×
0 followers0 following
Isaac Ritharson P
Washington, United States
An aspiring AI developer and Research Scientist0 followers0 following
- About
- High School
- Bachelor's
- Target
- TOEFL
- GRE
Male
Washington, United States
Work ExperienceResearch Assistant (RA) at Karunya Water Institute - WI (R & D)
Karunya Institute of Technology and Sciences - Part Time
Jan 1, 2023 - Present · 3 yrs 3 mos
Tamil Nadu, India
Supervisor : Dr. J. Brema, Civil Dept.
+Responsibilities: Exploratory Data Analysis, Climate Modelling (Precipitation, Relative Humidity (R2HM, Windspeed, SST), Time Series Modelling, Model Training and Interpretation (Auto-arima, LSTM and Regressors).
+Conducted a study to demonstrate Precipitation patterns in the Alappuzha region, Kerala, using MERRA-2 data collected from "NASA POWER Project" under Karunya Water Institute.
Python Programming Essentials Trainee
Cisco - Internship
Dec 1, 2021 - May 1, 2022 · 5 mos
Tamil Nadu, India
Position Held/Title: Python Developer
+Gained excessive training in Python fundamentals; Control statements, Loops, Functions, Recursion, Dictionaries, and Web Development. Solved 100+ problem statements through the Snackify portal.
+Course completion: OpenEDG and PCAP Essentials.
+As a Final Project : Developed a python program to check if the input address is IPv4 or IPv6 based on pre-defined conditions.
Customer and Business Analyst
Nellai Agencies - Freelance
May 1, 2022 - Jun 1, 2022 · 1 mo
Tamil Nadu, India
Position Held/Title: Customer and Business Analyst, Theni
+Deployed a Machine Learning Web-Application using Streamlit for Nellai Agency, a retailing company to help identify optimal products and the most prominent customers along with the estimated sales of individual products over time.
+Implementation made using LSTM algorithm achieved an accuracy of 86.37%.
Applied Deep Learning Academic Intern Winter 2022-23
NUS Computing - Part Time
Dec 1, 2022 - Jan 1, 2023 · 1 mo
Singapore, Singapore
Data Analytics using Deep Learning Winter 2022
Assessed Grade: A+
Tech Innovation, Artificial Intelligence Content Writer
Medium - Part Time
Mar 1, 2022 - May 1, 2023 · 1 yr 2 mos
Tamil Nadu, India
+With passion for technology and to create a positive impact on society. I post blogs on emerging trends in artificial intelligence and their applications in various domains.
+To develop my skills and address innovative solutions that can solve real-world problems and improve people’s lives, I focus on assistive hardware technology, synergy of artificial intelligence (AI) and
cutting-edge tools like the new era in the realm of vaccine development and other medical applications.
+Writes about emerging topics like Cyborgs and Cybernetics, Intersection of artificial intelligence (AI) and emotional intelligence, enabling machines to recognize, interpret, and respond to human emotions and many more.
ML in Business and Healthcare Trainee
Yantra Byte Foundation: New Delhi, IN - Part Time
Aug 1, 2022 - Nov 1, 2022 · 3 mos
Delhi, India
AI and ML wirth Application in field of Business and Healthcare
field : Healthcare Analytics
+Derived the significance of Age in Exercise-Induced Angina benefiting in early identification of anginal pain.
+Trained ML algorithms to categorize normal, ST-T wave abnormality and ventricular Hypertrophy to, improving diagnosis by 10%.
Summer Undergraduate Research Fellowship (SURF)
National University of Singapore - Internship
Jan 1, 2022 - Apr 1, 2023 · 1 yr 3 mos
Singapore, Singapore
Guide: Dr. Tan Wee Kek
+Studied the Residual Neural Architecture (ResNets) for facial reconstruction.
+Understood the pre-built GAN Model and re-trained it to support facial reconstruction behind masked-face images with an improved structural score of 75.5%.
ProjectsWeb Development Basics SaaS-SaaP Repository
Role - Student
for Academic
Mar 3, 2021 - May 4, 2023
Working with Angular JS, Working with Node, Angular JS Form, Design a Website using HTML 5 form elements and media elements, JavaScript Timer Functions and Object, JavaScript–DOM Elements and Events, Responsive Website Design using Bootstrap, Webpage Design using HTML5 and Advanced CSS3
Working with jQuery.
