检索结果-内蒙古大学图书馆

Accurate and Efficient Human Activity Recognition Through Semi-Supervised Deep Learning

IEEE Sensors Journal 2025年

作者： Long, Xianlei Wang, Ping Gu, Fuqiang Yan, Jinjin Yu, Fangwen Li, Yan Chen, Chao Guo, Songtao Chongqing University College of Computer Science Chongqing400044 China Harbin Engineering University Qingdao Innovation and Development Center Qingdao266400 China Tsinghua University Department of Precision Instrument Beijing China Macquarie University School of Computing Sydney Australia Chongqing University State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing400044 China

In recent years, deep learning has been widely used for human activity recognition (HAR) based on wearable sensor data due to its excellent performance. However, deep learning approaches often need a large amount of labeled data to train the model. The collection of huge amounts of labeled activity data is usually labor-intensive and even cost-prohibitive, limiting the practical use of these methods. An effective way to address this issue is to use semi-supervised learning methods. Yet, most existing semi-supervised approaches fail to fully make use of unlabeled data to improve deep learning models' accuracy and generalizability. In this work, we propose an innovative Adaptive Confidence Semi-supervised HAR (ACS-HAR) method that can dynamically adjust the selective confidence threshold based on the model's learning state, thereby making more efficient use of unlabeled data. Experimental results on six public datasets demonstrate that our method outperforms traditional supervised methods by up to 5.20% accuracy and state-of-the-art semi-supervised methods by up to 3.30% *** release our code at https://***/objwww/ACS-HAR. © 2001-2012 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Design of an AI-enabled Crime Value Index Evaluation System for Geo-location based on Crime Data Analysis 4

Design of an AI-enabled Crime Value Index Evaluation System ...

引用

4th International Conference on Inventive Research in computing Applications, ICIRCA 2022

作者： Prashant Jain, Peeyush Choudhary, Saomya Center for Development of Advanced Computing Department of Artificial Intelligence Mohali India Center for Development of Advanced Computing Department of Cyber Security Mohali India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Intentionally inflicting injury on another individual, whether physical, psychological, or financial, is a crime. It is a widespread and complex societal problem that has an impact on people's quality of life, economic progress, and national prestige. Many scholars have studied the rise in criminality in recent years, as various social, economic, and environmental developments happened in all parts of the world as a result of increased urbanization, with governors facing even greater issues. Focus has been placed on improving urban transportation, health, and public safety. The conventional crime rate conveys the information about the number of occurrences recorded by the police for a certain population. It's a measure of how many incidents of criminal activity were reported to the authorities. The rate is determined by dividing the total number of crimes reported to and investigated by law enforcement agencies by the population at large. The rate accounts for all crimes equally, regardless of category or severity. For instance, one murder is equivalent to one rape. Here, the crime index value is calculated which is very important for crime analysis. With the help of the Crime Index, the user can easily visualize the increase or decrease in the crime rate as recorded by the police. It achieves so by not considering the change in volume of a certain crime, but also the severity of that crime in contrast to other crimes © 2022 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Real-Time Prediction of Cognitive State on Smartphone 1

引用

3rd International Conference on "Emerging Trends and Technologies on Intelligent Systems" (ETTIS-2023)

作者： Jain, Priyanka Sharma, Greeshma Kirode, Piyush Koria, Harsh Deep, Aakash Jain, Naveen Kumar Center for Development of Advanced Computing New Delhi India

ISBN: (数字)9789819939633

ISBN: (纸本)9789819939626

With the pace of high cutting-edge technical solutions, the ease of availability and affordability are the parameters which affect the accessibility of it to the general mass. This motivated us for a handy real-time analysis of human cognitive state using smartphones. In a technology-driven society, it is very important to measure and predict meaningful brain signals in real time. As electroencephalograph (EEG) represents a solution that has high temporal resolution, it becomes a useful tool for society. One such application is to understand that attention is useful for learning and relaxation is useful for health. This research paper provides a framework that gives insight into mobile-based real-time mental state visualization along with levels of attention and relaxation. The framework is built with an Indian-made, eight-channel EEG device (neuphony). This is the first study to show a brain-mobile interface for omnipresent, prevalent computing. We eventually construct a sophisticated mobile-based EEG monitoring system by combining signal processing algorithm with an Android mobile application and we verify its effectiveness using real-time EEG data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A fault-tolerant approach for detection of singular points in noisy fingerprint images

