检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Qi, Xiaoming Zhang, Jingyang Fu, Huazhu Yang, Guanyu Li, Shuo Jin, Yueming Department of Biomedical Engineering Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Ministry of Education Nanjing China Institute of High Performance Computing A*STAR Singapore Departments Biomedical Engineering and Computer and Data Science Case Western Reserve University Cleveland United States

Federated continual learning (FCL) offers an emerging pattern to facilitate the applicability of federated learning (FL) in real-world scenarios, where tasks evolve dynamically and asynchronously across clients, especially in medical scenario. Existing server-side FCL methods in nature domain construct a continually learnable server model by client aggregation on all-involved tasks. However, they are challenged by: (1) Catastrophic forgetting for previously learned tasks, leading to error accumulation in server model, making it difficult to sustain comprehensive knowledge across all tasks. (2) Biased optimization due to asynchronous tasks handled across different clients, leading to the collision of optimization targets of different clients at the same time steps. In this work, we take the first step to propose a novel server-side FCL pattern in medical domain, Dynamic Allocation Hypernetwork with adaptive model recalibration (FedDAH). It is to facilitate collaborative learning under the distinct and dynamic task streams across clients. To alleviate the catastrophic forgetting, we propose a dynamic allocation hypernetwork (DAHyper) where a continually updated hypernetwork is designed to manage the mapping between task identities and their associated model parameters, enabling the dynamic allocation of the model across clients. For the biased optimization, we introduce a novel adaptive model recalibration (AMR) to incorporate the candidate changes of historical models into current server updates, and assign weights to identical tasks across different time steps based on the similarity for continual optimization. Extensive experiments on the AMOS dataset demonstrate the superiority of our FedDAH to other FCL methods on sites with different task streams. The code is available:https://***/jinlab-imvr/FedDAH. © 2025, CC BY-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Enhance Energy Using Bio-Inspired Algorithms in Manet: An Overview

Enhance Energy Using Bio-Inspired Algorithms in Manet: An Ov...

引用

Electrical engineering and Automatic Control (ICEEAC), International Conference on

作者： Abdelmalek Djihene Boumedjout Amal Kies Ali dept. Computer science USTO Oran Algeria dept. Systems Engineering ENPO Maurice Audin Oran Algeria

ISBN: (数字)9798350349740

ISBN: (纸本)9798350349757

The limited power availability in Mobile Ad hoc Networks (MANETs) poses a fundamental challenge, as node instability and the lack of power supply contribute to reduced network lifetime, impacting MANET performance. In recent years, there has been a growing interest in exploring Artificial Intelligence approaches, particularly bio-inspired algorithms, for MANET routing due to their adaptability and robustness. These approaches have shown promise in minimizing energy consumption, reducing overhead, and improving overall network efficiency. This paper provides an overview of enhancing energy efficiency using bio-inspired algorithms through the application of various meta-heuristic approaches in MANET routing. This paper provides a synthesis of existing research on bio-inspired algorithms in MANET routing, highlighting their effectiveness in addressing energy-related challenges. Furthermore, the paper outlines potential future research directions, including the ex- ploration of hybrid algorithms and the integration of machine learning techniques to further optimize energy efficiency in MANETs.

关键词： Machine learning algorithms Heuristic algorithms Metaheuristics Machine learning Routing Ad hoc networks Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin Framework for Reinforcement Learning with Real-Time Self-Improvement via Human Assistive Teleoperation

arXiv

引用

arXiv 2024年

作者： Olayemi, Kabirat Van, Mien Maguire, Luke McLoone, Sean The Centre for Intelligent Autonomous Manufacturing Systems School of Electronics Electrical Engineering and Computer Science Queens University Belfast United Kingdom

Reinforcement Learning (RL) or Deep Reinforcement Learning (DRL) is a powerful approach to solving Markov Decision Processes (MDPs) when the model of the environment is not known a priori. However, RL models are still faced with challenges such as handling covariate shifts and ensuring the quality of human demonstration. To address these challenges and further advance DRL models, our work develops a human-in-the-loop DRL framework via digital twin that leverages human intelligence after deployment to retrain the DRL model in real time. First, we develop a pre-trained model fully based on learning through trial and error in the simulated environment allowing scalability and automation while eliminating variability and biases that can come from subjective human guidance. Second, instead of deploying the trained model directly on the UGV, we create a digital twin which controls the physical UGV from the virtual environment. Third, to allow continuous learning without catastrophic forgetting, we introduce the ability of the model to self-improve with the help of small human guidance at the start of the retraining. We test the performance of our proposed model in both simulation and real-world environments with both static and dynamic obstacles. The results indicate that our proposed approach not only outperforms the baseline models in terms of reward accumulation but also demonstrates superior training efficiency. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Algorithm with Deep Learning Based Secured Lifetime Maximization in Vehicular Adhoc Networks

Metaheuristic Algorithm with Deep Learning Based Secured Lif...

