Stopping Criterion Research Articles

Assessing opinion on lower LDL-cholesterol lowering, and the role of newer lipid-reducing treatment options.

While statins are the gold standard for lipid-lowering therapies, newer therapies, such as PCSK9 inhibitors, have also demonstrated low-density lipoprotein cholesterol (LDL-C) reduction, but with a similar or better safety profile. Conflicting guidance has contributed to a low uptake. More up-to-date, evidence-led guidance supports greater use of newer therapies, particularly in combination with statins, to reduce LDL-C to levels shown to be effective in trials. The aim of this study was to determine how such guidance can be implemented more effectively in the UK. Using a modified Delphi approach, a panel of healthcare professionals with an interest in the management of dyslipidaemia developed 27 statements across four key themes. These were used to form an online survey that was distributed to healthcare professionals working in cardiovascular care across the UK. Stopping criteria included 100 responses received, a seven-month window for response (September 2021 to March 2022), and 90% of statements passing the predefined consensus threshold of 75%. A total of 109 responses were analysed with 23 statements achieving consensus (four statements <75%). Variance was observed across respondent role, and by UK region. From the high degree of consensus, seven recommendations were established as to how evidence-based guidance can be delivered, including a call for personalised therapy strategies and simplification of LDL-C goals, which should be achieved within as short a time as possible.

A Novel Lightweight Deep Convolutional Neural Network Model for Human Emotions Recognition in Diverse Environments

A picture is worth a thousand words to convey information during daily life communication. Recognizing a person’s emotions from facial expressions (FEs) has become a prevalent research field in the past few decades. Deep learning (DL) models, mainly deep convolutional neural networks (DCNNs), are trending in the last few years to perform recognition/classification tasks. Several prior DCNNs have resulted in good recognition accuracy for facial emotion recognition (FER) systems. Still, there is a need for an effective as well as efficient FER system that can recognize the FEs irrespective of the illumination conditions, subjects’ gender, age range, geographical locations, race, etc. In this work, we have presented a novel lightweight DCNN model that can recognize the FEs in the aforementioned conditions. We have made it lightweight by optimal selection of its hidden layers, which ultimately resulted in the reduced number of floating point operations (FLOPs). We have embedded the data augmentation step into the model’s training phase to enhance its generalization ability. An early stopping criterion is also introduced to prevent the model’s overfitting. We have trained and evaluated the performance of the proposed model on widely used benchmarks for FEs databases. We have selected five diverse databases (two collected in the lab, one based on stylized cartoon characters, and two collections in an unconstrained realistic environment), including CK+, Karolinska Directed Emotional Faces (KDEF), Facial Expression Research Group (FERG), Facial Expression Recognition‐2013 (FER‐2013), and Real‐World Affective Faces Database (RaF‐DB). The recognition accuracy of 99.98%, 99.25%, 88.17%, 84.09%, 69.87%, and 69.16% is achieved for the FERG, CK+, KDEF, RaF‐DB, FER‐2013 human faces (FER‐2013H), and FER‐2013 complete (FER‐2013C) database, respectively. Our model outperforms the number of state‐of‐the‐art FER approaches in terms of recognition accuracy and FLOPs.

AN ENHANCED FRAMEWORK FOR MORRIS BY COMBINING WITH A SEQUENTIAL SAMPLING STRATEGY

The Morris method is an effective sample-based sensitivity analysis technique that has been applied in various disciplines. To ensure a more proper coverage of the input space and better performance, an enhanced framework for Morris is proposed by considering the combination of a sequential sampling strategy and the traditional Morris method. The paper introduces utilizing progressive Latin hypercube sampling to generate starting points while progressively preserving Latin hypercube property. Then the calculations for Elementary Effects, which occupies the major computational cost of Morris, become sequential. An adaptive stop criterion is also constructed to end the algorithm when the convergence condition is satisfied. Therefore, the proposed procedure makes the cost of Morris more manageable and minimizes the computational burden by conducting only model runs that are necessary to achieve reliable results. Two numerical examples and two real-world cases are given to illustrate the effectiveness and robustness of the framework.

