检索结果-内蒙古大学图书馆

Information and Education Technology (ICIET), International Conference on

作者： Wu-Yuin Hwang Ika Qutsiati Utami Department of Computer Science and Information Engineering National Dong Hwa University Graduate Institute of Network Learning Technology National Central University Taiwan Graduate Institute of Network Learning Technology National Central University Taoyuan Taiwan Faculty of Advanced Technology and Multidiscipline Universitas Airlangga Indonesia

ISBN: (数字)9798350371772

ISBN: (纸本)9798350371789

This paper introduced an interactive system for generating contextualized and personalized mathematic word problems (MWP) from authentic contexts using the Generative Pre-trained Transformers (GPT). Our proposed Automatic Question Generation (AQG) system comprises (1) the authentic contextual information acquisition through image recognition by TensorFlow and augmented reality (AR) measurement through AR Core, (2) a personalized mechanism based on instructional prompts to generate three difficulty levels for learner's different needs, and (3) MWP generation through GPT with authentic contextual information and personalized needs. A quasi-experiment was conducted by recruiting 51 fifth-grade students to evaluate the effectiveness of the proposed AQG on their geometry learning performance. The results revealed that students who learned with the proposed AQG outperformed students who learned with a decontextualized way on geometry learning performances. Therefore, our proposed AQG is useful for promoting mathematic problem-solving activity in an authentic context.

关键词： Geometry Image recognition Interactive systems Education Transformer cores Transformers Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Reinforcement Learning Beyond Expectation

arXiv

引用

arXiv 2022年

作者： Rajabi, Arezoo Ramasubramanian, Bhaskar Maruf, Abdullah Al Poovendran, Radha Network Security Lab Department of Electrical and Computer Engineering University of Washington SeattleWA98195 United States Electrical and Computer Engineering Western Washington University BellinghamWA98225 United States

Cyber and cyber-physical systems equipped with machine learning algorithms such as autonomous cars share environments with humans. In such a setting, it is important to align system (or agent) behaviors with the preferences of one or more human users. We consider the case when an agent has to learn behaviors in an unknown environment. Our goal is to capture two defining characteristics of humans: i) a tendency to assess and quantify risk, and ii) a desire to keep decision making hidden from external parties. We incorporate cumulative prospect theory (CPT) into the objective of a reinforcement learning (RL) problem for the former. For the latter, we use differential privacy. We design an algorithm to enable an RL agent to learn policies to maximize a CPT-based objective in a privacy-preserving manner and establish guarantees on the privacy of value functions learned by the algorithm when rewards are sufficiently close. This is accomplished through adding a calibrated noise using a Gaussian process mechanism at each step. Through empirical evaluations, we highlight a privacy-utility tradeoff and demonstrate that the RL agent is able to learn behaviors that are aligned with that of a human user in the same environment in a privacy-preserving manner. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Age of Information Analysis for CR-NOMA Aided Uplink Systems with Randomly Arrived Packets

arXiv

引用

arXiv 2023年

作者： Sun, Yanshi Ye, Yanglin Ding, Zhiguo Zhou, Momiao Liu, Lei School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Department of Computer and Information Engineering Khalifa University Abu Dhabi United Arab Emirates Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts and Telecommunications Xi’an710121 China

This paper studies the application of cognitive radio inspired non-orthogonal multiple access (CR-NOMA) to reduce age of information (AoI) for uplink transmission. In particular, a time division multiple access (TDMA) based legacy network is considered, where each user is allocated with a dedicated time slot to transmit its status update information. The CR-NOMA is implemented as an add-on to the TDMA legacy network, which enables each user to have more opportunities to transmit by sharing other user’s time slots. A rigorous analytical framework is developed to obtain the expressions for AoIs achieved by CR-NOMA with and without re-transmission, by taking the randomness of the status update generating process into consideration. Numerical results are presented to verify the accuracy of the developed analysis. It is shown that the AoI can be significantly reduced by applying CR-NOMA compared to TDMA. Moreover, the use of re-transmission is helpful to reduce AoI, especially when the status arrival rate is low. Copyright © 2023, The Authors. All rights reserved.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

DQ-WiAPDoM: A DQN-based AP Deployment Optimization Method for Wi-Fi FTM Positioning

DQ-WiAPDoM: A DQN-based AP Deployment Optimization Method fo...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： Zihao Liu Han Li Bo Gao Ke Xiong Pingyi Fan School of Computer and Information Technology Beijing Jiaotong University Beijing China Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China

This paper focuses on how to optimize the deployment location of the anchor Wi-Fi access points (APs) in order to enhance the indoor positioning performance of the finetime measurement (FTM) protocol. Compared to conventional Wi-Fi positioning, FTM protocol is able to achieve relatively good indoor positioning performance since it estimates distance between a sender and its receiver with the flight duration of Wi-Fi signals. However, the FTM-based positioning accuracy in NLoS environments is still not high, which restricts its application in indoor scenarios. To this end, we formulate an optimization problem to maximize the total number of LoS paths by optimizing the locations of the anchor APs. To solve the problem, we propose a Deep Q-network (DQN)-based AP deployment optimization method (DQ-WiAPDoM), which utilizes DQN to optimize the locations of APs such that the total number of LoS paths over all covered area is maximized. Experimental results show that DQ-WiAPDoM converges well and is able to reduce the average positioning error efficiently.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-supervised learning of a tailored Convolutional Auto Encoder for histopathological prostate grading 31