Visualization Basics to Advanced Complete Repository
Role - Contributor
for Academic
Apr 1, 2023 - May 1, 2023
Plotting Methods Present in the Matplotlib Library, 2D Plots, 3D Plot, D3 Data-Driven Documents, Drawing Circle, Plotting Networks and Plots using D3.js, Synchronization of Animation and Audio, Visualizing GIS using D3.js, Visualizing one, two, and multi-dimensional data, Working with Colors
Tutorial: Tindog-site using Advanced CSS and Bootstrap
Role - Student
for Personal
May 1, 2022 - Jun 1, 2022
Developed a Fun Dating Website for dogs through which they can find their dream partners.
Frameworks used: HTML, Advanced CSS and Bootstrap
Statistical Analyisis and Data Science Repository (Complete learning)
Role - Student
for Academic
Apr 1, 2020 - May 1, 2022
Basic Tutorials for
+Exploratory Data Analysis (EDA), Python Programming for Data Science, KNN Classifier, Performance metrics: MAE, MSE, and R Squared Value, Statistical Inference: Hypothesis Testing with Z-test, Working with Data Using Pandas, Decision Trees (DT), K-means Clustering, Recommendation Systems.
iRobot-Building a Concept Site
Role - Student
for Personal
May 1, 2022 - Jul 1, 2022
Built a concept commercial site for selling futuristic robots using bootstrap, CSS, and HTML5 #web-project.
Building a Personal Site using HTML and CSS (Cascading Style Sheets)
Role - Student
for Academic
Jan 1, 2023 - Apr 1, 2023
Building a basic personal site using HTML5 and CSS
Building a Personal CV Site only using HTML
Role - Student
for Academic
Jan 1, 2020 - May 1, 2020
Building a Personal site for CV/resume using HTML5 to display the profile in a web page
ANN 101: Deep Learning Repository (Complete learning)
Role - Contributor
for Personal
Jun 1, 2023 - Jul 1, 2023
Basic Tutorials for
+Convolutional Neural Networks (CNN), Generative Adversarial Network (GAN), Long Short-Term Memory (LSTM), Linear Regression, Logistic Regression, Multi-Layer Perceptron (MLP) with Optimisation, Support Vector Machines (SVM), Single Layer Perceptron (SLP)
Motion, Hand Tracking and Color Identification algorithms using cv2
Role - Student
for Personal
Jan 15, 2020 - Dec 1, 2020
+Simple-Face-Detection-with-sample-image-using-Computer-Vision
+Motion-Detection-Using-cv2-Library-in-Python
+MaskDetector-Real-Time-Face-Mask-Detection-with-Keras-and-OpenCV
+Dress-Colour-IDENTIFICATION-using-Computer-Vision-Python
+Hand Tracking and Moving virtual objects using cv2
Implemented through Hand Tracking Module from Cvzone to track hand movements including moving virtual objects from one place to another. Using computer vision along with Colour Detection Algorithms to detect the color of an object using cv2 and python
Deploying an End-to-End Machine Learning Web Application using Streamlit
Role - Student
for Academic
May 1, 2023 - Jun 1, 2023
Time Series Analysis and Forecasting using univariate LSTM Algorithm. Made for Nellai Agencies ,Monthly sales analysis
QF - MDS Tool using a Massively Trained Multi-lingual Transformer Model (mT5)
Role - Student
for Academic
Jun 1, 2023 - Aug 1, 2023
+Combined NLP Techniques, web scraping, and transformer models to derive abstract summaries.
+Built an MDS tool using Flask, selenium, and lightweight mt5-small model improving response & retrieval.
Face-Detection and Recognition of Students with Student Database
Role - Student
for Academic
Jan 1, 2022 - Feb 1, 2022
Face Detection and Recognition using FaceCascadeClassifier and cv2 Libraries
Implementation of oneAPI Deep Neural Networks (oneDNN) for Assistive Navigation
Role - Student
for Personal
May 10, 2023 - Jul 10, 2023
+Designed a 3D Haptic glass to assist hard-to see individuals during road crossing.
+Deployed models in Jetson Nano, Servo Motor for haptic feedback.
+Realistic scenarios like Pedestrian and Lane Detection were implemented with low latency. Intel Equipathon Winning Project.
Environmental Modelling and Analysis: Precipitation Patterns in Alappuzha -Kerala
Role - Student
for Academic
Jun 1, 2023 - Nov 1, 2023
+ Conducted research to demonstrate Precipitation patterns in the Alaphzha region, Kerala, using MERRA-2 data
as part of the “NASA POWER Project”, in Karunya Water Institute under Dr. J. Brema, Civil Dept.
