检索结果-内蒙古大学图书馆

IAENG International Journal of computer science 2022年第1期49卷 260-269页

作者： Li, M.Y. Zhao, J. Master’s Student of School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

Accurately detecting the keypoints of small persons in an image using bottom-up multi-person pose estimation algorithms is exceptionally difficult owing to scale variation challenges. HigherHRNet initially solved the challenge of multi-player scale change pose estimation. However, because it uses repeated cross-scale fusion, owing to inherent defects in channel reduction, semantic information is lost. Furthermore, the aliasing effects produced by the miscellaneous feature maps formed after cross-scale fusion have a significant impact on the detection accuracy of small persons. In this paper, we propose a novel bottom-up human pose estimation algorithm based on HigherHRNet, called Channel-Enhanced HigherHRNet (CE-HigherHRNet). CE-HigherHRNet comprises three main components: a multiscale sub_pixel skip fusion module, a lightweight attention mechanism (with channel attention enhanced and spatial attention modules), and a high-resolution feature pyramid with an added Dupsampling module. The lightweight attention mechanism optimizes the feature map after each fusion. Deconvolution is replaced with Dupsampling, which strengthens the network’s scale awareness and makes it more sensitive to robust scale changes. The average precision (AP) of CE-HigherHRNet on the COCO test-dev dataset was 71.9% (an improvement of 1.4% compared with HigherHRNet). Furthermore, the average detection accuracy of small persons was 68.1% AP (an improvement of 1.5% AP). These results verify that the proposed CE-HigherHRNet is more robust in processing scale changes and has a stronger ability to handle crowded environments. Thus, it is more accurate in positioning small persons in images and human bodies in crowded environments. © 2022. All Rights Reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Milling Force Prediction of Titanium Alloy Based on Support Vector Machine and Ant Colony Optimization

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第2期48卷 1-12页

作者： Zhang, Xiaoxia Yu, Ziqiao Hu, Yinyin Yang, Jiao A Professor of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan11041 China A Master Student of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Milling force prediction of titanium alloy plays an important role in titanium alloy milling process. In the article, the milling process of titanium alloy materials is analyzed, and this material quality is affected directly by the milling force. Support vector machine (SVM) has shown prominent performance for many real-world problems. However, SVM computational complexity increases, as the number of samples increases. How to effectively apply it to massive datasets is still a serious challenge. Although there are some literatures on parameter optimization techniques of SVM regression, the performance of this model still needs to be further studied and improved. We present a new milling force predicting model, namely ACO&SVM, which integrate SVM regression with ACO algorithm to enhance the prediction accuracy of milling force for mill process of titanium alloy. The primary innovation feature of hybrid model is to apply the ACO to automatically determine parameters of SVM regression model. In addition, as being applied to discrete optimization, to solve continuous optimization problems, ACO algorithm needs to transform continuous variables into discrete ones by discretizing of continuous variables. The results have shown that proposed ACO&SVM model yields better prediction accuracy, and thus it can be widely applied to the fields of material processing optimization. © 2021. All Rights Reserved.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Cuckoo Search for the Resources-Constrained Project Scheduling Problem

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2021年第2期48卷 1-12页

作者： Shen, Xin Zhang, Xiaoxia Yu, Ziqiao X. Shen is a Master Student of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China X. X. Zhang is a Professor of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan11041 China A Master Student of School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Resource-constrained project scheduling problem (RCPSP) is a kind of representative practical engineering problem, the purpose is to schedule activities in the project through rational use of limited resources in the minimum time. This paper proposes an improved hybrid cuckoo algorithm (CS&SA) to solve the RCPSP problem. Firstly, the individual elements are randomly coded into priority vectors, and the population is decoded using serial scheduling to convert the individual into a set of task scheduling sequences. Secondly, the Levy flight is redesigned to change the algorithm from random walk to adaptive as the population fitness changes. Then, this article adds three neighborhood update techniques to meet the update requirements of the algorithm at different stages. Finally, in order to prevent the algorithm from falling into a local optimum, this paper introduces a simulated annealing strategy to allow the algorithm to accept some individuals with poor quality with a certain probability in each iteration. In the testing part, this paper firstly tests the effectiveness and optimization of three different-scale examples in the classic example library PSPLIB for RCPSP problems. Among them, the average error of the CS&SA algorithm in the small-scale J30 is 0.25%, and the average error in the medium-scale J60 is 11.21%, and the average error of the large-scale J120 is 19.83%. Then, by comparing other intelligent optimization algorithms, it is proved that NCS&SA is superior to other algorithms in optimization and accuracy. © 2021. All Rights Reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A light-weight tool for teaching the development and evaluation of requirements documents

A light-weight tool for teaching the development and evaluat...

