检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Cai, Le Ferguson, Sam Lu, Haiyan Fang, Gengfa School of Electrical and Data Engineering School of Computer Science Faculty of Engineering & IT University of Technology Sydney SydneyNSW2007 Australia

The high feature dimensionality is a challenge in music emotion recognition. There is no common consensus on a relation between audio features and emotion. The MER system uses all available features to recognize emotion;however, this is not an optimal solution since it contains irrelevant data acting as noise. In this paper, we introduce a feature selection approach to eliminate redundant features for MER. We created a Selected Feature Set (SFS) based on the feature selection algorithm (FSA) and benchmarked it by training with two models, Support Vector Regression (SVR) and Random Forest (RF) and comparing them against with using the Complete Feature Set (CFS). The result indicates that the performance of MER has improved for both Random Forest (RF) and Support Vector Regression (SVR) models by using SFS. We found using FSA can improve performance in all scenarios, and it has potential benefits for model efficiency and stability for MER task. © 2022, CC BY.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging Reinforcement Learning to Improve Content Retrieval 3

Leveraging Reinforcement Learning to Improve Content Retriev...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Indira, G. Shelke, Ganesh C. Sharma, Bhuvnesh Singh, Vaishali Mahesh, T.R. Reddy, B. Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India Department of Information Technology Vishwakarma Institute of Information Technology Pune India Vivekananda Global University Department of Mechanical Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Computer Science Engineering Faculty of Engineering and Technology Karnataka Bangalore India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9798350319125

Reinforcement studying (RL) is an artificial intelligence (AI) paradigm that can be used to decorate content material retrieval systems, which frequently rent supervised gaining knowledge of strategies. It explains how traditional methods of content retrieval often struggle with providing accurate and relevant search results, and how reinforcement learning offers a potential solution by continuously learning and adapting to user behavior and preferences. The abstract also highlights the benefits and challenges of using this approach, as well as the potential impact it could have on the field of information retrieval. It could permit greater scalability and advanced user experience. The proposed method is predicted to surpass existing content material retrieval structures in terms of content material accuracy and efficiency. © 2023 IEEE.

关键词： Artificial Intelligence Data Mining Information Retrieval Optimization Personalization Search Algorithms User Experience

来源：评论

学校读者我要写书评

暂无评论

Exp[licit] An Educational Robot Modeling Software based on Exponential Maps

Exp[licit] An Educational Robot Modeling Software based on E...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Johannes Lachner Moses C. Nah Stefano Stramigioli Neville Hogan Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge MA USA Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA USA Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

Deriving a robot’s equations of motion typically requires placing multiple coordinate frames, commonly using the Denavit-Hartenberg convention to express the kinematic and dynamic relationships between segments. This paper presents an alternative using the differential geometric method of Exponential Maps, which reduces the number of coordinate frame choices to two. The traditional and differential geometric methods are compared, and the conceptual and practical differences are detailed. The open-source software, $\operatorname{Exp}[\text { licit }]^{\mathrm{TM}}$, based on the differential geometric method, is introduced. It is intended for use by researchers and engineers with basic knowledge of geometry and robotics and aims to serve as a supportive resource during the study of differential geometric approaches. Code snippets and an example application are provided to demonstrate the benefits of the differential geometric method and assist users to get started with the software.

关键词： Knowledge engineering Geometry Mechatronics Educational robots Robot kinematics Motion segmentation Dynamics

来源：评论

学校读者我要写书评

暂无评论

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning 7

Impact of CLAHE-based image enhancement for diabetic retinop...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Hayati, Mira Muchtar, Kahlil Roslidar Maulina, Novi Syamsuddin, Irfan Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-Aided diagnosis of diabetic retinopathy. © 2022 Elsevier B.V.. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2025年

作者： Fidêncio, Aline Xavier Grün, Felix Klaes, Christian Iossifidis, Ioannis Robotics and BCI Laboratory Institute of Computer Science Ruhr West University of Applied Sciences Mülheim an der Ruhr Germany Faculty of Electrical Engineering and Information Technology Ruhr University Bochum Bochum Germany KlaesLab Department of Neurosurgery University Hospital Knappschaftskrankenhaus Ruhr University Bochum Bochum Germany Faculty of Computer Science Ruhr University Bochum Bochum Germany

