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

Skin Cancer is the most common (accounting for 40% of cancer cases globally) and potentially life-threatening type of cancers. It was diagnosed in about 5.6 million individuals last year. Automated classification of skin lesions through images has been a challenge throughout the years because of fine variability in their appearance. Deep Learning techniques exhibit potential in tackling fine-margined image-based analysis and manage to provide accurate results. The three modelling stages include data collection and augmentation, model architecture and finally prediction into 7 different types of skin cancer namely actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi and vascular lesions. A Convolutional Neural Network was fabricated (using TensorFlow) obtaining an accuracy of 81.24%. Further Transfer learning Approach was implemented in PyTorch, which yielded accuracies of 96.40%, 98.20%, 98.70% and 99.04% respectively for Wide Resnet101, Resnet50, Densenet121 and VGG19 with batch normalization, which are all trained end-to-end from images directly, to proliferate the scalability of these models and curtail initial diagnostic costs. The aim of this research paper is to render non-invasive skin cancer screening a common norm, making it simpler. © 2020 IEEE.

World University root node

School of Computer Engineering & Technology

Proceedings of the 3rd International Conference on Intelligent Sustainable Systems, ICISS 2020

Skin lesion classification using deep learning and image processing

The flux density distribution and the temperature of the receiver are important parameters to assess the net thermal energy of any Solar Power Concentrator. In the present work, a heliostat field utilizing ganged type of heliostats for process heating application has been designed. A prototype model of the central receiver system consisting of ganged heliostats has been constructed and installed at Pune, Maharashtra, India. A thermocouple method was used to evaluate the total energy focused by the model heliostat system on a flat receiver. The flux density distribution was validated with the ray tracing simulation software ‘SolTrace’. The simulated flux density distribution was found to be in agreement with the measured one for a surface normal error of 10 milliradian. A heliostat field having 100 m2 total mirror area was designed in the north south cornfield layout. This heliostat field was simulated in ‘SolTrace’ software by considering the surface normal errors as 10 milliradian and the total energy gain was estimated. For the purpose of simulation to investigate the solar flux falling on the receiver, four days of the year were selected. It includes the March equinox, summer solstice, September equinox, and winter solstice. © 2020 This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.. All Rights Reserved.

School of Mechanical Engineering

Fulltext

Journal of Thermal Engineering

EXPERIMENTAL AND NUMERICAL INVESTIGATIONS OF SOLAR FLUX DENSITY DISTRIBUTION OVER FLAT PLATE RECEIVER OF MODEL HELIOSTAT SYSTEM

Human and Organizational Factors (HOFs) play an important role in the safe, reliable, and maintainable operation of the CNC turning center (CNCTC). Several human performance influencing factors (PIFs) and organizational factors (OFs) influence the human reliability. In this paper, some human PIFs and OFs which may affect the human reliability during maintenance phase are defined and considered for the prioritization according to their criticality using the expert judgments. It is observed that experience is the most important human performance influencing factor (PIF) and safety culture is the most critical organizational factor (OF) affecting the human reliability. The time-between-failure (TBF) and time-to-repair (TTR) data significantly influenced by HOFs are analyzed using the techniques of reliability and maintainability, and the results of the analysis are compared with those of the TBF and TTR data which are not significantly affected by HOFs. The field failure and repair data were sorted considering the influence of hardware, software, and HOFs using expert judgments and outcomes of reliability and maintainability analysis. It has been observed that 16.33% of the total failures and 15.49% of total repairs are significantly influenced by HOFs. Nearly 66% of the total failures and repairs are due to hardware system. The reliability and maintainability of the CNCTC are greatly influenced by HOFs. The HOFs can reduce the expected life of the components or sub-systems of the CNCTC by 33%. © 2020, Springer Nature Singapore Pte Ltd.

Lecture Notes in Mechanical Engineering

Effects of Human and Organizational Factors on the Reliability and Maintainability of CNC Turning Center

Industrial production is pushed on by the constantly changing market requests and global competition. To keep up with these demands and thrive in a furiously competitive market, rapid advances in current manufacturing technologies are required. Automation is the trendsetter among the technologies currently in operation. To aid in the development of production methods, the idea proposed is predictive maintenance and asset tracking. Predictive maintenance is a revolution in the way machines that are in continuous operation can be constantly monitored to detect an anomaly before it blows up into a full-fledged problem. The device is kept under constant monitoring and readings of different parameters, for example, temperature and vibrations are tabbed. Any reading that strays from the regular pattern could indicate a flaw in the device. By predicting this, downtime for maintenance can be reduced. Asset tracking is another revolutionary method to speed up efficiency in the industrial sector. Using different technologies like Wireless Sensor Networks (WSNs), the assets and their locations can be viewed using a remote device. The benefit of the same lies in the fact that often an asset whose location is unknown, wastes production time of the team by unnecessarily having to look for it. Ultimately, the idea is to implement these technologies using the modern concepts of Machine Learning, Data Visualization, Cloud Computing and the Internet of Things. This paper provides a brief introduction to the architecture of such a system followed by a detailed rundown of the above methodologies for real-time applications. © 2020 IEEE.

