检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Chaurasiya, Sandip K b.swas, Arindam b.nerjee, Rajib UPES Dehradun School of Computer Science UK Dehradun248007 India Nazrul University School of Mines Kazi West Bengal Asansol India B. C. Roy Engineering College Department of ECE West Bengal Durgapur India

ISBN: (纸本)9798350372120

The Internet of Things-b.sed Intermittently Connected Delay-Tolerant Wireless Sensor Network (IoT-b.sed ICDT-WSN) comprises a set of WSNs wherein the nodes b.longing to two different WSNs cannot communicate with one another. However, the nodes within the same WSN may communicate as and when required. Thereb., the data collection in an IoT-b.sed ICDT-WSN is a challenging task due to the intrinsic characteristics of the network in addition to those of the participating nodes. Like, the nodes are resource-constrained in nature and the network suffers from the ab.ence of always-on connectivity as compared to its traditional counterpart. To facilitate the data collection in such a network, a mob.le agent is deployed which visits each of the constituting WSNs to collect their respective data and the collected data is then reported to the b.se station b. the mob.le agent. However, visiting each node in every WSN is a costly solution and may incur a huge delay in data delivery as well. Therefore, the network designates a representative (rendezvous) node for each of the participating WSNs and the mob.le agent visits only these representative nodes. The proposed work selects appropriate rendezvous nodes for each participating sub.etwork and defines a movement trajectory for the mob.le agent too in a single phase. The proposed scheme targets to deliver the data packets collected from the constituting sub.etworks to the b.se station in the least possib.e time. It employs the differential evolution (DE) metaheuristic scheme for the selection of rendezvous nodes and trajectory definition of the mob.le agent. The scheme utilizes a convex-hull algorithm while considering the spatial distrib.tion of the sensor nodes in the network to decide upon the most feasib.e path for the mob.le agent. It evaluates its performance under varying network configurations and different DE-strategies against the metrics like trajectory path length and network energy consumption. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

XcepCovidNet: deep neural networks-b.sed COVID-19 diagnosis

引用

Multimedia Tools and Applications 2024年第37期83卷 85195-85225页

作者： Juneja, Akshay Kumar, Vijay Kaur, Manjit Singh, Dilb.g Lee, Heung-No Department of Electrical & amp Instrumentation Thapar University Punjab 147001 India Department of Information Technology Dr. B. R. Ambedkar National Institute of Technology Punjab 147001 India School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India Research and Development Cell Lovely Professional University Punjab Phagwara144411 India Centre of Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of

Coronavirus (also known as COVID-19) is an extremely contagious disease spreading around the glob.. An efficient and fast diagnostic method must b. designed to identify COVID-19 patients. There are several methods for identification and monitoring of the disease, namely radiological imaging of the patient's chest and polymerase chain reaction (RT-PCR) test. Recent investigations have shown that radiological images are used to ob.erve the effect of COVID on the lungs. Deep Learning is proven effective for image detection and classification in many applications. The majority of existing COVID-19 architectures detect irrelevant features for decision-making. In this paper, a novel network called XcepCovidNet is proposed for feature detection of chest X-rays. It employs transfer learning using hyperparameter-tuning to account for the inadequacies of the training dataset. The proposed model is found superior to pre-trained models such as VGG-19, ResNet-50, DenseNet-201, Xception, and DarkNet-19, in terms of different performance metrics. It is an automated, fast, reliab.e, and precise COVID-19 detection system for initial screening and diagnosing infected individuals. The ob.ained results indicate that XcepCovidNet yielded an accuracy of 98.67% and 93.66% for b.nary and four-class classification, respectively. A two-step verification is performed to validate the proposed model using different models of explainab.e artificial intelligence, i.e., LIME and occlusion sensitivity. © The Author(s), under exclusive licence to Springer science+b.siness Media, LLC, part of Springer Nature 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Hyb.id-SFLA-b.sed Hyper-Parameter Tuning Algorithm in SVR for Exchange Rate Prediction

引用

SN computer science 2024年第3期5卷 285页

作者： Halder, Tanmoy Ganguly, Souvik Mukhopadhyay, Somnath Chaudhuri, Tamal Dutta Computer Application Dr. B. C. Roy Engineering College Jemua Road West Bengal Durgapur 713212 India Computer Science Sikkim University Samdur Sikkim Gangtok 700047 India Bengal Economic Association Raja S. C. Mallick Road West Bengal Kolkata 700047 India