PLAYGROUND FPS Shooter made using Unity3D Engine
Role - Student
for Academic
Jan 1, 2022 - Oct 1, 2022
+A FPS Shooter game made using Unity Game Engine, worked on 3D modelling (Blender3D), Lighting Properties, Textures, Game Flows, Levels, Physics and Animations (using C#) #AiforGames
Novel Deep learning-based CNN architecture for Rice Leaf Disease Detection
Role - Student
for Academic
Jan 1, 2022 - Jan 1, 2023
Image Blending using Generative Adversarial Networks
Role - Summer Undergraduate Research Fellowship
for Academic
Jan 1, 2023 - Apr 1, 2023
Ensemble Deep Learning for Accurate Waste Classification: VGG16 vs MobileNetV2 vs CNN
Role - Applied Deep Learning Academic Intern Winter 2022-23
for Academic
Dec 1, 2022 - Jan 1, 2023
+The project aimed at finishing garbage classification using a deep learning model and comparing the classification performance of VGG16 and CNN based on a publicly accessible image dataset.
Research PapersDeepRice: A Deep Learning and Deep Feature based Classification of Rice Leaf Disease Subtypes
Oct 17, 2023 - Artificial Intelligence in Agriculture
Rice stands as a crucial staple food globally, with its enduring sustainability hinging on the prompt detection of rice leaf diseases. However, safeguarding paddy crops against diseases holds paramount importance for elevated crop quality and yields. In the recent past, the identification of leaf pathologies in crops predominantly relies on manual methods using specialized equipment, which proves to be time consuming and inefficient. This study offers a remedy by harnessing Deep Learning (DL) and transfer learning techniques to accurately identify and classify rice leaf diseases. A comprehensive dataset comprising 5932 self-generated images of rice leaves was assembled along with the benchmark datasets, categorized into 9 classes irrespective of the extent of disease spread across the leaves. These classes encompass diverse states including healthy leaves, mild and severe blight, mild and severe tungro, mild and severe blast, as well as mild and severe brown spot. Following meticulous manual labelling and dataset segmentation, which was validated by agricultural experts, data augmentation strategies were implemented to amplify the number of images. The datasets were subjected to evaluation using the proposed tailored Convolutional Neural Networks. Their performance was scrutinized in conjunction with alternative transfer learning approaches like VGG16, Xception, ResNet50, DenseNet121, Inception Resnet V2, and Inception V3. The effectiveness of the proposed CNN model was gauged by its capacity to generalize to unseen images, yielding an exceptional accuracy of 99.94%, surpassing the benchmarks set by existing state-of-the-art models. Further, the layer wise feature extraction is also visualized as the interpretable AI.
Early Detection of Neurological Disorders: A Deep Learning Approach utilizing T1, T2, T1C+ MRI Scans
Mar 22, 2024 - American Institute of Physics (AIP) Proceedings
Neurological disorders are conditions that affect the central nervous system. These problems have skyrocketed in different parts of the world post-COVID era. In response to the observed decline in cognitive function, escalating neurological disorders, and an upsurge in depressive states among young adults contributing to diminished academic and physical performance, a comprehensive investigation was undertaken. The focus of this investigation was on a specific demographic, namely the student population of Karunya University representing diverse academic disciplines. The objective was to identify pivotal factors contributing to compromised mental well-being in the academic setting, drawing upon the framework established by the Young Minds Matter Institute in Australia. To augment identification precision via an exploration of neural plasticity, we employed deep-transfer CNN models. These models were proficient at processing Magnetic Resonance Images (MRI) to accurately delineate and classify various neurological conditions. Furthermore, a meticulous comparative analysis was conducted to evaluate the efficacy of leading algorithms with CNN models. The study also includes an exhaustive review of associated conditions and their precautionary measures including standard deviation (σ), range (low-high), and thresholds, thresholds providing a comprehensive understanding of multifaceted conditions. The experimental results show that the VGG-16 and Xception models excelled in classifying lower-order disorders (MRI), with VGG-16 holding superior for high-contrast resolution MRIs.
