检索结果-内蒙古大学图书馆

An Effective Power Optimization Approach Based on Whale Optimization Algorithm with Two-Populations and Mutation Strategies

引用

Chinese Journal of Electronics 2024年第2期33卷 423-435页

作者： Juncai HE Zhenxue HE Jia LIU Yan ZHANG Fan ZHANG Fangfang LIANG Tao WANG Limin XIAO Xiang WANG Hebei Agricultural University Beijing Information Science and Technology University School of Computer Science and Engineering Beihang University School of Electronic and Information Engineering Beihang University

Power is an issue that must be considered in the design of logic circuits. Power optimization is a combinatorial optimization problem, since it is necessary to search for a logical expression that consumes the least amount of power from a large number of Reed-Muller(RM) logical expressions. The existing approach for optimizing the power of multi-output mixed polarity RM(MPRM) logic circuits suffer from poor optimization results. To solve this problem, a whale optimization algorithm with two-populations strategy and mutation strategy(TMWOA) is proposed in this paper. The two-populations strategy speeds up the convergence of the algorithm by exchanging information about the two-populations. The mutation strategy enhances the ability of the algorithm to jump out of the local optimal solutions by using the information of the current optimal solution. Based on the TMWOA, we propose a multi-output MPRM logic circuits power optimization approach(TMMPOA). Experiments based on the benchmark circuits of the Microelectronics Center of North Carolina(MCNC) validate the effectiveness and superiority of the proposed TMMPOA.

关键词： Multi-output mixed polarity Reed-Muller Power optimization Combinatorial optimization problem Whale optimization algorithm Two-populations strategy Mutation strategy

来源：评论

学校读者我要写书评

暂无评论

Local Fine-grained Visual Tracking

引用

IEEE Transactions on Multimedia 2025年 27卷 3426-3436页

作者： Wu, Jingjing Sun, Yifan Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Baidu China

This paper introduces a novel local fine-grained visual tracking task, aiming to precisely locate arbitrary local parts of objects. This task is motivated by our observation that in many realistic scenarios, the user demands to track a local part instead of a holistic object. However, the absence of an evaluation dataset and the distinctive characteristics of local fine-grained targets present extra challenges in conducting this research. To tackle these issues, firstly, this paper constructs a local fine-grained tracking (LFT) dataset to evaluate the tracking performance for local fine-grained targets. Secondly, this paper designs a cutting-edge solution to handle the challenges posed by properties of local objects, including ambiguity and high-proportion backgrounds. It consists of a hierarchical adaptive mask mechanism and foreground-background differentiated learning. The former adaptively searches for and masks ambiguity, which drives the network to concentrate on the local target instead of the holistic objects. The latter is constructed to distinguish foreground and background in an unsupervised manner, which is beneficial to mitigate the impacts of high-proportion backgrounds. Extensive analytic experiments are performed to verify the effectiveness of each submodule in the proposed fine-grained tracker. Our datasets and code will be publicly available soon: https://***/hfutwujingjing/local-fine-grained-tracking. © 1999-2012 IEEE.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

OCRBench: on the hidden mystery of OCR in large multimodal models

引用

Science China(information Sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

UAV-supported intelligent truth discovery to achieve low-cost communications in mobile crowd sensing

引用

Digital Communications and Networks 2024年第4期10卷 837-852页

作者： Jing Bai Jinsong Gui Guosheng Huang Shaobo Zhang Anfeng Liu School of Computer Science and Engineering Central South UniversityChangSha410083China School of Information Science and Engineering Hunan First Normal UniversityChangsha410205China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangTan411100China

Unmanned and aerial systems as interactors among different system components for communications,have opened up great opportunities for truth data discovery in Mobile Crowd Sensing(MCS)which has not been properly solved in the *** this paper,an Unmanned Aerial Vehicles-supported Intelligent Truth Discovery(UAV-ITD)scheme is proposed to obtain truth data at low-cost communications for *** main innovations of the UAV-ITD scheme are as follows:(1)UAV-ITD scheme takes the first step in employing UAV joint Deep Matrix Factorization(DMF)to discover truth data based on the trust mechanism for an information Elicitation Without Verification(IEWV)problem in MCS.(2)This paper introduces a truth data discovery scheme for the first time that only needs to collect a part of n data samples to infer the data of the entire network with high accuracy,which saves more communication costs than most previous data collection schemes,where they collect n or kn data ***,we conducted extensive experiments to evaluate the UAV-ITD *** results show that compared with previous schemes,our scheme can reduce estimated truth error by 52.25%–96.09%,increase the accuracy of workers’trust evaluation by 0.68–61.82 times,and save recruitment costs by 24.08%–54.15%in truth data discovery.

