检索结果-内蒙古大学图书馆

15th IEEE India Council International Conference, INDICON 2018

作者： Haritha, H. Kumar, C. Santhosh Anand Kumar, A. Kesavankutty Nayar, P.C. Gopinath, Siby Ramachandran, K.I. Amrita Vishwa Vidyapeetham Department of Electronics and Communication Engineering Amrita School of Engineering Coimbatore India Department of Neurology Amrita Vishwa Vidyapeetham Amrita Institute of Medical Sciences Kochi India Department of Psychiatry Amrita Vishwa Vidyapeetham Amrita Institute of Medical Sciences Kochi India Center for Computational Engineering and Networking Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9781538682357

In this paper, we explore several approaches for improving the performance of a stress detection system (SDS) with electrocardiogram (ECG) signal as its input. Time and frequency domain features extracted from the heart rate variability (HRV), is input to a support vector machine (SVM) backend classifier, for the baseline SVM-SDS. We used ECG data from normative population and patients with severe stress disorders for validating the effectiveness of SDS. We observed that there are variations in the HRV parameters among the normative population, and the patients with stress disorder, usually referred to as person specific variations. To minimize the person specific variations, we explored three methods: 1. Locality-constrained linear coding (LLC) - input feature vectors are expressed in terms of person independent basis vectors. 2. Fisher vector encoding (FVE) -input features are expressed in a person independent feature space using Gaussian mixture models (GMM) trained patient independently. 3. Covariance normalization (CVN) - minimizes the person specific variations in the input vector through feature normalization. For the CVN-SDS, we obtained a sensitivity of 87.50% absolute, specificity of 100.00% absolute and accuracy of 91.66% absolute, which is 31.43%, 31.43% and 33.33% absolute improvement over the SVM-SDS. © 2018 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction of Hyperspectral Images for Classification using Randomized Independent Component Analysis

Dimensionality Reduction of Hyperspectral Images for Classif...

引用

International Conference on Signal Processing and Integrated Networks (SPIN)

作者： Chippy Jayaprakash Bharath Bhushan Damodaran Sowmya V. K.P. Soman Center for Computational Engineering and Networking (CEN) Amrita School of Engineering Coimbatore India Univ. Bretagne-Sud Vannes France Amrita School of Engineering Bangalore Karnataka IN

Independent Component Analysis (ICA) is a commonly used technique for the dimensionality reduction of Hyperspectral images (HSI) to capture the linear relationship in the original input features of the image. Even though kernel methods were introduced to capture the nonlinear features, they possess high computational complexity, while dealing with a large number of pixels of HSI. Recent research has introduced Random Fourier feature maps (RFF) to project high dimensional data to low dimension. In this paper, we propose a nonlinear component analysis for the dimensionality reduction of HSI based on RFF maps. The proposed method has experimented on two dataset namely Pavia University and Salinas scene. It is verified that the feature extracted using RFF maps outperforms the conventional and kernel methods, in terms of classification accuracy.

关键词： Kernel Feature extraction Hyperspectral imaging Dimensionality reduction Principal component analysis Independent component analysis

来源：评论

学校读者我要写书评

暂无评论

Fractal Geometry: Enhancing computational Thinking with MIT Scratch

Fractal Geometry: Enhancing Computational Thinking with MIT ...

引用

International Conference on Computing and networking Technology (ICCNT)

作者： R Vinayakumar KP Soman Pradeep Menon Center for Computational Engineering and Networking (CEN) Amrita Vishwa Vidyapeetham Coimbatore India Lakhshya Cyber Security Labs Pvt Ltd Coimbatore

Recent developments in pedagogy have focused upon computational thinking. computational thinking provides a way to solve the problem and it is a key practice of science education. The importance of computational thinking is rarely found in K-12 education. computational thinking is a an important skill everyone needs and it is correlated with many other concepts. These factors have made the development of new tools and syllabus. In this paper, we aim to show the experiments of fractal geometry using MIT Scratch. These computational exercises facilitate to learn many of computational thinking skills that are very important for the people in the near future. Based on our experience with students, we claim that the concept of fractal and its implementation in MIT Scratch is the best practices to improve computational thinking in K-12 school level students.

