检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2023年 1-7页

作者： Tian, Chunwei Zhang, Xuanyu Liang, Xu Li, Bo Sun, Yougang Zhang, Shichao School of Software Northwestern Polytechnical University Xi'an Shaanxi China School of Software Northwestern Polytechnical University Xi'an China School of Electronics and Information Northwestern Polytechnical University Xi'an Shaanxi China Institute of Rail Transit National Maglev Transportation Engineering R&D Center Tongji university Shanghai China School of Computer Science and Engineering Central South University Changsha Hunan China

Deep convolutional neural networks (CNNs) can improve recognition rate in license plate to improve traffic. However, these methods may refer to big computational costs and a lot of parameters. In this paper, we propose a knowledge distillation with a fast CNN for license plate detection (KDNet). KDNet uses knowledge distillation to guide a CNN to optimize parameters and quickly obtain a detector for license plate. To overcome naive effect of local information, a non-local similarity mechanism is used into a CNN to enhance effect of global information for extracting salient information in license plate detection. Experimental results that this proposed KDNet is superior to detection speed for license plate. The code of KDNet can be obtained at https://***/hellloxiaotian/KDNet. IEEE

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Throughput Maximization in Cognitive Radio Network with NOMA

引用

computers, Materials & Continua 2022年第1期70卷 195-212页

作者： Xiaoli He Yu Song Yu Xue Muhammad Owais Weijian Yang Xinwen Cheng School of Computer Science Sichuan University of Science and EngineeringZigong643000China Department of Network Information Management Center Sichuan University of Science and EngineeringZigong643000China School of Information Engineering South West University of Science and TechnologyMianyang621010China School of Computer and Software Nanjing University of Information Science and TechnologyJiangsu210044China Alhamd Islamic University Airport Road Quetta BalochistanPakistan

Spectrum resources are the precious and limited natural *** order to improve the utilization of spectrum resources and maximize the network throughput,this paper studies the resource allocation of the downlink cognitive radio network with non-orthogonalmultiple access(CRN-NOMA).NOMA,as the key technology of the fifth-generation communication(5G),can effectively increase the capacity of 5G *** optimization problem proposed in this paper aims to maximize the number of secondary users(SUs)accessing the system and the total throughput in the *** the constraints of total power,minimum rate,interference and SINR,CRN-NOMA throughput is maximized by allocating optimal transmission ***,for the situation of multiple sub-users,an adaptive optimization method is proposed to reduce the complexity of the optimization ***,for the optimization problem of nonlinear programming,a maximization throughput optimization algorithm based on Chebyshev and convex(MTCC)for CRN-NOMA is proposed,which converts multi-objective optimization problem into single-objective optimization problem to *** the same time,the convergence and time complexity of the algorithm are *** analysis and simulation results show that the algorithm can effectively improve the system *** terms of interference and throughput,the performance of the sub-optimal solution is better than that of orthogonal-frequency-division-multiple-access(OFDMA).This paper provides important insights for the research and application of NOMA in future communications.

关键词： Resource allocation non-orthogonal multiple access cognitive radio network throughput maximization Chebyshev convex

来源：评论

学校读者我要写书评

暂无评论

Lake Water Level Forecasting Using LSTM and GRU: A Deep Learning Approach 9th

Lake Water Level Forecasting Using LSTM and GRU: A Deep Lear...

引用

9th Future Technologies Conference, FTC 2024

作者： Du, Yuxin Fan, Jing Happonen, Ari Paulraj, Dassan Tuape, Micheal Department of Software Engineering School of Engineering Sciences Lappeenranta-Lahti University of Technology Mukkulankatu 19 Lahti15210 Finland Department of Software Engineering School of Engineering Sciences Lappeenranta-Lahti University of Technology Yliopistonkatu 34 Lappeenranta53850 Finland Department of Computer Science and Engineering R.M.K. Engineering College Chennai India

ISBN: (纸本)9783031731242

Artificial Intelligence and Deep Learning-based methods show constant promise in addressing time series forecasting challenges. Lake water level forecasting is an essential & significant environmental and societal impact related time series forecasting problem, with climate change connections. Lakes’ diverse hydrological characteristics make high-performance forecasting models to be lake-specific. Thus, comprehensive experiments are necessary to develop accurate deep learning-based forecasting models. We propose an approach for effective and efficient systematic search conduction for high-performance Deep Learning forecasting models. The method is applicable across various time series forecasting challenges. The research was structured around three experimental groups, each focusing on predicting the water levels of Lake Vesijärvi in Lahti, Finland, over periods of 1 day, 3 days, and 7 days, respectively with Long Short-Term Memory and Gated Recurrent Unit. The results are highly promising. All models achieved a Nash-Sutcliffe Efficiency above 0.95 and a Root Mean Squared Error below 0.025. The best-performing model achieved a Nash-Sutcliffe Efficiency above 0.99 and a Root Mean Squared Error below 0.0011. All evaluation metrics were calculated from testing data without signs of overfitting. This research provides insights into Deep Learning-based time series forecasting and a replicable method to conduct such studies effectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Lakes

