检索结果-内蒙古大学图书馆

9th international conference on Information Management and Technology, ICIMTech 2024

作者： Liawatimena, Suryadiputra Gunawan, Devina Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Deparment BINUS Graduate Program Master of Computer Science Jakarta11480 Indonesia Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Modern retail businesses face a significant challenge with the inefficiency of manually changing price labels on shelves. This manual process not only consumes valuable time and resources but also increases the likelihood of errors, leading to potential inaccuracies in pricing and a less streamlined shopping experience for customers. The proposed solution is the implementation of an Electronic Shelf Label (ESL) system that automatically displays the prices of goods on retail business shelves. This system connects a website (front end and back end) to e-paper via a Wi-Fi network and microcontroller, allowing retail business owners to update prices more easily. Additionally, buyers can search for desired items through the website. The results are the time to send data from the website to the e-paper, namely, to know the performance of the e-paper used. The average time required from 10 attempts to send data from the website to the e-paper is 20.935 seconds. Since the data is connected to the server and will be updated automatically, using this system will be more efficient than manually changing the price label, although it takes time to transfer data from the website to the e-paper. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Application of computer Vision Approach for Automation and Classification of Fashion Store

Application of Computer Vision Approach for Automation and C...

引用

2024 international conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adebayo, Aminat Abiodun, Moses Kazeem Awoniran, Ifeoluwa Temitayo Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Adeniyi, Jide Kehinde Rueben Aremu, Dayo Alhikman University Dept. of Computer Science Ilorin Nigeria Landmark University Dept. of Computer Science Omu-Aran Nigeria Bowen University Dept. of Computer Science Iwo Nigeria University of Ilorin Dept. of Computer Science Ilorin Nigeria

ISBN: (纸本)9798350358155

The fashion industry has long been interested in utilizing computer vision techniques to automate tasks such as recognizing different types of clothing items in images. This study proposed a novel convolutional neural network (CNN) architecture for the classification of fashion outfits into three categories: shoes, sunglasses, and trousers. The proposed CNN architecture is based on state-of-the-art deep learning techniques and is trained on a fairly large-scale dataset of fashion images. The effectiveness of the proposed CNN architecture is evaluated through extensive experiments and analysis. The result demonstrates that the proposed CNN architecture achieves a high accuracy rate of 0.99 on each diagonal value of the confusion matrix. This indicates that the proposed CNN is capable of accurately classifying each item type with high accuracy. Additionally, the study investigates the impact of various hyperparameters on the performance of the proposed CNN architecture and found that the model which uses a 7x7 filter size and 64 filter number yields higher accuracy compared to other filter combinations. The study demonstrates the potential of CNN in automating fashion item recognition, which can lead to improved efficiency and accuracy in the fashion industry. It can also form the basis for developing more advanced computer vision systems for the fashion industry. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An optimized MCHVD approach to curtail handover failures in wireless networks

引用

international Journal of Information Technology (Singapore) 2024年第3期16卷 1989-1995页

作者： Gupta, Sachin Deepak, Shashikant Bhuvana, J. Singh, Vaishali Jindal, Kanika Vekariya, Vipul Chandrasekhar, Malepati Narula, Gagandeep Singh Department of Management Sanskriti University Uttar Pradesh Mathura India Department of UGDX ATLAS SkillTech University Mumbai India Department of Computer Science and Information Technology Jain (Deemed to be University) Bengaluru India Maharishi School of Engineering and Technology MUIT Lucknow India Department of Electronics and Communication Engineering Noida Institute of Engineering and Technology Uttar Pradesh Noida India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara India Department of Computer Science Engineering Presidency University Bengaluru India Guru Gobind Singh Indraprastha University Delhi Dwarka India

The applications of wireless local area networks (WLAN’s) are highly accepted by mobile terminals (MT’s) due to their high transmission bandwidth and reduced costs. However, in such high speed networking platforms, there is a possibility of unnecessary handover failure (UHF) due to limited coverage of WLAN’s. Therefore, the given paper provides a multi-criteria hysteresis vertical handover decision (MCHVD) approach for wireless systems in order to minimize handover failure by analysing and validating its performance with conventional received signal strength (RSS) scheme of source and target cells. Using OPNET simulator, the proposed approach is tested over 60 samples, which are divided equally among networks such as Wi-Fi, Worldwide Interoperability for Microwave Access (WiMAX), and Universal Mobile Telecommunication System (UMTS) based on parameters like G power as 0.8, threshold energy limit as 0.05%, and confidence interval as 95%, thereby keeping the maximum accepted error as 0.05 and beta as 0.2. An independent sample T-test is done, which reveals that the probability of handover failure (p) is 0.01 (p < 0.05), which is found to be statistically significant in the MCHVD approach when compared with the conventional RSS scheme. The results show that the handover failure rate for MCHVD is significantly lower than that for conventional RSS-based methods with respect to 20 iterations. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： RSS UMTS Vertical handover Wi-Fi WiMAX Wireless networks

来源：评论

学校读者我要写书评

暂无评论

ChatGPT in Higher Education: Perceptions of computer science-Related Students 15

ChatGPT in Higher Education: Perceptions of Computer Science...

