检索结果-内蒙古大学图书馆

Convolutional Neural Networks Aided Reinforcement Learning for Accelerated Optimization of Antenna Topology

Applied Computational Electromagnetics Society Journal 2025年第1期40卷 35-41页

作者： Dou, Jiangling Gong, Hao Wei, Shuaibing Chen, Haokang Chen, Yujie Shen, Tao Song, Jian Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming650500 China School of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China College of Mechanical and Electrical Engineering Yunnan Electromechanical Vocational and Technical College Kunming650500 China

A machine learning (ML) framework is proposed to achieve the automatic and rapid optimization of antenna topologies. A convolutional neural network (CNN) is utilized as a surrogate model (SM) and is combined with reinforcement learning (RL) algorithms. Specifically, the RL agent interacts with simulation software to learn. Data accumulated from electromagnetic (EM) simulations are used to train the SM. The CNN-based SM predicts antenna performance based on the topology of the antenna. Subsequently, the SM replaces EM simulations within the RL training environment. The RL agent interacts with the CNN-based SM to search for the optimal topology. This approach significantly reduces dependence on time-consuming EM simulations. To validate the effectiveness of the optimization method, a center-fed microstrip patch antenna is optimized. Simulation results demonstrate that, compared to other optimization methods, impedance bandwidth is improved, while the number of simulation samples and optimization time are significantly reduced. © ACES.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A machine learning approach for skin lesion classification on iOS: implementing and optimizing a convolutional transfer learning model with Create ML

引用

International Journal of computers and applications 2024年第8期46卷 666-685页

作者： Benedek Szabo, Aron Katona, Jozsef Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Instrumentation and Automation Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Department of Informatics GAMF Faculty of Engineering and Computer Science Kecskemét Hungary

The integration of machine learning (ML) into mobile applications presents unique challenges, particularly in resource-constrained environments such as iOS devices. Skin lesion classification is a critical task in dermatology, where accurate and efficient diagnostic tools can significantly aid in early detection of malignant lesions. This study aims to implement a machine learning-based iOS mobile application and develop a binary classification model for skin lesion images to determine whether a lesion is malignant. The research utilized Create ML to develop a convolutional neural network optimized for iOS, employing a transfer learning approach. A logistic regression model was cascaded with the convolutional neural network N to enhance classification accuracy. The model's performance was assessed through various validation metrics, ensuring its robustness and efficiency within the constraints of mobile hardware. A curated dataset from the International Skin Imaging Collaboration archive was used for training and testing. The model achieved an accuracy of 92%, a precision of 90%, a recall of 93%, and an F1-score of 91% in classifying skin lesions. These metrics validate the model's efficacy in identifying malignant lesions. Data curation involved collecting, labeling, and preparing a dataset from publicly available sources, ensuring the inclusion of diagnostically relevant features. The final model was integrated into an iOS application using Core ML and Vision frameworks. The developed application demonstrates reliable performance in classifying skin lesions with high accuracy on iOS devices. The inclusion of comprehensive performance metrics justifies the efficacy of the proposed approach. Future work will explore enhancements in model architecture and object detection capabilities to further improve diagnostic precision and application usability. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Surface flashover in 50 years:*** modification,structureoptimisation,and characteristics enhancement

引用

High Voltage 2025年第2期10卷 243-278页

作者： Zhen Li Ji Liu Yoshimichi Ohki George Chen Shengtao Li Key Laboratory of Engineering Dielectrics and Its Application Ministry of EducationHarbin University of Science and TechnologyHarbinHeilongjiangChina State Key Laboratory of Electrical Insulation and Power Equipment Xi'an Jiaotong UniversityXi'anShaanxiChina Research Institute for Materials Science and Technology Waseda UniversityShinjukuJapan School of Electronics and Computer Science University of SouthamptonSouthamptonUK

