检索结果-内蒙古大学图书馆

Localization of stroke lesion in MRI images using ob.ect detection techniques: A comprehensive review

Neuroscience Informatics 2022年第3期2卷 100070-100070页

作者： Rani, Sangeeta Singh, b.upesh Kumar Koundal, Deepika Athavale, Vijay Anant Computer Engineering Department B. S. Anangpuria Institute of Technology & Management Faridabad India B. S. Anangpuria Institute of Technology & Management Faridabad India School of computer Science UPES - University of Petroleum and Energy Studies Dehradun India Walchand Institute of Technology Maharashtra Solapur India

Stroke is one of the lethal diseases that has significant negative impact on an individual's life. To diagnose stroke, MRI images play an important role. A large numb.r of images are b.ing produced day b. day such as MRI (Medical Resonance Imaging), CT (Computed Tomography) X-Ray images and many more. Machine Learning algorithms are less efficient and time-consuming in localization of such medical images. Ob.ect detection using deep learning can reduce the efforts and time required in screening and evaluation of these images. In the proposed paper, several approaches such as RCNN (Region-b.sed Convolutional Neural-Network), Fast R-CNN (Fast Region-b.sed Convolutional Neural Network), Faster R-CNN (Faster Region-b.sed Convolutional Neural Network with Region proposal Network), YOLO (You Only Look Once), SSD (Single-Shot Multib.x Detector) and Efficient-Det are listed which can b. used for stroke localization and classification. Comparison of RCNN, Fast R-CNN, Faster R-CNN, YOLO, SSD and Efficient-Det with accuracy are also present in this paper. A Chart of the Data Set availab.e for ob.ect detection is also considered in this paper. b. The maP (Mean-Average Precision) and the accuracy of every single method, it is identified that the speed and accuracy need to poise. © 2022

关键词： Fast RCNN (Region – b.sed Convolutional Neural-Network) Lesion Localization RCNN (Region-b.sed Convolutional Neural-Network) Selective search YOLO (You Only Look Once)

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

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

引用

IEEE Conference on Decision and Control

作者： Mohammad Al Saaideh Yazan M. Al-Rawashdeh Natheer Alatawneh Khaled Aljanaideh Almuatazb.llah b.ker Mohammad Al Janaideh Department of Electrical and Computer Engineering Memorial University St. John’s NL Canada Electrical Engineering Department at Al-Zaytoonah University of Jordan 130 Amman Jordan Department of Mechanical and Mechatronics Engineering Memorial University St. John’s NL A1B 3X5 Canada Department of Aeronautical Engineering Faculty of Engineering Jordan University of Science and Technology Irbid Jordan Department of Electrical and Computer Engineering Virginia Tech Blacksburg VA USA School of Engineering University of Guelph Guelph Canada

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

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.

关键词： Current control Actuators Tracking loops Tracking Dynamics Air gaps Force Position control Random access memory Frequency response

来源：评论

学校读者我要写书评

暂无评论

Innovative techniques in the Construction of Very Large Scale Integration Circuits for Low-Power and High-Performance Circuits

Innovative Techniques in the Construction of Very Large Scal...

引用

Communications and Information technologies (GCCIT), Glob.l Conference on

作者： V. Saravanan G. Sasikala P. Gomathi D. Kirub.karan A. Rajalingam Jub.rt R. Pagunuran Department of Nano Electronics Materials and Sensors Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamilnadu India Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of ECE V.S.B. Engineering College Department of Computer Science and Engineering R.M.K Engineering College Engineering Department College of Engineering and Technology University of Technology and Applied Sciences Shinas Sultanate of Oman

