检索结果-内蒙古大学图书馆

A Two-Step Approach for Multi-topology Identification and Parameter Estimation of Power Distribution Networks

CSEE Journal of Power and Energy systems 2024年第6期10卷 2446-2456页

作者： Li Ma Lei Wu Nian Liu Wei Pei Institute of Electrical Engineering and Key Laboratory of Long-Duration and Large-Scale Energy StorageChinese Academy of SciencesBeijing 100190China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power UniversityBeijing 102206China

To improve observability in power distribution networks(PDN),a two-step framework of multi-topology identification and parameter estimation is proposed in this ***,in the first step,a mixed-integer linear program(MILP)model-based split method is proposed to recognize mixed topologies in a multi-record dataset without a prerequisite on the number of topology categories and values of nodal voltage phase *** the second step,line parameters and nodal voltage phase angles are estimated using the Newton-Raphson method based on nodal measurements of real and reactive power injections,as well as voltage ***,a modified estimation model is proposed to apply to the multitopology ***,case studies on an IEEE 33-bus system illustrate the effectiveness of the proposed models in identifying the PDN’s topologies,as well as estimating line parameters and voltage phase angles.

关键词： MILP Newton-Raphson method parameter estimation power distribution system topology identification

来源：评论

学校读者我要写书评

暂无评论

Prediction Analysis of Greeting Gestures based on Data Augmentation and LSTM 23

Prediction Analysis of Greeting Gestures based on Data Augme...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Wibow, Angga Wahyu Sato-Shimokawara, Eri Kurnianingsih Graduate School of System Design Tokyo Metropolitan University Department of Computer Science Tokyo Japan Politeknik Negeri Semarang Department of Electrical Engineering Semarang Indonesia

ISBN: (纸本)9798331528041

The field of Human Activity Recognition (HAR) is growing significantly in several areas but little research focuses on cultural behavior. How machine learning can explain human activity as a promotional tool in understanding cultural differences in a region is very challenging. Studies using Recurrent Neural Network (RNN), especially Long Short-Term Memory (LSTM), require large data when used to research human activity recognition. Using small data is a challenge when using LSTM. This study aims to determine which data augmentation is most appropriate when used using LSTM to predict Japanese greeting gestures, namely eshaku, keirei, saikeirei, waving hands, and Indonesian greeting gestures, namely the movement of bringing both hands together in front of the chest with a slight bow of the head. This study proposes to compare several data augmentations, namely jittering, scaling, permutation, cropping, reverse, time shifting, frequency domain, and synthetic data generation. We evaluate model performance using the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2) metrics. The experimental results show that Time Shifting has the best MSE, RMSE, and MAE values compared to others and Frequency Domain has the best R2 values compared to others. This study concludes that Time Shifting and Frequency Domain are the best data augmentation methods when using LSTM in predicting greeting gestures using small data. These findings provide valuable insights into the effectiveness of various data augmentation methods in motion prediction tasks with limited data sets, as well as the importance of selecting appropriate data augmentation methods in human motion analysis. Future work could use data from two or more people using model explanations generated by machine learning and developing a new method for cultural behavior. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Harnessing CNNs for Accurate Skin Disease Identification 3

Harnessing CNNs for Accurate Skin Disease Identification

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Dhoundiyal, Parveen Sharma, Vikrant Vats, Satvik Singh, Karan Graphic Era Hill University Department of Computer Science & Engineering Uttarakhand Dehradun India School of Computer and System Sciences Jnu New Delhi New Delhi India

ISBN: (纸本)9798350342338

Skin disorders are common and can be brought on by several things, including viruses, bacteria, allergies, or fungi. The speed and precision of detecting skin diseases have increased because of developments in laser and photonics-based medical technologies. The expense of such a diagnostic is still considerable, though, which restricts accessibility. An automated early-stage dermatological screening system has been developed using image processing techniques to solve this issue. Effective skin disease classification requires the extraction of key information from pictures, and many detection algorithms rely on computer vision. DenseNet169 and NASNetMobile are some of the methods that were employed in the study. Graphs were used to display the results as the researchers compared the algorithms' performance based on training accuracy and confusion matrix. Keywords: Skin Disease, Medical Diagnosis, Deep Learning, Transfer Learning, CNNs © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Hierarchical AI Architecture for Meta-Described Local Dynamic Maps in Autonomous Driving 16

Distributed Hierarchical AI Architecture for Meta-Described ...

