检索结果-内蒙古大学图书馆

IAENG International Journal of computer science 2025年第1期52卷 23-31页

作者： Guo, Ying Wang, Li School of Computer Science and software Engineering University of Science and Technology Liaoning Anshan114051 China College of Computer Science and Technology Liaoning Anshan114051 China

End-to-end training has emerged as a prominent trend in speech recognition, with Conformer models effectively integrating Transformer and CNN architectures. However, their complexity and high computational cost pose deployment challenges. To address these issues, we propose a multi-task Chinese speech recognition method based on the Squeezeformer model. We replace the FMCF structure in Conformer with an MF/CF structure, leveraging the convolutional module as a local Multi- Head Attention (MHA) module to enhance efficiency. Multilevel down-sampling and up-sampling using a time-series U-Net further reduce computational costs. By eliminating redundant LayerNorm layers and employing depthwise separable convolutions, we streamline the model, reduce parameters, and lower deployment costs. An Adaptor Layer is integrated into the MHSA module to mitigate the vanishing gradient problem, and a ScaleVar Layer is added to enhance flexibility. Additionally, the RealFormer module is introduced on the decoding side to improve context understanding. Combining Connectionist Temporal Classification (CTC) with attention-based encoding and decoding models for multi-task learning improves performance and accuracy. Experimental results show that the proposed method reduces the parameters on AISHELL-1 dataset by 16% and reduces the character error rate to 5.50%. At the same time, it also shows good performance on AISHELL-2 dataset. © (2025), (International Association of Engineers). All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Image Guidance Encoder-Decoder Model in Image Captioning and Its Application

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第9期51卷 1385-1392页

作者： Yang, Zhen Zhou, Ziwei Wang, Chaoyang Xu, Liang School of Applied Technology University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China

This paper introduces a new network model - the Image Guidance Encoder-Decoder Model (IG-ED), designed to enhance the efficiency of image captioning and improve predictive accuracy. IG-ED, a fusion of the convolutional network VGGNet-16 and the long short-term memory network (LSTM), is designed based on the encoder-decoder structure. The image captioning performance sees significant enhancements when leveraging the IG-ED network model. The network training process unfolds in a series of steps. Initially, the input image undergoes convolution via the VGGNet-16 network, producing a 512-dimensional vector. Concurrently, each word in the image's caption is encoded to generate a corresponding 512-dimensional vector consistent with the image feature dimension. These two vectors form the input for the decoding process. Subsequently, the vectors are fed into the redesigned fusion LSTM (F-LSTM) network at different time steps to gradually train the parameters of the IG-ED framework. The training process is completed by utilizing a loss function for determining convergence. Evaluation of the IG-ED model's performance is conducted using CIDEr and seven other evaluation metrics on the MSCOCO 2014 dataset. The results exhibit substantial improvements over the "Adaptive Attention Mode" network and "Neural Talk" network. Additionally, the parameter count of the IG-ED architecture is significantly reduced compared to the "Adaptive Attention Mode" network, leading to decreased computational resource requirements and enabling edge computing on the neural network. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Exploring Innovation: Artificial Intelligence (AI) in Pharmacy 7

Exploring Innovation: Artificial Intelligence (AI) in Pharma...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Raymond, David Mankar, Divyani Gudadhe, Amit Faculty of Engineering And Technology Department of Computer Science And Medical Engineering Maharashtra Wardha India Faculty of Engineering And Technology Department of Basic Science And Humanities Maharashtra Wardha India

ISBN: (纸本)9798350359299

Artificial Intelligence (AI) has emerged as a disruptive force in the pharmaceutical industry, driving unprecedented breakthroughs across various domains. This article provides a comprehensive overview of the cutting-edge applications of AI in pharmacy, spanning medication safety, clinical decision support, personalized medicine, and drug discovery. AI is revolutionizing drug development processes, enabling precision pharmacy techniques, and enhancing clinical decision-making through Machine Learning, Deep Learning, and Natural Language Processing. Despite the potential for transformation, challenges such as moral dilemmas and legal restrictions persist. Nevertheless, the integration of AI will revolutionize pharmacy practice, leading to improved patient outcome and ushering in a new era of healthcare. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based rumor detection approach for COVID-19

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 435-449页

作者： Rani, Poonam Jain, Vibha Shokeen, Jyoti Balyan, Arnav Department of Computer Engineering Netaji Subhas University of Technology Delhi India Department of Computer Science and Engineering University Institute of Engineering and Technology Maharshi Dayanand University Haryana Rohtak India

