Automatic Adaptation Research Articles

Adapting Software with Affective Computing: A Systematic Review

Strategies aimed at keeping the user's interest in using computer applications are being studied to provide greater user engagement, and can influence how people interact with computers. One of the approaches that can promote user engagement is Affective Computing (AC), based on the premise of recognizing the user's emotional state and adjusting the computer application to respond to such state in real-time. Although it is a relatively new area, over the past few years many research works have investigated the use of AC in various activities and objectives. To provide an overview on the use of AC in computer applications, this article presents a systematic literature review based on available articles on the main scientific databases of the Computer Science area. The main contribution of this review is the analysis of different types of applications. Based on the 58 articles analyzed, the main emotion recognition techniques and approaches to the adaptation of computer applications, as well as the limitations and challenges to be overcome were compiled. Our conclusions present the limitations and challenges still to be overcome in the area of automatic adaptation of computer applications by means of AC.

Design, Modeling and Control of a Novel Morphing Quadrotor

In this letter, the design, modeling and control of a novel morphing quadrotor are presented. The morphing quadrotor can fly stably and accurately in the air while simultaneously undergoing shape transformation, regardless of the asymmetry of the model. The four arms can rotate around hinges on the main body of the quadrotor to form various topological models. The arms are not in the same plane, so they can overlap with each other. In the extreme case, the width of the morphing quadrotor can be reduced to the diameter of a single rotor to allow the quadrotor to fly through narrow gaps more easily. Reinforcement learning (RL) with an extended-state approach is introduced in this paper to optimize the attitude control law and enable automatic adaptation to model changes. A deterministic policy gradient (DPG) algorithm based on an actor-critic structure with four neural networks in a model-free approach is used to train the controller. Finally, a linear programming method named fast simplex algorithm is presented to solve the control allocation problem of morphing quadrotors in real time with affordable computational cost in this paper. The controller has been tested on our real morphing quadrotor platform and achieves excellent flight performance.

Automatic online multi-source domain adaptation

Knowledge transfer across several streaming processes remain challenging problem not only because of different distributions of each stream but also because of rapidly changing and never-ending environments of data streams. Albeit growing research achievements in this area, most of existing works are developed for a single source domain which limits its resilience to exploit multi-source domains being beneficial to recover from concept drifts quickly and to avoid the negative transfer problem. An online domain adaptation technique under multi-source streaming processes, namely automatic online multi-source domain adaptation (AOMSDA), is proposed in this paper. The online domain adaptation strategy of AOMSDA is formulated under a coupled generative and discriminative approach of denoising autoencoder (DAE) where the central moment discrepancy (CMD)-based regularizer is integrated to handle the existence of multi-source domains thereby taking advantage of complementary information sources. The asynchronous concept drifts taking place at different time periods are addressed by a self-organizing structure and a node re-weighting strategy. Our numerical study demonstrates that AOMSDA is capable of outperforming its counterparts in 5 of 8 study cases while the ablation study depicts the advantage of each learning component. In addition, AOMSDA is general for any number of source streams. The source code of AOMSDA is shared publicly inhttps://github.com/Renchunzi-Xie/AOMSDA.git.