Study On Mental Health and Obesity among Children Based on Daily Activities and Effects using Machine Learning
Sep 22, 2023 - IEEE
Organisation: Karunya University
Conference: ICCPCT 2023
+This study investigated the correlation between daily activities and mental health in children aged 12 to 17. Focusing on those with mental health issues leading to stress, depression, and unhealthy eating habits, the study employs historical and statistical data, utilized the extra trees algorithm to determine feature importance.
+The findings categorized daily activities based on their impact, offering insights into major and minor contributors to conditions like obesity.
+The study aims to inform future research on the intricate relationship between daily activities, mental health, and obesity, ultimately contributing to the long-term well-being of children as they transition into adulthood.
Multi-Document Summarization Made Easy: An Abstractive Query-Focused System Using Web Scraping and Transformer Models
Aug 6, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. D. Sujitha Juliet.
Organisation: Karunya University
Conference: CONIT 2023
+The work proposed a web-based abstractive QF-MDS that simplified the process of summarizing multiple documents on any given topic. The system uses techniques, including web scraping, natural language processing, and transformer models, to automate the summarization process improving the ease of accessibility to information for users.
+The system was designed to take user input in the form of a query, the number of words to be summarized, and the number of documents to be referred to. It then utilizes Google search engine API integration to retrieve the most relevant webpages based on their ranking, and performs web scraping of tags using beautiful soup (bs4) and selenium frameworks.
+The scraped data undergoes pre-processing, including stop word removal, tokenization (using Auto tokenizer) , and visualizing frequency matrix and word-cloud plots (using seaborn and matplotlib). The transformer model ranks the words based on frequency and generates a summary of the text that is coherent, concise, and relevant to the user's query.
Modeling Precipitation Patterns in Alappuzha - Kerala: An Analysis of Regression and Time Series Approaches
Aug 7, 2022 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. J. Brema, Civil Engineering Dept.
Organisation: Karunya Water Institute (WI)
Conference: CONIT 2023
+The study brings out the relationship between meteorological parameters in Alappuzha, a district in Kerala, India. The analysis was made using the real-time data obtained from NASA's POWER project.
+The experiment considered T2M, RH2M, WS2M, SST and PETCORR parameter values and employed statistical analysis techniques, including correlation, regression, and time series Modeling, to examine
the direct relationship between variables and forecast future precipitation levels.
+Upon careful curation, visualizations provided us with better insights to identify trends within the data. A comprehensive comparison helped us identify the best model using mean squared (MSE) and r-squared (R2) values.
GAN-Based Facial Feature Reconstruction for Improved Masked Face Recognition during Covid
Sep 22, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisors: Dr. K. Vidya, Dr. Tan Wee Kek.
Organisation: Karunya University, NUS Singapore (extended study - Image Blending Using GANs)
Conference: ICCPCT 2023
+We proposed a GAN-based approach to learn the underlying relationships between masked and unmasked facial features and generate plausible reconstructions of the missing facial features.
+The suggested strategy produced high-quality and precise reconstructions of the missing facial features, and it can be used for face recognition tasks.
+The findings suggested that GAN-based face reconstruction has the potential to overcome the limitations posed by face masks, providing a solution that preserves individual privacy and security while ensuring accurate face recognition.
Feature Engineering and Machine Learning for Iot-based Applications: An Overview of Algorithms
Sep 22, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. K. Vidya.
Organisation: Karunya University
Conference: ICAISS 2023
+The paper extensively reviewed machine learning algorithms for feature estimation, highlighting its strengths, weaknesses, and suitable applications. It addressed challenges in feature interpretation for IoT
applications, proposing strategies like data preprocessing and model optimization to overcome issues such as data variability and resource constraints.
+A comparative analysis of algorithms based on accuracy, speed, and efficiency served as a practical guide for selecting the most appropriate algorithm for range-based prediction applications in IoT scenarios.
Chatbots Embracing Artificial Intelligence Solutions To Assist Institutions in Improving Student Interactions
Sep 22, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. Mythily M.
Organisation: Karunya University
Conference: ICCPCT 2023
+This study delved into the integration of Chatbot systems within the education sector, highlighting the constructive influence of Chatbot technology on students and institutional management through efficient service delivery. Employed Python frameworks such as Flask, HTML, CSS, and JavaScript for Front End Development.
+The research employed PyTorch, along with Natural Language Toolkit (NLTK) for to categorize user messages and NLP techniques including tokenization and stemming to allow Chatbots perform semantic, sentiment analysis, so to provide periodic outcomes from a diverse range of potential responses.
