Artificial Intelligence, Algorithms, and Databases: Innovations and Cross-Disciplinary Impact

Dear Colleagues,

Data-driven intelligent learning algorithms and deep learning models are a branch of artificial intelligence that emphasizes developing and using information learned from databases or time-series databases. Many real-world applications for complex industrial engineering or design problems could be modeled as optimization problems. Learning from time-series data or non-time-series databases, data-driven intelligent optimization algorithms and deep learning models represent an emerging approach that utilizes metaheuristic algorithms or deep models. These approaches have been actively investigated and applied to many real-world applications, mainly 5G communications, wireless sensor networks, scheduling, logistics and other operations.

Data-driven intelligent learning algorithms and deep learning models are a collection of search, learning and optimization techniques. Intelligent optimization algorithms include bio-inspired intelligent algorithms, evolutionary computation methods, swarm intelligence, etc. Deep learning models include CNNs, RNNs, LSTMs, GRUs, Autoencoders, GANs, Transformers, MLPs, DBNs, RBMs, Spiking Neural Networks (though less common), Capsule Networks, U-Net, YOLO, DQN, etc. With these methods, the optimization problems, which can be represented in any form, do not need to be mathematically represented as continuous and differentiable functions. The only requirement for representing optimization problems is to evaluate the objective function or loss function. Therefore, data-driven intelligent learning algorithms and deep learning models could be utilized to solve more general optimization problems, especially for problems that are very difficult to solve with traditional hill-climbing algorithms.

Real-world applications have complex properties. Firstly, 5G communications face several challenges and problems, which can be categorized into technical, infrastructural, and societal issues. Wireless sensor networks also face significant challenges that need to be addressed to ensure their effective and reliable operation. Managing a large number of sensor nodes efficiently is challenging, particularly in terms of data aggregation, routing, and network organization. Multiple sensors may generate redundant data, leading to unnecessary energy consumption and bandwidth usage. Moreover, massive data are collected and used in scheduling tasks to optimize route selection, taxi dispatching, dynamic transit bus scheduling, and other mobility services to improve the efficiency of operations. Another example is logistics, where material movements within and between supply chain entities, including warehouses, factories, distribution centers, and retail shops, are improved and optimized with advanced data-oriented techniques.

Due to the complexity of real-world applications, no one panacea can solve all troubles. Data-driven intelligent learning algorithms and deep learning models are practical approaches to handling such complexity by utilizing CNNs, RNNs, LSTMs, Autoencoders, GANs, Transformers, evolutionary computation, swarm intelligence, and other meta-heuristics methods based on domain expert knowledge and experience.

Scope of the Special Issue:

Submissions involving real-world case studies are encouraged on the following topics (but not limited to):

• Artificial intelligence;
• Deep learning;
• Data mining;
• Data-driven optimization methods;
• Time-series forecasting;
• Time-series anomaly detection;
• Swarm intelligence;
• Intelligent computing;
• Bio-inspired algorithms and nature-inspired computing;
• Computational intelligence and evolutionary algorithms;
• Meta-heuristic algorithms;
• Intelligent optimization algorithms;
• CNNs, RNNs, LSTMs, GRUs, Autoencoders, GANs, Transformers, MLPs, DBNs, RBMs, Spiking Neural Networks, Capsule Networks, U-Net, YOLO, etc.;
• Other related topics.

Dr. Junfeng Chen
Dr. Shi Cheng
Prof. Dr. Xiaohui Yan
Guest Editors

Dr. Sicheng Hou
Guest Editor Assistant

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 250 words) can be sent to the Editorial Office for assessment.

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. Mathematics 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 2600 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.

• artificial intelligence
• deep learning
• swarm intelligence
• data-driven optimization methods
• time-series forecasting
• computational intelligence and evolutionary algorithms
• meta-heuristic algorithms
• intelligent optimization algorithms
• data mining
• CNNs
• RNNs
• LSTMs
• autoencoders
• GANs
• transformers
• time-series anomaly detection