检索结果-内蒙古大学图书馆

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

作者： Balayogi, G. Kuppusamy, K.S. Department of Computer Science School of Engineering and Technology Pondicherry University Puducherry India

ISBN: (纸本)9789819939626

Usable security is an area of active research. Several factors needs to be considered while making the security usable. As the digital platforms have evolved into the primary source of information and service consumption, it is essential to make digital space secure and usable for all categories of users which certainly includes persons with visual impairments. Several attacks have been targeted toward people with visual impairments, as they are dependent on the Internet for their day-to-day activities. With the significant number of users with disabilities, there are various attempts to make the digital ecosystem safer for persons with disabilities. This paper discusses the key challenges encountered while designing a usable security systems for persons with visual impairments. This work proposes a shoulder surfing resistant Personal Identification Number (PIN) entry mechanism for visually impaired individuals utilizing smartphone’s touch feature. The proposed model maps the finger movements into a predefined digit. As the movements look random for an outsider, shoulder surfing becomes significantly complex. © 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

GAIT: A Computing Survey Towards Approaches, Methodologies and Applications

GAIT: A Computing Survey Towards Approaches, Methodologies a...

引用

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

作者： Singhal, Prateek Yadav, Rakesh Kumar Maharishi University of Information Technology Department of Computer Science & Engineering Lucknow India

ISBN: (纸本)9798350302820

A pattern or manner of walking called 'human gait analysis' is now being used in medical diagnosis. The examination of human gait points to a number of orthopaedic and neurological system problems. This article provides a state-of-the-art examination of gait analysis techniques, strategies. The literature is gathered from a number of digital libraries linked to reputable SCI/(E) indexing journals. This study provides a detailed explanation of the theoretical underpinnings of gait parameters, including the many types, methodology, applications and tools that have been utilised in the past. Additionally, attention is placed on the numerous methods for gait analysis that are based on kinematics, kinetics, and computational intelligence in the literature. Numerous readers in the community who are working on gait pattern analysis for diagnosis and related rehabilitation programmes will also benefit from the study that has been provided. © 2023 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Multi Label Classification Algorithm Based on Conditional Local Correlations among Labels and Ensemble Learning 25

Multi Label Classification Algorithm Based on Conditional Lo...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Alazaidah, Raed Nasir, Ola Hadi, Wael Samara, Ghassan Al Daoud, Essam Aljaidi, Mohammad Khouj, Mohammed Talat Elsoud, Esraa Abu Alzoubi, Haneen Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Petra University Faculty of Information Technology Department of Cyber Security Amman Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Applied Science Private University Faculty of Information Technology Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

Multi-Label Classification (MLC) is an advanced form of traditional classification, where each data instance is simultaneously associated with multiple labels. The importance of MLC has increased significantly in recent years, due to its wide range of application areas. Modern algorithms, when faced with the challenge of multiple labels, continue to show suboptimal performance, conversely, they show significantly superior performance when processing single-label datasets. This paper proposes a new algorithm to deal with the problem of transforming datasets from multiple labels to single labels by exploiting conditional and local correlations between labels after applying the Apriori predictive algorithm to extract relationships. Six ensemble learning models: Voting Hard, Voting Soft, Voting Weighted, Stacking LR, Stacking RF, and Stacking SVM, along with four classification models: SMO, DecisionStump, Random Forest, and Random Committee, were applied to three datasets. The algorithm showed effective and good performance by comparing the results of the proposed Multi Label Classification algorithm based on Conditional Local Correlations among Labels (MLC-CLCL) with several popular algorithms for dealing with multiple labels. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing compatibility and biodegradability of polylactic acid/biomass composites through torrefaction of forest residue

引用

Journal of Bioresources and Bioproducts 2025年第1期10卷 51-61页

作者： June-Ho Choi Myeong Rok Ahn Chae-Hwi Yoon Yeon-Su Lim Jong Ryeol Kim Hyolin Seong Chan-Duck Jung Sang-Mook You Jonghwa Kim Younghoon Kim Hyun Gil Cha Jae-Won Lee Hoyong Kim Center for Bio-based Chemistry Korea Research Institute of Chemical Technology(KRICT)Ulsan 44429South Korea Department of Wood Science and Engineering College of Agriculture and Life SciencesChonnam National UniversityGwangju 61186South Korea Interdisciplinary Program in IT-Bio Convergence System Chonnam National UniversityGwangju 61186South Korea

This study investigated the effects of torrefaction on forest residue(FR)and its subsequent ap-plication as a bulk-loading filler in polylactic acid(PLA)*** enhanced the chemical properties of FR,improving its compatibility with PLA,and the crystallinity increased from 24.9%to 42.5%.The process also improved the hydrophobicity of PLA/biomass composites,as demonstrated by the water contact angle of 76.1°,closely matching that of neat PLA(76.4°).With the introduction of 20%modified biomass properties after torrefaction treatment,the tensile strength of PLA/biomass composite increased from 58.7 to 62.3 ***,the addition of torrefied forest residue(TFR)accelerated biodegradation by increasing the onset of degrada-tion and inhibiting *** 90 d,the biodegradability of PLA/biomass composites reached 94.9%,which had a 6.9%increase compared to the neat PLA(88.8%).Overall,this study highlights the potential of torrefaction in enhancing both the physical properties and biodegrad-ability of PLA-based composites,contributing to a more sustainable approach to reducing plastic pollution.

