检索结果-内蒙古大学图书馆

A review of federated learning in renewable energy applications:Potential,challenges,and future directions

Energy and AI 2024年第3期17卷 444-457页

作者： Albin Grataloup Stefan Jonas Angela Meyer Bern University of Applied Sciences School of Engineering and Computer ScienceQuellgasse 21Biel2501Switzerland Universitàdella Svizzera italiana Faculty of InformaticsVia la Santa 1Lugano-Viganello6962Switzerland Delft University of Technology Department of Geoscience and Remote SensingStevinweg 1Delft2628The Netherlands

Federated learning has recently emerged as a privacy-preserving distributed machine learning *** learning enables collaborative training of multiple clients and entire fleets without sharing the involved training *** preserving data privacy,federated learning has the potential to overcome the lack of data sharing in the renewable energy sector which is inhibiting innovation,research and *** paper provides an overview of federated learning in renewable energy *** discuss federated learning algorithms and survey their applications and case studies in renewable energy generation and *** also evaluate the potential and the challenges associated with federated learning applied in power and energy ***,we outline promising future research directions in federated learning for applications in renewable energy.

关键词： Federated learning Renewable energy Dis tributed learning Data heterogeneity Privacy Data sharing Wind energy Solar energy Buildings Review

来源：评论

学校读者我要写书评

暂无评论

SynthBA: Reliable Brain Age Estimation Across Multiple MRI Sequences and Resolutions 3

SynthBA: Reliable Brain Age Estimation Across Multiple MRI S...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Puglisi, Lemuel Rondinella, Alessia De Meo, Linda Guarnera, Francesco Battiato, Sebastiano Ravi, Daniele University of Catania Dept. of Math and Computer Science Catania Italy University College London Department of Neuroinflammation London United Kingdom School of Physics Engineering and Cs University of Hertfordshire Hatfield United Kingdom

ISBN: (纸本)9798350378009

Brain age is a critical measure that reflects the biological ageing process of the brain. The gap between brain age and chronological age, referred to as brain PAD (Predicted Age Difference), has been utilized to investigate neurodegenerative conditions. Brain age can be predicted using MRIs and machine learning techniques. However, existing methods are often sensitive to acquisition-related variabilities, such as differences in acquisition protocols, scanners, MRI sequences, and resolutions, significantly limiting their application in highly heterogeneous clinical settings. In this study, we introduce Synthetic Brain Age (SynthBA), a robust deep-learning model designed for predicting brain age. SynthBA utilizes an advanced domain randomization technique, ensuring effective operation across a wide array of acquisition-related variabilities. To assess the effectiveness and robustness of SynthBA, we evaluate its predictive capabilities on internal and external datasets, encompassing various MRI sequences and resolutions, and compare it with state-of-the-art techniques. Additionally, we calculate the brain PAD in a large cohort of subjects with Alzheimer's Disease (AD), demonstrating a significant correlation with AD-related measures of cognitive dysfunction. SynthBA holds the potential to facilitate the broader adoption of brain age prediction in clinical settings, where re-training or fine-tuning is often unfeasible. The SynthBA source code and pre-trained models are publicly available at https://***/LemuelPuglisi/SynthBA. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Traffic Flow Prediction Using LSTM Networks and Big Data Integration for Urban Mobility Optimization 7

Advanced Traffic Flow Prediction Using LSTM Networks and Big...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Rangaiah, Yagateela Pandu Revathi, V. Dutt, Amit Sharma, Smita Al-Rubaye, Taqi Mohammed Khattab Rani, K. Pushpa Institute of Aeronautical Engineering Department of Electronics and Communication Enfineering Dundigal Hyderabad500043 India New Horizon College of Engineering Department of Applied Sciences Bangalore India Lovely Professional University Phagwara India Amity University Amity School of Engineering & Technology Greater Noida India The Islamic University College of Medical Technologies Department of Medical Laboratory Technology Najaf Iraq Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