Prevention of School Shooting using Neural Networks and Computer Vision
Aug 18, 2022 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. M. Rajeshwari.
Organisation: Karunya University
Conference: ICICICT 2022
+The delay in response during voluntary gun shootout events has led to questioning the security in schools premises. To enhance security conditions, an automated system that utilizes DNNs to authenticate identity of students through facial recognition (HAAR Classifiers) was
proposed.
+YOLOv3 (Object detection algorithm) was integrated to identify harmful weapons, ensuring safety, along with Colour identification algorithms to distinguish anomalies.
+The captured images of suspects on the live feed were automatically directed to authorities for quick inspection ensuring a quicker passage for communication, utilized IOT devices (buzzers) to raise alerts in the nearby stations.
Design and Evaluation of a Brain Signal-based Monitoring System for Differently-Abled People
Mar 2, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
+We presented a method to help medical professionals correctly infer therapies by using the six emotions that patients express. The classes included: Turning on the fan, Leisure, Drained, Starving, Need to Use the Toilet, and Time to Take Prescription.
+Following the analysis of the baseline features, machine learning algorithms were trained, their effectiveness was assessed, and the result was then input into a planned program to notify the caretaker.
+The voting classifier was determined to be the best model, since it demonstrated the highest likelihood of correctly predicting the category.
A Web-based Real-time Sales Data Analysis using LSTM Model for Better Insight
Mar 17, 2023 - Institute of Electrical and Electronics Engineers (IEEE)
Supervisor: Dr. J. Anitha.
Organisation: Karunya University
Conference: ICACCS 2023
+A machine learning-based web application was deployed in real-time for the company Nellai Agencies, to analyse their monthly sales data. An LSTM model was trained with data to predict the sales for the next 'n' days.
+The performance of the model was evaluated with the metrics such as Mean Absolute Error (MAE) & R2Score. The results obtained were used to make insights by the company by visualizing predicted graphs.
+Concluded that, the impact of using a machine learning-based web application supported better decision-making, including the distribution of sales & production, finding the prominent customer, increasing the profitability of the company.
VolunteeringUniversity Rep ISP'30
at Internshala
Jan 1, 2022 - Present
Education
+Successfully guided students with Internshala student programs which contributed to the improvement in overall placement rates by connecting students with internships relevant to their field of study.
+Organized events enhancing awareness and engagement with Internshala initiatives on campus.
Covid-19 Relief FieldOps Cadet
at Global Digital Corps
Jan 1, 2022 - May 1, 2022
Health
+Position/Title: Covid-19 Relief FieldOps Cadet
(Active)
+Served a total 12 hrs during the COVID-19 pandemic, taking part of the GDC FieldOps Cadet Training Program, aided quick disaster response using CoronaSafe Network by improving coordination among local workers.
+Aided Distribution of items reaching 150+ households in need during the height of the pandemic.
+Spread awareness on the use of digital tools and technology for disaster preparedness, enhancing community resilience.
NSS Social Worker & Volunteer
at National Service Scheme
Jul 1, 2022 - Present
Social Services
+With more than 300 active members in NSS Karunya. We are working on organising weekly visits to the King’s Home (a chlidren's orphanage) at Coimbatore.
+We have conducted weekly social awareness campaigns on covid-19 and waste management. Drives for blood donation camps and allocating student groups for poster making and website building.
+We are involved in actively recruiting new members for volunteering services.
Smile Foundation
at Fundraiser & Event Handler
May 1, 2014 - May 1, 2014
Children
(Organiser at Monarch Internation School, pannimadai) Part of the ‘Shiksha Na Ruke' initiative
+Canvased through the school with charts, and posters brining an additional 60+ students to join the campaign.
+Rose a fund amount of ₹ 4000 distributing smile badges, stationary items, smile caps and bags in return for every donation.
+Engaged my neighbors in the local area to donate for the same, introduced a healthy competition among my peers, finding a positive way to raise additional funds for this program, making it an immense success.
Peer Reviewer
at IOS Press
Oct 1, 2023 - Present
Education
Journal: IDT (Intelligent Decision Technologies)
+Took part as a peer-reviewer to make sure that articles are of fine quality, within the scope of the journal, and suitable for publication.
Articles I have reviewed:
+IDT-230359: Optimization Design of Railroad Freight Station Computer Inquiry System Based on Robot Intelligent Configuration System.
+IDT-230693: On-line Task Allocation for Multi-Robot Teams Under Dynamic Scenarios.