About the Book
From the last two decades, researchers are looking at the imbalanced data learning as a prominent research area. Majority of critical real-world application areas like finance, health, network, news, online advertisement, social network media and weather data are imbalanced.
Some of the real-time research areas that need attention are fraud/defaulter detection, rare disease/reaction prediction, network intrusion detection, fake news detection, fraud advertisement detection, cyberbullying identification, disaster events prediction, etc.
Machine learning algorithms are based on the heuristic of equally distributed balanced data and provide the biased result towards the majority data class, which is not acceptable at all, as the imbalanced data is omnipresent in real-life scenarios and forcing researchers to learn from imbalanced data equally for foolproof application design.
The imbalanced data is multifaceted and demands new perception to explore the knowledge using novelty at sampling approach of data preprocessing, active learning approach and cost perceptive approach to resolve data imbalance.
Objectives
The aim of this book is to provide the new aspect for imbalanced data learning in an exceptional way by providing the advancement in the traditional methods of big data with the help of case study and numerous future prospects from the expertise of academia, engineering and industry.
So, the edited relevant theoretical frameworks and the latest empirical research findings help to improve the understanding the impact of imbalanced data and its resolving techniques based on the Data Preprocessing, Active Learning, and Cost Perceptive Approaches.
Topics
- Data Preparation
- Feature Engineering
- Sampling Techniques
- Partitioning
- Granularity Management
- Sensitivity Management
- Locality Management
- Rare Itemsets Mining
- Supervised Learning Algorithms
- Unsupervised Learning Algorithms
- Ensemble Algorithms
- Hybrid Algorithms
- Scalable Algorithms
- Hyper Parameter Tuning
- Storage Structure: Database, Data Warehouses and Data Lakes
- Metadata Management
- Evaluation Measure
- Data Visualization
- Case Study: in the area not limited to the following
- Social Network Mining
- Finance
- Health
- Weather
- Disaster Management
Target Audience
- Target Audience is researchers, faculties, engineers, and students with a background in computer science, engineering, industry people. This book can be used as a textbook or reference book for graduates and post-graduate levels courses like data science, machine learning, data mining, and pattern mining to deal with the problem of learning from imbalanced data.
- Also, this book can be utilized for multidisciplinary research scholars as it will provide a great source of literature to understand imbalanced data and its impact, novel approaches and the future research directions.
- The book can help the beginner and intermediate researchers to re-engineer their way of thinking for the solution approach. The readers will be benefited by having a clear vision of imbalanced data characteristics and learning using out of the box solution.
Submission Guidelines
- All submissions should be done through this link.
- No publication fees
- The books of this series are submitted to Web of Science, SCOPUS, DBLP
Important Dates
- Proposal Submission Deadline: 11th November 2020
- Acceptance Notification: 25th November 2020
- Full chapter Submission: 24th January 2021
- Review Results Returned: 9th March 2021
- Final Acceptance Notification: 20th April 2021
Contact
- Dr. Dipti Rana
Sardar Vallabhbhai National Institute of Technology, India
dpr@coed.svnit.ac.in - Dr. Rupa Mehta
Sardar Vallabhbhai National Institute of Technology, India
rgm@coed.svnit.ac.in
For more details, click the link below.
Call for Chapters: Data Preprocessing, Active Learning, and Cost Perceptive Approaches for Resolving Data Imbalance
Responses