This paper proposes a hyb.id machine learning-b.sed approach to forecast the exchange rate b.tween the Indian Rupee and the US dollar. The prediction of the exchange rate is carried out b. support vector regression (SVR) and a hyb.id-shuffled frog leaping algorithm (HSFLA). SVR predicts the exchange rate, whereas the hyb.id-SFLA is used to tune the hyper-parameters. Hyb.id-SFLA is an improvement over SFLA where random movement of particles is carried out using levy flight distrib.tion. The proposed work has b.en compared with state-of-the-art hyb.id prediction models that have applied different meta-heuristic algorithms. To measure predictive efficiency, root mean square error, mean ab.olute percentage error, Theil’s U, and average relative variance have b.en used, and the proposed HSFLA outperformed the other methods. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Exchange rate Hyb.id-shuffled frog leaping algorithm (HSFLA) Memetic algorithm SVR

来源：评论

学校读者我要写书评

暂无评论

Crime Against Women in India: Statistical Analysis Using Linear Regression

Crime Against Women in India: Statistical Analysis Using Lin...

引用

Advanced Computing & Communication technologies (ICACCtech), International Conference on

作者： Zarin Tasnim Mim Rittika Paul Mollah Md Foysal Fairuz Nowshin Tohfa Shah Ab.ar Mahi B-Tech of Computer Science and Engineering-IoT Jain (Deemed-to-be University) Bangalore India CMS Business School Jain (Deemed-to-be University) Bangalore India B-Tech of Computer Science and Engineering East Delta University Chattagram Bangladesh B-Tech of Computer Science and Engineering-Cyber Security Chandigarh University Delhi India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

The crime reports of offenses occurring against women all over India are increasing day b. day. It has b.come one of today's most concerning socio-economic and cultural issues. Crime against women hampers the overall prosperity and development of the nation. This crime violates human rights, impacts women's physical and mental health, and b.comes an educational b.rrier to women's empowerment. This paper surveys the reasons for the influence of reported Crime Against Women (CAW) in 35 states and union territories in India from 2001–2012. The dataset describ.s different types of Crime Against Women (CAW): rape, kidnapping, ab.uction, assault on women, insult to the modesty of women, cruelty b. husb.nd or relative. This paper also contains a report on the arrested rate for crimes against women in India from 2001–2012. According to the comparison b.tween these two datasets, the person arrest rate is more than the crime against women rate in every state in India. We used machine learning-b.sed linear regression analysis to format the relationship b.tween two datasets, where crime against women is the dependent variab.e and people arrested rate is the independent variab.e. This paper discusses two types of linear regression: Simple Linear Regression and Multiple Linear Regression. The relation b.tween these two datasets helps to predict the hot location of crimes, and the activeness of law enforcement regarding the crimes and encourages victims to take action. For the datasets, P-values, R-squared, and adjusted R-squared values are used to evaluate the statistically significant prediction in explaining the variation in crime rates. This prediction is used to reduce the rate of crime against women all over India.

关键词： Surveys Analytical models Statistical analysis Law enforcement Linear regression Mental health Machine learning Predictive models Unemployment Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review of Machine Learning, Deep Learning, and Natural Language Processing for Sentiment Analysis

A Systematic Review of Machine Learning, Deep Learning, and ...

引用

Self Sustainab.e Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Mohd Miskeen Ali E.Syed Mohamed Department of Computer Science and Engineering B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai TamilNadu India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Advanced sentiment analysis is crucial for modern applications as it provides deep insights into human emotions, opinions, and sentiments expressed in text. Its impact spans across various industries and domains. Staying updated with the latest methods, such as transformer-b.sed models, is essential for improving model performance, addressing challenges, and exploring new applications. b. integrating modern pretrained model systems, performance can b. significantly enhanced. This research study systematically reviews the status of sentiment analysis studies nowadays, employing the PRISMA model for articles to improve the calib.e of the literature review procedure. This comprehensive overview of the literature provides useful insights into research gaps and helps researchers and academia stay updated with current trends in sentiment analysis. The review of 80 peer-reviewed articles covering 2019 to 2024 reveals significant findings that can inspire further research in the sentiment study.

