Lane Detection for Autonomous Vehicles using Segmentation Architecture on Custom Datasets with IOU 77% Use of Gradient Measured Curvature, Image Processing Method and applying to the data

System/Technologies used: Python, Deep Learning, OpenCV  Lane Detection for Autonomous Vehicles Using Segmentation architecture on Custom Datasets With IOU 77%  Used Gradient Measured Curvature. Image Processing Method and applying to the data

System/Technologies used: Python, OpenCV  Generation of ground Truth (Mask) of the input image for Segmentation  Find the Errors in Annotation  Model Training  Image Preprocessing

Evaluating the Probability of Default Using Python Objective: Identifying the right eligible applicant for credit and excluding the one with high risk. Tools : Jupyter notebook Libraries : Pandas, numpy, matplotlib, scikit-learn. Approach: Data Exploration | Data Preparation | Model Building | Model Evaluation | Model Tuning.

Objective: Tweet data to predict sentiment on electronic products of netizens. Tools: Jupyter notebook Libraries: Pandas, numpy, nltk, PorterStemmer, sklearn, TfidfVectorizer Approach: Data Exploration | Data preparation | Removing stopwords | Model building

Developed in python used keras api and Tensorflow libraries

Developed in python used Open cv and dlib library

Developed in Python Used Keras API and Tensorflow libraries Used Signal processing

Objective: Identifying the right eligible applicant for credit and excluding the one with high risk.Tools : Jupyter notebookLibraries : Pandas, numpy, matplotlib, scikit-learn.Approach: Data Exploration Data Preparation Model Building Model Evaluation Model Tuning.