检索结果-内蒙古大学图书馆

8th International Conference on Inventive Communication and Computational Technologies, ICICCT 2024

作者： Arumugam, M. Arun, G. Mekala, R. Anusuya, K. Department of Computer Technology—PG Kongu Engineering College Tamil Nadu Erode Perundurai638060 India Tamil Nadu Vel Nagar Chennai600062 India Department of Information Science and Engineering Bannari Amman Institute of Technology Tamil Nadu Erode Sathyamangalam638401 India Kongu Engineering College Tamil Nadu Erode Perundurai638 060 India

ISBN: (纸本)9789819777099

Printed circuit boards, or PCBs, are a part of nearly all electronic equipment. The rapid development of integrated circuit and semiconductor technology has made it possible for printed circuit boards (PCBs) to have dimensions as small as a single unit. For this reason, quick and accurate PCB defect detection must be accomplished. Deep learning offers a promising solution for high-precision and rapid defect detection due to its ability to automatically learn complex patterns from data. To identify PCB defects, this research combines deep learning algorithms Faster Region-based Convolutional Neural Network (R-CNN) with computer vision techniques. The study investigates how well different backbone models—ResNet50, MobileNetV2, and EfficientNetB0—work in the Faster R-CNN architecture to accurately detect PCB defects. MobileNetV2 and EfficientNetB0 put computing efficiency first, while ResNet50 is renowned for its depth and capacity to capture fine-grained characteristics. How these changes affect the detection performance will be determined through the comparison analysis. Different backbone architectures provide the model with different computing efficiency and representational capacities, which makes feature extraction and defect detection possible. With the ultimate goal of improving quality control procedures in electronics production, the performance is assessed using an extensive dataset of diverse PCB images. The findings show that it is effective in recognizing and accurately forecasting defects. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Semiconductor device manufacture

来源：评论

学校读者我要写书评

暂无评论

Data Driven Stochastic Game Network-Based Smart Home Monitoring System Using IoT-Enabled Edge Computing Environments

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Verma, Prabal Sood, Sandeep K. Kaur, Harkiran Kumar, Mohit Wu, Huaming Gill, Sukhpal Singh Department of Information Technology National Institute of Technology Srinagar India Department of Computer Applications National Institute of Technology Kurukshetra India Department of Computer Science Guru Nanak Dev University Amritsar India Department of Information Technology National Institute of Technology Jalandhar India Center for Applied Mathematics Tianjin University Tianjin China School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom

Edge computing plays a crucial role in the processing of Consumer Internet of Things (IoT)-enabled latency-sensitive applications. In smart homes, dynamic action strategies based on multiple IoT objects with edge processing can be the best solution for handling adverse events. To overcome these challenges, the use of Stochastic Game Net (SGN) forming IoT devices as players with predefined action sets is one of the feasible solutions. Relative to this context, the edge-assisted IoT-enabled data-driven SGN model is proposed to handle various events in the smart home environment. Stochastic Petri Nets (SPNs) and game theory are integrated into our proposed model to build data-driven dynamic SGNs for the smart home environment. Dynamic SGNs for a comprehensive smart home system are generated in real-time through transitions based on sensor data, enhancing interoperability and scalability in smart home environments. We use the Net logo tool and state-of-the-art smart home sensor datasets to generate dynamic SGNs for various events. Experimental results demonstrate the effectiveness of the proposed model within a data-driven smart home environment. It shows that the present work significantly outperforms other state-of-the-art techniques in terms of decision-making at the edge layer. Moreover, using the proposed system the energy efficacy increased to around 39mJ/K nodes, and the average temporal delay for different events was reduced significantly. IEEE

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Leveraging Point Annotations in Segmentation Learning with Boundary Loss 27th