Digital Technologies for Innovative Mental Health Rehabilitation

Schizophrenia is a chronic mental illness, characterized by the loss of the notion of reality, failing to distinguish it from the imaginary. It affects the patient in life’s major areas, such as work, interpersonal relationships, or self-care, and the usual treatment is performed with the help of anti-psychotic medication, which targets primarily the hallucinations, delirium, etc. Other symptoms, such as the decreased emotional expression or avolition, require a multidisciplinary approach, including psychopharmacology, cognitive training, and many forms of therapy. In this context, this paper addresses the use of digital technologies to design and develop innovative rehabilitation techniques, particularly focusing on mental health rehabilitation, and contributing for the promotion of well-being and health from a holistic perspective. In this context, serious games and virtual reality allows for creation of immersive environments that contribute to a more effective and lasting recovery, with improvements in terms of quality of life. The use of machine learning techniques will allow the real-time analysis of the data collected during the execution of the rehabilitation procedures, as well as enable their dynamic and automatic adaptation according to the profile and performance of the patients, by increasing or reducing the exercises’ difficulty. It relies on the acquisition of biometric and physiological signals, such as voice, heart rate, and game performance, to estimate the stress level, thus adapting the difficulty of the experience to the skills of the patient. The system described in this paper is currently in development, in collaboration with a health unit, and is an engineering effort that combines hardware and software to develop a rehabilitation tool for schizophrenic patients. A clinical trial is also planned for assessing the effectiveness of the system among negative symptoms in schizophrenia patients.

Parametric Study of Nonequilibrium Shock Interference Patterns over a Fuselage-and-Wing Conceptual Vehicle

Predicting shock/shock and shock/boundary-layer interactions in gas flows that surround high-speed vehicles is key in aerodynamic design. Under typical hypersonic conditions, these flow structures are influenced by complex nonequilibrium phenomena leading to high-temperature effects. In this work, the conceptual Bedford wing-body vehicle is studied to analyze flow patterns in shock/shock and shock/boundary-layer interactions with thermochemical nonequilibrium. A parametric computational fluid dynamics study is carried out for different hypersonic operating conditions, with respect to the freestream Mach number. Simulations are performed with the SU2-NEMO solver coupled to the Mutation++ library, which provides all the necessary thermodynamic, kinetic, and transport properties of the mixture and chemical species. The Adaptive Mesh Generation library is used for automatic anisotropic mesh adaptation. Numerical results show that increasing the freestream Mach number from 4 to 10 leads to changes in the shock layer, locations of shock impingement, and regions of boundary-layer separation. Despite these changes, the change in freestream Mach number has little impact on the overall shock interaction structures.

Design of a novel inchworm in-pipe robot based on cam-linkage mechanism

This paper presents a novel double-direction inchworm in-pipe robot, called the Cam-Linkage Robot (CLR), used to carry sensors and instruments to perform inspection and cleaning jobs inside pipelines. The prototype has been developed to improve the driving ability and reduce the difficulty of control. CLR is suitable for pipe diameters from 360 mm to 400 mm due to its functions of manual adjustment and automatic adaptation. The structure of CLR was presented and some critical design issues on the principle of cam-linkage mechanism were discussed. Based on cam-linkage mechanism, CLR could press the wall actively and creep in two directions via only one motor, so this research has broken the limitation that traditional active wall-press robot needs more than one actuator. The cam pressure angle could be reduced to 0, and the propulsion ability was almost not weakened by the support motion at the stable support stage. Finally, experiments were conducted to validate the locomotion principle and the effectiveness of CLR.

Uyarlanabilir Nöro-Bulanık Çıkarım Sistemi Tabanlı Modern Kontrolörlerle Bir Hidroelektrik Santralinde Frekans Kontrolü

In power systems, the constant frequency, constant voltage, and the power output are desired and determine the quality of the generated electrical energy. Therefore, frequency control is crucial in power systems. The parameters of conventional controllers used in power generation plants are determined according to the system's characteristics at the stage of installation, they cannot adapt to the changing system dynamics as the lifespan of power plants increases. Thus, studies on the automatic adaptation of controller parameters to the continuously changing system dynamics are needed. In this study, conventional PI and PID controllers applied to the power system for frequency control of a hydroelectric power plant were examined comparatively with Fuzzy Gain Scheduled PI (FGPI) controller and Adaptive Neuro-Fuzzy Inference System-based PI (ANFIS-PI) and PID (ANFIS-PID) controllers in the simulation environment. The obtained results demonstrated that Adaptive Neuro-Fuzzy Inference System-based controllers were quite successful compared to the others.

