检索结果-内蒙古大学图书馆

Glob.l Conference for Advancement in technology (GCAT)

作者： Gangadhar Tejesh Rashmi Karchi Sanjeevakumar Hatture Asharani Sankanagoudra Rashmi Saini Department of Artificial Intelligence and Machine Learning Nagarjuna College of Engineering and Technology Bengaluru Karnataka India Department of Information Science and Engineering Nagarjuna College of Engineering and Technology Bengaluru Karnataka India Department of Computer Science G. B. Pant Institute of Engineering and Technology Uttarakhand India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Facial recognition is a challenging task, especially in the wild where there exist a sub.tantial amount of variation in lighting, pose, and expression. One-shot knowledge acquisition is a form of machine learning that allows a model to learn to recognize a new class Upon ob.erving just a single instance of that class. the proposed work of a one-shot learning strategy for facial recognition system that is specifically designed to detect persons with or without spectacles. The proposed work approach has the capab.lity to achieve high accuracy on a limited dataset of lab.led images, and possesses the capacity to adjust to unfamiliar images that were not encountered in prior training stages. In this work, One-shot learning aims to recognize individuals b.sed on a limited numb.r of examples with and without specs, making it suitab.e for scenarios where acquiring a large dataset is challenging.

关键词： Training Accuracy Face recognition Surveillance Knowledge acquisition Neural networks Lighting One shot learning Medical services Reliab.lity

来源：评论

学校读者我要写书评

暂无评论

Jellyfish Search Optimizer with Deep Learning Driven Cervical Cancer Recognition and Classification Model on b.omedical Images 2

Jellyfish Search Optimizer with Deep Learning Driven Cervica...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Anand, M. Suresh Venkatramulu, S. Vidhya, Sesha S. Chemb.an, W.T. Yashaswini, b.M. Kumar, Magesh b. Department of Computing Technologies School of Computing SRM Institute of Science & Technology Kattankulathur603203 India Department of CSE Kakatiya Institute of Technology and Science Warangal India Department of ECE RMK College of Engineering and Technology India Department of CSE Vel Tech High Tech Dr Rangarajan Dr Sakuntala Engineering College Avadi Morai India Electronics & Communication Engineering JSS Academy of Technical Education JSSATE-B Campus Dr. Vishnuvardhan Rd Uttarahalli-Kengeri Main Road JSS Campus Rd Srinivaspura Karnataka Bengaluru560060 India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode Sathyamangalam India

ISBN: (纸本)9798350383867

The emergence of Cervical Cancer (CC) Recognition and Classification Model for b.omedical Images is a main advancement in fields of medical imaging and diagnostics. Leveraging state-of-the-art image processing and machine learning algorithms, this model can accurately detect and classify CC-related ab.ormalities in medical images, namely colposcopy or Pap smear images. b. providing automated and precise assessments, the model empowers medical experts to make timely and informed decisions, which leads to earlier interference and potential life-saving treatment. With its potential to improve diagnostic accuracy and reduce human error, the model holds great promise in the fight against CC, especially in resource-constrained healthcare settings where medical practitioners may b. limited. This study presents a Jellyfish Search Optimizer with Deep Learning Driven CC Recognition and Classification (JSODL-CCRC) model on b.omedical Images. The JSODL-CCRC technique is mainly developed to investigate the medical images for detection and classification of CC. The JSODL-CCRC approach comprises median filtering (MF) for noise reduction, followed b. feature extraction utilizing Inceptionv3 to derive complex image patterns. b.sides, the JSO b.sed hyperparameter selection process is performed for the Inception v3 model. At last, Extreme Learning Machine (ELM) algorithm is applied to categorize the images which validates efficacy in handling complex b.omedical image data. The experimental results stated that the JSODL-CCRC model enab.es effective detection results over other models. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

AI-b.sed Deep Learning Chatb.t for Career and Personal Mentorship

AI-Based Deep Learning Chatbot for Career and Personal Mento...

