Special Session 1:
INTELLIGENT SYSTEMS FOR ANOMALY ANALYTICS USING AI SOLUTIONS
Anomaly/outlier detection is a process to discover the irregularities,inconsistencies,deviations,exceptions, distortions, etc. of an object or its behavior, and dynamics.Anomalies generally occur in several real-world cases like fraud in finance,gene sequence analysis,product quality control,space and astronomic exploration, cybersecurity, market surveillance, faulty systems, business compliance, images/videos in social media, bushfire early warning, fake news and medical diagnosis disease. Early and automatic alert of anomalies or even their prediction before occurrence are of great concern.
The basic challenge with generated data is to identify the anomalous behavior. A large volume of data often comes from connected devices like automobiles or due to their malfunctioning, faulty parts and hazardous environmental conditions. Therefore, statistical analysis, artificial intelligence based intelligent systems and their insights are required everywhere for anomaly analysis. Additionally, self-learning based intelligent systems are also needed to evolve automatically based on the perceptions obtained from newer events. As the data is growing bigger, the amount of patterns recognized also rises, directing to more consistent and accurate output. Furthermore, seamless integration is required in intelligent systems to integrate with present systems. Also, in many cases, deep learning-based models are difficult to regulate and tough to understand. Additionally, the increased complexity of real-world cyber-physical systems is providing upsurge to unprecedented challenges of facing anomaly analytics. The main challenge is to react and respond in real time to critical events. Certain anomalies could produce disasters that direct to vast economic loss unless discovered and dealt with on-time. Therefore, an automated real-time intelligent system is required to facilitate the error-free handling of complex and large datasets with alerts.
The aim of this special issue is to invite contributors to submit their new findings in form of review/ research papers based on AI and related key challenges for analysing anomalies in diverse domains. Topics relevant to this Special Issue may include (but are not limited to):
|Machine/Deep learning for anomaly analytics||Intelligent systems for deep anomaly analytics|
|AI powered anomaly analysis||Explainability in anomaly detection|
|Anomaly modeling and analysis||Analyzing negative feedback, sentiment and emotion|
|Augmented intelligence for anomaly detection||Analyzing abnormal effect, consequence, impact and risk|
|Analyzing abnormal actions, activities, behaviors, events and their development|
|AI based Intelligent systems for Anomaly analytics in various domains are: Social networks, Smart Cities, Industries, cybersecurity, education,
healthcare, Agriculture, Business, social networks, space exploration, Internet of Things (IoT).
Deepika Koundal is currently associated with the University of Petroleum and Energy Studies, Dehradun. She received recognition and an honorary membership from the Neutrosophic Science Association at the University of Mexico, USA. She is also selected as a Young scientist in 6th BRICS Conclave by NIAS-DST in 2021. She received the MTech. and a Ph.D. degree in Computer Science & Engineering from Panjab University,Chandigarh in 2015. She is the awardee of research excellence award given by UPES in 2022 and Chitkara University in 2019. She has published approx. 100 research articles in reputed SCI and Scopus-indexed journals, conferences, and two books. She is currently a guest editor in Computers & Electrical Engineering, Internet of Things Journals (Elsevier) and IEEE Transaction of Industrial Informatics, Computational and Mathematical Methods in Medicine, MDPI Sensor, SPIE, Hindawi, and CMC. She is also serving as Associate Editor in IET Image Processing and the International Journal of Computer Applications. She also has served on many technical program committees as well as organizing committees and invited to give guest lectures and tutorials in Faculty development programs, international conferences and summer schools. Her areas of interest are Artificial Intelligence, Wireless Sensors, IoT, Biomedical Imaging and Signals, Soft Computing, and Machine Learning/ Deep Learning. She has also served as a reviewer in many repudiated journals of IEEE, Springer, Elsevier, IET, Hindawi, Wiley and Sage.