An Exergame Solution for Personalized Multicomponent Training in Older Adults

In addition to contributing to increased training motivation, exergames are a promising approach to counteract age-related impairments. Mobility limitations, cognitive impairment, and urinary incontinence are very common in older adults. To optimally address these conditions, exergames should include interventions for strength, balance, cognition, and pelvic floor muscle training. In this study, we develop a personalized multicomponent exergame solution for the geriatric rehabilitation of age-related impairments. The exergame can provide interventions for balance, strength, cognition, and urinary incontinence in one single session, accommodating the needs of older adults with multiple disabilities. For its development, we involved a multidisciplinary team that helped us to specify the structure and contents of the exergame considering training requirements, game design principles, and end-user characteristics. In addition to allowing the customization of the training components, the exergame includes automatic adaptation of difficulty/load, in line with player progress over time. The game mechanics ensures the fulfilment of training needs as defined by the therapist. The exergame is cross-platform compatible (web-based) and includes novel means of interaction with wearable sensors.

A Bayesian inference and model selection algorithm with an optimization scheme to infer the model noise power

ABSTRACT Model fitting is possibly the most extended problem in science. Classical approaches include the use of least-squares fitting procedures and maximum likelihood methods to estimate the value of the parameters in the model. However, in recent years, Bayesian inference tools have gained traction. Usually, Markov chain Monte Carlo (MCMC) methods are applied to inference problems, but they present some disadvantages, particularly when comparing different models fitted to the same data set. Other Bayesian methods can deal with this issue in a natural and effective way. We have implemented an importance sampling (IS) algorithm adapted to Bayesian inference problems in which the power of the noise in the observations is not known a priori. The main advantage of IS is that the model evidence can be derived directly from the so-called importance weights – while MCMC methods demand considerable postprocessing. The use of our adaptive target adaptive importance sampling (ATAIS) method is shown by inferring, on the one hand, the parameters of a simulated flaring event that includes a damped oscillation and, on the other hand, real data from the Kepler mission. ATAIS includes a novel automatic adaptation of the target distribution. It automatically estimates the variance of the noise in the model. ATAIS admits parallelization, which decreases the computational run-times notably. We compare our method against a nested sampling method within a model selection problem.

Automatically adaptive, stabilized finite element method via residual minimization for heterogeneous, anisotropic advection–diffusion–reaction problems

We describe a stable finite element formulation for advection–diffusion–reaction problems that allows for the easy implementation of robust automatic adaptivity. We consider locally vanishing, heterogeneous, and anisotropic diffusivities, as well as advection-dominated diffusion problems. We apply a general stabilized finite element framework (Calo et al., 2020) that seeks a discrete solution through a residual minimization process on a proper stable discontinuous Galerkin (dG) dual norm. This technique leads to a sequence of saddle-point problems that are discretely stable and deliver a robust error estimate that drives mesh adaptivity. In this work, we demonstrate the method’s efficiency in extreme scenarios, where the solutions’ quality and performance are comparable to classical discontinuous Galerkin formulations in the respective discrete space norm on a particular mesh. We focus on the practical implementation of the adaptive technology to a broad range of engineering applications, from singularly perturbed linear advection-dominated diffusion to highly non-linear problems. This technique starts from coarse meshes and adapts itself to achieve a user-specified solution quality.

Skeleton Driven Action Recognition Using an Image-Based Spatial-Temporal Representation and Convolution Neural Network

