SIME Lab Tales

Research is the strong foundation upon which every successful academic institution is built. Here at SIME under the guidance of esteemed faculty members and professors with an avid group of students we are always working and looking to widen and deepen our interests and knowledge. Here are the Research Projects for 2021-2022.

CoviKnow App

This project was led by Srijan Jha - a Junior researcher at the Society for Industrial Management and Engineering. The topic of the project is 'DEVELOPMENT OF A MOBILE DRUG RECOMMENDER SYSTEM FOR COVID-19'. The primary aim of the project is to develop an android application that would assist a patient in getting drug prescriptions based on what symptoms the patient is suffering from COVID-19. Recommender systems are among the many solutions used to obtain valid information. When searching for an item, users obtain a list of recommended results that may match their preferences. Several recommender systems for healthcare have been developed, the challenges recorded so far are that most of them are web-based. This project focuses on the design and development of a mobile recommender system for COVID-19. The main objective of this project was to design a mobile application system for patients that will be able to suggest or recommend drugs based on a listed symptom and to design a recommender algorithm that uses evolving rules using collaborative filtering modeling technique.

Lean Six Sigma Analysis of Coffee Manufacturing Facility

This project was led by Badavath Sushal, a junior researcher at the society. It aims at analysis of supply chain data to understand the root cause of problem that is making the whole chain lag. Almost all quality improvement methods require data collection and analysis to solve quality problems. The combination of six sigma and lean manufacturing creates a six sigma lean approach which aims to reduce variations and waste. In this project, the correlation has been analysed between the caffeine content and the extraction time i.e how the extraction time would affect the caffeine content, and how can we optimize it for a better yield. Understanding the root cause of low quality helps to mitigate it, the process of removing such bottlenecks keeps going on.

Design and Operation of a Drone suitable for the Operations of Animal Husbandry Industry

This project is being carried by Team Scalar (a team of Junior Researchers at SIME) led by Shashank. In its initial stage it deals with design and operation of a drone suitable for the operations of animal husbandry industry. It will be equipped with solar power to get extra energy during its operation, and will pass through a series of iterations before finally saturating the design. Performance of propeller was checked by performing CFD analysis, Further structural analysis of components will be performed to validate calculations of forces and dimensions along with drop test and CFD for frame and design changes will be made accordingly, Finally simulation of electric circuit and sensors will be done to make a fully functional model of drone.


A project on food points and crowd prediction is done by the Team Vector. This project has two parts:- The first one, helps to know the nearest food point and the second one, helps to know the crowd at the food points as well as the availability of food items at appropriate prices. This project will help the students of BIT Mesra to explore the food points specifically the freshers who are new to the vast campus of BIT Mesra. This will not only save their time but also their money. Through the project, all the food points will come under one umbrella. With slight modification, the project can be used at the local and national levels. Contributors - Abhishek Pandey, Aditya Raj Choudhary, Anuj Agrawal , Krishna Kumar Singh Garia

Website link


Crypto/Stock Prediction Algorithms

A project regarding Crypto/Stock prediction algorithms was done by Sanket Patel- a junior researcher at SIME. During this study, the forecasting of the bitcoin market was analyzed. The spread of machine learning methods was utilized, and a comprehensive set of potential market-predictive features was considered. Bitcoin market's predictability over six years of overtime was also examined, and further, the spread of machine learning models was investigated. It was found that while all models outperformed a random classifier, recurrent neural networks and gradient boosting classifiers were particularly well-suited for the prediction tasks.