As the number of Internet of Things (IoT) devices continues to grow, understanding and mitigating potential vulnerabilities and threats is crucial. With IoT devices becoming ubiquitous in critical sectors like healthcare, transportation, energy, and industrial automation, identifying and addressing risks is increasingly important. A comprehensive risk management approach enables IoT stakeholders to safeguard user data and privacy, as well as system integrity. Existing risk assessment frameworks focus on qualitative risk analysis methodologies, such as operationally critical threat, asset, and vulnerability evaluation (OCTAVE). However, security risk assessment, particularly for IoT ecosystem, demands both qualitative and quantitative risk assessment. This paper proposes RAM-IoT, a risk assessment model for IoT-based critical assets that integrates qualitative and quantitative risk assessment approaches. A multi-criteria decision making (MCDM) approach based on fuzzy Analytic Hierarchy Process (fuzzy AHP) is proposed to address the subjective assessment of the IoT risk analysts and their corresponding stakeholders. The applicability of the proposed model is illustrated through a use case connected to service delivery in the IoT. The proposed model provides a guideline to researchers and practitioners on how to quantify the risks targeting assets in IoT, thereby providing adequate support for protecting IoT ecosystems.

Object detection is a critical task in computer vision with applications across various domains, ranging from autonomous driving to surveillance systems. Despite extensive research on improving the performance of object detection systems, identifying all objects in different places remains a challenge. The traditional object detection approaches focus primarily on extracting and analyzing visual features without considering the contextual information about the places of objects. However, entities in many real-world scenarios closely relate to their surrounding environment, providing crucial contextual cues for accurate detection. This study investigates the importance and impact of places of images (indoor and outdoor) on object detection accuracy. To this purpose, we propose an approach that first categorizes images into two distinct categories: indoor and outdoor. We then train and evaluate three object detection models (indoor, outdoor, and general models) based on YOLOv5 and 19 classes of the PASCAL VOC dataset and 79 classes of COCO dataset that consider places. The experimental evaluations show that the specialized indoor and outdoor models have higher mAP (mean Average Precision) to detect objects in specific environments compared to the general model that detects objects found both indoors and outdoors. Indeed, the network can detect objects more accurately in similar places with common characteristics due to semantic relationships between objects and their surroundings, and the network’s misdetection is diminished. All the results were analyzed statistically with t-tests.

Multimodal journey planners are used worldwide to support travelers in planning and executing their journeys. Generated travel plans usually involve local mobility service providers, consider some travelers’ preferences, and provide travelers information about the routes’ current status and expected delays. However, those planners cannot fully consider the special situations of individual cities when providing travel planning services. Specifically, authorities of different cities might define customizable regulations or constraints of movements in the cities (e.g., due to construction works or pandemics). Moreover, with the transformation of traditional cities into smart cities, travel planners could leverage advanced monitoring features. Finally, most planners do not consider relevant information impacting travel plans, for instance, information that might be provided by travelers (e.g., a crowded square) or by mobility service providers (e.g., changing the timetable of a bus). To address the aforementioned shortcomings, in this paper, we propose ROUTE, a framework for customizable smart mobility planners that better serve the needs of travelers, local authorities, and mobility service providers in the dynamic ecosystem of smart cities. ROUTE is composed of an architecture, a process, and a prototype developed to validate the feasibility of the framework. Experiments’ results show that the framework scales well in both centralized and distributed deployment settings.

Interactive Machine Learning (ML) has the potential to lower the manual labelling effort needed, as well as increase classification performance by incorporating a human-in-the loop component. However, the assumptions made regarding the interactive behaviour of the human in experiments are often not realistic. Active learning typically treats the human as a passive, but always correct, participant. Machine teaching provides a more proactive role for the human, but generally assumes that the human is constantly monitoring the learning process. In this paper, we present an interactive online framework and perform experiments to compare active learning, machine teaching and combined approaches. We study not only the classification performance, but also the effort (to label samples) and attention (to monitor the ML system) required of the human. Results from experiments show that a combined approach generally performs better with less effort compared to active learning and machine teaching. With regards to attention, the best performing strategy varied depending on the problem setup.