引用

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Miyata, Hiroshi Arimoto, Kazutami Saitoh, Masatoshi Hayami, Atsushi Mizuno, Hisayoshi Shimazu, Yukihiko Yokogawa, Tomoyuki Technoaccel Networks Corp. Tokyo Office Tokyo Japan Okayama Prefectural University Computer Science and System Engineering Sousya Okayama Japan Toyota Motor Corporation Information and Communication Planning Division Tokyo Japan Okayama Prefectural University Computer Science and System Engneering Sousya Okayama Japan

ISBN: (纸本)9798350377903

In autonomous driving, sharing information among vehicles to enhance safety is an important issue. However, it is not yet clear how each terminal car processes information and how to share it with other cars. Therefore, this paper proposes a distributed hierarchical AI architecture in which each edge distributed terminal of a car or intermediate cloud is equipped with a processing AI that generates metadata and builds them hierarchically. The hierarchical AI consists of multiple AI information processing layers and generates metadata links by concatenating the output of each layer. The hierarchical and spatially distributed nature of information processing allows for a compact digital twin that enables efficient spatiotemporal processing by receiving only the data necessary for that terminal and facilitating the processing necessary for that terminal. As a concrete example, we created software for vehicle front camera image processing for local dynamic maps for autonomous driving, and we evaluated the intensity and processing load of the proposed architecture. In the future, we will continue to study the software and hardware necessary to increase the hierarchy and speed of AI processing. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Super-resolution reconstruction of single image for latent features

引用

Computational Visual Media 2024年第6期10卷 1219-1239页

作者： Xin Wang Jing-Ke Yan Jing-Ye Cai Jian-Hua Deng Qin Qin Yao Cheng School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu 610000 China State Key Laboratory of Rail Transit Vehicle System Southwest Jiaotong UniversityChengdu 610000China School of Marine Engineering Guilin University of Electronic TechnologyGuilin 541000China School of Computer and Information Security Guilin University of Electronic TechnologyGuilin 541000China

Single-image super-resolution(SISR)typically focuses on restoring various degraded low-resolution(LR)images to a single high-resolution(HR)***,during SISR tasks,it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture *** challenge can lead to issues such as model collapse,lack of rich details and texture features in the reconstructed HR images,and excessive time consumption for model *** address these problems,this paper proposes a Latent Feature-oriented Diffusion Probability Model(LDDPM).First,we designed a conditional encoder capable of effectively encoding LR images,reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed *** then employed a normalized flow and multimodal adversarial training,learning from complex multimodal distributions,to model the denoising *** so boosts the generative modeling capabilities within a minimal number of sampling *** comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics,providing a fresh perspective for tackling SISR tasks.

关键词： image superresolution reconstruction denoising diffusion probabilistic model normalized flow adversarial neural network variational auto-encoder

来源：评论

学校读者我要写书评

暂无评论

An Improved Method for Approximating the Infinite-Horizon Value Function of the Discrete-Time Switched LQR Problem

引用

Journal of systems Science & Complexity 2024年第1期37卷 22-39页

作者： HOU Tan LI Yuanlong LIN Zongli Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240China Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904-4743USA

This paper considers the problem of approximating the infinite-horizon value function of the discrete-time switched LQR *** particular,the authors propose a new value iteration method to generate a sequence of monotonically decreasing functions that converges exponentially to the value *** method facilitates us to use coarse approximations resulting from faster but less accurate algorithms for further value iteration,and thus,the proposed approach is capable of achieving a better approximation for a given computation time compared with the existing *** numerical examples are presented in this paper to illustrate the effectiveness of the proposed method.

关键词： Optimal control switched linear systems switched LQR problem.

来源：评论

学校读者我要写书评

暂无评论

INVESTIGATING DIFFERENT SIMILARITY METRICS USED IN VARIOUS RECOMMENDER systemS TYPES: SCENARIO CASES 7

INVESTIGATING DIFFERENT SIMILARITY METRICS USED IN VARIOUS R...

引用

7th International Conference on Smart City Applications, SCA 2022

作者： Stitini, Oumaima Kaloun, Oumaima Bencharef, Omar Computer and System Engineering Laboratory Cadi Ayyad University Marrakech40000 Morocco

A recommendation system represents a very efficient way to propose solutions adapted to customers needs. It allows users to discover interesting items from a large amount of data according to their preferences. To do this, it uses a similarity metric, which determines how similar two users or products are. In the case of recommender systems, similarity computation is a practical step. The calculation of similarity may be used for both items and users. Following the similarity calculation, a user or item with a comparable computation value can be recommended together with the goods to a user with similar preferences. The user's requirements influence the choice of similarity metric. This paper explores various similarity measurement methods employed in recommender systems. We compare correlation and distance techniques to determine the capabilities of different similitude calculation algorithms and synthesize which similarity measure is adapted for which type of recommendation. © 2022 International Society for Photogrammetry and Remote Sensing. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Review of Animal Remote Managing and Monitoring system 5