关键词： Unmanned aerial systems Trust computing Truth discovery Deep matrix factorization Low-cost communications

来源：评论

学校读者我要写书评

暂无评论

Deep LBP-Enriched Real-time Segmentation for Hair Defect Detection

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第4期9卷 2304-2321页

作者： Wang, Xiaodong Wang, Jie Xie, Zhiyao Yan, Fei Huang, Haiyan Zeng, Zhiqiang College of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China School of Computer Engineering Guangzhou City University of Technology Guangzhou510800 China

In the industrial production of medical syringes, existing Deep Semantic Segmentation (DSS) methods, which generally have numerous network parameters, face significant challenges in real-time hair defect detection due to hair’s unique characteristics, including its irregular and thin structure. Moreover, potential hair overlapping with the syringe further complicates the detection process. In this case, conventional DSS methods are hard to explore the accurate low-level visuospatial information that is critical for detecting hair defects. Considering the wide applicability and effectiveness of the Local Binary Pattern (LBP) for detecting irregular and thin structural defects, we argue that LBP may help DSS models to extract more detailed hair features as a way to improve their performance in detecting hair defects on syringes. Inspired by this idea, this study proposes a Deep LBP-Enriched Real-time Segmentation (DLERS) method for hair defect detection, which maintains a lightweight network structure and leverages the LBP encoding mechanism to facilitate DSS models to extract more detailed edge features. Besides, to alleviate the influence of the hair-like noise and fragmentary edges, we propose employing a joint loss function that combines the Dice loss, BCE loss, and Edge loss to train our network. To evaluate the performance of DLERS, we conduct experiments on one real-world syringe dataset. The competitive results (e.g., 85.36% MIoU and 149.1 FPS) prove the effectiveness of our method. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Study on the Inter-Pretability of Network Attack Prediction Models Based on Light Gradient Boosting Machine(LGBM)and SHapley Additive exPlanations(SHAP)

引用

computers, Materials & Continua 2025年第6期83卷 5781-5809页

作者： Shuqin Zhang Zihao Wang Xinyu Su School of Computer Science Zhongyuan University of TechnologyZhengzhou450000China School of Cyberspace Security Information Engineering UniversityZhengzhou450000China

The methods of network attacks have become increasingly sophisticated,rendering traditional cybersecurity defense mechanisms insufficient to address novel and complex threats *** recent years,artificial intelligence has achieved significant progress in the field of network ***,many challenges and issues remain,particularly regarding the interpretability of deep learning and ensemble learning *** address the challenge of enhancing the interpretability of network attack prediction models,this paper proposes a method that combines Light Gradient Boosting Machine(LGBM)and SHapley Additive exPlanations(SHAP).LGBM is employed to model anomalous fluctuations in various network indicators,enabling the rapid and accurate identification and prediction of potential network attack types,thereby facilitating the implementation of timely defense measures,the model achieved an accuracy of 0.977,precision of 0.985,recall of 0.975,and an F1 score of 0.979,demonstrating better performance compared to other models in the domain of network attack *** is utilized to analyze the black-box decision-making process of the model,providing interpretability by quantifying the contribution of each feature to the prediction results and elucidating the relationships between *** experimental results demonstrate that the network attack predictionmodel based on LGBM exhibits superior accuracy and outstanding predictive ***,the SHAP-based interpretability analysis significantly improves the model’s transparency and interpretability.

关键词： Artificial intelligence network attack prediction light gradient boosting machine(LGBM) SHapley Additive exPlanations(SHAP) interpretability

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Multi-Task Deep Learning for WiFi Fingerprint Database Construction in Building-Scale Localization

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 488-500页

作者： Wang, Chun Luo, Juan Yin, Luxiu Li, Chuang Huang, Wenbin Liang, Wei Li, Kuan-Ching Hunan Normal University College of Information Science and Engineering China Hunan University College of Computer Science and Electronic Engineering China Hunan University of Science and Technology School of Computer Science and Engineering China Nanjing University of Information Science and technology School of Computer Science China

