| 1. |
- Giaretta, Alberto, 1988-
(författare)
-
Securing the Internet of Things with Security-by-Contract
- 2021
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Smart homes, industry, healthcare, robotics; virtually every market has seen the uprising of Internet of Things (IoT) devices with different degrees and nuances. IoT devices embody different desirable characteristics, such as mobility, ubiquity, variety, and affordability. All combined, these features made so that IoT devices reached 35 billion units in the world. However, the sudden uprising of market demand put enormous pressure on manufacturers. The necessity of delivering to customers as many devices as possible, in the shortest time possible, leads manufacturers to overlook features that are not perceived critical by the users, such as resiliency to cyberattacks. This led to severe security issues. The prime example is Mirai, a malware that infected hundreds of thousands of IoT devices in 2016 and used them to strike lethal Distributed Denial of Service (DDoS) attacks.In the first part of this thesis, we present the state of the art regarding IoT devices security resilience. In particular, we provide relevant examples of breaches, an analysis of the relationship between IoT and Cloud from a security point of view, and an example of an IoT device penetration test. Then, we focus on the usage of IoT devices in DDoS-enabled botnets and we provide an extensive study of DDoS-enabling malwares, discussing their evolution and their capabilities.In the second part, we contextualise the gathered knowledge and we show that the highlighted problems stem from two main causes: insecure configurations and insufficient secure configurability.We also show that, to address these two issues, it is necessary to equip IoT devices with precise and formal descriptions of their behaviour. Therefore, we propose SC4IoT, a security framework for IoT devices that combines Security-by-Contract (SC) paradigm and Fog Computing paradigm. First, we provide a thorough breakdown of our proposal. We start from high-level lifecycles that describe how devices participate to SC4IoT. Then, we discuss the pillars that compose the framework (e.g., security contracts and security policies), together with their formal descriptions. Last, we provide precise algorithms for achieving security-policy matching capabilities, as well as routines for allowing the framework to deal with dynamic changes while maintaining consistency.
|
|
| 2. |
- Asadi, Sahar, 1983-
(författare)
-
Towards Dense Air Quality Monitoring : Time-Dependent Statistical Gas Distribution Modelling and Sensor Planning
- 2017
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis addresses the problem of gas distribution modelling for gas monitoring and gas detection. The presented research is particularly focused on the methods that are suitable for uncontrolled environments. In such environments, gas source locations and the physical properties of the environment, such as humidity and temperature may be unknown or only sparse noisy local measurements are available. Example applications include air pollution monitoring, leakage detection, and search and rescue operations.This thesis addresses how to efficiently obtain and compute predictive models that accurately represent spatio-temporal gas distribution.Most statistical gas distribution modelling methods assume that gas dispersion can be modelled as a time-constant random process. While this assumption may hold in some situations, it is necessary to model variations over time in order to enable applications of gas distribution modelling for a wider range of realistic scenarios.This thesis proposes two time-dependent gas distribution modelling methods. In the first method, a temporal (sub-)sampling strategy is introduced. In the second method, a time-dependent gas distribution modelling approach is presented, which introduces a recency weight that relates measurement to prediction time. These contributions are presented and evaluated as an extension of a previously proposed method called Kernel DM+V using several simulation and real-world experiments. The results of comparing the proposed time-dependent gas distribution modelling approaches to the time-independent version Kernel DM+V indicate a consistent improvement in the prediction of unseen measurements, particularly in dynamic scenarios under the condition that there is a sufficient spatial coverage. Dynamic scenarios are often defined as environments where strong fluctuations and gas plume development are present.For mobile robot olfaction, we are interested in sampling strategies that provide accurate gas distribution models given a small number of samples in a limited time span. Correspondingly, this thesis addresses the problem of selecting the most informative locations to acquire the next samples.As a further contribution, this thesis proposes a novel adaptive sensor planning method. This method is based on a modified artificial potential field, which selects the next sampling location based on the currently predicted gas distribution and the spatial distribution of previously collected samples. In particular, three objectives are used that direct the sensor towards areas of (1) high predictive mean and (2) high predictive variance, while (3) maximising the coverage area. The relative weight of these objectives corresponds to a trade-off between exploration and exploitation in the sampling strategy. This thesis discusses the weights or importance factors and evaluates the performance of the proposed sampling strategy. The results of the simulation experiments indicate an improved quality of the gas distribution models when using the proposed sensor planning method compared to commonly used methods, such as random sampling and sampling along a predefined sweeping trajectory. In this thesis, we show that applying a locality constraint on the proposed sampling method decreases the travelling distance, which makes the proposed sensor planning approach suitable for real-world applications where limited resources and time are available. As a real-world use-case, we applied the proposed sensor planning approach on a micro-drone in outdoor experiments.Finally, this thesis discusses the potential of using gas distribution modelling and sensor planning in large-scale outdoor real-world applications. We integrated the proposed methods in a framework for decision-making in hazardous inncidents where gas leakage is involved and applied the gas distribution modelling in two real-world use-cases. Our investigation indicates that the proposed sensor planning and gas distribution modelling approaches can be used to inform experts both about the gas plume and the distribution of gas in order to improve the assessment of an incident.