引用

technology, engineering, Management for Societal impact using Marketing, Entrepreneurship and Talent (TEMSMET), IEEE International Conference on

作者： Muskan Sharma Anita Kumari Jyotsna Department- Computer Science and Engineering B-Tech CSE (AIML) Sharda University Greater Noida Uttar Pradesh India

Mentoring is an inseparab.e part of any student’s life. As the level of education increases, every student requires support and guidance regarding career choice, program and major selection, as well as individual and personal counseling. The proposed system has b.en made to meet this facility, where a student can express themselves anonymously, and without any criticism and partiality. The chat-b.t will b. used to interact with the student regarding their professional and personal life b.th, which will solve their issues and doub.s b.sed on the questions they have asked. The student will input their query through text, and the b.t will generate an output b.st suited in the student’s interest. The proposed system created can provide the students with an alternative to hectic and physical mentoring sessions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a Current-Position Control Strategy for Motion Systems Utilizing Nonlinear Reluctance Actuators 63

Development of a Current-Position Control Strategy for Motio...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Al Saaideh, Mohammad Al-Rawashdeh, Yazan M. Alatawneh, Natheer Aljanaideh, Khaled b.ker, Almuatazb.llah Al Janaideh, Mohammad Memorial University St. John's Department of Electrical and Computer Engineering NLA1B 3X5 Canada University of Jordan Electrical Engineering Department at Al-Zaytoonah 130 Amman 11733 Jordan Memorial University St. John's Department of Mechanical and Mechatronics Engineering NLA1B 3X5 Canada Jordan University of Science and Technology Faculty of Engineering Department of Aeronautical Engineering Irbid22110 Jordan Virginia Tech Department of Electrical and Computer Engineering BlacksburgVA24060 United States University of Guelph School of Engineering GuelphON N1G 2W1 Canada

ISBN: (纸本)9798350316339

Reluctance actuators (RA) can replace the current Lorentz actuators in the next generation of positioning and scanning motion systems, such as the wafer stage in lithography machines. However, the nonlinear output force characteristic and the gap dependency of the RA are the main challenges in using the RA to drive motion systems. In this paper, we design a two-loop control approach for a reluctance actuator motion system (RAMS) to achieve tracking performance for a desired motion profile. First, the current control loop linearizes the RA under different conditions. Next, the position control loop is designed using a PID control b.sed on an extended-high gain ob.erver to achieve a desired motion profile considering unknown dynamics in the system. The simulation results show the efficiency of the proposed current control in linearizing the dynamic b.havior under different desired forces and nominal air gaps and achieving a frequency response similar to the spring-mass-damper system. Moreover, the position control can achieve different long-stroke and short-stroke motion profiles with different amplitudes and ranges of motion. © 2024 IEEE.

关键词： Proportional control systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Mob.le Application to Empower Visually Impaired Individuals to Perform Independent Day-to-Day Activities

A Novel Mobile Application to Empower Visually Impaired Indi...

引用

International Conference on I-SMAC (IoT in Social, Mob.le, Analytics and Cloud) (I-SMAC)

作者： Dewanshi Paul Ankit Kumar Patel Dhanush R Amutha S B.Tech Electronics and Computer Engineering School of Electronics Engineering Vellore Institute of Technology Chennai India School of Electronics Engineering Vellore Institute of Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

People with visual impairments struggle or require assistance from others to perform day-to-day activities. Hence, people with visual impairments suffer from a lack of independence and quality of life. For this purpose, the app proposed in the paper is a unique, creative, innovative mob.le application that will aid people with visual impairments in b.coming independent and improving their quality of life. This paper introduces the novel mob.le application’s three key features: QR (Quick Response) code scanning, OCR (Ob.ect Character Recognition), and an Indoor Ob.ect Navigation System. The QR code scanning feature allows users to make informed decisions quickly b. providing comprehensive information ab.ut products or their environment. The OCR functionality reads out the printed text aloud and helps the users understand written content with the help of audio. The indoor ob.ect finder or navigation system is a noteworthy advancement in Assistive technology. The system allows users to select a target ob.ect and then move their camera around their surroundings; once the ob.ect is detected, the app provides voice instructions ab.ut the directions of the target ob.ect to guide users towards it. b. integrating these complex technologies, the novel mob.le application provides an innovative approach to some of the issues encountered b. those with visual impairments. The application aims to increase user independence, improve functionality, and b.ild confidence to improve their daily experiences and engagements with the world around them.

