DIGICOGS
DIGICOGS: DIGital Twins for Industrial COGnitive Systems through Industry 4.0 and Artificial Intelligence
Today, in Industry 4.0, Big data analytics – which is used to sort through massive amounts of data and identifies important patterns – have become useful in the advancement of industrial cognitive systems in process industries & are a major theme in current industrial technology development. The challenge is to achieve the advantage of using a data-driven cognitive system by integrating the heterogeneous data from multiple sources that can easily be used in a machine learning model and adjust the algorithms. The objective of DIGICOGS is to provide a digital twin that combines sensor information, AI and machine learning and big data analytics that underpin the new wave of the cognitive system. In DIGICOGS, cutting-edge solutions will be achieved through data-driven analytics, real-time monitoring and intelligent adaptive prediction based on combination of information i.e, sensor data, domain and context. DIGICOGS comprises MDH (a research group), Seco Tools (supplier to process industry and to GKN) & GKN (manufacturing industry). The project tasks will be performed as several work packages (WPs) including different methodologies, such as determining the state of the art, studying the data, defining the use-cases, developing the tools and evaluating the results. Thus, it is believed that the DIGICOGS technologies will strengthen Swedish industrial competence and competitiveness. The results from the project can be re-used and repeated with other Seco Tools customers and companies in process industry.
Project Leader: Mobyen Uddin Ahmed, Professor
Funding Agencies: EU
XAPP
xApp: Explainable AI for Industrial Applications
Explainable AI (XAI) is an emerging and demanding field in AI technologies. Mälardalen University (MDH) being the forerunner in the race of AI has already started working on projects such as ARTIMATION where XAI is being practically implemented. To enhance the calibre of researchers in the new domain XAI, having external expertise will be highly beneficial.
Since the mobility will focus on the application of AI within an industrial perspective, this is aligned with MDH's strategy of coproduction and will add value to make MDH internationally recognized for its activities in the areas of AI and ML.
Strengthen the research and education competence and collaboration in XAI between Sweden and the USA by establishing the staff exchange.
MONITOR
Trusty
TRUSTY: TRUSTWORTHY INTELLIGENT SYSTEM FOR REMOTE DIGITAL TOWER
Overall, the goal of TRUSTY is to provide adaptation in the level of transparency to enhance the trustworthiness of AI-powered decisions in the context of remote digital towers (RDTs). While in an actual tower, operators have direct visual access to the taxiway and runway monitoring, the RDTs concept only provides such information through video transmission with a warning and the corresponding explanation. To deliver trustworthiness in an AI-powered intelligent system TRUSTY will consider several approaches, and they are listed:
Project Leader: Mobyen Uddin Ahmed, Professor
Funding Agencies: EU
BariansafeDrive
BRAINSAFEDRIVE: A Technology to detect Mental States During Drive for improving the Safety of the road
BRAINSAFEDRIVE will develop a tool as attentional detectors that detect drivers’ mental state in terms of stress, cognitive load, sleepiness in real time during simulated and/or natural driving situations.
Here, the project combines two necessary state of the art expertise’s:
the acquisition and analysis of cerebral signals i.e. Electroencephalography (EEG) and Electrooculography (EOG);
the application of artificial intelligence and machine learning algorithms.
The drivers’ mental state will be correlated with vehicular parameters e.g. brake, speed, acceleration, lane chnges etc and classify the driving as "normal, healthy and safe” driver.
Project Leader: Mobyen Uddin Ahmed, Professor
Funding Agencies: VINNOVA
Artimation
ARTIMATION: TRANSPARENT ARTIFICIAL INTELLIGENCE AND AUTOMATION TO AIR TRAFFIC MANAGEMENT SYSTEMS
Artificial Intelligence (AI) has recently improved by leaps and bounds and is now present in every application domain. This is also the case for Air Transportation, where decision making is more and more associated with AI and in particular with Machine Learning (ML). While these algorithms are meant to help users in their daily tasks, they still face acceptability issues. Users are doubtful about the proposed decision or even worse opposed to it since the decision provided by AI is most of the time opaque, non-intuitive and not understandable by a human. So, compared to a natural discussion between two users, the machines often provide information without the opportunity to justify it. In other words, today’s automation systems with AI or ML do not provide additional information on top of the data processing result to support its explanation which makes them not transparent enough. Also, when AI is applied in a high-risk context such as Air Traffic Management (ATM) individual decision generated by the AI model should be trusted by the human operators. Understanding the behaviour of the model and explanation of the result is a necessary condition for trust. To address these limitations, the ARTIMATION project investigates the applicability of AI methods from the domain of Explainable Artificial Intelligence (XAI). In the project, we will investigate specific features to make AI model transparent and post hoc interpretable (i.e., decision understanding) for users in the domain of ATM systems.
Project Leader: Mobyen Uddin Ahmed, Professor
Funding Agencies: EU
CPMXAI
CPMXai: Cognitive Predictive Maintenance and Quality Assurance using Explainable Ai and Machine Learning
The practice of predictive maintenance has escalated since the advancement in Artificial Intelligence (AI) and Machine Learning (ML). It anticipates the maintenance required, avoiding unnecessary costs (saving time, energy, money and resources) and breakdowns of machines. However, for more accurate and better predictions cognitive predictive maintenance is required.
CPMXai has 3 objectives i.e.,
identify use cases in the industries,
develop a new automatic data labelling tool with the help of digital twin and lastly,
develop a self-monitoring, self-learning, self-explainable system to predict.
Project Leader: Mobyen Uddin Ahmed, Professor
Funding Agencies: VINNOVA
Copyright © 2023 Trustworthy AI Research Group