Guaranteed contraction of adaptive inexact hp-refinement strategies with realistic stopping criteria

The purpose of this contribution it to theoretically analyze the adaptive refinement strategies for conforming hp-finite element approximations of elliptic problems proposed for exact algebraic solvers in (P. Daniel, A. Ern, I. Smears and M. Vohralk, Comput. Math. Appl. 76 (2018) 967–983.) and for inexact algebraic solvers in (P. Daniel, A. Ern, and M. Vohralk, Comput. Methods Appl. Mech. Eng. 359 (2020) 112607.). Both of these strategies are driven by guaranteed equilibrated flux energy error estimators. The employed hp-refinement criterion stems from solving two separate local residual problems posed only on the patches of elements around marked vertices selected by a bulk-chasing criterion. In the above references, we have derived a fully computable guaranteed bound on the ratio of the error on two successive steps of the hp-adaptive loop. Here, our focus is to prove that this ratio is uniformly smaller than one, and thus the convergence of the adaptive and adaptive inexact hp-refinement strategies. To be able to achieve this goal, we have to introduce some additional assumptions on the h- and p-refinements, namely an extension of the marked region, as well as a sufficient h- or p-refinement of each marked patch. We investigate two such strategies, where one ensures a polynomial-degree-robust guaranteed contraction. In the inexact case, a sufficiently precise stopping criterion for the algebraic solver is requested, but this criterion remains fully computable and also realistic in the sense that in our numerical experiments, it does not request the algebraic error to be excessively small in comparison with the total error.

Грубо-сеточные поправки в вычислении действия матричной экспоненты подпространством Крылова

A coarse grid correction (CGC) approach is proposed to enhance the efficiency of the matrix exponential and phi matrix function evaluations. The approach is intended for iterative methods computing the matrix-vector products with these functions. It is based on splitting the vector by which the matrix function is multiplied into a smooth part and a remaining part. The smooth part is then handled on a coarser grid, whereas the computations on the original grid are carried out with a relaxed stopping criterion tolerance. Estimates on the error are derived for the two-grid and multigrid variants of the proposed CGC algorithm. Numerical experiments demonstrate the efficiency of the algorithm, when employed in combination with Krylov subspace and Chebyshev polynomial expansion methods.

Analytical solution for expandable polyurethane grouting in a rock fracture

Expandable polyurethane grout has been extensively utilized for the reinforcement and sealing of rock fractures. The diffusion mechanism of this grout is particularly unique, owing to the time-dependent characteristics of both its density and viscosity. However, the non-synchronous relationship between the change in diffusion radius and pressure poses challenges in deriving analytical solutions. In light of this, our study presents an innovative analytical model to effectively simulate the diffusion behavior of expandable polyurethane within rock fractures. Notably, this model considers both the self-expanding source and the convective driving force. The outcomes of our research demonstrate that spread and pressure exhibit distinct characteristic times, allowing us to employ the same equations with diverse parameters, yielding a semi-deterministic approach. In this approach, the first run of the model is deterministic while the second entails empirical considerations. Further, a comparison of analytical results with experimental injections was made involving varying grouting quantities, revealing excellent agreement between the measured and calculated pressures. The present model can be employed for fitting and real-time monitoring after calibration, enabling the exploration of conventional stop criteria, as well as refusal and mass criteria. Additionally, this model facilitates the formulation of conditions to effectively achieve the target, considering vital factors such as the time-spread relation, expansion ratio, and gel time.

RANSAC for Robotic Applications: A Survey.

Random Sample Consensus, most commonly abbreviated as RANSAC, is a robust estimation method for the parameters of a model contaminated by a sizable percentage of outliers. In its simplest form, the process starts with a sampling of the minimum data needed to perform an estimation, followed by an evaluation of its adequacy, and further repetitions of this process until some stopping criterion is met. Multiple variants have been proposed in which this workflow is modified, typically tweaking one or several of these steps for improvements in computing time or the quality of the estimation of the parameters. RANSAC is widely applied in the field of robotics, for example, for finding geometric shapes (planes, cylinders, spheres, etc.) in cloud points or for estimating the best transformation between different camera views. In this paper, we present a review of the current state of the art of RANSAC family methods with a special interest in applications in robotics.

