Hybrid Artificial Intelligence for Systems and Applications

Dear Colleagues,

This Special Issue contains extended papers from the sixth International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI′ 2024), 17–19 April 2024, Funchal (Madeira Island), Portugal (https://aspai-conference.com).

In recent years, the field of artificial intelligence (AI) has witnessed remarkable advancements, with systems and applications spanning various domains such as healthcare, finance, transportation, and manufacturing. One of the emerging paradigms within AI is hybrid artificial intelligence (HAI), which combines the strengths of different AI techniques to effectively address complex real-world problems. The concerns mentioned above related to trustworthy AI cannot be addressed through a single paradigm. We must incorporate various AI paradigms, such as learning, reasoning, optimization, inference, and meta-heuristics. Thus, the concept of “hybrid AI” is introduced that, computationally and mathematically, integrates different paradigms. Hybrid AI integrates multiple AI approaches, including symbolic reasoning, machine learning, evolutionary computation, expert systems, and fuzzy logic, among others, to create more robust and adaptive systems. The concept of hybrid AI stems from the recognition that no single AI technique can excel in all scenarios. While machine learning algorithms, such as deep neural networks, excel at pattern recognition and classification tasks, they may struggle with explainability and reasoning. Conversely, symbolic reasoning approaches are adept at logical inference and decision making but may lack the scalability and flexibility offered by machine learning techniques. By integrating these complementary approaches, hybrid AI endeavors to overcome the limitations of individual techniques and harness their combined capabilities to tackle complex problems more effectively. The systems and applications in hybrid AI are diverse and far-reaching. In healthcare, hybrid AI systems can assist in medical diagnoses and treatment recommendations by combining clinical expertise with data-driven insights from patient records and medical imaging. In finance, hybrid AI models can enhance risk assessments and portfolio optimization by integrating predictive analytics with expert knowledge of market dynamics. Similarly, in autonomous vehicles, hybrid AI enables robust decision making by combining sensor data processing with rule-based reasoning and machine learning for adaptive behavior in dynamic environments. Thus, this Special Issue, “Hybrid Artificial Intelligence for Systems and Applications”, aims to provide insights into principles, methodologies, and applications in this interdisciplinary field. Through a deeper understanding of hybrid AI, researchers, practitioners, and enthusiasts can leverage its potential to develop innovative solutions to complex real-world challenges, ultimately advancing the frontier of artificial intelligence and its practical applications across diverse domains.

Prof. Dr. Mobyen Uddin Ahmed
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. Digital is an international peer-reviewed open access quarterly 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 1000 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 (AI)
• hybrid artificial intelligence (HAI)
• learning
• reasoning
• optimization
• inference
• meta-heuristics
• symbolic reasoning
• machine learning
• evolutionary computation
• expert systems
• fuzzy logic

Title: Real-time Detection, Evaluation and Mapping of Crowd Panic Emergencies Based on Geo-biometrical data and Machine Learning
Authors: Lazarou Ilias
Affiliation: Department of Surveying and Geoinformatics Engineering, University of West Attica
Abstract: Crowd panic emergencies can pose serious risks to public safety, and effective detection and mapping of such events are crucial for rapid response and mitigation. In this paper, we propose a real-time system for detecting and mapping crowd panic emergencies based on machine learning and georeferenced biometric data from wearable devices and smartphones. The system uses a Gaussian SVM machine learning classifier to predict whether a person is stressed or not and then performs real-time spatial analysis to monitor the movement of stressed individuals. To further enhance emergency detection and response, we introduce the concept of CLOT (Classifier Confidence Level Over Time) as a parameter that influences the system's noise filtering and detection speed. Concurrently, we introduce a newly developed metric called DEI (Domino Effect Index). The DEI is designed to assess the severity of panic-induced crowd behavior by considering factors such as the rate of panic transmission, density of panicked people, and alignment with the road network. This metric offers immeasurable benefit by assessing the magnitude of the cascading impact, enabling emergency responders to quickly determine the severity of the event and take necessary actions to prevent its escalation. Based on individuals' trajectories and adjacency, the system produces dynamic areas that represent the development of the phenomenon's spatial extent in real-time. The results show that the proposed system is effective in detecting and mapping crowd panic emergencies in real-time. The system generates three types of dynamic areas: a dynamic crowd panic area based on the initial stressed locations of the persons, a dynamic crowd panic area based on the current stressed locations of the persons, and the dynamic geometric difference between these two. These areas provide emergency responders with a real-time understanding of the extent and development of the crowd panic emergency, allowing for a more targeted and effective response. By incorporating the CLOT and the DEI, emergency responders can better understand crowd behavior and develop more effective response strategies to mitigate the risks associated with panic-induced crowd movements. In conclusion, our proposed system enhanced by the incorporation of these two new metrics, proves to be a dependable and efficient tool for detecting, mapping, and assessing the severity of crowd panic emergencies, leading to a more efficient response, and ultimately safeguarding public safety.