Adaptive Discretization for Computerized Tomography

Two adaptive discretization frameworks are tested for computerized tomography (CT) data reconstruction. Removal of inactive pixels is primary motivation. Efficient and user independent entropy optimized masking is employed for spatial filtering purposes. Density of nodes at high gradient of reconstructed physical property is used as adaptation criterion. An alternative option, independent from noisy projection data and nature of the physical properties, is also discussed. Sensitivity analysis between the uniform and nonuniform (evolved via adaptive route) reconstruction grid reveals the utility of nonuniform grids. Iterative and transform based reconstruction techniques are used. Outcomes are tested successfully on three real world projection data from two different compact CT setups and one commercial high-resolution micro-CT scanner.     

Applied data science in patient-centric healthcare: Adaptive analytic systems for empowering physicians and patients

We define the emerging research field of applied data science as the knowledge discovery process in which analytic systems are designed and evaluated to improve the daily practices of domain experts. We investigate adaptive analytic systems as a novel research perspective of the three intertwining aspects within the knowledge discovery process in healthcare: domain and data understanding for physician- and patient-centric healthcare, data preprocessing and modelling using natural language processing and (big) data analytic techniques, and model evaluation and knowledge deployment through information infrastructures. We align these knowledge discovery aspects with the design science research steps of problem investigation, treatment design, and treatment validation, respectively. We note that the adaptive component in healthcare system prototypes may translate to data-driven personalisation aspects including personalised medicine. We explore how applied data science for patient-centric healthcare can thus empower physicians and patients to more effectively and efficiently improve healthcare. We propose meta-algorithmic modelling as a solution-oriented design science research framework in alignment with the knowledge discovery process to address the three key dilemmas in the emerging “post-algorithmic era” of data science: depth versus breadth, selection versus configuration, and accuracy versus transparency.     

Convolutional neural network with adaptive inferential framework for skeleton-based action recognition

In the task of skeleton-based action recognition, CNN-based methods represent the skeleton data as a pseudo image for processing. However, it still remains as a critical issue of how to construct the pseudo image to model the spatial dependencies of the skeletal data. To address this issue, we propose a novel convolutional neural network with adaptive inferential framework (AIF-CNN) to exploit the dependencies among the skeleton joints. We particularly investigate several initialization strategies to make the AIF effective with each strategy introducing the different prior knowledge. Extensive experiments on the dataset of NTU RGB+D and Kinetics-Skeleton demonstrate that the performance is improved significantly by integrating the different prior information. The source code is available at: https://github.com/hhe-distance/AIF-CNN.     

Design of an adaptive super-twisting decoupled terminal sliding mode control scheme for a class of fourth-order systems

This paper proposes an adaptive super-twisting decoupled terminal sliding mode control technique for a class of fourth-order systems. The adaptive-tuning law eliminates the requirement of the knowledge about the upper bounds of external perturbations. Using the proposed control procedure, the state variables of cart-pole system are converged to decoupled terminal sliding surfaces and their equilibrium points in the finite time. Moreover, via the super-twisting algorithm, the chattering phenomenon is avoided without affecting the control performance. The numerical results demonstrate the high stabilization accuracy and lower performance indices values of the suggested method over the other ones. The simulation results on the cart-pole system as well as experimental validations demonstrate that the proposed control technique exhibits a reasonable performance in comparison with the other methods.     

The initiation and propagation of detonation in supersonic combustible flow with boundary layer

Adaptive simulations solving the Navier-Stokes equations have been conducted in order to get a better understanding on the detonation initiation and propagation in a stoichiometric H₂/O₂/Ar supersonic mixture with boundary layer. The detonation is initiated by a continuous hot jet. When reflecting on the wall, the jet induced bow shock interacts with the boundary layer and forms the shock boundary layer interaction phenomena, while in Euler result the bow shock forms Mach reflection. The investigation shows that the Navier-Stokes simulation result is structurally in better agreement with the experiment compared with that of the inviscid Euler simulation result. The bow shock interacts with the separation shock, forming the shock induced combustion behind the interaction zone. Then the combustion front couples with shock and forms Mach stem induced detonation. The Mach stem induced detonation continues to getting higher and propagating upstream, initiating the main flow. The initiated partial detonation exists with the separation shock induced combustion front, forming an “oblique shock induced combustion-partial detonation” structure in the main flow. The investigation on the influence of free stream Mach number further confirms that the boundary layer has an important influence on detonation initiation. The parametric studies also show that there exists a free stream Mach number range to initiate the partial detonation in supersonic combustible flow successfully.     

