检索结果-内蒙古大学图书馆

Variant component principal linear reduction for prediction of hypothyroid disease using machine learning

Journal of Physics: Conference Series 2021年第1期1767卷

作者： M. Shyamala Devi P. Swathi Ayesha Jahangir A. Dhanunjai Sai Kumar A. Naga bhushan Naidu M. Raghuram Manas Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Final Year B.Tech Student Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Third Year B.Tech Students Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai

With the tremendous technological growth, the world is shifted to adapt the different food and life style by the people that results in the improper working of the body organs. The change in the food habits leads to a major problems that we face in the current scenario is the presence of hypothyroid in the body. The likelihood of hypothyroid still ruins as a challenging issue due to the uncertainty of proper symptoms. With this background, the machine learning can be used towards health care scenarios for the prediction of disease based on the patients past history. This paper focus on predicting the existence of hypothyroid with respect to the patients' medical parameters. The hypothyroid patient dataset is taken from the UCI Metadata repository with 24 columns and 3163 unique patient's records is used for the experimentation of hypothyroid with the following contributions. Firstly, the hypothyroid dataset from UCI machine repository is subjected with the data processing and exploratory analysis of the dataset. Secondly, the unrefined data set is fixed with different classifier algorithm to find the presence of hypothyroid and to examine the efficiency metrics before and after feature scaling. Thirdly, the data is processed to PCA with various combination of components as 5, 7 and 10 and is fixed with different classifier algorithm to examine the efficiency metrics before and after feature scaling. Fourth, the data is processed to LDA with various combination of components as 5, 7 and 10 and is fixed with different classifier algorithm to examine the efficiency metrics before and after feature scaling. Experimental results show that the Kernel Support Vector Machine classifier is found to have the accuracy of 99.52% for all the 10, 7, 5 component reduced PCA dataset. Similarly, the Logistic Regression, Kernel Support Vector Machine and Gaussian Naïve bayes classifier is found to have the accuracy of 99.52% for all the 10, 7, 5 component reduced LDA dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Activation Layers Implication of CNN Sequential Models for Facial Expression Recognition

引用

IOP Conference Series: Materials science and Engineering 2021年第1期1074卷

作者： M. Shyamala Devi Ankita Sagar Karan Thapa Mreenmoy Hazarika P. Swathi Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Final Year B.Tech Student Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai

Facial Expression Recognition is the critical part in the human emotional detection in the field of image processing. The application tends to soft or hard real time application based on the power of expression detection of idle image or videos. The Social communication with any object can be done by verbal or non-verbal format. Expression and Emotion detection completely rely on the non-verbal communication and facial expression. Machine Learning play an important role in the recognition of facial expression. An attempt is made in this paper to analyse the performance of Convolutional neural network models with diverse activation layer for the performance ***, the facial expression dataset is extracted from the website http://***/ckagree/, http://***/database/faces/ is subjected with the data processing. Secondly, the data analysis is done for the distribution of expression image in the training and testing dataset. Thirdly, the facial expression images are detected with HAAR cascade and then the images are cropped with (350, 350). Fourth, the facial expression images is applied with normalized and the bottleneck features are created for training and testing data. Fifth, the training dataset is fitted with convolutional sequential neural network models with various activation layers like Sigmoid, Elu, Relu, Selu, Tanh, Softsign and Softplus. Sixth, the performance analysis is done with loss and accuracy for all the epoch of all CNN models for all the activation layers. Experimental results show that CNN sequential model with Relu activation layer is found to have the accuracy of 100%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extracting Facial Features in Filter Modified Images using Neural Networks

引用

IOP Conference Series: Materials science and Engineering 2021年第1期1074卷

作者： M Sumithra M Shyamala Devi A Poornima Shatadru Sarkar Harish Patel Preethi Mahankali boggula Navya Assistant Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Final Year B.Tech Student Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai

Facial identification plays a vital role in this digital era. Recent advancements in technology provide various filtering effects while capturing the images. Extracting the facial features from the filter modified image becomes challenging. To identify the important facial attribute values from those images, special features extraction techniques needs to be applied. Facial points are the key factors to recognize the face. When these factors are altered, facial detection becomes crucial. Initially apply the image pre-processing techniques to reduce the noise level in the images then perform feature selection. To overcome the curse of dimensionality, Occam's razor approach is followed to limit the selection of attributes. In different stages the features are going to be filtered by replacing the weaker attributes. Later Pearson Correlation, a filter based correlation technique is applied to evaluate the deviated numerical value from the target. The deviated features can be treated with Lasso effect to suppress the poor weighted features. Finally through recursive feature elimination, highest influencing attribute factor can be identified. In this approach some of the facial feature which is used in training the neural network can be discarded based on the deviation rates. In terms of accuracy the proposed system can recognize the dataset with 70% of accuracy with filter effected images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Epoch interrogation for skin cancer detection using convolutional neural network models