The ubiquity of handheld devices and easy access to the Internet help users get easy and quick updates from social media. Generally, people share information with their friends and groups without inspecting the posts’ veracity, which causes false information propagation in the network. Moreover, detecting false news and rumors in such a massive load of unstructured information is a very tedious task. Results, many literature papers explored different machine learning and deep learning approaches to detect the presence of rumors on social media networks. Although detection of misleading news and rumors is not sufficient, therefore, we have proposed a model for the detection and prevention of transmitted rumors in this paper. In this paper, we use blockchain technology to verify the credibility of information and design a framework with four layers: network layer, blockchain layer, machine layer, and device layer, to prevent the propagation of rumors in the network. We also use deep learning techniques to identify the anomalies in the network. The Bi-directional Long Short Term Memory (Bi-LSTM) model is used to prevent the introduction of new rumors by continuously monitoring incoming messages in the network. The experimental results demonstrate that the proposed Bi-LSTM model outperforms state-of-the-art machine learning methods and recent baseline work. Performance is compared over different metrics such as accuracy, precision, recall, f1-score, and specificity. Experiment results show that our Bi-LSTM model outperforms all the other approaches and achieved 99.63 % accuracy. Additionally, the probability of incorrect detection is significantly low with only 0.13% false positive. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Latency Minimization Using an Adaptive Load Balancing Technique in Microservices Applications

引用

computer Systems science & engineering 2023年第7期46卷 1215-1231页

作者： G.Selvakumar L.S.Jayashree S.Arumugam Department of Computer Science and Engineering KPR Institute of Engineering and TechnologyCoimbatore641407India Department of Computer Science and Engineering PSG College of TechnologyCoimbatore641004India Department of Computer Science and Engineering Nandha College of EngineeringErode638052India

Advancements in cloud computing and virtualization technologies have revolutionized Enterprise Application Development with innovative ways to design and develop complex *** Architecture is one of the recent techniques in which Enterprise Systems can be developed as fine-grained smaller components and deployed *** methodology brings numerous benefits like scalability,resilience,flexibility in development,faster time to market,*** the advantages;Microservices bring some challenges *** microservices need to be invoked one by one as a *** most applications,more than one chain of microservices runs in parallel to complete a particular requirement To complete a user’s *** results in competition for resources and the need for more inter-service communication among the services,which increases the overall latency of the application.A new approach has been proposed in this paper to handle a complex chain of microservices and reduce the latency of user requests.A machine learning technique is followed to predict the weighting time of different types of *** communication time among services distributed among different physical machines are estimated based on that and obtained insights are applied to an algorithm to calculate their priorities dynamically and select suitable service instances to minimize the latency based on the shortest queue waiting *** were done for both interactive as well as non interactive workloads to test the effectiveness of the *** approach has been proved to be very effective in reducing latency in the case of long service chains.

关键词： Microservices load balancing cloud computing latency optimization netflix

来源：评论

学校读者我要写书评

暂无评论

The Effect of Key Nodes on theMalware Dynamics in the Industrial Control Network

引用

computers, Materials & Continua 2024年第4期79卷 329-349页

作者： Qiang Fu JunWang Changfu Si Jiawei Liu College of Computer Science and Technology Shenyang University of Chemical TechnologyShenyang110142China College of Computer Science and Engineering Northeastern UniversityShenyang110169China

As industrialization and informatization becomemore deeply intertwined,industrial control networks have entered an era of *** connection between industrial control networks and the external internet is becoming increasingly close,which leads to frequent security *** paper proposes a model for the industrial control *** includes a malware containment strategy that integrates intrusion detection,quarantine,and ***,the role of keynodes in the spreadofmalware is studied,a comparisonexperiment is conducted to validate the impact of the containment *** addition,the dynamic behavior of the model is analyzed,the basic reproduction number is computed,and the disease-free and endemic equilibrium of the model is also obtained by the basic reproduction ***,through simulation experiments,the effectiveness of the containment strategy is validated,the influence of the relevant parameters is analyzed,and the containment strategy is *** otherwords,selective immunity to key nodes can effectively suppress the spread ofmalware andmaintain the stability of industrial control *** earlier the immunization of key nodes,the *** the time exceeds the threshold,immunizing key nodes is almost *** analysis provides a better way to contain the malware in the industrial control network.

关键词： Key nodes dynamic model industrial control network simulation

来源：评论

学校读者我要写书评

暂无评论

A Priority-Based Hierarchical Framework for k-Robust Multi-Agent Path Finding

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 5631-5641页

作者： Zhang, Kaixiang Mao, Jianlin Zhang, Shufan Wang, Ning Kunming University of Science and Technology Faculty of Mechanical and Electrical Engineering Kunming650500 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China

Multi-agent path finding is one of the key problems in the topic of multi-agent system. While some inevitable execution delays resulting from the realistic factors, such as robot faults or avoiding human etc., may make the path plan invalid. Our aim is to effectively find paths with robustness to k-delays for all agents, i.e., each agent can get a k-step margin in its paths without breaking the whole plan, especially for the large-scale systems. We propose a priority-based hierarchical framework for k-robust multi-agent path finding, where the pattern of searching path while avoiding conflict is profit to reduce the burden of conflict handling in k-robust planning. Then, the classification and generation rules of robust constraints are designed to guarantee global k-robustness of prioritized planning. Finally, for the new challenge of k-robust starting predicament, a multi-level key-agent guided priority adjustment mechanism is proposed to improve solution success rate. Experimental results show that the proposed algorithm can effectively reduce the runtime, and averagely maintain a success rate of over 95%. Especially for large-scale problems with hundreds of agents, the runtime can be reduced to a few seconds. In addition, the runtime does not increase dramatically as the k-value grows from 0 to 7. © 2016 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov Arnold Network for Hyperspectral Image Classification: A Detailed Explanation 2

