检索结果-内蒙古大学图书馆

11th international conference on Educational data Mining, EDM 2018

作者： Nanda, Gaurav Hicks, Nathan M. Waller, David R. Goldwasser, Dan Douglas, Kerrie A. School of Engineering Education Purdue University West Lafayette United States Department of Computer Science Purdue University West Lafayette United States

this study proposes a formal multi-step methodology for qualitative assessment of topic modeling results in the context of online learner motivation to purchase Statements of Participation (SoP). We developed Latent Dirichlet Allocation (LDA) based topic models on open-ended responses of three post-course survey questions from 280 open courses offered on the FutureLearn learning platform. For qualitative assessment, we first determined the theme of the topic based on the words that constituted the topic and responses that were most strongly associated with the topic. then, we verified the theme by comparing the topics assigned by LDA model on a test set with manual annotation. We also performed sentiment analysis to check for alignment with human judgment. Learner motivations in each theme were interpreted with the Expectancy-Value-Cost framework. Our analyses indicated that, primarily, learners were motivated to purchase the SoP based on perceptions of the utility value and financial cost of the certificate. We found that human judgment agreed with the topic model more frequently when LDA topic weights were larger. © 2018 international Educational data Mining Society. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Advanced distributed learning partnership laboratory 11

Advanced distributed learning partnership laboratory

引用

11th international conference on Developments in eSystems engineering, DeSE 2018

作者： Elhassan Ali, Fawzia Awad Klett, Fanny Computer Science Dept. Sudan University of Science and Technology Khartoum Sudan German Workforce Advanced Distributed Learning Partnership Laboratory Waltershausen Germany

ISBN: (纸本)9781538667125

the rapid expansion of information and communication technologies in relation to big data analysis generates the vital demand to gain the maximum benefit of the 'big data'. Business intelligence and learning analytics are recently drawing considerable attention in market and society being one of the most competitive and profitable areas of interest to businesses and organizations, including higher education institutions. Business intelligence systems have already demonstrated significant impact on strategic decision making and trends forecasting. learning analytics is going to extend the value of business intelligence in the field of education and training in proportion to retention, students' success and satisfaction. Hence, the overall organization's performance and ranking-in a wider scope-will be transformed toward informed, timelier, high-valued, evidenced and high-quality decisions benefiting the students, and accordingly, achieving sustainable organization's performance in a middle term, and society advancement in a longer term. this paper focuses on investigating the potential of business intelligence approaches toward a meaningful analysis of the organization's and student's experience by making use of business intelligence enhanced learning analytics. It provides valuable insights into the integration and use of business intelligence in the learning analytics application area by highlighting recent research and developments. Furthermore, it suggests paths to resolving current issues in the interrelationship between higher education institutions' and learning performance by designing a novel closed-loop feedback framework that aims at improving the learning outcomes for the students, and the organization, and prepares for smart educational management. © 2018 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Software defect prediction: do different classifiers find the same defects?

引用

SOFTWARE QUALITY JOURNAL 2018年第2期26卷 525-552页

作者： Bowes, David Hall, Tracy Petric, Jean Univ Hertfordshire Sci & Technol Res Inst Hatfield AL10 9AB Herts England Brunel Univ London Dept Comp Sci Uxbridge UB8 3PH Middx England

During the last 10 years, hundreds of different defect prediction models have been published. the performance of the classifiers used in these models is reported to be similar with models rarely performing above the predictive performance ceiling of about 80% recall. We investigate the individual defects that four classifiers predict and analyse the level of prediction uncertainty produced by these classifiers. We perform a sensitivity analysis to compare the performance of Random Forest, Na < ve Bayes, RPart and SVM classifiers when predicting defects in NASA, open source and commercial datasets. the defect predictions that each classifier makes is captured in a confusion matrix and the prediction uncertainty of each classifier is compared. Despite similar predictive performance values for these four classifiers, each detects different sets of defects. Some classifiers are more consistent in predicting defects than others. Our results confirm that a unique subset of defects can be detected by specific classifiers. However, while some classifiers are consistent in the predictions they make, other classifiers vary in their predictions. Given our results, we conclude that classifier ensembles with decision-making strategies not based on majority voting are likely to perform best in defect prediction.

