10 results on '"Zhang, Tong"'
Search Results
2. Overview of Text Mining
- Author
-
Weiss, Sholom M., Indurkhya, Nitin, Zhang, Tong, Gries, David, Series editor, Schneider, Fred B., Series editor, Weiss, Sholom M., Indurkhya, Nitin, and Zhang, Tong
- Published
- 2015
- Full Text
- View/download PDF
3. P 2 FEViT: Plug-and-Play CNN Feature Embedded Hybrid Vision Transformer for Remote Sensing Image Classification.
- Author
-
Wang, Guanqun, Chen, He, Chen, Liang, Zhuang, Yin, Zhang, Shanghang, Zhang, Tong, Dong, Hao, and Gao, Peng
- Subjects
IMAGE recognition (Computer vision) ,TRANSFORMER models ,REMOTE sensing ,CONVOLUTIONAL neural networks ,DATA mining ,SPATIAL ability - Abstract
Remote sensing image classification (RSIC) is a classical and fundamental task in the intelligent interpretation of remote sensing imagery, which can provide unique labeling information for each acquired remote sensing image. Thanks to the potent global context information extraction ability of the multi-head self-attention (MSA) mechanism, visual transformer (ViT)-based architectures have shown excellent capability in natural scene image classification. However, in order to achieve powerful RSIC performance, it is insufficient to capture global spatial information alone. Specifically, for fine-grained target recognition tasks with high inter-class similarity, discriminative and effective local feature representations are key to correct classification. In addition, due to the lack of inductive biases, the powerful global spatial context representation capability of ViT requires lengthy training procedures and large-scale pre-training data volume. To solve the above problems, a hybrid architecture of convolution neural network (CNN) and ViT is proposed to improve the RSIC ability, called P 2 FEViT, which integrates plug-and-play CNN features with ViT. In this paper, the feature representation capabilities of CNN and ViT applying for RSIC are first analyzed. Second, aiming to integrate the advantages of CNN and ViT, a novel approach embedding CNN features into the ViT architecture is proposed, which can make the model synchronously capture and fuse global context and local multimodal information to further improve the classification capability of ViT. Third, based on the hybrid structure, only a simple cross-entropy loss is employed for model training. The model can also have rapid and comfortable convergence with relatively less training data than the original ViT. Finally, extensive experiments are conducted on the public and challenging remote sensing scene classification dataset of NWPU-RESISC45 (NWPU-R45) and the self-built fine-grained target classification dataset called BIT-AFGR50. The experimental results demonstrate that the proposed P 2 FEViT can effectively improve the feature description capability and obtain outstanding image classification performance, while significantly reducing the high dependence of ViT on large-scale pre-training data volume and accelerating the convergence speed. The code and self-built dataset will be released at our webpages. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
4. Obstructed Nearest Neighbor Query Under Uncertainty in the Internet of Things Environment
- Author
-
Li Chuan-Wen, Lu Guang, Zhang Yi, Zhang Tong, and Chen Kun-Lun
- Subjects
General Computer Science ,Computer science ,Internet of Things ,0102 computer and information sciences ,02 engineering and technology ,computer.software_genre ,uncertain data ,01 natural sciences ,k-nearest neighbors algorithm ,020204 information systems ,0202 electrical engineering, electronic engineering, information engineering ,General Materials Science ,Pruning (decision trees) ,Spatial analysis ,Nearest neighbor ,business.industry ,General Engineering ,010201 computation theory & mathematics ,Scalability ,Location-based service ,Trajectory ,Probability distribution ,The Internet ,lcsh:Electrical engineering. Electronics. Nuclear engineering ,Data mining ,business ,lcsh:TK1-9971 ,computer ,obstructed space - Abstract
The internet of things provides a convenient life for all of us. Physical devices with locational systems connected to the internet can provide navigation and recommendation services in cooperation with the Location Based Services (LBS). The nearest neighbor query is the most common query type in the LBS research area. On the other hand, due to privacy protection or inaccuracies in measurement instructions, data uncertainties are typical in the IoT environment. This uncertainty will affect the results of nearest neighbor queries. The existence of plane obstacles also brings the challenge to the spatial data query. In this paper, the obstacles and data uncertainties in continuous nearest query are studied. We also designed a pruning strategy that significantly reduced the number of objects to be calculated. In addition, we propose a concept of safe region and an algorithm to generate a safe region. We also designed an index method for saving safe regions. The experimental results show that our approach outperforms the state-of-the-art one in efficiency and scalability.