Review of Animal Remote Managing and Monitoring System

引用

5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022

作者： Ojo, John Io Tu, Chunling Owolawi, Pius A Du, Shengzhi Plessis, Deon Du Department of Computer System Engineering Tshwane University of Technology Pretoria South Africa

ISBN: (纸本)9781450398749

Livestock is an integral part of everyday life contributing to the social, cultural, and economic sectors. Livestock farming faces challenges in animal remote management and monitoring, due to cost constraints and product quality requirements. The latest development of smart techniques, especially the Internet of Things (IoT) and cloud devices/services provide significant potential for efficient and secure farm management. This paper presents a review of smart farm management and monitoring systems for livestock based on IoT techniques, including the monitoring of animal behavior, weather condition, environment, and more. The review provides a comprehensive understanding of the sensing techniques, data analysis, communication, hardware, and software used in existing smart livestock solutions. © 2022 ACM.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

An optimized Parkinson’s disorder identification through evolutionary fast learning network

引用

International Journal of Intelligent Computing and Cybernetics 2022年第3期15卷 383-400页

作者： Bouslah Ayoub Taleb Nora LRI Laboratory Computer Science DepartmentUniversity of BadjiMokhtar AnnabaAnnabaAlgeria Complex System Engineering Laboratory Computer Science DepartmentUniversity of Badji Mokhtar AnnabaAnnabaAlgeria

Purpose-Parkinson’s disease(PD)is a well-known complex neurodegenerative ***,its identification is based on motor disorders,while the computer estimation of its main symptoms with computational machine learning(ML)has a high exposure which is supported by researches ***,ML approaches required first to refine their parameters and then to work with the best model *** process often requires an expert user to oversee the performance of the ***,an attention is required towards new approaches for better forecasting ***/methodology/approach-To provide an available identification model for Parkinson disease as an auxiliary function for clinicians,the authors suggest a new evolutionary classification *** core of the prediction model is a fast learning network(FLN)optimized by a genetic algorithm(GA).To get a better subset of features and parameters,a new coding architecture is introduced to improve GA for obtaining an optimal FLN ***-The proposed model is intensively evaluated through a series of experiments based on Speech and HandPD benchmark *** very popular wrappers induction models such as support vector machine(SVM),K-nearest neighbors(KNN)have been tested in the same *** results support that the proposed model can achieve the best performances in terms of accuracy and ***/value-A novel efficient PD detectionmodel is proposed,which is called *** A-W-FLN utilizes FLN as the base classifier;in order to take its higher generalization ability,and identification capability is alsoembedded to discover themost suitable featuremodel in the detection ***,the proposedmethod automatically optimizes the FLN’s architecture to a smaller number of hidden nodes and solid connecting *** helps the network to train on complex PD datasets with non-linear features and yields superior result.

关键词： Parkinson’s disease(PD) Fast learning network(FLN) Genetic algorithm(GA) Speech and handwriting patterns PD identification system

来源：评论

学校读者我要写书评

暂无评论

Fractional Order Differential Evolution

引用

IEEE Transactions on Evolutionary Computation 2024年第3期29卷 1-1页

作者： Wang, Kaiyu Gao, Shangce Zhou, MengChu Zhan, Zhi-Hui Cheng, Jiujun Faculty of Engineering University of Toyama Toyama-shi Japan Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA College of Artificial Intelligence Nankai University Tianjin China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

Differential evolution (DE) is a widely recognized method to solve complex optimization problems as shown by many researchers. Yet, non-adaptive versions of DE suffer from insufficient exploration ability and uses no historical information for its performance enhancement. This work proposes Fractional Order Differential Evolution (FODE) to enhance DE performance from two aspects. Firstly, a bi-strategy co-deployment framework is proposed. The population-based and parameter-based strategies are combined to leverage their respective advantages. Secondly, the fractional order calculus is first applied to the differential vector to enhance DE’s exploration ability by using the historical information of populations, and ensures the diversity of population in an evolutionary process. We use the 2017 IEEE Congress on Evolutionary Computation (CEC) test functions, and CEC2011 real-world problems to evaluate FODE’s performance. Its sensitivity to parameter changes is discussed and an ablation study of multi-strategies is systematically performed. Furthermore, the variations of exploration and exploitation in FODE are visualized and analyzed. Experimental results show that FODE is superior to other state-of-the-art DE variants, the winners of CEC competitions, other fractional order calculus-based algorithms, and some powerful variants of classic algorithms. IEEE

关键词： Particle swarm optimization (PSO)

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：