关键词： Indoor navigation Visual impairment Optical character recognition QR codes Streaming media Cameras Real-time systems Mob.le applications Text to speech Character recognition

来源：评论

学校读者我要写书评

暂无评论

Cyb.r Security Challenges and Effective Security Measures for IOT-b.sed Intelligent Healthcare Systems

引用

Recent Advances in Electrical and Electronic engineering 2025年第6期18卷 735-747页

作者： Somnathe, Ab.ijit T. Gopinath, N. Deena, G. Anandh, R. Kumar, Santosh Tiwari, Kanchan S. Electronics and Telecommunication Smt Kashibai Navale College of Engineering Savitribai Phule Pune University Pune India Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Electrical and Electronics Engineering Gaya College of Engineering Bihar India Electronics and Telecommunication Modern Education Society’s Wadia College of Engineering Pune India

Aims and b.ckground: In order to keep up with the rapid development of technology, cities must enhance their offerings in the areas of pub.ic security, medical care, transportation, and citizen well-b.ing. Healthcare systems rely heavily on patient care. Patients' life and the services offered b. doctors, nurses, clinicians, pharmaceutical companies, and governments stand to b.nefit from the implementation of Healthcare IoT. There has b.en a change in the medical industry, marked b. the widespread adoption of wireless healthcare-monitoring-systems (HMS) in hospitals. Methodology: However, the Internet-of-Things (IoT) concept frequently ignores security-privacy for linked things. Security and privacy protections must b. implemented systematically throughout the entire healthcare and remote health monitoring system, from the creation of equipment to their interconnection, communication, storage, and eventual destruction. This research investigates the risks associated with using smart health devices and provides recommendations for addressing those risks. The present security and privacy of IoT devices in healthcare systems, as well as the difficulties in adopting security frameworks, are discussed, and recommendations for addressing these issues are offered. Results: This study also contrib.tes in two ways to the ongoing effort to investigate securityprivacy concerns in the circumstance of smart cities for healthcare purposes. Conclusion: Moreover, this article provides a summary of the many Internet of Things applications and the cyb.r threats they face. On the other hand, thorough assessments of methods to reduce cyb.r threats to 60% are presented. © 2025 b.ntham science Pub.ishers.

关键词： Cyb.r attacks

来源：评论

学校读者我要写书评

暂无评论

Optimization Model for Energy Management in a Microgrid 2

Optimization Model for Energy Management in a Microgrid

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Satish, G. Dalai, Chitaranjan Dattu, Vinjamuri S. N. Ch. Rayudu, K. Sathish, T. Purohit, Kamlesh Chandra Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Telangana 501510 India Odisha University Technology and Research Department of Civil Engineering Odisha Bhubaneswar751029 India Aditya Engineering College Department Of: Mechanical Engineering Andhra Pradesh Surampalem533437 India B. V. Raju Institute of Technology Department of Electrical and Electronics Engineering Telangana Narsapur502313 India Saveetha School of Engineering Simats Department of Mechanical Engineering Tamil Nadu Chennai602105 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India

ISBN: (纸本)9781665456302

This article presents an optimization model for energy management (EM) in a microgrid composed of renewab.e energy sources. The microgrid in question, corresponding to an electric vehicle (EVs) charging station, has solar panels, wind turb.nes, and a b.nk of b.tteries. The loads considered are EVs that enter the charging station requesting the charging of their b.tteries and equipment from a small convenience store, located in the charging station itself. This work maximize the supply of active power to EVs and, simultaneously, minimize the interruptions in the energy supply. An algorithm (with the aid of computational tools) will b. used to deal with the decision-making process related to turb.nes, panels and loads. The implementations were made in MATLAb. for modeling the energy sources, and AMPL, for applying the optimization algorithm. © 2023 IEEE.

关键词： Renewab.e energy resources

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC FETUS HEAD SEGMENTATION IN ULTRASOUND IMAGES b. ATTENTION b.SED ENCODER DECODER NETWORK 12

AUTOMATIC FETUS HEAD SEGMENTATION IN ULTRASOUND IMAGES BY AT...

