检索结果-内蒙古大学图书馆

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Yuan, Tailan Xiong, Wen Yun, Lijun School of Information Science and Technology Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Kunming China

ISBN: (纸本)9798350319934

As the network-structure complexity and the passenger volume continuously grow, how to accurately perform passenger flow guidance is a crucial issue for metro operators. Transfer route recommendation is a core approach for passenger flow guidance. Existing works are limited in obtaining route attributes (such as transfer walking time and waiting time, etc.). Furthermore, most of existing methods may not work well in the scenario of sudden passenger flow, because of their limited capability to accurately measure the real-time crowding. To address these issues, a data fusion based transfer route recommendation method (DFTRR) is proposed. Specifically, we first propose a spatio-temporal diversity-based method (STD) to measure the trajectory similarity. Based on that, we fuse two kinds of heterogeneous data, i.e., swiping records of smart cards and Wi-Fi signal records of mobile devices to extract a passenger's complete trip. And then we present the historical median travel time to alleviate the computation issue of route attributes. Meanwhile the mean crowding level is introduced to accurately measure the real-time crowding of routes. Finally, a generalized travel cost based on median travel time, number of transfers and mean crowding level is constructed for transfer route recommendation. The experimental results illustrate that the accuracy of STD algorithm is higher than the baseline 34.92% at maximum;DFTRR can offer the optimal transfer route according to passengers' preferences under sudden passenger flow. © 2022 IEEE.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Live Demonstration: A fully embedded adaptive real-time hand gesture classifier leveraging HD-sEMG and deep learning

Live Demonstration: A fully embedded adaptive real-time hand...

引用

IEEE Biomedical Circuits and systems (BIOCAS)

作者： Xavier Isabel Thomas Labbé Félix Chamberland Étienne Buteau Evan Campbell Ulysse Côté-Allard Simon Tam Paul Fortier Alexandre Campeau-Lecours Mounir Boukadoum Erik Scheme Benoit Gosselin Electrical Engineering and Computer Engineering Department Laval University Institute of Biomedical Engineering University of New-Brunswick Department off Technology Systems University of Oslo Mechanical Engineering Department Laval University Computer Science Department University of Quebec at Montreal

In a fully immersive virtual reality setting, visitors will actively participate in our demonstration, engaging in an interactive videogame utilizing our cutting-edge HD-sEMG Bracelet. Prior to this, they will undergo state-of-the-art training to personalize their machine learning gesture recognition model. The gameplay will be broadcast on a computer monitor, allowing onlookers to observe while the demonstrator explains the core concept of our work. By wearing the bracelet, the player gains control over their limb in a game inspired by Simon Says. Throughout the demonstration, visitors will gain firsthand experience and knowledge about the forthcoming advantages of HD-sEMG for control applications, such as prosthesis control. They will also discover how the EMaGer HD-sEMG Bracelet capitalizes on its uniform and high electrode density to enhance the reliability of hand gesture recognition models utilized in myoelectric prosthesis control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-talker Verbal Interaction for Humanoid Robots

Multi-talker Verbal Interaction for Humanoid Robots

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Bartlomiej Klin Ryszard Beniak Michal Podpora Arkadiusz Gardecki Joanna Rut Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Department of Computer Science Opole University of Technology Faculty of Production Engineering and Logistics Opole University of Technology

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

Working in multi-talker mode is viable under certain conditions, such as the fusion of audio and video stimuli along with smart adaptive beamforming of received audio signals. In this article, the authors verify part of the researched novel framework, which focuses on adapting to dynamic interlocutor’s location changes in the engagement zone of humanoid robots during the multi-talker conversation. After evaluating the framework, the authors confirm the necessity of a complementary and independent method of increasing the interlocutor’s signal isolation accuracy. It is necessary when video analysis performance plummets. The authors described the leading cause as insufficient performance during dynamic conversations. The video analysis cannot derive a new configuration when the interlocutor’s speech apparatus moves beyond the expected margin and the video frame rate drops.

