avatar

Albin James Maliakal

Department of Computer Science & Engineering,
Indian Institute of Technology Madras
albinjames2002@gmail.com


Bio

Education

Research Interests

Technical Skills

Blogs

Publications

  1. Computational Finance
    Computational Methods for Optimal Hedging in Markov Modulated Markets
    Albin James Maliakal
    Computational Finance
    Project Page Working Paper

Teaching & Sharing

  1. Urban Computing
    Intelligent Traffic Monitoring and Control
    This presentation introduced an intelligent traffic monitoring system combining IoT architecture (V2X, RSUs, edge-cloud layers) with Q-Learning for dynamic signal optimization. It examined real-time data flows, modular design, and the synergy of distributed sensing with reinforcement learning.
    May 28, 2025
    PDF Website Offline (20+ people, 30 minutes)

  2. Computational Finance
    Design and Comparative Analysis of Advanced Quantitative Trading Strategies
    This presentation examined advanced quantitative trading strategies in Python, focusing on momentum and mean reversion models applied to stock data. It covered data collection, preprocessing, technical indicators, and analyzed performance metrics and algorithmic trading outcomes.
    April 22, 2025
    PDF Website Offline (30+ people, 30 minutes)

  3. Theory of Computation
    A Brief Introduction to Computational Complexity
    This presentation on Computational Complexity examined the resources required for solving computational problems, focusing on time and space complexity. It categorized problems into classes like P, NP, and PSPACE, enhancing understanding of algorithm efficiency.
    November 12, 2024
    PDF Website Offline (20+ people, 30 minutes)

    4. Projects

    1. Image Segmentation
      ChromaCut
      ChromaCut is a cutting-edge toolkit for high-precision image segmentation, integrating advanced superpixel over-segmentation and graph-based techniques like the Boykov-Kolmogorov (Min-cut/Max-flow) algorithm. It processes images by first dividing them into superpixels for detailed analysis, then applies graph-based methods for accurate segmentation. Using CIDE2000 for color evaluation and foreground extraction, it enhances segmentation precision across diverse image types.
      PDF Website

    2. Image Segmentation
      NeuroCluster
      NeuroCluster is an advanced image segmentation toolkit leveraging the Improved Intuitionistic Fuzzy C-Means (IIFCM) algorithm, specifically tailored for magnetic resonance (MR) image analysis. This toolkit enables precise segmentation of MR images into distinct regions, enhancing the ability to identify and analyze various brain structures based on pixel intensity and color values.
      PDF Website Open Source

    3. Speech Recognition
      FinSpeech
      This project aims to enhance speech recognition capabilities within banking dialogues by employing a Convolutional, Recurrent, and Dense Neural Network (CRDNN) alongside Language Model (LM) support. Utilizing the HarperValleyBank (HVB) corpus, the project strives to develop an ASR system that can accurately transcribe spoken banking dialogues, improving customer service experiences and operational efficiencies.
      PDF Website Open Source

    4. Image Denoising
      AutoDigit
      This project investigates the use of autoencoders for denoising images to improve handwritten digit recognition accuracy using the MNIST dataset. By introducing noise to the dataset and employing an autoencoder for image reconstruction, the study aims to enhance digit classification performance, demonstrating the practical applications and effectiveness of autoencoders in deep learning.
      PDF Website Open Source

    Contact

    Address： Kottayam, Kerala
    Email： albinjames2002@gmail.com
    Tel：(+91) 9495401332
    Personal public account：albinjm