检索结果-内蒙古大学图书馆

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural Computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

Joint V2V Group Association and Transmission Power Control in Federated Vehicular Networks

引用

IEEE Internet of Things Journal 2025年第11期12卷 18167-18182页

作者： Liu, Su Guan, Peiyuan Li, Yushuai Li, Tianyi Zolfagharian, Zolaikha Yu, Jiong Huang, Tingwen Xinjiang University School of Computer Science and Technology Urumqi830046 China University of Oslo Department of Informatics Oslo0316 Norway Aalborg University Department of Computer Science Aalborg9220 Denmark University of Tehran School of Electrical and Computer Engineering Iran Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

With growing awareness of privacy protection, Federated Learning (FL) in vehicular network scenarios effectively addresses privacy concerns, leading to the development of Federated Vehicular Networks (FVN). In FVN, vehicles maintain a global model by transmitting local models and iterative processing, resulting in significant communication overhead. In the Internet of Vehicles (IoV), as the majority of the spectrum resources are allocated to Vehicle-to-Vehicle (V2V) communication, vehicles engaged in FL encounter uplink interference when these resources are reused. This compromises the efficacy of FL vehicle communication. To address this issue, we propose FedCDC, a new Federated learning framework with adaptive weight Clustering with knowledge Distillation and Channel sharing-based resource allocation. First, we implement a communication compression strategy based on clustering and distillation to alleviate transmission load. Then, we develop a resource allocation strategy to maximize the Signal-to-Interference-plus-Noise Ratio (SINR) for both FL vehicles and V2V groups, which investigates two critical components: channel pairing and power coordination. We formulate the optimization issue as a multi-objective optimization problem that is solved offline using the MIDACO solver. Due to the dynamic characteristics of FVN, we employ a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to enhance efficiency. Finally, extensive experiments demonstrate that our approach significantly reduces data transmission and offers an efficient resource coordination plan, thus improving FL communication efficiency and ensuring the Quality of Service (QoS) for both V2V groups and FL vehicles. © 2014 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Improving LSTM-based Indoor Positioning via Simulation-Augmented Geomagnetic Field Dataset 2

Improving LSTM-based Indoor Positioning via Simulation-Augme...

引用

2nd IEEE International Conference on Mobility, Operations, Services and Technologies, MOST 2024

作者： Vinciguerra, Elio Russo, Enrico Palesi, Maurizio Ascia, Giuseppe Rafique, Hamaad University of Catania Department of Electrical Electronic and Computer Engineering Catania Italy

ISBN: (纸本)9798350307733

Indoor positioning systems are now extensively used, enabling the precise localization of a user within a predefined space. The effectiveness of these services, particularly through the use of the geomagnetic field as feature, is notable, primarily due to its widespread natural availability, bypassing the need for dedicated infrastructure. Algorithmically, to establish a unique correlation between the data obtained by sensors at a specific location and the reference data used by the system, even in environments where the geomagnetic field exhibits minimal variations, a Recurrent Neural Network has been employed. This involves inputting the user's path into the network. To avoid costly dataset collection we employ a simulation-augmented approach. Furthermore, we combine the output of the proposed algorithm with inertial measurement unit data. Therefore, the proposed system attains an average error of around 0.4 meters in simulations and 1.6 meters in real-world scenarios. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Urban Traffic Management Through Machine Learning Prediction Models for Sensor-Less Roads 8

Enhancing Urban Traffic Management Through Machine Learning ...

引用

8th International Conference on Intelligent Traffic and Transportation, ICITT 2024 - incorporating the 8th International Conference on Communication and Network Technology, ICCNT 2024

作者： de Souza Oliveira, Thamires Di Grande, Sarah Berlotti, Mariaelena Cavalieri, Salvatore Torrisi, Vincenza Calabrò, Giovanni Inturri, Giuseppe Department of Electrical Electronic and Computer Engineering University of Catania Catania Italy

