Deep Learning-Based Dog vs Cat Image Classification using CNN
Built a deep learning model using Convolutional Neural Networks (CNN) with TensorFlow and Keras to classify images of dogs and cats.
• Applied image preprocessing, resizing, normalization, and data augmentation
• Designed CNN architecture with convolutional, pooling, and dense layers
• Evaluated model performance using training and validation datasets
GitHub: https://github.com/Soumik-Acharya495/-Deep-Learning-Based-Dog-vs-Cat-Image-Classification-using-CNN-/blob/main/CNN_CAT_DOG.ipynb
Performance Analysis of Wavelength Division Multiplexing (WDM) System using Multivariate Regression
Worked on the analysis and optimization of a Wavelength Division Multiplexing (WDM) system to improve data transmission performance in optical communication networks.
The project focused on evaluating key performance parameters such as Bit Error Rate (BER) and signal quality under varying input conditions and number of channels. Applied multivariate regression techniques to predict system performance and analyze the relationship between different parameters.
Conducted simulations and data analysis to compare actual and predicted results, improving understanding of system behavior and efficiency. The project demonstrates strong analytical, mathematical modeling, and data interpretation skills.
Key Highlights:
• Analyzed BER performance across multiple channels
• Applied regression modeling for prediction and optimization
• Compared actual vs predicted results using error metrics
• Worked with data visualization and interpretation
Rainfall Prediction using Machine Learning and Data Analysis
Developed a machine learning-based rainfall prediction system using historical weather data to forecast precipitation patterns.
The project involved data preprocessing, exploratory data analysis (EDA), and feature selection to identify key factors influencing rainfall. Built and trained machine learning models to predict rainfall based on parameters such as temperature, humidity, wind speed, and atmospheric pressure.
Performed model evaluation using accuracy metrics and optimized performance through parameter tuning. Visualized trends and insights using data visualization techniques to better understand weather patterns.
Key Highlights:
• Performed data cleaning and preprocessing on weather datasets
• Conducted Exploratory Data Analysis (EDA) to identify patterns
• Built and evaluated machine learning models for prediction
• Used visualization to interpret rainfall trends and insights
Dog vs Cat Image Classification using CNN
Built a CNN model using TensorFlow and Keras; applied preprocessing, augmentation, and tuning.
Rainfall Prediction using Machine Learning
Developed a regression model using weather data; performed preprocessing and evaluation.
Optimum Threshold Detection in WDM System
Built an ML model for threshold detection; applied regression and evaluation metrics.