Brain-computer interfaces (BCIs) are developed for individuals with motor disabilities to offer alternative methods of communication, such as controlling and interacting with external devices. These systems are designed to improve quality of life, particularly for those with limited mobility. BCIs that rely on non-invasive recordings, such as electroencephalography (EEG), have been developed for a wide range of scenarios due to their practicality and safety. However, BCI performance is often limited by non-stationarities in the EEG data, which can arise from changes in the subject’s mental state or device characteristics, such as electrode impedance. These challenges motivate ongoing research into the development of adaptive BCIs capable of handling such variations. Over the past years, the interest in using the so-called error-related potentials (ErrPs) to improve BCI performance has increased. This is because ErrPs represent the neural response to both self-made and external errors and can be measured using non-invasive techniques. These signals have been combined with different BCI paradigms and used in different works to improve BCI performance via error correction or adaptation. In this work we introduce and explore a new approach for creating an adaptive ErrP-based BCI by evaluating the use of reinforcement learning (RL). This study demonstrates the feasibility of a RL-driven adaptive brain-computer interface (BCI) framework that integrates error-related potentials (ErrPs) and motor imagery. By employing two RL agents to dynamically adapt to EEG non-stationarities, we validate the framework on both a publicly available motor imagery dataset and using a novel experimental protocol involving a fast-paced game designed to enhance user engagement. Results highlight the framework’s potential: RL agents successfully learned control policies from user interactions, achieving robust performance across datasets. However, a critical finding emerged from the game-based p

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

RIS-Enabled Joint Near-Field 3D Localization and Synchronization in SISO Multipath Environments

arXiv

引用

arXiv 2024年

作者： Yan, Han Chen, Hua Liu, Wei Yang, Songjie Wang, Gang Yuen, Chau The Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China The Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo315211 China The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China China The School of Electrical and Electronics Engineering Nanyang Technological University Singapore

Reconfigurable Intelligent Surfaces (RIS) show great promise in the realm of 6th generation (6G) wireless systems, particularly in the areas of localization and communication. Their cost-effectiveness and energy efficiency enable the integration of numerous passive and reflective elements, enabling near-field propagation. In this paper, we tackle the challenges of RIS-aided 3D localization and synchronization in multipath environments, focusing on the near-field of mmWave systems. Specifically, our approach involves formulating a maximum likelihood (ML) estimation problem for the channel parameters. To initiate this process, we leverage a combination of canonical polyadic decomposition (CPD) and orthogonal matching pursuit (OMP) to obtain coarse estimates of the time of arrival (ToA) and angle of departure (AoD) under the far-field approximation. Subsequently, distances are estimated using l1-regularization based on a near-field model. Additionally, we introduce a refinement phase employing the spatial alternating generalized expectation maximization (SAGE) algorithm. Finally, a weighted least squares approach is applied to convert channel parameters into position and clock offset estimates. To extend the estimation algorithm to ultra-large (UL) RIS-assisted localization scenarios, it is further enhanced to reduce errors associated with far-field approximations, especially in the presence of significant near-field effects, achieved by narrowing the RIS aperture. Moreover, the Cramér-Rao Bound (CRB) is derived and the RIS phase shifts are optimized to improve the positioning accuracy. Numerical results affirm the efficacy of the proposed estimation algorithm. © 2024, CC BY.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing

arXiv

引用

arXiv 2022年

作者： Nguyen, Hai M. Chu, Nam H. Nguyen, Diep N. Hoang, Dinh Thai Nguyen, Van-Dinh Hà, Minh Hoàng Dutkiewicz, Eryk Krunz, Marwan The School of Electrical and Data Engineering University of Technology Sydney Australia The College of Engineering and Computer Science VinUniversity Hanoi Viet Nam The ORLab Faculty of Computer Science Phenikaa University Hanoi Viet Nam The Department of Electrical and Computer Engineering University of Arizona United States

