检索结果-内蒙古大学图书馆

6th International Youth Conference on Radio Electronics, Electrical and Power engineering, REEPE 2024

作者： Kohel, Karim Osama, Mohamed Mohamed, Nourhan Mokhtar, Mohamed Tamer, Omar Fakhr, Mohamed Waleed University of Northampton Faculty of Engineering Department of Computer Northampton United Kingdom Arab Academy for Science and Technology Faculty of Engineering Department of Computer Cairo Egypt

ISBN: (纸本)9798350382891

Gaze tracking is the process of estimating where a person is looking on the screen using only information from eye movement without additional input from the user, it contributes greatly in understanding and improving human-computer interactions. This paper addresses an improved gaze tracking technique building upon established approaches that are using generic web cameras instead of requiring high-cost specific hardware like infrared cameras and sensors. In the proposed method, a pipeline was constructed of various high performing AI models such as Google's MediaPipe face localization and face landmarks solutions to acquire both Iris metrics and localized eye image data. The data obtained is then passed to the proposed model that uses both image data and location metrics to predict the user's gaze position on the screen using a multi-modal architecture. Experiments done on realistic desktop environments show 8% mean distance error of the screen dimensions with a standard deviation of +/-6% from the actual gaze location. The proposed method is not affected by most logistical limitations affecting other similar approaches. © 2024 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Distress Detection Using a Hybrid SVM - CNN Classifier 1

Distress Detection Using a Hybrid SVM - CNN Classifier

引用

1st International Conference on Computational Intelligence for Information, Security and Communication Applications, CIISCA 2023

作者： Varsha, Modha Aithal, Yukthi R Fathima, Sufia Sen, Snigdha Global Academy of Technology Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350339727

Due to the escalating frequency of reported crimes, there has been a surge in research endeavors focused on various approaches to enhance monitoring and surveillance techniques. As opposed to vision-based applications, which are currently the most used framework for monitoring purposes, audio-based systems can be more flexible and relatively less intrusive. While current research studies predominantly utilize images as the primary input for Deep Learning (DL) algorithms, it is worth noting that sound can also serve as a valuable source of input for these models. In this paper, we propose and develop a novel hybrid deep learning model for identifying and detecting people in distress by their screams. The working of our proposed system is built by integrating sound detection module and DL model which will help us to detect if a person is in distress or not. The system uses hybridization concept consisting of Support Vector Machine (SVM) and Convolutional Neural Network (CNN) models, with the audio snippet undergoing 3 levels of classification, with the accuracy of each level found to be 93%, 100% and 92% respectively. The audio data is finally classified as an instance of distress or no-distress. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Emergency vs Non-Emergency Vehicle Classification: Enhancing Intelligent Traffic Management Systems

Emergency vs Non-Emergency Vehicle Classification: Enhancing...

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Madan, S. Shetty, Kishan Kodipalli, Ashwini Rao, Trupthi Kumaraswamy, S. Global Academy of Technology Dept. of Computer Science and Engineering Karnataka Bengaluru India Global Academy of Technology Dept of Artificial Intelligence and Data Science Karnataka Bengaluru India Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350300826

Due to its dense population, India frequently experiences traffic congestion, which puts lives in danger by trapping vehicles like ambulances, police cars, and fire trucks which run on road for emergency purpose. It becomes crucial to give these vehicles priority and allow for their easy passage. However, it becomes challenging or even impossible for traffic police to effectively handle such circumstances. Therefore, there is a requirement for an automated system that can locate emergency vehicles in high-traffic areas, alert the controller, or drive itself to direct other vehicles to make room. This study suggests an automated method for identifying emergency vehicles from CCTV footage that makes use of deep convolutional neural networks (CNN). The objective is to effectively identify and classify emergency vehicles in real-time, leveraging the power of advanced object detection techniques. With an accuracy of 91.73% and a loss of 0.2120, the suggested technique outperformed existing optimizers in accurately recognizing and classifying emergency vehicles. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Recursive and Non-Recursive Approach in TREE Traversal

Comparative Study of Recursive and Non-Recursive Approach in...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Srusti, G. Varsha, M. Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

Tree traversal is a technique which involves visiting, verifying, and updating each node in a tree just once. This paper gives insight on the various approaches for the same. The tree can be visited in two ways recursively and non-recursively. This paper initiates an exploratory analysis between recursive and non-recursive algorithms for inorder, preorder, and postorder traversals. The execution time and the space-time complexity are analysed. Although the recursive approach performs efficiently in accordance with the time complexity. The non-recursive approach is given more weightage for specific occasions. In this frame of reference, this paper offers to answer the pertinent questions - which approach performs better? and when to use which approach? This paper can not only serve as a guide for researchers but also for programmers who aim on storing information and representing hierarchical data but also throws light on providing efficient algorithms for insertion, deletion, and searching. © 2023 IEEE.

