Desing and Validation of a Light Inference System to Support Embedded Context Reasoning

Embedded context management in resource-constrained devices (e.g. mobile phones, autonomous sensors or smart objects) imposes special requirements in terms of lightness for data modelling and reasoning. In this paper, we explore the state-of-the-art on data representation and reasoning tools for embedded mobile reasoning and propose a light inference system (LIS) aiming at simplifying embedded inference processes offering a set of functionalities to avoid redundancy in context management operations. The system is part of a service-oriented mobile software framework, conceived to facilitate the creation of context-aware applications—it decouples sensor data acquisition and context processing from the application logic. LIS, composed of several modules, encapsulates existing lightweight tools for ontology data management and rule-based reasoning, and it is ready to run on Java-enabled handheld devices. Data management and reasoning processes are designed to handle a general ontology that enables communication among framework components. Both the applications running on top of the framework and the framework components themselves can configure the rule and query sets in order to retrieve the information they need from LIS. In order to test LIS features in a real application scenario, an ‘Activity Monitor’ has been designed and implemented: a personal health-persuasive application that provides feedback on the user’s lifestyle, combining data from physical and virtual sensors. In this case of use, LIS is used to timely evaluate the user’s activity level, to decide on the convenience of triggering notifications and to determine the best interface or channel to deliver these context-aware alerts.d

Design and Validation of a Light Inference System to Support Embedded Context Reasoning

Embedded context management in resource-constrained devices (e.g. mobile phones, autonomous sensors or smart objects) imposes special requirements in terms of lightness for data modelling and reasoning. In this paper, we explore the state-of-the-art on data representation and reasoning tools for embedded mobile reasoning and propose a light inference system (LIS) aiming at simplifying embedded inference processes offering a set of functionalities to avoid redundancy in context management operations. The system is part of a service-oriented mobile software framework, conceived to facilitate the creation of context-aware applications?it decouples sensor data acquisition and context processing from the application logic. LIS, composed of several modules, encapsulates existing lightweight tools for ontology data management and rule-based reasoning, and it is ready to run on Java-enabled handheld devices. Data management and reasoning processes are designed to handle a general ontology that enables communication among framework components. Both the applications running on top of the framework and the framework components themselves can configure the rule and query sets in order to retrieve the information they need from LIS. In order to test LIS features in a real application scenario, an ?Activity Monitor? has been designed and implemented: a personal health-persuasive application that provides feedback on the user?s lifestyle, combining data from physical and virtual sensors. In this case of use, LIS is used to timely evaluate the user?s activity level, to decide on the convenience of triggering notifications and to determine the best interface or channel to deliver these context-aware alerts.

Diffusion Gradient Temporal Difference for Cooperative Reinforcement Learning with Linear Function Approximation

We introduce a diffusion-based algorithm in which multiple agents cooperate to predict a common and global statevalue function by sharing local estimates and local gradient information among neighbors. Our algorithm is a fully distributed implementation of the gradient temporal difference with linear function approximation, to make it applicable to multiagent settings. Simulations illustrate the benefit of cooperation in learning, as made possible by the proposed algorithm.

Gesture recognition using mobile phone's inertial sensors

The availability of inertial sensors embedded in mobile devices has enabled a new type of interaction based on the movements or “gestures” made by the users when holding the device. In this paper we propose a gesture recognition system for mobile devices based on accelerometer and gyroscope measurements. The system is capable of recognizing a set of predefined gestures in a user-independent way, without the need of a training phase. Furthermore, it was designed to be executed in real-time in resource-constrained devices, and therefore has a low computational complexity. The performance of the system is evaluated offline using a dataset of gestures, and also online, through some user tests with the system running in a smart phone.

