检索结果-内蒙古大学图书馆

11th international conference on Multimedia and Network Information Systems (MISSI)

作者： Conde-Cespedes, Patricia Chavando, Julie Deberry, Eliza Inst Super Elect Paris 28 Rue Notre Dame Champs Paris France Stanford Univ San Francisco CA USA

ISBN: (纸本)9783319986784;9783319986777

Twitter constantly attempts to suspend dangerous or suspicious accounts. this strategy has been questionably ineffective as users continuously recreate their accounts. As a result, there are many accounts that are left unchecked and potentially dangerous to the promotion of ideals and attacks. In this paper, we present a classification method based on sentiment analysis and word2vec to detect suspicious accounts. We evaluate our approach in real use case of main concern using data crawled directly from Twitter. Our classifier returns high accuracy in detecting suspicious accounts.

关键词： Prediction Classification Twitter Word2Vec Sentiment analysis SVM Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Electrical Equipment through thermal Imaging and Interpretable Machine learning Applied on a Newly-introduced dataset

Fault Diagnosis of Electrical Equipment through Thermal Imag...

引用

international conference of Signal Processing and intelligent Systems (ICSPIS)

作者： Mohamad Najafi Yasser Baleghi Sayyed Asghar Gholamian Seyyed Mehdi Mirimani Electrical & Computer Engineering Noshivani University of Technology Babol Iran Power System Noshivani University of Technology Babol Iran

ISBN: (数字)9781728186290

ISBN: (纸本)9781728186306

In this study, an interpretable, fully automated pipeline for condition monitoring of electrical equipment using thermal imaging is proposed. A wider array of defects in comparison with other thermography surveys is investigated. While many fault conditions led to significant heat dissipation, a number of fault conditions result in even less heat dissipation than that of healthy equipment, implying a challenging segmentation. To overcome this problem, a pre-processing step is applied which divides data into two distinct categories according to the equipment's thermal state, namely 'cold' and 'hot' states. Afterwards, Random Forest and AdaBoost classifiers are utilized for segmentation using a sliding window approach, with regard to Interpretable Machine learning. Moreover, a new dataset of infrared images of transformer and 3-phase induction motors is created. the proposed method has been evaluated on the very same dataset, achieving state-of-the-art results.

关键词： Heating systems Image segmentation Pipelines Imaging Signal processing Feature extraction Testing

来源：评论

学校读者我要写书评

暂无评论

Using Dtrace for Machine learning Solutions in Malware Detection

Using Dtrace for Machine Learning Solutions in Malware Detec...

引用

international conference on Computing and Networking Technology (ICCNT)

作者： Aiswarya Mohan K.P. Saranya Chandran Gilad Gressel T.U. Arjun Vipin Pavithran Cyber Security Systems and Networks Amrita Viswa Vidhyapeetham Amritapuri India

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Malware cannot be ignored today as evidenced by the havoc created by Wannacry[29], [12], [23]. Every day malicious actors are writing more intelligent malware. the attacks evolve as actors learn to evade detection techniques, which makes malware detection a pressing need. Research is being done on the Windows platform to detect malware in many forms[55], [54], [31]. In our work, we focus on detecting Windows malware. We use Dtrace[18], a dynamic tracing framework recently introduced in Windows, to collect system call information from an affected system. We are trying to expand the utility of Dtrace to detect malware. We process the collected system-call data to extract features and to create a dataset suitable for machine learning. Using machine learning, we build a decision tree classifier and show that the model can detect malware using the sequences of system-calls made by malicious processes. We obtained an f1 score of 91 with maintaining an even class distribution between the benign and malicious labels.

关键词： Malware Operating systems Feature extraction Random forests databases Decision trees data collection

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning based Multi-Objective Systems for Financial Trading

Deep Reinforcement Learning based Multi-Objective Systems fo...

引用

Recent Advances and Innovations in engineering (ICRAIE)

作者： Kiran Bisht Arun Kumar G. B. Pant University of Agriculture and Technology Pantnagar Uttarakhand India

ISBN: (数字)9781728188676

ISBN: (纸本)9781728188683

Because of the risky nature of stock market, most people do not feel a secure option to invest their money in financial trading. Focusing on this basic concern of investors much research efforts are devoted to develop automated trading systems that make intelligent decisions according to the market situation and help investor to make profit beside risk. In contrast, in this paper we proposed multi-objective systems based on deep reinforcement learning for stock trading. Target of the multi-objective systems is to get maximum profit by adjusting risk. We design the whole structure of systems consisting two deep neural networks first is LSTM autoencoder for robust feature extraction and second deep reinforcement learning with LSTM recurrent neural network for decision making in order to achieve the investor's goal. We conduct an experiment on real historic data for verification of the systems and compare them with conventional trading systems.

