The advances in Internet of things lead to an increased number of devices generating and streaming data. These devices can be useful data sources for activity recognition by using machine learning. However, the set of available sensors may vary over time, e.g. due to mobility of the sensors and technical failures. Since the machine learning model uses the data streams from the sensors as input, it must be able to handle a varying number of input variables, i.e. that the feature space might change over time. Moreover, the labelled data necessary for the training is often costly to acquire. In active learning, the model is given a budget for requesting labels from an oracle, and aims to maximize accuracy by careful selection of what data instances to label. It is generally assumed that the role of the oracle only is to respond to queries and that it will always do so. In many real-world scenarios however, the oracle is a human user and the assumptions are simplifications that might not give a proper depiction of the setting. In this work we investigate different interactive machine learning strategies, out of which active learning is one, which explore the effects of an oracle that can be more proactive and factors that might influence a user to provide or withhold labels. We implement five interactive machine learning strategies as well as hybrid versions of them and evaluate them on two datasets. The results show that a more proactive user can improve the performance, especially when the user is influenced by the accuracy of earlier predictions. The experiments also highlight challenges related to evaluating performance when the set of classes is changing over time.

The objective of this study is to provide a better understanding of the potential of using Artificial Intelligence (AI) to improve Public Transport (PT), by reviewing research literature. The selection process resulted in 87 scientific publications constituting a sample of how AI has been applied to improve PT. The review shows that the primary aims of using AI are to improve the service quality or to better understand traveller behaviour. Train and bus are the dominant modes of transport investigated. Furthermore, AI is mainly used for three tasks; the most frequent one is prediction, followed by an estimation of the current state, and resource allocation, including planning and scheduling. Only two studies concern automation; all the others provide different kinds of decision support for travellers, PT operators, PT planners, or municipalities. Most of the reviewed AI solutions require significant amounts of data related to the travellers and the PT system. Machine learning is the most frequently used AI technology, with some studies applying reasoning or heuristic search techniques. We conclude that there still remains a great potential of using AI to improve PT waiting to be explored, but that there are also some challenges that need to be considered. They are often related to data, e.g., that large datasets of high quality are needed, that substantial resources and time are needed to pre-process the data, or that the data compromise personal privacy. Further research is needed about how to handle these issues efficiently.

Proper modeling of human behavior is crucial when developing agent-based models to investigate the effects of policies, such as the potential consequences of interventions during a pandemic. It is, however, unclear, how sophisticated behavior models need to be for being considered suitable to support policy making. The goal of this paper is to identify recommendations on how human behavior should be modeled in Agent-Based Social Simulation (ABSS) as well as to investigate to what extent these recommendations are actually followed by models explicitly developed for policy making. By analyzing the literature, we identify seven relevant aspects of human behavior for consideration in ABSS. Based on these aspects, we review how human behavior is modeled in ABSS of COVID-19 interventions, in order to investigate the capabilities and limitations of these models to provide policy advice. We focus on models that were published within six months of the start of the pandemic as this is when policy makers needed the support provided by ABSS the most. It was found that most models did not include the majority of the identified relevant aspects, in particular norm compliance, agent deliberation, and interventions’ affective effects on individuals. We argue that ABSS models need a higher level of descriptiveness than what is present in most of the studied early COVID-19 models to support policymaker decisions. 

This article provides an overview of recent research on edge-cloud architectures in hybrid energy management systems (HEMSs). It delves into the typical structure of an IoT system, consisting of three key layers: the perception layer, the network layer, and the application layer. The edge-cloud architecture adds two more layers: the middleware layer and the business layer. This article also addresses challenges in the proposed architecture, including standardization, scalability, security, privacy, regulatory compliance, and infrastructure maintenance. Privacy concerns can hinder the adoption of HEMS. Therefore, we also provide an overview of these concerns and recent research on edge-cloud solutions for HEMS that addresses them. This article concludes by discussing the future trends of edge-cloud architectures for HEMS. These trends include increased use of artificial intelligence on an edge level to improve the performance and reliability of HEMS and the use of blockchain to improve the security and privacy of edge-cloud computing systems.

The research delves into intelligent hybrid heat management Systems, exploring the challenges faced and solutions for enhancing efficiency. Hybrid heating systems are complex cyber-technical systems that combine city heating networks with renewable energy sources, such as heat pumps and solar panels. Traditional heating systems often lack adaptability to internal and external conditions, leading to suboptimal performance and user expectations. This paper proposes a new approach by integrating smart technologies, the Internet of Things, Artificial Intelligence, Machine Learning, optimization techniques, and trade-offs into the management of hybrid heat systems. The emphasis is also placed on the fact that the introduction of smart technologies makes it possible to make hybrid heating systems human-oriented and meet individual needs. Energy efficiency improvement is achievable by combining solutions, such as actual forecasting, with intelligent management that adapts to changing climates and user behaviors. The challenges addressed include inadequate responsiveness to load changes, inaccurate heat consumption forecasting, and inefficient data management. The paper emphasizes the need for intelligent systems that comply with the current standards, providing cost optimization, socializing and ensuring resilience, customer orientation, reliability, safety, and trustworthiness. This exploration of intelligent hybrid heat management systems seeks to overcome existing challenges and pave the way for a sustainable, digitally optimized future in district heating systems.

