检索结果-内蒙古大学图书馆

Balancing Exploration–Exploitation of Multi-verse Optimizer for Parameter Extraction on Photovoltaic Models

Journal of Bionic engineering 2024年第2期21卷 1022-1054页

作者： Yan Han Weibin Chen Ali Asghar Heidari Huiling Chen Xin Zhang College of Computer Science and Artificial Intelligence Wenzhou UniversityWenzhou325035China School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehranIran School of Biomedical Engineering National Engineering Research Center of Ophthalmology and OptometryEye HospitalWenzhou Medical UniversityWenzhou325027China Key Lab of Biohealth Materials and Chemistry of Wenzhou Wenzhou UniversityWenzhouChina Key Laboratory of Intelligent Informatics for Safety&Emergency of Zhejiang Province Wenzhou UniversityWenzhouChina

Extracting photovoltaic(PV)model parameters based on the measured voltage and current information is crucial in the simulation and management of PV *** accurately and reliably extract the unknown parameters of different PV models,this paper proposes an improved multi-verse optimizer that integrates an iterative chaos map and the Nelder–Mead simplex method,*** experiments verified that the proposed INMVO fueled by both mechanisms has more affluent populations and a more reasonable balance between exploration and ***,to verify the feasibility and competitiveness of the proposal,this paper employed INMVO to extract the unknown parameters on single-diode,double-diode,three-diode,and PV module four well-known PV models,and the high-performance techniques are selected for *** addition,the Wilcoxon signed-rank and Friedman tests were employed to test the experimental results *** evaluation metrics,such as root means square error,relative error,absolute error,and statistical test,demonstrate that the proposed INMVO works effectively and accurately to extract the unknown parameters on different PV models compared to other *** addition,the capability of INMVO to stably and accurately extract unknown parameters was also verified on three commercial PV modules under different irradiance and *** conclusion,the proposal in this paper can be implemented as an advanced and reliable tool for extracting the unknown parameters of different PV *** that the source code of INMVO is available at https://***/woniuzuioupao/INMVO.

关键词： Photovoltaic models Multi-verse optimizer Nelder-Mead simplex Iterative chaos map

来源：评论

学校读者我要写书评

暂无评论

VITMST++: Efficient Hyperspectral Reconstruction Through Vision Transformer-Based Spatial Compression

IEEE Open Journal of Signal Processing

引用

IEEE Open Journal of Signal Processing 2025年 6卷 398-404页

作者： Silveira, Ana C. Caznok do Carmo, Diedre S. Ueda, Lucas H. Fantinato, Denis G. Costa, Paula D. P. Rittner, Leticia Universidade Estadual de Campinas Department of Computer Engineering and Automation School of Electrical and Computer Engineering Campinas13083-852 Brazil Universidade Estadual de Campinas CPQD Recod.AI Institute of Computing Campinas13083-852 Brazil

Hyperspectralchannel reconstruction transforms a subsampled multispectral image into hyperspectral imaging, providing higher spectral resolution without a dedicated acquisition hardware and camera. Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (MST++) is a state-of-the-art channel reconstruction technique, but it faces memory limitations for high spatial-resolution images. In this context, we introduced VITMST++, a novel architecture incorporating Vision Transformer embeddings for spatial compression, multi-resolution image context, and a custom channel-weighted loss. Developed for the ICASSP 2024 HyperSkin Challenge, VITMST++ outperforms the state-of-the-art MST++ in both performance and computational efficiency in channel reconstruction. In this work, we perform a deeper analysis on the main aspects of VITMST++ efficiency, quantitative performance, and generalization to other datasets. Results show that VITMST++ achieves similar values of SAM and SSIM hyperspectral reconstruction metrics when compared to state-of-the-art methods, while consuming up to three fold less memory and needing up to 10 times fewer multiply-add operations. © 2020 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

The combination of the NDBI and machine learning algorithms to classification the development of urban areas in Surabaya uses Landsat 8 Imagery. 25

The combination of the NDBI and machine learning algorithms ...

引用

25th International Electronics Symposium, IES 2023

作者： Wibowo, Prasetyo Fariza, Arna Saputra, Ferry Astika Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350314731

Development is a transformation that occurs in order to better people's lives. In this instance, efforts are required to monitor development progress swiftly and efficiently so that outcomes that support the government's new policies are obtained. With a population of 2,848,583 people, Surabaya is the largest metropolitan city in Eastern Indonesia. An increase in population can impact Surabaya's development and generate potential issues with urban planning development. Through these issues, remote sensing technology can efficiently and swiftly detect advances in Surabaya. This research study employs Landsat 8 image data with a combination of Normalized Build-Up Index (NDBI) as pre-processed pixels to segment into urban areas. It employs machine learning to classify urban areas to separate class types in depth. The findings show that the method successfully classified subclasses in residential and industrial areas. Random Forest (RF) outputs have an overall accuracy of 85%, whereas Decision Tree (DT) outputs have an overall accuracy of 84%. This study's findings also indicate the possibility for practical applicability to various case studies, such as conducting detections in forests, plantations, mining, and coastal environments. © 2023 IEEE.