来源：评论

学校读者我要写书评

暂无评论

A study on the impact of pre-trained model on Just-In-Time defect prediction 23

A study on the impact of pre-trained model on Just-In-Time d...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo Beihang University State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China City University of Hong Kong Department of Computer Science Hong Kong

ISBN: (纸本)9798350319583

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone's pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Analysis of Techniques for Detection and Removal of Zero-Day Attacks (ZDA) 2nd

Analysis of Techniques for Detection and Removal of Zero-Day...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Hamid, Khalid Iqbal, Muhammad Waseem Aqeel, Muhammad Liu, Xiangyong Arif, Muhammad Department of Software Engineering The Superior University Lahore54000 Pakistan Department of Computer Science The Superior University Lahore54000 Pakistan School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China

ISBN: (纸本)9789819902712

Zero-day attacks (ZDAs) are previously unknown flaws and errors in operating systems, networks, and general-purpose software. ZDAs are the cause to open security breach holes for external users or hackers for illegal operations before patches. ZDAs are different from viruses, worms and Trojans. They are very difficult to detect and remove because they are unknown to users and even programmers. Conventional defense systems are useless against such types of attacks. This paper investigates the zero-day attacks, their vulnerabilities, the intensity of these attacks and the reasons in a real-time environment. Different techniques are compared to investigate ZDAs. The hybrid technique has been used to check the behavior of data traffic coming from outside the world in the virtual environment for zero-day attacks. Static check tools (MD5 Checksum, AV-Suite, and SOPHOS) and behavioral check tools (SANDBOX) have been used for the verification and validation of results. The second comparatively best technique is Machine Learning-Based Technique which showed the best results. The results show how to choose the best solution against zero-day attacks in the real-time environment of the software. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Zero-day attack

来源：评论

学校读者我要写书评

暂无评论

PESTA: An Elastic Motion Capture Data Retrieval Method

引用

Journal of computer science & Technology 2023年第4期38卷 867-884页

作者：蒋子飞李伟黄艳尹义龙郭宗杰彭京亮 School of Software Shandong UniversityJinan 250101China Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles 90089U.S.A Shandong Provincial Key Laboratory of Network Based Intelligent Computing Jinan 250022China School of Information Science and Engineering University of JinanJinan 250022China

Prevalent use of motion capture(MoCap)produces large volumes of data and MoCap data retrieval becomes crucial for efficient data *** clips may not be neatly segmented and labeled,increasing the difficulty of *** order to effectively retrieve such data,we propose an elastic content-based retrieval scheme via unsupervised posture encoding and strided temporal alignment(PESTA)in this *** retrieves similarities at the sub-sequence level,achieves robustness against singular frames and enables control of tradeoff between precision and *** firstly learns a dictionary of encoded postures utilizing unsupervised adversarial autoencoder techniques and,based on which,compactly symbolizes any MoCap ***,it conducts strided temporal alignment to align a query sequence to repository sequences to retrieve the best-matching sub-sequences from the ***,it extends to find matches for multiple sub-queries in a long query at sharply promoted efficiency and minutely sacrificed *** performance of the proposed scheme is well demonstrated by experiments on two public MoCap datasets and one MoCap dataset captured by ourselves.

关键词： motion capture(MoCap) content-based retrieval adversarial autoencoder temporal alignment

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Integrity Estimation of Twitter Based Event Recognition Using Scrutiny of Analyzed Data 2

Integrity Estimation of Twitter Based Event Recognition Usin...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Siva Rama Lingham, N. Parameswari, M. Karthick, P. Priya, T. Subha Rathi Rajesh, G. Jagannathan, J. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Knowledge Institute of Technology Department of Computer Science and Engineering Salem India Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Computer Science and Engineering Chennai India School of Engineering and Technology Jeppiaar University Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Software and Systems Engineering Vellore Katpadi632014 India

