The influence of the exposome on major health conditions like cardiovascular disease (CVD) is widely recognized. However, integrating diverse exposome factors into predictive models for personalized health assessments remains a challenge due to the complexity and variability of environmental exposures and lifestyle factors. A machine learning (ML) model designed for predicting CVD risk is introduced in this study, relying on easily accessible exposome factors. This approach is particularly novel as it prioritizes non-clinical, modifiable exposures, making it applicable for broad public health screening and personalized risk assessments. Assessments were conducted using both internal and external validation groups from a multi-center cohort, comprising 3,237 individuals diagnosed with CVD in South Korea within twelve years of their baseline visit, along with an equal number of participants without these conditions as a control group. Examination of 109 exposome variables from participants' baseline visits spanned physical measures, environmental factors, lifestyle choices, mental health events, and early-life factors. For risk prediction, the Random Forest classifier was employed, with performance compared to an integrative ML model using clinical and physical variables. Furthermore, data preprocessing involved normalization and handling of missing values to enhance model accuracy. The model's decision-making process were using an advanced explainability method. Results indicated comparable performance between the exposome-based ML model and the integrative model, achieving AUC of 0.82(+/-)0.01, 0.70(+/-)0.01, and 0.73(+/-)0.01. The study underscores the potential of leveraging exposome data for early intervention strategies. Additionally, exposome factors significant in identifying CVD risk were pinpointed, including daytime naps, completed full-time education, past tobacco smoking, frequency of tiredness/unenthusiasm, and current work status. © 2024 The Author(s)

This paper investigates the effects of various randomization techniques on Deep Neural Networks (DNNs) learning performance. We categorize the existing randomness techniques into four key types: injection of noise/randomness at the data, model structure, optimization or learning stage. We use this classification to identify gaps in the current coverage of potential mechanisms for the introduction of randomness, leading to proposing two new techniques: adding noise to the loss function and random masking of the gradient updates. We use a Particle Swarm Optimizer (PSO) for hyperparameter optimization and evaluate over 30,000 configurations across standard computer vision benchmarks. Our study reveals that data augmentation and weight initialization randomness significantly improve performance, and different optimizers prefer distinct randomization types. The complete implementation and dataset are available on GitHub1. This paper for the Hot-off-the-Press track at GECCO 2024 summarizes the original work published at [2]. © 2024 Copyright held by the owner/author(s).

[2] Mohammed Ghaith Altarabichi, Sławomir Nowaczyk, Sepideh Pashami, Peyman Sheikholharam Mashhadi, and Julia Handl. 2024. Rolling the dice for better deep learning performance: A study of randomness techniques in deep neural networks. Information Sciences 667 (2024), 120500.

In the rapidly evolving field of AI, Explainable Artificial Intelligence (XAI) has become paramount, particularly in Intelligent Environments applications. It offers clarity and understanding in complex decision-making processes, fostering trust and enabling rigorous scrutiny. The Shapley value, renowned for its accurate quantification of feature importance, has emerged as a prevalent standard in both academic research and practical application. Nevertheless, the Shapley value's reliance on the calculation of all possible coalitions poses a significant computational challenge, as it falls within the class of NP-hard problems. Consequently, approximation techniques are employed in most practical scenarios as a substitute for precise computations. The most common of those is the SHAP (SHapley Additive exPlanations) technique, which quantifies the influence exerted by a specific feature on decision outcomes of a specific Machine Learning model. However, the Shapley value's theoretical underpinnings focus on assessing and understanding feature impact on model evaluation metrics, rather than just alterations in the responses. This paper conducts a comparative analysis using controlled synthetic data with established ground truths. It juxtaposes the practical implementation of the SHAP approach with the theoretical model in two distinct scenarios: one using the F1-score and the other, the accuracy metric. These are two representative characteristic functions, capturing different aspects and whose appropriateness depends on the specific requirements and context of the task to be solved. We analyze how the three alternatives exhibit similarity and disparity in their manifestation of feature effects. We explore the parallels and differences between these approaches in reflecting feature effects. Ultimately, our research seeks to determine the conditions under which SHAP outcomes are more aligned with either the F1-score or the accuracy metric, thereby providing valuable insights for their application in various Intelligent Environment contexts. © 2024 IEEE.