As urbanization expands at a rate faster than ever before we experience traffic jams which call for sophisticated predictive methods in order to improve the traffic systems. Hypothesized from the heuristic analysis of big traffic data, the present paper outlines a new traffic flow prediction model. The proposed methodology uses big real-time traffic data and historical big data with a machine learning approach that can detect and analyse temporal and spatial dependencies. The model incorporates DL concepts like Long Short-Term Memory (LSTM) networks which capture the sequential dependencies and the complex correlation in traffic flows. Moreover, we also have Feature Selection mechanism to filter the traffic data indicators and thus decrease the data dimensions and increase the prediction accuracy. The integration of big data analytics is helpful in real-time adjustments to changes in traffic and is more accurate. By testing the method on different traffic datasets, the authors show that the proposed method outperforms the traditional models. The findings of this research are novel and significant because this framework can be easily applied and implemented for the traffic flow prediction across various cities, helping in management of traffic and thereby limit traffic congested areas. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Implementation and Comparative Analysis of Static and Dynamic Load Balancing Algorithms in SDN

Implementation and Comparative Analysis of Static and Dynami...

引用

Advancement in Technology (ICONAT), International Conference for

作者： M Shona Rinki Sharma Department of Computer Science and Engineering Ramaiah University of Applied Science Bengaluru India

In the contemporary years, the Internet usage has full-fledged and has made the advance of networking techniques to accomplish the necessities of better bandwidth, throughput and less latency. Software defined networking (SDN) is a technique which organizes the network functions intellectually by using software applications. One of the foremost challenges is load balancing amongst the manifold servers. Most of the applications cannot be performed well without employing load balancers. The existing load balancing mechanisms are basically either of two types: Static and Dynamic. In this paper the performance of static and dynamic load balancing algorithms are scrutinized. The simulation results of few static algorithms and a Dynamic algorithm are exposed in this paper. The relative analysis of the results of Static and Dynamic load balancing algorithms based on latency, throughput, Packet Delivery Ratio and Packet loss percentage are primed in this paper.

关键词： Manifolds Heuristic algorithms Simulation Packet loss Load management Throughput Software

来源：评论

学校读者我要写书评

暂无评论

Machine Vision Observation, Artificial Intelligence Pattern Recognition, Protective Circuit Design, Characterization of Multiple Materials, and Nano-Structural Analysis for Investigating InGaN Green Light Emitting Diode Degradation in a Salty Water Vapor Environment

Machine Vision Observation, Artificial Intelligence Pattern ...

引用

2024 IEEE International Reliability Physics Symposium, IRPS 2024

作者： Chen, Cheng-Shan Yang, Chun-Yen Yang, Shao-Jui Wang, Deng-Yi Kuo, Yaw-Wen Hsiao, Wei-Han Chou, Hsin-Hung Lin, Chia-Feng Li, Yung-Hui Wu, Yewchung Sermon Chen, Hsiang Han, Jung National Yang Ming Chiao Tung University Department of Materials Science and Engineering Hsinchu30010 Taiwan National Chi Nan University Department of Electrical Engineering Nantou54561 Taiwan National Chi Nan University Department of Applied Materials and Optoelectronic Engineering Nantou54561 Taiwan Chang Gung University Department of Electrical Engineering Taoyuan33302 Taiwan National Chi Nan University Department of Computer Science & Information Engineering Nantou54561 Taiwan National Chung Hsing University Department of Materials Science and Engineering Taichung40227 Taiwan Hon Hai Research Institute AI Research Center Taipei11494 Taiwan Yale University Department of Electrical Engineering New HavenCT06511 United States

ISBN: (纸本)9798350369762

This study delves into the degradation of GaN-based LEDs in saline environments, a relatively underexplored area of research. LEDs are known for their longevity, but face challenges under extreme conditions. Utilizing artificial intelligence, machine vision, and material analysis, this study detects early signs of LED degradation[1], [2]. The results highlight the impact of saline exposure on LED performance, with some LEDs continuing to function for up to 30 minutes before failure. Advanced circuits ensure uninterrupted operation. Encompassing electrical engineering, computer science, and materials science, this study provides a comprehensive approach to LED fault detection and protection. © 2024 IEEE.