Leveraging Point Annotations in Segmentation Learning with...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Breznik, Eva Kervadec, Hoel Malmberg, Filip Kullberg, Joel Ahlström, Håkan de Bruijne, Marleen Strand, Robin Department of Information Technology Uppsala University Uppsala Sweden Department of Biomedical Engineering and Health Systems Royal Institute of Technology Stockholm Sweden Antaros Medical Mölndal Sweden Department of Surgical Sciences Uppsala University Uppsala Sweden Department of Radiology and Nuclear Medicine Erasmus MC Rotterdam Netherlands Department of Computer Science University of Copenhagen Copenhagen Denmark

ISBN: (纸本)9783031782008

This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design, the boundary loss imposes a stronger penalty on the errors the farther away from the object boundary they occur. Hence it is inappropriate for cases of weak supervision where the ground truth label is much smaller than the actual object and a certain amount of false positives (w.r.t. the weak ground truth) is actually desirable. Using intensity-aware distances instead may alleviate this drawback, allowing for a certain amount of false positives with similar intensities without a significant increase to the training loss. This formulation is potentially more attractive than existing CRF-based regularizers, due to its simplicity and computational efficiency. We perform experiments on two multi-class datasets;ACDC (heart segmentation) and POEM (whole-body abdominal organ segmentation). Results are encouraging and show that this supervision strategy has great potential. On ACDC it outperforms the CRF-loss based approach, and on POEM data it performs on par with it. The code is made openly available. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Prediction Approach for Diabetic Retinopathy Using Deep Learning Based Convolutional Neural Networks Algorithm by Means of Retina Photographs

引用

computers, Materials & Continua 2021年第2期66卷 1613-1629页

作者： G.Arun Sampaul Thomas Y.Harold Robinson E.Golden Julie Vimal Shanmuganathan Seungmin Rho Yunyoung Nam CSE Department J.B.Institute of Engineering and TechnologyHyderabad500075India School of Information Technology and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Engineering Anna University Regional CampusTirunelveli627007India Department of Information Technology National Engineering CollegeKovilpatti628503India Department of Software Sejong University209 Neungdong-roGwangjin-guSeoul05006Korea Department of Computer Science and Engineering Soonchunhyang UniversityAsan31538Korea

Retinopathy is a human eye disease that causes changes in retinal blood vessels that leads to bleed,leak fluid and vision *** of retinopathy are blurred vision,changes in color perception,red spots,and eye pain and it cannot be detected with a naked *** this paper,a new methodology based on Convolutional Neural Networks(CNN)is developed and proposed to intelligent retinopathy prediction and give a decision about the presence of retinopathy with automatic diabetic retinopathy screening with accurate *** CNN model is trained by different images of eyes that have retinopathy and those which do not have *** fully connected layers perform the classification process of the images from the dataset with the pooling layers minimize the coherence among the adjacent *** feature loss factor increases the label value to identify the patterns with the kernel-based *** performance of the proposed model is compared with the related methods of DREAM,KNN,GD-CNN and *** results show that the proposed CNN performs better.

关键词： Convolutional neural networks dental diagnosis image recognition diabetic retinopathy detection

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Machine Learning Classification Algorithms for Breast Cancer Diagnosis 9

Performance Analysis of Machine Learning Classification Algo...

引用

9th IEEE International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2021

作者： Gupta, Gargi Sharma, Medhavani Choudhary, Shalu Pandey, Kavita Jaypee Institute of Information Technology Department of Computer Science and Engineering India

ISBN: (纸本)9781665417037

Machine Learning based learning algorithms gives the machine the power to learn on its own without being explicitly programmed by a programmer. It helps in automating the task like classification, clustering, etc. which previously required human intervention. Machine Learning-based classification algorithms today are being widely used for the diagnosis of various diseases such as Breast Cancer. Breast Cancer is one of the primary causes of death among women all over the world in the past recent years. In this paper, Random Forest, Logistics Regression, Decision Tree, Naive Bayes and SVM classification algorithms have been implemented. The experiment in this article has been conducted on the most popular Wisconsin Diagnosis Breast Cancer Dataset (WDBC)[l]. The main objective of conducting this experiment is to analyze the correctness and accuracy of classification algorithms used to classify cancer-causing tumours (Malignant) from non-cancerous tumours (Benign) with the highest precision and accuracy. The experiment results show that Random Forest gave the highest accuracy amongst all the classification algorithms. © 2021 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Performance and Security Analysis in Cloud Using Drops and T-Coloring Methods 4

Performance and Security Analysis in Cloud Using Drops and T...