关键词： Technological innovation Recurrent neural networks Decision making Reinforcement learning Reliability engineering Real-time systems Stock markets

来源：评论

学校读者我要写书评

暂无评论

Deep Approaches on Malicious URL Classification

Deep Approaches on Malicious URL Classification

引用

international conference on Computing and Networking Technology (ICCNT)

作者： Arijit Das Ankita Das Anisha Datta Shukrity Si Subhas Barman Jalpaiguri Government Engineering College Jalpaiguri India

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Malicious URLs are one of the biggest threats to this digital world and preventing it is one of the challenging tasks in the domain of cyber security. Previous research to tackle malicious URLs using hard-coded features have proven good indeed, but it comes with the limitation that these features are non-exhaustive and therefore detection algorithms fail to recognize new or unseen malicious URLs. However, with the deep learning revolution, this problem can be easily solved, since deep learning models extract features of their own by learning from patterns occurring in such URLs. In this paper, we have shown a comparative study of deep learning based architectures - simple RNN, simple LSTM and CNN-LSTM and how these methods can be effective for classifying URLs as malicious or benign. We have compared their performances on the basis of accuracy, precision and recall, where CNN-LSTM architecture outperforms the other two with an accuracy of 93.59%.

关键词： Feature extraction Uniform resource locators Training data models Numerical models Deep learning Vocabulary

来源：评论

学校读者我要写书评

暂无评论

Improving the Concentration of Students With Attention Deficit Hyperactivity Disorder and Autism Spectrum Disorder: Electroencephalographic Analysis on the Effect of learning Activity Interventions

引用

international Journal of intelligent Technologies & Applied Statistics 2020年第1期13卷 49-63页

作者： Ming-Hseuh Tsai Sy-Ruen Huang Shao-Chin Chang Yu-Ling Lo Yun-Chieh Lu Research Center for Education Systems and Policy National Academy f or Educational Research New Taipei City Taiwan Chung Chou University of Science and Technology Changhua County Taiwan Ph.D. Program of Electrical and Communications Engineering Feng-Chia University Taichung City Taiwan Department of Early Childhood Education Asia University Taichung City Taiwan

this study examined whether the learning concentration of students with attention deficit hyperactivity disorder (ADHD) or autism spectrum disorder (ASD) can be improved through participation in one-on-one learning activities. A total of 13 students with ADHD or ASD were recruited to participate in various weekly one-on-one learning activities, in an effort to improve the concentration of students with special needs. Brainwave data were collected through electroencephalography and analyzed to explore students' concentration performance in different learning activities. To achieve the objective of this study, a multi-baseline design (ABAB), a type of single-subject design method, was employed. the experiment spanned 21 weeks, covering a fall and a spring semester: the first three weeks were defined as the 1st baseline phase, the 4th to 10th weeks as the 1st experimental phase, the 11th to 13th weeks as the 2nd baseline phase, and the 14th to 21th weeks as the 2nd experimental phase. the learning activities took place in the morning self-study period once a week, and the experiment was only suspended during two of the weeks because of school events. the purpose of the two baseline phases was to collect students' brainwave data. Students' brainwaves were measured for two minutes under two scenarios; first, while they were relaxed with eyes looking straight ahead; second, they were reading a passage. the purpose of the two experimental phases was to gradually enhance students' concentration by training them to perceive their own emotions through brainwave lamps. Initial results yielded different brainwave data for students with different types of disorders. After participating in the training on learning concentration, some students demonstrated improved concentration; however, after the 2nd experimental phase, students' concentration declined. the reason was that the activities in both experimental phases were identical, and thus, they no longer provoked students' inte

关键词： Attention def icit hyperactivity disorder (ADHD) Autism spectrum disorder (ASD) Brainwave test Concentration

来源：评论

学校读者我要写书评

暂无评论

Interactive Apparel Coordination Recommendation System Reflecting Situation and Preference

Interactive Apparel Coordination Recommendation System Refle...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Muneyuki Unehara Yui Hasegawa Koichi Yamada Izumi Suzuki Nagaoka University of Technology Japan Undergraduate School of Information and Management Systems Engineering Nagaoka University of Technology Japan

ISBN: (数字)9781728197326

ISBN: (纸本)9781728197333

this study proposes an apparel coordination recommendation system, which reflects the user's situation of wearing clothing and individual preference, based on the Interactive Evolutionary Computation. the proposed system is a practical method in three respects that are not found in previous studies. First, the images of the actual product were used so that the user could use in practice. Secondly, using the latest data from SNS, we generated the outfits that the system presents outfits based on the type and color of clothing that are actually paid attention. thirdly, the subjective evaluation of the user is accumulated as an individual preference, and the outfit is presented by a simple procedure for daily use. From results of the experiments, it was confirmed that the proposed system was effective in clarifying and reconfirming the user's preference of outfits.

