检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Singhal, Amit Pratap, Preksha Dixit, Krishna Kant Kathuria, Kajol Raj Kumar Goel Institute of Technology Department of Computer Science & Engineering UP Ghaziabad India Meerut Institute of Engineering and Technology Department of Information Technology UP Meerut India Gla University Department of Electrical Engineering UP Mathura India Gl Bajaj Institute of Technology & Management Department of Information Technology UP Greater Noida India

ISBN: (纸本)9798350371055

Explainable Artificial Intelligence (Explainable AI, XAI) is a discipline of studies that seeks to apprehend and provide an explanation for the selection-making tactics that AI systems and algorithms make approximately records and to enhance the accuracy of the decisions and fashions generated through those techniques. XAI seeks to offer more transparency and expertise into the internal workings of AI and systems, gaining knowledge of structures that could assist in enhancing agreement with and adoption of those structures in organizations. XAI leverages a spread of techniques and techniques, along with rule sets, good judgment-based total structures, quantitative metrics, and visualizations, to explain complicated AI choices and fashions. Via explainability, customers can higher apprehend how an AI machine or algorithm arrived at its decision, what variables had been used to provide that result, and the way the choice will be suffering from new or augmented records. © 2024 IEEE.

关键词： Apprehend Approximately Structures Techniques Transparency

来源：评论

学校读者我要写书评

暂无评论

Virtual Bazar-An Interactive Virtual Reality Store to Support Healthier Food Choices 1

Virtual Bazar-An Interactive Virtual Reality Store to Suppor...

引用

1st International Conference on Informatics, ICI 2022

作者： Chandak, Abhimanyu Singh, Ashutosh Mishra, Shubham Gupta, Sarishty Jaypee Institute of Information Technology Department of Computer Science & Engineering and Information Technology Noida India

ISBN: (纸本)9781665437219

Virtual Reality (VR) has been incorporated in almost every possible application domain, but majority of the online shopping platforms are providing their customers only simple two-dimensional image-based and text-based interfaces to shop upon. This kind of monotonous shopping environment not only makes consumers lose their interest in shopping but also restricts personalized services to consumers such as providing healthier alternatives to the products or providing with suggestions based on their past shopping pattern [1]. Keeping these issues in mind the prototype of a VR based game 'Virtual Bazar' is proposed which allows its users to shop in a Virtual Reality supermarket environment. The proposed model keeps a check on the Calorie requirements set by the user, shows Nutritional information of products and create awareness for Healthier Products. It consists of two runs, in the first run users add items to their cart based on their desires with no warnings and nutritional values being shown. In the second run users are shown Nutritional information regarding products along with warnings on products having high Sugar or Carbohydrate values and with these suggestions the user again adds items to the cart. Based on the items of the two shopping lists, separate scores are calculated and analyzed. 50 different people within the age bracket of 20-35 years have played this game and ANNOVA Test has been performed on the scores obtained by these players. The results suggest that the players were benefited by the game as they learnt to choose healthier products. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Multigrain-Multilabel (MGML) Dataset for Smartphone-Based Human Activity Recognition

引用

SN computer Science 2024年第7期5卷 859页

作者： Thakur, Tushti Saha, Anindita Mallik, Manjarini Chowdhury, Chandreyee Department of Mechanical Engineering Jadavpur University Kolkata India Department of Information Technology Techno Main Saltlake Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India

