检索结果-内蒙古大学图书馆

Transfer Learning for Russian Handwriting Recognition

学校读者我要写书评

暂无评论

Transfer Learning for Russian Handwriting Recognition

International Conference on Telecommunications and Signal Processing (TSP)

作者： Andrey Levkov Dmitry Kaplun Anastasiia Safonova Depart. of Computer Engineering St. Petersburg Electrotechnical University "LETI" St. Petersburg Russia Depart. of Automation and Control Processes St. Petersburg Electrotechnical University "LETI" St. Petersburg Russia Depart. of Information Systems St. Petersburg Electrotechnical University "LETI" St. Petersburg Russia

Handwriting recognition is one of the most important tasks in computer vision. Despite the variety of methods and algorithms used for text recognition in various languages, the recognition of handwritten Russian words is still a completely unsolved problem, which keeps the relevance of this topic. This paper proposes the application of a convolutional neural network (CNN) to the task of recognizing the 100 most frequently used Russian words, trained on a new unique dataset. A unique algorithm for extracting Russian handwritten words from forms was applied to obtain a new dataset. The paper also presents the results of a comparison of such powerful models as VGG-16, VGG-19, ResNet-50, and ResNet-101, which were trained using transfer learning technology. The best results were shown by VGG-16 with 98.7% accuracy, and the worst results were shown by ResNet-50 with 80% accuracy.

关键词：

User Experience Evaluation in Virtual Reality based on Subjective Feelings and Physiological Signals

学校读者我要写书评

暂无评论

User Experience Evaluation in Virtual Reality based on Subje...

2020 Engineering Reality of Virtual Reality Conference, ERVR 2020

作者： Niu, Yunfang Wang, Danli Wang, Ziwei Sun, Fan Yue, Kang Zheng, Nan State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Computer and Information Technology Liaoning Normal University Dalian China

At present, the research on emotion in the virtual environment is limited to the subjective materials, and there are very few studies based on objective physiological signals. In this article, the authors conducted a user experiment to study the user emotion experience of virtual reality (VR) by comparing subjective feelings and physiological data in VR and two-dimensional display (2D) environments. First, they analyzed the data of self-report questionnaires, including Self-assessment Manikin (SAM), Positive And Negative Affect Schedule (PANAS) and Simulator Sickness Questionnaire (SSQ). The result indicated that VR causes a higher level of arousal than 2D, and easily evokes positive emotions. Both 2D and VR environments are prone to eye fatigue, but VR is more likely to cause symptoms of dizziness and vertigo. Second, they compared the differences of electrocardiogram (ECG), skin temperature (SKT) and electrodermal activity (EDA) signals in two circumstances. Through mathematical analysis, all three signals had significant differences. Participants in the VR environment had a higher degree of excitement, and the mood fluctuations are more frequent and more intense. In addition, the authors used different machine learning models for emotion detection, and compared the accuracies on VR and 2D datasets. The accuracies of all algorithms in the VR environment are higher than that of 2D, which corroborated that the volunteers in the VR environment have more obvious skin electrical signals, and had a stronger sense of immersion. This article effectively compensated for the inadequacies of existing work. The authors first used objective physiological signals for experience evaluation and used different types of subjective materials to make contrast. They hope their study can provide helpful guidance for the engineering reality of virtual reality. c Society for Imaging Science and Technology 2019

关键词： Virtual reality

Generalization Boosted Adapter for Open-Vocabulary Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Wenhao Wang, Changwei Feng, Xuxiang Xu, Rongtao Huang, Longzhao Zhang, Zherui Guo, Li Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250013 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China The Aerospace Information Research Institute Chinese Academy of Sciences China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two core components: (1) a Style Diversification Adapter (SDA) that decouples features into amplitude and phase components, operating solely on the amplitude to enrich the feature space representation while preserving semantic consistency;and (2) a Correlation Constraint Adapter (CCA) that employs cross-attention to establish tighter semantic associations between text categories and target regions, suppressing irrelevant low-frequency "noise" information and avoiding erroneous associations. Through the synergistic effect of the shallow SDA and the deep CCA, GBA effectively alleviates overfitting issues and enhances the semantic relevance of feature representations. As a simple, efficient, and plug-and-play component, GBA can be flexibly integrated into various CLIP-based methods, demonstrating broad applicability and achieving state-of-the-art performance on multiple open-vocabulary segmentation benchmarks. © 2024, CC BY.

