M Senthilkumar

Bio: M Senthilkumar is an academic researcher from VIT University. The author has contributed to research in topics: Scheduling (computing) & Global warming. The author has an hindex of 3, co-authored 5 publications receiving 113 citations.

An assessment framework of intuitionistic fuzzy network for C2B decision making

Abstract: Decision making is a difficult task over the complex, spirited and competitive environment. A variety of research provides diverse notification for individual failure in making logical decisions under certain circumstances by applying normative approaches. In today's competitive market, the advance of technology is closely related to consumer needs for the extraction of good quality products at less cost which is in rarely finding a model in Consumer to Business (C2B). The aim of the paper is to optimize the C2B model by intuitionistic Fuzzy to resolve multi decision making problems. It derives multi criteria decision making to support complex environments in C2B using membership and non-membership attributes which is built to generate the intuitionistic fuzzy priority weighting vector based on minimum distance and similarity measures. This technique classifies the object type as per the customer needs with a ranking in the optimized way make efficient for the customer satisfaction.

Physicians medicament using linear public key crypto system

Abstract: Now-a-days, in the medical field, prescribing a medicine for a patient without mentioning its brand name is a tedious job. But it can be made possible, when both the parties (physician and pharmacist) are adapting well and standardized methodology. Our aim is to suggest an idea to make this process easy to understand and light to use. Based on the types of common diseases, the medicinal prescription lists can be categorized with relevant medicinal blocks. If a physician prescribes the medicine through this standardized predefined scheme, then the system will generate a unique number using Grace Code Cryptography and Linear RSA algorithms. The unique number will be given to the patient in the prescription sheet. Through this unique number, the pharmacist can get back the medical unit which is intended for a particular patient with the help of the same algorithms and using the standardized predefined scheme as it is a general template, and he delivers the medicine. So the patient will be given the prescribed medicine without specifying the brand name at any stage.

Calculating the user-item similarity using Pearson's and cosine correlation

Abstract: In this paper, we look into three different techniques for computing similarities for obtaining a recommendation for them. There are a number of different mathematical formulations that can be used to calculate the similarity between two items. On the basis of various parameters, we conclude Pearson's Correlation Coefficient provides better quality than the others.

Energy-Aware Task Scheduling Using Hybrid Firefly-BAT (FFABAT) in Big Data

Abstract: Abstract In modern times there is an increasing trend of applications for handling Big data. However, negotiating with the concepts of the Big data is an extremely difficult issue today. The MapReduce framework has been in focus recently for serious consideration. The aim of this study is to get the task-scheduling over Big data using Hadoop. Initially, we prioritize the tasks with the help of k-means clustering algorithm. Then, the MapReduce framework is employed. The available resource is optimally selected using optimization technique in map-phase. The proposed method uses the FireFly Algorithm and BAT algorithms (FFABAT) for choosing the optimal resource with minimum cost value. The bat-inspired algorithm is a meta-heuristic optimization method developed by Xin-She Yang (2010). This bat algorithm is established on the echo-location behaviour of micro-bats with variable pulse rates of emission and loudness. Finally, the tasks are scheduled with the optimal resource in reducer-phase and stored in the cloud. The performance of the algorithm is analysed, based on the total cost, time and memory utilization.

XGBRS Framework Integrated with Word2Vec Sentiment Analysis for Augmented Drug Recommendation

Abstract: Machine Learning is revolutionizing the era day by day and the scope is no more limited to computer science as the advancements are evident in the field of healthcare. Disease diagnosis, personalized medicine, and Recommendation system (RS) are among the promising applications that are using Machine Learning (ML) at a higher level. A recommendation system helps inefficient decision-making and suggests personalized recommendations accordingly. Today people share their experiences through reviews and hence designing of recommendation system based on users’ sentiments is a challenge. The recommendation system has gained significant attention in different fields but considering healthcare, little is being done from the perspective of drugs, disease, and medical recommendations. This study is engrossed in designing a recommendation system that is based on the fusion of sentiment analysis and radiant boosting. The polarity of the sentiments is analyzed through user reviews and the processed data is fed into the Extreme Gradient Boosting (XGBOOST) framework to generate the drug recommendation. To establish the applicability of the concept a comparative study is performed between the proposed approach and the existing approaches.

Analysing the concrete compressive strength using Pearson and Spearman

Abstract: Spearman's rank relationship coefficient is a nonparametric (dispersion free) rank measurement. Spearman's coefficient is not a measure of the direct relationship between two factors, as a few ”analysts” proclaim. Pearson's relationship coefficient is the covariance of the two factors separated by the result of their standard deviations. The possibility of the paper is to look at the estimations of Pearson's concrete compressive strength coefficient and Spearman's rank relationship coefficient and in addition their factual hugeness for various arrangements of information depicting provincial records of the financial advancement. In this, the Spearman correlation coefficient is based on the ranked values for each variable rather than the raw data. Spearman correlation is often used to evaluate relationships involving ordinal variables. The Pearson and Spearman's method is compared with the rank coefficient in the concrete compressive strength.

Memory efficient multi key (MEMK) generation scheme for secure transportation of sensitive data over cloud and IoT devices

Abstract: A new variant of RSA has been proposed called Memory Efficient Multi Key (MEMK) generation scheme. For sensitive data, our scheme will aid in exchanging the information between cloud to IoT and IoT to IoT devices. When cryptography belongs to the asymmetric type, then it has public and private keys. For memory efficiency, our scheme reuses the RSA scheme with a Diophantine form of the nonlinear equation. Moreover, our scheme performance comparatively performs well and this mainly due to the use of RSA public key alone. Due to this, our MEMK does not require multiplicative inverse function or Extended Euclid's algorithm. Finally, we have made an experimental result on various phases of MEMK PKC such as key generation, encryption, and decryption by varying the N-bit modulo bits from 1K to 10K.

Physicians medicament using linear public key crypto system

Abstract: Now-a-days, in the medical field, prescribing a medicine for a patient without mentioning its brand name is a tedious job. But it can be made possible, when both the parties (physician and pharmacist) are adapting well and standardized methodology. Our aim is to suggest an idea to make this process easy to understand and light to use. Based on the types of common diseases, the medicinal prescription lists can be categorized with relevant medicinal blocks. If a physician prescribes the medicine through this standardized predefined scheme, then the system will generate a unique number using Grace Code Cryptography and Linear RSA algorithms. The unique number will be given to the patient in the prescription sheet. Through this unique number, the pharmacist can get back the medical unit which is intended for a particular patient with the help of the same algorithms and using the standardized predefined scheme as it is a general template, and he delivers the medicine. So the patient will be given the prescribed medicine without specifying the brand name at any stage.

Data analysis using box and whisker plot for lung cancer

Abstract: In statistical analysis, we have a collection of data, with the use of these data, we have to do analysis based on our requirements. With the collection of data using Statistical analysis, we deal collection, analysis, presentation and organizing the data. With the help of statistical analysis, we can find underlying patterns, relationships, and trends between data samples. The R system for statistical computing is an environment for data analysis and graphics. Here we are going to implement boxplot method and control chart methods for Lung cancer dataset. With the help of boxplot, we can easily make relations between samples and we can find the outliers.

Decision making system using machine learning and Pearson for heart attack

Abstract: This informational collection is utilized to anticipate the odds of an event of heart assault for a patient. In the season of cutting edge smartphones contributing 12 attributes is not feasible. We play out the product metric examination on the given informational collection. In view of the investigation of information we try to bring the total number of attributes into a small figure and in the end, we may be able to choose which property can be considered and which characteristic can be disregarded.