引用

IOP Conference Series: Materials science and Engineering 2021年第1期1074卷

作者： A Poornima M Shyamala Devi M Sumithra Mullaguri Venkata bharath Swathi S Sathishkumar K Yogesh Shubham Santosh Upadhyay Nitesh Kumar Sah Assistant Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Assistant Professor Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Final Year B.Tech Student Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai

Skin cancer is very important notable disease and it is probable to everyone nowadays, it flourishes on the area of body where it exposed to ultraviolet rays. It leads anomalous gain in skin cells. It initiate on various parts of body like face, hand and bottoms of the feet as cautious hole or spot. The initial investigation of anomalous gain is essence to cure the disease at early stage, and it still remains a feasible challenge in the scientific improvements. From the analysis, this paper endeavour to inspect the category of disease with the following improvements. Initially, the skin dataset from ISIC machine archive is utilized for image processing. Secondly, the values of dataset images are normalized by dividing all the RGb values by 255. Thirdly, keras sequential API is used to add one layer at a time, initiating from the input. The CNN can extract the features that are useful for classifying the image, by using the kernel filter matrix. MaxPool reduce the computational cost by down-sampling the image, and the relu activation function is implemented to provide non linearity to the network. The flatten layer is utilized to remodel the final feature maps into 1D vector. CNN model provides accuracy of 94.83% with 3297 images and ResNet 50 model has attained accuracy of 90.78% due to less number of images used for classification. AlexNet model has attained accuracy of 81.8% with 1300 images and GoogleNet V3 inception has attained accuracy of 96% with 3374 images. Finally Vgg16 model has attained accuracy of 97.3% with 5636 samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design Of Novel Cloud Architecture For Energy Aware Cost Computation In Cloud Computing Environment

Design Of Novel Cloud Architecture For Energy Aware Cost Com...

引用

International Conference on Innovations in Power and Advanced Computing technologies

作者： S. Kaushik Srijan Singh Raquib Khan Pathan Associate Professor School of Computer Science and Engineering VIT University Vellore India B.Tech CSE - Student School of Computer Science and Engineering VIT University Vellore India

ISBN: (纸本)9781509056835

Cloud computing mainly aims to deliver the storage and retrieval of large number of data over the internet for cloud consumers. Many researchers and developers are into the deployment of Cloud architecture by analyzing it in the cloud data centers power consumption models. The challenges faced by the data analytics are to reduce the computational power for the data, as the data growth is infinite over the period. In order to solve this problem a novel approach is needed for the cloud computing for cost computational methods. Our proposed model is an energy aware cost computation for solving the complex data computation through load balancing in the cloud. Our experimental outcomes through Cloudsim have demonstrated the effectiveness and competence of the proposed cost computational algorithm in the Cloud environment in terms of response time, throughput and other QoS metrics.

关键词： Cloud computing cloud data center energy aware cost computation load balancing response time throughput

来源：评论

学校读者我要写书评

暂无评论

A semantic feedback on student's performance with data mining techniques: State of the art survey

A semantic feedback on student's performance with data minin...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： J. Naren Kirthika Ashokkumar Vaishnavi Raghavendran School of Computing SASTRA University Thanjavur India B.Tech Computer Science and Engineering School of Computing SASTRA University Thanjavur India B.Tech Information and Communication Technology School of Computing SASTRA University Thanjavur India

ISBN: (纸本)9781467394178

Feedback is assessing an individual's action in any endeavor. The judgment helps one to grow well in any field. by the feedback a student can understand and improve upon mistakes committed, teachers come to know about the student's capability and implement new teaching methods. New technologies also come up for the enhancement of Student's Performance. A study of the assessment of student performance through various papers using data mining and also with ontology based applications makes one decide certain factors like confidence level, stress and time management, holistic approach towards an issue which may be useful in giving a prediction about the students' work performance level in organizations. The Survey encompasses the assessment of a student's performance in academics using Data mining techniques and also with Ontology based Applications.

关键词： Ontologies Data mining Semantics OWL Decision trees Resource description framework Data models

来源：评论

学校读者我要写书评

暂无评论

Field Monitoring and Automation Using IOT in Agriculture Domain

引用

Procedia computer science 2016年 93卷 931-939页

作者： I. Mohanraj Kirthika Ashokumar J. Naren B.Tech Computer Science and Engineering School of Computing SASTRA University Thanjavur - 613401 India Assistant Professor School of Computing SASTRA University Thanjavur - 613401 India

Agriculture sector in India is diminishing day by day which affects the production capacity of ecosystem. There is an exigent need to solve the problem in the domain to restore vibrancy and put it back on higher growth. The paper proposes an e-Agriculture Application based on the framework consisting of KM-Knowledge base and Monitoring modules. To make profitable decisions, farmers need information throughout the entire farming cycle. The required information is scattered in various places which includes real time information such as market prices and current production level stats along with the available primary crop knowledge. A knowledge dataflow model is constructed connecting various scattered sources to the crop structures. The world around is getting automated replacing manual procedures with the advancement of technology, since it is energy efficient and engross minimal man power. The paper proposes the advantages of having ICT in Indian agricultural sector, which shows the path for rural farmers to replace some of the conventional techniques. Monitoring modules are demonstrated using various sensors for which the inputs are fed from Knowledge base. A prototype of the mechanism is carried out using TI CC3200 Launchpad interconnected sensors modules with other necessary electronic devices. A comparative study is made between the developed system and the existing systems. The system overcomes limitations of traditional agricultural procedures by utilizing water resource efficiently and also reducing labour cost.