关键词： III-V semiconductors

来源：评论

学校读者我要写书评

暂无评论

Effect of Credit Financing on the Supply Chain for Imperfect Deteriorating Items with Carbon Emission 11

Effect of Credit Financing on the Supply Chain for Imperfect...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Mittal, Mandeep Chauhan, Sudhir Kumar Rastogi, Shivangi School of Computer Science Engineering and Technology Bennett University Department of Mathematics Uttar Pradesh Greater Noida India Amity University Uttar Pradesh Aias Department of Mathematics Noida India Amity Institute of Applied Sciences Amity University Uttar Pradesh Noida India

ISBN: (纸本)9798350350357

The sustainable inventory model is a framework designed to ensure manufacturing processes' sustainability while maintaining profitability. During manufacturing, some items may experience degradation, resulting in imperfect goods. Nevertheless, a screening process is implemented to eliminate such items before they reach the consumers. Therefore, it is critical to scrutinize items prone to deterioration thoroughly. Suppliers prioritize trade credit in payments when supplying retailers, necessitating the development of an inventory model that caters to the needs of retailers dealing with imperfect and deteriorating quality items while considering carbon emissions and trade credit as a payment. The study presents numerical illustrations and sensitivity analysis for a better understanding of the model. © 2024 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Simulation of Pick and Place Robotic Arm using Coppeliasim 6

Simulation of Pick and Place Robotic Arm using Coppeliasim

引用

6th International Conference on Computing Methodologies and Communication, ICCMC 2022

作者： Rooban, S. Iwin Thanakumar Joseph, S. Manimegalai, R. Eshwar, Idupulapati Venkata Sai Mageswari, R Uma Koneru Lakshmaiah Education Foundation Department of Electronics and Communication Engineering Andhra Pradesh Guntur522502 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur522502 India PSG Institute of Technology and Applied Research Department of Computer Science and Engineering T.N 641062 India Vardhaman College of Engineering Department of Computer Science and Engineering Telangana Hyderabad501218 India

ISBN: (纸本)9781665410281

Technology is growing in a fast pace in terms of higher technical aspects to meet the requirements of the present industrial revolution. Technically sound human being alone not sufficient to co-op with the industrial revolution. To meet the growing demands of any industry through the available human in is a toughest task. Current industry revolution 4.0 is being implemented all over the world with the help of robotic technology. To perform the routine works and simple tasks increase the use of robotic arm handlings. At present there is a vast requirement for these types of robots in industries to perform repeatable actions like moving objects, welding, painting, packing goods, assembling of parts 3D printing etc., These types of robots are called robotic arm which are used precisely in industries to complete the work easier, quicker with perfection. The robotic arm is formed by connecting all the joints, motors to activate each joint of the robotic arm. Robotic arm is controlled by the micro controllers through program. The robotic arm is generally five to seven degrees of freedom and capable of rotate in all the directions. End effector is connected at the edge of the robot which is used to pick the objects. End effector is like the fingers in our human arm, in robotics how better the program controls the end effector decides the performance of the robotic arm. This work discusses the design of the robot arm through the coppeliasim. The designed manipulator gives the accurate and reliable output for picking and placing the object. © 2022 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Machine Learning Methods Through Evaluating the Impact of Contributing Factors on The Accuracy of Soil Moisture Prediction

A Comparative Study on Machine Learning Methods Through Eval...

引用

IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA)

作者： Md Nahin Islam Doina Logofatu Md Zahidul Haque Department of Computer Science and Engineering Frankfurt University of Applied Sciences Germany Department of Computer Science and Engineering Sylhet Engineering College Bangladesh Department of Computer Science and Engineering Waziup e.V Dresden Germany

In agricultural water practices, accurate prediction of soil moisture (SM) is crucial for the efficient use and management of water resources. However, due to the complex structural characteristics and meteorological factors involved, establishing an ideal model for predicting SM can be challenging. Ensemble Methods (EM) offer a promising solution to overcome this challenge and increase the accuracy of SM prediction. In this study, we make a twofold contribution to the SM study regarding how various factors can impact the moisture content of the soil. First, we discuss the potential of the Extra Tree Regressor (ETR), CatBoost Regressor (CBR), Random Forest Regressor (RFR), Extreme Gradient Boosting Regressor (XGBR), and several other algorithms for SM prediction using atmospheric variables (i.e., air temperature, humidity, wind, solar radiance, rainfall, etc.) and soil factors (i.e., soil humidity, crop coefficient culture, evapotranspiration measured, evapotranspiration reference). We then look at the impact of contributing factors through sensitivity analysis. The findings indicate that the Model Stacking approach exhibited relatively superior performance (R2 = 0.9982) in predicting input variables, surpassing both Model Blending (R2 = 0.9969) and Model Ensembling of the three different machine learning models: ETR (R2 = 0.9966), RFR (R2 = 0.9929), and CBR (R2 = 0.9935). In general, the utilization of the Model Stacking technique exhibits encouraging outcomes in enhancing the accuracy of sentiment analysis predictions. This approach stems from its capability to address the constraints associated with rudimentary algorithms, characterized by restricted parameters and expedited computation durations. Moreover, the comprehensive analysis of feature importance underscores the critical role of humidity, wind dynamics, and other environmental variables in shaping soil moisture dynamics across diverse irrigation regimes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Reptile Search Algorithm by Salp Swarm Algorithm for Medical Image Segmentation