|
|
| 3. |
- Dandan, Kinan, 1976-
(författare)
-
Enabling Surface Cleaning Robot for Large Food Silo
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Working conditions in the dry cleaning and sanitation of confined interior spaces are often extreme, and workers need overall protection with tight clothing, helmets, face mask, earmuffs, and respirators. The environment is dirty, noisy with bad visibility and heavy with a high static work load. Dry cleaning is mainly practised in silos for grain, foodstuff and flour, etc. The inside of the silo is a hazardous environment due to many factors such as an unsafe oxygen level, engulfment, biological, mechanical, electrical, and atmospheric hazards. The requirements of the EU norms related to hygiene and food quality indicate that silos should be cleaned frequently and cleaning is obligatory after a silo is totally emptied. Therefore, there is an increased societal need for silo cleaning and a natural necessity to replace humans by robot manipulators in executing this risky and dangerous job.This thesis presents a new concept of a flexible crawling mechanism for an industrial food cleaning robot, which is evaluated from the viewpoint of the capability to work inside a large food silo, scanning the desired surface, and performing the cleaning task. The main research questions investigated in this thesis are about: how to select the most important characteristics in designing a robot to fulfil the surface cleaning operation of a large confined space; how the crawling movement affects the dynamic behaviour of the robot mechanism; how the cleaning process affects the dynamic behaviour of the robot mechanism; how to develop the control of the robot to realize the locomotion and the cleaning process.The structure of the robot and the cleaning technology are well defined after an overview of the existing technologies and solutions for cleaning large confined spaces. The robot design is based on a suspension and crawling system, using minimal actuators, where the force of gravity is well used to simplify the control system and to stabilise the robot. Further, the static and dynamic analysis of the mechanical system is studied. In addition, the control architecture of the system is performed, where the required sensors and control algorithm are given. A scale model testing has also been used to verify the locomotion of the concept, while simple controllers and algorithms are used to manage the motions of the prototype.
|
|
| 4. |
- Landin, Cristina, 1984-
(författare)
-
AI-Based Methods For Improved Testing of Radio Base Stations : A Case Study Towards Intelligent Manufacturing
- 2023
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Testing of complex systems may often require the use of tailored-made solutions, expensive testing equipment, large computing capacity, and manual implementation work due to domain uniqueness. The aforementioned test resources are expensive and time-consuming, which makes them good candidates to optimize. A radio base station (RBS) is a complex system. Upon the arrival of new RBS generations, new testing challenges have been introduced that traditional methods cannot cope with. In order to optimize the test process of RBSs, product quality and production efficiency can be studied.Despite that AI techniques are valuable tools for monitoring behavioral changes in various applications, there have not been sufficient research efforts spent on the use of intelligent manufacturing in already existing factories and production lines. The concept of intelligent manufacturing involves the whole system development life-cycle, such as design, production, and maintenance. Available literature about optimization and integration of industrial applications using AI techniques has not resulted in common solutions due to the complexity of the real-world applications, which have their own unique characteristics, e.g., multivariate, non-linear, non-stationary, multi-modal, class imbalance; making it challenging to find generalizable solutions. This licentiate thesis aims to bridge the gap between theoretical approaches and the implementation of real industrial applications. In this licentiate thesis, two questions are explored, namely how well AI techniques can perform and optimize fault detection and fault prediction on the production of RBSs, as well as how to modify learning algorithms in order to perform transfer learning between different products. These questions are addressed by using different AI techniques for test optimization purposes and are examined in three empirical studies focused on parallel test execution, fault detection and prediction, and automated fault localization. For the parallel test execution study, two different