- Published
- 2021
5. Application of frequent item set mining algorithm in IDS based on Hadoop framework
- Author
-
Hou Ying and Zhang Tong
- Subjects
0209 industrial biotechnology ,Computer science ,business.industry ,Event (computing) ,Big data ,02 engineering and technology ,Intrusion detection system ,computer.software_genre ,020901 industrial engineering & automation ,Item set mining ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Data mining ,business ,computer - Abstract
With the coming of big data time, the huge number of IDS log makes the traditional computing technology and systems cannot cope and deal with the needs of the analysis of security log, so large-scale computing power has become a prerequisite for the effective implementation of data mining technology. Based on the Hadoop framework, this paper applies the parallel frequent item sets mining algorithm to the Snort Intrusion Detection System, which solves the problem that Snort-IDS cannot judge the security event itself. At the same time, it also solves the problem of decreasing the processing speed due to the enormous increase of data. So that the system has the ability of detecting new intrusions, enrich and improve the Snort-IDS functional system and the performance.
- Published
- 2018
6. Local–Global Memory Neural Network for Medication Prediction.
- Author
-
Song, Jun, Wang, Yueyang, Tang, Siliang, Zhang, Yin, Chen, Zhigang, Zhang, Zhongfei, Zhang, Tong, and Wu, Fei
- Subjects
SEQUENTIAL pattern mining ,SEQUENTIAL learning ,ELECTRONIC health records ,MEMORY ,DATA mining - Abstract
Electronic medical records (EMRs) play an important role in medical data mining and sequential data learning. In this article, we propose to use a sequential neural network with dynamic content-based memories to predict future medications, given EMRs. The local–global memory neural network contains two layers of memories: the local memory and the global memory. Particularly, our method learns the hidden knowledge within EMRs by locally remembering individual patterns of a patient (via local memory) and globally remembering group evidence of disease (via global memory). In addition, we show how our model can be modified to classify the hidden states of EMRs from different patients at each time step into different phases that indicate the progressions of medications in terms of a specific disease, in an unsupervised manner. Experimental results on real EMRs data sets show that, by learning EMRs with external local and global memories, with regard to a given disease, our model improves the prediction performance compared with several alternative methods. [ABSTRACT FROM AUTHOR]
- Published
- 2021
- Full Text
- View/download PDF
7. $\ell_{1}$ -Norm Heteroscedastic Discriminant Analysis Under Mixture of Gaussian Distributions.
- Author
-
Zheng, Wenming, Lu, Cheng, Lin, Zhouchen, Zhang, Tong, Cui, Zhen, and Yang, Wankou
- Subjects
GAUSSIAN distribution ,DISCRIMINANT analysis ,RAYLEIGH quotient ,HETEROSCEDASTICITY ,FEATURE extraction ,DATA distribution ,IMAGE color analysis ,CLASS differences - Abstract
Fisher’s criterion is one of the most popular discriminant criteria for feature extraction. It is defined as the generalized Rayleigh quotient of the between-class scatter distance to the within-class scatter distance. Consequently, Fisher’s criterion does not take advantage of the discriminant information in the class covariance differences, and hence, its discriminant ability largely depends on the class mean differences. If the class mean distances are relatively large compared with the within-class scatter distance, Fisher’s criterion-based discriminant analysis methods may achieve a good discriminant performance. Otherwise, it may not deliver good results. Moreover, we observe that the between-class distance of Fisher’s criterion is based on the $\ell _{2}$ -norm, which would be disadvantageous to separate the classes with smaller class mean distances. To overcome the drawback of Fisher’s criterion, in this paper, we first derive a new discriminant criterion, expressed as a mixture of absolute generalized Rayleigh quotients, based on a Bayes error upper bound estimation, where mixture of Gaussians is adopted to approximate the real distribution of data samples. Then, the criterion is further modified by replacing $\ell _{2}$ -norm with $\ell _{1}$ one to better describe the between-class scatter distance, such that it would be more effective to separate the different classes. Moreover, we propose a novel $\ell _{1}$ -norm heteroscedastic discriminant analysis method based on the new discriminant analysis (L1-HDA/GM) for heteroscedastic feature extraction, in which the optimization problem of L1-HDA/GM can be efficiently solved by using the eigenvalue decomposition approach. Finally, we conduct extensive experiments on four real data sets and demonstrate that the proposed method achieves much competitive results compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