关键词： Clothing Image color analysis databases Color User interfaces Multimedia Web sites Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

international Joint conference: 13th international conference on Soft Computing Models, SOCO 2018, 11th international conference on Computational Intelligence in Security for Information Systems, CISIS 2018 and 9th international conference on EUropean Transnational Education, ICEUTE 2018

International Joint Conference: 13th International Conferenc...

引用

international Joint conference: 13th international conference on Soft Computing Models, SOCO 2018, 11th international conference on Computational Intelligence in Security for Information Systems, CISIS 2018 and 9th international conference on EUropean Transnational Education, ICEUTE 2018

ISBN: (纸本)9783319941196

the proceedings contain 60 papers. the special focus in this conference is on Soft Computing Models. the topics include: Experimental Study on Modified Radial-Based Oversampling;deep learning for Big data Time Series Forecasting Applied to Solar Power;deep Dense Convolutional Networks for Repayment Prediction in Peer-to-Peer Lending;a Categorical Clustering of Publishers for Mobile Performance Marketing;spatial Models of Wireless Network Efficiency Prediction by Turning Bands Co-simulation Method;neural Visualization for the Analysis of Energy and Water Consumptions in the Automotive Industry;A MAS Architecture for a Project Scheduling Problem with Operation Dependant Setup Times;collision Detector for Industrial Robot Manipulators;MASPI: A Multi Agent System for Prediction in Industry 4.0 Environment;using Genetic Algorithms to Optimize the Location of Electric Vehicle Charging Stations;FEA Structural Optimization Based on Metagraphs;case-Based Support Vector Optimization for Medical-Imaging Imbalanced datasets;modeling a Synaesthete System to Generate a Tonal Melody from a Color Distribution;minimization of the Number of Employees in Manufacturing Cells;rationalization of Production Order Execution with Use of the Greedy and Tabu Search Algorithms;dealing with Capacitated Aisles in Facility Layout: A Simulation Optimization Approach;unlocking Augmented Interactions in Short-Lived Assembly Tasks;deep learning for Deflectometric Inspection of Specular Surfaces;Disturbances Based Adaptive Neuro-Control for UAVs: A First Approach;optimizing a Fuzzy Equivalent Sliding Mode Control Applied to Servo Drive Systems;case-Based Reasoning and Agent Based Job Offer Recommender System;genetic Simulation Tool for the Robustness Optimization of Controllers;fall Detection Analysis Using a Real Fall dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessing software quality of agile student projects by data-mining software repositories 11

Assessing software quality of agile student projects by data...

引用

11th international conference on Computer Supported Education, CSEDU 2019

作者： Koetter, Falko Kochanowski, Monika Kintz, Maximilien Kersjes, Benedikt Bogicevic, Ivan Wagner, Stefan Fraunhofer Institute of Industrial Engineering Nobelstr. 12 Stuttgart Germany Institute of Software Technology University of Stuttgart Universitätsstr. 38 Stuttgart Germany

ISBN: (纸本)9789897583674

Group student software projects are important in computer science education. Students are encouraged to self-organize and learn technical skills, preparing them for real life software development. However, the projects contribute to multiple learning objectives, making coaching students a time consuming task. thus, it is important to have a suitable best practice development process. For providing better insights for the students, the resulting software has to be of value and meet quality requirements, including maintainability, as in real life software development. Using source code quality metrics and by data mining repository data like commit history, we analyze six student projects, measuring their quality and identifying contributing factors to success or failure of a student project. Based on the findings, we formulate recommendations to improve future projects for students and researchers alike. Copyright © 2019 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Event-Driven data Pipeline for Network Management Systems

Event-Driven Data Pipeline for Network Management Systems

引用

international conference on Computing and Networking Technology (ICCNT)

作者： Ganesan Ponnuswami Sriram Kailasam Dileep Aroor Dinesh School of Computing and Electrical Engineering Indian Institute of Technology Mandi Himachal Pradesh India

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Developing an event-driven applications for network management systems(NMS) requires data-wrangling operations to be performed in a data pipeline with low latency and high throughput. data stream processing engines(SPEs) enables the pipeline to feature extract complex data in near real time. We present a low latency and high throughput data pipeline that performs operations such as data cleansing, filtering, aggregations and join of streams on pipeline stages for event-driven machine learning applications. When the data stream has imbalance in arrival of records, a standalone system handle it ineffectively that reduces the performance of data pipeline. In this work, the system powered by SPEs handle the imbalance by scaling out resources and degree of parallelism such that performance is not degraded.

关键词： Pipelines Storms Feature extraction throughput Engines Real-time systems Topology

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：