ISBN: (纸本)9781643685601

The process of urbanization on a global scale has generated a significant increase in metropolitan populations, which in turn brings with it a series of challenges for the management of transport infrastructure. In this context, the importance of accurate traffic flow prediction in urban traffic management systems stands out, with the city of Catania being used as the focus of this study. However, predicting traffic flow faces challenges, such as the high costs associated with acquiring extensive real traffic data, particularly when installing sensors on every road is not feasible. To address the issue of missing traffic flow data on roads without sensors, this study proposes an innovative approach based on machine learning, using the Long Short-Term Memory architecture and incorporating both sensor and floating car data. The results obtained are thoroughly analyzed and discussed, highlighting the ability of the LSTM model to provide accurate predictions of urban traffic, even with a limited amount of data available. These findings highlight the relevance of employing advanced machine learning techniques in the efficient management of urban mobility, aiming to improve the quality of life in cities and deal more effectively with the challenges of contemporary urban traffic. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Introduction to Heterogeneous Robotic Systems in 5G and Beyond Networks

引用

IEEE WIRELESS COMMUNICATIONS 2023年第2期30卷 64-65页

作者： Lu, Huimin Ho, Pin-Han Khalfi, Bassem Verikoukis, Christos Kyushu Institute of Technology Japan Department of Electrical and Computer Engineering The University of Waterloo Canada Oregon State University CorvallisOR United States University of Patras Department of Computer Engineering & Informatics Greece

Remote intelligence in the application of robotics and the autonomous system relies heavily on seamless wireless connections. The 5G mobile network technology meets traditional manufacturing enterprises' application requirements for wireless networks based on robot transformation and upgrading, robot interconnection, and remote interactive applications in production. However, there exists many challenging 5G communication issues, such as different communication protocols in the system varies with different robots and no dis-ruptive changes to the physical layer.

关键词： Special issues and sections Robots 5G mobile communication Physical layer Autonomous systems Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Ultra-Dense LEO Satellite-Aircraft Access and Service Management in Civil Aviation

引用

China Communications 2025年第1期22卷 277-292页

作者： Wang Yilei Ma Ting Liu Xiaoyu Gao Zhuxuan Zhou Haibo Shen Xuemin School of Electronic Science and Engineering Nanjing UniversityNanjing 210046China School of Electronic and Optical Engineering Nanjing University of Science and TechnologyNanjing 210094China The Department of Electrical and Computer Engineering University of WaterlooWaterloo N2L 3G1Canada

With the deployment of ultra-dense low earth orbit(LEO)satellite constellations,LEO satellite access network(LEO-SAN)is envisioned to achieve global Internet ***,the civil aviation communications have increased dramatically,especially for providing airborne Internet ***,due to dynamic service demands and onboard LEO resources over time and space,it poses huge challenges in satellite-aircraft access and service management in ultra-dense LEO satellite networks(UDLSN).In this paper,we propose a deep reinforcement learning-based approach for ultra-dense LEO satellite-aircraft access and service ***,we develop an airborne Internet architecture based on UDLSN and design a management mechanism including medium earth orbit satellites to guarantee lightweight ***,considering latency-sensitive and latency-tolerant services,we formulate the problem of satellite-aircraft access and service management for civil aviation to ensure service ***,we propose a proximal policy optimization-based access and service management algorithm to solve the formulated *** results demonstrate the convergence and effectiveness of the proposed algorithm with satisfying the service continuity when applying to the UDLSN.

关键词： civil aviation deep reinforcement learning satellite-aircraft access service management ultra-dense LEO satellite network

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Peltier Cooling System for Photovoltaic Thermal Management Using Simulation Tools 4

Design and Development of a Peltier Cooling System for Photo...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Oeishee, Moslema Hoque Muyeed, Munyem Ahammad Mehedi, Md. Rejoan Nidhi, Ramisa Sharar Brac University Electrical and Electronic Engineering Department Dhaka Bangladesh Brac University Computer Science and Engineering Department Dhaka Bangladesh

ISBN: (纸本)9798331530938

Mitigating the adverse effect of high temperature on photovoltaic (PV) module's efficiency in hot environment by using a thermoelectric cooling (TEC) method with PV through a detailed analysis, is the pivot objective of this paper. This research evaluates the Peltier module's effect on the power output and temperature of the PV modules in different ambient situations for the active cooling mode of the Peltier module. We utilized PVsyst and MATLAB (for initial circuit designs), as the simulation tools to analyze the performance ratio (PR) and thermal loss factor of the PV system for both with and without cooling conditions. Moreover, under an ambient temperature of 25.2°C, our developed TEC system enhances the PV module's performance ratio ranging from 83.42% to 85.8%, while The thermal loss factor is decreased ranging from -10.36% to -6.7%. These findings indicate that controlled cooling is capable of considerably improving PV performance, resulting in significant energy output rise. In addition to creating new paths to achieve more effective and sustainable energy production, this study demonstrates the way TEC systems might enhance solar energy systems, specifically in hot environments. © 2025 IEEE.

