检索结果-内蒙古大学图书馆

SlowFast Based Real-Time Human Motion Recognition with Action Localization

computer Systems Science & engineering 2023年第11期47卷 2135-2152页

作者： Gyu-Il Kim Hyun Yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon16227Korea Contents Convergence Software Research Institute Kyonggi UniversitySuwon16227Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon16227Korea

Artificial intelligence is increasingly being applied in the field of video analysis,particularly in the area of public safety where video surveillance equipment such as closed-circuit television(CCTV)is used and automated analysis of video information is ***,various issues such as data size limitations and low processing speeds make real-time extraction of video data *** analysis technology applies object classification,detection,and relationship analysis to continuous 2D frame data,and the various meanings within the video are thus analyzed based on the extracted basic *** recognition is key in this *** recognition is a challenging field that analyzes human body movements,requiring the interpretation of complex movements of human joints and the relationships between various *** deep learning-based human skeleton detection algorithm is a representative motion recognition ***,motion analysis models such as the SlowFast network algorithm,have also been developed with excellent ***,these models do not operate properly in most wide-angle video environments outdoors,displaying low response speed,as expected from motion classification extraction in environments associated with high-resolution *** proposed method achieves high level of extraction and accuracy by improving SlowFast’s input data preprocessing and data structure *** input data are preprocessed through object tracking and background removal using YOLO and DeepSORT.A higher performance than that of a single model is achieved by improving the existing SlowFast’s data structure into a frame unit *** on the confusion matrix,accuracies of 70.16%and 70.74%were obtained for the existing SlowFast and proposed model,respectively,indicating a 0.58%increase in *** detection,based on behavioral classification,the existing SlowFast detected 2,341,164 cases,whereas the proposed model detected 3,11

关键词： Artificial intelligence convolutional neural network video analysis human action recognition skeleton extraction

来源：评论

学校读者我要写书评

暂无评论

Abnormal Behavior Detection Using Deep-Learning-Based Video Data Structuring

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 2371-2386页

作者： Min-Jeong Kim Byeong-Uk Jeon Hyun Yoo Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Contents Convergence Software Research Institute Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Gyeonggi-doKorea

With the increasing number of digital devices generating a vast amount of video data,the recognition of abnormal image patterns has become more ***,it is necessary to develop a method that achieves this task using object and behavior information within video *** methods for detecting abnormal behaviors only focus on simple motions,therefore they cannot determine the overall behavior occurring throughout a *** this study,an abnormal behavior detection method that uses deep learning(DL)-based video-data structuring is *** and motions are first extracted from continuous images by combining existing DL-based image analysis *** weight of the continuous data pattern is then analyzed through data structuring to classify the overall *** performance of the proposed method was evaluated using varying parameter settings,such as the size of the action clip and interval between action *** model achieved an accuracy of 0.9817,indicating excellent ***,we conclude that the proposed data structuring method is useful in detecting and classifying abnormal behaviors.

关键词： Deep learning object detection abnormal behavior recognition classification data structuring

来源：评论

学校读者我要写书评

暂无评论

Possibilities about the design Lean canvas model and its adaptation in the agile testing

Possibilities about the design Lean canvas model and its ada...

引用

2017 Symposium for Young Scientists in Technology, engineering and Mathematics, SYSTEM 2017

作者： Nidagundi, Padmaraj Novickis, Leonids Faculty of Computer Science and Information Technology Institute of Applied Computer Systems Riga Technical University Riga Latvia Head of the Division of Software Engineering Faculty of Computer Science and Information Technology Riga Technical University Riga Latvia

software development industry is inventing new development methodologies in last 10 years for improving the existing developing tools, process and delivering a high-quality software to end customer in short time. In recent year's waterfall development becomes less attractive in the software industry and shifted its attention towards the new software development methodologies such as agile. Agile brought the new dimension to software development and improved the development, testing process and added new challenges. There are different agile development methodologies in practice such as Scrum, FDD, Kanban, DSDM, XP, ASD, Lean, and Crystal, all these have different approaches in software development but share the same principle of the agile. Nowadays software development process adopted a new number of software tools in the overall process of development and software testing also moved towards the more automation to deploy, validate and verify the software code as early possible. In recent years, lean canvas is used for the planning and validating the business model and this paper will bring more focus on the lean canvas model design adaptation in agile software test strategy building, test planning and guiding the test team to work fast. Copyright © 2017 held by the authors.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

A Patient Specific Algorithm for Plasmodium Malaria Detection on Cell Images

A Patient Specific Algorithm for Plasmodium Malaria Detectio...