关键词： Landsat

来源：评论

学校读者我要写书评

暂无评论

A novel online reinforcement learning-based linear quadratic regulator for three-level neutral-point clamped DC/AC inverter

Energy Conversion and Economics

引用

Energy Conversion and Economics 2024年第5期5卷 281-292页

作者： Qie, Tianhao Zhang, Xinan Xiang, Chaoqun Iu, Herbert Ho Ching Fernando, Tyrone Department of Electrical Electronic and Computer Engineering The University of Western Australia Perth Australia School of Traffic and Transportation Engineering Central South University Changsha China

This article proposes a novel online reinforcement learning-based linear quadratic regulator for the three-level neutral-point clamped DC/AC voltage source inverter. The proposed controller employs online updated fixed-weight recurrent neural network (NN) and policy iteration to dynamically adjust the optimal control gains based on real-time measurements without any knowledge of the system model or offline pre-training. Moreover, it produces a constant switching frequency with low current harmonics. Compared to the existing control methods, it provides superior control performance, guaranteed control stability, and simplified NN design. Experimental results are presented to verify the effectiveness of the proposed control method. © 2024 The Author(s). Energy Conversion and Economics published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology and the State Grid Economic & Technological Research Institute Co., Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Labor Exploitation Detections for Taiwan Distant Water Fishing Industry

引用

SN computer Science 2024年第1期5卷 46页

作者： Karthikeyan, P. Hsiung, Pao-Ann School of Computer Science and Engineering RV University Bengaluru India Department of Computer Science and Information Engineering National Chung Cheng University Chiayi 62102 Taiwan

Taiwan plays a significant role in global seafood supply chains, accounting for approximately 10% of global tuna catches. The country is a substantial producer of tuna, shrimp, and squid, and its seafood industry is worth an estimated $1.3 billion annually. The Taiwan Distant Water Fishing (DWF) industry faces several challenges, including concerns about labor practices and illegal fishing. However, the government is working to address these issues and improve the industry’s sustainability. This research addresses labor exploitation, specifically within Taiwan’s DWF industry. The proposed research introduces a Mobile face verification system (MFVS) to overcome human error in work-hour recording. A multimodal labor exploitation detection system is also developed, utilizing Retrained-You Only Look Once-v7 and the Global Fishing Watch (GFW) model. The multimodal performance is evaluated using DWF data, demonstrating superior performance to the GFW model. The overall accuracy of the multimodal labor exploitation detection system for the Taiwan DWF Industry is 0.87, while the GFW model achieves an accuracy of 0.83 explicitly. The research facilitates combat labor exploitation and improves industry sustainability. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Distant water fishing Global fishing watch Labor exploitations Multimodal Retrained YOLOv7

来源：评论

学校读者我要写书评

暂无评论

The Future of Work: Robotic Process Automation and its Role in Shaping Tomorrow’s Business Landscape

引用

SN computer Science 2025年第2期6卷 1-19页

作者： Bhardwaj, Vivek Yadav, Shveta Kaur, Navjeet Anand, Darpan School of Computer Science and Engineering Manipal University Jaipur Jaipur India School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

In the new era of automation, Robotic Process Automation (RPA) has emerged as a powerful suite of tools for automating mundane, repetitive, rule-based, and structured tasks using software bots without disrupting existing infrastructure. Due to its significant potential, RPA has garnered considerable attention in the business world, being both easier and cheaper to implement while enhancing efficiency and productivity. This study begins by examining the characteristics of an RPA system and suitability of processes for RPA. This study delves into the role and impact of RPA in modern businesses, highlighting its transformative potential. It also explores the latest trends in RPA research, providing insights into cutting-edge developments and innovative applications. Furthermore, the paper addresses the challenges faced in implementing RPA and offers strategies for overcoming these obstacles, aiming to enhance the efficiency and effectiveness of RPA deployments in various business contexts. Lastly, RPA software bots were developed to quickly and accurately extract data from various invoices. The results show that, when implemented correctly, an RPA system is both easy to deploy and scalable, while maintaining high accuracy. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Artificial intelligence Business processes Intelligent automation Robotic process automation (RPA) Software bots

来源：评论

学校读者我要写书评

暂无评论

Adaptive Incremental Broad Learning System Based on Interval Type-2 Fuzzy Set with Automatic Determination of Hyperparameters

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1713-1725页

作者： Wu, Haijie Lin, Weiwei Chen, Yuehong Shi, Fang Shen, Wangbo Chen, C. L. Philip South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Pengcheng Laboratory Shenzhen518066 China Guangdong Polytechnic Normal University School of Mathematics and Systems Science Guangzhou510665 China South China Agricultural University College of Mathematics and Informatics Guangzhou510642 China South China University of Technology School of Computer Science and Engineering Guangzhou511442 China

