检索结果-内蒙古大学图书馆

22nd Asia Simulation Conference, AsiaSim 2023

作者： Mazni, Mazleenda Husain, Abdul Rashid Shapiai, Mohd Ibrahim Ibrahim, Izni Syahrizal Zulkifli, Riyadh Anggara, Devi Willieam School of Electrical Engineering Faculty of Engineering Universiti Teknologi Malaysia Johor Skudai Malaysia Faculty of Mechanical Engineering Universiti Teknologi MARA Cawangan Johor Kampus Pasir Gudang Jalan Purnama Masai Malaysia Centre for Artificial Intelligence and Robotics International Institute of Technology Universiti Teknologi Malaysia Kuala Lumpur Malaysia Forensic Engineering Centre Institute for Smart Infrastructure and Innovative Construction Faculty of Civil Engineering Universiti Teknologi Malaysia Johor Malaysia School of Computing Faculty of Engineering Universiti Teknologi Malaysia Skudai Malaysia

ISBN: (纸本)9789819972395

Detecting cracks on concrete surfaces is a crucial task in civil engineering inspections, but it poses significant challenges due to the small and concealed nature of cracks. Visual detection is particularly difficult on uneven or rough concrete surfaces. To overcome these challenges, our research focuses on developing an automated system that utilizes a wall-climbing robot for crack classification. Our main objective is to introduce a crack classification technique using MobileNetV2, enabling real-time classification without human intervention. The Convolution Neural Network (CNN) model used for crack classification is based on MobileNetV2, which is fine-tuned by adjusting the sensitivity of its hyperparameters. Through extensive experiments, we evaluate the performance of this CNN approach specifically designed for embedded systems. After evaluating our proposed approach of crack-detection on publicly available datasets, we have found that out of all the pre-trained CNN models MobileNetV2 yields the best performance with 99.56% detection accuracy, precision of 99.65%, recall of 99.48%, and F1-Score of 99.56%. However, it is important to note that the training time for this model is relatively high, taking 25,500 s. Future study of the study should focus on optimizing the computation time to improve efficiency. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Identification of Anomaly Scenes in Videos Using Graph Neural Networks

引用

Computers, Materials & Continua 2023年第3期74卷 5417-5430页

作者： Khalid Masood Mahmoud M.Al-Sakhnini Waqas Nawaz Tauqeer Faiz Abdul Salam Mohammad Hamza Kashif Department of Software Engineering Lahore Garrison UniversityLahore54000Pakistan School of Business Skyline University CollegeSharjahUAE Al-Madinah International University–Faculty of Computer and Information Technology Kuala LumpurMalaysia College of Computer and Information Systems Islamic University of MadinahMadinahKingdom of Saudi Arabia School of IT Skyline University CollegeSharjahUAE Faculty of Engineering Computing and Science(FECS)-Swinburne University of TechnologySarawak Department of General Education Skyline University CollegeUniversity City of SharjahUAE Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan

Generally,conventional methods for anomaly detection rely on clustering,proximity,or *** themassive growth in surveillance videos,outliers or anomalies find ingenious ways to obscure themselves in the network and make conventional techniques *** research explores the structure of Graph neural networks(GNNs)that generalize deep learning frameworks to graph-structured *** node in the graph structure is labeled and anomalies,represented by unlabeled nodes,are predicted by performing random walks on the node-based graph *** to their strong learning abilities,GNNs gained popularity in various domains such as natural language processing,social network analytics and *** detection is a challenging task in computer vision but the proposed algorithm using GNNs efficiently performs the identification of *** Graph-based deep learning networks are designed to predict unknown objects and *** our case,they detect unusual objects in the form of malicious *** edges between nodes represent a relationship of nodes among each *** case of anomaly,such as the bike rider in Pedestrians data,the rider node has a negative value for the edge and it is identified as an *** encoding and decoding layers are crucial for determining how statistical measurements affect anomaly identification and for correcting the graph path to the best possible *** show that the proposed framework is a step ahead of the traditional approaches in detecting unusual activities,which shows a huge potential in automatically monitoring surveillance *** autonomous monitoring of CCTV,crime control and damage or destruction by a group of people or crowd can be identified and alarms may be triggered in unusual activities in streets or public *** suggested GNN model improves accuracy by 4%for the Pedestrian 2 dataset and 12%for the Pedestrian 1 dataset compared to a few state-of the-art techniq

关键词： Graph neural network deep learning anomaly detection auto encoders

来源：评论

学校读者我要写书评

暂无评论

Steps Towards a Philosophy of computing Education (Discussion Paper) 23

Steps Towards a Philosophy of Computing Education (Discussio...