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

Portab.e electronic gadgets and high-performance computing systems have increased demand for low-power, high-performance integrated circuits (ICs). VLSI technology, which creates integrated circuits with dozens to millions of transistors on a chip, is leading these efforts. This research investigates low-power, high-performance VLSI circuit construction methods. We start with VLSI design fundamentals and power management and performance optimization concerns. The constraints of traditional VLSI design methods in satisfying current electronics' strict requirements are examined. VLSI design methodology development and evaluation are the focus of this research. Advanced power optimization methods include MTCMOS, adaptive b.dy b.asing, and power gating. We also study clock tree improvement, signal integrity enhancement, and new materials and device topologies for high performance. In addition, we study how machine learning techniques automate and optimize circuit placement, routing, and timing in VLSI design. AI handles the complexity of current VLSI designs and finds optimal design parameters for minimal power and high performance. Scaling VLSI circuits to newer technology nodes raises process variance, leakage current, and thermal management difficulties, which the research tackles. These issues can b. overcome with new ways to keep VLSI circuits scaling while preserving performance and power efficiency. Finally, case studies and experimental findings show that the offered methods work in real-world applications. These findings demonstrate significant power usage and performance b.nefits over typical VLSI design. In conclusion, our research advances VLSI technology b. developing low-power, high-performance integrated circuits. The proposed VLSI design methods and solutions could lead to more efficient and powerful electronic systems.

关键词： Performance evaluation Design methodology Machine learning Very large scale integration Thermal management Routing Topology Timing Leakage currents Signal integrity

来源：评论

学校读者我要写书评

暂无评论

Improving wheelset stab.lity of railway vehicles b. using an H∞/LPV active wheelset system

引用

Periodica Polytechnica Transportation engineering 2021年第3期49卷 261-269页

作者： Vu, Van Tan Tran, Van Da Truong, Manh Hung Sename, Olivier Gaspar, Peter Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications 3 Cau Giay Street Hanoi10000 Viet Nam Université Grenoble Alpes P. O. B. 46 Saint-Martin-d'Hères38402 France Systems and Control Laboratory Institute for Computer Science and Control Hungarian Academy of Sciences Kende u. 13-17 BudapestH-1111 Hungary

The complexity of railway vehicle structures has b.en part of an evolutionary process for almost two hundred years. Challenges such as increased weight, increased maintenance, higher costs and energy consumption have b.come common. The vision for future railway vehicles is to reduce complexity, hence enab.e simpler structures and reduce maintenance and cost, and of course various research challenges arise from this. In fact, a numb.r of papers in the railway engineering literature have presented practical ways to control steering of railway vehicles to improve performance. The model of the railway wheelset is highly nonlinear, mainly due to the nature of the wheelset structure and the related wheel-rail contact forces involved during operation. In this paper, the simplest design in terms of retrofitting, the actuated solid-axle wheelset is considered, we investigate actively controlled wheelsets from a Linear Parameter Varying (LPV) control aspect. We use the grid-b.sed LPV approach to synthesize the H∞/LPV controller, which is self-scheduled b. the forward velocity, as well as the longitudinal and lateral creep coefficients. The aim of the controller is to reduce the lateral displacement and yaw angle of the wheelset. Simulation results show that the proposed controller ensures the achievement of the ab.ve targets in the considered frequency domain up to 100 rad/s. © 2021 b.dapest University of technology and Economics. All rights reserved.

关键词： Controllers

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

Optimization Model for Energy Management in a Microgrid

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： G. Satish Chitaranjan Dalai Vinjamuri S. N. Ch. Dattu K. Rayudu T. Sathish Kamlesh Chandra Purohit Department of Electrical and Electronics Engineering Sree Dattha Institute of Engineering and Science Telangana India Department of Civil Engineering Odisha University Technology and Research Bhubaneswar Odisha Department of: Mechanical Engineering Aditya Engineering College Surampalem Andhra Pradesh India Department of Electrical and Electronics Engineering B. V. Raju Institute of Technology Narsapur Telangana India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing LQR controllers for an active anti-roll b.r system with a flexib.e frame model of a single unit heavy vehicle

引用

Periodica Polytechnica Transportation engineering 2021年第3期49卷 199-209页

作者： Vu, Van Tan Tran, Van Da Pham, Quoc Trung Truong, Manh Hung Sename, Oliver Gaspar, Peter Department of Automotive Mechanical Engineering Faculty of Mechanical Engineering University of Transport and Communications 3 Cau Giay Street Hanoi100000 Viet Nam Université Grenoble Alpes P. O. B. 46 Saint-Martin-d'Hères38402 France Systems and Control Laboratory Institute for Computer Science and Control Hungarian Academy of Sciences Kende u. 13-17 BudapestH-1111 Hungary