The fuzzy broad learning system (FBLS) has received increasing attention due to its ability to quickly train from broad learning systems (BLS) and interpretability with fuzzy inference. However, the randomness of BLS brings instability to the training performance of the model, so the hyperparameters of the model are crucial for its performance. Currently, many FBLS use grid search to determine hyperparameters. However, grid search brings longer search time and the parameters obtained have randomness, which may not necessarily be the optimal hyperparameters. In response to these challenges, this paper proposes a fuzzy broad learning system with automatic determination of hyperparameters (ADHFBLS). We construct a novel FBLS based on the interval type-2 fuzzy set and design an incremental learning algorithm for rules and enhancement nodes to support rapid model expansion. Meanwhile, a heuristic hyperparameter automatic optimization algorithm is designed to overcome the randomness and long optimization time of grid search. Experiments have shown that ADHFBLS has higher accuracy and shorter model tuning time compared to some state-of-the-art models based on FBLS. © 1993-2012 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Prediction of Resource Usage for multi-parametric Deep Learning training and inference 27

Evaluation and Prediction of Resource Usage for multi-parame...

引用

27th Pan-Hellenic Conference on Progress in Computing and informatics with International Participation, PCI 2023

作者： Tsalera, Eleni Stratogiannis, Dimitrios Papadakis, Andreas Voyiatzis, Ioannis Samarakou, Maria Department of Informatics and Computer Engineering University of West Attica Greece Athens Greece

ISBN: (纸本)9798400716263

Deep learning is increasingly used in diverse application fields with results typically surpassing those of traditional machine learning techniques. The portfolio of available neural networks is wide, consisting of the full range in terms of complexity, from compact networks to large ones with multiple layers and parameters. This heterogeneity in the model topology is reflected, not necessarily linearly, on the required computational resources for training and inference. Similarly, the environments where the neural networks are trained and executed are transformed from fully-fledged centralized nodes to distributed architectures with constrained resources. In this view, computational resource requirements can be one of the criteria for resource usage management and neural network selection. In this work we measure the training times for a set of five convolutional neural networks of varying complexity and age (GoogleNet, ShuffleNet, VGGish, YAMNet) under different training configurations, considering the batch size, the number of epochs and the learning rate. These measurements are used to create a CPU-time-training dataset of more than 500 values. This dataset is used to train and evaluate models, based on neural networks, for estimating and predicting training times depending on the models employed and the training parameters. Five regression models have been trained and evaluated in terms of correlation coefficient and root mean square error. In addition, we measure the CPU times needed for inference for a subset of the trained models, which prove to be uncorrelated with the corresponding training times. © 2023 Owner/Author.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Lane detection networks based on deep neural networks and temporal information

引用

Alexandria engineering Journal 2024年 98卷 10-18页

作者： Lin, Huei-Yung Chang, Chun-Ke Tran, Van Luan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei106 Taiwan Department of Electrical Engineering National Chung Cheng University Chiayi621 Taiwan School of Engineering Eastern International University Binh Duong Viet Nam

In the past few years, the lane detection technique has become a key factor for autonomous driving systems and self-driving cars on the road. Among the various vehicle subsystems, the lane detection module is one of the essential parts of the Advanced Driver Assistance System (ADAS). Conventional lane detection approaches use machine vision algorithms to find straight lines in road scene images. However, it is challenging to identify straight or curved lane markings in complex environments. To deal with this problem, this paper presents a lane detection technique based on deep learning. It is combined with a 3D convolutional network, so the temporal information is added to the network architecture. Using the front camera images, the system can immediately detect the lane marking information ahead. Moreover, we propose an approach for improvement by adding the time axis to the network architecture. In addition to using 3D-ResNet50, the temporal convolution and spatial convolution are separated for processing. The accuracy is 91.34% improved after adding time and space split convolution with LeakyReLU. The experiments carried out using real scene images have demonstrated the feasibility of the proposed technique for applications to various complex scenes. © 2024 The Author(s)

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Designing a Digital Repository for the Cultural and Natural Heritage of the Island of Zakynthos 9

Designing a Digital Repository for the Cultural and Natural ...

引用

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Palamas, Stergios Kabassi, Katerina Mylonas, Phivos Ionian University Department of Informatics Corfu Greece Ionian University Department of Environment Zakynthos Greece University of West Attica Department of Informatics and Computer Engineering Athens Greece

ISBN: (纸本)9798350342482

The present study discusses the design of a digital archive for the preservation and dissemination of the Cultural and Natural Heritage of Zakynthos Island. The proposed architecture suggests a Content Management System (CMS) to provide the core functionality, while a web application, interacting with the CMS through a RESTFul API, will provide an alternative front-end targeting mainly on-site end-users using mobile devices. Authors and contributors can submit multimedia content to the repository, which is reviewed and approved by system administrators before publishing, ensuring this way the information quality and *** system will also provide a RESTful API, allowing integration with 3rd party systems and web applications, thereby expanding the repository's reach and capabilities. Content delivery is personalized based on user profiles, location, and preferences, enhancing engagement and usability. By integrating these features, the repository effectively preserves and makes accessible the unique cultural and natural heritage of Zakynthos to both local and global audiences. © 2024 IEEE.

关键词： Augmented Reality Biodiversity Content Management Systems Cultural Heritage Multimedia Digital Repositories Natural Heritage Web Applications

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：