Sankeerthana Satini

Data Science | Machine Learning | Computer Vision | NLP | Data Analysis and Visualization

Sankeerthana Satini

Hello There! I'm currently a Freelance ML Engineer passionate about solving pressing problems by applying ML and Computer Vision to real-world use cases.

My work spans a wide range of end-to-end projects in different domains, ranging from Object Detection and ML to Data Analytics as well.

Please feel free to reach out regarding ideas for collaborations or for Data Science, Analytics, ML and Computer Vision freelancing tasks!

You can download my resume over here:

Skills and Certifications

Programming Languages

Python | MATLAB

Data Science & ML

Data Mining | Predictive Analytics | Unsupervised Learning | CI/CD

Computer Vision

Video & Image Processing | 2D & 3D Object Detection | Segmentation

Data Analytics & Visualization

Insight Generation | Google Looker Studio | Tableau | Microsoft Power BI

NLP

Sentiment Analysis | OpenAI APIs | ChatGPT Models

Cloud Platforms

Amazon Web Services

Work and Publications

Singapore Management University (SMU)

Research Engineer

Dec 2023 - Jan 2024
  • Developed data-loading, processing and modelling pipelines for a vision-based throat cancer diagnosis system by engineering robust object detection models.
  • Developed novel approaches for video classification to ensure robustness in processing large-scale, real-world medical image data.
  • Carecam

    Machine Learning Engineer

    Aug 2023 - Oct 2023
  • Worked on a vision-based Software as a Medical Device (SaaMD) product that aids clinicians in their diagnosis of the patient’s gait.
  • Solved critical bottlenecks by integrating LIDAR data.
  • Optimized the pipeline involving tasks like scaling, smoothing, normalization and data manipulation.
  • Led the migration of training and deployment codes to AWS to build a cloud solution.
  • Asurion

    Computer Vision Intern

    Aug 2022 - Nov 2022
  • Worked on developing an AI assisted Mobile Phone Insurance Product that detects cracks and damage intensity done to a phone using YOLOv5.
  • Optimised the processing and modelling pipeline.
  • Conceptualised an automated Continuous ML Feedback Loop as part of the CI/CD process using AWS Service.
  • Researched and Implemented 3D Object Detection Models using Point Clouds.
  • A*STAR - Institute for Infocomm Research

    Data Scientist Intern

    May 2021 - Dec 2021
  • Worked on a vision-based 2D object detection system for Autonomous Service Robots in Hospitals, through a Semi-Supervised Learning Approach.
  • Oversaw the training and optimization for SSD-MobileNetv2, STAC, and Unbiased Mean Teacher Model to assess Semi-Supervised and Incremental Learning efficacy.

  • Publications

  • International Conference on Social Robotics (ICSR) 2021
  • Pahwa, R. S., Chang, R., Jie, W., Satini, S., Viswanathan, C., Yiming, D., Jain, V., Pang, C. T., & Wah, W. K. (1970, January 1). A survey on object detection performance with different data distributions. https://link.springer.com/chapter/10.1007/978-3-030-90525-5_48"

  • Conference on Learning Factories (CLF) 2022
  • Chang, R., Pahwa, R. S., Wang, J., Chen, L.,Satini, S.,Wan, K. W., & Hsu, D. (2022, April 7). Creating semi-supervised learning-based Adaptable Object Detection Models for Autonomous Service Robot. SSRN. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4075994

    Learnseeker

    Data Analytics Intern

    July 2020 - Nov 2020
  • Worked on designing, developing and automating Dashboards for Tuition Centers to enable them to provide a personalised AI_assisted learning assisted for their students.
  • Projects

    Object Detection - Robot Vision

    Trained the robot to detect images to navigate an obstacle course. Project spanned from Image Collection to Deployment of YOLOv5 into a Raspberry Pi.

    Final Year Project - Pedestrian Detection

    Developed Novel Modifications to existing data augmentations to increase the YOLOX accuracy while solving the problem of Intra-class Occlusion.

    Emotion Recognition using AI and EEG Signals

    Developed ResNets to detect emotions from synchrosqueeze-transformed EEG Signals.

    Sentiment Analysis of Skincare Reviews

    Carried out Sentiment analysis using RNNs to detect whether the reviews were positive or negative.

    Mask Detection - YOLOv4 (DarkNet)

    Trained and Optimized YOLOv4 Model to detect whether a person was wearing a mask or not.

    Product Analysis Dashboard

    Developed a dashboard using Google Looker Studio to analyse the top 10 products based on their popularity.

