Robust Tuning Research Articles

A hybrid deep learning skin cancer prediction framework

Skin cancer, a critical health concern, necessitates accurate early detection and classification to mitigate its impact. However, the limited availability of medical datasets and the challenge of optimizing learnable parameters in deep learning strategies for medical images pose significant hurdles. To address these challenges, we propose an innovative solution—a hybrid artificial intelligence (AI) framework for skin cancer prediction. This framework consists of two pivotal steps: firstly, a comprehensive skin cancer dataset is curated by combining diverse public datasets encompassing multiple disease types. This facilitates robust weight tuning of Convolutional Neural Networks (CNNs) by enhancing the diversity of the learning process. Subsequently, the optimization of deep learning is meticulously executed through the artificial Bee Colony (ABC) strategy, effectively mitigating the potential adverse effects of initial parameter randomness on AI model performance. Rigorous evaluation of the hybrid framework against eight prominent CNN models, including DenseNet121, InceptionResNetV2, and others, underscores its superior predictive capabilities. The optimized hybrid framework achieves exceptional results, boasting an accuracy of 93.04%, recall of 92.0%, precision of 93.0%, and an impressive F1-score of 93.12%. In summary, our proposed hybrid solution demonstrates a substantial advancement in multi-disease skin cancer classification. It outperforms existing AI models and holds promise as a pragmatic smart solution with far-reaching implications.

Robust PI-PD Controller Design: Industrial Simulation Case Studies and a Real-Time Application

PI-PD controllers have superior performance compared to traditional PID controllers, especially for controlling unstable and integrating industrial processes with time delays. However, computing the four tuning parameters of this type of controller is not an easy task. Recently, there has been significant interest in determining the tuning rules for PI-PD controllers that utilize the stability region. Currently, most tuning rules for the PI-PD controller are presented graphically, which can be time-consuming and act as a barrier to their industrial application. There is a lack of analytical tuning guidelines in the literature to address this shortfall. However, the existing analytical tuning guidelines do not consider a rigorous design approach. This work proposes new robust analytical tuning criteria based on predefined gain and phase margin bounds, as well as the centroid of the stability region. The proposed method has been tested using various simulation studies related to a DC–DC buck converter, a DC motor, and a heat exchanger. The results indicate that the proposed tuning rules exhibit strong performance against parameter uncertainty with minimal overshoots. Furthermore, the suggested technique for simultaneous control of yaw and pitch angles has been tested in a real-time application using the twin rotor multi-input multi-output system (TRMS). Real-time results indicate that, compared to other methods under investigation, the suggested approach provides nearly minimal overshoots.

Integrated Active Quenching Circuit for high-rate and distortionless SPAD-based time-resolved fluorescence applications.

Time-Correlated Single Photon Counting (TCSPC) is a pivotal technique in low-light-detection applications, renowned for its exceptional sensitivity and bandwidth, widely used in Fluorescence Lifetime Imaging Microscopy (FLIM) and quantum optics. Despite its features, TCSPC is significantly hindered by the pile-up effect, which may distort measurements at high photon-detection rates. Overcoming pile-up is challenging, with traditional solutions often involving complex post-processing or multichannel systems, complicating the TCSPC setup and limiting performance. A breakthrough to overcome this issue is matching the photodetector dead time to an integer multiple of the laser period, obtaining a distortionless histogram even at high illumination conditions. Building on this concept, we present an Active Quenching Circuit (AQC) developed in high-voltage 150 nm technology, achieving unprecedented control over the Single Photon Avalanche Diode (SPAD) dead time. Our design compensates for Process, Voltage, and Temperature (PVT) variations, ensuring ultra precise and robust dead time tuning. The presented AQC achieves a dead-time resolution of 50 ps suitable for time-resolved experiments within a selectable range of laser frequencies from 20 to 100 MHz, maintaining close-to- ideal linearity in dead-time control. Experimental validations through fluorescence measurements reveal a distortion as low as 0.43% under elevated count-rate conditions, highlighting the efficacy of our circuit in overcoming the pile-up limitation.

Advanced Method Optimization for Sampling and Analysis Instrumentation.

