MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

Engineering and Technology

The term “big data” means a large amount of data, and big data management refers to the efficient handling, organization, or use of large volumes of structured and unstructured data belonging to an organization. Due to the gradual availability of plenty of raw data, the knowledge extraction process from big data is a very difficult task for most of the classical data mining and machine learning tools. In a previous paper, the correlative naive Bayes (CNB) classifier was developed for big data classification. This work incorporates the fuzzy theory along with the CNB classifier to develop the fuzzy CNB (FCNB) classifier. The proposed FCNB classifier solves the big data classification problem by using the MapReduce framework and thus achieves improved classification results. Initially, the database is converted to the probabilistic index table, in which data and attributes are presented in rows and columns, respectively. Then, the membership degree of the unique symbols present in each attribute of data is found. Finally, the proposed FCNB classifier finds the class of data based on training information. The simulation of the proposed FCNB classifier uses the localization and skin segmentation datasets for the purpose of experimentation. The results of the proposed FCNB classifier are analyzed based on the metrics, such as sensitivity, specificity, and accuracy, and compared with the various existing works.

School of Computer Engineering & Technology

World University root node

Fulltext

Journal of Intelligent Systems

FCNB: Fuzzy correlative naïve bayes classifier with MapReduce framework for big data classification

Human-Computer Interaction is a flourishing area in terms of research and has many real-world applications. Keeping this in mind, we came up with an idea to develop Human- Computer interaction for proper conduct of physical exercises at home, using information sensed by an RGB-D camera, namely the Microsoft Kinect. Along with Kinect, we also make use of a Machine Learning technique to perform operations on captured data to predict the accuracy of a performed physical exercise. Our approach is based on the study of the movement of various joints in the human body, which we examine with the use of the Kinect. We take into account an algorithm for our implementation - Hidden Markov Model (HMM). We combine these and detect the posture of a user while he performs a particular exercise, before comparing it with our ideal database of postures. Based on this comparison, we predict the accuracy of the exercise and aim to improve and correct the form of the user in terms of performance of the exercise.

International Journal of Computer Applications

Virtual Personal Trainer using Microsoft Kinect and Machine Learning

Images of four qualities of mangoes and guavas are evaluated for color and textural features to characterize and classify them, and to model the fruit appearance grading. The paper discusses three approaches to identify most discriminating texture features of both the fruits. In the first approach, fruit’s color and texture features are selected using Mahalanobis distance. A total of 20 color features and 40 textural features are extracted for analysis. Using Mahalanobis distance and feature intercorrelation analyses, one best color feature (mean of a*[L*a*b* color space]) and two textural features (energy a*, contrast of H*) are selected as features for Guava while two bestcolor features (R std, H std) and one textural features (energy b*) are selected as features for mangoes with the highest discriminate power. The second approach studies some common wavelet families for searching the best classification model for fruit quality grading. The wavelet features extracted from five basic mother wavelets (db, bior, rbior, Coif, Sym) are explored to characterize fruits texture appearance. In third approach, genetic algorithm is used to select only those color and wavelet texture features that are relevant to the separation of the class, from a large universe of features. The study shows that image color and texture features which were identified using agenetic algorithm can distinguish between various qualities classes of fruits. The experimental results showed that support vector machine classifier is elected for Guava grading with an accuracy of 97.61% and artificial neural network is elected from Mango grading with an accuracy of 95.65%. Practical applications: The proposed method is nondestructive fruit quality assessment method. The experimental results has proven that Genetic algorithm along with wavelet textures feature has potential to discriminate fruit quality. Finally, it can be concluded that discussed method is an accurate, reliable, and objective tool to determine fruit quality namely Mango and Guava, and might be applicable to in-line sorting systems

School of Electronics & Communication Engineering

Journal of Texture Studies (Wiley)

Appearance and characterization of fruit image textures for quality sorting using wavelet transform and genetic algorithms

This paper describes a half car model of an active suspension where control strategy is based on controlling the mass flow rate of air into the air spring. Three control strategies based on controlling the mass flow rate of air into air spring are presented. Equations of motion are developed and solved using MATLAB. Using the results of the simulation of the model based on each of these control strategies for different gain values in the control system, it is concluded that the stiffness of the suspension can be dynamically controlled by using a suitable value of gain in the control system. It is observed that an undamped active air suspension based on mass flow control having the mass flow of air into air spring as a function of the relative velocity between the sprung and unsprung mass with the gain equal to one has zero response of the sprung mass in bounce. The response of sprung mass in bounce and pitching motion is less than the input from the road for the damping ratio in suspension not exceeding 0.3. Hence, the control strategy based on mass flow control having the mass flow of air to air spring as a function of the velocity of sprung mass with respect to the velocity of unsprung mass with the gain equal to one is proposed.