引用

15th IEEE Global engineering Education conference (IEEE EDUCON)

作者： Hammer, Sabine Ottinger, Sarah Zoennchen, Benedikt Hohendanner, Michel Hobelsberger, Martin Thurner, Veronika Hsch Munchen Univ Appl Sci Dept Comp Sci & Math Munich Germany Hsch Munchen Univ Appl Sci Munich Ctr Digital Sci & AI Munich Germany Tech Univ Munich Chair Cyber Trust Munich Germany

ISBN: (纸本)9798350394023;9798350394030

In the field of education ChatGPT has sparked both admiration and controversy. This study explores students' perspectives, specifically focusing on those in computer science-related fields. We investigated their motivations, trust, perceptions of utility, and reliability of ChatGPT by conducting two surveys-one at the beginning and another at the end of the semester. During the semester, students were encouraged to engage with ChatGPT. Our findings highlight the tool's multifaceted use in an academic settings, establishing it as a valuable resource for a variety of learning tasks. Most students have incorporated ChatGPT into their regular academic activities and view it as a beneficial aid. They perceive it as a multi-task solver and anticipate significant advancements in its writing assistance features in the near future. Many, not only attribute high accuracy to it but think that it adheres to appropriate content and structural norms. Our results suggest that active confrontation with ChatGPT enhances understanding of its capabilities, limitations and autoregressive nature. Consequently, we recommend an approach of informed engagement that includes the distinction between language processing and genuine language understanding and a carefully crafted terminology.

关键词： ChatGPT large language models higher education educational technology

来源：评论

学校读者我要写书评

暂无评论

multi-hop Attention-based Graph Pooling: A Personalized PageRank Perspective 3

Multi-hop Attention-based Graph Pooling: A Personalized Page...

引用

3rd international conference on Distributed Computing and High Performance Computing, DCHPC 2024

作者： Haddadian, Parsa Booryaee, Roya Abedian, Rooholah Moeini, Ali University of Tehran College of Engineering Department of Engineering Science Iran University of Tehran Faculty of Engineering Science College of Engineering Iran

ISBN: (纸本)9798350381580

Over the past ten years, graph representation learning has garnered a lot of attention due to the variety of graph-structured data and its efficiency in both time and space. One essential method for obtaining effective graph representations is graph pooling. Numerous studies on the graph pooling technique have been conducted. Cutting-edge results on a range of graph representation learning tasks were made possible by the combination of graph neural networks and self-attention mechanisms. Nevertheless, the attention mechanism has limitations since it ignores nodes that have no direct connection via an edge but provide valuable network context information. This paper proposes a graph pooling approach based on Personalized PageRank and self-attention, which improves the model to take into account both node properties and graph structure. The experimental findings indicate that, with a suitable number of parameters, the MAGPool approach delivers greater accuracy on the benchmark datasets. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of Epileptic Seizures using Novel multi-Layered Convolution Neural Network in Comparison with Fully Convolutional Neural Network to Improve the Accuracy 8

Detection of Epileptic Seizures using Novel Multi-Layered Co...

引用

8th IEEE international conference on science, Technology, engineering and Mathematics, ICONSTEM 2023

作者： Sasi Kumar, G. Jai Sharma, K. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350347791

This research study is to detect the Epileptic seizures using Novel multi-Layered Convolutional Neural Networks (NMLCNN) and to compare the performance with Fully Convolutional Neural Networks (FCNN). By using Novel multi-Layered Convolution Neural Networks algorithm works with the data collected from the observations of nervous system cells. The changes in the Epileptic seizures from the resource's constraint, when the criteria met with randomizing, this will arrange in random ways for n times. The most typical beginning of a seizure is detectable through analysis of the Electroencephalogram (EEG). To examine this, the study utilized 20 samples in each group, with a Gpower value of 80%. The study used a predefined significance value and a Confidence Interval (CI) of 95%.This experiment found that NMLCNN has 92.25% and FCNN has 87.55% of accuracy for epileptic seizure. The Novel multi-Layered Convolutional Neural Network achieved 0.012 significance using group analysis and provided significance. This probing concludes based on accuracy and significance results, detection of Epileptic seizures using Novel multi-layered Convolutional Neural Networks has performed better compared to Fully Convolutional Neural Network. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Framework on Positioning of Medical Sensors in Healthcare Domain

A Framework on Positioning of Medical Sensors in Healthcare ...