This work presents a generalized approach for analytical method optimization that branches the gap between techniques historically employed and accurate modern optimization techniques suitable for various applications. The novelty of the described strategy is the utilization of multivariate, multiobjective optimization with Karush-Kuhn-Tucker conditions to bound the optimization space to solutions within the physical limitations of instrumentation. Briefly, the basic steps outlined in this paper are to (1) determine the objective(s) that should be maximized or minimized based on the goals of the analytical application, (2) conduct a screening experiment, (3) perform ANOVA to determine the parameters which have a statistically significant effect on the objective, (4) conduct an experiment (e.g., Box-Behnken design) to collect data for fitting the objective equation, and (5) determine the physical constraints of the parameters and solve the Lagrangian to determine the optimal method parameters. A broad approach to optimization target selection allows for robust method tuning to develop improved data sets amenable for chemometrics and machine learning algorithm development. Gas chromatography-mass spectrometry was selected as a use case due to its broad use across scientific fields and time-consuming method development involving numerous parameters. This strategy can reduce the cost of research, improve data quality, and enable the rapid development of new analytical techniques.

Performance Evaluation of Fractional Proportional–Integral–Derivative Controllers Tuned by Heuristic Algorithms for Nonlinear Interconnected Tanks

This article presents an in-depth analysis of three advanced strategies to tune fractional PID (FOPID) controllers for a nonlinear system of interconnected tanks, simulated using MATLAB. The study focuses on evaluating the performance characteristics of system responses controlled by FOPID controllers tuned through three heuristic algorithms: Ant Colony Optimization (ACO), Grey Wolf Optimizer (GWO), and Flower Pollination Algorithm (FPA). Each algorithm aims to minimize its respective cost function using various performance metrics. The nonlinear model was linearized around an equilibrium point using Taylor Series expansion and Laplace transforms to facilitate control. The FPA algorithm performed better with the lowest Integral Square Error (ISE) criterion value (297.83) and faster convergence in constant values and fractional orders. This comprehensive evaluation underscores the importance of selecting the appropriate tuning strategy and performance index, demonstrating that the FPA provides the most efficient and robust tuning for FOPID controllers in nonlinear systems. The results highlight the efficacy of meta-heuristic algorithms in optimizing complex control systems, providing valuable insights for future research and practical applications, thereby contributing to the advancement of control systems engineering.

Robust Tuning of Optimized Tuned Controller for Wind Power System Network to Improve Power Quality

Robust Tuning of Optimized Tuned Controller for Wind Power System Network to Improve Power Quality

A Particle Swarm and Smell Agent-Based Hybrid Algorithm for Enhanced Optimization

The particle swarm optimization (PSO) algorithm is widely used for optimization purposes across various domains, such as in precision agriculture, vehicular ad hoc networks, path planning, and for the assessment of mathematical test functions towards benchmarking different optimization algorithms. However, because of the inherent limitations in the velocity update mechanism of the algorithm, PSO often converges to suboptimal solutions. Thus, this paper aims to enhance the convergence rate and accuracy of the PSO algorithm by introducing a modified variant, which is based on a hybrid of the PSO and the smell agent optimization (SAO), termed the PSO-SAO algorithm. Our specific objective involves the incorporation of the trailing mode of the SAO algorithm into the PSO framework, with the goal of effectively regulating the velocity updates of the original PSO, thus improving its overall performance. By using the trailing mode, agents are continuously introduced to track molecules with higher concentrations, thus guiding the PSO’s particles towards optimal fitness locations. We evaluated the performance of the PSO-SAO, PSO, and SAO algorithms using a set of 37 benchmark functions categorized into unimodal and non-separable (UN), multimodal and non-separable (MS), and unimodal and separable (US) classes. The PSO-SAO achieved better convergence towards global solutions, performing better than the original PSO in 76% of the assessed functions. Specifically, it achieved a faster convergence rate and achieved a maximum fitness value of −2.02180678324 when tested on the Adjiman test function at a hopping frequency of 9. Consequently, these results underscore the potential of PSO-SAO for solving engineering problems effectively, such as in vehicle routing, network design, and energy system optimization. These findings serve as an initial stride towards the formulation of a robust hyperparameter tuning strategy applicable to supervised machine learning and deep learning models, particularly in the domains of natural language processing and path-loss modeling.