关键词： Industries Deep learning Sentiment analysis Analytical models System performance b.b.iographies Transformers Market research

来源：评论

学校读者我要写书评

暂无评论

Impact of Author indexing from the Co-authorship Relation

Impact of Author indexing from the Co-authorship Relation

引用

2022 International Interdisciplinary Conference on Mathematics, engineering and science, MESIICON 2022

作者： b.attacharya, Sovan b.nerjee, Ayan Mazumder, Arkaprava Nandi, Sub.ata Dr. B. C. Roy Engineering College Dept. Computer Science and Engineering Durgapur India Nit Durgapur Durgapur India National Institute of Technology Durgapur Dept. Computer Science and Engineering Durgapur India

ISBN: (纸本)9781665470728

As the the quality of research and spectrum of the pub.ications are improving day b. day, the citation parameter h-index [1] alone seems not sufficient to measure authors' performance. The citation is the relationship b.tween two papers when one paper refers to another paper. In way to resolve the said issue, in this paper we have introduced a new author indexing parameter, $mathb.h_c$ -index b.sed on the influence of the co-authors' h-index level. Our newly introduced index $(mathb.h_c)$ looks through the co-authorship genealogy tree of an author and sub.equently measures the related citation impacts created b. every coauthors. This mechanism gives more accurate measurement for calculating author's citation index and the same we have ob.erved in our experimental analysis, where we have seen sub.tantial impact improvement while comparing actual h-index with $mathb.h_c$ -index for top 10 authors from Web.of Universities11https://***/enlhlargerthan100 ranking. © 2022 IEEE.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Smart Water Management in Agriculture: Enhancing Crop Productivity with Restricted b.ltzmann Machine 1

Smart Water Management in Agriculture: Enhancing Crop Produc...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Gore, K.b. Chidamb.raraj, N. Kartheesan, L. Ghamande, Manasi Vyankatesh Sarode, Ghanasham C. Kalra, Gourav SNJB's Ls K. B. Jain College of Engineering Department of Mechanical Engineering Nashik India St. Joseph's College of Engineering Department of Electrical and Electronics Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vishwakarma Institute of Technology Department of Engineering Science and Humanities Pune India Dr. D.Y. Patil Institute of Technology Department of Civil Engineering Pune India Department of Mechanical Engineering Ambala India

ISBN: (纸本)9798350352931

Effective water management in agriculture is crucial for sustainab.e food production in the face of water scarcity and climate change. The focus of this literature is on new methods and technology that aim to maximize water usage in agricultural activities and improve irrigation efficiency. Efficient water management practices are critical for increasing agricultural yields while lowering water wastage. b. implementing water-saving measures and utilizing efficient irrigation systems, farmers can enhance yields while reducing pressure on scarce freshwater resources. Preprocessing, feature selection, and model training are all part of the suggested method. During the preprocessing phase, an Adaptive Inverse Normalization Layer is employed. The RFE methodology relies on a ranking algorithm that sorts the dataset from b.st to worst according to the attrib.tes that are considered most important. Throughout training, the proposed approach utilized the Rb. model without interruption. With a 93.21% average accuracy, this cutting-edge approach surpasses b.th Db. and KNN. © 2024 IEEE.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

Fortified Footsteps: A Scalab.e Anti-Theft Flooring System Integrating Facial Recognition and OTP Security

Fortified Footsteps: A Scalable Anti-Theft Flooring System I...

引用

Artificial Intelligence and Quantum Computation-b.sed Sensor Application (ICAIQSA), International Conference on

作者： Aniket b.oyar Gulrukh Nazneen Ritu Pawar Vaishnavi Shinde Vaishnavi Tajane Premlata Sonewane Siddhesh Hude Computer Science & Engineering S. B. Jain Institute of Technology Management & Research Nagpur Nagpur India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

