Search

Although the field of Artificial Intelligence in Education (AIEd) has a substantial history as a research domain, never before has the rapid evolution of AI applications in education sparked such prominent public discourse. Given the growing AIEd literature base in higher education, it is important to ensure that the field has a solid research and conceptual grounding as AI adoption increases. This review of reviews is the first comprehensive meta review to explore the scope and nature of AIEd in higher education (AIHEd) research, by synthesising secondary research (e.g., systematic reviews), indexed in the Web of Science, Scopus, ERIC, EBSCOHost, IEEE Xplore, ScienceDirect and ACM Digital Library, or captured through snowballing in OpenAlex, ResearchGate and Google Scholar. Reviews were included if they synthesised applications of AI solely in formal higher or continuing education, were published in English between 2018 and July 2023, were journal articles or full conference papers, and if they had a method section. 66 publications were included for data extraction and synthesis in EPPI Reviewer, which were predominantly systematic reviews (66.7%), published by authors from North America (27.3%), conducted in teams (89.4%) in mostly domestic-only collaborations (71.2%). Findings show that these reviews mostly focused on AIHEd generally (47.0%) or Profiling and Prediction (28.8%) as thematic foci, however key findings indicated a predominance of the use of Adaptive Systems and Personalisation in higher education. Research gaps identified suggest a need for greater ethical, methodological, and contextual considerations within future research, alongside interdisciplinary approaches to AIHEd application. Suggestions are provided to guide future primary and secondary research. © 2024, The Author(s).

Cloud computing is the widespread acceptance of a promising paradigm offering a substantial amount of storage and data services on demand. To preserve data confidentiality, many cryptosystems have been introduced. However, current solutions are incompatible with the resource-constrained end-devices because of a variety of vulnerabilities in terms of practicality and security. In this article, we propose a practical and secure data-sharing system by introducing a new design of attribute-based encryption with verifiable outsourced decryption-attribute-based encryption (VO-ABE for short). Our system offers: (1) data sharing at a fine-grained level; (2) a scalable key issuing protocol without any secure channel; (3) a verifiable outsourced decryption mechanism for resource-constrained end-devices against the malicious cloud service provider; and (4) adaptive security against the real-world attacks. To formalize our solution with cryptographic analysis, we present the formal definition of VO-ABE and its concrete construction with provable security. In particular, our design leverages the techniques of the traditional ABE, verifiable outsourced decryption, and randomness extractor to support fine-grained access control, cost-effective data sharing, and security assurance with high entropy. Moreover, our design is provably secure in the adaptive model under the standard assumption, which offers a stronger security guarantee since the state-of-the-art solution is selectively secure under the non-standard assumption and suffers from a variety of real-world attacks. The implementation and evaluation demonstrate that our solution enjoys superior functionality and better performance than the relevant solutions. More importantly, our solution is compatible with the resource-constrained end-devices since the decryption mechanism takes around 1.1 ms and is 22.7x faster than the state-of-the-art solution.

This thesis explores the effectiveness of an adaptive hint system in mitigating player frustration and improving player experience within Two-Dimensional (2D) puzzle platformers. By dynamically detecting when a player is stuck, the system aims to offer timely and relevant assistance without overwhelming the player or detracting from the game’s challenge. The primary objective is to assess how this system can alleviate frustration and identify effective methods for delivering hints that enhance the overall player experience. Initially, a pre-study analysis was conducted to determine the most effective method for detecting player stuckness, ultimately adopting a Wizard-of-Oz approach due to its feasibility within the project’s scope. The adaptive hint system was then designed and implemented in a pseudo-game, incorporating a tiered hint delivery mechanism that balanced abstract and concrete hints. User tests were conducted with 14 participants divided into control and experimental groups to assess the system’s impact on player experience. The experimental setup included real-time monitoring and semi-structured interviews, with data analyzed using non-parametric statistical methods to evaluate the hint system’s effectiveness. The findings indicated that the adaptive hint system did not significantly reduce player frustration compared to the control group, with the experimental group even reporting slightly higher frustration levels. Despite this, participants in the experimental group generally felt that the hint system improved their experience. The hint delivery methods were effective, making the game more fun and easier to play. However, responses varied by genre preferences, highlighting the need for personalized hint delivery. The research also underscored the limitations of the in-person Wizard-of-Oz method and the importance of larger sample sizes and extended gameplay duration for future studies. While the adaptive hint system showed potential, its overall effe

In this work we propose a new practical synchronization protocol for multiple Euler Lagrange (EL) systems without structural linear-in-the-parameters (LIP) knowledge of the uncertainty and where the agents can be interconnected before control design by unknown state-dependent interconnection terms. This setting is meant to overcome two standard a priori assumptions in the literature concerning uncertainty with LIP structure and absence of interaction among agents before designing the synchronization protocol. To overcome these assumptions, we propose an adaptive distributed control mechanism having the purpose of estimating the coefficients of the resulting state-dependent uncertainty structure., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Team Bart De Schutter, Delft Center for Systems and Control

We present here some lessons learned from observations and applications of child-robot interaction research in diverse ecosystems such as schools, therapy centers, and hospitals, where the interaction was facilitated in real-world circumstances rather than lab settings. Specifically, we use observational results from our reflections on multiple child-robot interaction practices in the wild conducted over a 9-year research period. Using these exploratory studies, we outline some general design considerations and adaptation guidelines for improving the design and implementation of robotic systems in healthcare and education that might lead to more practical, feasible, and ethically sustainable results., Part of ISBN 9798400708244QC 20231229