WiFi-based indoor positioning has emerged as a crucial technology for enabling smart consumer electronic applications, particularly in large-scale buildings. The construction of WiFi fingerprint databases using received signal strength (RSS) is foundational due to its widespread deployment. However, achieving high positioning accuracy typically requires labor-intensive and time-consuming site surveys. While recent crowdsourcing methods have facilitated the collection of numerous RSS samples, these samples frequently lack labels and reliability in multi-scale building *** this paper, we design a novel semi-supervised and multi-task mean-teacher model (MTMT-DNN) to annotate crowdsourcing unlabeled multi-scale fingerprint samples. This method enables the construction of a comprehensive fingerprint database without requiring intensive manual effort or compromising positioning accuracy. Our key idea is to first develop a multi-task Deep Neural Network (MT-DNN) for simultaneously annotating building, floor, and intra-floor coordinate labels by leveraging their complementary information. Then we employ the mean-teacher semi-supervised learning to leverage additional unlabeled fingerprint data for further improving the annotating performance and reducing intensive manual effort. Finally, we train the MTMT-DNN model by developing two multi-task loss functions and ensuring consistency between them, thereby enhancing the reliability of the annotated crowdsourced fingerprints. We conducted real-world experiments in a 20,000 m2 site encompassing three multi-story buildings. The results demonstrate that our proposed method significantly reduces the workload of manually collecting labeled fingerprint samples. With only 20% of labeled fingerprints collected, we achieve 99% average annotation accuracy for building and floor labels and an average coordinates annotation error within 4 m. © 1975-2011 IEEE.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Improved PBFT Consensus Algorithm Based on Threshold Signature and RabbitMQ

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1476-1490页

作者： Xu, Xiang Liu, Chun-Yuan School of Computer and Information Engineering Heilongjiang University of Science and Technology Harbin Heilongjiang150022 China

Due to its decentralized and tamper-proof features, blockchain is frequently employed in the financial, traceability, and distributed storage industries. The agreement algorithm, which is a crucial component of the blockchain distributed storage system, is responsible for maintaining data integrity and ensuring system security. It also has a significant impact on the blockchain system’s transaction throughput and confirmation time. Compared with public chain, alliance chain has fewer nodes and access mechanism, so PBFT consensus algorithm based on voting is generally used. However, there are still many shortcomings in the practical application of this algorithm. To solve the problem, an improved Byzantine consensus algorithm (TRPBFT) based on threshold signature and RabbitMQ is proposed in this paper. The experimental findings demonstrate that the enhanced consensus algorithm significantly increases both consensus efficiency and data throughput. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Attention Model for Non-intrusive Load Monitoring based on Time Series Feature

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第4期51卷 396-400页

作者： Meng, Zhaorui Xie, Xiaozhu Xie, Yanqi Sun, Jinhua School of Computer and Information Engineering Xiamen University of Technology Fujian Xiamen361024 China

Non-intrusive load monitoring (NILM) has become a widely used approach to monitor energy consumption by installing monitoring equipment at the power supply entrance. However, the accuracy of traditional deep neural network decomposition models falls short of meeting practical demand. To address this limitation, the present study introduces a novel hybrid neural network model, which integrates temporal feature extraction and an attention mechanism. The proposed model is designed to discern the salient attributes within power time series signals, thereby reducing the dimensionality of the resulting characteristic temporal signals via the application of Principal Component Analysis (PCA). Next, a Gated Recurrent Unit (GRU) neural network with an attention mechanism extracts the features of the generated information vector, and generates the load decomposition model after multiple iterations of learning. The experimental outcomes on the REDD public dataset substantiate the superiority of the proposed model over alternative deep learning techniques, including CNN, GRU, and GRU with attention. The proposed model demonstrates a significantly elevated degree of precision within the domain of load identification. © (2024) International Association of Engineers.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An enhanced framework for smart automated evaluations of answer scripts using NLP and deep learning methods

引用

Multimedia Tools and Applications 2025年第11期84卷 8491-8513页

作者： G, Mohanraj R.K, Nadesh M, Marimuthu V, Sathiyapriya School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore632014 India School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Knowledge Institute of Technology Salem637504 India

The manual process of evaluating answer scripts is strenuous. Evaluators use the answer key to assess the answers in the answer scripts. Advancements in technology and the introduction of new learning paradigms need automation of the evaluation process. This work aims to develop an enhanced novel hybrid framework that can evaluate answer scripts and automatically assign marks for different type of questions based on keywords, grammar, symbols, special keywords, and the given factors. First, the proposed system uses Optical Character Recognition (OCR) to convert image answer scripts into an editable text format. Second, the sentence transformers, the Natural Language Processing (NLP) technique flips the answer script and answers key texts into word embedding vectors. To find similarity measures, these vectors are matched using BERT encoding, spearmanś rank-order correlation, and fuzzy search. At last, the proposed model is trained using Deep Columnar Convolutional Neural Network (DCCNN) in the third step with MINST and Kaggle handwritten mathematical symbols and tested with the segmented mathematical equations to find the similarity. The performance of proposed model is measured using precision, recall, accuracy, and F1-score, and its gives highest accuracy of 93% and 95% when compared to the existing methodologies. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Optical character recognition

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：