Towards flexibility and robustness of LSM trees

Log-structured merge trees (LSM trees) are increasingly used as part of the storage engine behind several data systems, and are frequently deployed in the cloud. As the number of applications relying on LSM-based storage backends increases, the problem of performance tuning of LSM trees receives increasing attention. We consider both nominal tunings—where workload and execution environment are accurately known a priori—and robust tunings—which consider uncertainty in the workload knowledge. This type of workload uncertainty is common in modern applications, notably in shared infrastructure environments like the public cloud. To address this problem, we introduce Endure, a new paradigm for tuning LSM trees in the presence of workload uncertainty. Specifically, we focus on the impact of the choice of compaction policy, size ratio, and memory allocation on the overall performance. Endure considers a robust formulation of the throughput maximization problem and recommends a tuning that offers near-optimal throughput when the executed workload is not the same, instead in a neighborhood of the expected workload. Additionally, we explore the robustness of flexible LSM designs by proposing a new unified design called K-LSM that encompasses existing designs. We deploy our robust tuning system, Endure, on a state-of-the-art key-value store, RocksDB, and demonstrate throughput improvements of up to 5×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes $$\\end{document} in the presence of uncertainty. Our results indicate that the tunings obtained by Endure are more robust than tunings obtained under our expanded LSM design space. This indicates that robustness may not be inherent to a design, instead, it is an outcome of a tuning process that explicitly accounts for uncertainty.

Comparison of head direction cell firing characteristics across thalamo-parahippocampal circuitry.

Head direction (HD) cells, which fire persistently when an animal's head is pointed in a particular direction, are widely thought to underlie an animal's sense of spatial orientation and have been identified in several limbic brain regions. Robust HD cell firing is observed throughout the thalamo-parahippocampal system, although recent studies report that parahippocampal HD cells exhibit distinct firing properties, including conjunctive aspects with other spatial parameters, which suggest they play a specialized role in spatial processing. Few studies, however, have quantified these apparent differences. Here, we performed a comparative assessment of HD cell firing characteristics across the anterior dorsal thalamus (ADN), postsubiculum (PoS), parasubiculum (PaS), medial entorhinal (MEC), and postrhinal (POR) cortices. We report that HD cells with a high degree of directional specificity were observed in all five brain regions, but ADN HD cells display greater sharpness and stability in their preferred directions, and greater anticipation of future headings compared to parahippocampal regions. Additional analysis indicated that POR HD cells were more coarsely modulated by other spatial parameters compared to PoS, PaS, and MEC. Finally, our analyses indicated that the sharpness of HD tuning decreased as a function of laminar position and conjunctive coding within the PoS, PaS, and MEC, with cells in the superficial layers along with conjunctive firing properties showing less robust directional tuning. The results are discussed in relation to theories of functional organization of HD cell tuning in thalamo-parahippocampal circuitry.

Auto-Tuning Software Tool for Inverse Response Model Robust Tuning of 1-DoF PID and FOPID Controllers

The main objective of this work is to present a software tool that allows to perform the tuning process of PID and Fractional Order PID controllers in an automated method. The tool tunes 1DoF PID and FOPID controllers for a controlled process with a inverse response second-order plus dead time model. This tuning is based on the Inverse Response Model Robust Tuning (IRM-RoT) rule, which aims to achieve optimal control system performance while ensuring a target robustness. Additionally, the tool measures the performance obtained from the control system, as well as the robustness achieved, and displays the control signal obtained by implementing the tuned controller. The examples used show the main characteristics of the tool and conclude that it can be a very useful contribution for educational purposes in fields such as electrical engineering.

PID/FOPID Tuning Rule Based on a Second Order Inverse Response Process Model with Robustness Considerations

This paper deals with the design of a proportional-integral-derivative (PID) and fractional-order proportional-integral-derivative (FOPID) controller tuning rule for second-order controlled processes with inverse response. The design of the rules takes into account specific levels of robustness and performance for both load disturbance rejection and set-point tracking tasks. In the first step, the optimal parameters for both controllers are obtained from optimizations that seek to minimize the error in both control modes while maintaining the robustness constraint. Subsequently, fitting functions to the optimal parameters are sought to capture their behavior with the possibility of finding optimal parameters with the tuning rule designed between certain ranges of the model parameters. For FOPID and PID controllers, the rule IRM-RoT (Inverse Response Model Robust Tuning) have been developed. The performance of the controllers was compared using examples, and the results showed that fractional order controllers provide a novel solution for inverse response dynamics in process control.

Fractional-Order PID Optimal Tuning Rule based on a FOPDT Process Model with Robustness Constraints

This paper introduces a tuning rule design for fractional order PID controllers. The design is based on a first order plus dead time model for the controlled process. The control problem presented, requires minimizing the integrated absolute error for each control mode, then making a different set of rules for set-point and load-disturbance response. For the proposed optimization, a robustness constraint based on the maximum value of the sensitivity function has been considered so that the tuned controllers have an optimal performance and guarantee the stability of the control system at the time of implementation. By performing a curve fitting process towards the optimal controller parameters, the Model based Robust Tuning rule was designed and its improvement over other tuning methods is validated through examples.