Surface flashover is a gas-solid interface insulation failure that significantly jeopardises the secure operation of advanced electronic,electrical,and spacecraft *** the widespread application of numerous material modification and structure optimisation technologies aimed at enhancing surface flashover performance,the influence mechanisms of the present technologies have yet to be systematically discussed and *** review aims to introduce various material modification technologies while demonstrating their influence mechanisms on flashover performances by establishing relationships among‘microscopic structure-mesoscopic charge transport-macroscopic insulation failure’.Moreover,it elucidates the effects of chemical structure on surface trap parameters and surface charge transport concerning flashover *** review categorises and presents structure optimisation technologies that govern electric field *** identified technologies highlight that achieving a uniform tangential electric field and reducing the normal electric field can effectively enhance flashover ***,this review proposes recommendations encompassing mathematical,chemical,evaluation,and manufacturing *** systematic summary of current technologies,their influence mechanisms,and associated advantages and disadvantages in improving surface insulation performance is anticipated to be a pivotal component in flashover and future dielectric theory.

关键词： material modification structure optimization surface flashover structure optimisation technologies chemical structure charge transport insulation failure

来源：评论

学校读者我要写书评

暂无评论

Reliable and Stable Routing in VANET Using Multi-Objective Function Aided K-Means Clustering with Heuristic Algorithm 1

Reliable and Stable Routing in VANET Using Multi-Objective F...

引用

1st International Conference on Trends in engineering Systems and Technologies, ICTEST 2024

作者： Das, Nabanita Barooah, Maushumi Das, Anupam Assam Engineering College Jalukbari Department of Computer Application Assam Guwahati781013 India The Assam Royal Global University Betkuchi Department of Computer Science and Engineering Guwahati781035 India

ISBN: (纸本)9798350307795

The expansion of Vehicular Ad-hoc Networks (VANET) has brought a heightened focus on service delivery within the realm of the smart transit systems. Nevertheless, the mobility attributes inherent to vehicular networks often result in frequent route disruptions, particularly when transmitting data. This circumstance holds true in both advanced and emerging nations, where substantial time is wasted due to congested traffic conditions. These consequences are substantial, encompassing heightened stress levels for drivers, reduced efficiency for diverse personal and commercial vehicles, and escalated emissions of harmful gases, especially those that contribute to air pollution, affecting the well-being of residents in densely populated regions. Clustering stands as a formidable approach for establishing a stable topological arrangement. Therefore, an efficient reliable routing scheme is developed in VANET with the help of a clustering algorithm. The node clustering is initially performed with the help of the K-means Clustering algorithm (KMC) in VANET. An Advanced Pelican Optimization Algorithm (APOA) is utilized for choosing a shorter and more stable route between all available routes to make efficient routing in VANET. The multi-objective functions like delay, hop count, energy, and the ratio of packet delivery are considered for the efficient routing in VANET to make energy-efficient transmission. The effectiveness of the proposed KMC-based optimal routing in VANET is validated with the conventional routing schemes in accordance with some of the metrics to determine efficacy. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Dynamics of Online Culinary Convenience: A Systematic Exploration 2

Unveiling the Dynamics of Online Culinary Convenience: A Sys...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Bhatt, Chandradeep Bisht, Anurag Sharma, Sanjay Gupta, Shefali Singh, Teekam Graphic Era Hill University Cse Department Dehradun India Graphic Era Hill University Computer Science and Engineering Dehradun India Sgrr Univeristy Computer Application Department Dehradun India Chitkara University Institute of Engineering and Tech Chitkara University Punjab India Graphic Era Deemed to Be University Computer Science and Engineering Dehradun India Sgrrits Computer Application Department Dehradun India

ISBN: (纸本)9798350306415

The industry for online food delivery has grown quickly, changing how customers access and use food services. Finding foods that are suitable for their diets and leanings among the dozen selections offered to customers and users is frequently difficult. For this study, existing research on customer behavior in online food ordering systems is reviewed in order to identify any gaps where intelligent advocacy systems can be very helpful. The proposed work focuses on utilizing sophisticated machine learning algorithms and approaches to create personalized food advice that takes into consideration user preferences, previous order history, and contextual data. The findings of the empirical study offer priceless insights into the efficiency of intelligent suggestion systems and their influence on user engagement. The results provide guidance for future advancement in the sector and help to understand consumer preferences as well as the difficulties that online meal ordering platforms have had to overcome. My suggested system includes an online food ordering option that makes it simple for clients. My system makes it simple to purchase food online from restaurants and use the mess service. This study looks into how the online food ordering landscape is changing and aims to offer opinions on how intelligent advising systems could improve user experience. The ultimate goal of this is to help companies devise plans to enhance customer service and spur expansion in the online food ordering sector. © 2024 IEEE.

