检索结果-内蒙古大学图书馆

27th International Conference on Knowledge Based and Intelligent Information and engineering Sytems, KES 2023

作者： Abdulwahid, Nibras Othman Akrout, Sana Fakhfakh Amor, Ikram Amous Ben Miracl Laboratory Enet'com Technopole of Sfax Sfax University Road Tunis km 10 Sfax3018 Tunisia Department of Information Systems College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj11942 Saudi Arabia

The traditional educational systems in certain nations, such as those in the Arab world, use the previous year's scores to forecast academic achievement. Meanwhile, the science, technology, engineering, arts and mathematics (STEAM) educational system also considers the student's talents and interests, in addition to their test results, for each of the years of study used to forecast academic achievement. However, despite the numerous variables that could potentially impact a student's future profession, the STEAM educational system accurately predicts the academic achievement of students in five to seven broad majors. A smart model, data, generative, factors (DGF), has been proposed to assign a specific major for each student based on their academic background, interests, skills, and main influencing factors. The DGF model uses the supervised deep neural network and is trained by the generative adversarial network (GAN) algorithm. The DGF model has the capability to predict a specific major among 17 different majors for every student, with a high learning performance (1.4133), a plausible error rate (0.0046), a rational number of learning epochs (206), and an optimal accuracy of 99.99%. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Deep Learning Depp neural network Generative Adversarial Network algorithm predicting student's academic performance STEAM Education

来源：评论

学校读者我要写书评

暂无评论

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Secondary Frequency Control of Dual-Port Grid Forming Control

Secondary Frequency Control of Dual-Port Grid Forming Contro...

引用

Power Tech Conference

作者： Irina Subotic Dominic Groß Automatic Control Laboratory ETH Zürich Switzerland Department of Electrical and Computer Engineering University of Wisconsin-Madison USA

Grid-forming converters are widely envisioned to be the cornerstone of future converter-dominated power systems. However, standard grid forming (GFM) control strategies assume a fully controllable source with enough headroom behind the converter and only implicitly address renewable generation limits through the converter limits. This can lead to instabilities on time scales of both primary and secondary frequency control and jeopardize the safe and reliable operation of electric power systems. In this work, we leverage the recently proposed dual-port GFM control that maps power imbalances in the grid to the power generation interfaced by the power converter. We show that this mechanism allows for considering and transparently addressing limits of renewable generation (e.g., solar photovoltaics and wind) in primary and secondary frequency control. We illustrate that renewable generation using dual-port GFM control can directly integrate into prevailing secondary control methods such as automatic generation control (AGC). Moreover, we discuss the limitations of standard AGC when one or more areas of a power system are dominated by renewable generation and propose an anti-windup strategy to address the power generation limits of renewables. Finally, we verify our findings in a time-domain, electromagnetic transient (EMT) simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Zeng, Siliang Li, Chenliang Garcia, Alfredo Hong, Mingyi Department of Electrical and Computer Engineering University of Minnesota MN United States Department of Industrial and Systems Engineering Texas A&M University TX United States

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving. However, the structure of an expert's preferences implicit in observed actions is closely linked to the expert's model of the environment dynamics (i.e. the "world" model). Thus, inaccurate models of the world obtained from finite data with limited coverage could compound inaccuracy in estimated rewards. To address this issue, we propose a bi-level optimization formulation of the estimation task wherein the upper level is likelihood maximization based upon a conservative model of the expert's policy (lower level). The policy model is conservative in that it maximizes reward subject to a penalty that is increasing in the uncertainty of the estimated model of the world. We propose a new algorithmic framework to solve the bi-level optimization problem formulation and provide statistical and computational guarantees of performance for the associated optimal reward estimator. Finally, we demonstrate that the proposed algorithm outperforms the state-of-the-art offline IRL and imitation learning benchmarks by a large margin, over the continuous control tasks in MuJoCo and different datasets in the D4RL benchmark. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Control:A Graph-Theoretic Perspective

引用

Journal of systems Science & Complexity 2021年第5期34卷 1973-2002页

作者： CHEN Fei REN Wei State Key Laboratory of Synthetical Automation for Process Industries Northeastern UniversityShenyang 110004China School of Control Engineering Northeastern University at QinhuangdaoQinhuangdao 066004China. Department of Electrical and Computer Engineering University of CaliforniaRiversideCA 92521USA

