 465 parallel instructions across six languages spanning different resource levels. To ensure consistent cross-lingual evaluation, we develop a requirement-based protocol that leverages English requirements as semantic anchors. These requirements are then used to validate the translations across languages. Extensive experiments with various LLMs reveal notable variations in instruction-following performance across resource levels, identifying key influencing factors such as constraint categories, instruction complexity, and cultural specificity. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Coding Observer Nodes for Sybil Attacks Detection in Mobile Wireless Sensor Networks 19

Coding Observer Nodes for Sybil Attacks Detection in Mobile ...

引用

19th IEEE International Conference on Embedded and Ubiquitous computing, EUC 2021

作者： Sassani Sarrafpour, Bahman A. Alomirah, Abdulaziz Pang, Shaning Sarrafpour, Soshian School of Computing Engineering Applied Technology Unitec New Zealand Auckland New Zealand School of Computing Engineering Applied Technology Unitec New Zealand Auckland New Zealand Federation University School of Engineering Information Technology Physical Science Melbourne Australia Yale University School of Medicine Newhaven United States

ISBN: (纸本)9781665400367

Sybil attack is one of the most common and serious attacks in wireless sensor networks, in which a malicious node illegitimately forges several (fake) identities. These fake copies confuse and collapse the network. Sybil attack causes too many threats to the routing algorithm, data aggregation, fair resource allocation, voting system, and misbehavior detection. In this paper, we propose a new lightweight algorithm for detecting the Sybil attack in mobile wireless sensor networks using observer nodes. Observer nodes are normal, trustful nodes which have been initially programmed to observe the network and report malicious behaviors. An observer node counts the number of times a node has appeared as a common neighbor between itself and its neighbors. After collecting some information about its neighbors, each observer node considers the nodes whose counters are above a threshold as critical, and nodes having all critical nodes in their neighborhood are considered suspicious nodes. The results show that the true detection rate of the proposed algorithm is 98.1%, and its false detection rate is 0.5%, while similar algorithms could not achieve better than 95.4% and 1.2% for these metrics, respectively. In addition, the proposed algorithm outperforms other algorithms in terms of overhead. © 2021 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Data Fusion Architecture Empowered with Deep Learning for Breast Cancer Classification

引用

Computers, Materials & Continua 2023年第12期77卷 2813-2831页

作者： Sahar Arooj Muhammad Farhan Khan Tariq Shahzad Muhammad Adnan Khan Muhammad Umar Nasir Muhammad Zubair Atta-ur-Rahman Khmaies Ouahada Faculty of Computing Riphah International UniversityIslamabad45000Pakistan Department of Forensic Sciences University of Health SciencesLahore54000Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O.Box 524Johannesburg2006South Africa School of Computing Skyline University CollegeUniversity City SharjahSharjah1797United Arab Emirates Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Department of Software Faculty of Artificial Intelligence&SoftwareGachon UniversitySeongnamGyeonggido13120Korea Department of Computer Science Bahria UniversityLahore CampusLahore54000Pakistan Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia

Breast cancer(BC)is the most widespread tumor in females worldwide and is a severe public health *** is the leading reason of death affecting females between the ages of 20 to 59 around the *** detection and therapy can help women receive effective treatment and,as a result,decrease the rate of breast cancer *** cancer tumor develops when cells grow improperly and attack the healthy tissue in the human *** are classified as benign or malignant,and the absence of cancer in the breast is considered *** learning,machine learning,and transfer learning models are applied to detect and identify cancerous tissue like *** research assists in the identification and classification of *** implemented the pre-trained model AlexNet and proposed model Breast cancer identification and classification(BCIC),which are machine learning-based models,by evaluating them in the form of comparative *** used 3 datasets,A,B,and *** fuzzed these datasets and got 2 datasets,A2C and *** A2C is the fusion of A,B,and C with 2 classes categorized as benign and *** B3C is the fusion of datasets A,B,and C with 3 classes classified as benign,malignant,and *** used customized AlexNet according to our datasets and BCIC in our proposed *** achieved an accuracy of 86.5%on Dataset B3C and 76.8%on Dataset A2C by using AlexNet,and we achieved the optimum accuracy of 94.5%on Dataset B3C and 94.9%on Dataset A2C by using proposed model BCIC at 40 epochs with 0.00008 learning *** proposed fuzzed dataset model using transfer *** fuzzed three datasets to get more accurate results and the proposed model achieved the highest prediction accuracy using fuzzed dataset transfer learning technique.

