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

School of Computer Engineering & Technology

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.

World University root node

Engineering and Technology

School of Mechanical Engineering

International Conference on Emerging Trends in Engineering and Technology, ICETET

Enhancement in Dentistry using Machine Learning: A Systematic Review

Autism Spectrum Disorder (ASD) is a neurological condition that can affect a person's language development, speech, cognition, and social skills for the rest of their lives. Prevalence of ASD is about 1 in 100 children in India under the age of 10, and nearly 1 in 8 has at least one neurodevelopmental condition according to the 2011 Census [24]. Machine/Deep Learning methods have proven helpful in order to quickly and accurately determine the risk of ASD. Early intervention in the child's preschool and primary school years can aid in the development of important social, communicative, functional, and behavioral skills. It has been observed that very few studies and research has been done on ASD in India, which is our motivation to take this as our project. The very sparse number of current studies show that there is no existing dataset for children in India. In this paper, we intend to first understand what autism spectrum disorder is, the symptoms it presents itself in, currently available diagnosis tests, treatment options and how AI is relevant in this domain. Further, the idea would be to understand the extent of ASD study and research done in India. We have pioneered ASD Research in India as we formulated a dataset of Indian children to kickstart ASD research in India. Out of the three approaches we tried, the CNN-RNN Video Classification approach where the CNN block has a pretrained feature extractor (Inception V3) to classify whether a child has ASD or not performed with 98.48 % train and 90.48 % test accuracy. We have further explained the wide future scope this research inquiry has to offer. Our research intends to help establish the need for a population-specific study in the detection and diagnosis of ASD in Indian children. © 2022 IEEE.

2022 IEEE 3rd Global Conference for Advancement in Technology, GCAT 2022

AutiScan: Screening of Autism Spectrum Disorder Specific to Indian Region

One of the major platforms today to express your emotions, expressions, feelings, and views about something or about any product is social media. People put forth what they feel, therefore their individual posts can be judged as a reflection of their personality, but how to judge a personality of a person based on social media posts and that too of say large data, say thousands, and produce analysis on it. In our studies, we specialize in using deep learning to build a classifier that can classify individuals according to their Myers-Briggs Type Index (MBTI) solely using textual content samples from their social media posts as an input. There are two reasons for developing such a classifier. First, due to the fact social media is so ubiquitous, one of these classifiers might have lots of statistics to degree character, permitting extra human beings to realize their MBTI character type, possibly extra reliably and faster. Our second incentive is the opportunity that our classifier can be more correct than the cutting-edge assessments, as evidenced with the aid of using the low retest mistakes price for character assessments executed with the aid of using expert psychologists. It may be possible to use our classification method to verify the accuracy of these first assessments, to give individuals more confidence in their results. In some cases, a text classification may be more comprehensive than a single personality assessment. © 2022 Totem Publisher, Inc.

International Journal of Performability Engineering

Personality Prediction through Social Media Posts

COVID-19 emerged in November 2019 in the Wuhan city of China. Since then, it has expanded exponentially and reached every corner of the world. To date, it has infected more than three hundred eighty-five million people and caused more than five million seven hundred deaths. Traditional COVID-19 diagnostic tests lack sensitivity and result in false-negative reports several times. Using X-Rays and CT scans to detect covid-19 can aid the diagnosis process when powered by deep learning techniques. Using deep learning will provide accurate results in a fast and automatic manner. The proposed research work has performed a total of twenty-eight experiments. This research work has experimented with seven different Deep Learning models including, DenseNet201, MobileNetV2, DenseNet121, VGG16, VGG19, InceptionV3, and ResNet50. The performance of each model is tested based on the distinct image enhancement techniques. The four different experiments include raw data, data preprocessed with gamma correction for two different gamma values (0.7 and 1.2), and Contrast Limited Adaptive Histogram Equalization (CLAHE). Gamma Correction with gamma value 1.2 performed the best. Lastly, this research work has created an ensemble of three best-performing algorithms including, DenseNet201, MobileNetV2, DenseNet121, and achieved an accuracy, precision, recall, f1 score, and AUC of 98.34%, 98.61%, 98.78%, 98.2%, and 99.8%, respectively. © 2022 IEEE.

Proceedings - International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2022

Automatic COVID-19 Detection from Chest X-Rays using Deep Learning Techniques

Lecture Notes in Electrical Engineering

University Recommendation System for Higher Studies in USA

Analytical Study of Content-Based and Collaborative Filtering Methods for Recommender Systems

Image Analysis using systems like Content based Image Retrieval is the information retrieval system which helps in retrieving similar images, found very useful in many areas. Feature vectors are the compact and precise representation of Images which effectively needs to be used in Image Retrieval System. The performance of Image Retrieval is majorly dependent on the quality of feature vectors. Many intelligent algorithms are proposed in literature to retrieve the features of images and represent it in an optimal way. Feature Vectors with reduced dimensions are always preferred for image retrieval systems. Quality of Feature Vectors is always checked using the output of image retrieval. There has always been a trade-off between the size of the feature vector and retrieval performance. Common measures used for checking retrieval system performance are precision, recall. This paper discusses the important measure: “discrimination power” of Image feature vector to check feature vector quality in context of image matching and retrieval. The discrimination power of Image Feature Vector, and its use-case with our feature extraction method is discussed here. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

On Discrimination Power of Image Feature Vector

We mean to use the new headway in innovation to foster dietary as evaluation arrangements which is a more advantageous way to deal with screen every day food admission and control dietary patterns. Food, calorie and sustenance estimation framework is extremely useful for people groups to gauge and deal with their every day food admission. AI will make proposals dependent on the things that are of client's advantage or loved by them before. Additionally these calculations are utilized to suggest the food that the client might like. The suggested food and food in standard plans set by client's own circumstance are in a similar group, which meets the client's healthful equilibrium. We feature the issue of determination of legitimate eating regimen that should satisfy everybody's nourishing prerequisites. © Grenze Scientific Society, 2022.

13th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2022

Diet Recommendation by Machine Learning

Background: Decision makers use the process of determining the best course of action by processing, analysing & interpreting the data to gain insights, known as Business Intelligence. Some decision support systems use sales figures to predict future expansion, but few consider the effect of customer data. Objectives: The main objective of this study is to build a model that will give a forecast based on fine-tuned sales numbers using some customer-centric features. Methods/Approach: We first use the RFM model to segment the customers into distinct segments based on customer buying characteristics and then discard the segments that are irrelevant to the business. Then we use the ARIMA model to do the sales forecasting for the remainder of the data. Results: Using this model, we were able to achieve a better fitment of the data for the prediction model and achieved a better accuracy when used after RFM analysis. Conclusions: We tried to merge two different concepts to do a cross-functional analysis for better decision-making. We were able to present the RFM-ARIMA model as a better metric or approach to fine-tune the sales analysis. © 2022 Sanket Tanaji Londhe et al.

Business Systems Research

Customer-Centric Sales Forecasting Model: RFM-ARIMA Approach

Student Centric Learning experiences is always a challenge and important aspect of teaching pedagogy. It became more complex and challenging in current scenario of online teaching and learning. Amongst many innovative active learning methods, PBL: Pr oblem based learning is majorly used in Engineering Education. Problem based learning, if worked as a group activity, each team member must actively contribute to ensure the learning objective which is a big problem. “Check Solve Pass” technique is a unique method proposed in this paper with the aim of motivating active contribution of each team member in Collaborative PBL. With the experimentation of this method, significant improvement in active participation of each group member is observed. © 2022, Rajarambapu Institute Of Technology. All rights reserved.