Progress in development of multi-agent control is *** approaches for multiagent control,estimation,and optimization are discussed in a systematic way with particular emphasis on the graph-theoretic *** is paid to the design of multi-agent systems via Laplacian dynamics,as well as the role of the graph Laplacian spectrum,the challenges of unbalanced digraphs,and consensus-based estimation of graph *** emergent issues,e.g.,distributed optimization,distributed average tracking,and distributed network games,are also reported,which have witnessed extensive development *** are over 200 references listed,mostly to recent contributions.

关键词： Consensus cooperative control distributed average tracking distributed optimization multi-agent system

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristic computing knacks for target angle estimation in monostatic radar system with coprime arrays

引用

Ain Shams engineering Journal 2024年第5期15卷

作者： Akbar, Sadiq Sohail, Muhammad Asif Zahoor Raja, Muhammad Zaman, Fawad Ullah, Rizwan Abdul Rehman Khan, Muhammad Ajavakom, Nopdanai Phanomchoeng, Gridsada Department of Mechanical Engineering Faculty of Engineering Chulalongkorn University Bangkok10330 Thailand Hefei230026 China Future Technology Research Center National Yunlin University of Science and Technology Douliou64002 Taiwan Department of Electrical & Computer Engineering COMSATS University Islamabad Islamabad44000 Pakistan Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok10330 Thailand Department of Electrical & Computer Engineering COMSATS University Islamabad Attock Campus 43600 Pakistan Human-Robot Collaboration and Systems Integration Research Unit Faculty of Engineering Chulalongkorn University Bangkok10330 Thailand

Angle estimation of signals received by antenna arrays is a key step in adaptive beamforming, used to detect and locate targets in space. It is desirable to reduce costs by employing a smaller number of antennas while maintaining efficiency and degrees of freedom (DOF) of the system at the same time. Co-prime antenna arrays not only circumvent the operational constraints of cost and hardware complexity, but also boost the DOF by utilizing far fewer antennas as compared to traditional uniform linear arrays. In this paper, meta-heuristic computing paradigm for estimating arrival angle of targets with co-prime arrays incorporated in monostatic radar is proposed. The system's autocorrelation and Mean Square Error (MSE) are used for fitness function optimized by global/local search with Genetic Algorithm (GA) and Pattern Search (PS). Monte Carlo simulations are performed to evaluate the performance via estimation accuracy, MSE, and computational cost for varying numbers of impinging waves. © 2024 THE AUTHORS

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep learning for automatically predicting early haematoma expansion in Chinese patients

引用

Stroke & Vascular Neurology 2021年第4期6卷 610-614,I0067-I0072页

作者： Jia-wei Zhong Yu-jia Jin Zai-jun Song Bo Lin Xiao-hui Lu Fang Chen Lu-sha Tong Department of Neurology Zhejiang University School of Medicine Second Affiliated HospitalHangzhouChina College of Computer Science and Technology Zhejiang UniversityHangzhouChina State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University School of Mechanical EngineeringHangzhouChina Department of Computer Science and Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina

Background and purpose Early haematoma expansion is determinative in predicting outcome of intracerebral haemorrhage(ICH)*** aims of this study are to develop a novel prediction model for haematoma expansion by applying deep learning model and validate its prediction *** Data of this study were obtained from a prospectively enrolled cohort of patients with primary supratentorial ICH from our *** developed a deep learning model to predict haematoma expansion and compared its performance with conventional non-contrast CT(NCCT)*** evaluate the predictability of this model,it was also compared with a logistic regression model based on haematoma volume or the BAT *** A total of 266 patients were finally included for analysis,and 74(27.8%)of them experienced early haematoma *** deep learning model exhibited highest C statistic as 0.80,compared with 0.64,0.65,0.51,0.58 and 0.55 for hypodensities,black hole sign,blend sign,fluid level and irregular shape,*** the C statistics for swirl sign(0.70;p=0.211)and heterogenous density(0.70;p=0.141)were not significantly higher than that of the deep learning ***,the predictive value for the deep learning model was significantly superior to that of the logistic model of haematoma volume(0.62;p=0.042)and the BAT score(0.65;p=0.042).Conclusions Compared with the conventional NCCT markers and BAT predictive model,the deep learning algorithm showed superiority for predicting early haematoma expansion in ICH patients.