关键词： e-Agriculture Knowledge base Monitoring Ontology

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of back Propagation and Simulated Annealing Algorithms for Neural Net Classifier Optimization

引用

Procedia Engineering 2012年 38卷 448-455页

作者： Subhendu Sekhar behera Subhagata Chattopadhyay B.Tech Department of Computer Science & Engineering National Institute of Science & Technology Berhampur-761008 India Professor Department of Computer Science & Engneering National Institute of Science & Technologys Berhampur-761008 India

Optimizing the convergence of a Neural Net Classifier (NNC) is an important task to increase the speed and accuracy in the decision-making process. Learning algorithms are used to facilitate such optimization process. Simulated Annealing (SA) and back propagation (bP) are two popular optimization algorithms. The objective of the study is to compare the optimization performances of SA and bP on a feed-forward NNC that relies more on bP. For the study, five standard datasets, such as WINE, IRIS, DIAbETES, TEACHING ASSISTANT EVALUATION (TAE), and GLASS are considered. Experimental results reveal that during training and testing SA has outperformed bP (except for WINE data and that is during testing only). The generalised notion is that bP is one of the best optimisers for NNC. Hence, the experimental results are interesting. The authors assume that it is due to the fact that SA is a much randomized approach to find the global solution, while bP is a gradient-based search and thus has an inclination to be trapped in the local minima. Another important reason could be that bP relies on its best learning (occurred during its training) while classifying test cases, which might not be appropriate for a new dataset. SA, on the other hand, initiates a new search with the given dataset and because of its randomized search space, is able to converge into the global minima. The paper therefore argues that for optimising in a classical NNC, SA is more efficient than bP because of its random and flexible search space.

关键词： ANN back Propagation Simulated Annealing Classification Comparison

来源：评论

学校读者我要写书评

暂无评论

A refined MSAPSO algorithm for improving alignment score

引用

Research Journal of Applied sciences, Engineering and technology 2012年第21期4卷 4404-4407页

作者： Arulmani, K. Guru Prasad, M. Hariharan, R. Sivasankaran, N. Department of Computer Science and Engineering SASTRA University Srinivasa Ramanujan Centre Kumbakonam-612 001 Tamilnadu India B.Tech Computer Science and Engineering SASTRA University Srinivasa Ramanujan Centre Kumbakonam-612 001 Tamilnadu India

Multiple Sequence Alignment (MSA) is an important part of bioinformatics domain in which two or more biological sequences, such as proteins, DNA or RNA are aligned sequentially. This Multiple Sequence Alignment plays a vital role in the generation of phylogenetic tree as well as predicting the protein structure. The protein sequences are generally used to generate the Phylogenetic tree. To attain this, we have transformed the protein sequences into numerical values using a substitution matrix and optimized those numerical values using Particle Swarm Optimization (PSO) method. The PSO is a meta-heuristic computational approach for performing optimization. The PSO uses the random values for pair-wise sequence alignment, resulting in decrease in the rate of the residues matched. This study presents how the rate of matching process can be improved by replacing the random values with the substitution matrix values if there is a positive value in the matrix. As result of this, we have also found that the score of the alignment sequence has been improved. © Maxwell Scientific Organization, 2012.

关键词： bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Hybrid controller for inverted pendulum

Hybrid controller for inverted pendulum

引用

International Conference on Advances in Power Conversion and Energy technologies (APCET)

作者： Yogesh Singh Manisha bhatotia Ranajit Mitra M.Tech student of the Electronics and computer Engineering Department IIT Roorkee Uttarakhand India B.Tech student of the Electronics & Instrumentation control YMCA university of science & technology Faridabad India

Inverted pendulum system is a nonlinear multivariable system which is inherently unstable. It requires designing of a hybrid controller which can adapt in different disturbance conditions and work appreciably well when compared to conventional controllers. In this paper, a hybrid controller for inverted pendulum is designed. Initially Fuzzy and LQR controllers for inverted pendulum are designed, then data are collected from these controllers, which then are used to train Adaptive neuro-fuzzy inference system (ANFIS). This hybrid controller has advantages of Fuzzy, LQR controllers and of neural networks; so it gives better performance.

关键词： Mathematical model Fuzzy logic IP networks Control systems Equations Neural networks Fuzzy control

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：