关键词： Automation Accuracy Array signal processing Humanoid robots Oral communication Human factors

来源：评论

学校读者我要写书评

暂无评论

Detection of the Optimal Reflection Symmetry Axis with the Jaccard Index and the Radon Transform

Detection of the Optimal Reflection Symmetry Axis with the J...

引用

2022 International Russian Automation Conference, RusAutoCon 2022

作者： Lomov, Nikita Seredin, Oleg Kushnir, Olesia Tula State University Office of Research and Development Tula Russia 'Computer Science and Control' of the Russian Academy of Sciences Complex Systems Department Federal Research Center Moscow Russia Tula State University Cognitive Technologies and Simulation Systems Lab Tula Russia

ISBN: (数字)9781665466554

ISBN: (纸本)9781665466554

This study determines the optimal reflection symmetry axis of an object in a binary image using the Jaccard index. We propose to find the global optimum on the grid by estimating the upper bounds of the Jaccard index with the Radon transform. Several approaches to improving the Jaccard index computation for a given line are considered. It is shown that for the shear symmetry the optimal skew for a candidate symmetry axis can be found analytically. Some strategies for enumerating possible symmetry axes and selecting the initial approximation are proposed. The experiments show that the Jaccard index for the optimal axis found by the proposed method is not inferior to the exhaustive brute-force of the axes passing through the points of the object contour considering the rasterization error. In terms of speed, the proposed method significantly exceeds the previously developed methods for limiting the exhaustive search. © 2022 IEEE.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Large-scale Path Planning and Time Window Allocation in UAV-assisted Wireless Sensor Networks with Variational Multi-dimensional Optimization

Large-scale Path Planning and Time Window Allocation in UAV-...

引用

IEEE International Conference on Automation science and engineering (CASE)

作者： Boyuan Zhang Rui Lai Guanghong Gong Haitao Yuan Jinhong Yang Jia Zhang MengChu Zhou School of Automation Science and Electrical Engineering Beihang University Beijing China CSSC Systems Engineering Research Institute in Beijing China Department of Computer Science Lyle School of Engineering at Southern Methodist University Dallas TX USA Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Wireless Sensor Networks (WSNs) have been widely deployed, and it is crucial to enhance their network longevity and transmission efficiency. This work comprehensively considers communication interference, transmission rate constraints, and motion constraints of Unmanned Aerial Vehicles (UAVs). We propose an energy-efficient UAV-assisted WSN framework with big data transmission. To minimize the weighted sum of UAV’s and WSNs’ energy consumption, we jointly optimize sensor clustering, path planning, and time window allocation by an improved intelligent optimization algorithm assisted by deep learning named Variational Multidimensional Optimization (VMO) with co-evolved Multiple Subpopulations, noted as VMOMS for short. The effectiveness of the proposed VMOMS algorithm for solving high-dimensional problems is demonstrated through numerical analysis and simulation results. These findings highlight the efficiency and practicality of the designed UAV-assisted hierarchical architecture of WSNs, thereby showcasing its potential to enable reliable data transmission from remote WSNs to a centralized cloud server.

关键词： Wireless sensor networks Clustering algorithms Big Data Autonomous aerial vehicles Path planning Energy efficiency Peer-to-peer computing Resource management Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Requirements for Building a Business-Driven Reference Architecture for Implementation of Big Data Analytics by Public Sector Organizations: A Case Study of Uganda

Requirements for Building a Business-Driven Reference Archit...

引用

Advancements of Artificial Intelligence in African Context (AAIAC), International Conference on the

作者： Matendo Didas Frederick Chali Noe Elisa Jabhera Matogoro Department of Information Systems and Technology The University of Dodoma Dodoma Tanzania Department of Computer Science and Engineering The University of Dodoma Dodoma Tanzania