Robust Bilinear Probabilistic PCA Using a Matrix Variate t Distribution.

The bilinear probabilistic principal component analysis (BPPCA) was introduced recently as a model-based dimension reduction technique on matrix data. However, BPPCA is based on the Gaussian assumption and hence is vulnerable to potential outlying matrix-valued observations. In this article, we present a new robust extension of BPPCA, called BPPCA using a matrix variate t distribution ( t BPPCA), that is built upon a matrix variate t distribution. Like the multivariate t , this distribution offers an additional robustness tuning parameter, which can downweight outliers. By introducing a Gamma distributed latent weight variable, this distribution can be represented hierarchically. With this representation, two efficient accelerated expectation-maximization (EM)-like algorithms for parameter estimation are developed. Experiments on a number of synthetic and real datasets are conducted to understand t BPPCA and compare with several closely related competitors, including its vector-based counterpart. The results reveal that t BPPCA is generally more robust and accurate in the presence of outliers. Moreover, the expected latent weights under t BPPCA can be effectively used for outliers' detection, which is much more reliable than its vector-based counterpart due to its better robustness.

Robust high-dimensional tuning free multiple testing

Robust high-dimensional tuning free multiple testing

Robust multi‐loop control of a floating wind turbine

AbstractA principal challenge facing the control of floating offshore wind turbines (FOWTs) is the problem of instability, or “negative damping,” when using blade pitch feedback to control generator speed. This closed‐loop instability can be attributed to non‐minimum phase zeros in the transfer function from blade pitch to generator speed. Standard approaches to improving stability and performance include robust tuning of control gains and introducing multiple feedback loops to respond to platform motion. Combining these approaches is nontrivial because multiple control loops complicate the impact of coupling in the system dynamics. The single‐loop approach to analyzing stability robustness neglects inter‐loop coupling, while a simplistic multi‐loop approach is highly sensitive to dimensional scaling and overestimates the robustness of the single‐loop controller. This work proposes a sensitivity representation that separates some of the natural FOWT dynamic coupling into a parallel feedback loop in the sensitivity function loop to address both of these concerns. The modified robustness measure is used with a simplified linear FOWT model to optimize scheduled multi‐loop control parameters in an automated tuning procedure. This controller is implemented for the 10‐MW Ultraflexible Smart FLoating Offshore Wind Turbine (USFLOWT) and compared against conventional single‐ and multi‐loop controllers tuned using frequency‐domain analysis and high‐fidelity OpenFAST simulations. The multi‐loop robust controller shows the highest overall performance in generator speed regulation and tower load reduction, though consideration of power quality, actuator usage, and other structural loading leads to additional trade‐offs.

Robust [formula omitted] parameterization with low tuning complexity of cascaded control for feed drives

This paper presents a robust parameterization method for the well-established cascaded control structure of feed drives and applies it to both proportional (P) and sliding mode (SMC) position controllers. The controller parameterization is based on the structured μ-synthesis technique, which allows direct robust tuning of fixed control structures with respect to the conflicting goals of tracking and disturbance rejection over different frequency ranges. The proposed strategy explicitly takes into account both matched and unmatched uncertainties and considers the dynamics of the Kalman filter and feedforward control, ensuring robust stability and performance based on a simple low-order plant model with only two parameters. To ensure industrial applicability, the parameterization problem is formulated in a signal-based manner and the tuning complexity is limited to the selection of only two hyperparameters by directly extracting the information from measurements. Extensive experimental results are performed on an industrial feed drive to validate the performance and robustness of the proposed approach. For example, compared to P-PI cascade control with feedforward and nominally tuned SMC position control, the robustly parameterized SMC position controller reduces the root-mean-square tracking error by 79% and 61% during high-speed milling experiment. Even under variation of model parameters by 20%, the robustly parameterized SMC still cuts the tracking error by more than 44% in the comparison.