关键词： Fractals Programming profession Education Visualization Games

来源：评论

学校读者我要写书评

暂无评论

Building-Blocks: Generating 3D Design by Snapping Blocks

Building-Blocks: Generating 3D Design by Snapping Blocks

引用

International Conference on Computing and networking Technology (ICCNT)

作者： R Vinayakumar KP Soman Pradeep Menon Center for Computational Engineering and Networking (CEN) Amrita Vishwa Vidyapeetham Coimbatore India Lakhshya Cyber Security Labs Pvt Ltd Coimbatore

In this paper, we present a browser-based, visual and media-rich programming platform for K-12 schools that allows novices to create complex 3D shapes. This provides an easy way for designers, architects, and artists to imagine the development of an object. The word computation has received increased attention in today's world because of its applicability in all fields. This tool is very helpful for the user who doesn't have prior programming knowledge and they want to learn and apply the computational concepts as part of their design process. `Building-Blocks' is a graphical programming language used for generation of 3D structures using computational algorithms. This helps to create personally meaningful projects: designing a model, getting the physical object from a model, sharing ideas and project activities with others in Building-Blocks community.

关键词： Three-dimensional displays Shape computational modeling Education Graphical user interfaces Buildings Visualization

来源：评论

学校读者我要写书评

暂无评论

CT-Blocks Analyser: Analysing CT-Blocks Projects

CT-Blocks Analyser: Analysing CT-Blocks Projects

引用

International Conference on Computing and networking Technology (ICCNT)

作者： R Vinayakumar KP Soman Pradeep Menon Center for Computational Engineering and Networking (CEN) Amrita Vishwa Vidyapeetham Coimbatore India Lakhshya Cyber Security Labs Pvt Ltd Coimbatore

This paper introduces CT-Blocks Analyser which is used for analysing computational thinking concepts of CT-Blocks project activities. This uses the emerging techniques of educational data mining and learning analytics to automate the instructional approach for CT-Blocks projects. CT-Blocks aims to infuse computational thinking within K-12 curriculum. The big data toolkit called, CT-Blocks Analyser which is specifically developed for CT-Blocks, a visually appealing programming environment for beginners; a block based programmable platform interconnected with more features in which students enjoy the learning process and it tries to make the users master in computational thinking.

关键词： Tools Big Data Programming profession Sprites (computer) Data mining

来源：评论

学校读者我要写书评

暂无评论

Alg-Design: Facilitates to Learn Algorithmic Thinking for Beginners

Alg-Design: Facilitates to Learn Algorithmic Thinking for Be...

引用

International Conference on Computing and networking Technology (ICCNT)

作者： R Vinayakumar KP Soman Pradeep Menon Center for Computational Engineering and Networking (CEN) Amrita Vishwa Vidyapeetham Coimbatore India Lakhshya Cyber Security Labs Pvt Ltd Coimbatore

Algorithmic thinking is one of the main key concepts in computational thinking. With using computers in close to all areas of our lives, the progress of algorithmic solutions to problems is very crucial. The comprehension of the character of problems and their algorithmic solutions is enormously most important for everyone. Algorithmic thinking is the capability to realize, execute, assessment, and create computational procedures for solving problems. This paper presents Alg-Design, a visual and block based programming environment to facilitate novices to improve the comprehension of Algorithmic thinking using programming and computing. The visual programming environment motivates students and they find enjoyable while creating personally meaningful projects.

关键词： Programming profession Visualization Programming environments Games Sprites (computer) Chaos

来源：评论

学校读者我要写书评

暂无评论

Digital Storytelling Using Scratch: Engaging Children Towards Digital Storytelling

Digital Storytelling Using Scratch: Engaging Children Toward...

引用

International Conference on Computing and networking Technology (ICCNT)

作者： R. Vinayakumar K.P. Soman Pradeep Menon Center for Computational Engineering and Networking (CEN) Amrita Vishwa Vidyapeetham Coimbatore India Lakhshya Cyber Security Labs Pvt Ltd Coimbatore India

Engaging youngsters with ancient approaches in education, especially reading, grows ever tougher in the face of their attachment to tablets and PC games. In this paper, we explore the digital storytelling more interesting and memorable for children. Digital storytelling is recognized as a motivating instructional approach that engages learners in 21 st century learning skills which will be essential to success in the future. Digital storytelling is one of the latest pedagogical approaches that can engage learners in computational thinking. Educators are in search of recent technologies and education approaches to engage students in computational thinking. Digital storytelling using MIT Scratch have the potential to meet this demand.

关键词： Sprites (computer) Dogs Media Programming profession Games Education

来源：评论

学校读者我要写书评

暂无评论

Deep Convolution Network Based Prediction Model For Medical Diagnosis Of Lung Cancer - A Deep Pharmacogenomic Approach : deep diagnosis for lung cancer

Deep Convolution Network Based Prediction Model For Medical ...