    Final Year Project - Pedestrian Detection

    Github Link: https://github.com/sankeerthana14/fyp-pedestrian-detection.git


    Project Description

    This project was my Final Year Project (FYP) where I got the chance to design and execute a research project from scratch. The scope was Pedestrian Detection and the deliverables of this project are a Research Report and a Research Poster published in NTU's collections.


    After conducting a comprehensive Literature Review where I critically analysed the current state-of-the computer vision models as well as approaches that were being implemented in the field of Pedestrian Detection so far, Pedestrian Occlusion specifically intra-class pedestrian occlusion was a pressing problem.


    Key Research Takeways

    In order to mitigate the effects of Intra-class Pedestrian Occlusion, I came up with a novel modification to an existing augmentation technique - 'Cutout'. Cutout applies black square patches on the image to mimic an occlusion This allows the model to learn how to handle occluded cases in real-life scenarios. However, this doesn't mitigate the effects of Intra-class Occlusion.


    Hence, I modified the augmentation to overlay black square patches using an IoU threshold strategy such that the model learns to focus on the non-occluded part of the pedestrian to effectively mitigate the effects of Intra-class Occlusion.


    With this new augmentation, there was a whopping 13% increase in detection accuracy of the YOLOX model that was trained on the Penn-Fudan Pedestrian Detection Dataset.



    Research Poster detailing the key points.




    Emotion Recognition using AI and EEG Signals

    Github Link: https://github.com/sankeerthana14/EmoRecTFR.git


    Project Description

    This project was done as a part of NTU's Undergraduate Research Experience on Campus (URECA) Programme. This Programme was for open for selected students to pursue research at an undergraduate level.


    The Problem to solve was to create a Deep Learning Model that would recognise Emotions from EEG Signals. The model chosen was ResNet50 and the raw EEG Signals were processed. The processing steps included signal processing steps such as filtering and normalization. Synchrosqueeze Transform was applied to the EEG Signals and images of the transformed EEG frequency graphs were collated and arranged into a dataset.


    The ResNet50 model was then trained on this dataset, and hyperparameter tuning was done to find the best results. Please feel free to take a look at the codes via the Github Link above.


    Sentiment Analysis of Skincare Reviews

    Github Link: https://github.com/sankeerthana14/IR-Sentiment-Analysis.git


    Project Description

    In this Project, given crawled dataset compiled from web scraping of e-commerce websites. I explored various tools/packages to generate labels such as 'Flair', 'Spacy' and 'Vader' and compared their performance and accuracy of the generated labels.


    After necessary data processing steps including Tokenization and SMOTE to tackle the problem of imbalanced classes in the dataset, I created a Simple RNN architecture and a CNN architecture from scratch to classify the reviews into Positive or Negative. Hyperparameter tuning was also done to get the best results for both the models.


    Example of a review detection by RNN.


    "I have combination sensitive skin, even Cera Ve daily moisturizer causes irritation. This cream is the best I’ve ever felt AND reduces redness. Will definitely be restocking once my first order goes empty!"


    Actual Class: Positive

    RNN Detected Class: Positive


    Please feel free to take a look at the codes in the Github Link above.


    Mask Detection Using YOLOv4 DarkNet Framework

    Github Link: https://github.com/sankeerthana14/Mask-Detection.git


    Project Description

    Prior to this Project, I had implemented Object Detection Models using Tensorflow and PyTorch. However, in a bid to try something new, through this personal project, I explored training and evaluating a YOLOv4 model with the DarkNet framework using Linux Commands. The YOLOv4 model was trained on the Roboflow Mask Detection dataset and evaluated on the same.


    Detections made by the YOLOv4.



    Please feel free to take a look at the codes in the Github Link above.


    Product Analysis Dashboard

    Github Link: https://github.com/sankeerthana14/recommendation-system-viz.git


    Project Description

    This was essentially an end-to-end project spanning from Data processing to Dashboard Visualization.


    In this project, I implemented a Popularity Based Recommendation System that returns the top 10 products based on the number of reviews each product has gotten. This is a brute force approach and hence to make it more robust. I have implemented certain steps such as calculating the average rating received and factoring it in when it comes to recommending the top products.


    I have then visualized the results in the form of a dashboard as dashboard allows us to extract more insights about each product, as well as all the products as a whole. The dashboard has been creted using Google Looker Studio.



    Testimonials

    Contact

    Feel free to reach out to me :)