引用

2023 IEEE National Aerospace and Electronics Conference, NAECON 2023

作者： Narayanan, Barath Narayanan De Silva, Manawaduge Supun Hardie, Russell C. University of Dayton Research Institute Sensor and Software Systems Division Dayton United States University of Dayton Department of Electrical and Computer Engineering Dayton United States

ISBN: (纸本)9798350338782

computer-aided detection of plasmodium malaria on cell images from digital microscopy provides an invaluable second opinion to medical experts. Traditionally, well-established deep learning algorithms are widely used to detect plasmodium, but these techniques have not been deployed due to the uninterpretable nature of the decisions made by the network. To address this, we present an ensemble method that fuses the predictions based on the class activation mapping (CAM) results from multiple networks via a novel selector network. We study the performance on a publicly available dataset of cell images by using three convolutional neural network architectures, Xception, ResNet50, and InceptionV3,to produce CAM results for the selector network and performance comparison. Our proposed approach helps enhance doctors' trust and outperforms the traditional methods by 1%. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of Linux-based application which supports CDMA and WiBro network

Design and implementation of Linux-based application which s...

引用

8th International Conference Advanced Communication Technology, ICACT 2006

作者： Kim, Dohyung Yun, Minhong Kim, Sunja Lee, Cheol-Hoon Embedded S/W Research Division Electronics and Telecommunications Research Institute Dept. of Computer Engineering System Software Lab. Chungnam National University

ISBN: (纸本)8955191294

This paper describes the design and implementations of the first application service based on embedded Linux;Mobile Teller which uses WiBro network for data communications and CDMA network for voice communications. When a sender on a dual-mode terminal types texts, the texts are transmitted to a TTS server located in the Internet through WiBro network. Subsequently, the TTS server changes the texts into voices and transmits the voice data to the dual-mode terminal. At last the dual-mode terminal sends the voice to the receiver through the CDMA network. In case of noisy environment, Mobile Teller makes user to voice communication.

关键词： computer operating systems

来源：评论

学校读者我要写书评

暂无评论

Full abstractness of a metric semantics for action refinement

引用

Fundamenta Informaticae 1999年第4期40卷 335-382页

作者： Den, Hartog, J.I. De, Vink, E.P. De, Bakker, J.W. Math. and Computer Science Division Vrije Universiteit Amsterdam Netherlands KPN Research Leidschendam Netherlands Department of Software Engineering CWI Amsterdam Netherlands KPN Research P.O. Box 421 2260 AK Leidschendam Netherlands

For a process language with action refinement and synchronization both an operational and a denotational semantics are given. The operational semantics is based on an SOS-style transition system specification involving syntactical refinement sequences. The denotational semantics is an interleaving model which uses semantical refinement 'environments'. It identifies those statements which are equal under all refinements. The denotational model is shown to be fully abstract with respect to the operational one. The underlying metric machinery is exploited to obtain this full abstractness result. Usually, action refinement is treated either in a model with some form of true concurrency, or, when an interleaving model is applied, by assuming that the refining statements are atomized. We argue that an interleaving model without such atomization is attractive as well.

关键词： operational semantics denotational semantics metric topology action refinement full abstractness semantical refinement

来源：评论

学校读者我要写书评

暂无评论

Work in progress: One approach to software engineering project selection for small student populations 125

Work in progress: One approach to software engineering proje...

引用

125th ASEE Annual Conference and Exposition

作者： Bender, Paul A. Ohio Dominican University Department of Software Engineering ColumbusOH United States Division of Mathematics Computer and Natural Sciences Ohio Dominican University United States

software engineering is a discipline that by its nature expects students to engage in group work. Our software engineering program culminates with a senior project course that is intended to provide students with an opportunity to see a software project through one or more increments that can be delivered to the customer. In addition, it is desirable for students to gain real world experience working in a group on a software project for a real customer. Ideally, groups will consist of 3 to 5 students in the senior project course, however, since our program is small, we may have fewer than 3 students enrolled in the course during any given offering. The goal of this work is to find a sustainable method of providing students with opportunities to work on group projects for outside entities, even when the enrollment in the capstone course precludes forming groups of the desired size. Our initial investigation is evaluating the effectiveness of utilizing *** as a source for student projects. *** is a website that seeks to match volunteer developers with projects for non-profit organizations7. By utilizing ***, we provide an opportunity for students to work in a team that includes individuals from outside the institution. Students also have an opportunity to work with a real customer and engage in a service learning project consistent with the university's mission. This work examines two trials. The first trial had a single student participant and was quite successful. The second trial had 4 students participate, but had mixed results. © American Society for engineering Education, 2018.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic load sharing services with OSF DCE 1

