On the Democratization of AI: Bridging the Gap with AutoML

Riding the wave of recent groundbreaking achievements, artificial intelligence (AI) is currently the buzzword on everybody’s lips and, allowing algorithms to learn from historical data, Machine Learning (ML) emerged as its pinnacle. The multitude of algorithms, each with unique strengths and weaknesses, highlights the absence of a universal solution and poses a challenging optimization problem. In response, automated machine learning (AutoML) navigates vast search spaces within minimal time constraints. By lowering entry barriers, AutoML emerged as promising the democratization of AI, yet facing some challenges. In data-centric AI, the discipline of systematically engineering data used to build an AI system, the challenge of configuring data pipelines is rather simple. We devise a methodology for building effective data pre-processing pipelines in supervised learning as well as a data-centric AutoML solution for unsupervised learning. In human-centric AI, many current AutoML tools were not built around the user but rather around algorithmic ideas, raising ethical and social bias concerns. We contribute by deploying AutoML tools aiming at complementing, instead of replacing, human intelligence. In particular, we provide solutions for single-objective and multi-objective optimization and showcase the challenges and potential of novel interfaces featuring large language models. Finally, there are application areas that rely on numerical simulators, often related to earth observations, they tend to be particularly high-impact and address important challenges such as climate change and crop life cycles. We commit to coupling these physical simulators with (Auto)ML solutions towards a physics-aware AI. Specifically, in precision farming, we design a smart irrigation platform that: allows real-time monitoring of soil moisture, predicts future moisture values, and estimates water demand to schedule the irrigation.

Study of risky situations using experimental data coming from an instrumented bicycle

The aim of this master’s thesis is to study the risky situations of the cyclist when they interact with road infrastructure and other road users as well as the influence of speed on safety. This research activity is linked with the SAFERUP (Sustainable, Accessible, Resilient, and Smart Urban Pavement) European funded project where one of the doctoral candidate has performed experiments on the bicycle simulation at the Gustave Eiffel university in the PICS-L laboratory (Paris) and instrumented bicycle at the Stockholm (Sweden). The approach of the experiment was to hire a number of people who have participated in the riding of the Instrumented bicycle (Stockholm) and bicycle simulator (PICS-L) which were developed by attaching different sensors and devices to measure important parameters of the bicycle riding and their data was collected to analysis in order to understand the behavior of the cyclist to improve the safety. In addition, a mobile eye tracker wore by participants to record the real experiment scenario, and after the end of the trip, each participant shared their remarks regarding their experience of bicycle riding according to different portions of the road infrastructure. In this research main focus is to analyze the relevant data such as speed profiles, video recordings and questionnaire surveys from the instrumented bicycle experiment. In fact, critical situations, where there was a higher probability, were compared with the subjective evaluation of the participant to be conscious of the issues related to the safety and comfort of the cyclist in different road characteristics.