关键词： patients expansion predicting

来源：评论

学校读者我要写书评

暂无评论

Learning Cross-Modal Audiovisual Representations with Ladder Networks for Emotion Recognition

Learning Cross-Modal Audiovisual Representations with Ladder...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Lucas Goncalves Carlos Busso Department of Electrical and Computer Engineering Multimodal Signal Processing (MSP) Laboratory The University of Texas at Dallas Richardson TX USA

Representation learning is a challenging, but essential task in audiovisual learning. A key challenge is to generate strong cross-modal representations while still capturing discriminative information contained in unimodal features. Properly capturing this information is important to increase accuracy and robustness in audiovisual tasks. Focusing on emotion recognition, this study proposes novel cross-modal ladder networks to capture modality-specific information while building strong cross-modal representations. Our method utilizes representations from a backbone network to implement unsupervised auxiliary tasks to reconstruct intermediate layer representations across the acoustic and visual networks. The skip connections between the cross-modal encoder and decoder provide powerful modality-specific and multimodal representations for emotion recognition. Our model on the CREMA-D corpus achieves high performance with precision, recall, and F1 scores over 80% on a six-class problem.

关键词： Representation learning Emotion recognition Visualization Focusing Speech recognition Signal processing Acoustics

来源：评论

学校读者我要写书评

暂无评论

An Insight into the Dynamics of a Dual Active Bridge

An Insight into the Dynamics of a Dual Active Bridge

引用

IEEE Transportation Electrification Conference and Expo (ITEC)

作者： Ezekiel Olayiwola Arogunjo Joseph Olorunfemi Ojo Electrical and Computer Engineering Department Laboratory for Electric Machines and Power Electronics Tennessee Technological University Cookeville TN USA

This paper aims at analyzing the effect of the zero dynamics of the Dual Active Bridge Isolated Bidirectional dc-dc converter (DAB) on the dynamics of the complete DAB system. It also explains its influence on controller design for the DAB system. In carrying out these analyses, the state space model of the DAB, as well as the first harmonic approximation (FHA) of the model are derived. The ZVS and the stability analysis of the system are undertaken based on the FHA model of the system. The system is shown to be stable for a constant output voltage operation for the entire power range while it is unstable for the constant power load (CPL) operation for load demands close to the system maximum power. It is also shown that the transformer winding currents are part of the zero dynamic states and are always stable regardless of the operating conditions of the system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Level Speaker Representation for Target Speaker Extraction

Multi-Level Speaker Representation for Target Speaker Extrac...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Ke Li, Junjie Wang, Shuai Wei, Yangjie Wang, Yi Wang, Yannan Li, Haizhou Key Laboratory of Intelligent Computing in Medical Image Northeastern University China SDS SRIBD The Chinese University of Hong Kong Shenzhen China The Hong Kong Polytechnic University Hong Kong Tencent Ethereal Audio Lab Tencent Shenzhen China University of Bremen Germany Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (纸本)9798350368741

Target speaker extraction (TSE) relies on a reference cue of the target to extract the target speech from a speech mixture. While a speaker embedding is commonly used as the reference cue, such embedding pre-trained with a large number of speakers may suffer from confusion of speaker identity. In this work, we propose a multi-level speaker representation approach, from raw features to neural embeddings, to serve as the speaker reference cue. We generate a spectral-level representation from the enrollment magnitude spectrogram as a raw, low-level feature, which significantly improves the model's generalization capability. Additionally, we propose a contextual embedding feature based on cross-attention mechanisms that integrate frame-level embeddings from a pre-trained speaker encoder. By incorporating speaker features across multiple levels, we significantly enhance the performance of the TSE model. Our approach achieves a 2.74 dB improvement and a 4.94% increase in extraction accuracy on Libri2mix test set over the baseline. © 2025 IEEE.

关键词： Cocktail party problem selective auditory attention speaker confusion speaker feature target speaker extraction

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：