Contextual anomaly detection aims to identify objects that are anomalous only within specific contexts, while appearing normal otherwise. However, most existing methods are limited to a single context defined by user-specified features. In practice, identifying the right context is not trivial, even for domain experts. Moreover, for high-dimensional data, the notion of meaningful contexts that can unveil anomalies becomes substantially more complex. For instance, multiple useful contexts can often capture different phenomena. In this work, we introduce ConQuest, a new unsupervised contextual anomaly detection approach that automatically discovers and incorporates multiple contexts useful for detecting and interpreting anomalies. Through experiments on 25 datasets, we show that ConQuest outperforms various state-of-the-art methods. We also demonstrate its benefits in terms of increased direct interpretability. © The Author(s) 2024.

The purpose of the study is to demonstrate the feasibility of combining traffic simulator technology with machine learning (ML) methods to create realistic and comprehensive synthetic traffic data. Synthetic data alleviates many ethical and privacy concerns, significantly reduces the costs associated with data collection, and enables researchers to study scenarios and conditions that are difficult or impossible to replicate in real-world environments. Access to large amounts of diverse and controlled data is essential for developing and testing artificial intelligence (AI) models and leads to more reliable and robust results. Traffic simulators like SUMO have been successfully used for that purpose in the past, creating realistic vehicular traces. One drawback is that, without coupling them with complex physics emulators, they are not capable of generating internal vehicle parameters. Such parameters, on the other hand, are crucial for many purposes, from understanding energy efficiency and optimizing driver behavior to predictive maintenance and monitoring the degradation of key components, such as driveline batteries. In this paper, we propose Synthetic Traffic Data Generator (STDG) and demonstrate that an ML model that is trained on the internal parameters of a vehicle in one set of conditions (Sweden) can be used to generate synthetic data corresponding to another setting (Monaco). The proposed method promises to eliminate the need for an expensive collection of the original vehicle parameters across many different settings. Moreover, sharing the synthetic data with additional stakeholders is easier due to the reduced security and integrity risk of exposing the vehicle’s privacy-sensitive original parameters. This study compares several ML techniques, including deep learning (DL) based, for generating internal parameters of vehicles, such as fuel rate, engine speed, and wet tank air pressure. Using the actual bus data from a small city to train our ML models, we attempt to forecast the internal parameters of the buses in various scenarios. The proposed method first utilizes SUMO to generate synthetic waypoints for the bus and then predicts the other parameters using the trained model, thereby producing synthetic data with internal parameters for buses operating in a new urban environment. Our preliminary results indicated that our model is performing well within a 90% confidence interval. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

One of the most widely adopted approaches for eXplainable Artificial Intelligence (XAI) involves employing of Shapley values (SVs) to determine the relative importance of input features. While based on a solid mathematical foundation derived from cooperative game theory, SVs have a significant drawback: high computational cost. Calculating the exact SV is an NP-hard problem, necessitating the use of approximations, particularly when dealing with more than twenty features. On the other hand, determining SVs for all features is seldom necessary in practice; users are primarily interested in the most important ones only. This paper introduces the Economic Hierarchical Shapley values (ecoShap) method for calculating SVs for the most crucial features only, with reduced computational cost. EcoShap iteratively expands disjoint groups of features in a tree-like manner, avoiding the expensive computations for the majority of less important features. Our experimental results across eight datasets demonstrate that the proposed technique efficiently identifies top features; at a 50% reduction in computational costs, it can determine between three and seven of the most important features. © The Author(s) 2024.

In an era where visual communication is important, understanding the key components that make climate change videos effective is essential for improving awareness and driving meaningful actions. This research presents an overview of YouTube’s educational content on climate change, aiming to identify elements that contribute to the effectiveness of these videos. We used a questionnaire targeting bachelor’s and master’s students to learn about their preferences regarding the available videos and their beliefs concerning the use of YouTube as an educational platform. A curated list of videos was used to explore how students perceive their influence on personal interest and engagement in climate change. Accordingly, each student watched three videos related to climate change and provided information concerning their impressions. By reviewing various attributes of the videos related to climate change, such as the content structure, engagement, and similar, we extracted the essential characteristics that are associated with more positive reactions to these videos as significant educational tools.

