Sir Padampat Singhania University

About: Sir Padampat Singhania University is a education organization based out in Udaipur, India. It is known for research contribution in the topics: Encryption & Diesel fuel. The organization has 124 authors who have published 228 publications receiving 2066 citations. The organization is also known as: SPSU.

Mapping of Disease Names to Standard Codes for Effective EHR System in India

Abstract: Ministry of health and family welfare (Govt of India) have recommended some guidelines for effective adoption of (Electronic Health Records (EHR) In these guidelines various health record standards are also recommended Electronic Health Record is need of the time in India Successful treatment methods are available in India The Health care is provided in different hierarchy and all service providers are involved at each hierarchy The hierarchy is distributed among rural, semi urban and urban sector Health care service is provided by Auxiliary Nurse Midwifery (ANM), Accredited Social Health Activist (ASHA), Primary Health centres, Govt Medical Officers and general practitioners and specialist in relevant area of treatment This paper speaks about providing the EHR Model with recording health information using standards recommended by National electronic Health record authority (NeHA)

Rigorous design of moving sequencer crash tolerant atomic broadcast with unicast broadcast

Abstract: This article investigates a novel mechanism of atomic broadcast in distributed systems. Various mechanisms are already given for moving sequencer based atomic broadcast like RMP [1], DTP [2] and Pin Wheel [3]. Since all these mechanisms are built on broadcast broadcast (BB) variant [4] of fixed sequencer atomic broadcast hence introduce a very large number of messages [4]. Here we propose a novel mechanism that works on unicast broadcast (UB) invariant of fixed sequencer atomic broadcast in order to build moving sequencer atomic broadcast. The proposed mechanism relies on unicast broadcast hence it will introduce a very less number of messages in comparison to previous mechanisms [4]. Along with broadcast any process may get crash any time. Hence, system must be so efficient such that it can tolerate such crashes and maintains normal behavior so that reliability of system will be maintained. The proposed work will tolerate any crash failure of processes in system and reduce the load on sequencer (by providing an opportunity to each process to be a sequencer). We have used B [5] as formal technique for development of our model. B uses set theory as a modeling notation, refinements to represent system at different abstraction level. We have used Pro B [19] model checker and animator for constraint based checking, discover errors due to invariant violation and deadlocks, thereby, validating the specifications. We present an abstract model specifying atomic broadcast with a fixed sequencer and introducing moving sequencer in first refined version then introduction of crash tolerance in second refined version.

Multiple Image Encryption with Fractional Hartley Transform and Robust Chaotic Mapping

Abstract: In this paper, we present a simple yet highly robust mechanism for multiple image encryption with optical transformation. A fractional order Hartley transform framework along with secret reversible integer transform (RIT) is used to decorrelate the images. The selection of fractional orders is based on a robust chaotic mapping. Optical transforms support fast and parallel processing but have limitation in digital implementation due to complex coefficients. We present a paradigm where complexity is completely eliminated at each security level to overcome the need of time consuming phase retrieval algorithms. The amalgamation of chaos further make it a highly sensitive and secure technique. This method gives optimum results with almost uniform histogram and lossless recovery of data which is otherwise limitation of optical transforms whose energy is concentrated at the center.

An Image Texture based approach in understanding and classifying Baby Sign Language

Abstract: A sign language is a mode of communication in which the intent of the message or the message itself is conveyed through body postures or the movement of the parts of the body like head, eyebrows and cheeks etc. Every expression is distinct and has distinguishable parts of language, its grammatical content fully displayed through gestures. There are more than three hundred sign languages used in the world. The baby sign language is a method of communication between the mothers and their toddlers by means of gestures, clearly expressing their emotions and desires. In the present research work study of the existing literature has been carried out and then prepared a data set of still jpeg images for 60 odd baby signs, performed GLCM(Gray Level Co-Occurrence Matrix) based feature extraction, then performed classification of gestures using KNN and Random Forest based machine learning algorithms. A classification accuracy of 73% has been achieved on the dataset prepared.

Machine Learning Techniques for Music Genre Classification

Abstract: Music plays a significant role in one’s life. The quantity of music released daily is increasing tremendously on Internet platforms like Soundcloud and Spotify. Music brings like-minded people together. Classification has been a challenging task in the field of music retrieval (MIR). Categorization of music can help explain some of the exciting problems such as creating song references, finding related songs, and finding communities that will love that particular song. The aim of our research is to find the best machine learning algorithm that predicts the type of songs using machine learning methods. This paper provides a comparative analysis of the varied machine learning methods used in the field of genre planning.