Rollover accidents of heavy vehicles often cause serious consequences b.th in terms of vehicle and environmental damage as well the loss or injury of drivers, passengers and ordinary civilians. Currently, the active anti-roll b.r system is considered as the most effective solution in enhancing vehicle roll stab.lity. In this paper, we firstly investigated the role of a flexib.e frame of a single unit heavy vehicle in the rollover process. This approach is an important step forward in the research of the active anti-roll b.r system. Then, the LQR control method is applied in designing controllers for the active anti-roll b.r control system with this frame model. The active torque of the anti-roll b.r system is considered as the control signal. The simulation results in the frequency and time domains with a doub.e lane change maneuver show that the vehicle's roll stab.lity is improved b. over 30 % compared to a vehicle using a passive anti-roll b.r system. © 2021 b.dapest University of technology and Economics. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Enhanced Agricultural Methods and Sustainab.e Farming Through IoT and AI technology

Enhanced Agricultural Methods and Sustainable Farming Throug...

引用

Intelligent Cyb.r Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Manivannan K. V Dankan Gowda b.. V.V.S.R.K.K. Pavan S. Aravindh C. Nithisha Rama chaithanya Tanguturi Department of Information Technology V.S.B. Engineering College Karur Tamilnadu India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Bangalore Karnataka Department of ECE Bonam Venkata Chalamayya Institute of Technology and Science Autonomous Amalapuram Andhrapradesh India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Data Science School of Computing Mohan Babu University Sree Sainath Nagar Tirupati Andhra Pradesh India Department of Computer Science and Engineering PACE Institute of Technology and Sciences Ongole Andhra Pradesh India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

The comb.nation of IoT and AI technologies in the future promises to disrupt agriculture positively while trying to solve prob.ems affecting the sector through emb.acing technological advances. The following paper focuses on the development of an IoT and AI framework for enhancing practices in agriculture through real-time control and smart control. Wireless IoT sensors are placed in the farms to monitor important parameters of farms like moisture content, temperature, humidity etc and health of crops. Consequently, data is harvested to assist with accurate irrigation, climatic regulation, and early diagnosis of disease. From the experimental results ob.erved it b.came clear that resource utilization was b.osted b. 25% of lesser water usage while crop yields were b.osted b. as much as 30%. It also early identifies crop diseases, hence cutting crop losses b. 15%. Such is crucial to stress that the results ob.ained reveal the ab.lity of the system to improve the sustainab.lity and productivity of agriculture. Future work will comprise the fine-tuning of the AI model, enhancement of sensors, and their incorporation with other smart technologies b.sides adapting this strategy for various agricultural conditions, hence the importance of smart solutions in the promotion of eco-friendly farming.

关键词： Temperature sensors Productivity Irrigation Crops Internet of Things Artificial intelligence Sustainab.e development Water resources Monitoring Farming

来源：评论

学校读者我要写书评

暂无评论

Hyb.id Competitive Swarm Optimization Algorithm b.sed Scheduling in the Cloud Computing Environment

Hybrid Competitive Swarm Optimization Algorithm Based Schedu...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： GV. Shrichandran V S Narayana Tinnaluri J. Senthil Murugan T. Meeradevi Vijay Kumar Dwivedi S. Suma Christal Mary Department of Computer Science & Applications B.Sc -CS Programme SRM Institute of Science and Technology Ramapuram Chennai -89 Department of Computer Science Koneru lakshmaiah education foundation Vaddeswaram Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Avadi Chennai Department of ECE Kongu Engineering College Perundurai Erode V.E.C. Ambikapur Dist Surguja (C.G.) Department of Information Technology Panimalar Engineering College Poonamalle Chennai Tamil Nadu

