检索结果-内蒙古大学图书馆

13th CCF Conference on Computer Supported Cooperative Work and Social Computing (ChineseCSCW)

作者： Ban, Zihan Yan, Jiafei Sun, Hailong Beihang Univ Sch Comp Sci & Engn SKLSDE Lab Beijing 100191 Peoples R China Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing 100191 Peoples R China

ISBN: (纸本)9789811330445;9789811330438

Question answering community is an online service of user-generated content, where users seek help by posting questions and help others by offering answers. In question answering community, most of high quality answers are posted by some users called experts. The early identification of experts is of great significance to the success of community, based on which we can take measures to avoid the loss of expert users and encourage them to make more contributions. Different from the related works, we put forward an efficient method of supervised learning to identify potential topical experts in question answering community. Above all, we define and quantify the concepts of expert. Then on a specific topic, we extract the user features from three dimensions, including text-feature, behavior-feature and time-feature. Finally, we use the classification algorithms in machine learning to identify whether a user is the potential expert on current topic. Based on the data of Stack Overflow, we carry out a lot of experiments and implement a potential experts identification system. The results demonstrate the excellent effectiveness of our method based on artificial neural network model. Besides, we find that expert users are inclined to interact with other expert users, providing new ideas for future research on this subject.

关键词： Question answering community Potential experts identifying Feature extraction classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Frequency detection of experimental errors through Learning Analytics techniques 15

Frequency detection of experimental errors through Learning ...

引用

15th International Conference of Technology, Learning and Teaching of Electronics (TAEE)

作者： Costa, Heverton Marcos Alves, Gustavo R. da Silva, Juarez Bento da Mota Alves, Joao Bosco Univ Fed Santa Catarina PPGTIC Ararangua Brazil Polytech Porto CIETI Sch Engn Porto Portugal

ISBN: (纸本)9781665421614

The process that systematically collects and analyzes large volumes of data in order to improve the teaching-learning process is called Learning Analytics. Based on data processing, educational data mining and visualization, it is possible to monitor academic progress, enhancing actions on how the teacher should conduct the discipline. The objective of this research is to mine data from experiments carried out in the remote laboratory called "Virtual Instrument Systems in Reality". In order to create classification groups according to theoretical analysis studied in circuit analysis. The k-NN classification model was used for this research. The algorithm presented a very satisfactory result, its accuracy resulted in samples with values greater than 0.9. Considering an excellent form of classification analysis for circuits with 1:1, 0:1, 1:0 model.

关键词： Learning Analytics classification algorithm VISIR Remote Laboratory Simple Electrical Circuits

来源：评论

学校读者我要写书评

暂无评论

Detection of Android Malware Security on System Calls

Detection of Android Malware Security on System Calls

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Chen Da Zhang Hongmei Zhang Xiangli Guangxi Colleges and Universities Key Laboratory of cloud computing and complex systems Guilin University of Electronic Technology

ISBN: (纸本)9781509001668

In order to detect the security of Android software which isn't installed efficiently and accurately,this paper pro poses a new malware detection method based on system calls *** samples are pretreated by classification to refine and distinguish characteristics of various types of Android software;Restrictions and normalization are applied to process system call frequency information to improve the detection *** with the characteristics of random forest algorithms and data obtained,optimal training model is set up,and ultimately Android software security is detected *** experiments,the detection accuracy rate of Android tool software and financial software more than 93 percent,with higher accuracy.

关键词： system calls android system malware detection classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Interpretable CNN for ischemic stroke subtype classification with active model adaptation

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2022年第1期22卷 3-3页

作者： Zhang, Shuo Wang, Jing Pei, Lulu Liu, Kai Gao, Yuan Fang, Hui Zhang, Rui Zhao, Lu Sun, Shilei Wu, Jun Song, Bo Dai, Honghua Li, Runzhi Xu, Yuming Zhengzhou Univ Sch Informat Engn Zhengzhou Peoples R China Zhengzhou Univ Cooperat Innovat Ctr Internet Healthcare Zhengzhou Peoples R China Deakin Univ Inst Intelligent Syst Burwood NSW Australia Zhengzhou Univ Affiliated Hosp 1 Dept Neurol Zhengzhou Peoples R China

