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

School of Mechanical Engineering

World University root node

Materials Today: Proceedings

Performance simulation of HFC-161 as an alternative refrigerant to HCFC-22 for room air conditioner

Reservoir characterization is of key importance in upstream industry as it ensures maximum productivity of crude along with the selection of an appropriate method for economic recovery from the sub-surface reservoir. Proper identification of hydraulic flow units and a detailed understanding of pore characteristics are essential in reservoir characterization studies. Here, hydraulic flow unit concept is applied for in-depth characterization of a complex petroleum reservoir from Indian sub-continent having fine-grained sandstone, siltstone together with shale. A semi-logarithmic porosity – permeability plot exhibited large heterogeneity of the reservoir under study. An improved relationship between porosity – permeability was developed through classification of the reservoir formation under study into three hydraulic flow units based on unique flow zone indicator value. Pore size classification of studied core samples were investigated using mercury intrusion capillary pressure curves and later, validated using fractal dimensions calculated using capillary pressure fractal model. Finally, factors affecting the heterogeneity in permeability of subjected reservoir were analyzed. The study indicates that quantitative evaluation of pore system by mercury intrusion porosimetry along with the fractal dimensional analysis can efficiently be applied for verification of hydraulic flow unit classification and hence, for the detailed characterization of heterogeneous petroleum reservoir. © 2021 Elsevier B.V.

School of Chemical Engineering

School of Petroleum Engineering

Journal of Petroleum Science and Engineering

Characterization of heterogeneous petroleum reservoir of Indian Sub-continent: An integrated approach of hydraulic flow unit – Mercury intrusion capillary pressure – Fractal model

Declining quality of air is one of the major challenges faced by cities across the globe today. A product of rapid industrialization and urbanization, air pollution has quickly manifested itself as an existential threat to human life in major urban centres of the world. Developing economies such as India and China are at the forefront in bearing the brunt of this phenomenon. Intelligent predictive analysis is critical for framing policies that can help in controlling the severe effects of air pollution. Although Deep Learning architectures have proven to be effective in reliably forecasting the concentration of hazardous air particles like PM2.5, their predictive capabilities are significantly reduced when the amount of data available is not enough for effective training. Newer monitoring stations often lack the resources and/or personnel to reliably collect meteorological and environmental data, thus suffering from crippling data-insufficiency issues which hinder the applicability of forecasting models. This paper proposes an ensemble approach for Multi-Source Transfer Learning, with the aim of mitigating the data shortage issue. The proposed method generates a cumulative prediction by transferring the knowledge learned from multiple source stations to a given target station, thereby better utilizing the data that is readily available from nearby stations to boost prediction performance. © 2021 IEEE.

School of Computer Engineering & Technology

Proceedings - IEEE 2021 International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2021

An Ensemble Approach to Multi-Source Transfer Learning for Air Quality Prediction

Single-point incremental forming (SPIF) process is an emerging sheet metal forming process in which constraint of using dedicated press tools is eliminated. Some process limitations like poor surface finish, longer forming time, higher geometrical error, and uneven wall thickness distribution restrict its applicability in sheet metal industry. But SPIF process with dummy sheet has the capability to overcome some of the prevailing limitations of SPIF process. In the present paper, influence of dummy sheet thickness, step size, wall angle, and feed rate on geometrical error in terms of root-mean-squared error (RMSE) of formed part is investigated. Box Behnken design is used to design the experiments. From the analysis of experimental result, it is found that dummy sheet thickness, step size, and wall angle are significant process parameters influencing RMSE. No significant influence of feed rate on RMSE is observed. RMSE increases with increase in dummy sheet thickness and wall angle, while it decreases with increases in step size. As feed rate increases, there is nominal decrease in RMSE which is desirable. So higher feed rate is recommended to reduce forming time. Further, empirical model is developed to predict RMSE. Also, optimization of process parameters is performed to minimize RMSE. Confirmation experiments were performed in order to check the accuracy of developed predictive model and it is found that predicted results are in good agreement with experimental results. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

Lecture Notes in Mechanical Engineering

Experimental investigation on geometric error in single-point incremental forming with dummy sheet

It is a big challenge to assess and monitor the well-being of geriatric people due to the rise in the average population and keep track of their health status on a daily basis. Nutrition screening is a method used to find the nutrition risk in patients that can be improved by nutritional therapy. Nutrition screening strategy helps to evaluate the nutrition risk of patients which can be improved by nutritional therapy. There are different types of screening forms identified based on age group and hospital settings. The primary objective of the paper is to study the screening forms MUST, NRS-2002, and MNA to identify the correlation between the form parameters using statistical methods. The purpose of this study is to design a system to understand the nutritional status of the patient and identify patients that will be benefited from nutrition therapy. A classification algorithm of data mining is proposed to identify patients with comorbidities and hence suffering from malnutrition. It will help physicians to take the daily decision-making activities to prevent the events before occurring. The patients’ health care can be monitored by the use of devices like mobile applications by observing patients’ nutrition intake. The developed system helps to keep track of the geriatric patient’s health and improve the method of how dietician or practitioner delivers care when the patient is monitored remotely. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Smart Innovation, Systems and Technologies

Malnutrition Identification in Geriatric Patients Using Data Mining

Requirement Engineering (RE) plays an integral role throughout the process of software development. Requirement identification and prioritisation are the foremost phases of the RE process. Latest RE research work uses Machine Learning (ML) algorithms to tackle RE problems such as identifying requirements and assigning priorities to requirements, which have given better results than that of traditional natural language processing methods. An adequate understanding of these ML methods, however, is still lacking. The aim of this study is to understand which of the ML algorithms is likely to classify and prioritise the requirements efficiently and how they can be evaluated. It is observed that the current approaches are having constraints of scalability and complexity. Different methods used for the text preprocessing of requirements from SRS and user reviews are also proposed. 6 different ML algorithms and 6 different prioritisation algorithms, which are most common methods, are found. The most popular performance parameters used are accuracy, precision and recall. The limitations of these ML approaches are irrespective of dependency of requirements, priorities are assigned to requirements, the results with respect to scalability and speed is inferior. © 2021 IEEE.