Kolmogorov Arnold Network for Hyperspectral Image Classifica...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Suman, Saurabh Pacharaney, Utkarsha Choudhary, Vishal Kumar Raushan, Rahul Kumar, Abhishek Kumar, Gulshan Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798331528713

Hyperspectral imaging (HSI) has been proved to be useful in numerous fields because of its ability to acquire the spectral information across the hundreds of contiguous bands. Nevertheless, the vast dimensionality of the hyperspectral data presents a great problem especially during data processing as well as during classification. Recently, one of the techniques that have attracted most interest for the classification of hyperspectral images is Kolmogorov Arnold Network (KAN), which is efficient with regard to those high-dimensional non- linear data sets found in hyperspectral imagery. This study focuses on how KAN can be utilized for classifying hyperspectral images, how B-spline curves can be used for augmenting the performance of the model, and what experimentation was done with the state-of-the-art hyperspectral data set. From these results, it was established that KAN plus B-spline curves was a good strategy for hyperspectral images classification compared to existing systems in both accuracy and speed. © 2024 IEEE.

关键词： Splines

来源：评论

学校读者我要写书评

暂无评论

Machine learning-assisted prediction and optimization of solid oxide electrolysis cell for green hydrogen production

引用

Green Chemical engineering 2025年第2期6卷 154-168页

作者： Qingchun Yang Lei Zhao Jingxuan Xiao Rongdong Wen Fu Zhang Dawei Zhang School of Chemistry and Chemical Engineering Hefei University of TechnologyHefei230009China East China Engineering Science and Technology Co.Ltd. Hefei230011China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao999078China

The solid oxide electrolysis cell(SOEC)holds great promise to efficiently convert renewable energy into ***,traditional modeling methods are limited to a specific or reported SOEC ***,four machine learning models are developed to predict the performance of SOEC processes of various types,operating parameters,and feed *** impact of these features on the SOEC's outputs is explained by the Shapley additive explanations and partial dependency plot *** preferredmodel is integratedwith a genetic algorithmto determine the optimal values of each input *** show the improved extreme gradient enhanced regression(XGBoost)algorithm is the core of the machine learning model of the process since it has the highest R^(2)(>0.95)in the three *** electrolytic cell descriptors have a greater impact on the system performance,contributing up to 54.5%.The effective area,voltage,and temperature are the three most influential factors in the SOEC system,contributing 21.6%,16.6%,and 13.0%to its *** temperature,high pressure,and low effective area are the most favorable conditions for H_(2)production *** conducting multi-objective optimization,the optimal current intensity and hydrogen production rate were determined to be 1.61 A/cm^(2)and 1.174 L/(h⋅cm^(2)).

关键词： Solid oxide electrolysis cell Machine learning H_(2)production rate Feature importance analysis System optimization

来源：评论

学校读者我要写书评

暂无评论

Application of Face Detection and Recognition Algorithm Based on Deep Learning in Automatic Interception of Target Person Video Clips

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第10期51卷 1546-1559页

作者： Wang, Zhibiao Tao, Ye Liu, Xu Yu, Jiayi Cui, Wenhua School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Current automatic segment extraction techniques for identifying target characters in videos have several limitations, including low accuracy, slow processing speeds, and poor adaptability to diverse scenes. This paper introduces an optimized algorithm to address these issues that enhance the RetinaFace and FaceNet models. We selected RetinaFace for face detection, employing MobileNetV1-0.25 as the backbone network and simplifying its Feature Pyramid Network (FPN) structure to boost detection speeds. Analysis of 460 images with a 720P resolution demonstrated an average speed improvement of 20.6%. For face recognition, we utilized FaceNet with MobileNetV3 as the backbone, augmenting its feature extraction capability by integrating four Receptive Field Block (RFB) structures and replacing the Squeeze-and-Excitation (SE) module with the Convolutional Block Attention Module (CBAM). Experimental results indicate that our enhancements elevate the maximum accuracy to 97%, outperforming the original model. Additionally, we integrated these refined algorithms and conducted disintegration experiments on segment extraction in 10 videos, evaluating various metrics. The findings show improvements in both precision and recall. We also compared our algorithm against the Dlib model;our system achieved an overall interception accuracy of 79.94%, surpassing Dlib’s 75.55%. This confirms the enhanced performance and feasibility of our proposed algorithm. © (2024), (International Association of Engineers). All rights reserved.

关键词： Face 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

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

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：