Managing university life is challenging for any student, including fast-paced self-reliant learning, first experiences with independent daily living, and the social demands of student life. These struggles are even more pronounced in students with Autism Spectrum Disorder (ASD), who might face additional difficulties, including interpersonal deficits, organisational challenges, lacking self-advocacy skills and sensory overload. This thesis uses a participatory design process to research how an adaptive, context-aware system could support students with autism in planning their student life, including managing time, tasks, stress and sensory stimulation. The first interviews resulted in a focus on intelligent planning systems with a low-effort interaction design. The design process will incrementally build towards intelligent support for personalised interactive scheduling as well as in-the-moment next-action recommendations that are context-aware and adaptive to data on the user’s stress level and sensory stimulation exposure.

Adaptive learning is a personalized instruction system that adjusts to the needs, preferences, and progress of learners. This paper reviews the current and future developments of adaptive learning in higher education, especially in relation to the digital education strategy of the European Union. It also uses a cluster analysis framework to explore the main themes and their relationships in the academic literature on adaptive learning. The paper highlights the potential of emerging technologies such as AI, eye-tracking, and physiological measurements to improve the personalization and effectiveness of adaptive learning systems. It presents various methods, algorithms, and prototypes that incorporate learning styles into adaptive learning. It also stresses the importance of continuous professional development in e-learning, media literacy, computer security, and andragogy for teachers who use adaptive learning systems. The paper concludes that adaptive learning can promote creativity, innovation, and lifelong learning in Ukrainian higher education, but it also acknowledges the challenges and suggests further research to assess its impact.

Previous state-of-the-art studies have proposed various analytical models to understand the double-spending attacks (DSA) occurred in Proof-of-Work (PoW) based Blockchains. Although many insights behind the double-spending attacks have been disclosed, we still believe that advanced versions of DSA can be developed to create new threats for the PoW-based blockchains such as the Bitcoin blockchain. In this paper, we present two new types of double-spending attacks in the context of the PoW-based blockchain and discuss the insights behind them. By considering more practical network parameters, such as the number of confirmation blocks, the hashpower of the double-spending attacker, the amount of coins in the target transaction, and the network-status parameter, we first analyze the success probability of the conventional double-spending attack, named Naive DSA. Based on Naive DSA, we create two new adaptive DSA, i.e., the Adaptive DSA and the Reinforcement Adaptive DSA (RA-DSA). In our analytical models, a double-spending attack is converted into a Markov Decision Process. We then exploit the Stochastic Dynamic Programming (SDP) approach to obtain the optimal attack strategies under Adaptive DSA and RA-DSA. Numerical simulation results demonstrate the correlations between each critical network parameter and the expected attacker's reward. Through the proposed analytical models, we aim to alert the PoW-based blockchain ecosystem that the threat of double-spending attacks is still at a dangerous level. For example, our findings show that the attacker can launch a successful attack with a small hashpower proportion much lower than 51% under RA-DSA. IEEE

Adaptive neural networks (NN) have been used to optimize OS kernel datapath functions because they can achieve superior performance under changing environments. However, how to deploy these NNs remains a challenge. One approach is to deploy these adaptive NNs in the userspace. However, such userspace deployments suffer from either high cross-space communication overhead or low responsiveness, significantly compromising the function performance. On the other hand, pure kernel-space deployments also incur a large performance degradation because the computation logic of model tuning algorithm is typically complex, interfering with the performance of normal datapath execution. This paper presents, a hybrid solution to build high-performance adaptive NNs for kernel datapath. At its core, decouples the control path of adaptive NNs into: 1) a kernel-space fast path for efficient model inference; and 2) a userspace slow path for effective model tuning. We have implemented with Linux kernel datapath and evaluated it with three popular datapath functions including congestion control, flow scheduling, and load balancing. Compared to prior works, achieves 44.4% better goodput for congestion control, and improves the completion time for long flows by 33.7% and 56.7% for flow scheduling and load balancing, respectively.

With the large-scale commercialization of 5G networks, Internet of Things (IoT) applications keep on emerging in recent years. Real-time environmental awareness is an essential part of various IoT applications, e.g., self-driving vehicles. Object detection plays a fundamental role in real-time environmental awareness, which is responsible for acquiring valuable object information from the environment automatically. Despite of the fast progress for object detection in general, small object detection still faces challenges. Because of the restricted scales, small objects are only capable of generating relatively week features after multiple convolutional layers, thus causing low detection accuracy. Existing schemes mostly focus on extracting rich multi-scale features, e.g., generating high resolution features through Generative Adversarial Networks (GAN), or generating multi-scale features through feature combination. Nevertheless, these schemes require complex network implementation, and usually suffer from high processing delay because of high resolution images. To resolve the problems mentioned above, we propose an Adaptive Dynamic neural network (AD-RCNN) that consists of three fundamental improvements. We first propose a dynamic region proposal network to improve the quality of region proposals. We then introduce a visual attention scheme to generate features of regions. At last, we put forward an adaptive dynamic training module to optimize final detection results. Experimental results demonstrate that AD-RCNN outperforms the state-of-the-art from the perspectives of mAP and Frames per Second (FPS). Specifically, at the resolution of 1024 of TT100K dataset, AD-RCNN achieves 68.8% mAP, which outperforms the baseline Faster RCNN by 8.52%.