Autonomous classification models in ubiquitous environments

Stream-mining approach is defined as a set of cutting-edge techniques designed to process streams of data in real time, in order to extract knowledge. In the particular case of classification, stream-mining has to adapt its behaviour to the volatile underlying data distributions, what has been called concept drift. Moreover, it is important to note that concept drift may lead to situations where predictive models become invalid and have therefore to be updated to represent the actual concepts that data poses. In this context, there is a specific type of concept drift, known as recurrent concept drift, where the concepts represented by data have already appeared in the past. In those cases the learning process could be saved or at least minimized by applying a previously trained model. This could be extremely useful in ubiquitous environments that are characterized by the existence of resource constrained devices. To deal with the aforementioned scenario, meta-models can be used in the process of enhancing the drift detection mechanisms used by data stream algorithms, by representing and predicting when the change will occur. There are some real-world situations where a concept reappears, as in the case of intrusion detection systems (IDS), where the same incidents or an adaptation of them usually reappear over time. In these environments the early prediction of drift by means of a better knowledge of past models can help to anticipate to the change, thus improving efficiency of the model regarding the training instances needed. By means of using meta-models as a recurrent drift detection mechanism, the ability to share concepts representations among different data mining processes is open. That kind of exchanges could improve the accuracy of the resultant local model as such model may benefit from patterns similar to the local concept that were observed in other scenarios, but not yet locally. This would also improve the efficiency of training instances used during the classification process, as long as the exchange of models would aid in the application of already trained recurrent models, that have been previously seen by any of the collaborative devices. Which it is to say that the scope of recurrence detection and representation is broaden. In fact the detection, representation and exchange of concept drift patterns would be extremely useful for the law enforcement activities fighting against cyber crime. Being the information exchange one of the main pillars of cooperation, national units would benefit from the experience and knowledge gained by third parties. Moreover, in the specific scope of critical infrastructures protection it is crucial to count with information exchange mechanisms, both from a strategical and technical scope. The exchange of concept drift detection schemes in cyber security environments would aid in the process of preventing, detecting and effectively responding to threads in cyber space. Furthermore, as a complement of meta-models, a mechanism to assess the similarity between classification models is also needed when dealing with recurrent concepts. In this context, when reusing a previously trained model a rough comparison between concepts is usually made, applying boolean logic. The introduction of fuzzy logic comparisons between models could lead to a better efficient reuse of previously seen concepts, by applying not just equal models, but also similar ones. This work faces the aforementioned open issues by means of: the MMPRec system, that integrates a meta-model mechanism and a fuzzy similarity function; a collaborative environment to share meta-models between different devices; a recurrent drift generator that allows to test the usefulness of recurrent drift systems, as it is the case of MMPRec. Moreover, this thesis presents an experimental validation of the proposed contributions using synthetic and real datasets.

Calix[6]arene Derivatives as Pivotal Components of Working Devices and Molecular Machine Prototypes

This Ph.D. thesis describes the synthesis, characterization and study of calix[6]arene derivatives as pivotal components for the construction of molecular machine prototypes. Initially, the ability of a calix[6]arene wheel to supramolecularly assist and increase the rate of a nucleophilic substitution reaction was exploited for the synthesis of two constitutionally isomeric oriented rotaxanes. Then, the synthesis and characterization of several hetero-functionalised calix[6]arene derivatives and the possibility to obtain molecular muscle prototypes was reported. The ability of calix[6]arenes to form oriented pseudorotaxane towards dialkyl viologen axles was then exploited for the synthesis of two calixarene-based [2]catenanes. As last part of this thesis, studies on the electrochemical response of the threading-dethreading process of calix[6]arene-based pseudorotaxanes and rotaxanes supported on glassy carbon electrodes are reported.

System for foreign exchange trading using genetic algorithms and reinforcement learning

Foreign exchange trading has emerged recently as a significant activity in many countries. As with most forms of trading, the activity is influenced by many random parameters so that the creation of a system that effectively emulates the trading process will be very helpful. A major issue for traders in the deregulated Foreign Exchange Market is when to sell and when to buy a particular currency in order to maximize profit. This paper presents novel trading strategies based on the machine learning methods of genetic algorithms and reinforcement learning.