8. Method of Non-reference Image Quality Assessment of SSIM Based on Regional Weighted Entropy
- Author
-
Zhang Tong, Zhao Shuna, and Li Xue
- Subjects
genetic structures ,Image quality ,Quality assessment ,business.industry ,Image processing ,Pattern recognition ,computer.software_genre ,Visualization ,Region of interest ,Human visual system model ,Entropy (information theory) ,Weighted entropy ,Data mining ,Artificial intelligence ,business ,computer ,Mathematics - Abstract
The traditional SSIM haven't considered the limitation of the Human Visual System, which different attention paid to different area in the same picture, and information of the picture itself, leading to the final results are inconsistent between objective and subjective evaluating effects. A new image weighted index, which is regional weighted information entropy index, is put forward to solve this problem. This method divide image into visual region of interest based on the image edge features. By calculated space influence factor and regional entropy of each interest area, formulating regional weighted entropy. The weighted value of each visual interest region is generated after normalization of regional weighted information entropy, and the average weighted structural similarity of all visual interest areas is used as the image assessing index. Test results show that the new method fits human visual system characteristics, and correlates well with subjective perception scores.
- Published
- 2014
9. An Ensemble Approach for Detecting Anomalous User Behaviors.
- Author
-
Xi, Xiangyu, Zhang, Tong, Ye, Wei, Wen, Zhao, Zhang, Shikun, Du, Dongdong, and Gao, Qing
- Subjects
COMPUTER security ,COMPUTER algorithms ,ANOMALY detection (Computer security) ,CLOUD computing ,DATA mining - Abstract
An intruder of a company's network may use stolen login credentials to silently collect sensitive data. Such malicious user behavior is difficult to detect as long as it does not trigger access violation or data leak alert. In this paper, we propose to use an ensemble of three unsupervised anomaly detection algorithms, namely OCSVM, RNN and Isolation Forest, to detect abnormal user behavior patterns. Besides, an User Behavior Analytics (UBA) Platform is proposed to collect logs, extract features and conduct experiments. The experiment results indicate that our algorithm outperforms each individual algorithm with recall of 96.55% and precision of 91.24% on average, while both OCSVM and RNN suffer from anomalies in the training set, and i F o r e s t produces more false positives and false negatives in prediction. [ABSTRACT FROM AUTHOR]
- Published
- 2018
- Full Text
- View/download PDF
10. 16S rRNA gene high-throughput sequencing data mining of microbial diversity and interactions.
- Author
-
Ju, Feng and Zhang, Tong
- Subjects
- *
RNA sequencing , *RIBOSOMAL RNA , *MICROBIAL diversity , *DATA mining , *BIOINFORMATICS , *BIOTECHNOLOGY - Abstract
The ubiquitous occurrence of microorganisms gives rise to continuous public concerns regarding their pathogenicity and threats to human environment, as well as potential engineering benefits in biotechnology. The development and wide application of environmental biotechnology, for example in bioenergy production, wastewater treatment, bioremediation, and drinking water disinfection, have been bringing us with both environmental and economic benefits. Strikingly, extensive applications of microscopic and molecular techniques since 1990s have allowed engineers to peep into the microbiology in 'black box' of engineered microbial communities in biotechnological processes, providing guidelines for process design and optimization. Recently, revolutionary advances in DNA sequencing technologies and rapidly decreasing costs are altering conventional ways of microbiology and ecology research, as it launches an era of next-generation sequencing (NGS). The principal research burdens are now transforming from traditional labor-intensive wet-lab experiments to dealing with analysis of huge and informative NGS data, which is computationally expensive and bioinformatically challenging. This study discusses state-of-the-art bioinformatics and statistical analyses of 16S ribosomal RNA (rRNA) gene high-throughput sequencing (HTS) data from prevalent NGS platforms to promote its applications in exploring microbial diversity of functional and pathogenic microorganisms, as well as their interactions in biotechnological processes. [ABSTRACT FROM AUTHOR]
- Published
- 2015
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.