Raj Kamal

Dr. Raj Kamal

teaches in the Department of Electronics and Communication Engineering, Computer Science and Engineering at the Prestige Institute of Management and Research. He recevied his PhD. from the Indian Institute of Technology, Delhi. His areas of research include (i) Industrial Applications of Internet of Things and Edge Computing , (ii) applications of Machine learning models in Soybean and other crops, (iii) Big Data Analytics and (iv) Adaptive Fault Diagnosis Algorithm for Controller Area Network (AFDCAN). He is presently guiding research students on topics: CNN Based Machine-Vision (MV) of the Machine Objects, Assembly-Functions and Operations for optimizing the production, machine parts inspection for defects, and Data Analytics and Visualisation of Data Streams”

"

Prestige Institute of Management and Research

Email: dr_rajkamal@hotmail.com

DVP term expires December 2023

Presentations

Emerging Applications in Industry4.0 and Automotive IoT

Emerging areas of IoT applications are many, for example, automotive, logistics, smart homes, smart cities, manufacturing, oil exploration and mining.

Explain the followings:

1. Connected automobiles need edge computing. Emerging areas are advanced driving assistants using cloud based analytics of video streams.

2. Smart homes

3. Smart cities

4. Manufacturing needs efficient analytics near the machines. Machines can embed intelligence by machine learning

Predictive maintenance of equipment and assembly lines is done using computing at the edges itself.

5. Oil and gas extraction need efficient analytics and work in adverse environments for networking to centralized cloud.

6. Mining needs efficient computations in adverse environmental conditions and network to centralized cloud may not be available at all

AI in Industrial IoT

Explain the following"

1. AI also means using feature engineering with output feature map (metrics).

2. The feature map metrics enabling the decision(s),

3. Identification of machine parts

4. Machine Vision Control and monitoring the assembly line operations

5. Computer Vision Application to Zero-Defect Manufacturing

Exploratory and Predictive Analytics of user preferences using example of from Kaggle LEGO toys datasets example using Spark ML

Apache Spark is an open-source distributed processing framework. The paper presents an architecture for exploring and predicting user’s preferences using Apache Spark. The architecture is evaluated on LEGO toys datasets using the Spark Machine Learning (ML) algorithms. The datasets analyzed consist of LEGO parts, categories, themes and color features. Spark ML algorithms are applied as (i) k-means analysis of clusters to identify commonalities of LEGO themes and colors, (ii) classifications using the Support Vector Machine (SVM), Naïve Bayes (NB) and Random Forest (RF) for theme preference identification, and (iii) linear, decision tree, RF, and Gradient Boost for regression analysis to identify color shift in user preferences. The paper elucidates the steps for analytics based on Spark. The results for exploratory and predictive analytics are presented. The evaluation metrics shows that the ensemble regression prediction is better when compared to other algorithms. The analytics give the interesting results. For example, LEGO company’s products have become more colourful (children preferences exhibiting colours spectral shift and width), diversified and multifaceted over-the-time. The architecture helps in discovering future directions for the new designs in future LEGO products. The proposed architecture can be successfully employed in the related domain to predict product and user’s preferences.