ISBN: (纸本)9798350328202

Twitter has been observed to be one of the essential data resources for dependable event accreditation. In any case, Twitter-based event affirmation structures can't guarantee assessment concerning their attestation results. Talk statement has been locked in starting late to enable liberal event Recognition. This problem is not yet evident in light of the assumption that most people tend to think that they have a specific limit to the data on Twitter that have frames based on events based on Twitter. Current appraisals see new pieces by seeing and looking at the significant psychological aspects of hitting the details on Twitter. No matter, the scale of the visual cues can be well established, with the intention that it is essential to design an integrated Twitter experiment with another set of extensible data resources to rectify this problem. The problem is the processes by which you should wholeheartedly investigate all converted data because it has different data structures, transfer times, etc. This issue of address, the paper proposes a framework for evaluating the use of Twitter-based events and examines two types of data resources for the reliability of impact testing. Our framework uses the resultant of the request obtaining by various events and relevant to the articles on it. This paper has improved the cleaning test with the proposed process how the integrity estimation of twitter based event can be recognized with the help of group of analyzed data. The evaluation indicates that the proposed system provides visible high-level testing events and a variety of low-level testing events. © 2024 IEEE.

关键词： Impact testing

来源：评论

学校读者我要写书评

暂无评论

Streamlining plant disease diagnosis with convolutional neural networks and edge devices

引用

Neural Computing and Applications 2024年第29期36卷 18445-18477页

作者： Ahamed, Md. Faysal Salam, Abdus Nahiduzzaman, Md. Abdullah-Al-Wadud, M. Islam, S. M. Riazul Department of Computer Science and Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical and Computer Engineering Rajshahi University of Engineering & ampTechnology Rajshahi6204 Bangladesh Department of Electrical Engineering Qatar University Doha Qatar Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Natural and Computing Sciences University of Aberdeen AberdeenAB24 3FX United Kingdom

In addressing labor-intensive process of manual plant disease detection, this article introduces an innovative solution—the lightweight parallel depthwise separable convolutional neural network (PDSCNN) coupled with a hybrid ridge regression extreme learning machine classifier. This combined approach automates plant disease classification, significantly expediting the learning process and reducing computational complexity. The PDSCNN model excels in feature capture, boasting a mere 9 layers and 0.053 million parameters, resulting in exceptional computational efficiency. On top of that, the classification performances of traditional ELM increased by introducing a hybrid ridge ELM model. Its accelerated operations, reduced memory usage, and optimized parallel processing render it lightweight and ideal for edge devices. The proposed framework exhibits remarkable efficacy, showcasing a precision of 95.76%, a recall of 89.29%, an F1-score of 91.25%, an accuracy of 94.22%, and an AUC of 99.72%. Moreover, training and testing times clock in at just 0.2314 and 0.0259 s, respectively. A comparative analysis against state-of-the-art transfer learning methods underscores its real-time analytical prowess. To demonstrate real-world applicability, we successfully validated our model on the Jetson Nano hardware, making it suitable for resource-constrained settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Cement Strength Prediction using Regression Techniques 10

Cement Strength Prediction using Regression Techniques

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Dewan, Ritu Polishetty, Rohith Sharan, Bhagwati Goyal, Mayank Kumar Balde, Amadou Mouctar Greynoon, Ameen Mohamad Ahmad Galgotias College of Engineering and Technology Department of Computer Science and Engineering Greater Noida India Sr. Software Engineer Migo India Limited Hyderabad India Srm University-AP School of Engineering and Sciences Department of Computer Science and Engineering Amaravati India Sharda University School of Engineering and Technology Department of Computer Science and Engineering Greater Noida India School of Engineering and Technology Sharda University Department of Computer Science and Applications Greater Noida India

ISBN: (纸本)9789380544472

One of the primary structural materials in the development business is concrete. Compressive strength is the most frequently utilized metric when assessing the strength and nature of cement. This paper clarifies how to make use of technical regression (RT) methodology to decide the legitimate dose of the concrete mixture. Water, Cement, Fly Ash, Blast Furnace, Superplasticizer, Coarse, and Fine Aggregate, were used as input parameters, on the other hand, compressive strength was used as an output parameter. The produced models were evaluated using statistical parameters: Linear Regression, Decision Tree Regression, and Random Forest Regression. In contrast with other applicable models, it was found that the Gaussian process regression model based on the function of the nucleus of radial bases delivered relatively better results. The recommended models should get a good deal on saving money on materials, labor, and time while also improving accuracy. The proposed concrete should be more durable and accordingly more cost-effective. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Cements

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：