Background TOAST subtype classification is important for diagnosis and research of ischemic stroke. Limited by experience of neurologist and time-consuming manual adjudication, it is a big challenge to finish TOAST classification effectively. We propose a novel active deep learning architecture to classify TOAST. Methods To simulate the diagnosis process of neurologists, we drop the valueless features by XGB algorithm and rank the remaining ones. Utilizing active learning framework, we propose a novel causal CNN, in which it combines with a mixed active selection criterion to optimize the uncertainty of samples adaptively. Meanwhile, KL-focal loss derived from the enhancement of Focal loss by KL regularization is introduced to accelerate the iterative fine-tuning of the model. Results To evaluate the proposed method, we construct a dataset which consists of totally 2310 patients. In a series of sequential experiments, we verify the effectiveness of each contribution by different evaluation metrics. Experimental results show that the proposed method achieves competitive results on each evaluation metric. In this task, the improvement of AUC is the most obvious, reaching 77.4. Conclusions We construct a backbone causal CNN to simulate the neurologist process of that could enhance the internal interpretability. The research on clinical data also indicates the potential application value of this model in stroke medicine. Future work we would consider various data types and more comprehensive patient types to achieve fully automated subtype classification.

关键词： Interpretability Ischemic Stroke Active learning classification algorithm Loss function

来源：评论

学校读者我要写书评

暂无评论

Smart Healthcare Data Acquisition System 3rd

Smart Healthcare Data Acquisition System

引用

International Conference on Computational Vision and Bio-Inspired Computing (ICCVBIC)

作者： Ghole, Tanvi Karande, Shruti Mondkar, Harshita Kulkarni, Sujata Sardar Patel Inst Technol Dept Elect & Telecommun Mumbai Maharashtra India

ISBN: (纸本)9783030372187;9783030372170

A general healthcare system monitors the parameters and simply display the readings. The records are maintained on paper. This paper aims in building an independent offline system for maintaining records in regions where network connectivity is an issue. After providing basic identification information it automatically logs vital parameters of patients acquired from the sensors. The records are maintained digitally and the system does a personalized data analysis for each patient, as "normality" is subjective to every patient. This system is trained to classify such minute details and create a cluster for each patient individually. As and when patient visit for checkup the data is added to his cluster and analysis is performed on it. Various suggestions are provided to the patient in order to avoid worsening the condition. It is a platform that provides the doctor with the patient's entire history when they visit a non-digitized area.

关键词： Personalized healthcare Data analysis Machine learning Clustering of data classification algorithm

来源：评论

学校读者我要写书评

暂无评论

An Empirical Comparison of Classifiers to Analyze Intrusion Detection 5

An Empirical Comparison of Classifiers to Analyze Intrusion ...

引用

5th International Conference on Advanced Computing & Communication Technologies (ACCT)

作者： Aggarwal, Preeti Sharma, Sudhir Kumar Ansal Univ Sch Engn & Technol Gurgaon India

ISBN: (纸本)9781479984886

The massive data exchange on the web has deeply increased the risk of malicious activities thereby propelling the research in the area of Intrusion Detection System (IDS). This paper aims to first select ten classification algorithms based on their efficiency in terms of speed, capability to handle large dataset and dependency on parameter tuning and then simulates the ten selected existing classifiers on a data mining tool Weka for KDD' 99 dataset. The simulation results are evaluated and benchmarked based on the generic evaluation metrics for IDS like F-score and accuracy.

关键词： Intrusion detection syste NSL-KDD classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Feature Selection and Intrusion Detection in Cloud Environment based on Machine Learning algorithms 15

Feature Selection and Intrusion Detection in Cloud Environme...

引用

15th IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) / 16th IEEE International Conference on Ubiquitous Computing and Communications (IUCC)

作者： Javadpour, Amir Abharian, Sanaz Kazemi Wang, Guojun Guangzhou Univ Guangzhou Guangdong Peoples R China Sharif Univ Technol Tehran Iran

ISBN: (纸本)9781538637906

Characteristics and way of behavior of attacks and infiltrators on computer networks are very difficult and need an expert. In addition;the advancement of computer networks, the number of attacks and infiltrations is also increasing. In fact, the knowledge coming from expert will lose its value over time and must be updated and made available to the system and this makes the need for expert person always felt. In machine learning techniques, knowledge is extracted from the data itself which has diminished the role of the expert. Various methods used to detect intrusions, such as statistical models, safe system approach, neural networks, etc., all weaken the fact that it uses all the features of an information packet rotating in the network for intrusion detection. Also, the huge volume of information and the unthinkable state space is also an important issue in the detection of intrusion. Therefore, the need for automatic identification of new and suspicious patterns in attempt for intrusion with the use of more efficient methods (Lower cost and higher performance) is needed more than before. The purpose of this paper is to provide a new method based on intrusion detection systems and its various architectures aimed at increasing the accuracy of intrusion detection in cloud computing.