引用

113th Annual ASEE Conference and Exposition, 2006

作者： Garbers, Ben Periyasamy, Kasi University of Wisconsin La Crosse United States Master of Software Engineering Program University of Wisconsin La Crosse United States IBM Computer Science Department Program University of Wisconsin La Crosse United States

Writing correct and consistent software requirements specification (SRS) is one of the most important goals of a requirements engineering process. The SRS serves as the basis for subsequent design, testing and maintenance of the software product. The more errors and inconsistencies contained in an SRS, the more time and efforts are required to correct them at a later stage in the development process. Most SRS documents are manually typed using a word processor and hence the writer is responsible for ensuring the correctness and consistency of the document. Without adequate tool support, the manual construction and analysis of SRS documents is a tedious process and is error-prone. This paper describes an interactive tool developed at the University of Wisconsin-La Crosse that assists students preparing an SRS document based on the IEEE standard 83019981. The tool provides an easy-to-use interface and the ability to create, edit, load and save SRS documents. In addition, it evaluates the requirements document based on criteria published by the software Metrics program at the software Assurance Technology Center, NASA2. A function-point metrics analyzer is also built into the tool so that the efforts required to complete the project specified in the document can be evaluated. © American Society for engineering Education, 2006.

关键词： computer aided software engineering

来源：评论

学校读者我要写书评

暂无评论

Proposal Based Studio Projects: How to Avoid Producing "Cookie Cutter" software Engineers

Proposal Based Studio Projects: How to Avoid Producing "C...

引用

Conference on software engineering Education & Training (CSEE&T)

作者： David Root Mel Rosso-Llopart Gil Taran Master of Software Engineering Programs Institute for Software Research School of Computer Science Carnegie Mellon University Pittsburgh PA USA

ISBN: (纸本)9780769531441

The proposal based studio is a method to teach software engineers best practices without developing a "cookie cutter" environment. It teaches students how to get projects done in the fixed time of a degree program without relying on a dogmatic, fixed "recipe" process. This paper discusses how students are provided a template with six general process areas for which they must "propose" solutions. These proposed solutions are unique to each 4 to 5 member master of software engineering team and are continuously reviewed by the faculty throughout the project.

关键词： Proposals software engineering computer science education Educational programs Gas insulated transmission lines computer science Best practices computer industry software development management Programming

来源：评论

学校读者我要写书评

暂无评论

Continuing Challenges in Selecting Industry Projects for Academic Credit: Points to Consider and Pitfalls to Avoid

Continuing Challenges in Selecting Industry Projects for Aca...

引用

Conference on software engineering Education & Training (CSEE&T)

作者： Gil Taran Dave Root Mel Rosso-Llopart Master of Software Engineering Programs Institute for Software Research School of Computer Science Carnegie Mellon University Pittsburgh PA USA

ISBN: (纸本)9780769531441

Many academic programs use industrial projects within their teaching curriculum. These provide an exposure to real customers, challenging problems currently faced by industry and the opportunity to interact with working professionals in a situation driven by quality, schedules, and users. Selecting projects that fit todaypsilas academic environment, is a constant challenge. This paper presents how at Carnegie Mellon we have refined our project selection criteria to provide a better fit between our needs and those of our industrial partners. Criteria, issues to consider and pitfalls to avoid in the project selection process will be discussed.

关键词： software engineering computer industry Industrial training Risk management Industrial relations computer science education Continuing education Educational programs Gas insulated transmission lines computer science

来源：评论

学校读者我要写书评

暂无评论

Exporting Studio: Critical Issues to Successfully Adopt the software Studio Concept

Exporting Studio: Critical Issues to Successfully Adopt the ...

引用

Conference on software engineering Education & Training (CSEE&T)

作者： David Root Mel Rosso-Llopart Gil Taran Master of Software Engineering Programs Institute for Software Research School of Computer Science Carnegie Mellon University Pittsburgh PA USA

ISBN: (纸本)9780769531441

In 1989 the professional masters of software engineering (MSE) program at Carnegie Mellon initiated a new approach to graduate level software projects: the software development studio. In 2002 the studio concept was first exported under a cooperative program to teach software engineering at an international partner university. However, CMU quickly determined that student projects, at this partner, lacked progress compared to their CMU counterparts. This paper will focus on the critical lessons that were learned from this ldquoexportrdquo that not only has helped this partnership but also others that are just starting.