Proceedings of the Confluence 2021: 11th International Conference on Cloud Computing, Data Science and Engineering

Classification and prioritisation of software requirements using machine learning - A systematic review

Smart devices are exciting and upcoming advancements in the field of Internet of things (IOT). It is an application of Raspberry Pi, from furniture in the residential and commercial sector to everyday devices like watches and headphones, every object is becoming smarter and hence, making human lives much easier and efficient. Users can actively interact with these devices using voice commands. These smart devices can also assist a user in their personal daily activities as well as in medical use. Currently, various variations of the smart mirror based on software and hardware compatibility as well as based on applications and uses are available in the market. The goal of this paper is to understand the working, various applications, and purposes of the smart mirror according to the varying features in different versions. This paper critically analyses the different versions of the smart mirror and its different features and applications. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Study Based on Advancements in Smart Mirror Technology

In the present experimental work, hybrid incremental sheet forming (HISF) process comprising stretch forming followed by single point incremental sheet forming (SPIF) is developed for forming conical frustum. Experimental investigation is done to find the influence of process parameters on thickness distribution and localized thinning in the formed parts. Experimental result reveals that stretching has a substantial effect on localized thinning in formed parts. Small improvement in the thickness distribution and localized thinning is found in formed parts. Experimental investigation on the influence of preform tool shape is also done to further improve thickness distribution. It is observed that the geometry of preform tool and amount of stretching has a great influence on thinning and thickness distribution. It is found that intermediate preform tool size and small amount of preforming results in forming conical frustum having uniform thickness distribution. Also, a considerable reduction in forming time using developed HISF process is observed as compared to SPIF process alone. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.

Hybrid incremental forming: Investigation on localized thinning and thickness distribution in formed parts

The extensive use of composites materials has created disposal and environmental issues. With awareness of preserving the environment, the use of environmentally friendly, sustainable and biodegradable composites have been started. From few decades, natural fiber-reinforced composites (NFRC's) and bio-degradable resins are used extensively for automotive, construction and other applications. The hybridization of synthetic fiber with natural fiber has gained the attention of researchers. The axisymmetric components such as pressure vessel, driveshaft, storage tanks, pipes, etc. are fabricated by filament winding process. Commonly glass, carbon, aramid fibers are used for this process. The use of natural fibers is challenging in filament winding as these fibers are not continuous, hydrophilic nature, poor bonding with matrix, available geographically, less tensile strength as compare to synthetic fibers. This paper is intended to explore the potential of natural fiber for the filament winding process. High cellulose content and low microfibril angle (MFA) in plant fiber are responsible for the high strength of the natural fiber. Surface modification techniques improve the adhesion between fiber and matrix which results in improving the tensile strength of the composite. Few researchers used sisal, flax and jute fiber for the filament winding process. This paper contains, an outline of filament winding process parameters like fiber tension, winding pattern, winding angle, optimum winding pattern and potential of few plant-based natural fibers and their properties have been highlighted for filament winding process. Also, surface modification techniques to improve the tensile strength of a few plant-based fibers are also been discussed. The global composite pressure vessel synthetic material market is expected to grow at a Compound Annual Growth rate (CAGR) of 23% from 2017 to 2023. The development of a new hybrid composite made of natural and synthetic fiber suitable for filament winding need to be discovered. © 2021 Elsevier Ltd. All rights reserved.

Biodegradable composites for filament winding process

Nowadays, Project-based learning is an integral part of many professional courses in Engineering. Projectbased learning is a student-centric approach in which students learn about a course by working in groups to solve an open-ended real world problem. In our opinion, it takes students near to the real world at a very early stage. For students, it acts as a tool to learn concepts and principles, to adapt to the evolving ICT industrial requirements and challenges. The objective here is to convey our systematic teaching and learning method, based on Project- based learning, to effectively learn the principles and practices of Software Engineering. Also, it prepares students how to apply these theoretical concepts to solve the real world problems by working in a team. For more than 10 years we are conducting this activity very rigorously for Third Year Computer Engineering students. This activity incorporates applying theory of Software Engineering to develop experiential learning by developing a mini-project using Database and Web Technology. Our 7- point method for development of mini-project has continuous Assessment through critical reviews and presentations by students. We conducted survey for all batches and took their feedback to understand the role of Project Based Learning in their Professional Career. Feedback of these students helps us to update our methodology and/or course contents. Applying Database technology and getting acquainted with development of user interface is bit easy for students but applying the Software Development Life Cycle [3] learnt in Software Engineering is quite challenging. There are many skills they learn and acquire while developing mini-project like questions to be asked during field work, design strategy and analysis through modelling, teamwork[4], time management, communication skills and many more which takes them a step closer and works as a basic building block for their growth as a software professional. Our survey questionnaire gives insight of all and acts as a measuring tool. This paper addresses our 7-point method, design, our process of evaluation and challenges faced by the students and faculty during this process with the help of representative projects. © 2021, Rajarambapu Institute Of Technology. All rights reserved.