关键词： Semantics

Structural reduction of CRNs with linear sub-CRNs

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2021年第14期54卷 149-154页

作者： Katalin M. Hangos György Lipták Gábor Szederkényi Systems and Control Laboratory Computer and Automation Research Institute P.O. Box 63 H-1518 Budapest Hungary Department of Electrical Engineering and Information Systems University of Pannonia Veszprém Hungary Faculty of Information Technology and Bionics Péter Pázmány Catholic University Budapest Hungary

A novel systems theory-based structural reduction method is proposed in this paper that can be applied to chemical reaction networks (CRNs) including subsystems consisting of linear reactions, i.e. a linear sub-CRN. The reduced model is a delayed CRN with distributed delays having less complexes (monomials) and reactions than the original model. The reduction is based on the fact that the input/output response of a linear sub-CNR can be seen as a time-delayed input to output relationship, therefore linear sub-CNRs can be interpreted as reactions with distributed delay from their input to their output complexes. The practically important example of a kinetic model describing the spread of the COVID-19 epidemic is used as a case study to illustrate the basic concepts and the computation method.

关键词： Delay Model reduction Chemical Reaction Networks COVID

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

学校读者我要写书评

暂无评论

Distributed Optimization with Finite Bit Adaptive Quantizati...

IEEE Conference on Decision and Control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Artificial Intelligence Thrust of the Information Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong China Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Division of Decision and Control Systems KTH Royal Institute of Technology SE-100 44 Stockholm Sweden

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node’s local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through 3-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only 3 -bits). Our proposed algorithm respects the network’s bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm’s operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm’s unique characteristics.

关键词： Adaptation models Quantization (signal) Heuristic algorithms Bandwidth Distributed algorithms Optimization Convergence

Lgtm: Local and Global Temporal Modeling in Spiking Neural Network

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Xue, Dengfeng Li, Wenjuan Yuan, Chunfeng Liu, Haowei Liu, Wei Yang, Li Li, Bing Hu, Weiming Sun, Haoliang Li, Zhetao School of Computer Science and Technology Xidian University Shaanxi Xi’an710119 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Information Science and Technology ShanghaiTech University Shanghai201210 China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing100029 China College of Information Science and Technology Jinan University Guangdong Guangzhou511436 China Xiangtan University China

Spiking neural networks (SNNs) have emerged as a promising energy-efficient alternative to convolutional neural networks owing to their spike-based computing. However, current SNNs do not fully leverage temporal information. To explore their potential, we present a novel framework, Local and Global Temporal Modeling (LGTM). The Local Module and the Global Module in LGTM are designed with shift and mean operations to fuse features at different temporal windows. Our method performs well on static and neuromorphic datasets, including CIFAR10, ImageNet, CIFAR10-DVS, and DVS128 Gesture datasets. In particular, compared with PSN based on ResNet18/34, our LGTM achieves top-1 accuracy of 68.41%/71.25% on the ImageNet while consuming 17.57%/7.94% less energy. In addition, we conduct systematic ablation studies and depict the visualization of various spiking features to provide insightful analysis of temporal modeling. © 2024, The Authors. All rights reserved.

关键词： Energy efficiency

Associative Learning Mechanism for Drug-Target Interaction Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Zhiqin Yao, Zheng Qi, Guanqiu Mazur, Neal Cong, Baisen College of Automation Chongqing University of Posts and Telecommunications Chongqing400065 China Computer Information Systems Department State University of New York at Buffalo State BuffaloNY14222 United States Diagnostics Co. Ltd. Danaher company China

As a necessary process in drug development, finding a drug compound that can selectively bind to a specific protein is highly challenging and costly. Drug-target affinity (DTA), which represents the strength of drug-target interaction (DTI), has played an important role in the DTI prediction task over the past decade. Although deep learning has been applied to DTA-related research, existing solutions ignore fundamental correlations between molecular substructures in molecular representation learning of drug compound molecules/protein targets. Moreover, traditional methods lack the interpretability of the DTA prediction process. This results in missing feature information of intermolecular interactions, thereby affecting prediction performance. Therefore, this paper proposes a DTA prediction method with interactive learning and an autoencoder mechanism. The proposed model enhances the corresponding ability to capture the feature information of a single molecular sequence by the drug/protein molecular representation learning module and supplements the information interaction between molecular sequence pairs by the interactive information learning module. The DTA value prediction module fuses the drug-target pair interaction information to output the predicted value of DTA. Additionally, this paper theoretically proves that the proposed method maximizes evidence lower bound (ELBO) for the joint distribution of the DTA prediction model, which enhances the consistency of the probability distribution between the actual value and the predicted value. The experimental results confirm mutual transformer-drug target affinity (MT-DTA) achieves better performance than other comparative methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions