Search

The rapid expansion of Internet of Things (IoT), edge, and embedded devices in the past decade has introduced numerous challenges in terms of security and configuration management. Simultaneously, advances in cloud-native development practices have greatly enhanced the development experience and facilitated quicker updates, thereby enhancing application security. However, applying these advances to IoT, edge, and embedded devices remains a complex task, primarily due to the heterogeneous environments and the need to support devices with extended lifespans. WebAssembly and the WebAssembly System Interface (WASI) has emerged as a promising technology to bridge this gap. As WebAssembly becomes more popular on IoT, edge, and embedded devices, there is a growing demand for hardware interface support in WebAssembly programs. This work presents WASI proposals and proof-of-concept implementations to enable hardware interaction with I2C and USB, which are two commonly used protocols in IoT, directly from WebAssembly applications. This is achieved by running the device drivers within WebAssembly as well. A thorough evaluation of the proof of concepts shows that WASI-USB introduces a minimal overhead of at most 8% compared to native operating system USB APIs. However, the results show that runtime initialization overhead can be significant in low-latency applications., Comment: Preprint of article submitted to IEEE/IFIP Network Operations and Management Symposium 2025

A Kubernetes cluster typically consists of trusted nodes, running within the confines of a physically secure datacenter. With recent advances in edge orchestration, this is no longer the case. This poses a new challenge: how can we trust a device that an attacker has physical access to? This paper presents an architecture and open-source implementation that securely enrolls edge devices as trusted Kubernetes worker nodes. By providing boot attestation rooted in a hardware Trusted Platform Module, a strong base of trust is provided. A new custom controller directs a modified version of Keylime to cross the cloud-edge gap and securely deliver unique cluster credentials required to enroll an edge worker. The controller dynamically grants and revokes these credentials based on attestation events, preventing a possibly compromised node from accessing sensitive cluster resources. We provide both a qualitative and a quantitative evaluation of the architecture. The qualitative scenarios prove its ability to attest and enroll an edge device with role-based access control (RBAC) permissions that dynamically adjust to attestation events. The quantitative evaluation reflects an average of 10.28 seconds delay incurred on the startup time of the edge node due to attestation for a total average enrollment time of 20.91 seconds. The presented architecture thus provides a strong base of trust, securing a physically exposed edge device and paving the way for a robust and resilient edge computing ecosystem., Comment: Pre-print of article accepted to IEEE ICCCN 2024

This research investigates whether the interaction methods of XR headsets can be improved by using haptic feedback. As a first and most common technique, indirect interactions are considered. Indirect interactions correspond to manipulations of virtual objects from a virtual distance using pre-defined hand gestures. As a second interaction technique, direct interaction (namely DIM) has been implemented where the user manipulates objects by virtually touching these with their hands. A third interaction method extends the previous one with haptic feedback (namely HEDIM). These 3 methods are compared with each other based on objective and subjective user tests, also taking into account financial considerations. This research concludes that the DIM improves upon the standard indirect method. Additionally, it has been observed that haptic feedback could enhance the DIM in specific situations. Nevertheless, when considering the current financial cost, our subjects were not convinced of the small improvements haptic feedback brings.

This paper focuses on video streaming over telecommunication networks, taking the important evolution towards network softwarizaton into account. The importance and the opportunities provided by volumetric media delivery will be outlined by means of examples. The most appropriate management platform design for volumetric media delivery and the various challenges and possible approaches will be highlighted next. Finally an overview of research challenges and opportunities will be presented to generate further collaborative research in this area of research.

