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 continuous battle against the variants of Corona Virus demands speedy treatment and quick diagnostic reporting on priority basis. With millions of people contracting the infection every day and a mortality rate of 2%, our goal is to solve this growing problem by developing an important and substantive method for diagnosing COVID19 patients. Due to a proportionally reduced number of medical practitioners, testing kits, and other resources in densely populated nations, the exponential development of COVID19 cases is having a significant impact on the health care system, making it increasingly important to identify infected patients. The goal of this work is to develop an exact, productive and time-saving algorithm to identify positive corona patients that addresses the aforementioned issues. In this paper, a Deep Convolution Neural Network model called "EfficientNet"is implemented and explored that can reveal significant diagnostic characteristics to enable radiologists and medical specialists locate COVID-19 infected patients using X-ray pictures of the chest and aid in the fight against the pandemic. The experimental findings conclusively indicate that an accuracy rate of 99.71 percent was obtained for binary classification of Non-COVID and COVID Chest X-ray pictures. Our pretrained Deep Learning classification model can be a significant contribution to recognizing COVID-19 inflicted individuals due to its high diagnostic accuracy. © 2022 IEEE.

World University root node

School of Computer Engineering & Technology

2022 IEEE 7th International conference for Convergence in Technology, I2CT 2022

Deep Pre-Trained Convolutional Neural System for High-Accuracy Covid19 Forecasting from Chest X-Rays

School of Electronics & Communication Engineering

Deep Learning Techniques for Automated Image Captioning

The solar PV panel is an attractive alternative among all other energy sources for electricity generation. The deposition of dust and stains can considerably decrease the effectiveness of the PV panel. Thus, the cleaning of the PV panel is essential. Many researchers are developing effective cleaning techniques for solar PV panels to maintain their efficiency over the period. The various PV panel cleaning techniques such as natural cleaning, manual washing and brushing, wind blowing, automated mechanical cleaning, automated water spraying, ultrasound vibration, the microcontroller-based automatic cleaning method, electrostatic cleaning system (EDS), superhyperbolic coating, and superhydrophilic coating are discussed in this paper. This review can help in selecting the most suitable method for PV panel cleaning. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

School of Mechanical Engineering

Lecture Notes in Mechanical Engineering

A Study on Impact of Various Solar Panel Cleaning Methods on Its Performance

The complex interactions of magnetic field with crude oil have always posed challenges in its commercial implementation as a wax deposition control method. In the present work, changes in viscosities of three crude oil samples subjected to varying magnetic fields and time of exposure were measured. The resultant data along with the data from literature was used to develop phenomenological models. These models related the final viscosity with the wax %, magnetic field, time of exposure and wax appearance temperature. The model parameters suggested that the amount of wax and the exposure time were the governing factors for viscosity reduction. Such models would help in the tuning of magnetic field strength and exposure time to obtain a desired viscosity reduction. This would help in the design of better oil transportation systems, thereby generating confidence in the method. © 2022

School of Chemical Engineering

Materials Today: Proceedings

Prediction of viscosity in magnetic fluid conditioning of crude oil

Segmentation of retinal structures, namely optic disc, vessel, demarcation line, and ridge, is essential for describing the characteristics of Retinopathy of Prematurity (ROP). Computerized systems are being developed for automatic segmentation in fundus images to assist the medical experts and bring consistency in the diagnosis. There are multiple challenges in the segmentation task of premature infants’ fundus images. The annotation and ground truth preparation required for the segmentation is complex, challenging, and expensive. Further, ROP datasets are not available publicly, and hence carrying out such a task needs a primary dataset and significant assistance from the domain expert. To address this gap, two primary datasets named HVDROPDB-BV and HVDROPDB-RIDGE were developed. The datasets consist of images captured by two different imaging systems, having different sizes, resolutions, and illumination. This made the trained models generic and robust to data variability and heterogeneity. We propose the modified U-Net architectures by incorporating squeeze and excitation (SE) blocks and attention gates (AG) to segment the demarcation line/ridge and vessel from these datasets. These modifications were tested and validated by ROP experts. The performance of all the three networks (U-Net, AG U-Net, and SE U-Net) was promising, with a variation of 1 to 6% in the dice coefficient for the HVDROPDB datasets. The area under the curve (AUC) obtained for all three networks was above 0.94, indicating them as excellent models. AG U-Net outperformed the other two networks, with a sensitivity of 96% and specificity of 89% for stage detection via new test images. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Multimedia Tools and Applications

Deep dive in retinal fundus image segmentation using deep learning for retinopathy of prematurity

The use of Artificial Intelligence with the help of machine learning has eased the work of healthcare practitioners. This systematic review aims to find effective machine learning models to detect dental caries and oral cancer. Image datasets used in the studies ranged from 74 to 3000 images. Different researchers used different approaches and different evaluation metrics to evaluate their studies with Accuracy and Area Under the Curve (AUC) being the most common metrics. The current implementations of machine learning models lay a foundation to reduce the time and effort required to develop newer models for future developments. Overcoming limitations of small datasets, data integration, and dataset standardization will increase the performance and accuracy of the models and will help machine learning become an integral part of dentistry. © 2022 IEEE.

