Dear Colleagues,

With the advances in big data analytics and machine learning technologies, people’s daily lives have been improved in many different ways. For example, tremendous improvement in image processing and language understanding technologies boost many applications in medical image diagnosis, face recognition, voice recognition, question answering, and machine reading comprehension. These have been possible largely due to the development of deep learning algorithms. However, deep learning algorithms rely on powerful machines and systems with GPUs to accomplish the complex and long training process. On the one hand, these solutions are limited by the computational power on single systems, which could not be scaled up indefinitely. Thus, big data analytics solutions utilize distributed frameworks to scale out in terms of data parallelism or task parallelism. On the other hand, the global environment has undergone an extremely rapid development that makes it difficult to maintain or recover to its original status. The impact of technology on environmental changes could lead to significant damages that also jeopardize human lives and global ecology. Many efforts have begun to address the sustainability issues by containing the environmental changes and slowing down deterioration—for example, addressing climate change, water resources, air quality, to name a few. This Special Issue focuses on ideas such as big data analytics for sustainability [1], federated learning [2], and distributed deep learning [3]. We aim to seek potential solutions and empirical studies that investigate sustainable technologies that are also energy efficient and resource efficient.

This issue includes, but is not limited to, the following topics:

• Performance of machine learning systems;
• Efficiency of deep learning algorithms;
• Resource allocation for improving sustainability in data mining;
• Effects of federated machine learning on sustainability;
• Energy efficiency of distributed deep learning systems;
• Sustainable big data analytics;
• Sustainable framework for large-scale data collection, processing, and analytics;
• Social media mining for sustainability;
• Social media monitoring for sustainability;
• Fake news detection for sustainability;
• Application of data science for sustainability in economy;
• The impact of big data analytics on environmental sustainability.

References:

[1] Zhihan Lv, Rahat Iqbal, Victor Chang, Big data analytics for sustainability, Future Generation Computer Systems, Volume 86, 2018, Pages 1238-1241.

[2] Jakub Konečný, H. Brendan McMahan, Daniel Ramage, “Federated Optimization: Distributed Optimization Beyond the Datacenter,” NIPS Optimization for Machine Learning Workshop (2015).

[3] Matthias Langer, Zhen He, Wenny Rahayu, Yanbo Xue, “Distributed Training of Deep Learning Models: A Taxonomic Perspective,” IEEE Transactions on Parallel and Distributed Systems, 2020, Volume: 31, Issue: 12, Pages: 2802-2818.

Dr. Jenq-Haur Wang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Big Data and Cognitive Computing is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• big data analytics
• data mining
• federated machine learning
• deep learning
• artificial intelligence
• distributed computing
• sustainable technology
• energy efficiency