In this paper, we show how different types of distributed mutual algorithms can be compared in terms of performance through simulations. A simulation-based approach is presented, together with an overview of the relevant evaluation metrics and approach for statistical processing of the results. The presented simulations can be used to learn master students of a course on distributed software the basics of algorithms for distributed mutual exclusion, together with how to properly conduct a detailed comparison study. Finally, a related work section is provided with relevant use cases where distributed mutual exclusion algorithm can be beneficial., Comment: Updated references, title and contents

In this paper, we detail how two types of distributed coordinator election algorithms can be compared in terms of performance based on an evaluation on the High Performance Computing (HPC) infrastructure. An experimental approach based on an MPI (Message Passing Interface) implementation is presented, with the goal to characterize the relevant evaluation metrics based on statistical processing of the results. The presented approach can be used to learn master students of a course on distributed software the basics of algorithms for coordinator election, and how to conduct an experimental performance evaluation study. Finally, use cases where distributed coordinator election algorithms are useful are presented., Comment: Updated references - Corrected typos

Kubernetes' high resource requirements hamper its adoption in constrained environments such as the edge and fog. Its extensible control plane is a significant contributor to this, consisting of long-lived processes called "controllers" that constantly listen for state changes and use resources even when they are not needed. This paper presents a WebAssembly-based framework for running lightweight controllers on-demand, only when they are needed. This framework extends the WebAssembly System Interface (WASI), in order to run Kubernetes controllers as lightweight Wasm modules. The framework runs these Wasm controllers in a modified version of Wasmtime, the reference WebAssembly (Wasm) runtime, that swaps idle controllers to disk and activates them when needed. A thorough evaluation shows this framework achieves a 64% memory reduction compared to traditional container-based controller frameworks., Comment: Pre-print of article accepted to IEEE CloudNet 2022

In this paper, we show how a resource allocation problem can be solved through Integer Linear Programming (ILP). A detailed illustrative example is presented, together with an exhaustive overview of the mathematical model. The size of the required vectors and matrix are determined as well. The presented example can be used to learn students the fundamental basics of ILP-based resource allocation. Next, the specific benefits of the ILP approach compared to other resource allocation algorithms are outlined in this paper. Finally, a related work section is provided with relevant references for further reading. The provided references contain examples of ILP-based resource allocation in modern networks and computing infrastructures.

As KGs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modelling techniques. The original work proposed the Weisfeiler-Lehman (WL) kernel to improve the quality of the representations. However, in this work, we show both formally and empirically that the WL kernel does little to improve walk embeddings in the context of a single KG. As an alternative to the WL kernel, we propose five different strategies to extract information complementary to basic random walks. We compare these walks on several benchmark datasets to show that the \emph{n-gram} strategy performs best on average on node classification tasks and that tuning the walk strategy can result in improved predictive performances.

Information extracted from electrohysterography recordings could potentially prove to be an interesting additional source of information to estimate the risk on preterm birth. Recently, a large number of studies have reported near-perfect results to distinguish between recordings of patients that will deliver term or preterm using a public resource, called the Term/Preterm Electrohysterogram database. However, we argue that these results are overly optimistic due to a methodological flaw being made. In this work, we focus on one specific type of methodological flaw: applying over-sampling before partitioning the data into mutually exclusive training and testing sets. We show how this causes the results to be biased using two artificial datasets and reproduce results of studies in which this flaw was identified. Moreover, we evaluate the actual impact of over-sampling on predictive performance, when applied prior to data partitioning, using the same methodologies of related studies, to provide a realistic view of these methodologies' generalization capabilities. We make our research reproducible by providing all the code under an open license.

In the time series classification domain, shapelets are small time series that are discriminative for a certain class. It has been shown that classifiers are able to achieve state-of-the-art results on a plethora of datasets by taking as input distances from the input time series to different discriminative shapelets. Additionally, these shapelets can easily be visualized and thus possess an interpretable characteristic, making them very appealing in critical domains, such as the health care domain, where longitudinal data is ubiquitous. In this study, a new paradigm for shapelet discovery is proposed, which is based upon evolutionary computation. The advantages of the proposed approach are that (i) it is gradient-free, which could allow to escape from local optima more easily and to find suited candidates more easily and supports non-differentiable objectives, (ii) no brute-force search is required, which drastically reduces the computational complexity by several orders of magnitude, (iii) the total amount of shapelets and length of each of these shapelets are evolved jointly with the shapelets themselves, alleviating the need to specify this beforehand, (iv) entire sets are evaluated at once as opposed to single shapelets, which results in smaller final sets with less similar shapelets that result in similar predictive performances, and (v) discovered shapelets do not need to be a subsequence of the input time series. We present the results of experiments which validate the enumerated advantages.