Individuals with Autism Spectrum Disorder (ASD) typically present difficulties in engaging and interacting with their peers. Thus, researchers have been developing different technological solutions as support tools for children with ASD. Social robots, one example of these technological solutions, are often unaware of their game partners, preventing the automatic adaptation of their behavior to the user. Information that can be used to enrich this interaction and, consequently, adapt the system behavior is the recognition of different actions of the user by using RGB cameras or/and depth sensors. The present work proposes a method to automatically detect in real-time typical and stereotypical actions of children with ASD by using the Intel RealSense and the Nuitrack SDK to detect and extract the user joint coordinates. The pipeline starts by mapping the temporal and spatial joints dynamics onto a color image-based representation. Usually, the position of the joints in the final image is clustered into groups. In order to verify if the sequence of the joints in the final image representation can influence the model’s performance, two main experiments were conducted where in the first, the order of the grouped joints in the sequence was changed, and in the second, the joints were randomly ordered. In each experiment, statistical methods were used in the analysis. Based on the experiments conducted, it was found statistically significant differences concerning the joints sequence in the image, indicating that the order of the joints might impact the model’s performance. The final model, a Convolutional Neural Network (CNN), trained on the different actions (typical and stereotypical), was used to classify the different patterns of behavior, achieving a mean accuracy of 92.4% ± 0.0% on the test data. The entire pipeline ran on average at 31 FPS.

Distributed Intelligence in the Internet of Things: Challenges and Opportunities

Widespread adoption of smart IoT devices is accelerating research for new techniques to make IoT applications secure, scalable, energy-efficient, and capable of working in mission-critical use cases, which require an ability to function offline. In this context, the novel combination of distributed ledger technology (DLT) and distributed intelligence (DI) is seen as a practical route towards the decentralisation of IoT architectures. This paper surveys DI techniques in IoT and commences by briefly explaining the need for DI, by proposing a comprehensive taxonomy of DI in IoT. This taxonomy is then used to review existing techniques and to investigate current challenges that require careful attention and consideration. Based on the taxonomy, IoT DI techniques can be classified into five categories based on the factors that support distributed functionality and data acquisition: cloud-computing, mist-computing, distributed-ledger-technology, service-oriented-computing and hybrid. Existing techniques are compared and categorized mainly based on related challenges, and the level of intelligence supported. We evaluate more than thirty current research efforts in this area. We define many significant functionalities that should be supported by DI frameworks and solutions. Our work assists system architects and developers to select the correct low-level communication techniques in an integrated IoT-to-DLT-to-cloud system architecture. The benefits and shortcomings of different DI approaches are presented, which will inspire future work into automatic hybridization and adaptation of DI mechanisms. Finally, open research issues for distributed intelligence in IoT are discussed.

Injecting domain knowledge in multi-objective optimization problems: A semantic approach

In the field of complex problem optimization with metaheuristics, semantics has been used for modeling different aspects, such as: problem characterization, parameters, decision-maker’s preferences, or algorithms. However, there is a lack of approaches where ontologies are applied in a direct way into the optimization process, with the aim of enhancing it by allowing the systematic incorporation of additional domain knowledge. This is due to the high level of abstraction of ontologies, which makes them difficult to be mapped into the code implementing the problems and/or the specific operators of metaheuristics. In this paper, we present a strategy to inject domain knowledge (by reusing existing ontologies or creating a new one) into a problem implementation that will be optimized using a metaheuristic. Thus, this approach based on accepted ontologies enables building and exploiting complex computing systems in optimization problems. We describe a methodology to automatically induce user choices (taken from the ontology) into the problem implementations provided by the jMetal optimization framework. With the aim of illustrating our proposal, we focus on the urban domain. Concretely, we start from defining an ontology representing the domain semantics for a city (e.g., building, bridges, point of interest, routes, etc.) that allows defining a-priori preferences by a decision maker in a standard, reusable, and formal (logic-based) way. We validate our proposal with several instances of two use cases, consisting in bi-objective formulations of the Traveling Salesman Problem (TSP) and the Radio Network Design problem (RND), both in the context of an urban scenario. The results of the experiments conducted show how the semantic specification of domain constraints are effectively mapped into feasible solutions of the tackled TSP and RND scenarios. This proposal aims at representing a step forward towards the automatic modeling and adaptation of optimization problems guided by semantics, where the annotation of a human expert can be now considered during the optimization process.