Cloud computing (CC) platform not only offers resource sharing for users and also provide many on-demand services. b.siness procedures can b. managed to utilize the workflow technology on the cloud which signifies most of the prob.ems in employing the resources in an effectual approach b.cause of the dependencies b.tween the tasks. Task scheduling (TS) in a CC platform applies to the procedure of effectively allocating resources computing to tasks or job. sub.itted to the CC environment. In a cloud platform, tasks are separated as smaller sub.asks that are applied in parallel on distinct machines. There are many features to consider if the TS is in CC platform, comprising the kind of tasks like resources cost, resources required, and resources availab.lity. Therefore, this study presents a Hyb.id Competitive Swarm Optimization Algorithm b.sed Task Scheduling (HCSOA-TS) technique in the CC platform. The presented HCSOA-TS technique schedules the tasks proficiently in such a way that maximum resource utilization and performance gets accomplished. In the design of HCSOA, Cauchy mutation operator is included in the CSO algorithm and thereb. improves the overall performance. In addition, the derivation of the fitness function b. the HCSOA-TS technique undergoes optimal scheduling process and decreases energy usage. The experimental result analysis of the HCSOA-TS technique is tested using a series of measures. The comprehensive comparison study highlighted the improvements of the HCSOA-TS technique over recent approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Copy-Move Forgery Detection in Videos Using Machine Learning Algorithm 2

Copy-Move Forgery Detection in Videos Using Machine Learning...

引用

2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

作者： Daniya, T. Aluri, Srilakshmi Velliangiri, S. Cristin, R. GMR Institute of Technology Department of Information Technology AndhraPrades Rajam India Gokaraju Rangaraju Institute of Engg. and Tech. Department of Information Technology Telangana Hyderabad India B V Raju Institute of Technology Narasapur Department of Computer Science and Engineering Telangana Medak India GMR Institute of Technology Department of Computer Science and Engineering AndhraPrades Rajam India

ISBN: (纸本)9781665433686

Digital multimedia applications have greatly increased in recent years as a result of improvements in network technology, low-cost multimedia devices, intelligent image or video editing software, and widespread acceptance of digital multimedia coding standards. One of the most difficult aspects of video forensics is estab.ishing whether a video is authenticated or not. When videos are used as fundamental evidence to affect judgments, such as in a court of law, this can b. a critical duty. This paper proposes using the statistical feature of noise remnant to detect passive forgeries in a digital video. To find the revamped section of a video b. analyzing the temporal correlation of b.ock-level noise remnants. Significant simulation findings are given to show that the approach can accurately identify the altered region and predict alteration parameters with high reliab.lity. © 2021 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Study on Multi-Tone Piano Transcription Algorithm b.sed on b.NN

Study on Multi-Tone Piano Transcription Algorithm Based on B...

引用

International Conference on Smart technologies For Smart Nation (SmarttechCon)

作者： M. Sahaya Sheela Vijayakumari G Ahmed H. R. Ab.as I. Parvin b.gum Anil Pratap Singh R J Anandhi Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology (Deemed to be University) Chennai Tamil Nadu India New Prince Shri Bhavani College Of Engineering And Technology Tamilnadu India College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Applications B.S.Abdur Rahman Crescent Institute of Science and Technology Vandalur Tamil Nadu Department of Computer Science & Engineering IES University Bhopal MP India Department of Information Science & Engineering New Horizon College of Engineering Bengaluru

b.NN ensemb.e can significantly improve the generalization ab.lity of knowledge system b. training multiple b.NNs and synthesizing their conclusions. It not only helps scientists to study machinery knowledge and neural computing in depth, b.t also helps ordinary engineers and technicians to use b.NN technology to solve real-world prob.ems. Ensemb.e knowledge has b.come one of the hot spots in the territory of machinery knowledge in recent years, and selective integration method has b.come an important direction of ensemb.e knowledge b.cause of its advantages in adaptab.lity, generalization and comb.nation. In this paper, the transcription of multi-tone piano is studied b.sed on b.NN. The corresponding study methods are used in the research. Through the estab.ishment of data graph and algorithm formula, the corresponding study is carried out. From the research, it can b. found that the piano transcription efficiency b.sed on b.NN is very high, up to ab.ut 90.43%. In the future, people may pay more Focus to the piano study of b.NN.

关键词：

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：