In the current Internet architecture, a packet is a minimal or fundamental unit upon which different actions such as classification,forwarding, or discarding are performed by the network nodes.When faced with constrained or poor network conditions, a packet is subjected to undesirable drops and re-transmissions, resulting in unpredictable delays and subsequent traffic overheads in the network. Alternately, we introduce qualitative communication services which allow partial, yet timely, delivery of a packet instead of dropping it entirely. These services allow breaking down packet payloads into smaller units (called chunks), enabling much finer granularity of bandwidth utilization. We propose Packet Wash as a new operation in forwarding nodes to support qualitative services. Upon packet error or network congestion, the forwarding node selectively removes some chunk(s)from the payload based on the relationship among the chunks or the individual significance level of each chunk. We also present a qualitative communication framework as well as a Packet Wash directive implemented in a newly evolved data plane technology,called Big Packet Protocol (BPP), Comment: Accepted in NEAT workshop, ACM SIGCOMM, August 2019, Beijing, China

The presence of bacteria or fungi in the bloodstream of patients is abnormal and can lead to life-threatening conditions. A computational model based on a bidirectional long short-term memory artificial neural network, is explored to assist doctors in the intensive care unit to predict whether examination of blood cultures of patients will return positive. As input it uses nine monitored clinical parameters, presented as time series data, collected from 2177 ICU admissions at the Ghent University Hospital. Our main goal is to determine if general machine learning methods and more specific, temporal models, can be used to create an early detection system. This preliminary research obtains an area of 71.95% under the precision recall curve, proving the potential of temporal neural networks in this context.

Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However, this comes at a cost of losing interpretability of the resulting model. This makes ensemble techniques impractical in applications where decision support, instead of decision making, is crucial. To bridge this gap, we present the GENESIM algorithm that transforms an ensemble of decision trees to a single decision tree with an enhanced predictive performance by using a genetic algorithm. We compared GENESIM to prevalent decision tree induction and ensemble techniques using twelve publicly available data sets. The results show that GENESIM achieves a better predictive performance on most of these data sets than decision tree induction techniques and a predictive performance in the same order of magnitude as the ensemble techniques. Moreover, the resulting model of GENESIM has a very low complexity, making it very interpretable, in contrast to ensemble techniques., Comment: Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks. States are mapped to hash codes, which allows to count their occurrences with a hash table. These counts are then used to compute a reward bonus according to the classic count-based exploration theory. We find that simple hash functions can achieve surprisingly good results on many challenging tasks. Furthermore, we show that a domain-dependent learned hash code may further improve these results. Detailed analysis reveals important aspects of a good hash function: 1) having appropriate granularity and 2) encoding information relevant to solving the MDP. This exploration strategy achieves near state-of-the-art performance on both continuous control tasks and Atari 2600 games, hence providing a simple yet powerful baseline for solving MDPs that require considerable exploration., Comment: 10 pages main text + 10 pages supplementary. Published at NIPS 2017

Scalable and effective exploration remains a key challenge in reinforcement learning (RL). While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep RL scenarios. As such, most contemporary RL relies on simple heuristics such as epsilon-greedy exploration or adding Gaussian noise to the controls. This paper introduces Variational Information Maximizing Exploration (VIME), an exploration strategy based on maximization of information gain about the agent's belief of environment dynamics. We propose a practical implementation, using variational inference in Bayesian neural networks which efficiently handles continuous state and action spaces. VIME modifies the MDP reward function, and can be applied with several different underlying RL algorithms. We demonstrate that VIME achieves significantly better performance compared to heuristic exploration methods across a variety of continuous control tasks and algorithms, including tasks with very sparse rewards., Comment: Published in Advances in Neural Information Processing Systems 29 (NIPS), pages 1109-1117