School of Mechanical Engineering

International Review of Mechanical Engineering

Active Air Suspension for a Vehicle Based on Control of Air Mass Flow Rate

The objectives of this article was to review the literature on image analysis studies. The review article discussed various contemporary topics and studies performed by researchers in last five years. The various topics discussed are Advances in Biomedical imaging, Big data work flow for biomedical image analysis, Biomedical Image Analysis of Micro-bubbles in Dental Ultrasonic Scalars, Dynamic Programming Based Segmentation in Biomedical Imaging, Thermal Image Analysis using Serpentine method, A Review of Novel Approaches In Orthopaedic And Endoscopy and Biomedical Image Analysis of Obturated Root Canal: A Proposed Approach etc. The advances in biomedical image analysis are discussed based on the transform type used and fusion type used. The various transforms such as Laplace, Wavelet, Shearlet, Hilbert, Warbler, Tunable and Q Hadamard etc. The various types of fusions are used by authors to calculate the accuracy but there are certain limitations which we have discussed. The big data workflow process is discussed in detail. The biomedical image analysis for micro-bubble of dental ultrasonic scalar is reviewed. M-tracking is used for calculating the bubble radius and speed of bubble for analysis purpose. The M-tracking plugin helps to track the location of bubble. The cavitation is one of the most effective method to remove the bio-film of biomedical surfaces. The dynamic based programming helps to highlight the lines, contour and organ margin or location. The biomedical image analysis has its four quadrant viz. physics, medical imaging, machine learning and image processing and graphics. All the above discussed studies provides sound basis for future research. The biomedical image analysis of obturated root canal using pixel programme is proposed work by the authors of this review article, is also discussed. This review article is helpful and informative to Ph.D. scholars, researchers, decision makers and experts in the field of biomedical image analysis. The review is also useful in inter-disciplinary fields which are concerned with biomedical image analysis. In future the biomedical image analysis can be effectively implemented for faster diagnosis, qualitative analysis of obturation.

Communications in Computer and Information Science

A Review of Contemporary Researches on Biomedical Image Analysis

Green Supply Chain Management (GSCM) has become one of most promising tool in reducing environmental hazards of manufacturing industries. Selection of indicators and its implementation needs good decision making. The Aim of Relative Reliability Risk Index (R3 I) is to assess relatively the reliability of an industry wherein GSCM can be implemented and to screen out the ones that are judged to have unacceptable level of rank and hence risk. The relative measurement of indicators is done by Analytical Hierarchy method and weights are assigned through entropy method. Alternatives Functionality Graph is plotted to get to know the strength of each indicator. Relative Reliability Risk Index (R3 I) is calculated and results obtained from the case study are compared.

International Journal of Mechanical Engineering and Technology

Relative Reliabilty Risk Index for Green supply chain management

Electrochemical machining (ECM) provides the alternative to traditional or conventional machining processes without a workpiece, with high material removal rates, irrespective of diverse mechanical properties of the workpiece. Even though ECM has a great potential, the process is still not fully explored and its research is in proce phenomena such as electrochemistry, mass transfer, heat transfer and hydrodynamics taking place simultaneously and leads to different material removal rate at each point on the anode surface (Workpiece). Due to this it is profile accurately in ECM process. This problem is considered for investigation by developing a Multiphysics simulation model for ECM hole making process and the effect of tool geometry on generated anode profile is stu dimensional control and performance of the electrochemical machining process. For development of Multiphysics simulation model for the tool design in ECM hole making process, finite element analysis (FEA) software, COMSOL is used becaus capability to couple various phenomena in ECM process in a single model for better accuracy.ECM performance characteristics namely; overcut and height of spike generated is predicted by simulation and the accuracy and capability. The predicted and experimental results agreed well and the developed innovative simulation model provides complete visualization and understanding of the ECM process.

An Innovative Simulation Approch to improve the electrochemical Machining Performance

A basic understanding of the changes in the condition of the surface is very muchrequired if improvement in product quality is to be attained. Surface integrity (SI)reveals the influence of surface properties and condition upon which materials arelikely to perform. Burnishing is a post machining process that is traditionally used toimpart specific physical, mechanical and tribological properties on ferrous and nonferrous surfaces. The aim of this work is to present and discuss the variousmethodologies and strategies that are adopted by researchers to predict surfaceintegrity of burnished component. The presentation of each approach along with itsadvantages and disadvantages should help both the researchers and practitioners byproviding compact yet adequate information to select the one that best suits theirneeds and specific requirements.

A Review Burnishing Process for Surface Roughness and Microhardness

This paper focus on the effect of volute tongue clearance variation on the performance of backward-curved blades centrifugal blower. The four types of casings of the centrifugal blower with different volute tongue clearances of 6%, 8%, 10% and 12.5% of impeller diameter were used for numerical and experimental analysis. Computational fluid dynamics model was developed for for the numerical analysis based on experimental setup. Reynolds-averaged Navier-Stokes equations with the standard k-ε turbulence model were discretized with finite volume approximations. The Numerical results were validated with the experimental results by using IS: 4894-1987. The performance parameters such as total pressure, efficiency and flow rate of the blower were calculated. The results show that the volute tongue clearance has a significant effect on the performance of centrifugal blower and these parameters increases with decrease in volute tongue clearances.

Materials Today, Elsevier

Effect of VoluteTongue Clearance Variation on Performance of Centrifugal Blower by Numerical andExperimental Analysis

Wireless sensor network (WSN) is a dynamic self - configured device which is used for the communicational purpose to monitor different scenarios. To the best of our knowledge, the main challenge faced in the field of wireless sensor network is computing, monitoring and the size of the sensor. In this paper we underscore the fact of analysis of the behavior of wireless sensor network using different factors and protocols. By analysis we can predict the behavior and analyze the superficiality. © 2017 IEEE.