关键词： Software defect prediction Prediction modelling Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hourly Prediction of Load using Edge Intelligence over IoT

Hourly Prediction of Load using Edge Intelligence over IoT

引用

international conference on Advanced Computing, ICAC

作者： Ipsita Dalai Prateek Mudali Arunima Sambhuta Pattanayak Bhawani Shankar Pattnaik Computer Science and Engineering National Institute of Science and Technology Under Biju Patnaik University of Technology Electronics and Communication Engineering RV College of Engineering Bangalore India

ISBN: (数字)9781728152868

ISBN: (纸本)9781728152875

Energy is the lifeblood of modern societies. In the past decades, due to the increases in population and comfort demands of people, energy consumption and associated CO2 emissions increased rapidly in the world. the next hour's energy prediction would help in facilitating future energy management, planning, and conservation in the industries and community setups. data-driven models provide a practical approach to energy consumption prediction. this paper offers an Internet of things (IoT) based Solution by running a data-driven model between edge and cloud layer to predict the energy consumption of a building in real-time. To achieve a real-time response from the system, the Machine learning (ML) inference algorithm runs in the edge node to predict the next hour energy demand of the building. A Microgrid IoT setup is established in the authors' organization for experimental purposes. this paper provides a substantial review of the four main ML approaches, including linear regression, multilayer perceptron, SMO Regression and Support Vector Machine (LibSVM) which have commonly been applied in forecasting and improving building energy performance. Considering the performance measures like Mean Absolute Error (MAE) and Root Mean Square Error (RMSE), this paper concludes that SVM performance is better in terms of prediction accuracy among all others. In terms of prediction time, it is concluded that the edge node takes less time for real-time prediction compared to the cloud.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Preferences of Novice Software engineering Students: Temperament Style and Attitudes Towards Programming Activities 11th

On Preferences of Novice Software Engineering Students: Temp...

引用

11th international conference on Informatics in Schools - Situation, Evolution, and Perspectives (ISSEP)

作者： Jevsikova, Tatjana Dagiene, Valentina Dolgopolovas, Vladimiras Vilnius Univ Inst Data Sci & Digital Technol Akad 4 LT-04812 Vilnius Lithuania

ISBN: (纸本)9783030027506;9783030027490

Educators' experience shows that learning programming is in many aspects problematic for novice software engineering students. On the other hand, software engineering processes and the view of programming has been changing during the recent years. In this paper, we address socio-cognitive aspects of computer science and software engineering in order to contribute to programming education enhancement: the research is focused on students' temperament style and favorite programming learning activities. the study of 158 first and second year students, studying programming specialties in five higher education institutions, has been presented. the "psychological portrait" of the surveyed students reflects the evolution of the temperament style in programming during last decades. the attitudes towards the programming activities, presented in this paper, may contribute to the development of enhancement of existing programming courses in higher education.

关键词： Temperament style and programming Personal characteristics and programming Programming students Novice programmers

来源：评论

学校读者我要写书评

暂无评论

Design of a Smart Desk for an IoT Testbed: Improving learning Efficiency and System Security 11th

Design of a Smart Desk for an IoT Testbed: Improving Learnin...

引用

11th international conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS)

作者： Yamada, Masafumi Cuka, Miralda Liu, Yi Oda, Tetsuya Matsuo, Keita Barolli, Leonard Fukuoka Inst Technol FIT Grad Sch Engn Higashi Ku 3-30-1 Wajiro Higashi Fukuoka 8110295 Japan Okayama Univ Sci OUS Dept Informat & Comp Engn Kita Ku 1-1 Ridaicho Okayama 7000005 Japan Fukuoka Inst Technol FIT Dept Informat & Commun Engn Higashi Ku 3-30-1 Wajiro Higashi Fukuoka 8110295 Japan

ISBN: (纸本)9783319615424;9783319615417

Due to the opportunities provided by the Internet, people are taking advantage of e-learning courses and enormous research efforts have been dedicated to the development of e-learning systems. So far, many e-learning systems are proposed and used practically. However, in these systems the e-learning completion rate is low. One of the reasons is the low study desire and motivation. In this work, we present an IoT-Based E-learning testbed using Raspberry Pi mounted on Raspbian. We carried out some experiments with a student of our laboratory for brain waves and, encryption and decryption time of cipher algorithms. We used MindWave Mobile (MWM) to get the data. For experimental results, when using our system the concentration is 80 [%] from 0 [s] to 400 [s]. But, for 400 [s] to 1000 [s], concentration is decreased. In the case of not using our system, concentration is almost the same (about 40 [%]) from 0 [s] to 1000 [s]. From simulation results, we found that the decryption time is faster than encryption time, however for 3-DES and Raspberry Pi decryption time is higher than encryption time.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

CNN+RNN Depth and Skeleton based Dynamic Hand Gesture Recognition 24

CNN+RNN Depth and Skeleton based Dynamic Hand Gesture Recogn...