Self-supervised learning of a tailored Convolutional Auto En...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Tabatabaei, Zahra Colomer, Adrián Engan, Kjersti Oliver, Javier Naranjo, Valery Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano Spain HUMAN-tech Universitat Politècnica de València Spain ValgrAI - Valencian Graduate School Research Network for Artificial Intelligence Spain Department of Electrical Engineering and Computer Science University of Stavanger Norway Department of Artificial Intelligence Tyris Tech S.L. Valencia Spain

ISBN: (纸本)9789464593600

According to GLOBOCAN 2020, prostate cancer is the second most common cancer in men worldwide and the fourth most prevalent cancer overall. For pathologists, grading prostate cancer is challenging, especially when discriminating between Grade 3 (G3) and Grade 4 (G4). This paper proposes a Self-Supervised Learning (SSL) framework to classify prostate histopathological images when labeled images are scarce. In particular, a tailored Convolutional Auto Encoder (CAE) is trained to reconstruct 128×128×3 patches of prostate cancer Whole Slide Images (WSIs) as a pretext task. The downstream task of the proposed SSL paradigm is the automatic grading of histopathological patches of prostate cancer. The presented framework reports promising results on the validation set, obtaining an overall accuracy of 83% and on the test set, achieving an overall accuracy value of 76% with F1-score of 77% in G4. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Conceptual Design of Wireless Smart Grid for the Optimization of Electric Transmission in Iraq

Conceptual Design of Wireless Smart Grid for the Optimizatio...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Aeshah Burhan Abbas Akram A. Almohammedi Mohammed Balfaqih Sam Darshi Electrical & Electronics Engineering Department Karabük University Karabük Turkey Electrical & Electronics Department Karabük University Karabük Turkey Automobile Transportation Department South Ural State University Chelyabinsk Russia Department of Computer and Network Engineering University of Jeddah Jeddah Saudi Arabia Department of Electrical Engineering Indian Institute of Technology Ropar Punjab India

Rapid development of technology has resulted in a considerable increase in electricity consumption, which has created a barrier not only because of the generation but also in delivery. Thus, when demand increases, the complexity of the electrical network increases as a result of the increased need for improved dependability, efficiency, protection, energy, and environmental sustainability. According to the world bank statistics, Iraq's loss was 51% during distribution, and it is considered significantly high. This study proposes a wireless network-based design for detecting and optimizing Iraq's electricity distribution infrastructure. Moreover, the suggested module is composed of several data gathering methods that are required for the various paths of the power distribution systems. This design offers viable support for a variety of issues confronting Iraq's power distribution systems, including variable voltage levels caused by fluctuating electrical usage, power burglary, manual invoicing, and transmission line breakdowns. The suggested design is intended for use with single-phase power transmission systems; however, it may be adapted for use with three-phase power distribution systems with slight improvements. The introduction of this method will result in significant energy savings, allowing for the availability of electricity to a greater number of users than previously possible in a crowded place. The suggested smart grid design, which was created for the Iraq context, permits real-time control of energy consumption, optimal electricity consumption, minimal loss, diagnosis of power failures, breakdowns, and automatic invoicing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Gain and Efficiency Triple U-shaped Slots Microstrip Patch Antenna for 5G Applications

High Gain and Efficiency Triple U-shaped Slots Microstrip Pa...

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Akram A. Almohammedi Ahmad Raad Sam Darshi Vladimir Shepelev Mohammad Hafiz Mohd Yusof Mohammed Balfaqih Electrical & Electronics Department Karabük University Karabük Turkey Automobile Transportation Department South Ural State University Chelyabinsk Russia Electrical & Electronics Engineering Department Karabük University Karabük Turkey Department of Electrical Engineering Indian Institute of Technology Ropar Punjab India Faculty of Computer and Mathematical Sciences Universiti Teknologi MARA Perak Malaysia Department of Computer and Network Engineering University of Jeddah Jeddah Saudi Arabia

The 28 GHz band is a frequency band that has been allocated for use in 5G mobile communication networks. It is part of the millimeter wave spectrum, which is a range of frequencies between 30 GHz and 300 GHz. This study proposes and investigates the 28 GHz 5G networks. A modified single element patch antenna with three grooved U-shaped holes is shown and is used to indicate a high gain and Efficiency for 28 GHz 5G antenna. The proposed antenna consists of the radiation element on a RTRogers 5880 laminate and is actuated by a microstrip feedline. The proposed work includes the most desirable characteristics, such as small size, light weight, low-cost fabrication and wide operation up to 1.4 GHz (27.1 - 28.5 GHz). The proposed antenna design also offers a high efficiency up to 89.73 %, high gain up to 8.14 dBi, and return loss up to −30 dB, resulting in attractive performance. The results obtained show that the antenna is a viable candidate for 5G applications at 28 GHz.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Biometric-Based Access Control Systems with Robust Facial Recognition in IoT Environments