Engineering Internet of Things (IoT) systems is a challenging task partly due to the dynamicity and uncertainty of the environment including the involvement of the human in the loop. Users should be able to achieve their goals seamlessly in different environments, and IoT systems should be able to cope with dynamic changes. Several approaches have been proposed to enable the automated formation, enactment, and self-adaptation of goal-driven IoT systems. However, they do not address deployment issues. In this paper, we propose a goal-driven approach for deploying self-adaptive IoT systems in the Edge-Cloud continuum. Our approach supports the systems to cope with the dynamicity and uncertainty of the environment including changes in their deployment topologies, i.e., the deployment nodes and their interconnections. We describe the architecture and processes of the approach and the simulations that we conducted to validate its feasibility. The results of the simulations show that the approach scales well when generating and adapting the deployment topologies of goal-driven IoT systems in smart homes and smart buildings.

Deep neural networks for positioning can improve accuracy by adapting to inhomogeneous environments. However, they are still susceptible to noisy data, often resulting in invalid positions. A related task, map matching, can be used for reducing geographical invalid positions by aligning observations to a model of the real world. In this paper, we propose an approach for positioning, enhanced with map matching, within a single deep neural network model. We introduce a novel way of reducing the number of invalid position estimates by adding map information to the input of the model and using a map-based loss function. Evaluating on real-world Received Signal Strength Indicator data from an asset tracking application, we show that our approach gives both increased position accuracy and a decrease of one order of magnitude in the number of invalid positions.

For the provision of efficient and high-quality public transport services in rural areas with a low population density, the introduction of Demand Responsive Transport (DRT) services is reasonable. The optimal design of such services depends on various socio-demographical and environmental factors, which is why the use of simulation is feasible to support planning and decision-making processes. A key challenge for sound simulation results is the generation of realistic demand, i.e., requests for DRT journeys. In this paper, a method for modelling and simulating commuting activities is presented, which is based on statistical real-world data. It is applied to Sjöbo and Tomelilla, two rural municipalities in southern Sweden.

The Internet of Things (IoT) has a great potential to change our lives. Billions of heterogeneous, distributed, intelligent, and sometimes mobile devices, will be connected and offer new types of applications and ways to interact. The dynamic environment of the IoT, the involvement of the human in the loop, and the runtime interactions among devices and applications, put additional requirements on the systems' architecture. In this paper, we use the Emergent Configurations (ECs) concept as a way to engineer IoT systems and propose an architecture for ECs. More specifically, we discuss (i) how connected devices and applications form ECs to achieve users' goals and (ii) how applications are run and adapted in response to runtime context changes including, e.g., the sudden unavailability of devices, by exploiting the Smart Meeting Room case.

The requirements of real-world data mining problems vary extensively. It is plausible to assume that some of these requirements can be expressed as application-specific performance metrics. An algorithm that is designed to maximize performance given a certain learning metric may not produce the best possible result according to these application-specific metrics. We have implemented A Metric-based One Rule Inducer (AMORI), for which it is possible to select the learning metric. We have compared the performance of this algorithm by embedding three different learning metrics (classification accuracy, the F-measure, and the area under the ROC curve), on 19 UCI data sets. In addition, we have compared the results of AMORI with those obtained using an existing rule learning algorithm of similar complexity (One Rule) and a state-of-the-art rule learner (Ripper). The experiments show that a performance gain is achieved, for all included metrics, when using identical metrics for learning and evaluation. We also show that each AMORI/metric combination outperforms One Rule when using identical learning and evaluation metrics. The performance of AMORI is acceptable when compared with Ripper. Overall, the results suggest that metric-based learning is a viable approach.

When evaluating data mining algorithms that are applied to solve real-world problems there are often several, conflicting criteria that need to be considered. We investigate the concept of generic multi-criteria (MC) classifier and algorithm evaluation and perform a comparison of existing methods. This comparison makes explicit some of the important characteristics of MC analysis and focuses on finding out which method is most suitable for further development. Generic MC methods can be described as frameworks for combining evaluation metrics and are generic in the sense that the metrics used are not dictated by the method; the choice of metric is instead dependent on the problem at hand. We discuss some scenarios that benefit from the application of generic MC methods and synthesize what we believe are attractive properties from the reviewed methods into a new method called the candidate evaluation function (CEF). Finally, we present a case study in which we apply CEF to trade-off several criteria when solving a real-world problem.

It is argued that in applications of concept learning from examples where not every possible category of the domain is present in the training set (i.e., many real world applications), classification performance can be improved by integrating suitable discriminative and characteristic models of classification. The suggested approach is to first discriminate between the categories present in the training set and then characterize each of these categories against all possible categories. To show the viability of this approach, a number of different discriminators and characterizers are integrated and tested. In particular, a novel characterization method that makes use of the information about the statistical distribution of feature values that can be extracted from the training examples is used. By using this method it is possible to control the degree of generalization and to deal with dependencies among features.