Indium-bond-and-stop-etch (IBASE) technique for dual-side processing of thin high-mobility GaAs/AlGaAs epitaxial layers

We present a reliable flip-chip technique for dual-side processing of thin (<1 μm) high-mobility GaAs/AlGaAs epitaxial layers. The technique allows the fabrication of small (micron-scale with standard UV photolithography) patterned back gates and dual-gate structures on the thin GaAs/AlGaAs films with good alignment accuracy using only frontside alignment. The technique preserves the high-mobility (>106 cm2/V-s at 2 K) and most (>95%) of the charge density of the two-dimensional electron gas systems and allows linear control of the charge density with small (<1 V) electrostatic gate bias. Our technique is motivated by a THz quantum well detector based on intersubband transitions in a single, wide GaAs/AlGaAs quantum well, in which a symmetric, well-aligned dual-gate structure (with a typical gate dimension of ∼5 ×5 μm) is required for accurate and precise tuning of the THz detection frequency. Using our Indium-Bond-And-Stop-Etch technique, we realize such dual-gate structure on 660-nm thick GaAs/AlGaAs epitaxial layers that contain a modulation-doped, 40-nm wide, single square quantum well. By independently controlling the charge density and the DC electric field set between the gates, we demonstrate robust tuning of the intersubband absorption behavior of the 40-nm quantum well near 3.44 THz at 30 K.

Two step I to II type transitions in layered Weyl semi-metals and their impact on superconductivity

Novel “quasi two dimensional” typically layered (semi) metals offer a unique opportunity to control the density and even the topology of the electronic matter. Along with doping and gate voltage, a robust tuning is achieved by application of the hydrostatic pressure. In Weyl semi-metals the tilt of the dispersion relation cones, kappa , increases with pressure, so that one is able to reach type II (kappa >1starting from the more conventional type I Weyl semi-metals kappa <1. The microscopic theory of such a transition is constructed. It is found that upon increasing pressure the I to II transition occurs in two continuous steps. In the first step the cones of opposite chirality coalesce so that the chiral symmetry is restored, while the second transition to the Fermi surface extending throughout the Brillouin zone occurs at higher pressures. Flattening of the band leads to profound changes in Coulomb screening. Superconductivity observed recently in wide range of pressure and chemical composition in Weyl semi-metals of both types. The phonon theory of pairing including the Coulomb repulsion for a layered material is constructed and applied to recent extensive experiments on HfTe_{5}.

Online estimation of state-of-charge inconsistency for lithium-ion battery based on SVSF-VBL

It is of great significance to estimate cell inconsistency for improving the service life and safety performance of the power battery pack. To accurately estimate the state-of-charge (SOC) inconsistency of cells with different performance parameters and working states, a method combining adaptive robust unscented Kalman filter and smooth variable structure filter with time-varying smoothing boundary layer (SVSF-VBL) is proposed. The cell mean-difference model is used to simulate the behavior characteristics of the battery module, including the cell mean model expressed by the dual polarization (DP) model and the cell difference model characterized by the hypothetical Rint model. Firstly, the improved forgetting factor recursive least square is applied to identify parameters of the DP model, and the unscented Kalman filter incorporating robust estimation and adaptive filter tuning is employed to estimate the SOC of the battery module. Then, SVSF-VBL is used to estimate the SOC difference between each cell and module based on the Rint model for improving the estimation accuracy and robustness. In addition, the comprehensive inconsistency of the cells can be captured by the secondary performance indicator inherent in SVSF-VBL, which contributes to the in-depth study of cell inconsistency. Finally, a series of tests are carried out to verify the performance of the proposed method, and the results show that the method can improve the estimation accuracy and convergence performance while effectively suppressing the system disturbance.

Robust 2DoF PI tuning rules for integrating processes with dead time via frequency response model matching

The integrating characteristics are commonly found in composition control and level control of a distillation column in chemical processes. This paper presents a simple and intuitive robust tuning method of two-degree-of-freedom (2DoF) proportional-integral (PI) controller for integrating processes with dead time. The frequency response model matching approach is utilized with performance and robustness considerations for both regulatory and servo control issues. The regulatory control issue aims at matching the frequency response of the closed-loop system with that of the reference model for disturbance rejection, where the feedback controller parameters are calculated by solving a group of overdetermined algebraic equations subject to a robustness constraint evaluated by the maximum sensitivity. The target of the servo response is to follow a prescribed set-point reference trajectory, with the set-point weighting factor tuned to satisfy a defined tracking performance metric. A curve fitting procedure is utilized to generate analytical tuning rules in terms of the process model parameters and the desired robustness specification. It is shown that, apart from giving more exact achievement of the control system robustness, the tuning rules presented work well for a wider range of process dynamics than the existing methods. Illustrative examples are given to show the effectiveness of the proposed method.