检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Yuhan Song, Mofei College of Software Engineering Southeast University Jiangsu Nanjing China Ministry of Education Jiangsu Nanjing China School of Computer Science and Engineering Southeast University Jiangsu Nanjing China

ISBN: (纸本)9798400706868

3D novelty detection plays a crucial role in various real-world applications, especially in safety-critical fields such as autonomous driving and intelligent surveillance systems. However, existing 3D novelty detection methods are constrained by the scarcity of 3D data, which may impede the model's ability to learn adequate representations, thereby impacting detection accuracy. To address this challenge, we propose a Unified Learning Framework (UniL) for facilitating novelty detection. During the pretraining phase, UniL assists the point cloud encoder in learning information from other modalities, aligning visual, textual, and 3D features within the same feature space. Additionally, we introduce a novel Multimodal Supervised Contrastive Loss (MSC Loss) to improve the model's ability to cluster samples from the same category in feature space by leveraging label information during pretraining. Furthermore, we propose a straightforward yet powerful scoring method, Depth Map Error (DME), which assesses the discrepancy between projected depth maps before and after point cloud reconstruction during novelty detection. Extensive experiments conducted on 3DOS have demonstrated the effectiveness of our approach, significantly enhancing the performance of the unsupervised VAE method in 3D novelty detection. Codes are avaliable at https://***/EugeneWon9/UniL. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Testing Method for Web Services Composition Based on Data-Flow

引用

Wuhan University Journal of Natural Sciences 2008年第4期13卷 455-460页

作者： HOU Jun XU Baowen XU Lei WANG Di XU Junling School of Computer Science and Engineering SoutheastUniversity Nanjing 211189 Jiangsu China State Key Laboratory of Software Engineering WuhanUniversity Wuhan 430072 Hubei China

This paper proposes a method of data-flow testing for Web services composition. Firstly, to facilitate data flow analysis and constraints collecting, the existing model representation of business process execution language （BPEL） is modified in company with the analysis of data dependency and an exact representation of dead path elimination （DPE） is proposed, which over-comes the difficulties brought to dataflow analysis. Then defining and using information based on data flow rules is collected by parsing BPEL and Web services description language （WSDL） documents and the def-use annotated control flow graph is created. Based on this model, data-flow anomalies which indicate potential errors can be discovered by traversing the paths of graph, and all-du-paths used in dynamic data flow testing for Web services composition are automatically generated, then testers can design the test cases according to the collected constraints for each path selected.

关键词： Web services composition business process execution language （BPEL） Web services description language （WSDL） data flow all-du-path

来源：评论

学校读者我要写书评

暂无评论

Analysis and Improvement of Steganography Protocol Based on Bell States in Noise Environment

引用

computers, Materials & Continua 2019年第5期59卷 607-624页

作者： Zhiguo Qu Shengyao Wu Wenjie Liu Xiaojun Wang Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China School of Computer&Software Nanjing University of Information Science and TechnologyNanjing210044China School of Electronic Engineering Dublin City UniversityDublinIreland

In the field of quantum communication,quantum steganography is an important branch of quantum information *** a realistic quantum communication system,quantum noises are unavoidable and will seriously impact the safety and reliability of the quantum steganographic ***,it is very important to analyze the influence of noise on the quantum steganography protocol and how to reduce the effect of *** paper takes the quantum steganography protocol proposed in 2010 as an example to analyze the effects of noises on information qubits and secret message qubits in the four primary quantum noise *** results show that when the noise factor of one quantum channel noise is known,the size of the noise factor of the other quantum channel can be adjusted accordingly,such as artificially applying noise,so that the influence of noises on the protocol is *** addition,this paper also proposes a method of improving the efficiency of the steganographic protocol in a noisy environment.

关键词： Quantum steganography quantum noise noise channel fidelity efficiency

来源：评论

学校读者我要写书评

暂无评论

Vehicle Classification Based on Deep Convolutional Neural Networks Model for Traffic Surveillance Systems 15

Vehicle Classification Based on Deep Convolutional Neural Ne...