The main challenge for industrial predictive models is how to effectively deal with big data from high-dimensional processes with nonstationary characteristics. Although deep networks, such as the stacked autoencoder (SAE), can learn useful features from massive data with multilevel architecture, it is difficult to adapt them online to track fast time-varying process dynamics. To integrate feature learning and online adaptation, this article proposes a deep cascade gradient radial basis function (GRBF) network for online modeling and prediction of nonlinear and nonstationary processes. The proposed deep learning method consists of three modules. First, a preliminary prediction result is generated by a GRBF weak predictor, which is further combined with raw input data for feature extraction. By incorporating the prior weak prediction information, deep output-relevant features are extracted using a SAE. Online prediction is finally produced upon the extracted features with a GRBF predictor, whose weights and structure are updated online to capture fast time-varying process characteristics. Three real-world industrial case studies demonstrate that the proposed deep cascade GRBF network outperforms existing state-of-the-art online modeling approaches as well as deep networks, in terms of both online prediction accuracy and computational complexity.

This paper addresses distributed adaptive optimal resource allocation problems over weight-balanced digraphs. By leveraging state-of-the-art adaptive coupling designs for multiagent systems, two adaptive algorithms are proposed, namely a directed-spanning-tree-based algorithm and a node-based algorithm. The benefits of these algorithms are that they require neither sufficiently small or unitary step sizes, nor global knowledge of Laplacian eigenvalues, which are widely required in the literature. It is shown that both algorithms belong to a class of uncertain saddle-point dynamics, which can be tackled by repeatedly adopting the Peter-Paul inequality in the framework of Lyapunov theory. Thanks to this new viewpoint, global asymptotic convergence of both algorithms can be proven in a unified way. The effectiveness of the proposed algorithms is validated through numerical simulations and case studies in IEEE 30-bus and 118-bus power systems., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Delft Center for Systems and Control

This work aims to improve the communication security of the industrial Internet of Things (IIoT) based on digital twins (DTs). The related technologies of quantum communication are introduced to improve network communication. Firstly, the key DTs technologies in the construction of IIoT are expounded. Also, the characteristics of quantum communication are analyzed. Secondly, a channel encryption scheme based on quantum communication is proposed to ensure the communication security of IIoT. The scheme uses the five-particle entanglement state and two-particle bell state as entanglement channels to realize two-particle quantum teleportation. Finally, an Adaptive Key Residue algorithm is proposed based on the quantum key distribution mechanism. The algorithm verification suggests that the success rate of service distribution decreases with the increase in network load. When the service load reaches 1000, the Adaptive Key Residue algorithm can maintain a success rate of service distribution in the network higher than 0.6. Besides, the success rate of service distribution increases with the growth of the total key generation rate V and the key pool capacity C. The research results reported here are of great significance for realizing the secure communication of IIoT systems based on digital twins to ensure the effective operation of network communication and the secure transmission of data.

The main challenge for industrial predictive models is how to effectively deal with big data from high-dimensional processes with nonstationary characteristics. Although deep networks, such as the stacked autoencoder (SAE), can learn useful features from massive data with multilevel architecture, it is difficult to adapt them online to track fast time-varying process dynamics. To integrate feature learning and online adaptation, this article proposes a deep cascade gradient radial basis function (GRBF) network for online modeling and prediction of nonlinear and nonstationary processes. The proposed deep learning method consists of three modules. First, a preliminary prediction result is generated by a GRBF weak predictor, which is further combined with raw input data for feature extraction. By incorporating the prior weak prediction information, deep output-relevant features are extracted using a SAE. Online prediction is finally produced upon the extracted features with a GRBF predictor, whose weights and structure are updated online to capture fast time-varying process characteristics. Three real-world industrial case studies demonstrate that the proposed deep cascade GRBF network outperforms existing state-of-the-art online modeling approaches as well as deep networks, in terms of both online prediction accuracy and computational complexity.

Internet of Things (IoT) systems are complex systems that can manage mission-critical, costly operations or the collection, storage, and processing of sensitive data. Therefore, security represents a primary concern that should be considered when engineering IoT systems. Additionally, several challenges need to be addressed, including the following ones. IoT systems’ environments are dynamic and uncertain. For instance, IoT devices can be mobile or might run out of batteries, so they can become suddenly unavailable. To cope with such environments, IoT systems can be engineered as goal-driven and self-adaptive systems. A goal-driven IoT system is composed of a dynamic set of IoT devices and services that temporarily connect and cooperate to achieve a specific goal. Several approaches have been proposed to engineer goal-driven and self-adaptive IoT systems. However, none of the existing approaches enable goal-driven IoT systems to automatically detect security threats and autonomously adapt to mitigate them. Toward bridging these gaps, this paper proposes a distributed architectural Approach for engineering goal-driven IoT Systems that can autonomously SElf-adapt to secuRity Threats in their environments (ASSERT). ASSERT exploits techniques and adopts notions, such as agents, federated learning, feedback loops, and blockchain, for maintaining the systems’ security and enhancing the trustworthiness of the adaptations they perform. The results of the experiments that we conducted to validate the approach’s feasibility show that it performs and scales well when detecting security threats, performing autonomous security adaptations to mitigate the threats and enabling systems’ constituents to learn about security threats in their environments collaboratively. © 2022 by the authors., open access

