Context is an important factor in computer vision as it offers valuable information to clarify and analyze visual data. Utilizing the contextual information inherent in an image or a video can improve the precision and effectiveness of object detectors. For example, where recognizing an isolated object might be challenging, context information can improve comprehension of the scene. This study explores the impact of various context-based approaches to object detection. Initially, we investigate the role of context in object detection and survey it from several perspectives. We then review and discuss the most recent context-based object detection approaches and compare them. Finally, we conclude by addressing research questions and identifying gaps for further studies. More than 265 publications are included in this survey, covering different aspects of context in different categories of object detection, including general object detection, video object detection, small object detection, camouflaged object detection, zero-shot, one-shot, and few-shot object detection. This literature review presents a comprehensive overview of the latest advancements in context-based object detection, providing valuable contributions such as a thorough understanding of contextual information and effective methods for integrating various context types into object detection, thus benefiting researchers.

As the proliferation of Internet of Things (IoT) devices grows, challenges in security, privacy, and interoperability become increasingly significant. IoT devices often have resource constraints, such as limited computational power, energy efficiency, bandwidth, and storage, making it difficult to implement advanced security measures. Additionally, the diversity of IoT devices creates vulnerabilities and threats that attackers can exploit, including spoofing, routing, man-in-the-middle, and denial-of-service. To address these evolving threats, Intrusion Detection Systems (IDSs) have become a vital solution. IDS actively monitors network traffic, analyzing incoming and outgoing data to detect potential security breaches, ensuring IoT systems remain safeguarded against malicious activity. This study introduces an IDS framework that integrates ensemble learning with rule induction for enhanced model explainability. We study the performance of five ensemble algorithms (Random Forest, AdaBoost, XGBoost, LightGBM, and CatBoost) for developing effective IDS for IoT. The results show that XGBoost outperformed the other ensemble algorithms on two publicly available datasets for intrusion detection. XGBoost achieved 99.91% accuracy and 99.88% AUC-ROC on the CIC-IDS2017 dataset, as well as 98.54% accuracy and 93.06% AUC-ROC on the CICIoT2023 dataset, respectively. We integrate model explainability to provide transparent IDS system using a rule induction method. The experimental results confirm the efficacy of the proposed approach for providing a lightweight, transparent, and trustworthy IDS system that supports security analysts, end-users, and different stakeholders when making decisions regarding intrusion and non-intrusion events.

Given the environmental impact and cost-efficiency challenges of the conventional central District Heating (DH) systems, there is a shift towards hybrid solutions. The demand for small-scale Heat Pumps (HPs), integral components of these systems, has surged due to their electrically driven, cost-effective operation, and potential to meet environmental goals. This paper conducts a systematic literature review by investigating and highlighting hybrid heating solutions and their role in decarbonizing the built environment. It compares and discusses the potential benefits and challenges of various hybrid HP-DH systems against conventional DH-only heating approaches. The study evaluates these systems based on economic, environmental, and energy efficiency aspects, and it explores the use of intelligent and AI-based algorithms. The results indicate that, from an economic perspective, the hybrid approach can potentially offer cost savings over the long term, considering factors such as initial investment and operating expenses. The findings of the reviewed works suggest that in a DH-HP configuration, an operational cost saving between 5% and 27%, and a CO2 reduction of up to 32.3% can be achieved without additional resources. Additionally, the environmental impact analysis indicates a significant decrease in greenhouse gas emissions, aligning with global efforts to mitigate global warming.

The Internet of Things (IoT) has transformed our daily life by enabling devices and objects to collect data, communicate, and collaborate to provision novel types of services. Engineering IoT systems is a complex process that should consider a number of quality characteristics to meet the systems’ goals. Towards identifying the key quality characteristics of IoT systems, in this study, we conduct semi-structured interviews with seven companies developing IoT solutions within smart energy, smart healthcare, smart surveillance, and smart buildings application areas. The study used the ISO/IEC 25010 model as a reference and a qualitative research approach, i.e., we conducted semi-structured interviews with ten experts and performed content analysis on the data collected from the interviews. The study findings reveal that the ISO/IEC 25010 model does not include the following key quality characteristics that practitioners consider when engineering IoT systems: trust, privacy, and energy consumption. Additionally, we report about trade-offs between quality characteristics, architectural constraints, and challenges related to the achievement of the identified quality characteristics when engineering IoT systems in practice.

Falls frequently present substantial safety hazards to those who are alone, particularly the elderly. Deploying a rapid and proficient method for detecting falls is a highly effective approach to tackle this concealed peril. The majority of existing fall detection methods rely on either visual data or wearable devices, both of which have drawbacks. This research presents a multimodal approach that integrates video and audio modalities to address the issue of fall detection systems and enhances the accuracy of fall detection in challenging environmental conditions. This multimodal approach, which leverages the benefits of attention mechanism in both video and audio streams, utilizes features from both modalities through feature-level fusion to detect falls in unfavorable conditions where visual systems alone are unable to do so. We assessed the performance of our multimodal fall detection model using Le2i and UP-Fall datasets. Additionally, we compared our findings with other fall detection methods. The outstanding results of our multimodal model indicate its superior performance compared to single fall detection models.

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.

Connected smart homes (CSH) have benefited immensely from emerging Internet of Things (IoT) technology. CSH is intended to support everyday life in the private seclusion of the home, and typically covers the integration of smart devices such as smart meters, heating, ventilation, and air conditioning (HVAC), intelligent lightening, and voice-activated assistants among others. Nevertheless, the risks associated with CSH assets are often of high concern. For instance, energy consumption monitoring through smart meters can reveal sensitive information that may pose a privacy risk to home occupants if not properly managed. Existing risk assessment approaches for CSH tend to focus on qualitative risk assessment methodologies, such as operationally critical threat, asset, and vulnerability evaluation (OCTAVE). However, security risk assessment, particularly for IoT environments, demands both qualitative and quantitative risk assessment. This paper proposes assets-based risk assessment model that integrates both qualitative and quantitative risk assessment to determine the risk related to assets in CSH when a specific service is used. We apply fuzzy Analytic Hierarchy Process (fuzzy AHP) to address the subjective assessment of the IoT risk analysts and stakeholders. The applicability of the proposed model is illustrated through a use case that constitutes a scenario connected to service delivery in CSH. The proposed model provides a guideline to researchers and practitioners on how to quantify the risks targeting assets in CSH.

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.