Big Data Analytics (BDA) technology is an emerging desire within public sector organizations. It can be applied to meet the rising global demand for informed decision-making and cost-effective and reliable public services. As a result, BDA has been put forward on the planning agendas of different public sector organizations and governments at large. However, regardless of BDA technologies being widely spread, there is a high failure rate associated with BDA implementation projects in public sector organizations. The paper determines the requirements for designing business-driven reference architecture for the implementation of BDA by public sector organizations, taking Uganda as a case study for developing countries, considering The Uganda Bureau of Statistics, the Ministry of Health, and the Ministry of Education purposively chosen. To accomplish the study's goals, the mixed research methodology (Questionnaire and Mini-literature review) was used. The study used a questionnaire and conducted a mini literature review executed under design science research methodology. The questionnaire was given to 36 Information Technology (IT) and Managerial (M) staff. Some of the derived requirements by the study that need public sector organizations’ attention include; the component for identifying the business process/Use case first for which data is needed so that these business processes generate added business value to the public sector organization in question, need to support diversified processing and analysis (like predictive, batch-oriented, real-time, and stream, among others), need to support high-level/advanced data security measures such as time multiplexing and Key management, component to support low, medium, and high volumes of data among others.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benefits and drawbacks of radiofrequency ablation via percutaneous or minimally invasive surgery for treating hepatocellular carcinoma

引用

World Journal of Gastrointestinal Surgery 2024年第11期16卷 3400-3407页

作者： Ching-Lung Hsieh Cheng-Ming Peng Chun-Wen Chen Chang-Hsien Liu Chih-Tao Teng Yi-Jui Liu Department of Computer Science and Information Engineering Feng Chia UniversityTaichung 40724Taiwan Department of Surgery Chung Shan Medical University HospitalTaichung 40201Taiwan School of Medicine Chung Shan Medical UniversityTaichung 40201Taiwan Department of Radiology Taichung Armed Forces General HospitalTaichung 406Taiwan Department of Medical Imaging and Radiological Sciences Central Taiwan University of Science and TechnologyTaichung 406Taiwan Department of Radiology School of MedicineNational Defense Medical CenterTaipei 11490Taiwan Department of Medical Imaging China Medical University Hsinchu Hospital and China Medical UniversityHsinchu 302Taiwan Institute of Nuclear Engineering and Science National Tsing Hua UniversityHsinchu 300Taiwan Department of Radiology Nantou Hospital of the Ministry of Health and WelfareNantou 540Taiwan Master’s Program of Biomedical Informatics and Biomedical Engineering Feng Chia UniversityTaichung 407Taiwan Department of Automatic Control Engineering Feng Chia UniversityTaichung 407Taiwan

The management of early stage hepatocellular carcinoma(HCC)presents significant *** radiofrequency ablation(RFA)has shown safety and effectiveness in treating HCC,with lower mortality rates and shorter hospital stays,its high recurrence rate remains a significant ***,achieving improved survival solely through RFA is challenging,particularly in retrospective studies with inherent *** is commonly used for guiding percutaneous RFA,but its low contrast can lead to missed tumors and the risk of HCC *** enhance the efficiency of ultrasound-guided percutaneous RFA,various techniques such as artificial ascites and contrast-enhanced ultrasound have been developed to facilitate complete tumor *** invasive surgery(MIS)offers advantages over open surgery and has gained traction in various surgical *** studies suggest that laparoscopic intraoperative RFA(IORFA)may be more effective than percutaneous RFA in terms of survival for HCC patients unsuitable for surgery,highlighting its ***,combining MIS-IORFA with these enhanced percutaneous RFA techniques may hold greater significance for HCC treatment using the MIS-IORFA *** article reviews liver resection and RFA in HCC treatment,comparing their merits and proposing a trajectory involving their combination in future therapy.