The efficacy of machine learning-based Human Activity Recognition (HAR) heavily relies on the datasets. Existing benchmark HAR datasets on smartphone accelerometer sensors provide mostly single-labeled, fine-grained activities like walking, sitting, etc. collected in lab set-up. In real life, users hardly perform an activity in isolation. Rather, the activities are often performed in sequence with non-uniform transition duration. So, for faster transitions, fine-grained data annotation is difficult and error-prone. A few existing benchmark datasets report coarse-grained activities like working, cooking, etc. that do not indicate enough information about the constituent fine-grained activities performed. HAR performance in these cases cannot satisfy real-life purposes like physical fitness prediction, or rehabilitation after surgery. To address this challenge, a Multigrain-multilabel (MGML) dataset has been designed by collecting smartphone accelerometer sensor readings from four users. Here, the coarse-grained activities are multi-labeled, and both fine-grained and coarse grained activities are covered. That means one can get information regarding the physical movements of the user from labelling information. The MGML dataset has been evaluated with four machine learning classifiers. We report a baseline classification accuracy of 95.40% for the classifiers considered. Experimentation has been conducted on the entire filtered and feature-engineered data. The effectiveness of feature engineering has also been shown. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature engineering Human Activity Recognition Machine learning Multi-labeled dataset Smartphone sensing

来源：评论

学校读者我要写书评

暂无评论

A Virtual Classroom for Special Need Students 10

A Virtual Classroom for Special Need Students

引用

10th International Conference on Reliability, Infocom Technologies and Optimization ,Trends and Future Directions, ICRITO 2022

作者： Tyagi, Rajneesh Goyal, Mukund Madhav Jain, Punit Pandey, Kavita Jaypee Institute of Information Technology Department of Computer Science & Engineering and Information Technology Noida India

ISBN: (数字)9781665474337

ISBN: (纸本)9781665474337

Virtual Learning Environments (VLE) are online platforms which are used for teaching and learning. There are many VLEs available for the students in the market that are helpful for them to study and learn online. These VLEs make use of latest technologies and features like accessing the course material, submitting the assignments, attending live lectures, viewing recorded lectures etc. Unfortunately, for Visually Impaired (VI) students these environments do not possess alternative features like voice feedback and voice commands that would help them operate the application, disabling VIs to make benefit from such applications. So, to eradicate this gap this paper proposes a solution that provides enhancements to accessibility issues, content and navigation that confront the visually impaired, in its implemented mobile-based application. The solution proposed is expected to assist the VIs and contribute to the society. Only the key features for assisting the VIs are presented in this paper. The system implemented different modules for class management and accessibility. It provides text-to-speech integration and voice command controls. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Profiling Casualty Severity Levels of Road Accident Using Weighted Majority Voting

引用

computers, Materials & Continua 2022年第6期71卷 4609-4626页

作者： Saba Awan Zahid Mehmood Hassan Nazeer Chaudhry Usman Tariq Amjad Rehman Tanzila Saba Muhammad Rashid Department of Software Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Computer Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Electronics Information and BioengineeringPolitecnico di MilanoMilano20122Italy College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia College of Computer and Information Sciences Prince Sultan UniversityRiyadhSaudi Arabia Department of Computer Engineering Umm Al-Qura UniversityMakkah21421Saudi Arabia

To determine the individual circumstances that account for a road traffic accident,it is crucial to consider the unplanned connections amongst various factors related to a crash that results in high casualty *** of the road accident data concentrated mainly on categorizing accidents into different types using individually built classification methods which limit the prediction accuracy and fitness of the *** this article,we proposed a multi-model hybrid framework of the weighted majority voting(WMV)scheme with parallel structure,which is designed by integrating individually implemented multinomial logistic regression(MLR)and multilayer perceptron(MLP)classifiers using three different accident datasets i.e.,IRTAD,NCDB,and *** proposed WMV hybrid scheme overtook individual classifiers in terms of modern evaluation measures like ROC,RMSE,Kappa rate,classification accuracy,and performs better than state-of-theart approaches for the prediction of casualty severity ***,the proposed WMV hybrid scheme adds up to accident severity analysis through knowledge representation by revealing the role of different accident-related factors which expand the risk of casualty in a road *** aspects related to casualty severity recognized by the proposed WMV hybrid approach can surely support the traffic enforcement agencies to develop better road safety plans and ultimately save lives.

