Search

Today, reinforcement learning is one of the most effective machine learning approaches in the tasks of automatically adapting computer systems to user needs. However, implementing this technology into a digital product requires addressing a key challenge: determining the reward model in the digital environment. This paper proposes a usability reward model in multi-agent reinforcement learning. Well-known mathematical formulas used for measuring usability metrics were analyzed in detail and incorporated into the usability reward model. In the usability reward model, any neural network-based multi-agent reinforcement learning algorithm can be used as the underlying learning algorithm. This paper presents a study using independent and actor-critic reinforcement learning algorithms to investigate their impact on the usability metrics of a mobile user interface. Computational experiments and usability tests were conducted in a specially designed multi-agent environment for mobile user interfaces, enabling the implementation of various usage scenarios and real-time adaptations. [ABSTRACT FROM AUTHOR]

Formation control is a fundamental task in the realm of autonomous multiagent systems. To drive a group of agents to maneuver continuously with the desired formation, this paper studies the finite‐time affine formation control problem with disturbances, input constraints and safety guarantee. A non‐singular terminal sliding mode control (NTSMC) is implemented to achieve finite‐time convergence of all followers to their desired positions. Additionally, an auxiliary system is deployed to address input constraints resulting from the physical properties of the affine formation system. To mitigate the impact of lumped disturbances, a finite‐time disturbance observer (FTDO) is employed to estimate the disturbances and compensate for their effects. Based on FTDO, the auxiliary system and the above NTSMC, a finite‐time robust controller is developed as the nominal controller. By modifying the nominal controllers to comply with safety constraints, control barrier functions are employed to ensure the safety of the formation system in obstacle‐filled environment. Finally, the effectiveness and feasibility of this method are validated through simulations and real‐world experiments. [ABSTRACT FROM AUTHOR]

Optimized user experience and individualized task assistance are key factors for the success of e-business applications because they serve both, users, and service providers. In this paper we present an adaptation agent for observing and analyzing interactive behavior, emotional state and task-accomplishment of individual users while working with interactive e-business applications. The agent recognizes specific situations and can adapt the interactive application at runtime by co-operating with a model-based user interface development framework (MBUID) and by providing domain-specific guidance for the user. After introducing purpose, business context of our approach, and related work, the paper discusses the structure and functionality of the SitAdapt adaptation agent. The operation of the adaptation agent is demonstrated for a travel-booking platform that currently serves as a workbench for testing and evaluating our situation-analytic and emotion-triggered approach for creating highly competitive and individualized business applications. [ABSTRACT FROM AUTHOR]

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 already rapidly growing AIEd literature base in higher education, now is the time to ensure that the field has a solid research and conceptual grounding. 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. [ABSTRACT FROM AUTHOR]

Electromyography-based wearable biosensors are used for prosthetic control. Machine learning prosthetic controllers are based on classification and regression models. The advantage of the regression approach is that it permits us to obtain a smoother and more natural controller. However, the existing training methods for regression-based solutions is the same as the training protocol used in the classification approach, where only a finite set of movements are trained. In this paper, we present a novel training protocol for myoelectric regression-based solutions that include a feedback term that allows us to explore more than a finite set of movements and is automatically adjusted according to real-time performance of the subject during the training session. Consequently, the algorithm distributes the training time efficiently, focusing on the movements where the performance is worse and optimizing the training for each user. We tested and compared the existing and new training strategies in 20 able-bodied participants and 4 amputees. The results show that the novel training procedure autonomously produces a better training session. As a result, the new controller outperforms the one trained with the existing method: for the able-bodied participants, the average number of targets hit is increased from 86% to 95% and the path efficiency from 40% to 84%, while for the subjects with limb deficiencies, the completion rate is increased from 58% to 69% and the path efficiency from 24% to 56%. [ABSTRACT FROM AUTHOR]

Today, reinforcement learning is one of the most effective machine learning approaches in the tasks of automatically adapting computer systems to user needs. However, implementing this technology into a digital product requires addressing a key challenge: determining the reward model in the digital environment. This paper proposes a usability reward model in multi-agent reinforcement learning. Well-known mathematical formulas used for measuring usability metrics were analyzed in detail and incorporated into the usability reward model. In the usability reward model, any neural network-based multi-agent reinforcement learning algorithm can be used as the underlying learning algorithm. This paper presents a study using independent and actor-critic reinforcement learning algorithms to investigate their impact on the usability metrics of a mobile user interface. Computational experiments and usability tests were conducted in a specially designed multi-agent environment for mobile user interfaces, enabling the implementation of various usage scenarios and real-time adaptations.