引用

International Conference on computer and Communications Technologies (ICCCT)

作者： Manickavasagan V Susila Sakthy S Department of Computer Science and Business Systems Sri Sairam Engineering College Chennai India Department of Information Technology Sri Sairam Engineering College Chennai India

ISBN: (数字)9798331537579

ISBN: (纸本)9798331537586

Wireless Sensor Networks (WSN)s along with Vehicular Adhoc Networks (VANETs) form two vital parts of contemporary smart systems because they help collect information and enable real-time response and decision-making in multiple applications. The effectiveness of these networks remains restricted due to their fluid topology designs as well as network security dangers and operational performance boundaries. The evaluation discusses artificial intelligence methods linked with metaheuristic approaches which optimize secure lifetimes for VANETs and WSNs. Energy consumption strategies and resource allocation as well as routing methods are reviewed using multiple metaheuristic algorithms. The research examines combination architectures of deep learning systems which handle real-time operational safety and efficiency while utilizing metaheuristic optimization for network optimization. A thorough evaluation of current methods shows their benefits together with their weaknesses as well as possible next steps for research. Research results showcase that the combination improves both WSNs and VANET network performance in terms of security and reliability.

关键词： Deep learning Wireless sensor networks Accuracy Metaheuristics Decision making Vehicular ad hoc networks Authentication Real-time systems Safety Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

So Far Yet So Near: Time Series Data Augmentation with Exploring non-Semantic Boundaries based on Reinforcement Learning

So Far Yet So Near: Time Series Data Augmentation with Explo...

引用

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

作者： Haoran Li Zhibo Zhang Jiarong Kang Xun Jiang Xiaoli Gong Jin Zhang Zhe Sun Andrzej Cichocki College of Computer Science Nankai University Tianjin China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Medicine and Faculty of Health Data Science Juntendo University Japan Polish Academy of Science Systems Research Institute Warsaw Poland

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://***/NKU-EmbeddedSystem/FreqSYN.

关键词： Semantics Time series analysis Signal processing algorithms Reinforcement learning Data augmentation Prediction algorithms Path planning Data models Kernel Speech processing

来源：评论

学校读者我要写书评

暂无评论

Interpretable Feature Optimization for Sadness Recognition in Speech Emotion Analysis

Interpretable Feature Optimization for Sadness Recognition i...

引用

International IEEE Conference on Intelligent systems, IS

作者： Siddharth Yayavaram Arnav Yayavaram Jabez Christopher Vasan Arunachalam Department of Computer Science and Information Systems BITS Pilani Hyderabad Telangana Department of Civil Engineering BITS Pilani Hyderabad Telangana

ISBN: (数字)9798350350982

ISBN: (纸本)9798350350999

The paper introduces a new interpretable intelligent system aimed at optimizing feature selection for Speech Emotion Recognition (SER), specifically targeting the emotion of ‘Sadness' across multiple datasets. The system employs Genetic Algorithm (GA) to improve classification performance for ‘Sadness' by maximizing the class-wise F1-score. The framework's efficacy is validated across four prominent speech emotion recognition datasets (Ravdess, Savee, Emodb, Tess), and selected features are analyzed using Shapley values to ascertain their significance in achieving high F1-scores. Experiments use a 10-fold cross-validation with a 90:10 split for training and testing data, while hyperparameters are fine-tuned across different algorithms. The framework's explainability analysis is depicted through beeswarm plots to aggregate these results. Additionally, the study analyzes the frequency distribution of selected feature types and how they manifest. The study's focus on explainability provides insights into the significance of selected features in recognizing sadness in speech, thereby paving the way for enhanced human-computer interaction systems.

关键词： Training Emotion recognition Speech recognition Speech enhancement Feature extraction Vectors Intelligent systems Optimization Genetic algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

There are More Fish in the Sea: Automated Vulnerability Repair via Binary Templates

arXiv

引用

arXiv 2024年

作者： Lin, Bo Wang, Shangwen Chen, Liqian Mao, Xiaoguang Key Laboratory of Software Engineering for Complex Systems College of Computer Science and Technology National University of Defense Technology Changsha China