This volume contains the proceedings of the 6th International Conference on Computer-Human Interaction Research and Applications (CHIRA 2022), which was held in Valletta, Malta as a hybrid event, from 27 to 28 October. CHIRA is sponsored by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC), and is held in cooperation with the ACM Special Interest Group on Management Information Systems and the European Society for Socially Embedded Technologies (EUSSET). The purpose of CHIRA is to bring together professionals, academics and students who are interested in the advancement of research and practical applications of human-technology & human-computer interaction. Different aspects of Computer-Human Interaction were covered in four parallel tracks: Human Factors and Information Systems, Interactive Devices, Interaction Design, and Adaptive and Intelligent Systems. Human-Computer Interaction is getting renewed interest as human-ai interaction due to the increasing success of artificial intelligence and its applications. In addition to paper presentations, CHIRA’s program included three invited talks delivered by internationally distinguished speakers: Alan Dix (Swansea University, United Kingdom), Truth in an Age of Information; Karen Holtzblatt (InContext Design, United States), Contextual Design: Origins, Ethics, and Diverse Voices; and Abigail Sellen (Microsoft Research Cambridge, United Kingdom), Transforming the Future of Work through Human-Centred Design. CHIRA received 36 paper submissions from 17 countries, of which 17% were accepted as full papers. The high quality of the papers received imposed difficult choices during the review process. To evaluate each submission, a double-blind paper review was performed by the Program Committee, whose members are highly qualified independent researchers in the CHIRA topic areas. All presented papers will be submitted for indexation by Scopus, Google Scholar, DBLP Computer Science B

Air traffic controller workload is a limiting factor in the current air traffic management system. Adaptive support systems have the potential to balance controller workload and gain acceptance as they provide support during times of need. Challenges in the design of adaptive support systems are to decide when and how to trigger support. The goal of this study is to gain empirical insights into these challenges through a human-in-the-loop experiment, featuring a simplified air traffic control environment in which a novel triggering mechanism uses the quality of the controller's decisions to determine when support is needed. The designed system seeks to prevent high workload conditions by providing resolution advisories when the controller exceeds a threshold of 'self-complicating' decisions. Results indicate that the new system is indeed capable of increasing the efficiency and safety compared to full manual control without intervention. More adaptive support, however, increased the frustration of participants, decreased acceptance, and did not result in improved workload ratings. These findings suggest that, unless we can better infer human intent in complex work environments, adaptive support at the level of decision-making is problematic. A potentially more fruitful direction is to provide support at the level of information integration, with full decision-making authority with the human., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Control & Simulation

The high maneuverability of fixed-wing unmanned aerial vehicles (UAVs) exposes these systems to several dynamical and parametric uncertainties, severely affecting the fidelity of modeling and causing limited guidance autonomy. This article shows enhanced autonomy via adaptation mechanisms embedded in the guidance law: a vector-field method is proposed that does not require a priori knowledge of the UAV course time constant, coupling effects, and wind amplitude/direction. Stability and performance are assessed using the Lyapunov theory. The method is tested on software-in-the loop and hardware-in-the-loop UAV platforms, showing that the proposed guidance law outperforms state-of-the-art guidance controllers and standard vector-field approaches in the presence of significant uncertainty., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Team Bart De Schutter

This work introduces a new single-stage adaptive controller for Euler-Lagrange systems with nonholonomic constraints. The proposed mechanism provides a simpler design philosophy compared to double-stage mechanisms (that address kinematics and dynamics in two steps), while achieving analogous stability properties, i.e. stability of both original and internal states. Meanwhile, we do not require direct access to the internal states as required in state-of-the-art single-stage mechanisms. The proposed approach is studied via Lyapunov analysis, validated numerically on wheeled mobile robot dynamics and compared to a standard double-stage approach., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Team Bart De Schutter

Recent advances in very-large-scale integration (VLSI) technologies have offered the capability of integrating thousands of processing elements onto a single silicon microchip. Multiprocessor systems-on-chips (MPSoCs) are the latest creation of this technology evolution. As an interconnection network, Network-on-Chip (NoC) has emerged as a scalable and promising solution for MPSoCs to achieve high performance. In NoCs, a routing algorithm is a critical part of a router and provides a path for a packet toward its destination. Every routing algorithm should exhibit two characteristics. First, the route selection function should provide enough degree of adaptiveness to avoid network congestion. Second, it should not offer stale information on network congestion status to the neighboring routers. Many researchers have investigated network congestion and proposed techniques to control/avoid congestion. Such congestion avoidance-based algorithms significantly improve NoC performance. However, they may result in hardware overhead for side network implementation to collect congestion status. This paper reviews various output selection strategies used by routing algorithms to route a packet on a less congested network region. It also classifies them based on techniques adopted to handle and propagate congestion information. Additionally, this article provides the implementation and analysis details of state-of-art selection methods.