关键词： MATLAB

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

An Efficient Encryption and Compression of Sensed IoT Medical Images Using Auto-Encoder

引用

computer Modeling in engineering & Sciences 2023年第2期134卷 909-926页

作者： Passent El-kafrawy Maie Aboghazalah Abdelmoty M.Ahmed Hanaa Torkey Ayman El-Sayed School of Information Technology and Computer Science Nile UniversityGiza12677Egypt Math and Computer Science Department Faculty of ScienceMenoufia UniversityMenoufia32511Egypt Department of Computer Engineering College of Computer ScienceKing Khalid UniversityAbha61421Saudi Arabia Computer Science and Engineering Department Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

Healthcare systems nowadays depend on IoT sensors for sending data over the internet as a common *** ofmedical images is very important to secure patient *** these images consumes a lot of time onedge computing;therefore,theuse of anauto-encoder for compressionbefore encodingwill solve such a *** this paper,we use an auto-encoder to compress amedical image before encryption,and an encryption output(vector)is sent out over the *** the other hand,a decoder was used to reproduce the original image back after the vector was received and *** convolutional neural networks were conducted to evaluate our proposed approach:The first one is the auto-encoder,which is utilized to compress and encrypt the images,and the other assesses the classification accuracy of the image after decryption and *** hyperparameters of the encoder were tested,followed by the classification of the image to verify that no critical information was lost,to test the encryption and encoding *** this approach,sixteen hyperparameter permutations are utilized,but this research discusses three main cases in *** first case shows that the combination of Mean Square Logarithmic Error(MSLE),ADAgrad,two layers for the auto-encoder,and ReLU had the best auto-encoder results with a Mean Absolute Error(MAE)=0.221 after 50 epochs and 75%classification with the best result for the classification *** second case shows the reflection of auto-encoder results on the classification results which is a combination ofMean Square Error(MSE),RMSprop,three layers for the auto-encoder,and ReLU,which had the best classification accuracy of 65%,the auto-encoder gives MAE=0.31 after 50 *** third case is the worst,which is the combination of the hinge,RMSprop,three layers for the auto-encoder,and ReLU,providing accuracy of 20%and MAE=0.485.

关键词： Auto-encoder cloud image encryption IoT healthcare

来源：评论

学校读者我要写书评

暂无评论

Blockchain in Project Management for Information Security, Transparency and Accountability

Blockchain in Project Management for Information Security, T...

引用

2025 International Conference on electronics, Information, and Communication, ICEIC 2025

作者： Rahman, Tahmid Noor Abedin Khan, Mohammad Fasiul Bin Shahed, Labib Kafi, Abdulla Hil BRAC University Department of Electrical and Electronic Engineering Dhaka Bangladesh BRAC University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331510756

Blockchain technology, first developed for Bitcoin, offers transformative potential for project management. We present ChainManager, a conceptual blockchain-based project management platform developed with Flutter. Built on Ethereum, the blockchain network is deployed using OCI (Oracle Cloud Infrastructure), offering adaptability to varying project needs. This platform for managing projects makes use of smart contracts and immutable activity tracking in order to ensure the safety of activities such as monitoring work hours and controlling access. According to our findings, blockchain technology has the capability to solve long-standing problems, such as maintaining the integrity of data and gaining the trust of stakeholders. On the other hand, limitations such as scalability and high energy consumption continue to exist, which calls for additional study and innovation. Although there are obstacles to overcome, the purpose of this study is to investigate how blockchain technology can revolutionize project management by securing project data, automating processes, enhancing overall operational efficiency, and guaranteeing responsibility to stakeholders. © 2025 IEEE.

关键词： Ethereum

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：