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

In today’s world of data, large amount of homogenous as well as heterogeneous data is available in service sectors like hotel, tourists etc. Accessing helpful information from these large pool of data is quite tedious task. In developing country like India, Hotel sector is becoming mature now and retrieving and providing information to the users to select appropriate hotel from any unknown place is very crucial. An automated system like recommendation system is useful to provide help in decision making process of any person. Large amount of hotel data, scalability and efficiency problem of traditional service recommendation system leads to create a new hotel recommendation system. In this intelligent system personalised recommendations are provided to the user based on keywords which elaboratesuser’s choices and preferences [8].This system uses collaborative-filtering approach to generate recommendations using MapReduce parallel processing paradigm. Implementations is based on real time data related to hotels situated in Pune city

School of Computer Engineering & Technology

World University root node

INFORMATION TECHNOLOGY IN INDUSTRY

HOTEL RECOMMENDATION SYSTEM BASED ON KASR SYSTEM

Ambulance is a medically equipped vehicle that transports patients to treatment facilities that have tested to be a lifesaver throughout several emergency cases. One of the issues during transportation of patients is traffic related problems. We studied various approaches available for vehicle tracking systems. After going through various research papers we found these techniques, i.e. GPS based tracking, RFID device, Google API, RESTful API which were proposed earlier and hence we deduce that existing ambulance routing technique is not effective as a result of there is lack of help provided to them during the transparent passage through the traffic congestion. This issue arises due to outdated dedicated GPS systems, no proper communication between police and ambulance and difficulty in providing accurate location of the ambulance. To tackle this issue, we propose a system which will help the traffic police easily track any upcoming ambulance with its priority using a mobile application. This system will help in fast, economical and efficient traffic control providing safe, easy and quick passage to the ambulance.

International Journal of innovative Science and Research Technology

Survey Paper on Ambulance Tracking Systems

Internet of Things has brought about revolutionary transformations in area of Monitoring and Maintenance of devices. Sensor technology equipped with the right intelligent algorithms have the potential to provide an end-to-end monitoring service for applications in various areas such as industrial machines, and home automation. This paper aims to describe a similar monitoring service for Fire Extinguishers stored in offices, and buildings. The proposed idea will allow user to monitor the real time status of the pressure inside the extinguisher by capturing an image of the pressure gauge and processing it using image processing algorithms and informing the user if attention is required.

PENSEE JOURNAL

Smart Monitoring of Fire Extinguisher System

&nbsp;Machine learning, a fragment of AI, is popularizing in every industrial domain and making a promising place for itself. It is flourishing for all the companies that are implementing ML. It very well possesses the ability to change the future of industries by offering better ways of working, instead of the existing traditional methods. The real estate sector has witnessed a quite similar situation in terms of the effect it has had on the sales of the real estate properties. ML has made business quite easy by predicting the sales prices of real estate properties on the basis of previous purchases and customer buying patterns. This project is about forecasting the house property prices in Bangalore city. It is accomplished by studying the various features of a particular house that fits appropriately into customer’s requirements, followed by deploying the linear regression ML model on the dataset. The study has shown that a linear regression model is a competent ML algorithm which is simple and at the same time gives accurate results. This project enlightens the fact that ML is a very good alternative for streamlining the business engagement in the real estate sector.

School of Electronics & Communication Engineering

PENSEE

Real estate price prediction using Machine learning

IJRACET

Comparative Study of Image Processing and Transfer Learning Techniques for an Automated PCB Fault Detection System

The purpose of the present work is to find out feasibility of the process to remove copper ions from the aqueous solution using powdered orange peel as an adsorbent. Powered activated carbon was also used along with pretreated orange peel to compare the efficiencies. Adsorption is taken into consideration to be one of the most excellent technologies broadly used in international environmental safety regions. Batch adsorption study was conducted to find out the impact related to the numerous strictures like pH, contact period, adsorbent dosage, concentration of preliminary metal Cu(II) ions besides the size of the adsorbent particle on the removal of copper ions from synthetic solutions. The statistics related to the adsorption isotherm which was obtained by carrying out the experiments, performing modeling of such data is very important so that forecasting of adsorption besides knowhow of adsorption. Experimental statistics were investigated with the use of numerous models related to the adsorption and that includes BET model, Freundlich model, Langmuir model as well as Modified Freundlich isotherms model. Equilibrium facts are also evaluated with the use of above-mentioned models related to the process of adsorption.