关键词： inorder non-recursive postorder preorder spacetime complexity

来源：评论

学校读者我要写书评

暂无评论

Review of 'Speech Emotion Recognition': A Comprehensive Study 6

Review of 'Speech Emotion Recognition': A Comprehensive Stud...

引用

6th IEEE International Conference on Advances in science and technology, ICAST 2023

作者： Shetye, Akshay Chavan, Shruti Parab, Akshay Patil, Kaushik Kulkarni, Sumitra Finolex Academy of Management and Technology Department of Computer Science and Engineering Ratnagiri India

ISBN: (纸本)9798350359817

The review article, 'Speech Emotion Recognition: A Comprehensive Study,' starts off by summarizing the significance of speech emotion recognition and highlighting all of the different ways it may be used in fields like healthcare, human-computer interaction, and customer service. It offers a methodical classification of various methodologies and comprises feature extraction techniques, classification algorithms, and datasets utilized in SER. A study of the field's transition from traditional handmade components to deep learning-based techniques is included, along with an explanation of their implications. This study offers a comprehensive understanding of the state of SER systems today, covering their benefits, limitations, and future implications. For academics, professionals, and decision-makers attempting to comprehend the workings of voice emotion recognition technology, it is a helpful resource. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CLEAN: Cloud-enabled Scalable Blockchain Outsourcing System Using Dynamic Programming 6

CLEAN: Cloud-enabled Scalable Blockchain Outsourcing System ...

引用

6th ACM International Symposium on Blockchain and Secure Critical Infrastructure, BSCI 2024

作者： Chan, Weilin Wei, Yihang Jiang, Peng Xu, Lei Zhu, Liehuang Yu, Jing School of Computer Science and Technology Beijing Institute of Technology Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706387

Blockchain technology has garnered significant attention in academic and industrial domains due to its ability to establish a secure and trustworthy environment. As blockchain techniques continue to advance, there is a growing demand for computing resources in dimensions like storage, data processing, and network bandwidth. To meet this demand, leveraging cloud computing as an off-chain resource for scalable on-chain services has emerged as a viable solution. However, allocating cloud resources in heterogeneous cloud computing environments presents challenges due to their inherent complexity. Native cloud environments encompass diverse cloud service providers with varying capabilities, pricing models, and performance characteristics. Given the cloud's capacity to scale resources based on demand, this paper introduces a novel approach called the Cloud-enabled Scalable Blockchain (CLEAN) outsourcing model. The CLEAN model aims to develop a scalable blockchain system that minimizes costs and enhances performance. We propose a dynamic programming algorithm considering influential factors such as cloud service costs, availability, and execution time. The algorithm aims to minimize expenses while ensuring efficient resource allocation. Experimental evaluations involving rigorous analysis have been conducted to assess the effectiveness of the proposed approach. The results indicate that CLEAN outperforms the Greedy Algorithm and Genetic Algorithm (GA) by maintaining relatively low latency across all the CLEAN settings. Additionally, CLEAN demonstrates lower energy consumption compared to the Greedy Algorithm and GA, with up to a 50% and 30% reduction, respectively, as the number of transactions increases. Furthermore, the experiments determine the optimal number of orderers for the three settings to balance the trade-off between time cost and performance. Moreover, the findings also reveal that simply increasing the number of orderers in the cloud does not guarantee improv

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Hashing and Analysis of Collision Resolution Techniques

Comparative Study of Hashing and Analysis of Collision Resol...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Gowda, Aviksha Nayana Anshumali, M. Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