引用

24th international conference on Pattern Recognition, ICPR 2018

作者： Lai, Kenneth Yanushkevich, Svetlana N. Department of Electrical and Computer Engineering Biometric Technologies Laboratory University of Calgary Alberta Canada

ISBN: (纸本)9781538637883

Human activity and gesture recognition is an important component of rapidly growing domain of ambient intelligence, in particular in assisting living and smart homes. In this paper, we propose to combine the power of two deep learning techniques, the convolutional neural networks (CNN) and the recurrent neural networks (RNN), for automated hand gesture recognition using both depth and skeleton data. Each of these types of data can be used separately to train neural networks to recognize hand gestures. While RNN were reported previously to perform well in recognition of sequences of movement for each skeleton joint given the skeleton information only, this study aims at utilizing depth data and apply CNN to extract important spatial information from the depth images. Together, the tandem CNN+RNN is capable of recognizing a sequence of gestures more accurately. As well, various types of fusion are studied to combine both the skeleton and depth information in order to extract temporal-spatial information. An overall accuracy of 85.46% is achieved on the dynamic hand gesture-14/28 dataset. © 2018 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparative study of Brain Tumor Segmentation using Different Segmentation Techniques in Handling Noise

Comparative study of Brain Tumor Segmentation using Differen...

引用

Joint international conference on Computer engineering, Network and intelligent Multimedia (CENIM) / 11th AUN/SEED-Net Regional conference on Computer and Information engineering (RCCIE)

作者： Iriawan, Nur Pravitasari, Anindya Apriliyanti Fithriasari, Kartika Irhamah Purnami, Santi Wulan Ferriastuti, Widiana Inst Teknol Sepuluh Nopember Fac Math Computat & Data Sci Dept Stat Surabaya Indonesia Univ Airlangga Fac Med Dept Radiol Surabaya Indonesia

ISBN: (纸本)9781538675090

Image segmentation has been popularly performed for researchers in the field of Biomedical, Informatics engineering, and Statistical Computation. this study tries to compare several methods for brain tumor image segmentation, especially in handling noise. the methods are K-means Cluster, Fuzzy C-Means (FCM) Cluster, Gaussian Mixture Model (GMM), and Fernandez-Steel Skew Normal (FSSN) Mixture model. K-means and FCM are the popular Partitioning methods for clustering, while GMM is model-based clustering method. the FSSN mixture model is the new model-based clustering introduced in this study. Both GMM and FSSN are formed through a finite mixture model with Bayesian Markov Chain Monte Carlo (MCMC) optimization. the dataset is the MRI brain tumor image from General Regional Hospital (RSUD) Dr. Soetomo Surabaya. Gaussian noise and Salt pepper noise are generated to see the robustness of each method. Various evaluation parameters like Silhouette Index, Partition Coefficient Index, and Misclassification Ratio are calculated for the appropriate methods and comparative analysis is carried out. the results indicate for partitioning methods especially FCM is more robust in handling Gaussian noise, while GMM is more robust in handling Salt and pepper noise. the outstanding result shows that the FSSN mixture model could handle both Gaussian and Salt pepper noise better than other methods.

关键词： image segmentation K-means FCM GMM Fernandez-Steel Skew Normal mixture Bayesian

来源：评论

学校读者我要写书评

暂无评论

Analysis of Users' Emotions through Physiology 11th

Analysis of Users' Emotions Through Physiology

引用

11th international conference on Genetic and Evolutionary Computing (ICGEC)

作者： Myroniv, Bohdan Wu, Cheng-Wei Ren, Yi Tseng, Yu-Chee Natl Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan

ISBN: (纸本)9789811064876;9789811064869

Most of the existing studies focus on physical activities recognition, such as running, cycling, swimming, etc. But what affects our health, it is not only physical activities, it is also emotional states that we experience throughout the day. these emotional states build our behavior and affect our physical health significantly. therefore, emotion recognition draws more and more attention of researchers in recent years. In this paper, we propose a system that uses off-the-shelf wearable sensors, including heart rate, galvanic skin response, and body temperature sensors to read physiological signals from the users and applies machine learning techniques to recognize their emotional states. We consider three types of emotional states and conduct experiments on real-life scenarios with ten users. Experimental results show that the proposed system achieves high recognition accuracy.

关键词： Emotion recognition Machine learning Physiological signals Wearable devices

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial for Special Section on the 11th international conference on intelligent Computing (ICIC)

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2017年第5期14卷 1104-1105页

作者： Huang, De-Shuang Bevilacqua, Vitoantonio Gromiha, M. Michael Tongji Univ Machine Learning & Syst Biol Lab Shanghai Peoples R China Polytech Bari Elect & Informat Engn Dept I-70126 Bari Italy Indian Inst Technol Dept Biotechnol Madras 600036 Tamil Nadu India

the papers in this special section were presented at the 11th international conference on intelligent Computing ICIC held in Fuzhou, China, on August 20-23, 2015. this conference was formed to provide an annual forum dedicated to the emerging and challenging topics in artificial intelligence, machine learning, bioinformatics, etc. It aims to bring together researchers and practitioners from both academia and industry to share ideas, problems, and solutions related to the multifaceted aspects of intelligent computing.

关键词： Special issues and sections Artificial intelligence Machine learning Bioinformatics Biomedical engineering Predictive models intelligent systems

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：