A novel adaptive weight selection algorithm for multi-objective multi-agent reinforcement learning

To solve multi-objective problems, multiple reward signals are often scalarized into a single value and further processed using established single-objective problem solving techniques. While the field of multi-objective optimization has made many advances in applying scalarization techniques to obtain good solution trade-offs, the utility of applying these techniques in the multi-objective multi-agent learning domain has not yet been thoroughly investigated. Agents learn the value of their decisions by linearly scalarizing their reward signals at the local level, while acceptable system wide behaviour results. However, the non-linear relationship between weighting parameters of the scalarization function and the learned policy makes the discovery of system wide trade-offs time consuming. Our first contribution is a thorough analysis of well known scalarization schemes within the multi-objective multi-agent reinforcement learning setup. The analysed approaches intelligently explore the weight-space in order to find a wider range of system trade-offs. In our second contribution, we propose a novel adaptive weight algorithm which interacts with the underlying local multi-objective solvers and allows for a better coverage of the Pareto front. Our third contribution is the experimental validation of our approach by learning bi-objective policies in self-organising smart camera networks. We note that our algorithm (i) explores the objective space faster on many problem instances, (ii) obtained solutions that exhibit a larger hypervolume, while (iii) acquiring a greater spread in the objective space.

Street lighting mesh network protocol

The digital revolution of the 21st century contributed to stem the Internet of Things (IoT). Trillions of embedded devices using the Internet Protocol (IP), also called smart objects, will be an integral part of the Internet. In order to support such an extremely large address space, a new Internet Protocol, called Internet Protocol Version 6 (IPv6) is being adopted. The IPv6 over Low Power Wireless Personal Area Networks (6LoWPAN) has accelerated the integration of WSNs into the Internet. At the same time, the Constrained Application Protocol (CoAP) has made it possible to provide resource constrained devices with RESTful Web services functionalities. This work builds upon previous experience in street lighting networks, for which a proprietary protocol, devised by the Lighting Living Lab, was implemented and used for several years. The proprietary protocol runs on a broad range of lighting control boards. In order to support heterogeneous applications with more demanding communication requirements and to improve the application development process, it was decided to port the Contiki OS to the four channel LED driver (4LD) board from Globaltronic. This thesis describes the work done to adapt the Contiki OS to support the Microchip TM PIC24FJ128GA308 microprocessor and presents an IP based solution to integrate sensors and actuators in smart lighting applications. Besides detailing the system’s architecture and implementation, this thesis presents multiple results showing that the performance of CoAP based resource retrievals in constrained nodes is adequate for supporting networking services in street lighting networks.

Reinforcement learning over encrypted data

Reinforcement learning is a particular paradigm of machine learning that, recently, has proved times and times again to be a very effective and powerful approach. On the other hand, cryptography usually takes the opposite direction. While machine learning aims at analyzing data, cryptography aims at maintaining its privacy by hiding such data. However, the two techniques can be jointly used to create privacy preserving models, able to make inferences on the data without leaking sensitive information. Despite the numerous amount of studies performed on machine learning and cryptography, reinforcement learning in particular has never been applied to such cases before. Being able to successfully make use of reinforcement learning in an encrypted scenario would allow us to create an agent that efficiently controls a system without providing it with full knowledge of the environment it is operating in, leading the way to many possible use cases. Therefore, we have decided to apply the reinforcement learning paradigm to encrypted data. In this project we have applied one of the most well-known reinforcement learning algorithms, called Deep Q-Learning, to simple simulated environments and studied how the encryption affects the training performance of the agent, in order to see if it is still able to learn how to behave even when the input data is no longer readable by humans. The results of this work highlight that the agent is still able to learn with no issues whatsoever in small state spaces with non-secure encryptions, like AES in ECB mode. For fixed environments, it is also able to reach a suboptimal solution even in the presence of secure modes, like AES in CBC mode, showing a significant improvement with respect to a random agent; however, its ability to generalize in stochastic environments or big state spaces suffers greatly.