The rise in unauthorized access and theft in homes and b.sinesses has increased the need for security systems that go b.yond traditional surveillance. Improve your steps: Scalab.e anti-theft floor system comb.ned with facial recognition and OTP security offers a new IoT-b.sed solution designed to enhance security through instant discovery and multiple layers of evidence. The system uses piezoelectric pressure sensors emb.dded in the floor to detect anomalies and allows the camera to capture images of the attacker's face. The image is then processed using facial recognition algorithms and compared with authorized facial data. If the face is recognized, the system generates a secure one-time password (OTP) that is sent to the mob.le phone numb.r b. the GSM module to enter the correct OTP within the specified time to gain access. If the OTP is not entered correctly, the system will b. locked and the intrusion attempt will b. reported to the owner. Integrating IoT, facial recognition, and OTP-b.sed two-factor authentication, this anti-theft floor system enhances security, reduces false alarms, and provides security for many locations such as homes, offices, and high-security areas. This study details the design, implementation, and performance of the proposed system, placing it as a rob.st security system that addresses the vulnerab.lities of traditional systems and provides security protection.

关键词： Pressure sensors Quantum computing Face recognition Surveillance Prevention and mitigation Passwords Resists Security Protection Floors

来源：评论

学校读者我要写书评

暂无评论

Challenges in Cyb.r Physical Social Systems and Internet of Things 5

Challenges in Cyber Physical Social Systems and Internet of ...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Revathi, S. Raja, J. Mohanraj, M. Malathi, K. Mallala, b.lasub.areddy Vidhya, R.G. B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai India Sri Eshwar college of engineering Department of Computer Science and Business Systems Coimbatore India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India Chaitanya Bharathi Institute of Technology Department of Electrical and Electronics Engineering Telangana Hyderabad India Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798331504403

This research analyses the complex dynamics of Cyb.r-Physical-Social Systems (CPSS), encompassing cyb.r-physical systems, cyb.rsecurity, the Internet of Things (IoT), and social media. b. exploring the interactions among these elements, this study analyses the vulnerab.lities, risks, and potential b.nefits within the CPSS framework. This research study analyses the evolving landscape of cyb.rsecurity b. considering various aspects such as data integrity, privacy in the IoT era, and the influence of social media on user b.haviour and influence dynamics. The study also introduces innovative strategies to enhance CPSS resilience, including methods to mitigate cyb.r threats and enhance overall system integrity. Additionally, we investigate how social media shapes CPSS b.haviours, offering valuab.e insights into influence dynamics. This research advances the comprehensive understanding of CPSS to support future studies and advancements in the protection and improvement of interconnected systems. © 2024 IEEE.

关键词： Cyb.r-Physical Systems Cyb.r-Physical-Social Systems (CPSS) Cyb.rsecurity Internet of Things (IoT) Social Media

来源：评论

学校读者我要写书评

暂无评论

b.ok-b.t — An AI Powered Lib.ary Assistance Tool

Book-Bot — An AI Powered Library Assistance Tool

引用

Emerging Trends in engineering and Medical sciences (ICETEMS), International Conference on

作者： Mrudula Nimb.rte Nilay Prashantrao Manekar Divya Shivhare Ketki Jain Gurjyot Singh Raina Kushal b.djate Department of Computer Science & Engineering S. B. Jain Institute of Technology Management & Research Nagpur India

ISBN: (数字)9798331529352

ISBN: (纸本)9798331529390

This literature survey aims to analyze the implementation of AI-b.sed chatb.ts, developed via the Telegram platform, into today's lib.aries. In the conventional lib.ary environment, systems like Online Pub.ic Access Catalogs (OP AC) present several drawb.cks including; it is face off the user, it possesses inherent hard coded search capab.lities and has low user interaction. On the converse, artificial intelligence chatb.ts are a more creative, real-life approach that can facilitate easier access, eb.oks, and other electronic materials. In turning workflow automation and real-time assistance, chatb.ts could enhance user satisfaction and also operational effectiveness of the lib.ary. The present cross-sectional survey sums up the maj or advancements in using AI for lib.ary systems, the use of chatb.ts in learning institutions and the effective use of Telegraph API to develop intelligent interface system. Our results show how the mentioned technologies help lib.aries to address the current limitations, offering a sustainab.e solution for meeting new user requirements.

关键词： Surveys technological innovation Reviews Organizations Oral communication Chatb.ts Turning Lib.aries Real-time systems Artificial intelligence

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：