As software vulnerabilities increase in both volume and complexity, vendors often struggle to repair them promptly. Automated vulnerability repair has emerged as a promising solution to reduce the burden of manual debugging and fixing activities. However, existing techniques exclusively focus on repairing the vulnerabilities at the source code level, which has various limitations. For example, they are not applicable to those (e.g., users or security analysts) who do not have access to the source code. Consequently, this restricts the practical application of these techniques, especially in cases where vendors are unable to provide timely patches. In this paper, we aim to address the above limitations by performing vulnerability repair at binary code level, and accordingly propose a template-based automated vulnerability repair approach for Java binaries. Built on top of the literature, we collect fix templates from both existing template-based automated program repair approaches and vulnerability-specific analyses, which are then implemented for the Java binaries. Our systematic application of these templates effectively mitigates vulnerabilities: experiments on the Vul4J dataset demonstrate that TemVUR successfully repairs 11 vulnerabilities, marking a notable 57.1% improvement over current repair techniques. Moreover, TemVUR securely fixes 66.7% more vulnerabilities compared to leading techniques (15 vs. 9), underscoring its effectiveness in mitigating the risks posed by these vulnerabilities. To assess the generalizability of TemVUR, we curate the ManyVuls4J dataset, which goes beyond Vul4J to encompass a wider diversity of vulnerabilities. With 30% more vulnerabilities than its predecessor (increasing from 79 to 103), ManyVuls4J serves as a robust benchmark for evaluating the performance of TemVUR. The evaluation on ManyVuls4J reaffirms TemVUR’s effectiveness and generalizability across a diverse set of real-world vulnerabilities. Copyright © 2024, The Authors.

关键词： Program debugging

来源：评论

学校读者我要写书评

暂无评论

Single-Model Attribution for Spoofed Speech via Vocoder Fingerprints in an Open-World Setting

arXiv

引用

arXiv 2024年

作者： Pizarro, Matías Laszkiewicz, Mike Kolossa, Dorothea Fischer, Asja Faculty of Computer Science Ruhr University Bochum Germany Electronic Systems of Medical Engineering Technische Universität Berlin Germany

As speech generation technology advances, so do the potential threats of misusing spoofed speech signals. One way to address these threats is by attributing the signals to their source generative model. In this work, we are the first to tackle the single-model attribution task in an open-world setting, that is, we aim at identifying whether spoofed speech signals from unknown sources originate from a specific vocoder. We show that the standardized average residual between audio signals and their low-pass filtered or EnCodec filtered versions can serve as powerful vocoder fingerprints. The approach only requires data from the target vocoder and allows for simple but highly accurate distance-based model attribution. We demonstrate its effectiveness on LJSpeech and JSUT, achieving an average AUROC of over 99% in most settings. The accompanying robustness study shows that it is also resilient to noise levels up to a certain degree. © 2024, CC BY.

关键词： Low pass filters

来源：评论

学校读者我要写书评

暂无评论

Exploring Large Language Models for Verilog Hardware Design Generation

Exploring Large Language Models for Verilog Hardware Design ...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Erik H. D'Hollander Ewout Danneels Karel-Brecht Decorte Senne Loobuyck Arne Vanheule Ian Van Kets Dirk Stroobandt Department of Electronics and Information Systems Ghent University Ghent Belgium School of Computer Science Engineering Ghent University Ghent Belgium

ISBN: (数字)9798350364606

ISBN: (纸本)9798350364613

Deep Learning Large Language Models (LLMs) have the potential to automate and simplify code writing tasks. One of the emerging applications of LLMs is hardware design, where natural language interaction can be used to generate, annotate, and correct code in a Hardware Description Language (HDL), such as Verilog. This work provides an overview of the current state of using LLMs to generate Verilog code, highlighting their capabilities, accuracy, and techniques to improve the design quality. It also reviews the existing benchmarks to evaluate the correctness and quality of generated HDL code, enabling a fair comparison of different models and strategies.

关键词： Training Codes Accuracy Reviews Large language models Natural languages Hardware

来源：评论

学校读者我要写书评

暂无评论

Non-central panorama indoor dataset

arXiv

引用

arXiv 2024年

作者： Berenguel-Baeta, Bruno Bermudez-Cameo, Jesus Guerrero, Jose J. Instituto de Investigacion en Ingenieria de Aragon Department of Computer Science and Systems Engineering University of Zaragoza Zaragoza Spain

Omnidirectional images are one of the main sources of information for learning based scene understanding algorithms. However, annotated datasets of omnidirectional images cannot keep the pace of these learning based algorithms development. Among the different panoramas and in contrast to standard central ones, non-central panoramas provide geometrical information in the distortion of the image from which we can retrieve 3D information of the environment [2]. However, due to the lack of commercial non-central devices, up until now there was no dataset of these kinds of panoramas. In this data paper, we present the first dataset of non-central panoramas for indoor scene understanding. The dataset is composed by 2574 RGB non-central panoramas taken in around 650 different rooms. Each panorama has associated a depth map and annotations to obtain the layout of the room from the image as a structural edge map, list of corners in the image, the 3D corners of the room and the camera pose. The images are taken from photorealistic virtual environments and pixel-wise automatically annotated. © 2024, CC BY.

关键词： computer vision

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：