引用

Journal of Bionic engineering 2023年第4期20卷 1766-1790页

作者： Laith Abualigah Mahmoud Habash Essam Said Hanandeh Ahmad MohdAziz Hussein Mohammad Al Shinwan Raed Abu Zitar Heming Jia Computer Science Department Prince Hussein Bin Abdullah Faculty for Information TechnologyAl Al-Bayt UniversityMafraq25113Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman UniversityAmman19328Jordan Faculty of Information Technology Middle East UniversityAmman11831Jordan Applied Science Research Center Applied Science Private UniversityAmman11931Jordan School of Computer Sciences Universiti Sains Malaysia11800Pulau PinangMalaysia Amman Arab University AmmanJordan Department of Computer Information System Zarqa UniversityP.O.Box 13132ZarqaJordan Deanship of E-Learning and Distance Education Umm Al-Qura UniversityMakkah21955Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Sorbonne Center of Artificial Intelligence Sorbonne University-Abu DhabiAbu DhabiUnited Arab Emirates School of Information Engineering Sanming UniversitySanming365004China

This study proposes a novel nature-inspired meta-heuristic optimizer based on the Reptile Search Algorithm combed with Salp Swarm Algorithm for image segmentation using gray-scale multi-level thresholding,called *** proposed method introduces a better search space to find the optimal solution at each ***,we proposed RSA-SSA to avoid the searching problem in the same area and determine the optimal multi-level *** obtained solutions by the proposed method are represented using the image *** proposed RSA-SSA employed Otsu’s variance class function to get the best threshold values at each *** performance measure for the proposed method is valid by detecting fitness function,structural similarity index,peak signal-to-noise ratio,and Friedman ranking *** benchmark images of COVID-19 validate the performance of the proposed *** results showed that the proposed RSA-SSA outperformed other metaheuristics optimization algorithms published in the literature.

关键词： Bioinspired Reptile Search Algorithm Salp Swarm Algorithm Multi-level thresholding Image segmentation Meta-heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Inf-TESLA++: A Blockchain-assisted Continuous Authentication Protocol for Broadcast Communication in Resource-Constrained Devices

Inf-TESLA++: A Blockchain-assisted Continuous Authentication...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Mallikarjun Reddy Dorsala Charugundla Lakshmi Nishitha Pendem Sathwik Gattu Srilekha Mahesh Kumar Morampudi Department of Computer Science and Engineering Indian Institute of Information Technology Sri City Chittoor India Department of Computer Science and Engineering School of Engineering and Applied Sciences (SEAS) SRM University AP India

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

Many applications widely use broadcast communications (BC) due to their efficiency in simultaneously distributing data to many receivers. More specifically, BC is essential in resource-constrained devices (RCDs) for conserving energy and bandwidth, which are vital for increasing the longevity and performance of RCDs. The three major challenges in BC are source authentication, data integrity and continuous authentication (CA). The first two challenges are effectively addressed in TESLA and its variants. However, achieving CA without incurring overheads on the sender and receiver sides remains an unresolved challenge. In this paper, we propose Infinite (Inf) TESLA++, assisted by Blockchain and smart contracts, to address the CA challenge with minimal overhead at sender and receiver. Our theoretical and simulation analysis demonstrates that Inf-TESLA++ incurs minimal overhead compared to existing protocols while eliminating the need for direct communication between the sender and receiver for synchronization.

关键词： Performance evaluation Smart contracts Authentication Receivers Bandwidth Blockchains Telecommunications Security Synchronization Testing

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：