检索结果-内蒙古大学图书馆

15th Asia-Pacific Web Conference on Web Technologies and Applications, APWeb 2013

作者： Xiao, Yingyuan Shen, Yan Wang, Hongya Wang, Xiaoye Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Key Laboratory of Computer Vision and System Tianjin University of Technology 300384 China Donghua University 201620 Shanghai China

ISBN: (纸本)9783642374005

Motivated by the fact that a great deal of information is closely related to spatial location, a new type of skyline queries, location-dependent skyline query (LDSQ), was recently presented. Different from the conventional skyline query, which focuses on non-spatial attributes of objects and does not consider location relationship (i.e., proximity), LDSQ considers both the proximity and non-spatial attributes of objects. In this paper, we explore the problem of efficient LDSQ processing in a mobile environment. We propose a novel LDSQ processing method based on peer-to-peer (P2P) sharing. Extensive experiments are conducted, and the experimental results demonstrate the effectiveness of our methods. © 2013 Springer-Verlag.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

A new dynamic method of machine learning from transition examples

Journal of Software

引用

Journal of Software 2011年第10期6卷 2064-2067页

作者： Zhang, Xiao-Dan Zhang, De-Gan Zhao, De-Xin Kang, Xue-Jing Qiao, Xiao-Dong Institute of Scientific and Technical Information of China Beijing 100038 China Tianjin Key Lab of Intelligent Computing and Novel software Technology Tianjin University of Technology China Key Laboratory of Computer Vision and System Tianjin University of Technology China

It's well known machine learning from examples is an effective method to solve non-linear classification problem. A new dynamic method of machine learning from transition example is given in this paper. This method can improve the traditional method ID3 which learns from static eigenvalues of examples. The limits of the traditional method ID3 lie on no comprehension and no memory, especially, no the varieties and dynamic correlation of eigenvalues. In the new method, it can learn from dynamic eigenvalues, the change of data can be learned because the training data is the initial eigenvalue and the end eigenvalue in the interval. All eigenvalue's varieties and correlation can be understood and remembered in application. By test experiments, the new method can be used as classifier when the multi-parameters are dynamic correlation, and it has special use in the many kinds of information fusion fields. © 2011 ACADEMY PUBLISHER.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Large-scale video compression： recent advances and challenges

引用

Frontiers of computer Science 2018年第5期12卷 825-839页

作者： Tao TIAN Hanli WANG Department of Computer Science and Technology Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Shanghai Engineering Research Center of Industrial Vision Perception & Intelligent Computing Shanghai 200092 China

The evolution of social network and multimedia technologies encourage more and more people to generate and upload visual information, which leads to the generation of large-scale video data. Therefore, preeminent compression technologies are highly desired to facilitate the storage and transmission of these tremendous video data for a wide variety of applications. In this paper, a systematic review of the recent advances for large-scale video compression （LSVC） is presented. Specifically, fast video coding algorithms and effective models to improve video compression efficiency are introduced in detail, since coding complexity and compression efficiency are two important factors to evaluate video coding approaches. Finally, the challenges and fu- ture research trends for LSVC are discussed.

关键词： large-scale video compression fast video coding compression efficiency

来源：评论

学校读者我要写书评

暂无评论

Data interpolating over RFID data streams for missed readings

Data interpolating over RFID data streams for missed reading...

引用

14th International Conference on Web-Age Information Management, WAIM 2013

作者： Xiao, Yingyuan Jiang, Tao Li, Yukun Xu, Guangquan Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Key Laboratory of Computer Vision and System Tianjin University of Technology 300384 China School of Computer Science and Technology Tianjin University 300072 Tianjin China

ISBN: (纸本)9783642395260

While tracing objects or analyzing human activities with RFID data sets, the quality of RFID data is a crucial aspect. The raw RFID data streams, however, tend to be noisy, including missed readings and unreliable readings. Traditional data cleaning tends to focus on a small set of well-defined tasks, including transformation, matching, and duplicate elimination. In this paper, we focus on exploring efficient methods for interpolating missed readings. We propose a novel probabilistic interpolating method and three novel deterministic interpolating methods based on time interval, containment relationship and inertia of objects, respectively. We conduct extensive experiments and the experimental results demonstrate the feasibility and effectiveness of our methods. © 2013 Springer-Verlag.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Ultra-large mode area multi-core orbital angular momentum transmission fiber designed by neural network and optimization algorithms

引用

Optoelectronics Letters 2023年第12期19卷 744-751页

作者： GU Zhiwei HUANG Wei ZHANG Ran FAN Junjie SONG Binbin Key Laboratory of Computer Vision and Systems(Ministry of Education) School of Computer Science and EngineeringTianjin University of TechnologyTianjin 300384China Engineering Research Center of Learning-Based Intelligent System(Ministry of Education) Tianjin University of TechnologyTianjin 300384China

A large mode area multi-core orbital angular momentum(OAM)transmission fiber is designed and optimized by neural network and optimization *** neural network model has been established first to predict the optical properties of multi-core OAM transmission fibers with high accuracy and speed,including mode area,nonlinear coefficient,purity,dispersion,and effective index *** the trained neural network model is combined with different particle swarm optimization(PSO)algorithms for automatic iterative optimization of multi-core structures *** to the structural advantages of multi-core fiber and the automatic optimization process,we designed a number of multi-core structures with high OAM mode purity(>95%)and ultra-large mode area(>3000µm^(2)),which is larger by more than an order of magnitude compared to the conventional ring-core OAM transmission fibers.

