Convergence of Big Data Technologies and Machine Learning: Integrated Applications

Dear Colleagues, 

The Special Issue has ignited a paradigm shift across virtually every scientific, industrial, and societal domain. The unprecedented volume, velocity, and variety of data generated today provide fertile ground for ML algorithms to uncover hidden patterns, generate predictive insights, automate complex decisions, and drive innovation at an unprecedented scale.

This Special Issue aims to capture the cutting-edge research and groundbreaking applications emerging from this powerful fusion. We seek high-quality, original contributions that demonstrate the practical application of ML techniques leveraging Big Data technologies (e.g., Hadoop, Spark, Flink, Kafka, NoSQL databases, cloud platforms, and distributed computing frameworks) to solve real-world challenges. We are particularly interested in work that moves beyond theoretical models and showcases tangible impact, scalability, and the unique challenges addressed when deploying ML at scale.

Scope and Topics of Interest

We invite submissions covering novel research and insightful case studies on the application of Big Data technologies enhanced by Machine Learning. Topics include the following:

1. Scalable ML Algorithms & Frameworks:

• Development and optimization of ML algorithms (deep learning, ensemble methods, reinforcement learning, etc.) designed explicitly for distributed Big Data environments (Spark MLlib, TensorFlow on Spark, Horovod, and Dask-ML).
• Efficient model training, inference, and hyperparameter tuning on massive datasets.
• Handling high-dimensional, sparse, streaming, and heterogeneous data with ML.
• Federated learning and privacy-preserving ML at scale.

2. Domain-Specific Applications (Illustrative Examples):

• Healthcare & Bioinformatics: Predictive diagnostics, personalized medicine, drug discovery, medical image analysis, genomic data analysis, and epidemic prediction.
• Smart Cities & IoT: Traffic prediction and optimization, energy grid management, environmental monitoring, predictive maintenance for infrastructure, and smart building automation.
• Manufacturing & Industry 4.0: Predictive maintenance, quality control, supply chain optimization, anomaly detection in industrial processes, and resource allocation.
• Natural Language Processing (NLP) at Scale: Large-scale sentiment analysis, machine translation, chatbots, document summarization, and topic modeling on massive text corpora.
• Computer Vision & Multimedia: Large-scale image/video recognition, content-based retrieval, video analytics, and autonomous systems perception.
• Cybersecurity: Anomaly detection in network traffic, intrusion detection/prevention systems, malware analysis, and threat intelligence fusion.
• Climate Science & Sustainability: Climate modeling, extreme weather prediction, resource management optimization, and environmental impact assessment.

3. Infrastructure, Systems & Engineering:

• Architectures for deploying and managing ML pipelines on Big Data platforms (feature engineering, model serving, and monitoring).
• Integration of ML with real-time data streams and complex event processing.
• Resource management and optimization for large-scale ML workloads in cloud/edge environments.
• Data lakehouse architectures for ML.
• Tools and platforms for MLOps (Machine Learning Operations) at scale.

4. Overcoming Big Data Challenges for ML:

• Techniques for handling data quality issues, missing values, and noise in large datasets.
• Scalable feature engineering and selection methods.
• Addressing Concept Drift in Streaming Data Applications.
• Ensuring model interpretability, fairness, and robustness when trained on massive data.

Dr. Chung-Hao Chen
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. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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.

• scalable machine learning
• computer vision
• cybersecurity
• bioinformatics
• natural language processing
• big data