approaches were used to find and cluster semantically similar test cases and propose their execution in parallel. For this purpose, Levenshstein distance and two NLP techniques are compared. The results show that cluster-based test scenarios can be automatically generated from requirement specifications and the execution of semantically similar tests can reduce the number of tests by 95\% in the study case if executed in parallel. Study number two investigates the possibility of predicting testing performance outcomes by analyzing anomalies in the test process and classifying them by their compliance with dynamic test limits instead of fixed limits. The performance measures can be modeled using historical data through regression techniques and the classification of the anomalies is learned using support vector machines and convolutional neural networks. The results show good agreement between the actual and predicted learned model, where the root-mean-square error reaches 0.00073. Furthermore, this approach can automatically label the incoming tests according to the dynamic limits, making it possible to predict errors in an early stage of the process. This study contributes to product quality by monitoring the test measurements beyond fixed limits and contributes to making a more efficient testing process by detecting faults before they are measured. Moreover, study two considers the possibility of using transfer learning due to an insufficient number of anomalies in a single product. The last study focuses on root cause analysis by analyzing test dependencies between test measurements using two known correlation-based methods and mutual information to find strength associations between measurements. The contributions of this study are twofold. First, test dependencies between measurements can be found using Pearson and Spearman correlation and MI; and their dependencies can be linear or higher order. Second, by clustering the associated tests, redundant tests are found, which could be used to update the test execution sequence and choose to execute only the relevant tests, hence, making a more efficient production process by saving test time.
|
|
| 5. |
- Persson, Andreas, 1980-
(författare)
-
Studies in Semantic Modeling of Real-World Objects using Perceptual Anchoring
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Autonomous agents, situated in real-world scenarios, need to maintain consonance between the perceived world (through sensory capabilities) and their internal representation of the world in the form of symbolic knowledge. An approach for modeling such representations of objects is through the concept of perceptual anchoring, which, by definition, handles the problem of creating and maintaining, in time and space, the correspondence between symbols and sensor data that refer to the same physical object in the external world.The work presented in this thesis leverages notations found within perceptual anchoring to address the problem of real-world semantic world modeling, emphasizing, in particular, sensor-driven bottom-up acquisition of perceptual data. The proposed method for handling the attribute values that constitute the perceptual signature of an object is to first integrate and explore available resources of information, such as a Convolutional Neural Network (CNN) to classify objects on the perceptual level. In addition, a novel anchoring matching function is proposed. This function introduces both the theoretical procedure for comparing attribute values, as well as establishes the use of a learned model that approximates the anchoring matching problem. To verify the proposed method, an evaluation using human judgment to collect annotated ground truth data of real-world objects is further presented. The collected data is subsequently used to train and validate different classification algorithms, in order to learn how to correctly anchor objects, and thereby learn to invoke correct anchoring functionality.There are, however, situations that are difficult to handle purely from the perspective of perceptual anchoring, e.g., situations where an object is moved during occlusion. In the absence of perceptual observations, it is necessary to couple the anchoring procedure with probabilistic object tracking to speculate about occluded objects, and hence, maintain a consistent world model. Motivated by the limitation in the original anchoring definition, which prohibited the modeling of the history of an object, an extension to the anchoring definition is also presented. This extension permits the historical trace of an anchored object to be maintained and used for the purpose of learning additional properties of an object, e.g., learning of the action applied to an object.