引用

Proceedings of the 23rd Koli Calling International Conference on computing Education Research

作者： Roger McDermott Mats Daniels Stephen T. Frezza School of Computing Robert Gordon University United Kingdom Dept. of Information Technology University of Uppsala Sweden Dept. of Engineering and Computing Franciscan University of Steubenville USA

ISBN: (纸本)9798400716539

Is it meaningful to talk about the philosophy of computing education? What is its subject matter and methods? Is it different from, or a subfield of, the philosophy of science education or the philosophy of technology education or the philosophy of engineering education? And how does the study of the philosophy of computing education help us with the goal of teaching students about computing? In this paper, we attempt to examine these questions. We look at the role of philosophical inquiry in the STEM fields and examine the philosophies of education found in those subjects. We first attempt to identify a framework for characterising questions of a philosophical nature that is appropriate for application to the STEM subjects. We describe the categories such questions fall under and consider methodological questions associated with this kind of inquiry. We also look at issues that arise within the philosophy of education and which are relevant when considering the philosophies of disciplinary education. We investigate some of the similarities and differences that exist between these fields and a philosophy of computing education and provide an initial description of the latter. We briefly consider other “sense-making” vocabulary used in computing education research, such as “theory” and suggest reasons why philosophical inquiry should be an important part of computing education research.

关键词： Philosophy Philosophy of computing Education Philosophy of Education Philosophy of engineering Education

来源：评论

学校读者我要写书评

暂无评论

AyurChat: Empowering Health through AI-Driven Ayurvedic Guidance

AyurChat: Empowering Health through AI-Driven Ayurvedic Guid...

引用

International Conference on computing and Networking technology (ICCNT)

作者： Syed Adeel Ahmed Gautam Gahlawat Fahad Imam G. Saranya Department of Networking and Communications School of computing College of Engineering and Technology S.R.M Institute of Science and Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

AyurChat is a project aiming to transform healthcare discussions by blending intelligence (AI) with the wisdom of Ayurveda. The innovative chatbot system, known as AyurChat acts as a health companion offering personalized advice, for medical queries. The main goal of AyurChat is to empower individuals to manage their health through natural solutions rooted in Ayurvedic principles. By utilizing cutting edge language processing and machine learning techniques, AyurChat engages in conversations with users understanding their health concerns and providing tailored guidance based on Ayurveda. This system aims to improve access to healthcare by bridging the gap between technology and traditional healing practices. With a ranging knowledge base covering Ayurvedic remedies AyurChat ensures thorough and precise responses to user’s health inquiries. Through AI driven algorithms evolves over time, enhancing its grasp of user needs and refining its recommendations continuously. AyurChat stands as an endeavor that uses AI to make Ayurvedic healthcare knowledge more accessible. Offering discussions and personalized advice it provides users with treatments from the realm of Ayurveda rather than conventional Western medicine along with web links for alternative medicines, like Siddha and Unani.

关键词： Navigation Law Scalability Refining Medical services Machine learning Transforms Oral communication Chatbots Research and development

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of CNN based Residue Number System for Performance Enhancement 3

Design and Analysis of CNN based Residue Number System for P...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Jency Rubia, J. Sherin Shibi, C. Babitha Lincy, R. Dhamodharan, S. K.Ramakrishnan College of Engineering Department Ece Tamil Nadu Trichy India Srm Institute of Science and Technology School of Computing Department of Ci Tamil Nadu Kattankulathur India Sri Eshwar College of Engineering Cce Department Tamil Nadu Coimbatore India