Federated Learning (FL) with quantization and deliberately added noise over wireless networks is a promising approach to preserve user differential privacy while reducing wireless resources. Specifically, an FL learning process can be fused with quantized Binomial mechanism-based updates contributed by multiple users to reduce the communication overhead/cost and to protect the privacy of participating users. However, optimizing quantization parameters, communication resources (e.g., transmit power, bandwidth, and quantization bits), and the added noise to guarantee the differential privacy requirement and performance of the learned FL model remains an open and challenging problem. This article aims to jointly optimize the level of quantization, parameters of the Binomial mechanism, and communication resources so as to maximize the convergence rate under the constraints of the wireless network and differential privacy (DP) requirement. To that end, we first derive a novel DP budget estimation of the FL with quantization and Binomial noise that is tighter than the state-of-the-art bound. We then analyze the relationship between the convergence rate and the transmit power, the bandwidth, the transmission time, and the quantization/noise parameters and provide a theoretical bound on the convergence rate. This theoretical bound is decomposed into two components, including the variance of the global gradient and an upper bound on the quadratic bias that can be minimized by optimizing the communication resources, quantization, and added noise parameters. The resulting optimization turns out to be a Mixed-Integer Non-linear Programming (MINLP) problem. To tackle it, we first transform this MINLP problem into a new problem whose solutions are proved to be the optimal solutions of the original one. We then propose an approximate algorithm to solve the transformed problem with an arbitrary relative error guarantee. Extensive simulations show that under the same wireless resour

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Automating Real-Time Data Analysis with Machine Learning Algorithms 3

Automating Real-Time Data Analysis with Machine Learning Alg...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Bhoite, Sonali P. Singh, Satendra Naval, Preeti Panduranga Rao, M.V. Bhushan, Bharat Indira, G. Vishwakarma Institute of Information Technology Department of Information Technology Pune India Vivekananda Global University Department of Mechanical Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India

ISBN: (纸本)9798350319125

Device getting-to-know algorithms enable the automation of actual-time information analysis, permitting agencies to behave on well-timed insights and optimize selection-making. By leveraging predictive models, companies can increase customized services, optimize operations, and obtain a competitive area. This paper discusses how device learning algorithms can automate real-time facts evaluation and the ways such algorithms can be used to uncover developments, locate anomalies, and enhance models. Moreover, the paper explores how applying device mastering algorithms can boost accuracy and efficiency in data evaluation, in addition to providing businesses with new opportunities for innovation. © 2023 IEEE.

关键词： Information analysis

来源：评论

学校读者我要写书评

暂无评论

Input Impedance and Performance Analysis of Series-Fed Microstrip Patch Array Antenna

Input Impedance and Performance Analysis of Series-Fed Micro...

引用

2022 International Conference on Power, Energy and Innovations, ICPEI 2022

作者： Phakaew, Thipamas Pongthavornkamol, Tiwat Thaiwirot, Wanwisa Chalermwisutkul, Suramate The Sirindhorn International Thai-German Graduate School of Engineering King Mongkut's U. of Technology North Bangkok Bangkok Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Pathum Thani Thailand King Mongkut's U. of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand

ISBN: (数字)9781665460194

ISBN: (纸本)9781665460194

This paper presents input impedance and performance analysis of a series-fed 2×1 patch array antenna operating at 9.55 GHz. Effects of substrate's dielectric constant and height are discussed. Input impedance is optimized step by step from a single patch to a 2×1 array. Low impedance patches provide higher gain at the cost of increased capacitive coupling between the elements. Consequently, input impedance at the operating frequency is affected by the higher resonant mode. Finally, a technique to mitigate the coupling between the patches is proposed. With the proposed technique, the higher resonant mode can be eliminated so that the 2×1 array can easily be matched and operates with the correct patch array mode. © 2022 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Image Classification Using Machine Learning and Local Binary Patterns Features

Diabetic Retinopathy Image Classification Using Machine Lear...

引用

International Symposium on electrical and Electronics engineering (ISEEE)

作者： Mihaela Miron Anisia Culea-Florescu Simona Moldovanu Department of Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania Department of Electronics and Telecommunications Faculty of Automation Computers Electrical Engineering and Electronics Dunarea de Jos University of Galati Galati Romania

Diabetic Retinopathy (DR) is a condition caused by diabetes that affects the blood vessels in the retina. Detecting the disease early and providing appropriate treatment are crucial in slowing its progression. Therefore, there is great potential in utilizing Machine Learning (ML) to improve the identification and monitoring of DR development in patients. Our study aims to explore the performance of six ML algorithms, namely Random Forest (RF), Adaptive Boosting (AB), K-Nearest Neighbor (K-NN), Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), and Quadratic Discriminant Analysis (QDA), in two binary classifications involving three classes: non-diabetic retinopathy (NoDR), moderate retinopathy (MR), and severe retinopathy (SV). These ML algorithms were applied to ten features extracted using local binary patterns (LBP). The first classification task involved distinguishing between NoDR and MR, while the second task involved differentiating between NoDR and SV. The RF technique achieved the highest classification accuracy, with 0.912 for the first task and 0.94 for the second task.

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：