引用

2024 international conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Rajput, Anuj Singh Prabha, S. Khare, Mayank Deep Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Internet Of Things Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

In the last several years, the incorporation of sensor technology into our everyday routines has resulted in improved comfort, convenience, and overall wellbeing. The size and cost of medical sensors have decreased as a consequence of technical improvements that have improved their use. Medical sensors make 'remote health monitoring, surgical procedures, therapy, and rehabilitation' more efficient and practical. We provide an in-depth historical overview of medical sensors during the last fifty years, emphasising their use in clinical settings. The evaluation also examines the impact of IoT on the advancement of sensor technologies and the uses of such technologies in healthcare. We also examine the benefits and drawbacks of several integrated architectures that have been recently proposed for the smooth integration of different medical sensors with novel paradigms and technologies, including those that are located at the edge, in the cloud, in the middle (mobile cloud computing), and in the sky (fog computing) of the network. We conclude by outlining the next challenges that must be overcome in order to fully actualize the best potential and benefits of medical sensor technologies and, in the end, build a robust, scalable, reliable, and affordable healthcare system. © 2024 IEEE.

关键词： Mobile cloud computing

来源：评论

学校读者我要写书评

暂无评论

Acoustic characterization of Mongolian khoomei vocal types based on computer analysis 24

Acoustic characterization of Mongolian khoomei vocal types b...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area international conference on Education Digitalization and computer science, EDCS 2024

作者： Ren, Huipeng Xi, Yaxin Hu, Axu Key Laboratory of Language and Cultural Computing Ministry of Education Northwest Minzu University Gansu Lanzhou China

This paper combines computer technology and adopts the research method of acoustic analysis, taking the Khoomei"Voice of Altai","Ordos Man","Four Mountains" and"Ten Fingers" as ... 详细信息

ISBN: (纸本)9798400710360

This paper combines computer technology and adopts the research method of acoustic analysis, taking the Khoomei"Voice of Altai","Ordos Man","Four Mountains" and"Ten Fingers" as the research objects. By using the speech analysis software KAY multi-Speech 3700 and the statistical software SPSS27.0 to analyze its speech signal, extract the parameters such as Intensity, Pitch, Formant, etc., and analyze the acoustic level of the Khoomei rendition method GaRiGa, the technique class of imitating running water Khoomei, the Khoomei preparatory tone nasal, the whistling Khoomei, and the technique of DengDeLe Khoomei to summarize the physical acoustic characteristics of the Khoomei. Physical acoustic characteristics of the Khoomei, and ultimately reveal the pronunciation mechanism of the Khoomei. © 2024 Copyright held by the owner/author(s).

关键词： multiprocessing programs

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Method with Part of Speech Tagging and Named Entity Recognition Techniques Towards Advanced Persistent Threat in Cyber Threat Intelligence: Work in Progress 11

An Enhanced Method with Part of Speech Tagging and Named Ent...

引用

11th international conference on Electrical engineering, computer science and Informatics, EECSI 2024

作者： Permana, Dendi Renaldo Stiawan, Deris Rini, Dian Palupi Afifah, Nurul Ningrum, Septiani Kusuma Budiarto, Rahmat Universitas Sriwijaya Indonesia Universitas Sriwijaya Computer Engineering Dept Indonesia Universitas Sriwijaya Informatic Engineering Dept Indonesia Universitas Sriwijaya COMNETS Research Group Indonesia College of Computing and Information Albaha University Saudi Arabia

ISBN: (纸本)9798350355314

This research enhances the development of natural language processing (NLP) by integrating part of speech (POS) tagging and named entity recognition (NER) techniques to annotate unstructured data from advanced persistent threat (APT) news. This paper uses combination of these two techniques with deep learning methods, specifically bidirectional long short-term memory (BiLSTM) and conditional random field (CRF) to automate data annotation. The objective is to automatically convert the unstructured APT data into structured threat information expression (STIX) format. The proposed approach can be further developed into cyber threat intelligence (CTI) system for information exchange and early warning against cybercrime. This research is currently in the preliminary stage with progress including data collection and preprocessing, and BiLSTM model building. The expected outcome is a model that capable of APT data labeling to enhance CTI systems. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Indoor Place Recognition Using multi-modal Range Information 7

A Comparative Study of Indoor Place Recognition Using Multi-...

引用

7th international conference on computer science and Artificial Intelligence, CSAI 2023

作者： Yang, Chenrushi Mei, Ruidong Cheng, Hui School of System Science and Engineering Sun Yat-sen University Guangdong Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China

ISBN: (纸本)9798400708688

This paper presents a discussion on the challenges encountered in localizing mobile robots in large-scale indoor environments, particularly the issues of kidnapping and localization failure, which are prevalent in factories and malls. Visual place recognition (VPR) methods are often used to alleviate these issues;however, in large-scale indoor settings, obtaining ground truth through precise 3D reconstruction using cameras can be time-consuming and challenging due to their limited field of view and varying illumination conditions. LiDAR is more suitable for large-scale mapping due to its wider field of view and its robustness to environmental changes and sensor drifts;however, the cost of LiDAR systems can be prohibitive for indoor applications. RGB-D cameras are lighter and less expensive, making them more suitable for a wide range of applications on multi-robot platforms. Therefore, it is important to investigate the use of RGB-D camera data for place recognition, especially in indoor contexts where only LiDAR maps can be used for place recognition. This paper presents a rigorous comparative study based on existing techniques to identify the key factors in addressing indoor place recognition challenges. © 2023 ACM.

关键词： Cameras

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：