2020 International Conference for Emerging Technology, INCET 2020

Cloud-based asset monitoring and predictive maintenance in an industrial IoT system

Activated carbon prepared from agro-waste material i.e. green coconut shell and bamboo using ZnCl2 as an activation agent in an adsorption column (fixed bed) was studied for the treatment of textile industry effluent. The experiment with the fixed-bed column was performed by different process parameters such as 200, 400 and 600 mg/L as different initial concentration of dye, at different bed heights of 100 mm, 200 mm, and 300 mm, and 10, 15, and 20 mL/min as different flow rates. The findings demonstrated that both breakthrough and exhaust times increase, with the height of the bed being increased, but decrease with the concentration of the dye inlet. The breakthrough point was found to depend upon the bed height and flow rate. The maximum uptake capacity was obtained when a 200 mm bed depth was used at an inlet concentration of dye 200 mg/L with a flow rate of 15 mL/minute. It was observed that the bamboo activated carbon BAC has high carbon content, and has a high potential for dyes removal and may become capable substitutes for costly activated carbon. The adsorption capacities of BAC, GCSAC are at par with respect to each other, the overall process scheme may become economical as these materials are available as wastes and practically free of cost. © 2020 Elsevier Ltd. All rights reserved.

School of Chemical Engineering

School of Civil Engineering

Materials Today: Proceedings

Adsorption of textile industry effluent in a fixed bed column using activated carbon prepared from agro-waste materials

Wireless Sensor Networks (WSNs) are key enablers for IoT and pervasive computing paradigm. While devices are being seamlessly enabled with connection and communication capabilities, exploring techniques to quantify and improve quality has gathered significance. This work explores quality of a Data Aggregation Tree (DAT) in sensor networks. DATs are building blocks for data collection in WSNs. In this work Quality of Experience (QoE) and Quality of Service (QoS) of DATs is evaluated using data aggregation ratio $$\alpha $$ and generated data $$\delta $$ respectively. An algorithm Quality Aware Data Aggregation Tree (QADAT) to construct a quality aware DAT is proposed. QADAT adapts the DAT to network and user expectation dynamics. Simulation results show the effectiveness of the proposed algorithm and demonstrates quality awareness through DAT adaptability.

Lecture Notes on Data Engineering and Communications Technologies

Quality Aware Data Aggregation Trees in Sensor Networks

Proper utilization of wireless sensor networks (WSNs) has direct impact on various application developed using it in our daily life. In the past years wireless sensor network is popular area of research due to its applicability in different real scenario like border surveillance, fire detection, underwater application, IoT, body area network, irrigation system. The large number of nodes cooperatively performs a specific task. The nodes work in hazardous environment where human intervention is not possible. The battery power is limited, so proper clustering helps to maintain the network life significantly. There is wide variety of methods to perform clustering. This paper presents general classification of state-of-art clustering schemes.

2020 11th International Conference on Computing, Communication and Networking Technologies, ICCCNT 2020

A survey on clustering in wireless sensor network

Control \& Cybernetics

A survey of big data classification strategies.

International Journal of Pure and Applied Mathematics

Machine Learning for Data Aggregation in Wireless Sensor Networks : A Survey Machine Learning for Data Aggregation in WSN : A Survey

This work has focused on investigating the comparative performance of the conventional type of offshore jacket substructure and a modified twisted-tripod jacket type (MTJ) under static and dynamic loading environment. Conventional four-legged and four number of MTJ structures, with a finite number of leg twisting angles from 0° to 90°, for supporting 5 MW NREL wind turbine were analysed for a selected site. In order to compare performance under dynamic loading, the dimensions of the structures were designed iteratively using static stress analysis to ensure that all structures had a similar level of load-carrying capability. Static analyses were performed using SACS v8 and models were imported to SAP-2000 for dynamic response spectrum analyses. The results obtained here reveal that, in addition to savings in material costs, the modified twisted-tripod jacket performs more efficiently than conventional four-legged jackets. This study has established a framework of procedure for simplified analysis of wind turbine jackets under dynamic loading environment. © Springer Nature Switzerland AG 2020.