Explainable AI in Machine/Deep Learning for Intrusion Detection in Intelligent Transportation Systems for Smart Cities

Advanced Learning Technologies for Intelligent Transportation Systems: Prospects and Challenges

“…This swift incident detection empowers transportation agencies to promptly dispatch first responders, efficiently clear obstructions, and implement mitigation strategies such as establishing detours to minimize disruptions to traffic flow [101], [102]. Reducing incident clearance time also plays a pivotal role in mitigating the secondary congestion and secondary accidents often stemming from primary incidents [103], [104]. With real-time incident alerts generated through DL-driven visual data analysis, transportation authorities can significantly enhance road safety and optimize incident management responses within urban traffic networks.…”

“…These systems frequently rely on intricate neural networks and DL models that can inherently lack transparency in their decisionmaking processes. XAI techniques bridge this opacity gap by enhancing the clarity and comprehensibility of AI systems [103], [251]. In the context of ITS, model transparency assumes paramount importance for scenarios where critical realtime decisions are made, such as autonomous vehicles navigating through traffic or traffic management systems controlling signal lights.…”

Explainable AI for Cyber-Physical Systems: Issues and Challenges

“…Fundamental cyber-physical system types in Industry 4.0 include smart factories, chatbots, human-computer interaction, smart healthcare, manufacturing, smart products, augmented reality, transportation industry, aviation, autonomous vehicles, smart consumer appliances, intelligent chemical industry, industrial robots, smart assistance, autonomous resource exploration, cybersecurity and privacy, predictive maintenance, and smart cities [2], [5], [13], [41]. Smart cities may employ diverse CPS such as smart transportation, smart airports, smart ports, smart hospitals, flood detection and mitigation, drainage monitoring systems, and smart power grids [34], [42].…”

Feature Attribution Analysis to Quantify the Impact of Oceanographic and Maneuverability Factors on Vessel Shaft Power Using Explainable Tree-Based Model

“…Numerous studies utilizing machine learning-based methodologies have been expanded with the aided Explainable Artificial Intelligence (XAI) approach to assist in better decision-making processes. This approach is making its way into a wide variety of domains, including education [ 18 ]; lithology [ 19 ] and geology [ 20 ]; social science [ 21 ]; construction engineering [ 22 , 23 ]; transportation [ 24 ] and smart cities [ 25 ]; healthcare [ 26 ] and medical [ 27 ]; mass media and entertainment [ 28 ]; tourism, travel, and hospitality [ 29 ]; supply chain management and manufacturing [ 30 ]; law enforcement [ 31 ] and legal [ 32 ]; information technology [ 33 ]; and financial services [ 34 , 35 ]. Overall, the research utilizing XAI to explain their machine learning model stated that it provides transparency of how the machine learning model produces its decision.…”