关键词： Prediction hybrid framework severity class casualty

来源：评论

学校读者我要写书评

暂无评论

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin Transformer

DAS-COD: Depth-Aware Camouflaged Object Detection via Swin T...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Chenye Tan, Min Gao, Zhigang Mao, Xiaoyang Xia, Zilin School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China College of Information Engineering China Jiliang University Hangzhou China University of Yamanashi Department of Computer Science and Engineering Kofu Japan

ISBN: (纸本)9781665410205

The successful integration of depth information into salient object detection tasks has catalyzed research interest in depth-enhanced camouflaged object detection (COD) tasks. However, the challenges associated with acquiring depth information pose significant hurdles to this task, especially given the lack of RGB-D datasets tailored specifically for COD. Consequently, employing depth estimation techniques to generate pseudo-depth information emerges as a viable solution in the realm of depth-enhanced COD tasks. In this study, we propose an architecture, DAS-COD (Depth-Aware Swin Transformer COD), that integrates Swin Transformer model with depth estimation techniques for the purpose of camouflaged object detection. In particular, we use a dual-stream Swin Transformer backbone to extract feature maps from different modalities. These maps are then enhanced with a multi-modal feature enhancement module. Additionally, to address the inherent discrepancies between pseudo-depth maps and actual depth information, we incorporate an edge-aware module to significantly improve the accuracy of boundary delineation in the predicted outcomes. We tested our proposed method on three different COD datasets. Our results show that the model achieves state-of-the-art performance across these camouflaged object detection datasets. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Improving cloud data security through hybrid verification technique based on biometrics and encryption system

引用

International Journal of computers and Applications 2022年第5期44卷 455-464页

作者： Hossain, Md. Alamgir Al Hasan, Md. Abdullah Department of Computer Science and Engineering Prime University Dhaka Bangladesh Bangladesh-Japan Information Technology Dhaka Bangladesh

Cloud computing is a unique network or environment where access, maintenance and process can be done from any part of the world. It is a customized internet-based computer server. It is a current trend of modern technology. For the massive computational power, it is the best option for storing data. There is no uncertainty that Cloud Data Server offers quick and solid types of assistance to its customers. When data is storing in the cloud storage the most important thing comes is the security of data. So, in recent years, cloud security is so much important issue because of the increasing of data. For the security of cloud computing, in this research, a hybrid verification technique is made which is based on biometric and encryption systems. In order to achieve strong and secure technique, this work use fingerprint as biometric technique and advanced encryption standard as a trustworthy encryption system. The primary goal of this paper is to avert information access from cloud information stockpiling focuses by unapproved clients. This new data security system can provide efficient authentication of cloud computing. © 2020 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Optimising 3D printing parameters through experimental techniques and ANOVA-Based statistical analysis

SPE Polymers

引用

SPE Polymers 2024年第2期5卷 228-240页

作者： Naveed, Nida Anwar, Muhammad Naveed Faculty of Technology School of Engineering University of Sunderland Sunderland United Kingdom Department of Computer & Information Sciences Faculty of Engineering and Environment Northumbria University Newcastle upon Tyne United Kingdom

Additive manufacturing (AM) has revolutionized the manufacturing industry by enabling the fabrication of complex geometries and designs with ease. 3D printing—fused deposition modeling (FDM) has emerged as a prevalent technique, owing to its versatility and cost-effectiveness. However, the FDM process is complex and depends on multiple parameters, which makes it challenging to obtain high-quality and consistent 3D printed components. The purpose of this study is to simplify the printing process for users and potentially improve the overall quality and consistency of printed objects. This research delved into optimising 3D printing parameters, specifically raster orientation and in-fill speed, for PLA material through three experimental studies. The mean effect of these parameters and the effects of their interaction through analysis of variance (ANOVA) on tensile properties were also discussed. Initial experiments identified the most suitable parameters and its optimal values for PLA, which were then applied to five different materials: PETG, PLA tough, Recycle PLA, Plain PLA, and ABS. Tensile tests assessed the printed parts, and scanning electron microscopy (SEM) was employed to analyze fracture interfaces and material failure causes. This study identified a raster of 45°/−45° and 30 mm/s infill speed as optimal for diverse 3D printing materials. Notably, ABS, PETG, and tough PLA exhibited better tensile strengths, surpassing manufacturer benchmarks. However, Plain PLA and Recycled PLA, despite lower tensile strengths, proved valuable for specific applications. Interestingly, all tested materials showed greater flexibility than manufacturer recommendations, suggesting their suitability in scenarios needing both strength and flexibility. This study's results offer promising avenues for refining 3D printing practices, to the advantage of all users. The findings from this study offer significant insights for future research to investigate the effect of other process