The sixth HUMANIZE workshop1 on Transparency and Explainability in Adaptive Systems through User Modeling Grounded in Psychological Theory took place in conjunction with the 27th annual meeting of the Intelligent User Interfaces (IUI)2 community that was hosted virtually by the University of Helsinki (Finland) on March 22, 2022. The 2022 edition of the workshop was held together with TExSS (Transparency and Explanations in Smart Systems) 3. The workshop provided a venue for researchers from different fields to interact by accepting contributions on the intersection of practical data mining methods and theoretical knowledge for personalization. A total of two papers was accepted for this edition of the workshop., Export Date: 2 May 2022; Conference Paper

The design of adaptive observers is a common approach for the joint state and parameter-estimation problem. Nonetheless, there are still some obstacles that have to be solved to improve the design of adaptive observers and extend its implementability to a larger class of systems. First, the separation of the state-estimation and the parameter-estimation requires a relative degree one or zero between some known signal and the parameters to be estimated. Second, standard stability proofs for adaptive observers cannot be easily extended to consider the unavoidable presence of sensor noise and unmodelled system uncertainty. Consequently, on the one hand, this work proposed a methodology to relax the relative degree condition through the use of a high-gain observer that will be coupled with the adaptive observer. On the other hand, the stability and performance of the proposed observer scheme will be analysed by the use of a strict Lyapunov function based on the Mazenc construction, which allows to have provable convergence and to study the effect of sensor noise and model uncertainty through common Lyapunov theory. Finally, the proposed approach is validated in a compartmental epidemiology model., Peer Reviewed, Postprint (author's final draft)

In this paper a novel method is proposed for constructing linear parameter varying (LPV) system models through adaptation For a class of nonlinear systems, an LPV model is built using its linear part, and its coefficients are considered as time-varying parameters The variation. M time IS controlled by an adaptation scheme with the goal of keeping the trajectories of the LPV system, close to those of the original nonlinear system Using the LPV model is a surrogate, a dynamical controller is built by utilizing self-scheduling methods for LPV systems, and it is shown that this controller will indeed stabilize, the original nonlinear system

When evaluating personalized or adaptive systems, we frequently rely on one single evaluation objective and one single method. This remains us with “blind spots”. A comprehensive evaluation may require a thoughtful integration of multiple methods. This tutorial (i) demonstrates the wide variety of dimensions to be eval- uated, (ii) outlines the methodological approaches to evaluate these dimensions, (iii) pinpoints the blind spots when using only one ap- proach, (iv) demonstrates the benefits of multi-method evaluation, and (v) outlines the basic options how multiple methods can be integrated into one evaluation design. Participants familiarize with the wide spectrum of opportunities how adaptive or personalized systems may be evaluated, and have the opportunity to come up with evaluation designs that comply with the four basic options of multi-method evaluation. The ultimate learning objective is to stimulate the critical reflection of one’s own evaluation practices and those of the community at large.

In this article, we propose a new protection scheme for backbone networks to guarantee high service availability. The presented scheme does not require any reconfiguration immediately after the failure (i.e., it is proactive). At the same time, it does not require any reserved backup network resources either. To achieve these seemingly contradictory goals, we utilize the recent advancements in Machine Learning (ML) to implement a network intelligence that periodically re-allocates the unused capacity as protection bandwidth to meet the service availability requirements of each connection. Our goal is achieved by two components (1) predicting the traffic for the next period on each link, and (2) intelligently selecting the best fit dedicated protection scheme for the next period depending on the estimated unused (spare) bandwidth and the previous service availability violations. Note that re-allocating protection bandwidth affects neither the operational connections nor the current best practice of operators to over-provision network bandwidth to support elephant flows. Finally, we provide a case study on the real traffic from Energy Sciences Network (ESnet), a high-speed, international scientific backbone network. The key benefit of our framework is that adaptively utilizing the over-provisioned bandwidth for spare capacity is sufficient to improve the availability from three-nines to five-nines (in ESnet for the 30 examined connections). The drawback is negligible bandwidth limitations; the user perceives a minor and very temporal bandwidth limitation in less than 0.1% of the time.

Today’s software landscape features a high degree of complexity, frequent change and many uncertainties. Cyber-attacks are a common occurrence and their consequences are often severe, thus, systems that are able to dynamically defend themselves from attacks are highly needed. Such systems are called self-protecting systems and aim to autonomously identify, analyse and mitigate threats by adapting their structure and behavior at runtime. This research project will contribute towards providing software-intensive systems with self-protection or adaptive-security capabilities. We enhance the security of architecture-based self-adaptive systems by equipping them with (proactive and reactive) self-protection capabilities as well as attack monitoring. Moreover, we provide a framework that allows an open, decentralized system system to mitigate security threats and self-organize to maximize the average trust between the system entities while maintaining their security policies. © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

The design of physiologically adaptive systems entails several complex steps from acquiring human body signals to create responsive adaptive behaviors that can be used to enhance conventional communication pathways between human and technological systems. Categorizing and classifying the computing techniques used to create intelligent adaptation via physiological metrics is an important step towards creating a body of knowledge that allows the field to develop and mature accordingly. This paper proposes the creation of a taxonomy that groups several physiologically adaptive (also called biocybernetic) systems that have been previously designed and reported. The taxonomy proposes two subcategories of adaptive techniques: control theoretics and machine learning, which have multiple sub-categories that we illustrate with systems created in the last decades. Based on the proposed taxonomy, we also propose a design framework that considers four fundamental aspects that should be defined when designing physiologically adaptive systems: the medium, the application area, the psychophysiological target state, and the adaptation technique. We conclude the paper by discussing the importance of the proposed taxonomy and design framework as well as suggesting research areas and applications where we envision biocybernetic systems will evolve in the following years.