关键词： DOM E-Commerce JWT machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Predictability of Random Vector Functional Link Networks in Forecasting Quality of Service (QoS) Parameters of IoT-Based Web Services Data

引用

International Journal of Sensors, Wireless Communications and Control 2023年第2期13卷 57-70页

作者： Lenka, Stitapragyan Pradhan, Sateesh Kumar Nayak, Samaleswari Prasad Nayak, Sarat Chandra Department of Computer Science Application Utkal University Odisha Bhubaneswar India Department of Computer Science and Engineering Silicon Institute of Technology Odisha Bhubaneswar India Department of Computer Science Yonsei University Seoul South Korea

Background: QoS parameters are volatile in nature and possess high nonlinearity, thus making the IoT-based service and recommendation process challenging. Methods: An efficient and accurate forecasting model is lacking in this area and needs to be explored. Though an artificial neural network is a prominent option for capturing such nonlinearities, its effi-ciency is limited by the structural complexity and iterative learning method. The random vector functional link network (RVFLN) significantly reduces the time complexity by randomly assigning input weights and biases without further modification. Only output layer weights are calculated iteratively by gradient methods or non-iteratively by least square methods. It is an efficient algorithm with low time complexity and can handle complex domain problems without compromising accuracy. Motivat-ed by these characteristics, this article develops an RVFLN-based model for forecasting QoS parameter sequences. Results: Two real-world IoT-enabled web service dataset series are used in developing and evaluating the effectiveness of RVFLN-based forecasts in terms of three performance metrics. Conclusion: Experimental results, comparative studies, and statistical tests are conducted to establish the superiority of the proposed approach over four other similar forecasting techniques. © 2023 Bentham science Publishers.

关键词： artificial neural network IoT QoS parameter forecasting random vector functional link network time series forecasting web service search

来源：评论

学校读者我要写书评

暂无评论

Using Neural Network-Based Time Series Analysis in Wireless Sensor Networks 2

Using Neural Network-Based Time Series Analysis in Wireless ...

引用

2nd International Conference on Artificial Intelligence and Machine Learning applications, AIMLA 2024

作者： Goyal, Manish Kumar Patil, Nagaraj Bhagat, Akash Kumar Vivekananda Global University Department of Computer Science & Application Jaipur India School of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India ARKA JAIN University Department of Computer Science & IT Jharkhand Jamshedpur India

ISBN: (纸本)9798350349221

Neural community-primarily based time series analysis (NNTSA) is an effective technique for research records collected from wireless sensor networks (WSNs). NNTSA uses models stimulated by means of biological neural networks to capture complicated time-various sensor statistics. It requires minimum training of the enter facts and offers a high degree of modelling accuracy. This method has turned out to be increasingly famous for WSN facts evaluation when you consider that it is miles appropriate for streaming statistics and seizing complicated patterns that might not be effortlessly detected with the aid of other techniques. NNTSA fashions are commonly carried out the use of supervised gaining knowledge of processes, together with lower back-propagation, wherein education styles are fed to a neural network at the same time as its parameters are adjusted the use of a fixed of desired output values, together with an average temperature over some time. After the NNTSA c section is complete, new patterns can be evaluated with the trained model to analyze their temporal conduct. NNTSA techniques have been applied in diverse areas, inclusive of fitness monitoring, site visitors management, and weather tracking, with suitable result. © 2024 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Empirical Analysis of Digital Currency Herding and Contagion Effect Using Deep Learning Approaches 3

Empirical Analysis of Digital Currency Herding and Contagion...