关键词： 3D printer fused deposition modeling (FDM) infill speed raster orientation

来源：评论

学校读者我要写书评

暂无评论

A security control scheme based on quantum keys for IoT terminals

引用

International Journal of Security and Networks 2023年第3期18卷 189-198页

作者： Zhu, Dexin Du, Xiaogang Mao, Jigui Song, Lijun College of Computer Science and Technology Changchun University Changchun130022 China College of Science Changchun University Changchun130022 China Jilin Engineering Laboratory for Quantum Information Technology Changchun130062 China

With the development of computer technology and the continuous improvement of computing power, the security control of internet of things terminals has received great attention. This paper proposes a security control scheme based on quantum keys for the internet of things terminals. In the wide area network, the control commands between Alice and Bob are transmitted by quantum key encryption. In the local area network, Bob sends the decrypted plaintext to the LED microcontroller board to execute the control instruction. This paper also designs a two-way identity authentication scheme based on a hash function, a sliding window key synchronisation scheme, and an eavesdropping experiment. Through experiments, the quantum key encoding rate of the quantum key distribution system is 7.4 kbps, the average time for Alice to send instructions is 141.6 ms, the average time for Bob to decrypt instructions is 12.4 ms, and the average time for key synchronisation in the time sliding pane is 116 ms. Even after stealing Alice’s ciphertext data, Eve still cannot recover the plaintext data. The scheme realises the security control of the internet of things terminal. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Covid-19 Twitter Data using Deep Learning Algorithm 2

Sentiment Analysis of Covid-19 Twitter Data using Deep Learn...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Valarmathi, B. Gupta, N. Srinivasa Karthick, V. Chellatamilan, T. Santhi, K. Chalicheemala, Dhanush Department of Software and Systems Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Manufacturing School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Assistant Systems Engineer Tata Consultancy Services Chennai India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

A key method used in the study of Natural Language Processing (NLP) is sentiment analysis, or emotion analysis, plays a pivotal role in text analysis. Its primary function is to discern and categorize the underlying emotions within textual content, classifying them as positive, neutral, or negative sentiments. A variety of textual inputs can be used with this process, including entire documents, individual sentences, and more. Understanding the sentiments expressed by individuals is of paramount importance to organizations in today's digital age. Clients and customers now have the means to express their thoughts and emotions with greater ease and immediacy than ever before. This wealth of sentiment data can offer valuable insights that organizations can leverage to enhance their products, services, and overall customer experience. The present study focuses on the sentiment analysis of Twitter data related to the COVID-19 pandemic, employing the Long Short-Term Memory (LSTM) algorithm. To improve the accuracy of sentiment analysis, a pre-processing procedure is introduced, which involves the use of the Neat Text module in Python to clean the tweets. In this research endeavor, a dataset comprising 1,79,107 COVID-19-related tweets is subjected to sentiment analysis using the proposed pre-processing module and LSTM. The results demonstrate an impressive accuracy rate of 96% in accurately determining the sentiments conveyed in these COVID-19 tweets. In contrast, the existing algorithm, based on Artificial Neural Network (ANN), achieved a significantly lower accuracy rate of 76%. This research not only showcases the effectiveness of LSTM and pre-processing in sentiment analysis but also highlights the significance of sentiment analysis in gaining valuable insights from vast amounts of textual data, especially when important events like the COVID-19 pandemic are involved. © 2024 Elsevier B.V.. All rights reserved.

关键词： COVID-19

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：