{"title":"GLCM Based Feature Extraction and Medical X-RAY Image Classification using Machine Learning Techniques","authors":"P. Mall, Pradeep Singh, Divakar Yadav","doi":"10.1109/CICT48419.2019.9066263","DOIUrl":"https://doi.org/10.1109/CICT48419.2019.9066263","url":null,"abstract":"The machine learning and artificial intelligence play a vital role to solve the challenging issues in Clinical imaging. The machine learning and artificial intelligence ease the daily life of both medical practitioner and patient's. Nowadays, the automatic system is designed with high accuracy to perceive abnormality in bone X-ray images. To achieve high accuracy system has less resource available image pre-processing tools are used to enhance the medical images quality. The image pre-processing involves the process like noise removal and contrast enhancement which provides instantaneous abnormality diagnosis system. The Gray Level Co-occurrence Matrix (GLCM) texture features are widely used in image classification problems. GLCM represents the second-order statistical information of gray levels between neighboring pixels in an image[1]. In the paper, we implemented different machine learning approaches to classify the bone X-ray images of MURA (musculoskeletal radiographs) dataset into fractures and no fracture category. The four different classifiers LBF SVM (Radial Basis Function support vector machine), linear SVM, Logistic Regression and Decision tree are used for abnormality detection. The performance evaluation of the above abnormality detection in X-ray images is performed by using five statistical parameters such as Sensitivity, Specificity, Precision, Accuracy and F1 Score, which shows significant improvement.","PeriodicalId":234540,"journal":{"name":"2019 IEEE Conference on Information and Communication Technology","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128802643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anubhav Shivhare, M. Maurya, Vatsal J. Sanglani, Manish Kumar
{"title":"Spatial Correlation Based Device Level Clustering for IoT","authors":"Anubhav Shivhare, M. Maurya, Vatsal J. Sanglani, Manish Kumar","doi":"10.1109/CICT48419.2019.9066136","DOIUrl":"https://doi.org/10.1109/CICT48419.2019.9066136","url":null,"abstract":"The advent of IoT has ushered an era of demands for new and intelligent schemes to manage the network without compromising on the network lifetime. Clustering of sensor motes in a network plays a vital role in IoT. Many research works are proposed for clustering the sensor motes based on the distance between each sensor motes to optimize the network lifetime. Moreover, recent advancements do not focus on spatial correlation information of a sensor mote along with its location information. The authors propose a novel scheme for device level clustering in multi-modal IoT network which takes spatial information into account for clustering of devices. Thus the research work highlights the importance of clustering methodology based on spatial correlation. Further, standard correlation metrices like Pearson's, Kendall's and Spearman's correlation were used to evaluate the performance of the proposed scheme. A comparison of deviation in cluster member nodes is also done to show the effectiveness of the scheme in load balancing.","PeriodicalId":234540,"journal":{"name":"2019 IEEE Conference on Information and Communication Technology","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114950806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Copyright and Reprint Permission","authors":"","doi":"10.1109/becithcon48839.2019.9063181","DOIUrl":"https://doi.org/10.1109/becithcon48839.2019.9063181","url":null,"abstract":"","PeriodicalId":234540,"journal":{"name":"2019 IEEE Conference on Information and Communication Technology","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123163097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. Rajesh, M. Javed, Shubham Srivastava, Madan Mohan Malaviya
{"title":"DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients","authors":"B. Rajesh, M. Javed, Shubham Srivastava, Madan Mohan Malaviya","doi":"10.1109/CICT48419.2019.9066242","DOIUrl":"https://doi.org/10.1109/CICT48419.2019.9066242","url":null,"abstract":"The popularity of Convolutional Neural Network (CNN) in the field of Image Processing and Computer Vision has motivated researchers and industry experts across the globe to solve different challenging research problems with high accuracy. The simplest way to train a CNN classifier is to directly feed the original RGB pixel images into the network. However, if we intend to classify images directly with its compressed data, the same approach may not work better, like in case of JPEG compressed images. This research paper investigates the issues of modifying the input representation of the JPEG compressed data, and then feeding into the CNN. The architecture is termed as DCT-CompCNN. This novel approach has shown that CNNs can also be trained with JPEG compressed DCT coefficients and subsequently can produce a good performance similar to the conventional CNN approach. The efficiency of the modified input representation is tested with the existing ResNet-50 architecture and the proposed DCT-CompCNN architecture on a public image classification datasets like CIFAR-10, Dogs vs Cats and MNIST datasets, reporting a better performance.","PeriodicalId":234540,"journal":{"name":"2019 IEEE Conference on Information and Communication Technology","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114146395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}