Special Session 2:
FAULT DETECTION AND CLASSIFICATION TECHNIQUES
Dr. Nasar Aldian Shashoa,
Fault detection (FD) has become increasingly important with the rising demand for reliability and safety of systems, driven by economic incentives as well environmental causes. Model-Based fault detection methods are the most frequently used for fault detection and these methods use a mathematical model of the monitored plant, and rely on the concept of analytical redundancy; the measured values are compared to analytically computed values of the respective variable. Any discrepancy can indicate that a fault may have occurred. However, the presence of modeling uncertainties, disturbances, and noise is inevitable. Now, instead of setting deviation of residual from zero as indicator of faults, a threshold that cares for the effect of modeling uncertainties, disturbances, and noise should be selected and if the residual exceeds the selected threshold, it gives an indication of the presence of faults. Selection of threshold is important for a fault detection system and one of the most relevant techniques for the diagnosis is the supervised classification. The session chair invite researchers, engineers and students to submit original scholarly works of the topics, which related but are not limit to the following topics:
|Parameter Estimation methods and Identification||Quantitative-based methods|
|System identification and model validation||Classification Techniques|
|Intelligent Fault Detection and Diagnostics Techniques||Robust Fault Detection and Diagnosis|
|Feature Extraction and Classification for Fault Diagnosis||Modeling and Simulation|
Nasar Aldian Ambark Shashoa holds his BSc degree in Electrical and Electronics Engineering, School of engineering, University of Tripoli, (academic year-1997/1998). He received his MSc degree from School of Electrical Engineering, University of Belgrade, Serbia 2005. He achieved his PhD from School of Electrical Engineering, University of Belgrade, Serbia 2013. In July 2013, he joined the electrical and electronic engineering department, Faculty of Engineering, Azzaytuna University, Tarhona, Libya. In September 2019, he joined the Libyan academy for postgraduate studies as Associate Professor. His research interests are control engineering, system identification, fault detection and isolation, and pattern recognition. Original results have been published 39 papers in international journals and international conferences. He is an international program committee member, steering committee member and scientific committee member in several international conferences at different countries. He is IEEE Senior member and IEEE Libya Subsection Chair. In addition to, he is an IEEE Control Systems Society Member, IEEE Signal Processing Society Member and IEEE Industrial Electronics Society.
Special Session 3:
SMART PROCESS MANAGEMENT IN HEALTHCARE ENGINEERING
Dr. Adnen El-Amraoui
|Dr. Ahmed Nait Sidi Moh
Full Professor, Jean Monnet University (UJM), Saint Etienne, France
LASPI Laboratory – IUT of Roanne
Research interest: Healthcare and industrial engineering https://scholar.google.com/citations?user=MK8UhCYAAAAJ&hl=fr
“Smart process management” refers to processes that incorporate digital technology. This is not the future but our present. In our everyday life, we are increasingly experiencing and adopting new devices/things with computing capabilities that can provide us with smart and/or assistance. This is the case for almost all different scenarios for human societies. One such scenario is the field of healthcare. The motivation behind “Smart process management” is to develop process management featuring higher agility, configurability, robustness and responsiveness while also ensuring the maintainability and sustainability of the processes and/or services. The smart and/or intelligent support for achieving systems with these ambitious objectives is coming from the computation capabilities that the devices/things in the process environment provide. The purpose of this special session is to bring together the researchers from smart process management as well as healthcare professionals to set up visions on how state-of-art digital technology techniques and computational intelligence can be, or are, used for solving healthcare engineering problems. This event is also a good opportunity to show how healthcare professionals can contribute in promoting new applications with computational intelligence. Topics of interest include (but are not limited to)
Articles and contributions handling the following topics in the field of Smart process management in healthcare systems
Adnen El-Amraoui is Associate Professor at the University of Artois, France. He received his Ph.D. degree in process control from the Technical University of Belfort-Montbéliard (UTBM), France, in 2011. From September 2014 to August 2018 (4 years), he was Associate Professor at the University of Orléans, France. From September 2013 to August 2014 (1 year), he was Post-Doctoral Researcher in the French Engineering School “Ecole Centrale de Lille” (EC-Lille), France. His research interests include combinatorial optimization, artificial intelligence, approximation, interval analysis, scheduling and production planning, supply chain management, transportation systems and maintenance. He is the first and the corresponding author of several publications in refereed journals (COR, CIE, EEAI, EJIE, 4-OR, JSSSE, SIC, etc.) and in several IEEE and IFAC conferences. He is also a member of scientific committee to review paper in international conferences (CASE, IESM, GOL, GISEH, etc.) and impacted journals (CIE, EAAI, EJIE,IJPE, etc.). He has been administrative and scientific manager in several research projects (ANR, FUI, RISE, UTIQUE “France-Tunisia”, etc.).
Ahmed Nait Sidi Moh is Full Professor at the Jean Monnet University (UJM), Saint Etienne, France. He received his Ph.D. degree in computer science and automatic control from the University of Technology of Belfort (UTBM), Belfort, France, in2003. He was Assistant Professor at the UTBM from 2004 to2011. After, he joined as Associate Professor the University of Picardie Jules Verne (UPJV), Amiens, France, where he obtained his “Habilitation à diriger des Recherches” (HDR) in computer engineering in 2016. He is the author of several articles published in international journals, conferences, and workshops. He is involved in several national and international events such as conferences and work-shops organization, he is the technical program committee member of many international journals and conferences; He has participated in national research groups. His research has been supported by many research and development projects including European grants, regional projects, and EU EACEA Erasmus Mundus projects. His research interest is in the field of healthcare and industrial engineering, with problems of modeling, analysis and control, performance evaluation, resources sharing, optimization, scheduling and interoperability for service composition, information and communication technologies.