School of Civil Engineering

Journal of Physics: Conference Series

Sorption of Cu (II) Ions by Adsorption using Orange Peel

In restaurant industry many of them do not have automated tool for monitoring the customers. Machine learning helps to predict information from the data and Data analysis will provide data in well visualized manner. This project is divided into 3 parts as descriptive learning, predictive learning and prescriptive learning. The application is prepared using php and Data analysis using Google Data Studio and python. With this product restaurant can find their weakness focus on it and can increase the revenue after filling it up. In the project descriptive analysis focuses on customer data and sales data. Predictive analytics focus on in store analysis and expense tracking by visualizations. Lastly, predictive analytics includes Apriori algorithm for making combos of menu and XGBoost and Random Forest Classifier algorithm. The project also includes NLP analysis on reviews given by the customers.

International Journal for Research in Applied Science & Engineering Technology (IJRASET)

Machine Learning and Data Analytics based Restaurant Management System for Improving Customer Experience

Abstract - A hearing aid is a device that sits in or behind the wearer's ear and is designed to modulate and amplify the sound for the wearer. Devices which were used earlier were called eаr trumpets or eаr horns, were раssive funnellike cones which amplified sound and were designed to collect sound and direct it into the eаr canal. The bоne аnсhоred d heаring аid, as well as cochlear inserts, are similar devices. Bluetooth open wireless technology for transmitting and transmitting and receiving dvtr оvеr shоrt distаnсеs (using shоrt-wаvelength rаdiо transmission in ISM band) frоm fix а 24002480 MHz) frоm stationary аnd mоbile devices. Originally designed as a wireless RS-232 data cable by telecommunications operator Eriсsson in 1994 [1]. It can connect multiple devices and cause sync issues. Bluetооth Special Interest Group, which has more than 16,000 member companies in the area of tеlесоmmuniсаtiоn, computing, networking, аnd consumer electronics and security, manages Bluetооth. The SIG oversees the develорment оf the sрeсifiсаtiоn, mаnаges the рrоgrаm which qualifies аnd рrоteсts the trаdemаrks. To be marketed as a Bluetooth device, it must be qualified according to the SIG's standards. The teсhnоlоgy necessitates a network of patents, which are only liсensed for those deviсes which qualify; hence, the рrоtосоl mаy be regаrded as рrоprietаry.

International Research Journal of Engineering and Technology (IRJET)

Design and Development of Hearing Aid System

International Journal for Research in Applied Science and Engineering Technology

A Review of Optical Character Recognition (OCR) in Healthcare

Retinal vessel segmentation aims to separate the structure of blood vessels from the fundus image background. This retinal vasculature is then used for detection of numerous diseases like retinopathy of prematurity (ROP), glaucoma, diabetic retinopathy, coronary heart disease, etc. Deep learning-based semantic segmentation techniques are considered a breakthrough in the field of medical diagnosis using artificial intelligence. Various methods for segmentation with convolutional neural networks have been developed which have become indispensable in tackling more advanced challenges with image segmentation. The limitation is that they all require huge quantities of labeled data which is difficult to collect. To overcome this, U-Net architecture is widely used for segmentation of medical images as it segments the pixels individually and can be trained with a small number of images. In this work, we have implemented U-Net architecture and evaluated it on two public datasets: ‘HRF’ and ‘DRIVE’. An accuracy of 96.64% was obtained on the DRIVE dataset and 94.28% on HRF dataset. To check the model robustness, we tested the model trained on the augmented DRIVE dataset on the HRF dataset and vice versa. The model trained on the augmented HRF training set achieves an accuracy of 95.04% when tested on the DRIVE dataset. Similarly, the model trained on the augmented DRIVE training set achieves an accuracy of 92.17% when tested on the HRF dataset. A progressive web application is also developed as part of this work, since there is no specific easy-to-use interface to perform segmentation of retinal fundus mentioned in the literature, to the best of our knowledge. This application accepts retinal fundus image as input and performs segmentation using trained U-Net model, to provide an output image of the blood vessels which will assist the ophthalmologists in screening retinopathy.<h2>Keywords</h2>U-Net&nbsp;Deep learning&nbsp;Semantic segmentation&nbsp;Retinal image segmentation&nbsp;Blood vessel patterns&nbsp;Machine learning&nbsp;