引用

3rd Odisha International Conference on Electrical Power engineering, Communication and Computing Technology, ODICON 2024

作者： Tripathy, Nrusingha Hota, Sarbeswara Mishra, Debahuti Dash, Biswajit Nayak, Subrat Kumar Tripathy, Jogeswar Deemed to Be University Department of Computer Science and Engineering Siksha 'O' Anusandhan Odisha Bhubaneswar India Deemed to Be University Department of Computer Application Siksha 'O' Anusandhan Odisha Bhubaneswar India Raajdhani Engineering College Department of Computer Science and Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350354379

In recent years, the use of virtual or cryptocurrency-based money has grown. Blockchain, a digital accounting system, is the foundation of cryptocurrency. The markets for cryptocurrencies are eminent for their high volatility and quick price swings. People tend to be more likely to follow the lead of others at times of notable price fluctuations out of a concern of losing money or missing out on possible gains. In this work, we taking the Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), the hybrid combinations of LSTM-Convolutional Neural Network (CNN), LSTM-Gated Recurrent Unit (GRU) and for Facebook Prophet (Fb-Prophet) model smoothing, triple exponential smoothing (Holt-Winters Method) is utilized, which adds seasonality into the forecasting model. In this work bitcoin exchanges providing real-time information casing the period from January 2012 to July 2020 is utilized. The price of cryptocurrencies fluctuates significantly throughout a range of time periods, from short-term intraday swings to long-term patterns that last for weeks or months. By altering the network layer design and the duration of the input sequences, LSTM-GRU models configured to adapt to various time horizons. In contrast to previous iterations, the hybrid LSTM-GRU performs well. When compared to other models, the model's Mean Absolute Error (MAE) score of 0.056 and Root Mean Square Error (RMSE) score of 0.073 are quite acceptable. Forecasting the value of cryptocurrencies will help traders and investors in making better-informed choices when purchasing, disposing of, and keeping assets. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework for Image Caption Generation Using Deep Reinforcement Learning 15

A Unified Framework for Image Caption Generation Using Deep ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shree, Ritu Narmadha, T. Joseph, Vishakha Vivekananda Global University Department of Computer Science & Application Jaipur India School of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Arka Jain University Department of Management Jharkhand Jamshedpur India

ISBN: (纸本)9798350370249

This paper introduces a unified framework for picture caption generation with the use of deep reinforcement mastering (RL) that combines convolution neural networks (CNNs) with RL. The paper first introduces a country representation as a remark for RL by means of combining CNN-primarily based photo representation and natural language processing (NLP) natural language representation. Then, the paper describes an RL-based reinforcement mastering (RL-RL) set of rules which uses the statement to generate captions. Eventually, the paper shows the experimental consequences of the proposed RL-RL set of rules on real-world datasets and shows that the RL-RL set of rules outperforms the present RL-NLP and CNN-RL algorithms. The paper additionally demonstrates the very best overall performance on the benchmark dataset COCO with a BLEU score of 0.645 and a METEOR score of 0.348. The proposed framework affords a sensible technique to generate interesting and affordable captions for photographs. © 2024 IEEE.

关键词： Benchmark Consequences Convolution Photographs Reinforcement Representation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Benefits of Interactive Communication Media Algorithms for Networking applications 3

Exploring the Benefits of Interactive Communication Media Al...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Ahmed, Zahid Beemkumar, N. Ghosh, Debanjan Vivekananda Global University Department of Computer Science & Application Jaipur India School of Engineering and Technology Department of Mechanical Engineering Karnataka Bangalore India Arka Jain University Department of Computer Science & It Jharkhand Jamshedpur India

ISBN: (纸本)9798350381931

Interactive communication media algorithms are useful tools for creating efficient and effective networking applications. Such algorithms enable the application to accurately predict user behaviour and preferences, use natural language processing to automate conversations, and integrate with other systems. This paper investigates the benefits of using interactive communication media algorithms for developing networking applications, including improved user experience, scalability, and quicker response times. Additionally, this paper will address potential limitations, such as the need for significant data collection and availability of relevant computing resources. Finally, this paper will conclude with a discussion of the potential implications of further investigations into interactive communication media algorithms for networking applications. © 2024 IEEE.

关键词： Behavioral research

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：