Real-Time Ventricular Volume Measured Using the Intracardiac Electromyogram.

Left ventricular end-diastolic volume (EDV) is an important parameter for monitoring patients with left ventricular assist devices (LVADs) and might be useful for automatic LVAD work adaptation. However, continuous information on the EDV is unavailable to date. The depolarization amplitude (DA) of the noncontact intracardiac electromyogram (iEMG) is physically related to the EDV. Here, we show how a left ventricular (LV) volume sensor based on the iEMG might provide beat-wise EDV estimates. The study was performed in six pigs while undergoing a series of controlled changes in hemodynamic states. The LV volume sensor consisted of four conventional pacemaker electrodes measuring the far-field iEMG inside the LV blood pool, using a novel unipolar amplifier. Simultaneously, noninvasive measurements of EDV and hematocrit were recorded. The proposed EDV predictor was tested for statistical significance using a mixed-effect model and associated confidence intervals. A statistically significant (p = 3e-07) negative correlation was confirmed between the DA of the iEMG and the EDV as measured by electric impedance at a slope of -0.069 (-0.089, -0.049) mV/mL. The DA was slightly decreased by increased hematocrit (p = 0.039) and moderately decreased with the opening of the thorax (p = 0.003). The DA of the iEMG proved to be a significant, independent predictor of EDV. The proposed LV volume sensor is simple to integrate into the inflow cannula of an LVAD and thus has the potential to inform the clinician about the state of LV volume in real time and to automatically control the LVAD.

An adaptive short-term forecasting method for the energy yield of flat-plate solar collector systems

The number of large-scale solar thermal installations has increased rapidly in Europe in recent years, with 70% of these systems operating with flat-plate solar collectors. Since these systems cannot be easily switched on and off but directly depend on the solar radiation, they have to be combined with other technologies or integrated in large energy systems. In order to most efficiently integrate and operate solar systems, it is of great importance to consider their expected energy yield to better schedule heat production, storage and distribution. To do so the availability of accurate forecasting methods for the future solar energy yield are essential. Currently available forecasting methods do not meet three important practical requirements: simple implementation, automatic adaption to seasonal changes and wide applicability. For these reasons, a simple and adaptive forecasting method is presented in this paper, which allows to accurately forecast the solar heat production of flat-plate collector systems considering weather forecasts. The method is based on a modified collector efficiency model where the parameters are continuously redetermined to specifically consider the influence of the time of the day. In order to show the wide applicability the method is extensively tested with measurement data of various flat-plate collector systems covering different applications (below 200°Celsius), sizes and orientations. The results show that the method can forecast the solar yield very accurately with a Mean Absolute Range Normalized Error (MARNE) of about 5% using real weather forecasts as inputs and outperforms common forecasting methods by being nearly twice as accurate.

Genetic robust kernel sample selection for chemometric data analysis

AbstractIn this work, we propose a new algorithm to improve existing techniques used in the field of spectroscopic data regression analysis. In particular, it combines the power of nonlinear kernel regressors (kernel ridge regression [KRR], kernel principal component regression [KPCR], and Gaussian process regression [GPR]) with an optimization based on nondominated sorting multi‐objective genetic algorithm (NSGAII) to filter the residual outliers in the prediction space and leverage points in the features space. The proposed algorithm, contrary to most existing robust algorithms, simultaneously optimizes many complementary objectives for an automatic adaptation and thus a better outliers detection. It is well known that the elimination of outliers greatly improves the regression model. It is thus the aim of this work to develop a new robust regression algorithm. It has been applied on five different datasets, and the results are compared to both classical nonlinear regression methods and the commonly used robust regression methods robust continuum regression (RCR), partial robust M‐regression (PRM), robust principal component regression (RPCR), robust PLSR (RSIMPLS), and locally weighted regression (LWR). They show that the proposed algorithm outperforms the classical nonlinear regression methods and is a promising competitor to the robust methods outperforming most of them. Even though the results obtained are only from five datasets, this algorithm can be considered an interesting contribution for improving data analysis in the field of chemometrics.