关键词： Breast cancer classification deep learning machine learning transfer learning learning rate

来源：评论

学校读者我要写书评

暂无评论

Smart Modular Parcel Locker System using Internet of Things (IoT)

Smart Modular Parcel Locker System using Internet of Things ...

引用

11th IEEE International Conference on System engineering and technology, ICSET 2021

作者： Ooi, Jing Zhi Tan, Chye Cheah School of Computing Asia Pacific University of Technology and Innovation Bukit Jalil Malaysia Asia Pacific University of Technology and Innovation Faculty of Computing Engineering and Technology Bukit Jalil Malaysia

ISBN: (纸本)9781665437660

The increase in use cases of last mile delivery is a by-product from the increase in efficiency of globalized goods transportation, to the point that it is applicable for non-commercial endpoints, e.g., personal accommodation. With the surge in use cases, there is an amplified cost in financial and time resources from both logistic companies and the recipients as the amount of endpoints rise. This paper details the development of a proposed system aimed to alleviate the effect by offering concentrated stopping locations to accommodate for different logistic companies to deposit multiple parcels into while the recipients collect them as needed through the implementation of contactless deposit and withdrawal, as well as a modular style of locker unit deployment in a scalable manner. © 2021 IEEE.

关键词： Costs Conferences Transportation Companies Systems engineering and theory Internet of Things Surges

来源：评论

学校读者我要写书评

暂无评论

Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion

arXiv

引用

arXiv 2024年

作者： Guo, Ji Li, Hongwei Jiang, Wenbo Lu, Guoming Laboratory Of Intelligent Collaborative Computing University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China

Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Networks (CNN) across various computer vision tasks. However, akin to CNN, ViTs are vulnerable to backdoor attacks, where the adversary embeds the backdoor into the victim model, causing it to make wrong predictions about testing samples containing a specific trigger. Existing backdoor attacks against ViTs have the limitation of failing to strike an optimal balance between attack stealthiness and attack effectiveness. In this work, we propose an Attention Gradient-based Erosion Backdoor (AGEB) targeted at ViTs. Considering the attention mechanism of ViTs, AGEB selectively erodes pixels in areas of maximal attention gradient, embedding a covert backdoor trigger. Unlike previous backdoor attacks against ViTs, AGEB achieves an optimal balance between attack stealthiness and attack effectiveness, ensuring the trigger remains invisible to human detection while preserving the model’s accuracy on clean samples. Extensive experimental evaluations across various ViT architectures and datasets confirm the effectiveness of AGEB, achieving a remarkable Attack Success Rate (ASR) without diminishing Clean Data Accuracy (CDA). Furthermore, the stealthiness of AGEB is rigorously validated, demonstrating minimal visual discrepancies between the clean and the triggered images. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Machine Learning Based Techniques for Breast Cancer Detection

Imbalanced Machine Learning Based Techniques for Breast Canc...

引用

2021 International Conference on System, Computation, Automation and Networking, ICSCAN 2021

作者： Mohammed, Ahmed Arunachalam, N. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai603203 India

ISBN: (纸本)9781665439862

Breast cancer is the world's second-leading cause of cancer death among women. It is the most frequent type of invasive cancer in women and the second biggest cause of mortality in the United States. Breast cancer is a disease in which the breast cells develop out of control. Many studies have been conducted in this area utilizing a machine learning technique, however some of them did not explore how to cope with imbalanced classes. The breast cancer dataset is an unbalanced dataset in which the total frequencies of benign class is larger than the total frequencies of malignant class. The problem with an unbalanced dataset is that it provides a high level of accuracy just by predicting the majority class, but fails to capture the minority class, which is usually the point of creating the model in the first place. Imbalanced classification approaches were employed in this study to predict breast cancer. The accuracy of prediction for multiple machine learning algorithms was determined utilizing imbalanced methodologies such as synthetic minority oversampling technique, random oversampling, and random under sampling technique respectively. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Digital Human Techniques for Education Reform 24