关键词： software engineering Programming Educational programs Project management software systems computer science education Gas insulated transmission lines computer science History software development management

来源：评论

学校读者我要写书评

暂无评论

Hybrid Convolutional Neural Networks for Enhanced Detection of Mango Leaf Diseases 6

Hybrid Convolutional Neural Networks for Enhanced Detection ...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Porna, Shweta Bhattacharjee Kabir, Md. Firoz Rana, Md. Imran Chowdhury Sajol, Md. Saiful Islam Roy, Tonmoy Khan, Mohammad Aman Ullah Adnan, Md. Al Bhavani, Girigula Durga Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh Master's in Information Technology University of the Cumberlands United States Bachelor of Business Administration International American university Los Angeles CA United States Louisiana State University Department of Computer Science and Engineering LA United States Data Analytics & Information Systems Utah State University Logan United States Brac University School of Data and Sciences Department of Computer Science and Engineering Dhaka1212 Bangladesh Noakhali Science And Technology University Bsc in software engineering Bangladesh Andhra Pradesh Amaravati522237 India

ISBN: (纸本)9798331505790

The classification of mango leaf diseases is critical for effective disease management and ensuring high-quality yields in mango cultivation. This paper presents a comprehensive study on using deep learning techniques to classify various mango leaf diseases, leveraging convolutional neural networks (CNNs) and hybrid models. A total of 7,524 images were used in our study. These included 4,000 training samples and 3,524 testing samples. The images were split into eight groups, which were powdery mildew, cutting weevil, anthracnose, bacterial canker, sooty mold, gall midge, healthy, and die back. The suggested method starts with feature extraction using VGG19 and MobileNetB1, then classification using both standalone models (ResNet50V2 + EfficientNetB1 and VGG16 + MobileNetB1). We employed data augmentation techniques like random brightness adjustment, rotation, and flipping to enhance the robustness of the model. We conducted hyperparameter tuning using hyperband and Bayesian optimization to optimize the model's performance. Experimental results demonstrate that the hybrid models achieved superior performance, with ResNet50V2 and EfficientNetB1 attaining a perfect accuracy of 100 % on the test set. These findings highlight the potential of deep learning techniques to improve the accuracy and reliability of mango leaf disease diagnosis, contributing significantly to the advancement of precision agriculture. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Learning and using the cognitive walkthrough method: a case study approach 95

Learning and using the cognitive walkthrough method: a case ...

引用

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

作者： Bonnie E. John Hilary Packer Departments of Computer Science and Psychology and the HCI Institute Carnegie Mellon University Pittsburgh PA Master of Software Engineering Program Carnegie Mellon University Pittsburgh PA

来源：评论

学校读者我要写书评

暂无评论

The Role of AI in Healthcare Policy Development and Management 1

The Role of AI in Healthcare Policy Development and Manageme...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Yadav, Sapna Mane, Pravin Swarnkar, Virendra Kumar Rawandale, Shital Kumar Patil, Alaknanda S. Katke, Kiran S. Bhat, Niyati Entrepreneurship Mindset Curriculum State Council of Educational Research and Training Delhi India Institute of Management and Entrepreneurship Development Pune India Bharti Vishwavidyalaya Department of Computer Science & Engineering Chhattisgarh Durg India Dean Industry Institute Interaction PCET's Pimpri Chinchwad College of Engineering Maharashtra Pune India Jspm Ntc E&tc Department Pune India Sanjivani College of Engineering Kopergaon Ahmednagar Department of Computer Engineering India Software Developer Master of Science California State University Long Beach CA90840 United States

ISBN: (纸本)9798350330915

This study looks at how artificial intelligence (AI) is incorporated into healthcare policy, with an emphasis on how it affects administrative procedures, treatment optimization, especially clinical choice support. Using a deductive methodology and interpretive thinking as a philosophy, an exploratory design with secondary data collecting was used. In the present-day environment, AI is being used more frequently in healthcare legislation, especially within medical settings. Clinical decision-making systems driven by AI have shown to offer a great promise for lowering diagnostic mistakes and increasing treatment precision. Improving patient outcomes through individualized AI-driven treatments for treatment improvement appears promising. But there are issues with algorithm prejudices as well as information privacy, among other ethical and legal issues. Establishing thorough guidelines, ongoing education, and auditing procedures are among the suggestions that are made. In order to guarantee fair and efficient integration of health care legislation, future research should prioritize longitudinal research and improving artificial intelligence algorithms © 2023 IEEE.

关键词： Artificial Intelligence Clinical Decision Support Ethical Considerations Healthcare Policy Treatment Optimization

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：