检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xu, Chengpei Jia, Wenjing Wang, Ruomei Luo, Xiaonan He, Xiangjian Faculty of Engineering and IT University of Technology Sydney Australia The Department of Computer Science University of Nottingham Ningbo China School of Data and Computer Science National Engineering Research Center of Digital Life Sun Yat-sen University China The School of Computer Science and Information Security Guilin University of Electronic Technology China

Bottom-up text detection methods play an important role in arbitrary-shape scene text detection but there are two restrictions preventing them from achieving their great potential, i.e., 1) the accumulation of false text segment detections, which affects subsequent processing, and 2) the difficulty of building reliable connections between text segments. Targeting these two problems, we propose a novel approach, named "MorphText", to capture the regularity of texts by embedding deep morphology for arbitrary-shape text detection. Towards this end, two deep morphological modules are designed to regularize text segments and determine the linkage between them. First, a Deep Morphological Opening (DMOP) module is constructed to remove false text segment detections generated in the feature extraction process. Then, a Deep Morphological Closing (DMCL) module is proposed to allow text instances of various shapes to stretch their morphology along their most significant orientation while deriving their connections. Extensive experiments conducted on four challenging benchmark datasets (CTW1500, Total-Text, MSRA-TD500 and ICDAR2017) demonstrate that our proposed MorphText outperforms both top-down and bottom-up state-of-the-art arbitrary-shape scene text detection approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Trajectory Optimization and Resource Allocation for HAP-Assisted UAV Wireless Networks

Energy Efficient Trajectory Optimization and Resource Alloca...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Hui Zhao Zheng Chang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Information Technology University of Jyväskylä Jyväskylä Finland

In this paper, we propose an energy efficiency (EE) optimization scheme for data collection in high altitude platform (HAP)-assisted unmanned aerial vehicle (UAV) network. The HAP acts as the aerial base station (ABS) to assist UAV and sensing devices (SDs) establishing direct uplink data transmission, i.e., device-to-UAV (D2U) communication. Our goal is to operate the UAV in an energy-efficient manner for cyclic data collection by dynamically clustering the target area and optimizing sink SD selection and transmit power in D2U communications. An optimization problem is formulated that maximizes the throughput-energy utility. Aiming at addressing the formulated problem, we propose a dynamic clustering algorithm based on Affinity Propagation (AP) to determine sink SDs for D2U communications, and a centralized reinforcement learning algorithm based on Proximal Policy Optimization (PPO) to obtain the optimal UAV trajectory and sink SDs' transmit power. Simulation results demonstrate that the proposed scheme has advantages in EE compared with other schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Deep Reinforcement Learning-based Trajectory Design for UAV-aided Edge Computing System

Multi-agent Deep Reinforcement Learning-based Trajectory Des...

引用

IEEE Conference on Wireless Communications and Networking

作者： Gengyuan Lu Zheng Chang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Information Technology University of Jyväskylä Jyväskylä Finland

The unmanned aerial vehicle (UAV)-aided communication system is able to extend the coverage of the cellular network and provide flexible connectivity to the ground users. Recently, in order to achieve the ambitious goal of ubiquitous computing and intelligence, UAV-aided mobile edge computing (MEC) system also attracts significant research interests. In this work, we investigate the trajectory design for a multi-UAV-aided MEC system to maximize the defined quality of experience (QoE) and service fairness of multiple ground user equipments (UEs). Since the practical communication environment is complex and time-varying, it is challenging for the multiple UAVs to dynamically make autonomous decisions. Meanwhile, the centralized decision-making scheme may also have a certain degree of transmission delay and affect efficiency of the considered system. Therefore, bearing in mind these challenges, in order to solve the formulated problem, we propose a multi-agent deep reinforcement learning algorithm using Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to design UAV’s trajectory via optimizing the flying angle and distance. The simulation results show that our proposed solution outperforms the traditional algorithms.

关键词： Deep learning Multi-access edge computing Simulation Heuristic algorithms Decision making Reinforcement learning Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Joint Sensing and Computation Offloading for Wireless Powered Mobile Edge Computing System

Joint Sensing and Computation Offloading for Wireless Powere...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Wenxin Wu Zheng Chang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Information Technology University of Jyväskylä Jyväskylä Finland

Mobile-edge computing (MEC) and wireless power transfer (WPT) are promising paradigms in the Internet of Things (IoT) era to alleviate limitations of energy and computation capacity of wireless devices (WDs). In this paper, we consider a wireless-powered MEC in which one hybrid access point (HAP) with a stable energy supply and computation capacity coordinates with a set of WDs with WPT and sensing capabilities. In the considered model, WDs first harvest RF energy transmitted by HAP and then sense data with stored energy for multiple sensing tasks. With MEC, WDs can execute tasks locally or offload data to HAP. To minimize the average latency, we formulate a joint sensing and processing optimization problem in a wireless powered-MEC system under energy and successful sensing probability constraints. This NP-hard problem can be decoupled into three subproblems. Then, we adopt an alternating algorithm to iteratively solve the WPT time, sensing time, and offloading policy subproblems. Simulation results demonstrate the effectiveness of our proposed joint optimization algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Boost Converter System with Solar Charging Controller for Electrical Equipment

Development of Boost Converter System with Solar Charging Co...