关键词： intrusion detection feature Selection classification algorithm machine learning neural network cloud computing

来源：评论

学校读者我要写书评

暂无评论

Blood Donor's safety using Data Mining 1

Blood Donor's safety using Data Mining

引用

International Conference on Green Computing and Internet of Things (ICGCIoT)

作者： Patil, Rohini Pawar, Pooja Poi, Madhu Patil, Tejashree Ghuse, Namrata SITRC Dept Comp Sci Nasik India

ISBN: (纸本)9781467379106

Blood is most essential constituent in human body. Blood centers collect, process and transport blood to hospitals and other health care centers. Sometimes blood is collected directly from blood donors rather than taking it from blood bank. Nowadays donor safety is major issue as blood is collected from different donors. Small amount of donors face reactions after donating blood and if not treated on time then it may lead to serious injury. The reactions that occur in the donor during blood donation at different hospitals and blood banks is collected, organized and analyzed by the DonorHART tool [1, 3]. The donor reactions information are captured and analyzed by DonorHART system[1]. The tool also monitors and researches the risks involved for donors at the time of blood donation or after the donation process. Data mining makes an effort to reveal the patterns in data that are difficult to detect and recognize with automatic pattern recognition. It is analyzing of data and then summarizing it into different form which is called as information and is taken from different databases. The proposed system is a web based application which helps to reduce the human mistakes or errors and different techniques can be applied for blood type classification, diagnosing diabetic symptoms, classifying blood type and identifying different donors reaction and apply preventive measures against them.

关键词： Blood Bank DonorHart tool Data Mining Database classification algorithm

来源：评论

学校读者我要写书评

暂无评论

Classify high dimensional datasets using discriminant positive negative association rules 5

Classify high dimensional datasets using discriminant positi...

引用

5th Asian Conference on Defense Technology (ACDT)

作者： Thanh Do Van Hieu Do Duc Giap Cu Nguyen Nguyen Tat Thanh Univ Dept Informat Technol Hcm Vietnam Univ Sci & Tech Hanoi VAST Dept Infor & Com Technol Hanoi Vietnam Thuongmai Univ Dept Manag Infor Sys & E Com Hanoi Vietnam

ISBN: (纸本)9781538676783

The purpose of this paper is to investigate the ability of binary classification using the possitive negative association rules mining (PNARs) for large dataset. The PNARs (as understood until now) called narrow PNARs (NPNARs for short) as well as their generalized forms called expanded PNARs (EPNARs for short) will be investigated. The paper proposes a classification algorithm based on mining the discriminant NPNARs and EPNARs. The algorithm integrates Dimensionality Reduction, Rule Generation, Removal of redundant rules and classification. The number of classified instances in testing datasets and the classification performance using the valid disriminant NPNARs and EPNARs found out by the proposed algorithm are compared with each other and with 12 other classification algorithms. Experimental results show that the mining of EPNARs rather than that of NPNARs has prospects to he a classification technique applied in the real world. The paper also outlines some issues that need to be researched in the near future so that using the mining of the discriminant EPNARs becomes an efficient technique for classifying high dimensional datasets.

关键词： classification prediction dimensionality reduction positive nagative association rules classification algorithm

来源：评论

学校读者我要写书评

暂无评论

NEW TECHNIQUES FOR IMPROVING THE PRACTICALITY OF AN SVM-BASED SPEECH/MUSIC CLASSIFIER

NEW TECHNIQUES FOR IMPROVING THE PRACTICALITY OF AN SVM-BASE...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Lim, Chungsoo Lee, Seong-Ro Lee, Yeon-Woo Chang, Joon-Hyuk Hanyang Univ Seoul 133791 South Korea Mokpo Natl Univ Mokpo South Korea

ISBN: (纸本)9781467300469

Variable bit-rate coding introduced for effective utilization of limited communication bandwidth requires accurate classification of input signals. This paper investigates implementation of a support vector machine (SVM)-based speech/music classifier in the selectable mode vocoder (SMV) framework, which is a standard codec adopted by the Third-Generation Partnership Project 2 (3GPP2). A support vector machine is well known for its superior pattern recognition capability;however, it is accompanied by a high computational cost. In order to achieve a more practical system, three techniques are proposed for the SVM-based speech/music classifier. The first is to prune support vectors that least contribute to the output of the SVM, while the other two are aimed at reducing the number of classification requests to the SVM-based classifier by eliminating or redirecting some of the classification requests to the classifier.

关键词： Codecs classification algorithm embedded software

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：