引用

15th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2018

作者： Zakria Cai, Jingye Deng, Jianhua Khokhar, Muhammad Saddam Umar Aftab, Muhammad School of Information and Software Engineering University of Electronic Science and Technology of China China School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China

ISBN: (纸本)9781728115351

Due to growth of vehicles in urban cities, such problems are increases traffic control systems, security and crime investigation, intelligent parking and electronic toll collection. Moreover, Logistics access management system (LMS)is also a big problem in urban cities and all the issues are challenging and demands to develop effective and efficient approach for vehicle classification. Mostly, traditional vehicle classification uses hand craft feature extraction method like SIFT, Surf, HoG etc. However, these approaches are not efficient in results. This paper presents the efficient framework for vehicle classification by using Inception-v3 model for image vector features extraction that is most advance deep learning neural network, and this model is not used before for vehicle classification. After that, different classification algorithms are implemented on the feature vector. The classification conducted on three vehicle datasets and results demonstration is helpful for researchers to choose dataset with algorithm performance. © 2018 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Biclustering analysis and comparison for gene expression data

引用

Revista de la Facultad de Ingenieria 2016年第12期31卷 183-198页

作者： Yin, Lu Liu, Yongguo School of Computer Science and Engineering University of Electronic Science and Technology of China ChengDu SiChuan611731 China School of Computer Engineering Huaiyin Institute of Technology HuaiAn JiangSu223003 China School of Information and Software Engineering University of Electronic Science and Technology of China ChengDu SiChuan610054 China

The advance of the high throughput technology allows to quantitative measure the level of expression of thousands of genes under several experimental conditions at one time which quickly produce many gene expression data. For efficiency processing the above data, many biclustering algorithms and many criterions are proposed. Even so, different biclustering algorithms generate different type of biclusters and draw various conclusions because the definition of the bicluster and its evaluation criterions used indifferent biclustering algorithms are similar but not the same. But there are only a few literatures forcomparing the biclustering algorithms and its evaluationcriterions. In this paper, the biclusters obtained by 11 biclustering algorithms are evaluated according to 7 criterions. In addition, the weight enrichment score and the proportion of the enriched biclusters by gene ontology are used for evaluating the biological significance of the biclustering *** analyzing the results of the chose biclustering algorithms, this study suggest that the biclustering algorithms provide a flexible solution for analyzing multiple types of gene expression data, and manyinteresting results are observedwhich facilitate exploratory data mining of gene expression data.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Extracting regular behaviors from social media networks

Extracting regular behaviors from social media networks

引用

3rd International Conference on Multimedia Information Networking and Security, MINES 2011

作者： Yan, Leiming Wang, Jinwei School of Computer and Software Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9780769545592

Social media network analysis has become very popular in recent years. How do real networks evolve over time? What are the normal evolving behaviors in a social media network? In order to extract behaviors occurring regularly to reveal the microscopic evolving properties in social networks, the evolving process of networks is modeled as stochastic states transition, and the evolving behaviors are described as topological structure changes of a series of sub graphs. Then, based on Maximal Frequent Sub graph mining technology, RB Miner (Regular Behaviors Miner) algorithm is proposed to identify such regular behaviors in network dataset. The empirical evaluation using both synthetic and real dataset verifies that the proposed algorithm is valid, and the regular behavior patterns show more dynamic information hidden in evolving social networks than normal frequent sub graph patterns. © 2011 IEEE.

关键词： Miners

来源：评论

学校读者我要写书评

暂无评论

Long short term memory model for analysis and forecast of PM2.5 4th

Long short term memory model for analysis and forecast of PM...