Although smart homes are tasked with an increasing number of everyday activities to keep users safe, healthy, and entertained, privacy concerns arise due to the large amount of personal data in flux. Privacy is widely acknowledged to be contextually dependent, however, the interrelated stakeholders involved in developing and delivering smart home services – IoT developers, companies, users, and lawmakers, to name a few – might approach the smart home context differently. This paper considers smart homes as digital ecosystems to support a contextual analysis of smart home privacy. A conceptual model and an ecosystem ontology are proposed through design science research methodology to systematize the analyses. Four privacy-oriented scenarios of surveillance in smart homes are discussed to demonstrate the utility of the digital ecosystem approach. The concerns pertain to power dynamics among users such as main users, smart home bystanders, parent-child dynamics, and intimate partner relationships and the responsibility of both companies and public organizations to ensure privacy and the ethical use of IoT devices over time. Continuous evaluation of the approach is encouraged to support the complex challenge of ensuring user privacy in smart homes.

This paper delves into the challenges encountered in decision-making processes within Hybrid Energy Systems (HES), placing a particular emphasis on the critical aspect of data integration. Decision-making processes in HES are inherently complex due to the diverse range of tasks involved in their management. We argue that to overcome these challenges, it is imperative to possess a comprehensive understanding of the HES architecture and how different processes and interaction layers synergistically operate to achieve the desired outcomes. These decision-making processes encompass a wealth of information and insights pertaining to the operation and performance of HES. Furthermore, these processes encompass systems for planning and management that facilitate decisions by providing a centralized platform for data collection, storage, and analysis. The success of HES largely hinges upon its capacity to receive and integrate various types of information. This includes real-time data on energy demand and supply, weather data, performance data derived from different system components, and historical data, all of which contribute to informed decision-making. The ability to accurately integrate and fuse this diverse range of data sources empowers HES to make intelligent decisions and accurate predictions. Consequently, this data integration capability allows HES to provide a multitude of services to customers. These services include valuable recommendations on demand response strategies, energy usage optimization, energy storage utilization, and much more. By leveraging the integrated data effectively, HES can deliver customized and tailored services to meet the specific needs and preferences of its customers. 

This paper compares machine learning models for short-term heat demand forecasting in residential and multi-family buildings, evaluating model suitability, data impact on accuracy, computation time, and accuracy improvement methods. The findings are relevant for energy suppliers, researchers, and decision-makers in optimizing energy management and improving heat demand forecasting. The included models in the study are k-NN, Polynomial Regression, and LSTM with weather data, building type, and time index as input variables. Single-dimensional models (Autoregression, SARIMA, and Prophet) based on historical consumption are also studied. LSTM consistently outperforms other models in accuracy across different input variable combinations, measured using mean absolute percentage error (MAPE). The incorporation of historical consumption data improved the performance of k-NN and Polynomial Regression models. The paper also explores dataset volume impact on accuracy and compares training and prediction times. k-NN has the least prediction times, Polynomial Regression takes longer, and LSTM requires more time. All models exhibit acceptable prediction times for heat consumption. LSTM outperforms single-dimensional models in accuracy and has lower prediction times compared to AR, SARIMA, and Prophet models.

The integration of the Internet of Things (IoT) and Machine Learning (ML) technologies has opened up for the development of novel types of systems and services. Federated Learning (FL) has enabled the systems to collaboratively train their ML models while preserving the privacy of the data collected by their IoT devices and objects. Several FL frameworks have been developed, however, they do not enable FL in open, distributed, and heterogeneous IoT environments. Specifically, they do not support systems that collect similar data to dynamically discover each other, communicate, and negotiate about the training terms (e.g., accuracy, communication latency, and cost). Towards bridging this gap, we propose ART4FL, an end-to-end framework that enables FL in open IoT settings. The framework enables systems' users to configure agents that participate in FL on their behalf. Those agents negotiate and make commitments (i.e., contractual agreements) to dynamically form federations. To perform FL, the framework deploys the needed services dynamically, monitors the training rounds, and calculates agents' trust scores based on the established commitments. ART4FL exploits a blockchain network to maintain the trust scores, and it provides those scores to negotiating agents' during the federations' formation phase.

Interactive machine learning (ML) adds a human-in-the-loop aspect to a ML system. Even though the input from human users to the system is a central part of the concept, the uncertainty caused by the human feedback is often not considered in interactive ML. The assumption that the human user is expected to always provide correct feedback, typically does not hold in real-world scenarios. This is especially important for when the cognitive workload of the human is high, for instance in online learning from streaming data where there are time constraints for providing the feedback. We present experiments of interactive online ML with human participants, and compare the results to simulated experiments where humans are always correct. We found combining the two interactive learning paradigms, active learning and machine teaching, resulted in better performance compared to machine teaching alone. The results also showed an increased discrepancy between the experiments with human participants and the simulated experiments when the cognitive workload was increased. The findings suggest the importance of taking uncertainty caused by human factors into consideration in interactive ML, especially in situations which requires a high cognitive workload for the human.