Applied AI research transcends theoretical progress and aims to operationalize AI's theoretical advancements to address practical challenges in the real world in areas such as healthcare, finance, education, transportation, and more and contribute positively to society. One illustration of the practical implementation of AI is in the detection of traffic signs or the classification of medical images, such as X-rays and MRI scans.

Applying AI in the complex real world poses several challenges, including lack of or no (quality) data, interoperability, security and privacy issues, and scalability issues other than the model's accuracy. Furthermore, in order to fully capitalize on the practical applications of AI, it is essential to consider additional AI-specific concerns, such as data drift, which arises from alterations in the external environment over time leading to changes in data (or data distribution). This is because data drift negatively impacts AI model accuracy, thereby undermining the purpose for which AI is implemented.

Our research on applied AI pertains to the solving of obstacles that arise from the convergence of multiple domains, including software engineering (e.g., AI deployment) and the sectors (e.g., healthcare, agriculture, and environment) in which AI is being applied. Our applied AI efforts are specifically directed towards the development, optimization, and deployment of AI solutions that aim to resolve particular challenges and enhance operations across various and intricate settings, ultimately generating concrete advantages.

Sustainable Development Goals:

Our research on applied AI aligns with the following Sustainable Development Goals of the United Nations: