A talk on the how to extract optimal set of features by applying metaheuristic-based feature selection approaches in high dimensional data
High-dimensional data can be challenging to work with because the number of variables can make it difficult to visualize, explore, and analyze the data. Additionally, high-dimensional datasets can be more susceptible to overfitting, where a model performs well on the training data but poorly on new data, due to the large number of variables. Techniques such as feature selection, dimensionality reduction, and regularization can help address these challenges. Meta-heuristic based feature selection is a technique used to select the most relevant features from a high-dimensional dataset. Meta-heuristics are optimization algorithms that are designed to find near-optimal solutions to complex problems. Meta-heuristic based feature selection has several advantages. It can handle high-dimensional datasets and can effectively select the most relevant features while reducing overfitting. Additionally, meta-heuristic algorithms are flexible and can be easily adapted to different types of models and fitness functions. Here we will discuss how to extract the optimal set of features from meta-heuristic based feature selection approaches in high dimensional datasets.
Date and Time
Location
Hosts
Registration
- Date: 03 Jun 2023
- Time: 07:00 PM to 08:00 PM
- All times are (UTC+05:30) Chennai
-
Add Event to Calendar
- Starts 02 June 2023 12:00 PM
- Ends 03 June 2023 04:00 PM
- All times are (UTC+05:30) Chennai
- No Admission Charge
Speakers
Dr. Pradip Dhal of Assistant Professor of CSE, Shiksha O Anusandhan Deemed to be University, Bhubaneswar
A talk on the how to extract optimal set of features by applying metaheuristic-based feature selection approaches in hig
High-dimensional data can be challenging to work with because the number of variables can make it difficult to visualize, explore, and analyze the data. Additionally, high-dimensional datasets can be more susceptible to overfitting, where a model performs well on the training data but poorly on new data, due to the large number of variables. Techniques such as feature selection, dimensionality reduction, and regularization can help address these challenges. Meta-heuristic based feature selection is a technique used to select the most relevant features from a high-dimensional dataset. Meta-heuristics are optimization algorithms that are designed to find near-optimal solutions to complex problems. Meta-heuristic based feature selection has several advantages. It can handle high-dimensional datasets and can effectively select the most relevant features while reducing overfitting. Additionally, meta-heuristic algorithms are flexible and can be easily adapted to different types of models and fitness functions. Here we will discuss how to extract the optimal set of features from meta-heuristic based feature selection approaches in high dimensional datasets.
Biography:
Pradip Dhal is currently working as an assistant professor in the department of CSE at Shiksha ‘O’ Anusandhan (SOA) (SOA) University Bhubaneswar. He has completed PhD in CSE from the National Institute of Technology Jamshedpur, India. He received his M.Tech degree in
Computer Science from the Central University of South Bihar Gaya, Bihar, India. Previously he worked as a Java Developer at Accenture India. His research interests include Machine Learning, Pattern Recognition, Data Mining, Medical Image Analysis, and Natural language Processing. He is the reviewer of various SCI-indexed journals like ISA Transactions (Elsevier), Journal of Supercomputing (Springer), Mobile Networks and Applications (Springer), BioData Mining (Springer), and Journal of Control Science and Engineering (Hindawi).
Email: