Call for Papers: Low Resource Machine Learning Algorithms (LR-MLA)
Guest Editors

Dr. Partha Pakray, National Institute of Technology Silchar, India
Dr. Somnath Mukhopadhyay, Assam University Silchar, India
Dr. Arnab Kumar Maji, North Eastern Hill University, India
Prof. David Pinto, Benemérita Universidad Autónoma de Puebla Mexico
Dr. Sunita Sarkar, Assam University Silchar, India
Scope
Machine Learning is an Artificial Intelligence (AI) application that is changing the way of business scenarios. It's an algorithm or model that learns patterns in large amounts of data and predicts similar patterns in new data. In layman's words, it's the idea that computers should be able to learn and adapt over time in order to make consistent repeatable decisions and outcomes. While machine learning is not new, there is now more data available than ever before, which has contributed to its current popularity. Machine learning is the future of marketing; these cutting-edge technologies help organizations to improve their customer experience and increase marketing initiatives. AI uses big analytics, machine learning, and various other methods to enhance insights into a specific target population. The collected information is used to provide a more efficient and tailored client experience across all interactions. Finally, machine learning aids in the elimination of human mistakes and potential guesswork during the client journey. Despite having brilliant AI business ideas, many applications gradually become disappointed when they find they lack sufficient data. Since data is the heart of any ML system, the problem of data scarcity is critical. A lack of datasets frequently causes poor performance in machine learning tasks. The majority of the time, data-related difficulties is the primary reason to fail the ML-based projects. In some ML applications, there is no relevant data, or the collection process is excessively difficult and time-consuming. Lack of data means more ML hidden doubts and inadequate outcomes. It is impossible to prepare data for machine learning, and even the most outstanding software faces obstacles without sufficient data filling. That's why big promising ML tasks often come as not as successful as expected, as data scientists are limited in the ways of acquiring and preparing data for machine learning. This problem is common for all applications which rely on data availability, such as image processing, natural language processing, cryptography and information security, intelligent systems, system optimization, and signal processing.


Topics
Relevant topics include but are not limited to:
 Low resource Natural Language Processing
 Low resource Data Communication
 Low resource Image Processing
 Low resource in Agriculture domain
 Low resource in Healthcare domain
 Low resource data science and analytics
 Low resource IoT systems

Important dates
Submission Date: 31.12.2021
Desk Rejection: 15.01.2022
First Round Decision: 15.03.2022
Revised Submission: 30.04.2022
Final Decision: 31.05.2022


Journal Link: https://www.springer.com/journal/11334/updates/19857864?fbclid=IwAR2ZJh1BKTJ6CeT0DhI_KNJUTYvjVZQzaGF-i4U-F4ci2_zwupBu1y9KX2E

Submission process
1. Submit paper as article type 'Original research'
2. Later in submission process, confirm that your paper belongs to a special issue
3. Select title of special issue from menu 'S.I. : LR-MLA’
Contact us:
If you have questions, please send email to the below address: som.cse@live.com/ parthapakray@gmail.com.