ISBN: (纸本)9781665462167

Convolutional Neural Network plays a vital role in Artificial intelligence and it's mainly harnessed for pattern recognition. However, it's quite tricky to achieve less image recognition time using the conventional CNN method. The conventional CNN module requires additional features that boost CNN performance in terms of delay. Thus, in this paper, the performance of the proposed system has been improved with the help of CNN-based Residue Number System (RNS). The performance of our designed CNN system is increased by reducing the delay in the Prewitt filter. Incorporating the proposed system in the Prewitt filter consumes less image recognition time. Further, the comparative analysis of the proposed work with other works for instance, the Binary Number System (BNS) and conventional RNS system has been performed. The accuracy of the recognition of an image is purely based on the numbers of test images. Therefore, the weight of the test image has been increased. But, the RNS scheme decreases the weight of a test image. Moreover, this comparative analysis investigates the better technique for delay minimization. Finally, the designed work is replicated and synthesized using MATLAB 2018b software. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning 24

Multimodal Unlearnable Examples: Protecting Data against Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Xinwei Jia, Xiaojun Xun, Yuan Liang, Siyuan Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences School of Cyberspace Security University of Chinese Academy of Sciences Beijing China Cyber Security Research Centre - NTU Nanyang Technological University Singapore Singapore School of Computing National University of Singapore Singapore Singapore School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Shenzhen China

ISBN: (纸本)9798400706868

Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. However, this reliance poses privacy risks, as hackers may unauthorizedly exploit image-text data for model training, potentially including personal and privacy-sensitive information. Recent works propose generating unlearnable examples by adding imperceptible perturbations to training images to build shortcuts for protection. However, they are designed for unimodal classification, which remains largely unexplored in MCL. We first explore this context by evaluating the performance of existing methods on image-caption pairs, and they do not generalize effectively to multimodal data and exhibit limited impact to build shortcuts due to the lack of labels and the dispersion of pairs in MCL. In this paper, we propose Multi-step Error Minimization (MEM), a novel optimization process for generating multimodal unlearnable examples. It extends the Error-Minimization (EM) framework to optimize both image noise and an additional text trigger, thereby enlarging the optimized space and effectively misleading the model to learn the shortcut between the noise features and the text trigger. Specifically, we adopt projected gradient descent to solve the noise minimization problem and use HotFlip to approximate the gradient and replace words to find the optimal text trigger. Extensive experiments demonstrate the effectiveness of MEM, with post-protection retrieval results nearly half of random guessing, and its high transferability across different models. Our code is available on the https://***/thinwayliu/Multimodal-Unlearnable-Examples. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Spoof Surface Plasmon Polaritons based Leaky-wave Antenna for Continuous Beam Scanning

Design and Analysis of Spoof Surface Plasmon Polaritons base...

引用

Microwaves Antennas and Propagation Conference (MAPCON)

作者： Ravi Anand Himansu Sekhar Senapati Debrati Dutta Anirban Sarkar School of Computing and Electrical Engineering Indian Institute of Technology Mandi Mandi Himachal Pradesh India

This research presents a general idea to develop a continuous beam scanning antenna utilizing the spoof surface plasmon polaritons (SSPPs)-based transmission line. The transmission line using the corrugated metallic grooves helps in strong confinement of field within the line, which further improves the coupling between the line and the radiators. Theoretically and numerically simulated results shows good agreement in terms of dispersion and scanning range. It is found that the antenna is highly capable of dual beam continuous scanning in the sub-6 GHz frequency band. The dual beam continuous scan from -90° (at 3.07 GHz) to +16° (at 4.9 GHz) in the visible space. The antenna achieved an overall gain of 9.8 dB and fractional bandwidth of 117% at centre frequency of 3.15 GHz. Owing to the single layer, groundless, and improved performance characteristics, the proposed antenna seems to be potential candidate for sub-6 GHz applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Classification using Crow Search Algorithm

Heart Disease Classification using Crow Search Algorithm

引用

Smart Electronics and Communication (ICOSEC), International Conference on

作者： M. Maragatharajan P. Naveen E. Nirmala School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh India Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore Tamilnadu

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

This work introduces cutting-edge research to predict heart diseases. This application designed for accurate and personalized assessment of cardiovascular health. This work aims to provide an overall understanding of an individual’s heart health by integrating these multifaceted data points. This work utilizes a vast dataset to establish correlations and patterns, enabling it to categorize users into specific risk groups or diagnose potential heart diseases. Through continuous learning and adaptation, the work refines its predictive capabilities, ensuring that it remains up-to-date with emerging medical knowledge. The work not only assists in early detection of cardiovascular issues but also aids in personalized risk assessment, guiding users towards lifestyle modifications and preventive measures based on their unique health profiles. This innovative solution holds the potential to revolutionize the field of cardiovascular health assessment, offering a proactive and data-driven approach to identify and manage heart diseases efficiently. This study considered two well-known machine learning models namely Extreme learning machine algorithms (ELM) and Crow search algorithm (CSA). The collected dataset consists of 10000 samples. We have attained 92.5% accuracy with the data set. The incorporation of machine learning models ensures scalability, adaptability, and precision, making it a valuable tool for both healthcare professionals and individuals striving for proactive heart care.