引用

4th International Conference on Emerging Research in Electronics, computer science and technology, ICERECT 2022

作者： Reddy, A.Basi Kumar, R.Yogesh Raj Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Bharath Institute of Higher Education and Research Department of Information Technology Chennai India

ISBN: (纸本)9781665456357

Data outsourcing to a 3rd party organize, as is done with cloud computing, raises security concerns. Data outsourcing may result from attacks just on cloud by the other users and nodes. Therefore, to protect data on the cloud, strict security measures are required. The rate at which data could be retrieved must be optimized by the implemented security solution. This work suggests the splitting and replication the data in the cloud with optimal system efficiency (DROPS), which adopts a thorough strategy to the security and efficiency concerns. In accordance with the DROPS method, split a file into fragments, then replicate the information among some of the cloud server. In order to guarantee that in the event of a successful assault, the adversary would not gain any useful information, each node merely retains a single fragment of a particular data file. In order to prevent an adversary from determining out the pieces, the nodes which store them are also spaced separated by a specific amount utilizing graph T-coloring. © 2022 IEEE.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

An Efficient IoT-Blockchain Sharding Technique using Frequently Transacting Sender and Receiver information

An Efficient IoT-Blockchain Sharding Technique using Frequen...

引用

International Conference for Convergence of technology (I2CT)

作者： Pramod Jain S A Yashaswini H M Sanket Salvi Nupur Dashputre Saanya Tyagi Krishna Panchal Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bangalore Karnataka Department of Computer Science and Engineering Dr. Ambedkar Institute of Technology Bangalore Karnataka School of Computer Engineering Technology MIT World Peace University Maharashtra India

ISBN: (数字)9798350394474

ISBN: (纸本)9798350394481

Distributed systems have become an integral part of many modern applications, processing large amounts of data and serving large numbers of users simultaneously. However, as these systems grow in size and complexity, it becomes increasingly difficult to ensure optimal performance and scalability. This scenario is more common for Internet of Things (IoT) applications. In this research, the problem of limited scalability of IoT frameworks is addressed by proposing a blockchain-integrated new sharding algorithm. The algorithm is based on analyzing transaction records of frequently traded sender-receiver pairs. Our goal is to improve the overall performance of the system and improve its ability to handle higher volumes of transactions. By analyzing a real dataset, we observed a significant reduction in overall execution time by about 10%, demonstrating the effectiveness of our proposed sharding algorithm. Additionally, we found that the algorithm continued to improve the transaction per second rate (TPS) as the number of tasks processed increased. These results highlight the potential of our proposed method for optimizing the efficiency and scalability of distributed systems. Further investigation and analysis across different datasets and system configurations are recommended to validate the generalizability and effectiveness of our approach.

关键词： Measurement Sharding Scalability System performance Distributed databases Receivers Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Physics-aware cross-domain fusion aids learning-driven computer-generated holography

引用

Photonics Research 2024年第12期12卷 2747-2756页

作者： GANZHANGQIN YUAN MI ZHOU FEI LIU MU KU CHEN KUI JIANG YIFAN PENG ZIHAN GENG Institute of Data and Information Tsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen 518071China School of Optoelectronic Engineering Xidian UniversityXi’an 710071China Department of Electrical Engineering City University of Hong KongHong Kong SARChina School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China Department of Electrical and Electronic Engineering The University of Hong KongHong Kong SARChina Department of Computer Science The University of Hong KongHong Kong SARChina