In response to the problem of disturbance in the imaging equipment of stratospheric airships, this study designs a vibration isolation and stability system for carrying imaging equipment. The system mainly consists of microprocessor, gimbal, voice coil motor (VCM) and rubber ring. By using adaptive control law based on characteristic model to control the double closed control loop of the motor composed of position loop and speed loop, the camera deflection caused by disturbance is effectively eliminated. Furthermore, in vertical vibration suppression, the adaptive control law based on the characteristic model is also applied to the double closed control loop of the voice coil motor, which removes most of the vertical vibration and realizes active vibration isolation. The passive isolation of the system is completed by rubber rings. The experimental results show that the vibration isolation and stabilization system have good performance in complex disturbance environments, effectively stabilizing the imaging equipment. [ABSTRACT FROM AUTHOR]

This article presents a promising self-learning-based robust control for output voltage tracking in DC–DC buck power converters, particularly for applications demanding high precision performance in face of large load uncertainties. The design involves a computationally simple online single hidden layer neural network, to rapidly estimate the unanticipated load changes and exogenous disturbances over a wide range. The controller is designed within a backstepping framework and utilizes the learnt uncertainty from the neural network for subsequent compensation, to eventually ensure an asymptotic stability of the tracking error dynamics. The results obtained feature a significant improvement of dynamic and steady-state performance concurrently for both output voltage and inductor current in contrast to other competent control strategies lately proposed in the literature for similar applications. Extensive numerical simulations and experimentation on a developed laboratory prototype are carried out to justify the practical applicability and feasibility of the proposed controller. Experimental results substantiate the claims of fast dynamic performance in terms of 94% reduction in the settling time, besides an accurate steady-state tracking for both output voltage and inductor current. Moreover, the close resemblance between computational and experimental results is noteworthy and unveils the immense potential of the proposed control system for technology transfer. [ABSTRACT FROM AUTHOR]

Navigation or route guidance systems are designed to provide drivers with real-time travel information and the associated recommended routes for their trips. Classical route choice models typically rely on utility theory to represent drivers’ route choice behavior. Such choices, however, may not be optimal from both the individual and the system perspectives. This is simply due to the fact that drivers usually have imperfect knowledge about the time-varying traffic conditions. In this article, we explore and propose a new model-free deep reinforcement learning (DRL) approach to solving the adaptive route guidance problem based on microsimulation. The proposed approach consists of three interconnected algorithms, including a network edge labeling algorithm, a routing plan identification algorithm, and an adaptive route guidance algorithm. Simulation experiments on both a toy network and a real-world network of Suzhou, China, are performed to demonstrate the effectiveness of the proposed approach in terms of guiding a single vehicle as well as multiple vehicles through complex traffic environments. Comparative results confirm that the DRL approach outperforms the traditional shortest path method by further reducing the average travel time in the network. [ABSTRACT FROM AUTHOR]

The present paper proposes the application of global and exact differentiators with dynamic gains based on higher-order sliding modes (HOSM) to the design of adaptive backstepping control for nonlinear uncertain systems of strict-feedback type. The use of this kind of differentiator in the closed-loop system allow us to guarantee global uniform stability (for any initial conditions) due to the variable nature of the dynamic gain. The dynamic gain can grow or decrease with the unmeasured state. In addition, asymptotic output tracking is also assured. In order to illustrate the results of the new theorem, the proposed controller is applied to a high-performance aircraft system, suppressing the wing-rock phenomenon usually observed for fast-speed flight conditions. Comparison results with a linear-inexact differentiator, a local HOSM differentiator with fixed gains and the proposed global and exact HOSM differentiator with dynamic gain shows the superiority of the latter over the former approaches. To demonstrate the practical efficacy of the proposed approach, we conclude with an experimental test featuring a DC motor and the novel differentiator-based backstepping control scheme.

Augmentative and alternative communication techniques (AAC) are essential to assist individuals facing communication difficulties. (1) Background: It is acknowledged that dynamic solutions that adjust to the changing needs of patients are necessary in the context of neuromuscular diseases. (2) Methods: In order address this concern, a differential approach was suggested that entailed the prior identification of the disease state. This approach employs fuzzy logic to ascertain the disease stage by analyzing intuitive patterns; it is contrasted with two intelligent systems. (3) Results: The results indicate that the AAC system's adaptability enhances with the progression of the disease's phases, thereby ensuring its utility throughout the lifespan of the individual. Although the adaptive AAC system exhibits signs of improvement, an expanded assessment involving a greater number of patients is required. (4) Conclusions: Qualitative assessments of comparative studies shed light on the difficulties associated with enhancing accuracy and adaptability. This research highlights the significance of investigating the use of fuzzy logic or artificial intelligence methods in order to solve the issue of symptom variability in disease staging. [ABSTRACT FROM AUTHOR]

Electromyography-based wearable biosensors are used for prosthetic control. Machine learning prosthetic controllers are based on classification and regression models. The advantage of the regression approach is that it permits us to obtain a smoother and more natural controller. However, the existing training methods for regression-based solutions is the same as the training protocol used in the classification approach, where only a finite set of movements are trained. In this paper, we present a novel training protocol for myoelectric regression-based solutions that include a feedback term that allows us to explore more than a finite set of movements and is automatically adjusted according to real-time performance of the subject during the training session. Consequently, the algorithm distributes the training time efficiently, focusing on the movements where the performance is worse and optimizing the training for each user. We tested and compared the existing and new training strategies in 20 able-bodied participants and 4 amputees. The results show that the novel training procedure autonomously produces a better training session. As a result, the new controller outperforms the one trained with the existing method: for the able-bodied participants, the average number of targets hit is increased from 86% to 95% and the path efficiency from 40% to 84%, while for the subjects with limb deficiencies, the completion rate is increased from 58% to 69% and the path efficiency from 24% to 56%.