引用

4th International Conference on Cloud Computing and Security, ICCCS 2018

作者： Yan, Leiming Zhou, Min Wu, Yaowen Yan, Luqi Jiangsu Engineering Center of Network Monitoring School of Computer and Software Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9783030000059

Atmospheric PM2.5 is a pollutant that has a major impact on the atmospheric environment and human health. Based on LSTM, we construct two prediction models, Stack LSTM and Encoder-Decoder, and evaluate the prediction performance of the model through four years of meteorological data training and testing models in Nanjing, Beijing, and Sanya. In the experiment, using the meteorological factors, contaminant factors, seasonal factors, and the normalized results of PM2.5 as input, the daily average PM2.5 concentration is predicted from 1 to 3 days. Experimental results show that the LSTM model has better performance than Random Forest and Encoder-Decoder. Using Nanjing as an example, comparing the forecast results of Nanjing PM2.5 with the data released by the environmental authorities, it is found that the value of the PM2.5 concentration predicted by the LSTM model is very close to the value of PM2.5 monitored by Nanjing’s environmental authorities. In prediction of PM2.5 for three consecutive days, the Root Mean Square Error (RMSE) of the LSTM model is only 18.96. Under the LSTM model, the prediction result of the three cities are better than other prediction models, which shows that the LSTM model has a good adaptability in predicting the PM2.5 concentration. © Springer Nature Switzerland AG 2018.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Method for Improving CNN-Based Image Recognition Using DCGAN

引用

computers, Materials & Continua 2018年第10期57卷 167-178页

作者： Wei Fang Feihong Zhang Victor S.Sheng Yewen Ding School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjing210044China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing210023China Computer Science Department University of Central ArkansasConway AR72035USA

Image recognition has always been a hot research topic in the scientific community and *** emergence of convolutional neural networks(CNN)has made this technology turned into research focus on the field of computer vision,especially in image *** it makes the recognition result largely dependent on the number and quality of training ***,DCGAN has become a frontier method for generating images,sounds,and *** this paper,DCGAN is used to generate sample that is difficult to collect and proposed an efficient design method of generating *** combine DCGAN with CNN for the second *** DCGAN to generate samples and training in image recognition model,which based by *** method can enhance the classification model and effectively improve the accuracy of image *** the experiment,we used the radar profile as dataset for 4 categories and achieved satisfactory classification *** paper applies image recognition technology to the meteorological field.

关键词： DCGAN image recognition CNN samples

来源：评论

学校读者我要写书评

暂无评论

Illumination invariant and face recognition based on homomorphic filtering and LoG operator1

引用

International Journal of Advancements in Computing Technology 2012年第21期4卷 17-24页

作者： Fan, Chun-Nian Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

In order to eliminate the effect of varying illumination on face recognition, a novel illumination invariant method based on homomorphic filtering and LoG operator is proposed. The method first performs homomorphic filtering on image under various lighting conditions, whose key component is a Difference of Gaussian (DoG) filter, which can effectively reduce the effect of varying illumination. Then a LoG operator is used for illumination invariant extraction. Experimental results on the Yale face database B and CMU PIE database show that the proposed method can effectively eliminate the effect of varying illumination on face recognition, and the extracted illumination invariant is robust.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Lever Arm Compensation of Autonomous Underwater Vehicle for Fast Transfer Alignment

引用

computers, Materials & Continua 2019年第4期59卷 105-118页

作者： Qi Wang Changsong Yang Shaoen Wu Yuxiang Wang School of Computer and software Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China Department of Computer Science Ball State UniversityMuncie 47306USA

Transfer alignment is used to initialize SINS(Strapdown Inertial Navigation System)in ***-arm effect compensation is studied existing in an AUV(Autonomous Underwater Vehicle)before launched from the mother *** AUV is equipped with SINS,Doppler Velocity Log,depth sensor and other navigation *** lever arm will cause large error on the transfer alignment between master inertial navigation system and slave inertial navigation system,especially in big ship *** paper presents a novel method that can effectively estimate and compensate the flexural lever arm between the main inertial navigation system mounted on the mother ship and the slave inertial navigation system equipped on the *** nonlinear measurement equation of angular rate is derived based on three successive rotations of the body frame of the master inertial navigation *** filter is utilized as the nonlinear estimator for its capability of non-linear *** analysis was conducted on the SINS state vector based on singular value decomposition *** equation of SINS was adopted as the system state *** experiments were conducted and results showed that the proposed method can estimate the flexural lever arm more accurately,the precision of transfer alignment was improved and alignment time was shortened accordingly.

关键词： Transfer alignment SINS lever-arm effect AUV observability analysis

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：