The rapid advancement of computer-generated holography has bridged deep learning with traditional optical principles in recent ***,a critical challenge in this evolution is the efficient and accurate conversion from the amplitude to phase domain for high-quality phase-only hologram(POH)*** computational models often struggle to address the inherent complexities of optical phenomena,compromising the conversion *** this study,we present the cross-domain fusion network(CDFN),an architecture designed to tackle the complexities involved in POH *** CDFN employs a multi-stage(MS)mechanism to progressively learn the translation from amplitude to phase domain,complemented by the deep supervision(DS)strategy of middle features to enhance task-relevant feature learning from the initial ***,we propose an infinite phase mapper(IPM),a phase-mapping function that circumvents the limitations of conventional activation functions and encapsulates the physical essence of *** simulations,our proposed method successfully reconstructs high-quality 2K color images from the DIV2K dataset,achieving an average PSNR of 31.68 dB and SSIM of ***,we realize high-quality color image reconstruction in optical *** experimental results highlight the computational intelligence and optical fidelity achieved by our proposed physics-aware cross-domain fusion.

关键词： computer cross holography

来源：评论

学校读者我要写书评

暂无评论

The Design of AI Algorithms for DG Setting 4

The Design of AI Algorithms for DG Setting

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Ganeshkumar, N. Das, Purushottam Hussein, Laith Dhabliya, Dharmesh Al Hassan Alhaidry, Wesam Abed Jweeg, Muhsin Al-Ansari, Ahmed Saadalwan, Ali Gitam School of Technology Department of Computer Science and Engineering Karnataka India Department of Cse Graphic Era Hill University Uttarakhand Dehradun India Graphic Era Deemed to Be University Uttarakhand Dehradun India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Vishwakarma Institute of Information Technology Information Technology Department Pune India National University of Science and Technology College of Technical Engineering DhiQar Iraq Al-Farahidi University Baghdad Iraq Al-kunooze University College Dental Department Basra Iraq Kut University College Business Administration Department wasit Al kut52001 Iraq

ISBN: (纸本)9798350360165

Artificial intelligence (AI) is the bedrock of management systems and will continue to support human society both now and in the future. These systems' decision-making processes must be transparent, especially in sensitive areas such as autonomous driving and healthcare, to build trust. Although methods exist for achieving algorithmic transparency, there are no well-established design techniques to systematically address descriptive issues when reviewing AI. In response, we introduce the Explainability in Design (EID) approach, which operationalizes the definition of AI into six fundamental concepts. EID was refined through iterative empirical studies, including applied learning and interviews with practitioners. An empirical study with AI system designers tested the utility of EID, demonstrating its effectiveness in reducing barriers to integrating explanatory functionality in AI systems and enhancing decision-making processes. © 2024 IEEE.

关键词： Autonomous Vehicles Design Methods Empirical Research Explanatory Capabilities Healthcare

来源：评论

学校读者我要写书评

暂无评论

Building Credibility, Trust, and Safety on Video-Sharing Platforms

Building Credibility, Trust, and Safety on Video-Sharing Pla...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Niu, Shuo Lu, Zhicong Zhang, Amy X. Cai, Jie Griggio, Carla F. Heuer, Hendrik Computer Science Clark University WorcesterMA United States Department of Computer Science City University of Hong Kong Hong Kong Allen School of Computer Science & Engineering University of Washington SeattleWA United States College of Information Sciences and Technology Pennsylvania State University University ParkPA United States Department of Computer Science Aarhus University Aarhus Denmark Institute for Information Management Bremen University of Bremen Bremen Germany

ISBN: (纸本)9781450394222

Video-sharing platforms (VSPs) such as YouTube, TikTok, and Twitch attract millions of users and have become influential information sources, especially among the young generation. Video creators and live streamers make videos to engage viewers and form online communities. VSP celebrities obtain monetary benefits through monetization programs and affiliated markets. However, there is a growing concern that user-generated videos are becoming a vehicle for spreading misinformation and controversial content. Creators may make inappropriate content for attention and financial benefits. Some other creators also face harassment and attack. This workshop seeks to bring together a group of HCI scholars to brainstorm technical and design solutions to improve the credibility, trust, and safety of VSPs. We aim to discuss and identify research directions for technology design, policy-making, and platform services for video-sharing platforms. © 2023 Owner/Author.

关键词： Accident prevention

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：