The current importance of digital competence makes it essential to enable people with disabilities to use digital devices and applications and to automatically adapt site interactions to their needs. Although most of the current adaptable solutions make use of predefined user profiles, automatic detection of user abilities and disabilities is the foundation for building adaptive systems. This work contributes to diminishing the digital divide for people with disabilities by detecting the web navigation problems of users with physical disabilities based on a two-step strategy. The system is based on web user interaction data collected by the RemoTest platform and a complete data mining process applied to the data. First, the device used for interaction is recognized, and then, the problems the user may be having while interacting with the computer are detected. Identification of the device being used and the problems being encountered will allow the most adequate adaptation to be deployed and thus make the navigation more accessible.

With the increasing ubiquity and scale of self-adaptive systems, there is a growing need to decentralize the functionality that realizes self-adaptation. Our focus is on architecture-based self-adaptive systems where one or more functions for monitoring, analyzing, planning, and executing are realized by multiple components that coordinate with one another. While some earlier studies have shed light on existing work on the decentralization of self-adaptive systems, there is currently no clear overview of the state of the art in decentralization of self-adaptive systems. Yet, having a precise view on the state of the art in decentralized self-adaptive systems is crucial for researchers to understand existing solutions and drive future research efforts. To address this gap, we conducted a mapping study. The study focused on papers published at 24 important venues that publish research on self-adaptation. The study focused on the motivations for choosing a decentralized approach to realize self-adaptation, the adaptation functions that are decentralized, the realization of the coordination, and the open challenges in the area.

Recently, we have been witnessing an increasing use of machine learning methods in self-adaptive systems. Machine learning methods offer a variety of use cases for supporting self-adaptation, e.g., to keep runtime models up to date, reduce large adaptation spaces, or update adaptation rules. Yet, since machine learning methods apply in essence statistical methods, they may have an impact on the decisions made by a self-adaptive system. Given the wide use of formal approaches to provide guarantees for the decisions made by self-adaptive systems, it is important to investigate the impact of applying machine learning methods when such approaches are used. In this paper, we study one particular instance that combines linear regression to reduce the adaptation space of a self-adaptive system with statistical model checking to analyze the resulting adaptation options. We use computational learning theory to determine a theoretical bound on the impact of the machine learning method on the predictions made by the verifier. We illustrate and evaluate the theoretical result using a scenario of the DeltaIoT artifact. To conclude, we look at opportunities for future research in this area.

This paper proposes to enrich robot motion data with trajectory curvature information. To do so, we use an approximate implementation of a topological feature named writhe, which measures the curling of a closed curve around itself, and its analog feature for two closed curves, namely the linking number. Despite these features have been established for closed curves, their definition allows for a discrete calculation that is well-defined for non-closed curves and can thus provide information about how much a robot trajectory is curling around a line in space. Such lines can be predefined by a user, observed by vision or, in our case, inferred as virtual lines in space around which the robot motion is curling. We use these topological features to augment the data of a trajectory encapsulated as a Movement Primitive (MP). We propose a method to determine how many virtual segments best characterize a trajectory and then find such segments. This results in a generative model that permits modulating curvature to generate new samples, while still staying within the dataset distribution and being able to adapt to contextual variables.

Many-Core Systems-on-Chip increasingly require Dynamic Multi-objective Management (DMOM) of resources. DMOM uses different management components for objectives and resources to implement comprehensive and self-adaptive system resource management. DMOMs are challenging because they require a scalable and well-organized framework to make each component modular, allowing it to be instantiated or redesigned with a limited impact on other components. This work evaluates two state-of-the-art distributed management paradigms and, motivated by their drawbacks, proposes a new one called Management Application (MA), along with a DMOM framework based on MA. MA is a distributed application, specific for management, where each task implements a management role. This paradigm favors scalability and modularity because the management design assumes different and parallel modules, decoupled from the OS. An experiment with a task mapping case study shows that MA reduces the overhead of management resources (-61.5%), latency (-66%), and communication volume (-96%) compared to state-of-the-art per-application management. Compared to cluster-based management (CBM) implemented directly as part of the OS, MA is similar in resources and communication volume, increasing only the mapping latency (+16%). Results targeting a complete DMOM control loop addressing up to three different objectives show the scalability regarding system size and adaptation frequency compared to CBM, presenting an overall management latency reduction of 17.2% and an overall monitoring messages' latency reduction of 90.2%. © 2021 ACM.

The fifth HUMANIZE workshop1 on Transparency and Explainability in Adaptive Systems through User Modeling Grounded in Psychological Theory took place in conjunction with the 26th annual meeting of the Intelligent User Interfaces (IUI)2 community in Texas, USA on April 17, 2021. The workshop provided a venue for researchers from different fields to interact by accepting contributions on the intersection of practical data mining methods and theoretical knowledge for personalization. A total of five papers was accepted for this edition of the workshop.