Dynamic load sharing services with OSF DCE

引用

1st International Workshop on Services in Distributed and Networked Environments, SDNE 1994

作者： Shi, Shepherd S.B. Lin, David D.H. Yang, C.S. Institute of Computer and Information Engineering National Sun Yat-Sen University Kaohsiung Taiwan Personal Software Division IBM AustinTX78758 United States

ISBN: (纸本)0818658355

This paper presents a dynamic load sharing implementation based on OSF(Open software Foundation) DCE (Distributed Computing Environment). Although DCE provides a wide spectrum of services for developing distributed application, DCE does not provide load sharing services. The proposed algorithm makes use of the technique of threshold and a smoothing function to reduce the overhead incurred by workload information update. The proposed algorithm also considers the heterogeneity of hardware platforms. © 1994 IEEE.

关键词： Functions

来源：评论

学校读者我要写书评

暂无评论

DrDiff: Drug Response Prediction Through Controllable Diffusion-GE and Graph Attention Network 27

DrDiff: Drug Response Prediction Through Controllable Diffus...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Choi, Seungyeon Seo, Samgmin Choi, Jonghwan Park, Chihyun Park, Sanghyun Department of Computer Science Yonsei University Seoul Korea Republic of Division of Software Hallym University Chuncheon Korea Republic of Department of Computer Science and Engineering Kangwon National University Chuncheon Korea Republic of

ISBN: (纸本)9781643685489

The accurate prediction of drug responses based on the genomic profile of a patient is essential to progress in the field of precision *** advent of various deep-learning algorithms based on publicly available large-scale omics datasets is the driving force behind research in this *** characteristics of biological datasets, characterized by high dimensions and low sample sizes, pose challenges of overfitting and limited generalization in prediction ***, constructing prediction models using biological data such as gene expression is further complicated by the need to account for the complex relationships among genes, which exacerbates the aforementioned *** address these challenges, we propose a drug response prediction framework (DrDiff) that integrates a denoising diffusion probabilistic model (DDPM) based data augmentation module with a graph attention network based drug response prediction *** proposed model showed a 10% higher AUC than the state-of-the-art models for drug response prediction for the six drugs considered in the study, suggesting the superior generalization performance of DrDiff over other baseline ***, we demonstrated the feasibility of generative models, which form one of the modules of the proposed framework, in overcoming the fundamental limitations of omics *** experiments bear out the feasibility of generative models, which form one of the modules of the proposed framework, in augmenting gene expression data. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Twin Dual-Arm Robot Testbed to Collect the Human Demonstration Data for Imitation Learning 13

A Twin Dual-Arm Robot Testbed to Collect the Human Demonstra...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Kim, Juhyung Heo, Sungwon Kim, Songwoo Jung, Ho-Jin Yoon, Han Ul Yonsei University Division of Computer and Telecomm. Engineering Mirae Campus Wonju Korea Republic of Graduate School Yonsei University Department of Computer Science Wonju Korea Republic of Yonsei University Division of Software Mirae Campus Wonju Korea Republic of

ISBN: (纸本)9798350373332

Collecting consistent human demonstrations has been a problematic issue in the field of a learning from demonstration. This paper presents a twin dual-arm robot testbed to collect human demonstration data while performing manual tasks in the activities of daily livings such as opening/closing a window, opening-up/closing-down a sauce bottle cap, etc. The testbed consists of the two sets of a dual-arm robot;for each robot, one-side arm has 6-DoF with a crab-gripper as its hand. Two dual-arm robots are mounted at the front and back of a table-type station. A human operator performs actions to complete a given task with the one at the back;the human operator's actions, meanwhile, are duplicated by the other robot at the front simultaneously. The experimental results show the testbed's potential to gather consistent human demonstration data for training a machine learning agent to manipulate the dual-arm robot under an imitation learning framework. © 2024 IEEE.

关键词： Bottles

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：