International Conference on Emerging Trends in Engineering and Technology, ICETET

Enhancement in Dentistry using Machine Learning: A Systematic Review

A blood collection monitor is a device used to collect blood from the donor. The apparatus comprises a cradle, which is provided with regular oscillations through a mechanical linkage mechanism. The standard blood is subtended in the cradle which gets naturally oscillated on the virtue of the cradle moment. The oscillatory movement causes the blood to homogenize with the anticoagulants present in the blood bag, preventing it from coagulation. Moreover, the device includes a blood quantification mechanism that weights the blood collected in the bag and displays the numeral value on the device monitor. These existing blood collection monitoring devices are broadly found to be expensive and heavyweight, making them unaffordable and difficult to port. Moreover, being functioned using electricity makes it dependent on the external power supply, thereby limiting its usage in areas lacking electricity. Thus, a novel attempt was made to resolve these deficiencies by introducing a mechanically operated blood collection and monitoring device. Irrespective of the device's proper functioning, the integration of mechanical transmission mechanism, quantification mechanism, and metallic casing resulted in heavy yet robust construction of the device. The present study discloses the optimization methodologies and their implementation to reduce the device's weight and make it sturdier. The main components of the device were selected for optimization, and the CAD interface was utilized to alter the materials and quantity the weight of the main parts. Other practices were also suggested for better utilization of the device, thereby making it practical and impactful. © 2022

Optimization of mechanically operated blood collection and monitoring device

Additive manufacturing is a developing approach for producing complicated, difficult manufacturing objects. Fused deposition modeling is a manufacturing technique that works on a layer-by-layer basis that is widely utilized in industrial applications for quick prototyping in product design and development. The application of additive manufacturing technology allows the easy creation of complicated objects. Researcher have worked on infill patterns and infill percentages. Most of the research is based on experimental results with varying single process parameters. A study on infill patterns is an important aspect because it influences quality, material cost as well as production cost. In this research work, the simulations were carried out on the 50% and 70% infill rectangular and triangular patterns. It was found that, stresses generated in the triangular pattern are large compared to the rectangular pattern at the 50% infill and vice versa for 70% infill. For 50% infill, the triangular patterns are best suited for applications than the rectangular pattern, and for 70% infill, the rectangular patterns are best suited for applications than the triangular Pattern. © 2022

Numerical comparison of additive manufacturing of ABS material based on infill design subjected to tensile load

Inventions of novel nanocomposites are highly recommended due to predominant physical, mechanical characteristics and infinite design possibilities. Manufacturing of these nanocomposites is a costly and challenging task, as it can show unpredictable characteristics behavior and different order of importance considered prior to manufacturing. Therefore, the selection of the most suitable nanocomposite fulfilling characteristics requirement in specific applications is highly needed. To tackle this difficulty, a novel approach to use multicriteria decision-making (MCDM) models to the nanocomposite selection was presented in this research. The TOPSIS (technique of order preference similarity to the ideal solution) and extended PROMETHEE II (EXPROM2) (preference ranking organization method for enrichment of evaluations) multicriteria decision models were used for the best alternative selection of novel graphene/Al6061 nanocomposites. The graphene/Al6061 nanocomposites were fabricated and characterized to tackle the low strength and hardness deficiency of Al6061. The criteria weights were determined by AHP (analytical hierarchy process). All nanocomposites were ranked and results were compared. The best materials were found as 10G (10% graphene reinforcement) due to excellent ultimate tensile strength (279.69 MPa), hardness (93.73 BHN), proof stress (248.55 MPa), though material cost (506.81 Rs) is high. The results of MCDM analysis were found satisfactory and can be utilized in design and manufacturing in aerospace, automobile, transportation, defense, and other applications. © 2022

Graphene/Al6061 nanocomposite selection using TOPSIS and EXPROM2 multi-criteria decision-making methods

Composite materials are increasingly being used in vehicle manufacturing applications due to their high stiffness, strength, as well as low density. The engine is the vehicle's biggest concentrated weight, and if not properly restricted and isolated, it can cause vibrations. Engine mounting is the most relevant aspects of a vehicle's architecture. The engine attachment to the vehicle has an important effect on total vibrations of the vehicle. Glass fibres have been most widely used in automotive sector, while carbon fibres are mainly used in the aerospace industry. Significant research in the field including car vibration damping could be seen, there hasn't been much done in the area of low-cost machineries or small-scale agricultural machinery. This article is focussing on composite materials used for different vehicle structures and engine mounts for agricultural equipment's and their comparative analysis. It has been observed that modifying the design and materials in accordance with the area of use improves the efficiency of the mount and vehicle structures. © 2022 Author(s).