关键词： network fiber OAM

来源：评论

学校读者我要写书评

暂无评论

Time series prediction based on decomposition and synthesis 2

Time series prediction based on decomposition and synthesis

引用

2nd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2019

作者： Li, Junguang Yang, Shuying Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China

ISBN: (纸本)9781450372619

In recent years, the deep learning method has been widely used in the financial field, promoting the development of stock price forecasting. The time series data in reality has complex characteristics, and the traditional single model has great limitations in prediction. For the problem that the time series data is too complicated, this paper proposes a time series mixed prediction model based on decomposition and synthesis. The time series is decomposed by empirical mode decomposition (EMD). For the problem that the calculation complexity becomes larger after decomposition, and the prediction error of each sub-component leads to the total error is still large. In this paper, the sampled entropy (SE) method is used to combine the decomposed subsequences, which reduces the computational complexity and total error of the algorithm. The combined sequence is predicted by the LSTM neural network. The experimental result show that the prediction accuracy of the model is significantly improved compared with the traditional model. © 2019 ACM.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Defending Poisoning Attacks in Federated Learning via Loss Value Normal Distribution 26

Defending Poisoning Attacks in Federated Learning via Loss V...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Han, Fei Zhang, Yao Zhao, Meng Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System of Ministry of Education Tianjin300384 China

ISBN: (纸本)9798350331684

As an emerging distributed machine learning paradigm, federated learning (FL) only shares model updates between clients and servers, and training data are secured on each client's device. Due to local data privacy, FL is vulnerable to poisoning attacks, which causes serious degradation in the model performance. In this paper, we analyze the targeted poisoning attacks of FL and reveal that when the data held by each client of FL is independent and identically distributed (iid), the loss of all non-poisoned models on some clean dataset agrees with a normal distribution (ND), while the loss value of the poisoned model deviates from this distribution. Based on this observation, we propose a method named ND-defense to defend FL targeted poisoning attacks. We set a small clean test dataset on the server, compute the loss of each client model on it, detect the abnormal ones with the proposed loss-value-based inspection algorithm, and then only aggregate the benign clients' models to get the global model. We conducted experiments on three benchmark datasets and compared several state-of-the-art defense methods. The results show that our NDdefense is effective in defending against targeted poisoning attacks. © 2023 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Research and implementation of POI recommendation system integrating temporal feature 3

Research and implementation of POI recommendation system int...

引用

3rd IEEE International Conference on Big Data Analysis, ICBDA 2018

作者： Liu, Jinxin Jiao, Xu Jin, Youzhi Liu, Xinyu Liu, Li Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China

ISBN: (纸本)9781538647936

Point-of-Interest is an interesting research topic of personalized recommendation. In this paper, a new position-based recommendation framework is proposing by using the time attribute. We establish a user matrix with user check-in data sets that contain time and location information. The user matrix is divided into the sub-matrices according to the set period and then every sub-matrix is decomposed into the user checking preference matrix and position feature matrix by using the non-negative matrix factorization. The user's attendance preferences at each time are integrated to get the user's final check-in preference for the candidate location to make recommendations more consistent with the needs of users. © 2018 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Visual Pop-can detection method based on adaboost

Visual Pop-can detection method based on adaboost

引用

3rd International Conference on Manufacturing Engineering and Process, ICMEP 2014

作者： Lin, Xin Yi Xue, Yan Bing Guo, Bao Hong Key Laboratory of Computer Vision and System Ministry of Education University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China

ISBN: (纸本)9783038350842

This paper puts forward a visual method of detecting pop-cans based on AdaBoost Algorithm. This method, is basing on the idea of AdaBoost Algorithm, and we use Haar Feature and LBP Feature to extract pop-can characteristics respectively. Finally we compare the differences of the training processes and the experiment results between these two detectors. It shows that these pop-can detectors that are trained by this visual method have high detection rate and speed. © (2014) Trans Tech Publications, Switzerland.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Object recognition using a Bayesian network imitating human neocortex

Object recognition using a Bayesian network imitating human ...

引用

2009 2nd International Congress on Image and Signal Processing, CISP'09

作者： Lei, Wang Xianbin, Wen Xu, Jiao Jianguang, Zhang Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin 300191 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300191 China

ISBN: (纸本)9781424441310

After Mountcastle proposed the theory that all parts of mammalian neocortex are uniform [1], more and more evidences were found to prove that no matter what function the field of neocortex provide, the organizing of cortex cells are same and have an hierarchical structure. It can be inferred every unit of neocortex process information using an identical algorithm. This means if people can find and imitate this algorithm, all intelligence work will be resolved in one way, the only difference is using different sensors. Base on this, Hawkins proposed a top-down model of neocortical operation [2], in which model, both continuous time and prediction play important roles in human's invariant recognition. Then George and Hawkins developed an inspired framework named "Hierarchical Temporal Memory" [3], using a hierarchical Bayesian network to perform prediction and temporal sequence in training the network, which partially implements Hawkins' model, and can provide a rather good performance in invariant recognition. We current study is extending their work by implementing the framework in visual category recognition field. ©2009 IEEE.

关键词： Bayesian networks

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：