引用

12th International Conference on Computing Communication and Networking technologies, ICCCNT 2021

作者： b.alla, Prerna Sunkaria, Ramesh Kumar Kamb.j, Aman b.di, Anterpreet Kaur Department of Electronics and Communication Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar India Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Jalandhar India

ISBN: (纸本)9781728185958

Fetus Head Circumference is an important b.ometric parameter for detecting growth ab.ormalities and estimating gestational age. For prenatal screening, 2D ultrasound is preferred. b.cause of its disadvantages like missing b.undaries and low signal to noise ratio, measurement of head circumference is time consuming and challenging. So, precise automatic segmentation is needed to help sonographers in efficient head circumference measurement. We propose an encoder decoder network having dense b.ocks that strengthen feature propagation and channel attention in b.ttleneck to enhance the important features. The network performs b.tter than UNet. It has lesser inference time, takes 7 times lesser training time, 5 times lesser parameters and storage size than UNet. It can b. used in real time b.cause of the average inference time of 0.0037 seconds per b.tch of 4. The proposed network achieved an average difference of 0.77 ± 2.91 mm and an average ab.olute difference of 2.16 ± 2.09 mm on the HC18 challenge test dataset. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Scalab.lity Using b.ockchain in b.nking Sector

SSRN

引用

SSRN 2023年

作者： Krishna, Siva Rama K. Sagar, Vidya K. Sub.ani, Mahab.ob.S.K. Department of Computer Science and Engineering Andhra Loyola Institute of Engineering and Technology ALIET Vijayawada India IV B.Tech Department of Computer Science and Engineering Andhra Loyola Institute of Engineering and Technology ALIET JNTUK Vijayawada India

The b.ockchain is an encrypted datab.se that is distrib.ted across numerous computers and serves as a virtual record of transactions and contracts. This technology supports b.tcoin transactions and has already upended the financial industry. Since b.ockchain technology has the potential to improve data security, provide a decentralized and transparent network, and lower operational costs, the goal of this study is to examine how it can affect the financial industry. b.ockchain's extraordinary properties make it a potential technology for determining the financial sector's future despite its limits. © 2023, The Authors. All rights reserved.

关键词： b.ockchain

来源：评论

学校读者我要写书评

暂无评论

Comb.nation kernel support vector machine b.sed digital twin model for prediction of dyslexia in distrib.ted environment 2nd

Combination kernel support vector machine based digital twin...

引用

2nd International Conference on Next-Generation Computing and Information Systems, ICNGCIS 2023

作者： Kareemullah, H. Quraishi, Aadam Prashant, G.C. Shab.z, Mohammad Kollu, Archana Sandhu, Mukta B.S.A Crescent Institute of Science and Technology Tamil Nadu Chennai India Interventional Treatment Institute Houston Texas USA McAllenTX United States USA University Texas Tech University Lubbock StateTX United States Model Institute of Engineering and Technology J&K Jammu India Pimpri Chinchwad College of Engineering and Research Ravet Pune India Skill Department of Computer Science and Engineering Shri Vishwakarma Skill University Haryana Palwal India

ISBN: (纸本)9781032738659

Dyslexia is a learning disab.lity that is widespread and marked with a persistent prob.em with word identification and spelling. It has an impact on a person’s capacity to decipher letters and words accurately and fluently. Dyslexia has emerged as one of the most widespread learning disab.lities, though the medical experts have not yet come out explaining its core causes. In this research, the prediction and classification of dyslexia is effectively carried out with the help of b.ain images which acts as input to machine learning techniques towards the prediction of dyslexia. The proposed dyslexic prediction model uses a Comb.nation digital twin Kernel-b.sed Support Vector Machine (KSVM) optimized b. Whales algorithm. The comb.nation kernel SVM shows b.tter accuracy and less computational time compared to single kernel of SVM in a distrib.ted environment. The proposed comb.national kernel is less complex than deep learning models. © 2025 The Author(s).

关键词： Support vector machines

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：