Urbanization is rapidly shaping our world, with more people than ever residing in cities. While cities offer numerous opportunities and conveniences, they also face critical challenges, including air pollution. Addressing these challenges is vital for creating healthier and more liveable urban environments. A transformative solution emerges, bridging the gap between sustainable urban mobility and air quality control through cutting-edge data-driven strategies. Finding a balance between efficient urban living and environmental stewardship is a pressing concern for cities worldwide. In envisioning a future where urban commuting becomes synonymous with eco-friendliness and air quality improvement, a comprehensive platform harnesses the power of data analytics and real-time information to empower commuters and city planners alike. Its intelligent algorithms continuously analyse air quality information, allowing it to predict and address poor air quality. This platform seamlessly integrates with existing urban infrastructure, making it accessible to commuters through user-friendly mobile applications and web interfaces. Commuters can receive personalized recommendations for eco-friendly commuting options. One standout feature is its ability to forecast air quality in urban areas, enabling users to make informed decisions that prioritize their health and environmental sustainability. Encouraging a sense of community among eco-conscious urban residents, it incentivizes sustainable behaviours and offers rewards for reducing emissions. By collecting data on commuting choices and air quality conditions, the platform contributes valuable insights to city authorities for urban planning and pollution control. Representing a paradigm shift in urban living, it aligns individual choices with broader sustainability and air quality goals. It is a testament to the power of technology, data, and community engagement in building smarter, greener, and healthier cities. The proposed approach presents the significance of the system as a transformative solution for sustainable urban living and air quality control, emphasizing the use of cutting-edge technology, data-driven insights, and community engagement to address pressing urban challenges. © 2024 The Authors.

Accurate energy consumption prediction is crucial for optimising the operation of electric commercial heavy-duty vehicles, particularly for efficient route planning, refining charging strategies, and ensuring optimal truck configuration for specific tasks. This study investigates the application of multi-task curriculum learning to enhance machine learning models for forecasting the energy consumption of various onboard systems in electric vehicles. Multi-task learning, unlike traditional training approaches, leverages auxiliary tasks to provide additional training signals, which has been shown to enhance predictive performance in many domains. By further incorporating curriculum learning, where simpler tasks are learned before progressing to more complex ones, neural network training becomes more efficient and effective. We evaluate the suitability of these methodologies in the context of electric vehicle energy forecasting, examining whether the combination of multi-task learning and curriculum learning enhances algorithm generalisation, even with limited training data. We primarily focus on understanding the efficacy of different curriculum learning strategies, including sequential learning and progressive continual learning, using complex, real-world industrial data. Our research further explores a set of auxiliary tasks designed to facilitate the learning process by targeting key consumption characteristics projected into future time frames. The findings illustrate the potential of multi-task curriculum learning to advance energy consumption forecasting, significantly contributing to the optimisation of electric heavy-duty vehicle operations. This work offers a novel perspective on integrating advanced machine learning techniques to enhance energy efficiency in the exciting field of electromobility. © 2024 Copyright for this paper by its authors.

Explainable Artificial Intelligence (XAI) is crucial in ensuring transparency, accountability, and trust in machine learning models, especially in applications involving high-stakes decision-making. This paper focuses on addressing the research gap in federated learning (FL), specifically emphasizing the use of inherently interpretable underlying models. While most FL frameworks rely on complex, black-box models such as Artificial Neural Networks (ANNs), we propose using Decision Tree (DT) classifiers to maintain explainability. More specifically, we introduce a novel framework for horizontal federated learning using Extremely Fast Decision Trees (EFDTs) with streaming data on the client side. Our approach involves aggregating clients' EFDTs on the server side without centralizing raw data, and the training process occurs on the clients' sides. We outline three aggregation strategies and demonstrate that our methods outperform local models and achieve performance levels close to centralized models while retaining inherent explainability. © 2024 CEUR-WS. All rights reserved.