关键词： Forest residue Torrefaction Bulk-loading filler Polylactic acid composite Hydrophobicity Tensile strength Biodegradability

来源：评论

学校读者我要写书评

暂无评论

Parasitology Unveiled: Revolutionizing Microorganism Classification Through Deep Learning 6

Parasitology Unveiled: Revolutionizing Microorganism Classif...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Hosen, Md Delwar Bin Mohiuddin, Arafath Sarker, Nayamul Sakib, Md Shadman Al Sakib, Abdullah Dip, Riyadot Hossain Ahmed, Md. Redwan Haque, Rezaul North South University Department of Electronics and Communication Engineering Dhaka Bangladesh WestcliffUniversity Department of Information Technology California United States East West University Department of Computer Science and Engineering Dhaka Bangladesh Kyungdong University Department of Computer Engineering Gangwon-do Korea Republic of

ISBN: (纸本)9798350385779

Microorganisms play a crucial role in multiple fields, such as medical diagnostics, food safety, and ecological research, accounting for a significant 60% of Earth's biomass. This paper explores the complex connection between microorganisms and ecosystems, with a focus on accurate parasite classification methods. Conventional approaches, although important, have their limitations, leading to a growing dependence on CNN s in image analysis to enhance accuracy. Utilizing advanced DL techniques, particularly pretrained CNNs, has completely transformed the field of microorganism classification, providing unparalleled accuracy and efficiency. This study delves deeper into the intersection of swarm intelligence and DL algorithms, with a specific focus on the complex task of parasite identification. The effort is backed by a comprehensive dataset consisting of 34,298 images from ten different parasite species. The study employs meticulous preprocessing techniques, including uniform scaling and normalization, to maintain the integrity and precision of the dataset. These techniques serve as the foundation for subsequent modeling efforts. In addition, a comprehensive examination of four pretrained CNN architectures offers valuable insights that are crucial for selecting a model. Dynamic visualizations provide a thorough representation of model convergence dynamics, helping to enhance understanding of classification performance. The XceptionNet model stands out as the highest performer, achieving an impressive accuracy and F1 score of 0.9489 and 0.9492, respectively. This research demonstrates notable progress in the intersection of AI and biology, leading to new possibilities in disease diagnosis and improvements in public health practices by refining microorganism classification methods. © 2024 IEEE.

关键词： Microorganisms

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Machine Learning Algorithms and Transformer-based Methods for Multiclass Sentiment Analysis on Twitter 14

A Comparison of Machine Learning Algorithms and Transformer-...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Singh, Aakash Kumar, Suresh Netaji Subhas University of Technology Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350335095

The growing number of tweets being produced on Twitter and other social media platforms has made sentiment analysis a crucial task in comprehending individuals' viewpoints and emotions. We focus on the challenge of Twitter emotion classification in this paper and perform sentiment analysis on six different emotions: joy, anger, sadness, fear, surprise, and disgust. The performance of four distinct models is studied as this topic is addressed as a multiclass classification challenge: Naive Bayes, logistic regression, SVM, and DistilBERT, a transformer-based model. Experiments are run on a dataset of over 16,000 tweets that have been annotated with six emotions: joy, anger, sadness, fear, surprise, and disgust. DistilBERT outperforms the other models with an overall accuracy of 93.5%, according to our results. The accuracy of Naive Bayes is 78%, the accuracy of logistic regression is 89%, and the accuracy of SVM is 88%. Our research demonstrates the utility of transformer-based models, specifically DistilBERT, in sentiment analysis tasks using Twitter data. The findings also highlight the significance of appropriate pre-processing techniques in the performance of traditional machine learning models. Our findings have practical implications for businesses looking to gain insights into customer opinions and preferences via social media platforms such as Twitter. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-hop Clustering Approach with Low Energy Consumption in WSN

引用

computer Systems science & engineering 2023年第4期45卷 903-924页

作者： R.Nithya Roobaea Alroobaea Ahmed Binmahfoudh Zairi Ismael Rizman Department of Computer Science and Engineering Vivekananda College of Engineering for WomenTiruchengode637205Tamil NaduIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia School of Electrical Engineering College of EngineeringUniversiti Teknologi MARA23000DungunTerengganuMalaysia