В работе исследуется прикладная задача, связанная с проблемой адаптации систем поддержки принятия решений к изменениям условий среды. Предложен подход, основанный на использовании методологии высокоуровневых архитектур High Level Architecture (HLA). Во введении выделяются свойства современных задач и среды принятия решений. Обосновывается актуальность разработки технологий, ориентированных на адаптацию компьютерных систем. В основной части выполнен анализ технологий и средств разработки систем, выделены причины их быстрого устаревания. Для решения проблем масштабируемости и адаптируемости предложен вариант архитектуры программной системы в форме HLA-федерации. Описаны основные этапы предлагаемой технологии и их реализация при проектировании и программировании архитектуры. Эффективность подхода демонстрируется на примере прикладной системы поддержки принятия решений, которая используется в рамках образовательного проекта международной программы Erasmus+.

Many Collect ive Adaptive Systems (CASs) exist in nature: think of ant colonies, where large collectives of ants operate autonomously but interact with other ants and the environment to provide resilient global behaviors that sustain their colony. Following scientific studies that were aimed at understanding and predicting the evolution of these systems, and fueled by technological advances, research has started to investigate CAS engineering: the methods, tools, and techniques for building CASs. This naturally leads to a vision where collectives of humans and computational elements, situated both in the digital and physical worlds, collaborate to give rise to "intelligent" collective behavior supporting novel kinds of applications and services. Humans can be involved in two ways: both as users and as components of the CAS, in the sense that human behaviors and limitations are often integral to the system description. This has significant social implications that need to be considered by CAS researchers: in this paper, we share a discussion that took place between some experts thinking about CAS engineering, focusing on the social implication of CASs and related open research challenges. We hope that this provides a useful context for future research projects, research grant proposals, and research directions.

Since the dawn of the incorporation of ICTs into educational environments, specifically into teaching and learning processes, there have been expectations about the possibilities of individualized education in versatile environments that acknowledge students’ particularities. Although several studies have examined these situations, they are sometimes subjected to specific platforms or applications. An adaptive system must define the components to be adjusted according to specific determinants, in particular, the characteristics of the students’ profile and contextual elements, and also establish a mechanism for the adaptation. This paper proposes a system to generate customized virtual courses based on the separation of the structure of the course from the educational resources that support the educational activities. Such system is enhanced with production rules that determine the educational resources to be delivered at each moment guided by the characteristics in the student’s model. This methodological approach responds to the systemic definition of the adaptation strategy, which requires making the determinants, components and adaptation techniques explicit based on DSR. The proposed system is versatile because it can be enriched with new elements or variations of the attributes in the student profile, taking different models in learning styles and the categorization of personal, academic, or contextual characteristics reflected in the adaptation process. The result shows that the proposed model can provide a different course plan, with personalized activities, according to students’ characteristics and context., Desde los albores de la incorporación de las tic en los ambientes educativos, en concreto en los procesos de enseñanza y aprendizaje, se abrían expectativas sobre las posibilidades de la educación individualizada, en ambientes versátiles, en los que se reconocieran las particularidades de los estudiantes. A pesar de que existen diversos acercamientos a estas situaciones, en ocasiones están sujetos a plataformas o aplicaciones específicas. Un sistema adaptativo debe definir los componentes ajustados de acuerdo con determinantes específicos, en particular las características en el perfil del estudiante y los elementos contextuales, y, además, definir un mecanismo para dicha adaptación. El presente trabajo expone una propuesta para la generación de cursos virtuales personalizados, soportada en la separación de la estructura del curso y los recursos educativos que apoyan las actividades educativas y potenciadas, con un sistema de reglas de producción que determinan los recursos educativos a entregar en cada momento, guiadas por las características incluidas en el modelo del estudiante. El enfoque metodológico responde a la definición sistémica de la estrategia de adaptación, que exige hacer explícito los determinantes, los componentes y las técnicas de adaptación, con base en dsr. La versatilidad de la propuesta radica en que puede ser enriquecida con nuevos elementos o con variaciones de las características en el perfil del estudiante, al tomar diferentes modelos en estilos de aprendizaje y la categorización de características personales, académicas o contextuales, en tanto que se vean reflejadas en el proceso de adaptación. El resultado final evidencia que el modelo propuesto permite entregar un plan de curso diferente, con actividades personalizadas, de acuerdo con las características del estudiante y su contexto.

One of the challenges in current designs of wireless networks is that of guaranteeing end to end delivery of high priority data or packets in multi-path multi-hop networks for medical use especially for nodes with mobility. There are various solutions based on traffic engineering which are applied in wired networks to guarantee end to end delivery of packets. With mobile wireless networks, the environment is highly dynamic, therefore with different scenarios having multiple paths or routes in the network, the node has to adapt to the network for dependable delivery of priority packets. In so doing, a level of Qos can at least be guaranteed. This paper reviews some of the techniques to achieve adaptive network coding, and the objective is to implement adaptive network coding in multi-hop, multipath network for high reliability and dependability. As a preliminary study we investigate an Adaptive Network coding scheme in a Binary tree fashion with the root being the convolution coder for its feasibility. The objective is to design a control protocol to be used to adapt to the error changes that occur in the network thereby increasing performance., 2018 3rd International Conference on Computer and Communication Systems (ICCCS), Nagoya, Japan

Intentions serve multiple roles in human action. They help in making sense of our actions and those of others, and on this basis, coordination is possible. They cause, guide and sustain our actions. Additionally, they are about the present when we do act intentionally, but also they are about the future when we intend to do something later. From the aforementioned characteristics, it can be argued that intentions have a fundamental part in organizational interventions. Based on this assumption the paper proposes a model to make use of intentions in interventions. It aims to help in describing, conducting and learning about intervention processes. The model uses the graphical language advanced by the Soft Systems Methodology. The concept of intention and the assembling of the model, draw from Philosophies of Action, Language and Explanation and by the Theories of Relevance, Boundary Critique, and Complex Adaptive Systems.