引用

International Journal of Computer Science Issues 2011年第2期8卷 577-582页

作者： Saquib, Zia Soni, Santosh Kumar Suhasaria, Sweta Parekh, Dimple Vig, Rekha Center for Development of Advanced Computing Mumbai Maharashtra 400049 India Mumbai Maharashtra 400056 India

Singular point detection is one of the most crucial processes in fingerprint recognition systems. Singular points are used for fingerprint classification, matching and alignment. This paper presents a method for reliable detection of singular points, which is largely insensitive to the degradation of fingerprint quality. The approach involves two phases, wherein, first phase detects the singular points, which operates on the quadrant change information. The second phase involves the analysis and extraction of the locations having high probability of the existence of singular points. The second phase uses orientation reliability measure of the filtered fingerprint image. The spurious singular points are detected, and thereby eliminated. This model is tested on selected noisy images from a publicly available (Cross Match Verifier 300 sensor) fingerprint database scanned at 500 dpi. The experimental results show that the approach effectively eliminates the spurious singular points in the noisy images.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Host based intrusion detection architecture for mobile ad hoc networks

Host based intrusion detection architecture for mobile ad ho...

引用

9th International Conference on advanced Communication Technology (ICACT 2007)

作者： Ray, Prabhudutta Center for Development of Advanced Computing Department of Computer Science and Engineering Noida India

ISBN: (纸本)9788955191318

Mobile ad hoc network is a collection of mobile hosts' which can communicate with each other using wireless interfaces and can also dynamically form a network topology where each node can act as router to forwarding the packets to other nodes. These networks are in high demand due to the ease and speed in selling up such networks. Due to the inherent vulnerabilities of wireless medium and node mobility make such network highly susceptible to malicious attacks. Things are getting worst when some nodes getting hijacked or compromised and make this network to stop from the smooth workings. This paper proposes the host based intrusion detection architecture to identify lite malicious node and provide security support to continue the smooth workings of this network.

关键词： HAR ACM ARP CM ADM MDM HDD SCM etc

来源：评论

学校读者我要写书评

暂无评论

IMPLEMENTATION OF WEB CRAWLER

IMPLEMENTATION OF WEB CRAWLER

引用

2nd International Conference on Emerging Trends in Engineering and Technology (ICETET09)

作者： Gupta, Pooja Johari, Kalpana Linagay's University India Center for Development of Advanced Computing NOIDA India

ISBN: (纸本)9781424452507

The World Wide Web is an interlinked collection of billions of documents formatted using HTML. Ironically the very size of this collection has become an obstacle for information retrieval. The user has to shift through scores of pages to come upon the information he/she desires. Web crawlers are the heart of search engines. Web crawlers continuously keep on crawling the web and find any new web pages that have been added to the web, pages that have been removed from the web. Due to growing and dynamic nature of the web;it has become a challenge to traverse all URLs in the web documents and to handle these URLs. A focused crawler is an agent that targets a particular topic and visits and gathers only relevant web pages. In this dissertation I had worked on design and working of web crawler that can be used for copyright infringement. We will take one seed URL as input and search with a keyword, the searching result is based on keyword and it will fetch the web pages where it will find that keyword. This focused based crawler approach retrieve documents that contain particular keyword from the user's query;we are implementing this using breadth-first search. Now, when we retrieved the web pages we will apply pattern recognition over text. We will give one file as input and apply the pattern recognition algorithms. Here, pattern symbolizes text only and check how much text is available on the web page. The algorithms that I had used for pattern search are Knutt-Morri-Pratt, Boyer-Moore, Finite Automata algorithm.

关键词： Search engine focus crawler pattern recognition copyright infringement

来源：评论

学校读者我要写书评

暂无评论

CHALLENGES TO THE USE OF SUPERCOMPUTERS AND SCIENTIFIC VISUALIZATION FOR AUTOMOTIVE APPLICATIONS

引用

COMPUTERS & GRAPHICS 1993年第5期17卷 507-515页

作者： GINSBERG, M High-End Computing Section EDS Advanced Computing Center General Motors Research and Development Center 30500 Mound Road P.O. Box 9055 Warren MI 48090-9055 USA

Supercomputing and visualization facilities are used in the automotive industry to produce large-scale computer simulations of physical phenomena related to the efficient design, analysis, and manufacture of cars and trucks. Such tools are an economic necessity for creating very high-quality vehicles that can be rapidly brought from concept to production in an increasingly competitive worldwide automotive market. This paper focuses attention on current and future directions for supercomputing and scientific visualization in an automotive applications environment. Extensive references to automotive simulation work on vector/parallel computers at General Motors are given in the Appendix. The interactions of supercomputers and visualization tools are discussed along with potential bottlenecks which must be overcome.