The purpose of sensing the environment and geographical positions,device monitoring,and information gathering are accomplished using Wireless Sensor Network(WSN),which is a non-dependent device consisting of a distinct collection of Sensor Node(SN).Thus,a clustering based on Energy Efficient(EE),one of the most crucial processes performed in WSN with distinct environments,is *** order to efficiently manage energy allocation during sensing and communication,the present research on managing energy efficiency is performed on the basis of distributed *** of EE methods were incapable of supporting EE routing with MIN-EC in WSN in spite of the focus of EE methods on energy harvesting and minimum Energy Consumption(EC).The three stages of performance are proposed in this research *** the outset,during routing and Route Searching Time(RST)with fluctuating node density and PKTs,EC is reduced by the Hybrid Energy-based Multi-User Routing(HEMUR)model proposed in this *** efficiency and an ideal route for various SNs with distinct PKTs in WSN are obtained by this *** utilizing the Approximation Algorithm(AA),the Bregman Tensor Approximation Clustering(BTAC)is applied to improve the Route Path Selection(RPS)efficiency for Data Packet Transmission(DPT)at the Sink Node(SkN).The enhanced Network Throughput Rate(NTR)and low DPT Delay are provided by *** MAX the Clustering Efficiency(CE)and minimize the EC,the Energy Effective Distributed Multi-hop Clustering(GISEDC)method based on Generalized Iterative Scaling is *** Multi-User Routing(MUR)is used by the HEMUR model to enhance the EC by 20%during *** compared with other advanced techniques,the Average Energy Per Packet(AEPP)is enhanced by 39%with the application of proportional fairness with Boltzmann Distribution(BD).The Gaussian Fast Linear Combinations(GFLC)with AA are applied by BTAC method with an enhanced Communication Overhead(COH)for an increase in performance

关键词： Sensor node clustering routing energy consumption multi-path routing

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 Mobile WebRTC-Based Platform to Support Young and Upcoming Researchers 2

A Mobile WebRTC-Based Platform to Support Young and Upcoming...

引用

2nd Zimbabwe Conference on Information Communication and technology, ZCICT 2023

作者： Dlodlo, Nomusa Rwafa, Wilson Moyo, Sibonile Chilumani, Khesani R. University of Rhodes Department of Computer Science Makhanda South Africa National University of Science and Technology Department of Informatics and Analytics Bulawayo Zimbabwe

ISBN: (纸本)9798350318128

Lack of research support is impacting the research capacity in Zimbabwean universities, which calls for a system that supports young and upcoming researchers to be put in place. The problems that arise as a result of the status quo are that research output is lagging behind that of other countries, developing research capacity is impacted, quality research is lacking, and the critical research skills gap which hampers economic recovery is widening. The intention of this research is to develop a mobile WebRTC-based platform to connect established researchers with young and upcoming researchers for guidance and support and to enable peer-to-peer learning. This therefore is a form of knowledge management platform that encourages knowledge dissemination among Zimbabwean academics. This research builds a mobile application that allows young researchers to collaborate with more experienced researchers and peers. While the experienced researchers will use this technology to guide the young researchers, the platform will also encourage peer-to-peer learning. The application consists of the three APIs of the WebRTC platform of peer-to-peer learning, multipoint conferencing, and selective forwarding to build a rich environment for interaction between the researchers. © 2023 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Neuroimaging Data Analysis of an Artificially Intelligent Human Mind 2nd

Neuroimaging Data Analysis of an Artificially Intelligent Hu...

引用

Second International Conference on Security, Privacy and Data Analytics, ISPDA 2022

作者： Singh, Ajay Dhanda, Namrata Verma, Rajat Department of Computer Science and Engineering Amity University Uttar Pradesh Lucknow India Department of Computer Science and Engineering Pranveer Singh Institute of Technology Kanpur India

ISBN: (纸本)9789819935680

It was depicted by the specialists, how four decades of study on cognitive architectures has brought about a critical union of different strategies towards a bunch of essential suppositions, they name it, the Standard Model of Mind. The SMM initially made to address a consensual viewpoint of "human-like mind," either from artificial intelligence or cognitive exploration, which, if valid, should be valid for the human mind. We give a prompt examination of this speculation in light of a re-examination of fMRI data that span across many cognitive cycles and intricacy. The SMM was separated to two unmistakable potential decisions that entered either helpful or fundamental assumptions of the SMM using a spread-out approach (Dynamic Causal Showing) to focus on utilitarian relationship between mind locales. The results reveal that the SMM beats various models generally through each dataset, showing that the SMM best tends to the utilitarian prerequisites of cerebrum activity in fMRI data. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Memory architecture

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：