Most data structures use hash tables. A key method in computer science for effectively storing, accessing, and searching for data is hashing. It involves converting a key into a hash value and using this value to access the corresponding data in a table. Hash table utilization involves trade-offs, just like many other aspects of computer science. The implementation of hash-based containers has two key problems: the collision resolution mechanism and the hash function. However, collisions may occur when two keys are mapped to the same hash value. In this paper, the study is focused on the concept of collision in hashing along with how collision is resolved by comparing the performance of these collision resolution techniques in terms of their time and space complexities. Our findings indicate that each technique has its advantages and disadvantages, and that the best technique to use, relies on the particular application's needs. Therefore, this paper can serve as a guide for developers and researchers to choose the most suitable collision resolution technique for their specific use case. © 2023 IEEE.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

DAO to HANOI via DeSci: AI Paradigm Shifts from AlphaGo to ChatGPT

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 877-897页

作者： Qinghai Miao Wenbo Zheng Yisheng Lv Min Huang Wenwen Ding Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan 430070China Institute of Automation Chinese Academy of SciencesBeijing 100190China Institute of System Engineering Macao University of Science and TechnologyMacaoChina

From AlphaGo to ChatGPT,the field of AI has launched a series of remarkable achievements in recent ***,comparing,and summarizing these achievements at the paradigm level is important for future AI innovation,but has not received sufficient *** this paper,we give an overview and perspective on machine learning ***,we propose a paradigm taxonomy with three levels and seven dimensions from a knowledge ***,we give an overview on three basic and twelve extended learning paradigms,such as Ensemble Learning,Transfer Learning,etc.,with figures in unified *** further analyze three advanced paradigms,i.e.,AlphaGo,AlphaFold and ***,to enable more efficient and effective scientific discovery,we propose to build a new ecosystem that drives AI paradigm shifts through the decentralized science(DeSci)movement based on decentralized autonomous organization(DAO).To this end,we design the Hanoi framework,which integrates human factors,parallel intelligence based on a combination of artificial systems and the natural world,and the DAO to inspire AI innovations.

关键词： ChatGPT decentralized science(DeSci) decentralized autonomous organization(DAO) machine learning paradigm shift

来源：评论

学校读者我要写书评

暂无评论

Transforming Oilseed Production with the Power of IoT: Opportunities and Challenges

Transforming Oilseed Production with the Power of IoT: Oppor...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Jain, Hardik Gosai, Sanjeev Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

This paper explores the application of the Internet of Things (IoT) technology in oilseed production. With the growing demand for vegetable oil and biodiesel, there is a need to improve the efficiency and productivity of oilseed crops. IoT provides a solution to this problem by allowing for real-time monitoring of various parameters such as soil moisture, temperature, and nutrient levels. This data can be used to optimize irrigation, fertilization, and other crop management practices. The paper also discusses the various IoT sensors available for implementing such systems, as well as the challenges that need to be addressed for successful adoption. The results of the study demonstrate the potential of IoT in revolutionizing oilseed production, paving the way for increased efficiency and environmental sustainability. © 2023 IEEE.

关键词： Oilseeds

来源：评论

学校读者我要写书评

暂无评论

IoT in Healthcare: Reducing EMS Delivery Time Using IoT & Realtime Geospatial Query Engine

IoT in Healthcare: Reducing EMS Delivery Time Using IoT & Re...

引用

2023 International Conference on IoT, Communication and Automation technology, ICICAT 2023

作者： Pandey, Aman Kumar Mehta, Shashank Guruprasad, N. Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350302820

The Internet of Things (IoT) represents a network of interconnected digital devices that communicate wirelessly, enabling data collection, transmission, and storage without the need for human interaction. This paper introduces an innovative approach aimed at reducing fatalities resulting from major accidents on Indian roads by minimizing response time. By leveraging IoT devices such as smartphones and smartwatches, their embedded sensors can detect accident events. Utilizing a real-time geospatial search engine, potential nearby support services can be identified based on the accident's location, effectively reducing response time by eliminating idle periods. Furthermore, the paper explores the transformative potential of 5G technology in revolutionizing the system, enabling real-time monitoring of drivers and addressing existing system vulnerabilities. The paper underscores the urgency of implementing this system and thoroughly explores various user scenarios and expected technological behaviors. To enhance scalability and robustness, the integration of AI and machine learning techniques is proposed, facilitating large-scale deployment. Additionally, the paper delves into the constraints associated with implementing this technology and presents potential solutions to overcome them. © 2023 IEEE.

关键词： Smartphones

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：