Submission Deadline: 01 June 2025 View: 213 Submit to Special Issue
Dr. Mustafa Demetgül
Email: mdemetgul179@gmail.com
Affiliation: Institute of Applied Informatics and Formal Description Methods (aifb), KIT, Karlsruhe, 76133, Germany
Research Interests: Anomaly Detection, Signal Processing, Deep Learning, Machine Learning, Computer Vision, Data Science, Fault Diagnosis
Dr. Haluk Küçük
Email: hkucuk01@gmail.com
Affiliation: Applied Technology, Engineering Program, William Penn University, Oskaloosa, IA 52577, USA
Research Interests: Deep Learning, Robotics, Diagnostics
The concept of unmanned factories is becoming increasingly significant within the framework of Industry 4.0, and machine monitoring is a crucial aspect of this development. Numerous studies have highlighted the importance of addressing machine failures, which, although rare, are vital to the overall performance of manufacturing operations.
In any manufacturing environment, an unnoticed machinery problem is certain to worsen over time, potentially causing additional mechanical issues. To counteract this, intelligent manufacturing systems have been developed to predict failures in advance. Recent technological advancements have focused on integrated distributed intelligent manufacturing systems, incorporating distributed artificial intelligence theory and applications. Monitoring and predicting problems at an early stage, as well as timely repairing machine parts, are essential to maintaining operational efficiency. Effective machine monitoring allows for the early diagnosis of many faults, preventing more severe damage in the future.
Early detection of machine faults enhances reliability, reduces energy consumption, lowers service and maintenance costs, and extends the lifecycle and safety of machines. This, in turn, significantly reduces lifecycle costs.
Anomaly detection involves identifying instances in a dataset that significantly differ from the norm. Such anomalies are often of particular interest in various real-world analytical tasks, as they can indicate events that need special attention. Beyond industrial applications, potential uses include intrusion detection, payment fraud detection, public safety, autonomous vehicles, agriculture, driver behaviour, quality control, road monitoring, complex system monitoring, and medical data analytics.
Considerable work has been done in this area, and efforts to advance these developments are ongoing. The aim of this Special Issue is to gather recent advancements in machine learning and deep learning algorithms, signal processing techniques, feature extraction, feature selection, and data science studies, with a strong emphasis on application-oriented research. Topics of interest include, but are not limited to:
· Advanced signal processing techniques for machine monitoring
· Feature extraction and selection methods for anomalies detection and fault diagnosis
· Data science applications in anomalies detection
· Integration of distributed artificial intelligence in quality control and manufacturing systems
· Anomaly detection in time series, images, video, and text data
· Machine learning and deep learning algorithms for predictive maintenance
· Intelligent public safety, driver behavior, autonomous vehicles, and roads monitoring
· Anomaly detection in medical systems with computer vision and sensor data
· Intelligent cyber-security and payment fraud detection
· Complex system monitoring
We look forward to receiving contributions that offer new insights and innovative solutions in the field of anomaly detection.
Login
Register
Submit a Paper
Propose a Special lssue