Biometric-Based Access Control Systems with Robust Facial Re...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： B.V. Satish Babu J. Manoranjini Ravindra Changala Mohd Aarif S. Suma Christal Mary I Infant Raj Department of IT Prasad V Potluri Siddhartha Institute of Technology Vijayawada India Department of AI & ML Chaitanya Bharathi Institute of Technology Hyderabad India Department of Information Technology Guru Nanak Institutions Technical Campus Hyderabad India Associate Editor-Publishing Global Research Network Noida India Department of Information Technology Panimalar Engineering College Poonamalle Chennai India Department of Computer Science and Engineering K. Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

The integration of biometric-based access control systems with robust facial recognition technology within Internet of Things (IoT) environments holds paramount significance in addressing contemporary security challenges. The novelty of the research endeavours to contribute to this critical area by investigating and implementing a novel approach, employing Convolutional Neural networks (CNN) for facial classification within the biometric framework. The significance of this study lies in its potential to enhance security measures in IoT environments, ensuring reliable and efficient access control. Previous attempts at integrating facial recognition into IoT have encountered notable challenges, including suboptimal accuracy, vulnerability to adversarial attacks, and scalability issues. This research builds upon these prior issues by introducing CNN for facial classification, leveraging its capabilities in image processing and pattern recognition to achieve enhanced accuracy and resilience against potential security threats. The novelty of the study is underscored by the application of CNN within the biometric context of IoT, offering a cutting-edge solution tailored to the intricacies of interconnected devices. Experiments conducted on benchmark datasets showcase the promising capabilities of the proposed system, with face recognition accuracies reaching an impressive 98%. These results underscore the potential of this research to significantly advance the state-of-the-art in biometric-based access control, particularly within the context of IoT environments. The utilization of CNN introduces a pioneering element, contributing to the evolution of secure and efficient access control solutions in the era of IoT.

关键词： Access control Face recognition Scalability Image processing Signal processing Convolutional neural networks Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Joint User Cooperation and Scheduling for Federated Learning in CFmMIMO networks

Joint User Cooperation and Scheduling for Federated Learning...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： Han Bao Bo Gao Ke Xiong Pingyi Fan School of Computer and Information Technology Beijing Jiaotong University Beijing China Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China

This paper proposes a joint user cooperation and scheduling (JUCS) method to minimize the maximum transmission time among users in the synchronous federated learning (FL) architecture, since the user with the worst quality link limits the training performance of FL. To this end, an optimization problem is formulated to find the optimal user cooperation pairing and the power control coefficients. Meanwhile, as the links among users operate on the same frequency bands, the interface between them is taken into account in this paper. As the problem is non-convex, we decouple it into two sub-problems. For the first sub-problem, we propose a fair scheduling (FS)-based algorithm to schedule the helping users to pair with the ones who are required to be assisted. For the second sub-problem, an algorithm based on deterministic policy gradient (DDPG) is proposed to find the optimized power control coefficients. Experiments show that the proposed JUCS method shortens about 34.48% transmission time of the worst user in FL compared to the traditional one without JUCS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Bipartite Matching for HAP Access in Space-Air-Ground Integrated networks using Graph Neural network-Enhanced Reinforcement Learning

Online Bipartite Matching for HAP Access in Space-Air-Ground...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Yuejiao Xie Guanchong Niu Man-On Pun Zhu Han School of Science and Engineering the Future Network of Intelligence Institute (FNii) the Chinese University of Hong Kong Shenzhen China Guangzhou Institute of Technology Xidian University Guangzhou China Department of Electrical and Computer Engineering University of Houston Houston TX USA

Space-air-ground integrated networks have recently attracted intensive research interest as an emerging 6G architecture to significantly extend the network coverage. In this paper, we consider an aerial network consisting of high altitude platforms (HAPs) with limited battery power. As each ground user sequentially enters the network and makes access request, the target HAP has to make real-time decisions on accepting or denying the access request. By explicitly modeling the potential link cost and revenue associated with each request, this work optimizes the access control algorithm by maximizing the total network revenue for given HAP energy. More specifically, the access control problem is first formulated as an online bipartite matching (OBM) problem before a reinforcement learning (RL) architecture is proposed to resolve the OBM problem. To enhance the feature extraction capability of the proposed RL architecture, a graph neural network (GNN)- based encoder is developed to embed the network states before multi-head attention layers are employed to fuse temporal features from the encoder. Extensive computer experiments are performed to confirm that the proposed access control method can significantly outperform the conventional greedy online method while achieving comparable performance as compared to the offline solution but at much lower computational complexity.

关键词：

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：