Adaptive neuro-fuzzy inference system (ANIFS) and artificial neural network (ANN) applied for indium (III) adsorption on carbonaceous materials

Abstract

In this paper, we present an initial study relating the adsorption of indium (III) onto carbonaceous materials, namely the activated carbon (AC), multiwalled carbon nanotubes functionalized with OH (MWCNT–OH), and the multiwalled carbon nanotubes functionalized with COOH (MWCNT–COOH). The main objective of this study is the development of the adaptive neuro-fuzzy inference system (ANFIS) and an artificial neural network (ANN) for predicting the adsorption capacity in different operating conditions for different materials. Both models take into account the adsorbent type, adsorbent dosage (0.05, 0.25, 0.5, 1.0, 1.5, and 2.0?g L^?1), and the contact time (5, 20, 60, and 120?min) for predicting the adsorption capacity, which varied from 12.896 to 981.000?mg g^?1, a total record of 72 was used. Both modeling methodologies applied can represent the experimental data, taking into account the statistical values obtained. The ANFIS achieved the best performance when the hybrid method was selected, this leads into R of 0.9998, RMSE of 48,373 with 250 epochs. On the other hand, the ANN can represent the best performance when using the Levenberg–Marquardt algorithm, reaching an R of 0.9831, MSE of 0.0180 and 9 epochs. Considering the modeling and experimental aspects indicates that the increase of the adsorbent dosage diminished the adsorbent capacity. The increase of the contact time causes the effect to increase the adsorption capacity until its equilibrium. Lastly, it is possible to conclude that the MWCNT–COOH is the most suitable adsorbent to be used between the selected materials.     

Adaptive sliding mode disturbance rejection control with prescribed performance for robotic manipulators

This study proposes an adaptive sliding mode disturbance rejection control with prescribed performance for robotic manipulators. A transformation with respect to tracking error using certain performance functions is used to ensure the transient and steady-state performances of the trajectory tracking control for robotic manipulators. Using the transformed error, a nonsingular terminal sliding mode surface is proposed. A continuous terminal sliding mode control (SMC) is presented to stabilize the system. To compensate for the uncertainty and external disturbance, a novel sliding mode disturbance observer is proposed. Considering the unknown boundary of the derivative of a lumped disturbance, an adaptive law based on the idea of equivalent control is designed. Combining the adaptive law, continuous nonsingular terminal SMC, and sliding mode disturbance observer, the adaptive sliding mode disturbance rejection control with prescribed performance is developed. Simulations are carried out to demonstrate the effectiveness of the proposed approach.     

An enhancement algorithm based on adaptive updating template with Gaussian model for Si3N4 ceramic bearing roller surface defects detection

The method based on machine vision image processing is used to detect the surface defects of Si₃N₄ bearing roller. Owing to the variety of defects, small area and low contrast, it is easy to miss or error detection. In this paper, an adaptive update template defect enhancement algorithm based on Gaussian model is proposed. First, a large number of surface images of Si₃N₄ bearing roller are collected to obtain the non-defect background statistical feature, and the background characteristic curve is fitted by Gaussian model. Further, the initial background template is gained according to the Gaussian curve. Then, combined with the gray distribute of defect images and initial background template, unique adaptive update template can be established. Finally, subtraction operation and nonlinear enhancement are used to improve the comparison of defect information and background. Through inverse sorting, adaptive threshold segmentation and Canny operation, the precise positioning of defects is realized. The enhancement algorithm can effectively enhance the contrast and eliminate the influence of noise. The average detection time is 0.84s, and the detection accuracy is 96.2%.     

Dynamic load-altering attack detection based on adaptive fading Kalman filter in power systems

This paper presents an effective and feasible method for detecting dynamic load-altering attacks (D-LAAs) in a smart grid. First, a smart grid discrete system model is established in view of D-LAAs. Second, an adaptive fading Kalman filter (AFKF) is designed for estimating the state of the smart grid. The AFKF can completely filter out the Gaussian noise of the power system, and obtain a more accurate state change curve (including consideration of the attack). A Euclidean distance ratio detection algorithm based on the AFKF is proposed for detecting D-LAAs. Amplifying imperceptible D-LAAs through the new Euclidean distance ratio improves the D-LAA detection sensitivity, especially for very weak D-LAA attacks. Finally, the feasibility and effectiveness of the Euclidean distance ratio detection algorithm are verified based on simulations.     

Nonlinear controller design based on cascade adaptive sliding mode control for PEM fuel cell air supply systems

Optimized robust control for proton exchange membrane (PEM) fuel cell air supply systems is now a hot topic in improving the performance of oxygen excess ratio (OER) and the net power. In this paper, a cascade adaptive sliding mode control method is proposed to regulate oxygen excess ratio (OER) for proton exchange membrane (PEM) fuel cell air supply systems. Based on a simplified sixth-order nonlinear dynamic model, which takes parametric uncertainties, external disturbances and measurement noises into consideration, the nonlinear controller based on cascade adaptive sliding mode (NC-ASM) control is proposed. The method combines the nonlinear terms of super twisting algorithm and two added linear terms, and the modified second order sliding mode (SOSM) algorithm based on an observer is employed to form a cascade structure. Besides, an adaptive law is also utilized to regulate the parameters of the NC-ASM controller online. The performance of the controller is implemented on a real-time emulator. The results show that the proposed strategy performs better than the conventional constant sliding mode (CSM) control and PID method. Though during large range of load current and in the presence of various uncertainties, disturbances and noises, the NC-ASM controller can always converge rapidly, the feasibility and effectiveness are validated.