关键词： Computer graphics

来源：评论

学校读者我要写书评

暂无评论

International efforts for children online safety: A survey

引用

International Journal of Web Based Communities 2020年第2期16卷 123-133页

作者： Andrews, Dittin Alathur, Sreejith Chetty, Naganna Center for Development of Advanced Computing Electronics City Bangalore India National Institute of Technology Karnataka Surathkal Mangalore India

Children online safety is a global issue and attaining international attention to address it. Often, children are vulnerable to online threats. Aim of this paper is to review children online safety issues and identify existing international efforts for reducing online risks. In this regard, efforts from available international bodies for providing online safety to children are reviewed and reported. To overcome online risks, understanding the behaviour of online ecosystem and coping after facing risks are most important. The ecosystem involves different stakeholders such as service providers, physical network, online users being connected, social media sites and tools and technology. Elimination of online risks is difficult but the intensity of risks can be reduced. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

CALIBRATION AND VALIDATION OF THE CYGNSS LEVEL 1 DATA PRODUCTS 37

CALIBRATION AND VALIDATION OF THE CYGNSS LEVEL 1 DATA PRODUC...

引用

IEEE International Geoscience & Remote Sensing Symposium

作者： Gleason, Scott Ruf, Christopher Clarizia, Maria Paola Johnson, Joel O'Brien, Andrew Chang, Paul Jelenek, Zorana Said, Faozi Soisuvarn, Seubson AAI Center for development of Advanced Computing Pune India Banasthali Vidyapith Banasthali India

ISBN: (纸本)9781509049516

This presentation will include an overview of the recently launched NASA CYGNSS mission Level 1 calibration algorithms and their on-orbit validation [1], [2]. The validation of the Level 1 calibration will be performed in several steps, including a) a detailed noise floor analysis to assess the observed on-orbit noise power levels over the open ocean, b) multiple consistency checks using a forward model and co-located ocean wind and wave truth reference data and c) a term by term error analysis of all the non-ocean corrections applied to the final sigma0 estimates. An outline of the Level 1a (calibration from raw Level 0 instrument counts to units of watts for the received power) and the Level 1b (calibration from watts to bistatic scattering cross section) algorithms are each shown below. Three key components of the Level 1a calibration will be presented, namely, an analysis of the instrument (alone) and antenna noise characteristics over the ocean, a study of the range of received power levels from the surface, and comparisons with a forward model. The key components of the Level 1b calibration presented here will include validation of the main corrections applied to arrive at a surface sigma0 estimate, including receiver antenna gain, GPS transmitter and scattering area corrections.

关键词： Calibration Sea surface Wind speed Scattering Sea measurements Surface waves

来源：评论

学校读者我要写书评

暂无评论

Design and Validation of a Hyper-converged Blockchain Hardware and Software System Based on Domestic Chips 1st

Design and Validation of a Hyper-converged Blockchain Hardwa...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Liu, Xiaolong Yuan, Bo Wu, Faguo Enterprise Technology Center Aerospace Legione Technology Co. Ltd Haidian Beijing100195 China School of Computer Science and Engineering Beihang University Haidian Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Haidian Beijing100191 China Institute of Artificial Intelligence Beihang University Haidian Beijing100191 China Beihang University Haidian Beijing100191 China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Haidian Beijing100191 China

ISBN: (纸本)9789819794119

This paper proposes a hyper-converged blockchain hardware and software sys-tem based on domestic chips. By utilizing domestically firmware, the Linux operating system, X86 architecture Hygon processors, and ARM architecture Phytium processors, combined with servers, storage, network, and independently controllable blockchain technologies, the system achieves integrated hardware and software optimization. This significantly improves performance and scalability. Experimental results demonstrate that the system performs excellently in various high-security application scenarios, providing reliable solutions for government, finance, taxation, transportation, energy, and telecommunications sectors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Firmware

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：