引用

International Conference on Advances in Electronics, Computers and Communications (ICAECC)

作者： Akshay Iyer Hima Vyshnavi A M Krishnan Namboori P K Center for Research in Analytics And Technologies for Education(CREATE) Amrita School of Engineering Amritapuri Amrita Vishwa Vidyapeetham India Center for Computational Engineering & Networking(CEN) Amrita School of Engineering Amrita Vishwa Vidyapeetham Coimbatore India

The recently introduced deep learning environment has been used in post pharmacogenomic predictions on proneness to lung cancer. The well-established pre-trained model, VGG19 has been used to extract information from the pathological images specific to PTEN, EGFR, ERBB2, BRAF and CDKN2A for Lung cancer. The model finds to be suitable for the prediction of these mutations, specific to Indian populations. A model consisting of testing of specific genetic signatures and the deep convolution network based image classification has been suggested as an ingenious technique for the fast, cheap and effective predictions on mutations of lung cancer among Indian populations.

关键词： Cancer Lung DNA Sociology Statistics Genomics

来源：评论

学校读者我要写书评

暂无评论

Deep stance and gender detection in tweets on catalan independence@Ibereval 2017 2

Deep stance and gender detection in tweets on catalan indepe...

引用

2nd Workshop on Evaluation of Human Language Technologies for Iberian Languages, IberEval 2017

作者： Vinayakumar, R. Sachin Kumar, S. Premjith, B. Prabaharan, P. Soman, K.P. Center for Computational Engineering and Networking Amrita School of Engineering Amrita University India Center for Cyber Security Systems and Networks Amrita School of Engineering Amrita University India

This paper discusses deepyCybErNet submission methodology to the task on Stance and Gender Detection in Tweets on Catalan Independence@Ibereval 2017. The goal of the task is to detect the stance and gender of the user in tweets on the subject "independence of Catalonia". Tweets are available in two languages: Spanish and Catalan. In task 1 and 2, the system has to determine whether the tweet is in favor of, against or neutral to the tweets on the subject pertaining to the task in Spanish and Catalan languages respectively. In task 3 and 4, the system has to decide whether the person who tweets is a male or female. We submitted three systems for this task a Bag-of-Words (BOW) representation for tweets with logistic regression classiffier, Recurrent Neural Network (RNN) based approach, Long Short Term Memory (LSTM) based approach and gated recurrent based approach. These methods are highly language independent and can be used for the declarations of stance of tweets and identifying the gender of twitter user in any language. These methods have performed better in detecting stance and gender in tweets of Catalan language than in those of Spanish.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Population Wise Variation of Breast and Ovarian Cancer-A Pharmacogenomic Approach

引用

Materials Today: Proceedings 2018年第8期5卷 16106-16110页

作者： C. Lakshmi Anand A.M. Hima Vyshnavi Gilu Francis S. Karthikeyan P. Sanjay Kumar P.K. Krishnan Namboori Computational Chemistry Group (CCG) Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham Amrita University India Center for Computational Engineering & Networking (CEN) Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham Amrita University India Dept. of Electronics and Communications Engineering Amrita School of Engineering Coimbatore Amrita Vishwa Vidyapeetham Amrita University India

The somatic mutations in TP53 may be considered as one of the major genomic reasons behind breast and ovarian cancers. These two types of cancers have been reported as the major terminal diseases among women, with breast cancer as the second and ovarian cancer as the fifth cause of death as per the WHO reports last year. However, the proneness of the disease varies from trait to trait and even from person to person. A population-wise analysis of the risk factors associated with the variations results in the study of pharmacogenomic components such as epigenetics, metagenomics, environmental genomics and genomics . The single nucleotide polymorphism (SNP) has been identified as the effective genetic signature to include these variations. For TP53, 27 non-synonymous, pathogenic and deleterious SNPs have been identified in the world populations. Among Indian populations, the SNPs identified are rs1642785, rs1042522, rs8064946, rs12951053, rs1641549, rs1625895 and rs2078486. The frequency of TP53 is found to be high in New Zealand and Australian populations. The methylation probability of TP53 has been predicted through linear SVM using 10 classes of attributes keeping a total of 847 features. The prominent features identified during the epigenetic analysis useful for predicting the possibility of methylation of the gene are the constituents in the DNA sequence, epigenome/chromatin structure and presence of regulatory regions.

关键词： Epigenetics Metagenomics Environmental factors Genetic signature Pharmacogenomics SVM

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：