Develop Visual Inspection (Object Detection) model to filter out faulty medical parts on conveyor line.This reduces the manual inspection cost across 10 plants for 30+ defects, using vision techniques like Yolo V3, Fast R-CNN andDetectron2.Research paper exploration to create an optimal DL model.Developed object detection model and deep learning (CNN, R-CNN, FR-CNN, YOLO)Tuned the model to optimal performance.Used depth wise separable convolution and e cient net technique to reduce the model parameter without a ecting performance.Performed post optimization of the model by fusing its convolution, batch norm and activation layer together.Dashboard for the live monitoring along production lines to improve SPM rate and worker efficiency reducing operational costTensor ow, python and Flask was used in development phase, Docker was used in deployment phase.

Studied and experimented on various DL model to create an optimal DL model for improving the diagnostics capabilities via medicalimages.Increase the sharpness of edge, and increate the signal to noise ratio of the image.Developed an efficient light weight model with less hyperparameter in TensorFlow JS and python as good efficiency was achieveddue to depth wise separable convolutionThe Deep learning algorithm was developed to work in coordination with the image reconstruction loop of OSEM (Ordered subsetexpectation Maximization)TensorFlow JS and python was used in development phase. The model was deployed at AWS cloud platform as was served usingrestful API.

Developed CNN based deep learning model for emotion classification on video data.The model was tuned and optimized to improve the inference quality and reduce the time taken by the model.Data preprocessing – resize, color conversion, denoising, image enhancement, data augmentation using TensorFlow and python.AWS transcribe service is used for the audio sentiment classifications.TensorFlow, Tensorflow extended, and python was used in development phase and AWS cloud was used to deploy the model.

Helped in model selection and tuning.YOLO algorithm was used for the localization of the license plate on the image.OCR was developed separately to read the character present in the license plate.Radar was used to get the distance and velocity of the vehicle.An automated warning was generated if a vehicle crossed the red light.TensorFlow sequential and functional API was used in development phase.

YOLO was used to detect and localize the road sings.K-means was used to create the anchor box.The cropped image was sent to dashboard system.TensorFlow was used in development phase.

Lateral Dynamic Support (LDS) system was developed to support the driver while steering.Lane Departure Warning (LDW) system was developed to warn the driver if ego vehicle departs from ego lane.Lane Keeping system (LKS) was developed to keep the vehicle in the middle of the lane when activated.OSEK (Open Systems and their Interfaces for the Electronics in Motor Vehicles) is a real-time OS for motor vehicle and was used as abackbone.The DAS is capable for self-diagnostic and provides a Diagnostic protocol for other connected Electronic Control Unit.All the ECU were connected using Controlled Area Network (CAN) and are capable to log the fault and warn the driver for the faultycondition.

Developed a solution to abstract all necessary aspects of ML lifecycle including Feature Engineering, Model training / tuning andinterpretation to allow end-users with comprehensive solution for building ML modelsImplemented Bag of words, TFIDF, WORD2VEC, BERT, RNN and LSTM for converting text to word vectors.Used advanced NLP techniques spacy for POS tagging and parsing.

Build predictive data science solutions using regression technique to predict numbers of alertsThis application is used by the higher management to avoid the outages.Ensemble of Linear & Random Forest ML models to predict 500+ alerts for all application across the firm.Building Reusable Data Assets on python by integrating advanced/intelligent data quality checks and automating exploratory dataanalysis approaches.Worked on problem scoping, data gathering, EDA, modelling, insights, visualizations, monitoring and maintenance.

Responsible for maintaining the high availability of the database by implementing log-shipping and database mirroring and backupjobs in SSMS.Responsible for backup and restore as a part of disaster recovery processInvolved in performance tuning and query tunning.Developed jobs for schedule data transfer. Automate database backup and restore mechanism.Developed data pipeline using Python, SQOOP and hive.Responsible for creation and maintenance of data pipeline and work on data remediation.

◦ Develop Visual Inspection (Object Detection) model to filter out faulty medical parts on conveyor line.
◦ This reduces the manual inspection cost across 10 plants for 30+ defects, using vision techniques like Yolo V3, Fast R-CNN and
Detectron2.
Research paper exploration to create an optimal DL model.
Developed object detection model and deep learning (CNN, R-CNN, FR-CNN, YOLO)
Tuned the model to optimal performance.
Used depth wise separable convolution and efficient net technique to reduce the model parameter without affecting performance.
Performed post optimization of the model by fusing its convolution, batch norm and activation layer together.
Dashboard for the live monitoring along production lines to improve SPM rate and worker efficiency reducing operational cost
Tensorflow, python and Flask was used in development phase, Docker was used in deployment phase.

Studied and experimented on various DL model to create an optimal DL model for improving the diagnostics capabilities via medical
images.
◦ Increase the sharpness of edge, and increate the signal to noise ratio of the image.
◦ Developed an efficient light weight model with less hyperparameter in TensorFlow JS and python as good efficiency was achieved
due to depth wise separable convolution
◦ The Deep learning algorithm was developed to work in coordination with the image reconstruction loop of OSEM (Ordered subset
expectation Maximization)
◦ TensorFlow JS

Developed CNN based deep learning model for emotion classification on video data.
◦ The model was tuned and optimized to improve the inference quality and reduce the time taken by the model.
◦ Data preprocessing – resize, color conversion, denoising, image enhancement, data augmentation using TensorFlow and python.
◦ AWS transcribe service is used for the audio sentiment classifications.
◦ TensorFlow, Tensorflow extended, and python was used in development phase and AWS cloud was used to deploy the model.

◦ Helped in model selection and tuning.
◦ YOLO algorithm was used for the localization of the license plate on the image.
◦ OCR was developed separately to read the character present in the license plate.
◦ Radar was used to get the distance and velocity of the vehicle.
◦ An automated warning was generated if a vehicle crossed the red light.
◦ TensorFlow sequential and functional API was used in development phase.