Automatic adaptation of a Solar Plant Intelligent Control System

The article continues the authors’ scientific research in the field of solar plant intelligent control system. This paper presents a developed on-line and off-line automatic adaptation methods which allow solar plant intelligent control system to adapt to rapid dynamic of insolation in real time and to seasonal insolation fluctuations during night time. The experimental results show that the proposed solar plant intelligent self-adaptive control system produced robust and rapid maximum power point tracking, as compared to a classical solar plant MPPT system based on Perturb & Observe or particle swarm optimization under seasonal fluctuations or rapid dynamic of insolation.

Continuous Scale-Space Direct Image Alignment for Visual Odometry From RGB-D Images

In this letter, we propose a novel dense 3D image alignment algorithm that estimates the Euclidean transformation between pairs of camera poses from pixel intensities. The novelty consists in the automatic scale adaptation within each level of a multi-resolution image pyramid, using the scale-space representation of images. This is done through the continuous optimization of a scale parameter along with camera pose parameters in the same optimization framework. The proposed approach permits to significantly improve the robustness of the direct image alignment to large inter-frame motion. Various experiments on the TUM RGB-D dataset show that the proposed algorithm outperforms a fixed scale pyramid-based state-of-the-art alignment method.

A low power reconfigurable ADC for bioimpedance monitroing system

This article introduces a re-configurable pipeline analog-to-digital converter (ADC) deliberated for implantable surveillance devices for bio-impedance monitoring systems. To improve the efficiency of the bio-impedance method, an automatic adaptation circuit is introduced. This adaptive unit is responsible for setting the resolution and sampling rate on the basis of amplitude and frequency of the signal. Using a new, low-power automatic adaptation circuit low power consumption is achieved by using Dynamic Threshold metal oxide semiconductor (DTMOS) technique, it can automatically determine its setup. The converter has two modes of operations. In high-resolution mode, the converter has a 12-bit resolution and at low resolution mode, 8-bit resolution is used. The ADC bandwidth of low-speed mode is 100 kHz and high-speed mode is 1 GHz. The architecture is designed using 180 nm technology and simulated using Cadence virtuoso tool. The results achieved, low power consumption i.e. 0.844 mw, and it is operated with 1 V power supply. For signal to noise and distortion ratio (SNDR), effective number of bits (ENOB), the converter utilizes 71.06 dB, 11.45 in 12-bit and 72.3 dB, 7.41 in 8-bit mode respectively. By using proposed method around 20% of power consumption is reduced and 40% power supply is decreased. The proposed design is also used for mixed signal circuit testing.

A Highly Configurable High-Level Synthesis Functional Pattern Library

FPGA has recently played an increasingly important role in heterogeneous computing, but Register Transfer Level design flows are not only inefficient in design, but also require designers to be familiar with the circuit architecture. High-level synthesis (HLS) allows developers to design FPGA circuits more efficiently with a more familiar programming language, a higher level of abstraction, and automatic adaptation of timing constraints. When using HLS tools, such as Xilinx Vivado HLS, specific design patterns and techniques are required in order to create high-performance circuits. Moreover, designing efficient concurrency and data flow structures requires a deep understanding of the hardware, imposing more learning costs on programmers. In this paper, we propose a set of functional patterns libraries based on the MapReduce model, implemented by C++ templates, which can quickly implement high-performance parallel pipelined computing models on FPGA with specified simple parameters. The usage of this pattern library allows flexible adaptation of parallel and flow structures in algorithms, which greatly improves the coding efficiency. The contributions of this paper are as follows. (1) Four standard functional operators suitable for hardware parallel computing are defined. (2) Functional concurrent programming patterns are described based on C++ templates and Xilinx HLS. (3) The efficiency of this programming paradigm is verified with two algorithms with different complexity.