Unsupervised reinforcement learning via state entropy maximization

Reinforcement Learning (RL) provides a powerful framework to address sequential decision-making problems in which the transition dynamics is unknown or too complex to be represented. The RL approach is based on speculating what is the best decision to make given sample estimates obtained from previous interactions, a recipe that led to several breakthroughs in various domains, ranging from game playing to robotics. Despite their success, current RL methods hardly generalize from one task to another, and achieving the kind of generalization obtained through unsupervised pre-training in non-sequential problems seems unthinkable. Unsupervised RL has recently emerged as a way to improve generalization of RL methods. Just as its non-sequential counterpart, the unsupervised RL framework comprises two phases: An unsupervised pre-training phase, in which the agent interacts with the environment without external feedback, and a supervised fine-tuning phase, in which the agent aims to efficiently solve a task in the same environment by exploiting the knowledge acquired during pre-training. In this thesis, we study unsupervised RL via state entropy maximization, in which the agent makes use of the unsupervised interactions to pre-train a policy that maximizes the entropy of its induced state distribution. First, we provide a theoretical characterization of the learning problem by considering a convex RL formulation that subsumes state entropy maximization. Our analysis shows that maximizing the state entropy in finite trials is inherently harder than RL. Then, we study the state entropy maximization problem from an optimization perspective. Especially, we show that the primal formulation of the corresponding optimization problem can be (approximately) addressed through tractable linear programs. Finally, we provide the first practical methodologies for state entropy maximization in complex domains, both when the pre-training takes place in a single environment as well as multiple environments.

Thermal and air quality modeling of an electric vehicle cabin with low-cost sensors and reinforcement learning

The design process of any electric vehicle system has to be oriented towards the best energy efficiency, together with the constraint of maintaining comfort in the vehicle cabin. Main aim of this study is to research the best thermal management solution in terms of HVAC efficiency without compromising occupant’s comfort and internal air quality. An Arduino controlled Low Cost System of Sensors was developed and compared against reference instrumentation (average R-squared of 0.92) and then used to characterise the vehicle cabin in real parking and driving conditions trials. Data on the energy use of the HVAC was retrieved from the car On-Board Diagnostic port. Energy savings using recirculation can reach 30 %, but pollutants concentration in the cabin builds up in this operating mode. Moreover, the temperature profile appeared strongly nonuniform with air temperature differences up to 10° C. Optimisation methods often require a high number of runs to find the optimal configuration of the system. Fast models proved to be beneficial for these task, while CFD-1D model are usually slower despite the higher level of detail provided. In this work, the collected dataset was used to train a fast ML model of both cabin and HVAC using linear regression. Average scaled RMSE over all trials is 0.4 %, while computation time is 0.0077 ms for each second of simulated time on a laptop computer. Finally, a reinforcement learning environment was built in OpenAI and Stable-Baselines3 using the built-in Proximal Policy Optimisation algorithm to update the policy and seek for the best compromise between comfort, air quality and energy reward terms. The learning curves show an oscillating behaviour overall, with only 2 experiments behaving as expected even if too slow. This result leaves large room for improvement, ranging from the reward function engineering to the expansion of the ML model.

Directly training spiking neural networks for cyber-physical systems: from supervised to reinforcement learning

Spiking Neural Networks (SNNs) are bio-inspired Artificial Neural Networks (ANNs) utilizing discrete spiking signals, akin to neuron communication in the brain, making them ideal for real-time and energy-efficient Cyber-Physical Systems (CPSs). This thesis explores their potential in Structural Health Monitoring (SHM), leveraging low-cost MEMS accelerometers for early damage detection in motorway bridges. The study focuses on Long Short-Term SNNs (LSNNs), although their complex learning processes pose challenges. Comparing LSNNs with other ANN models and training algorithms for SHM, findings indicate LSNNs' effectiveness in damage identification, comparable to ANNs trained using traditional methods. Additionally, an optimized embedded LSNN implementation demonstrates a 54% reduction in execution time, but with longer pre-processing due to spike-based encoding. Furthermore, SNNs are applied in UAV obstacle avoidance, trained directly using a Reinforcement Learning (RL) algorithm with event-based input from a Dynamic Vision Sensor (DVS). Performance evaluation against Convolutional Neural Networks (CNNs) highlights SNNs' superior energy efficiency, showing a 6x decrease in energy consumption. The study also investigates embedded SNN implementations' latency and throughput in real-world deployments, emphasizing their potential for energy-efficient monitoring systems. This research contributes to advancing SHM and UAV obstacle avoidance through SNNs' efficient information processing and decision-making capabilities within CPS domains.