Digital Human Techniques for Education Reform

引用

7th International Conference on Educational technology Management, ICETM 2024

作者： Guo, Peirong Zhang, Qi Tian, Chunwei Xue, Wanli Feng, Xiaocheng School of Software Northwestern Polytechnical University Shaanxi Xi’an China School of Economics and Management Harbin Institute of Technology at Weihai Shandong Weihai China Shenzhen Research Institute of Northwestern Polytechnical University Northwestern Polytechnical University Guangdong Shenzhen China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Heilongjiang Harbin China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Guangdong Shenzhen China

ISBN: (纸本)9798400717468

The rapid evolution of artificial intelligence, big data, and generative AI models has ushered in significant transformations across various sectors, including education. Digital Human Technique, an innovative technology grounded in advanced computer science and artificial intelligence, is reshaping educational paradigms by enabling virtual humans to simulate human behavior, express emotions, and interact with users. This paper explores the application of Digital Human Technique in education reform, focusing on creating immersive, intelligent classroom experiences that foster meaningful interactions between teachers and students. We define Digital Human Technique and delve into its key technical components such as character modeling and rendering, natural language processing, computer vision, and augmented reality technologies. Our methodology involves analyzing the role of educational digital humans created through these technologies, assessing their impact on educational processes, and examining various application scenarios in educational reform. Results indicate that Digital Human Technique significantly enhances the learning experience by enabling personalized teaching, increasing engagement, and fostering emotional connections. Educational digital humans serve as virtual teachers, interactive learning aids, and facilitators of emotional interaction, effectively addressing the challenges of traditional educational methods. They also promote a deeper understanding of complex concepts through simulated environments and interactive digital content. © 2024 Copyright held by the owner/author(s).

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Heart Disease Using Deep Learning Model 8

Early Detection of Heart Disease Using Deep Learning Model

引用

8th International Conference on Smart Structures and Systems, ICSSS 2022

作者： Deepika, R. Srikaanth, P. Balaji Pitchai, R. Srm Institute of Science and Technology Kattankulathur Technology School of Computing Tamilnadu India Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur India B v Raju Institute of Technology Department of Computer Science and Engineering Narsapur India

ISBN: (纸本)9781665497619

Identifying and detecting the early signs of diseases is difficult due to asymptomatic conditions. Detecting the signs early gives the patient a higher chance of surviving. There are several technologies to identify the heart diseases for timely treatment. So far, different techniques of machine learning is used to predict heart abnormalities. Machine learning models trained by large amounts of data in the healthcare field contain a lot of medical images that enable the medical professionals to identify even minimal changes with a high level of accuracy. This paper presents the deep learning technique used to predict the heart abnormalities. Deep learning technique helps in processing the image data through various tests which include electrocardiogram, echocardiogram etc., that detects the abnormalities in the heart. © 2022 IEEE.

关键词： Heart Deep learning Medical services Feature extraction Data models Intelligent structures Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Explainable AI: A Way to Achieve Trustworthy AI

Explainable AI: A Way to Achieve Trustworthy AI

引用

IEEE International Conference on Big Data Security on Cloud (BigDataSecurity), High Performance and Smart computing (HPSC) and Intelligent Data and Security (IDS)

作者： Yanlu Li Yufeng Xiao Yinyan Gong Ronglin Zhang Yingzi Huo Yanbing Wu Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China

ISBN: (数字)9798350389524

ISBN: (纸本)9798350389531

AI is black-box and non-explainable, in other words, due to the complexity of the decision-making process of AI, people are unable to know why and how AI makes the decision. For these reasons, people will question and worry about AI’s decision-making. Against this background, researchers have proposed the concept of Explainable Artificial Intelligence (XAI). The aim of this paper is to help readers be able to better understand XAI through extensive surveys. In this paper, we discuss the concept of XAI, the motivation of the research, the current status of the research, and the difficulties in the research process. At the same time, we also discuss the specific methods to realize AI explainability by dividing AI explainability methods into two ways: transparent design and ex post facto interpretation. In addition, we select the three fields of healthcare, finance, and autonomous driving, discuss the application of XAI in these three fields, and select some representative results as examples through surveys. Finally, we summarize this article and present our outlook on the future development of XAI.

关键词： Surveys Explainable AI Decision making Finance Closed box Medical services Big Data

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：