关键词： Heart Adaptation models Machine learning algorithms Accuracy Scalability Medical services Machine learning Classification algorithms Risk management Diseases

来源：评论

学校读者我要写书评

暂无评论

A hydrophobic organic spacer cation for improving moisture resistance and efficiency in mixed-dimensional perovskite solar cells

EES Solar

引用

EES Solar 2025年第3期1卷 356-365页

作者： Prasun Kumar Satinder Kumar Sharma Ranbir Singh School of Mechanical and Materials Engineering (SMME) Indian Institute of Technology (IIT) Mandi Mandi Himachal Pradesh India Advanced Energy Conversion Laboratory (AECL) Indian Institute of Technology (IIT) Mandi Mandi Himachal Pradesh India School of Computing and Electrical Engineering (SCEE) Indian Institute of Technology (IIT) Mandi Mandi Himachal Pradesh India

Mixed-dimensional perovskite structures containing two-dimensional (2D) bulky organic cations offer enhanced stability but suffer from lower efficiency compared to their three-dimensional (3D) counterparts. To overcome the stability limitations while maintaining high efficiency, we introduce a hydrophobic sulfoxonium cation for mixed-dimensional perovskite solar cells (MxD-PSCs). Herein, we employ a novel triple organic cation comprising methylammonium iodide (MAI), formamidinium iodide (FAI), and trimethylsulfoxonium chloride (TMSCl) to formulate MAFA(TMS)_xPbI_3−xCl_x perovskites. The incorporation of TMSCl enhances moisture resistance due to its superior hydrophobicity, while also improving charge transfer and reducing non-radiative recombination as confirmed by optical, morphological, and electrical characterizations. The optimized MxD-PSCs achieve a remarkable power conversion efficiency (PCE) of 21.43%, V_OC of 1.10 V, and J_SC of 24.82 mA cm⁻², with FF being enhanced to 78.5% under one-sun illumination (AM 1.5G). Moreover, optimized MxD-PSCs also perform exceptionally with a PCE of 34.18% under indoor lighting (1000 lux). Furthermore, the devices exhibit outstanding stability, retaining 85% of their initial efficiency after 90 days in an inert environment and 84% after 1000 hours under ambient conditions. These findings highlight the potential of the TMSCl cation for enhancing both the stability and PCE of MxD-PSCs, offering a promising pathway for the development of long-lasting and high-performance PSCs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Bowen Song, Yufei Yu, Zhifei Hu, Shengshan Wan, Wei Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the advancement of deep learning, object detectors (ODs) with various architectures have achieved significant success in complex scenarios like autonomous driving. Previous adversarial attacks against ODs have been focused on designing customized attacks targeting their specific structures (e.g., NMS and RPN), yielding some results but simultaneously constraining their scalability. Moreover, most efforts against ODs stem from image-level attacks originally designed for classification tasks, resulting in redundant computations and disturbances in object-irrelevant areas (e.g., background). Consequently, how to design a model-agnostic efficient attack to comprehensively evaluate the vulnerabilities of ODs remains challenging and unresolved. In this paper, we propose NumbOD, a brand-new spatial-frequency fusion attack against various ODs, aimed at disrupting object detection within images. We directly leverage the features output by the OD without relying on its internal structures to craft adversarial examples. Specifically, we first design a dual-track attack target selection strategy to select high-quality bounding boxes from OD outputs for targeting. Subsequently, we employ directional perturbations to shift and compress predicted boxes and change classification results to deceive ODs. Additionally, we focus on manipulating the high-frequency components of images to confuse ODs' attention on critical objects, thereby enhancing the attack efficiency. Our extensive experiments on nine ODs and two datasets show that NumbOD achieves powerful attack performance and high stealthiness. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

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：