引用

IEEE International Conference on engineering Technologies and Applied Sciences (ICETAS)

作者： Babul Salam Ibrahim Dur Muhammad Soomro Sharman Sundarajoo Mohd Fakhrul Shahirin Electrical and Computer Engineering Department Gulf University for Science & Technology Kuwait Faculty of Electrical and Electronic Engineering Universiti Tun Hussein onn Malaysia Johor Malaysia

There are numerous DC to DC energy alteration utilizations where the origin voltage needs to be transformed to a larger resulting voltage. Boost converters utilization includes energy equipment for semiconductor manufacturing supplies, ultrasound instruments, X-ray devices, solar systems, and mercury ion motors. Notably, this type of converter is used to step up the photovoltaic generator's voltage to the required load voltage in solar systems. Hence, this study's principal interest is to form and compose a boost converter and a solar charging controller circuit. This system aims to change the uncontrolled input of DC to a regulated output of DC with the wanted level of voltage. There are three critical procedures involved to produce a boost converter. The first process was to design. Next was to simulate, and the final process was to construct the boost converter and a solar charging controller circuit. The operational frequency was configured at 20 kHz, and a duty cycle of 50% was employed. In this study, the OrCAD PSpice, Multisim, and Proteus software environments were used to simulate the develop the circuit to obtain results. Every parameter value was obtained from the hardware. The values obtained were compared with the calculation, simulation, and hardware results from the boost converter circuit as a validation procedure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparator Design Resistance Mitigation by using Cadence Virtuoso Tools in 45 Nanometer Process technology

Comparator Design Resistance Mitigation by using Cadence Vir...

引用

IEEE International Conference on Sensors and Nanotechnology

作者： Michelle Ang Syn Yi Razaidi Hussin Fakhrul Zaman Rokhani Faculty of Electronic Engineering Technology University Malaysia Perlis Arau Malaysia Department of Computer and Communications System Engineering University Putra Malaysia UPM Serdang Malaysia

This paper presents the resistance mitigation techniques for comparator design. Resistance plays an important role to semiconductor field. If resistance value higher than the design specification value, this might cause the electronic device burning and destroy. This project implements the techniques to mitigate resistance for the comparator design layout which are using multiple metal layers for routing, routing track improvement, increase metal width, increase number of vias and using higher metal layer for routing by using Cadence Virtuoso tools in 45 nanometer process technology. Based on the result, the total percentage for resistance mitigation for using multiple metal layers for routing is 73.66%, routing track improvement is 67.67%, increase metal width is 51.74%, increase number of vias is 50% and using higher metal layer for routing is 18.79%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lightning and Surge Arrester Simulation in Power Distribution System

Lightning and Surge Arrester Simulation in Power Distributio...

引用

IEEE International Conference on engineering Technologies and Applied Sciences (ICETAS)

作者： Babul Salam Ibrahim Dur Muhammad Soomro Sharman Sundarajoo Muhammad Noor Akhir Tahrir Electrical and Computer Engineering Department Gulf University for Science & Technology Kuwait Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Johor Malaysia

Lightning is a very significant occurrence that exists on earth. One stroke of lightning on a distribution network can be enough to be the root of a power outage. Therefore, this study examines and investigates the consequences of lightning and surge arresters in the power distribution system. A lightning surge is designed to examine consequences on a network. The metal oxide surge arrester (MOSA) performance illustration is pointedly diverse during significant impulse transients are considered. The MOSA is selected after comparing the shielding stages, momentary overvoltage, and power captivation competency. Picking a greater valued surge arrester raises its momentary overvoltage scope. Hence, its capability to endure against network voltage pressures develops but decreases the arrester's safety level for a specified shielding range. However, for the fast front surge arrester, its vital features are important for overvoltage related investigations relating quick front surges. Lightning surge and surge arrester simulation were carried out in the PSCAD software environment to investigate the effects of lightning and surge arresters in the distribution system. This study's simulation results indicate the significance and requirement of lightning defense systems installation in distribution networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model-Driven Sensing-Node Selection and Power Allocation for Tracking Maneuvering Targets in Perceptive Mobile Networks

arXiv

引用

arXiv 2023年

作者： Xie, Lei He, Hengtao Song, Shenghui Eldar, Yonina C. Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong The Faculty of Mathematics and Computer Science Weizmann Institute of Science Rehovot7610001 Israel