关键词： Percutaneous radiofrequency ablation Minimally invasive surgery Hepatocellular carcinoma Intraoperative radiofrequency ablation Contrast-enhanced ultrasound

来源：评论

学校读者我要写书评

暂无评论

MSConv: Multiplicative and Subtractive Convolution for Face Recognition

arXiv

引用

arXiv 2025年

作者： Zhou, Si Si, Yain-Whar Yuan, Xiaochen Li, Xiaofan Liu, Xiaoxiang Zhang, Xinyuan Lin, Cong Gong, Xueyuan School of Intelligent Systems Science and Engineering Jinan University Guangdong China Department of Computer and Information Science University of Macau China Faculty of Applied Sciences Macau Polytechnic University China

In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the model’s ability to extract representative and discriminative features. In the field of face recognition, traditional feature fusion methods include feature concatenation and feature addition. Recently, various attention mechanism-based fusion strategies have emerged. However, we found that these methods primarily focus on the important features in the image, referred to as salient features in this paper, while neglecting another equally important set of features for image recognition tasks, which we term differential features. This may cause the model to overlook critical local differences when dealing with complex facial samples. Therefore, in this paper, we propose an efficient convolution module called MSConv (Multiplicative and Subtractive Convolution), designed to balance the model’s learning of salient and differential features. Specifically, we employ multi-scale mixed convolution to capture both local and broader contextual information from face images, and then utilize Multiplication Operation (MO) and Subtraction Operation (SO) to extract salient and differential features, respectively. Experimental results demonstrate that by integrating both salient and differential features, MSConv outperforms models that only focus on salient features. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhanced In-Flight Connectivity for Urban Air Mobility via LEO Satellite Networks

Enhanced In-Flight Connectivity for Urban Air Mobility via L...

引用

International Conference on Telecommunications (ICT)

作者： Karnika Biswas Hakim Ghazzai Abdullah Khanfor Lokman Sboui CEMSE Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Computer Science Department College of Computer Science & Information Systems Najran University Najran Saudi Arabia Systems Engineering Department École de Technologie Supérieure (ÉTS) University of Québec Montréal Canada

ISBN: (数字)9798350356694

ISBN: (纸本)9798350356700

Urban Air Mobility (UAM) is the envisioned future of inter-city aerial transportation. This paper presents a novel, in-flight connectivity link allocation method for UAM, which dynamically switches between terrestrial cellular and Low Earth Orbit (LEO) satellite networks based on real-time conditions. Our approach prefers cellular networks for cost efficiency, switching to LEO satellites under poor cellular conditions to ensure continuous UAM connectivity. By integrating real-time metrics like signal strength, network congestion, and flight trajectory into the selection process, our algorithm effectively balances cost, minimum data rate requirements, and continuity of communication. Numerical results validate minimization of data-loss while ensuring an optimal selection from the set of available above-threshold data rates at every time sample. Furthermore, insights derived from our study emphasize the importance of hybrid connectivity solutions in ensuring seamless, uninterrupted communication for future urban aerial vehicles.

关键词： Satellites Costs Low earth orbit satellites Transportation Switches Real-time systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

Image Caption And Speech Generation Using LSTM And GTTS API

Image Caption And Speech Generation Using LSTM And GTTS API

引用

Augmented Intelligence and Sustainable systems (ICAISS), International Conference on

作者： K. Bhargav Ram Venkatesh B Sala Pooja Sai Sree Chunduru Anilkumar V. Surya Narayana Reddy Bhavya Kodumuri Department of Computer Science and Engineering BVRIT HYDERABAD College of Engineering for Women Hyderabad India Department of Computer Science and Engineering BVRIT HYDERABAD College of Engineering for Women Hydetabad India Systems Engineer Infosys Hyderabad India Dept of Information Technology GMR Institute Of Technology Rajam Andhra Pradesh Department of Computer Science and Engineering VNR VIGNANA JYOTHI INSTITUTE OF ENGINEERING AND TECHNOLOGY Hyderabad India Department of Computer Science and Engineering Vidya Jyothi Institute of Technology HYderabad India

Image Caption generation is one of the challenging tasks in the field of artificial intelligence. It is used to generate a textual description for a given picture. But due to, the recent advancement in deep learning techniques requires only one single end-to-end model to create a caption for the given image. This paper is intended to provide an image caption and speech generator used to generate a single-line description for a given image and audio/speech for the report generated. The researchers used a sophisticated pipeline of specifically designed models in the previous models. To achieve the proposed model, VGG16 and LSTM models are used to obtain descriptions for the image and GTTS API is used for the audio/speech generation.

关键词：

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：