|
|
| 6. |
- Akalin, Neziha, 1988-
(författare)
-
Perceived Safety in Social Human-Robot Interaction
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This compilation thesis contributes to a deeper understanding of perceived safety in human-robot interaction (HRI) with a particular focus on social robots. The current understanding of safety in HRI is mostly limited to physical safety, whereas perceived safety has often been neglected and underestimated. However, safe HRI requires a conceptualization of safety that goes beyond physical safety covering also perceived safety of the users. Within this context, this thesis provides a comprehensive analysis of perceived safety in HRI with social robots, considering a diverse set of human-related and robot-related factors.Two particular challenges for providing perceived safety in HRI are 1) understanding and evaluating human safety perception through direct and indirect measures, and 2) utilizing the measured level of perceived safety for adapting the robot behaviors. The primary contribution of this dissertation is in addressing the first challenge. The thesis investigates perceived safety in HRI by alternating between conducting user studies, literature review, and testing the findings from the literature within user studies.In this thesis, six main factors influencing perceived safety in HRI are lifted: the context of robot use, the user’s comfort, experience and familiarity with robots, trust, sense of control over the interaction, and transparent and predictable robot behaviors. These factors could provide a common understanding of perceived safety and bridge the theoretical gap in the literature. Moreover, this thesis proposes an experimental paradigm to observe and quantify perceived safety using objective and subjective measures. This contributes to bridging the methodological gap in the literature.The six factors are reviewed in HRI literature, and the robot features that affect these factors are organized in a taxonomy. Although this taxonomy focuses on social robots, the identified characteristics are relevant to other types of robots and autonomous systems. In addition to the taxonomy, the thesis provides a set of guidelines for providing perceived safety in social HRI. As a secondary contribution, the thesis presents an overview of reinforcement learning applications in social robotics as a suitable learning mechanism for adapting the robots’ behaviors to mitigate psychological harm.
|
|
| 7. |
- Banaee, Hadi, 1986-
(författare)
-
From Numerical Sensor Data to Semantic Representations : A Data-driven Approach for Generating Linguistic Descriptions
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- In our daily lives, sensors recordings are becoming more and more ubiquitous. With the increased availability of data comes the increased need of systems that can represent the data in human interpretable concepts. In order to describe unknown observations in natural language, an artificial intelligence system must deal with several issues involving perception, concept formation, and linguistic description. These issues cover various subfields within artificial intelligence, such as machine learning, cognitive science, and natural language generation.The aim of this thesis is to address the problem of semantically modelling and describing numerical observations from sensor data. This thesis introduces data-driven approaches to perform the tasks of mining numerical data and creating semantic representations of the derived information in order to describe unseen but interesting observations in natural language.The research considers creating a semantic representation using the theory of conceptual spaces. In particular, the central contribution of this thesis is to present a data-driven approach that automatically constructs conceptual spaces from labelled numerical data sets. This constructed conceptual space then utilises semantic inference techniques to derive linguistic interpretations for novel unknown observations. Another contribution of this thesis is to explore an instantiation of the proposed approach in a real-world application. Specifically, this research investigates a case study where the proposed approach is used to describe unknown time series patterns that emerge from physiological sensor data. This instantiation first presents automatic data analysis methods to extract time series patterns and temporal rules from multiple channels of physiological sensor data, and then applies various linguistic description approaches (including the proposed semantic representation based on conceptual spaces) to generate human-readable natural language descriptions for such time series patterns and temporal rules.The main outcome of this thesis is the use of data-driven strategies that enable the system to reveal and explain aspects of sensor data which may otherwise be difficult to capture by knowledge-driven techniques alone. Briefly put, the thesis aims to automate the process whereby unknown observations of data can be 1) numerically analysed, 2) semantically represented, and eventually 3) linguistically described.
|
|
| 8. |
- Can, Ozan Arkan, et al.
(författare)
-
Learning from Implicit Information in Natural Language Instructions for Robotic Manipulations
- 2019
-
Ingår i: Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP). - : Association for Computational Linguistics. ; , s. 29-39
-
Konferensbidrag (refereegranskat)abstract
- Human-robot interaction often occurs in the form of instructions given from a human to a robot. For a robot to successfully follow instructions, a common representation of the world and objects in it should be shared between humans and the robot so that the instructions can be grounded. Achieving this representation can be done via learning, where both the world representation and the language grounding are learned simultaneously. However, in robotics this can be a difficult task due to the cost and scarcity of data. In this paper, we tackle the problem by separately learning the world representation of the robot and the language grounding. While this approach can address the challenges in getting sufficient data, it may give rise to inconsistencies between both learned components. Therefore, we further propose Bayesian learning to resolve such inconsistencies between the natural language grounding and a robot’s world representation by exploiting spatio-relational information that is implicitly present in instructions given by a human. Moreover, we demonstrate the feasibility of our approach on a scenario involving a robotic arm in the physical world.
|
|
