KCG College of Technology

About: KCG College of Technology is a based out in . It is known for research contribution in the topics: Computer science & The Internet. The organization has 427 authors who have published 381 publications receiving 2193 citations.

Continuous user authentication using multimodal biometric traits with optimal feature level fusion

Abstract: The biometric process demonstrates the authenticity or approval of an individual in view of his/her physiological or behavioural characteristics. Subsequently, for higher security feature, the blend of at least two or more multimodal biometrics (multiple modalities) is requiring. Multimodal biometric technology gives potential solutions for continuous user-to-device authentication in high security. This research paper proposed continuous authentication (CA) process using multimodal biometric traits considers finger and iris print images to various feature extraction process. At that point, features are extracted into optimal feature level fusion (FLF) process. The final feature vector is acquired by concatenating directional information and centre area features. Disregard the optimal feature process the inspired fruit fly optimisation (FFO) model is considered, and then these model is fused into authentication procedure to find the matching score values (Euclidian distance) with imposter and genuine user. From the approach, results are accomplished most extreme accuracy, sensitivity and specificity compared with existing papers with better FPR and FRR value for the authentication process. The result shows 92.23% accuracy for the proposed model when compared to GA, PSO which is attained in MATLAB programming software.

Performance of spectrum sharing cognitive radio network based on MIMO MC-CDMA system for medical image transmission

Abstract: Cognitive radio (CR) is a futuristic technology which efficiently uses the underutilized TV band spectrum for mobile communication. The spectrum scarcity issue, mobile traffic due to ever-increasing number of clients utilizing the same spectrum and interference problems will be efficiently handled by CR networks. In this paper, we employ CR spectrum for safe transmission of medical reports consisting of magnetic resonance imaging (MRI) scanned images. An effective image encryption algorithm named Arnold cat-map (ACM) transform is used in order to prevent unauthorized alterations in the MRI scanned image by any un-authenticated personnel. Further, we upgrade the resolution of the MRI scanned image by super-resoluting it by SPARSE super-resolution technique. Furthermore, we analyze the transmission of MRI scanned image by considering turbo code as channel encoder. We incorporate space time block code (STBC) as multiple-input and multiple-output (MIMO) profile due to its supremacy in spatial diversity and code division multiple access (CDMA) for simultaneous data transmission to numerous users, for transmission of the MRI scanned report. We utilize CR sub-band frequency to realize multi-carrier (MC) communication and to generate orthogonal spread-spectrum. Furthermore, we also analyse the error rate performance of the system for various Stanford University Interim (SUI) channel models. Finally, from the simulations we divulge that CR defined MIMO MC-CDMA system obtain MRI image with enhanced resolution and upgraded privacy when communicating through realistic channel model specifications.

A Drug Recommendation System for Multi-disease in Health Care Using Machine Learning

Abstract: The remarkable technological advancements in the health care industry have improved recently for the betterment of patients’ life and providing better clinical decisions. Applications of machine learning and data mining can change the available data to valuable information that can be used for recommending appropriate drugs by analyzing symptoms of the disease. In this work, a machine learning approach for multi-disease with drug recommendation is proposed to provide accurate drug recommendations for the patients suffering from various diseases. This approach generates appropriate recommendations for the patients suffering from cardiac, common cold, fever, obesity, optical, and ortho. Supervised machine learning approaches such as Support Vector Machine (SVM), Random Forest, Decision Tree, and K-nearest neighbors were used for generating recommendations for patients. The experimentation and evaluation of the study was carried out on a sample dataset created only for testing purpose and is not obtained from any source (medical practitioner). This experimental evaluation shows that the Random Forest classifier approach yields a very good recommendation accuracy of 96.87% than the other classifiers under comparison. Thus, the proposed approach is considered as a promising tool for reliable recommendations to the patients in the health care industry.

Study on Machine learning based Social Media and Sentiment analysis for medical data applications

Abstract: Due to the rapid advancements in social media, it generates voluminous data in almost different areas of applications. Large amount of potential health related data are being available in large scale in various sources of internet. We explored the small use case of social media data for a particular disease, cancer on three different social media platforms such as google trends, twitter and online forums with the sentiment analysis of the mined text. The study shows that people are more relied on social media for their health related queries and the twitter analysis shows that there is a significant raise in the percentage of positive sentiments in the tweets shared by the organizations and individuals on cancer.