Cada vez es más común que los sistemas se puedan adaptar dinámicamente a contextos cambiantes en tiempo de ejecución. Dichos sistemas exhiben grados de variabilidad que dependen de las fluctuaciones del tiempo de ejecución en sus contextos. Aunque la variabilidad dinámica ha sido abordada por conceptos establecidos desde hace mucho tiempo en el campo de las familias de sistemas, se considera que este enfoque es insuficiente para satisfacer las necesidades de los sistemas distribuidos y dinámicamente adaptativos como los sistemas para la agricultura inteligente basados en IoT (Internet de las Cosas) considerados sistemas ciber-físicos. Estos sistemas son requeridos para mejorar la productividad y competitividad de la producción agrícola colombiana. En el caso de los sistemas que se adaptan dinámicamente, los enfoques para apoyar la variabilidad de sistemas ciber-físicos no pueden ser solo las especializaciones de componentes o las restricciones sobre las variables del sistema puesto que muchas veces las condiciones de funcionamiento de estos sistemas no son predecibles. En este estudio que busca establecer cuáles son las técnicas más apropiadas para la gestión de la variabilidad dinámica en sistemas adaptativos, ha sido necesario abordar el modelamiento de la arquitectura como una práctica clave en la ingeniería de software. Se considera que un lenguaje de modelamiento que permita representar este tipo de sistemas será definitivo para la producción de sistemas con el nivel de calidad y confiabilidad que se requiere. Todos los resultados de esta investigación están enfocados en propiciar a las compañías de desarrollo, las herramientas que les permitan aumentar la productividad, la flexibilidad y la calidad que requieren los sistemas ciber-físicos para el agro. Para el estudio será necesario analizar la literatura para crear un lenguaje que mejore el estado del arte y para evaluar y realizar por lo menos un caso de prueba de un sistema real, esto permitirá validar el l, It is becoming increasingly common for systems to be dynamically adapted to changing contexts at run time. Such systems exhibit degrees of variability that depend on the fluctuations of the runtime in their contexts. Although dynamic variability has been addressed by long-established concepts in the field of system families, this approach is considered insufficient to meet the needs of distributed and dynamically adaptive systems such as IoT (Internet of Things)-based intelligent agriculture systems considered cyber-physical systems. These systems are required to improve the productivity and competitiveness of Colombian agricultural production. For dynamically adapted systems, approaches to support the variability of cyber-physical systems may not be just component specializations or restrictions on system variables since often the operating conditions of these systems are not predictable. In this study that seeks to establish the most appropriate techniques for managing dynamic variability in self-adapting systems, it has been necessary to address architecture modeling as a key practice in software engineering. It is considered that a modeling language that allows to represent such systems will be definitive for the production of systems with the level of quality and reliability that is required. All the results of this research are focused on enabling development companies, the tools that allow them to increase the productivity, flexibility and quality that cyber-physical systems require for agriculture. For the study it will be necessary to analyze the literature to create a language that improves the state of the art and to evaluate and perform at least one test case of a real system, this will allow to validate the proposed language. This work starts from the premise that that language should allow you to specify software, hardware, monitoring, and action components on the physical environment of each system and represent physical objects that are part of the s

Tele-rehabilitation can complement traditional rehabilitation therapies by providing valuable information that can help in the evaluation, monitoring, and treatment of patients. Many patient tele-monitoring systems that integrate wearable technology are emerging as an effective tool for the long-term surveillance of rehabilitation progression, enabling continuous sampling of patient real-time movement in a non-invasive way, without affecting the normal daily activity of the outpatient, who, therefore, will not need to make frequent clinic visits. One of the main challenges of tele-rehabilitation systems is to pay special attention to the diversity of dysfunctions in patients by offering devices with customized behaviours adaptable to the physical conditions of each patient at the different stages of the rehabilitation therapy. Long-term monitoring systems need an adaptation policy to autonomously reconfigure their behaviour according to vital signs read during the physical activity of the patient, the remaining battery level, or the required accuracy of collected data. However, it would alsobe desirable to adjust such adaptation policies over time, according to the patient's evolution. This work presents a wearable patient-monitoring system for tele-rehabilitation that is able to dynamically self-configure its internal behaviour to the current context of the outpatient according to a set of adaptation policies that optimize battery consumption, taking into account other QoS parameters at the same time. Our system is also able to self-adapt its internal adaptation policies as a patient's condition improves, while maintaining the system's efficiency. We illustrate our proposal with a real mHealth case study. The results of the experiments show that the system updates the adaptation policies, taking into account specific indicators of the disease. The validation results show that the evolution of the self-adaptation policies correlates with the progression of different