Maneuvering target tracking will be an important service of future wireless networks to assist innovative applications such as intelligent transportation. However, tracking maneuvering targets by cellular networks faces many challenges. For example, the dense network and high-speed targets make the selection of the sensing nodes (SNs) and the associated power allocation very challenging. Existing methods demonstrated engaging performance, but with high computational complexity. In this paper, we propose a model-driven deep learning (DL)-based approach for SN selection. To this end, we first propose an iterative SN selection method by jointly exploiting the majorization-minimization (MM) framework and the alternating direction method of multipliers (ADMM). Then, we unfold the iterative algorithm as a deep neural network and prove its convergence. The proposed method achieves lower computational complexity, because the number of layers is less than the number of iterations required by the original algorithm, and each layer only involves simple matrix-vector additions/multiplications. Finally, we propose an efficient power allocation method based on fixed point (FP) water filling and solve the joint SN selection and power allocation problem under the alternative optimization framework. Simulation results show that the proposed method achieves better performance than the conventional optimization-based methods with much lower computational complexity. © 2023, CC BY.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Natural Lighting System Using Fiber Optics for Energy Efficiency

Natural Lighting System Using Fiber Optics for Energy Effici...

引用

IEEE International Conference on engineering Technologies and Applied Sciences (ICETAS)

作者： Babul Salam Ibrahim Dur Muhammad Soomro Sharman Sundarajoo Zulhelmi Nordin Electrical and Computer Engineering Department Gulf University for Science & Technology Kuwait Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn Malaysia Johor Malaysia

The sunlight's utilization as an illumination supply for lighting inside the building has expanded significantly since the 1900s. Lighting holds an integral part of the total electricity usage in a building. It is also one of the scopes with numerous ways to increase energy effectiveness by lowering energy usage. Hence, a natural lighting system is recommended to curtail electrical energy consumption for illumination throughout the daytime. This work aims to create a natural lighting system model to direct and address natural illuminance into challenging and complicated buildings. In this work, solar energy from the sun is conducted towards the fiber optics package's edge by utilizing a convex lens. This system aims to lower electrical-based lighting consumption during daytime illumination by transmitting the solar light over fiber optics. According to the sun's position, the system is sustained by an optic directional controller to guarantee the utmost connected illuminance. The control system would assure the highest illuminance accumulation also automatically turn on the electricity-based illumination if the acquired natural light did not satisfy the sufficient lux. The PIC16F877A microcontroller was used as a processor to power the tracking device engine. The percentage of the reduction in energy usage for daytime lighting was obtained. The obtained results show that this system will save energy during the day by 57%. Therefore, this paper represents a notable improvement in optical fiber natural lighting systems' commercialization in energy-saving and cost reduction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Hierarchical Reinforcement Learning Framework for Energy-Efficient 5G Base Stations in Urban Environments

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xu, Dianlei Su, Xiang Premsankar, Gopika Wang, Huandong Tarkoma, Sasu Hui, Pan University of Helsinki Department of Computer Science Helsinki00014 Finland Department of Electronic Engineering Beijing100084 China University of Helsinki Department of Agricultural Sciences Helsinki00014 Finland Aalto University Department of Information and Communications Engineering Finland University of Oulu Faculty of Information Technology and Electrical Engineering Oulu90014 Finland The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

The energy consumption of 5G base stations (BSs) is significantly higher than that of 4G BSs, creating challenges for operators due to increased costs and carbon emissions. Existing solutions address this issue by switching off BSs during specific periods or forming cooperation coalitions where some BSs deactivate while others serve users. However, these approaches often rely on fixed geographic configurations, making them unsuitable for urban areas with numerous BSs and mobile users. To tackle these challenges, we propose a hierarchical reinforcement learning (RL) framework for energy conservation in large-scale 5G networks. In the upper-layer, we propose a deep Q-network integrated with a graph convolutional network that dynamically groups BSs into coalitions from a macro perspective. This layer focuses on high-level coalition formation to optimize system-wide energy efficiency by considering the global state of the network. In the lower-layer, we combine attention mechanism with multi-agent RL and graph convolutional networks to design a scalable algorithm that maximizes local energy efficiency through optimizing the cooperation within each coalition. These two layers align global coalition dynamics with local intra-coalition cooperation to achieve system-wide energy optimization. Moreover, we accurately model large-scale urban 5G scenarios leveraging a high-fidelity network simulator, which enables our RL framework to learn from real-world feedback. Extensive experiments conducted with the simulator demonstrate that our proposed framework achieves remarkable energy savings of up to 75.6%, significantly outperforming baseline approaches. These findings highlight the effectiveness and superiority of our hierarchical RL optimization framework in addressing the energy consumption challenges faced by large-scale 5G networks. © 2002-2012 IEEE.

关键词： 5G mobile communication systems

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：