Second-order flows for computing the ground states of rotating Bose-Einstein condensates

Second-order flows in this paper refer to some artificial evolutionary differential equations involving second-order time derivatives distinguished from gradient flows which are considered to be first-order flows. This is a popular topic due to the recent advances of inertial dynamics with damping in convex optimization. Mathematically, the ground state of a rotating Bose-Einstein condensate (BEC) can be modeled as a minimizer of the Gross-Pitaevskii energy functional with angular momentum rotational term under the normalization constraint. We introduce two types of second-order flows as energy minimization strategies for this constrained non-convex optimization problem, in order to approach the ground state. The proposed artificial dynamics are novel second-order nonlinear hyperbolic partial differential equations with dissipation. Several numerical discretization schemes are discussed, including explicit and semi-implicit methods for temporal discretization, combined with a Fourier pseudospectral method for spatial discretization. These provide us a series of efficient and robust algorithms for computing the ground states of rotating BECs. Particularly, the newly developed algorithms turn out to be superior to the state-of-the-art numerical methods based on the gradient flow. In comparison with the gradient flow type approaches: When explicit temporal discretization strategies are adopted, the proposed methods allow for larger stable time step sizes; While for semi-implicit discretization, using the same step size, a much smaller number of iterations are needed for the proposed methods to reach the stopping criterion, and every time step encounters almost the same computational complexity. Rich and detailed numerical examples are documented for verification and comparison.

Designing Dispatching Rules via Novel Genetic Programming with Feature Selection in Dynamic Job-Shop Scheduling

Genetic Programming (GP) has been widely employed to create dispatching rules intelligently for production scheduling. The success of GP depends on a suitable terminal set of selected features. Specifically, techniques that consider feature selection in GP to enhance rule understandability for dynamic job shop scheduling (DJSS) have been successful. However, existing feature selection algorithms in GP focus more emphasis on obtaining more compact rules with fewer features than on improving effectiveness. This paper is an attempt at combining a novel GP method, GP via dynamic diversity management, with feature selection to design effective and interpretable dispatching rules for DJSS. The idea of the novel GP method is to achieve a progressive transition from exploration to exploitation by relating the level of population diversity to the stopping criteria and elapsed duration. We hypothesize that diverse and promising individuals obtained from the novel GP method can guide the feature selection to design competitive rules. The proposed approach is compared with three GP-based algorithms and 20 benchmark rules in the different job shop conditions and scheduling objectives. Experiments show that the proposed approach greatly outperforms the compared methods in generating more interpretable and effective rules for the three objective functions. Overall, the average improvement over the best-evolved rules by the other three GP-based algorithms is 13.28%, 12.57%, and 15.62% in the mean tardiness (MT), mean flow time (MFT), and mean weighted tardiness (MWT) objective, respectively.

NOAH as an Innovative Tool for Modeling the Use of Suburban Railways

The paper presents an innovative method called the “Nest of Apes Heuristic” (NOAH) for modeling specific problems by combining technical aspects of transport systems with human decision-making. The method is inspired by nature. At the beginning of the paper, potential problems related to modeling a suburban rail system were presented. The literature review is supplemented with a short description of known heuristics. The basic terminology, procedures, and algorithm are then introduced in detail. The factors of the suburban rail system turn into “Monkeys”. Monkeys change their position in the nest, creating leaders and followers. This allows for the comparison of the factor sets in a real system. The case study area covers the vicinity of Wroclaw, the fourth largest city in Poland. Two experiments were conducted. The first takes into account the average values of the factors in order to observe the algorithm’s work and formulate the stopping criteria. The second is based on the current values of the factors. The purpose of this work was to evaluate these values and to assess the possibilities of changing them. The obtained results show that the new tool may be useful for modeling and analyzing such problems.

Feature Selection in High-Dimensional Models via EBIC with Energy Distance Correlation.

In this paper, the LASSO method with extended Bayesian information criteria (EBIC) for feature selection in high-dimensional models is studied. We propose the use of the energy distance correlation in place of the ordinary correlation coefficient to measure the dependence of two variables. The energy distance correlation detects linear and non-linear association between two variables, unlike the ordinary correlation coefficient, which detects only linear association. EBIC is adopted as the stopping criterion. It is shown that the new method is more powerful than Luo and Chen's method for feature selection. This is demonstrated by simulation studies and illustrated by a real-life example. It is also proved that the new algorithm is selection-consistent.

An efficient method for time-dependent reliability problems with high-dimensional outputs based on adaptive dimension reduction strategy and surrogate model

Time-dependent reliability analysis with high dimensional outputs is a challenge because of ‘curse of dimensionality’ and accurate reliability estimation over entire time interval is computationally expensive. In this paper, an efficient time-dependent reliability analysis method is proposed for systems with high dimensional outputs based on adaptive dimension reduction strategy and Kriging. The adaptive Kriging model is constructed in low-dimensional space after performing principal component analysis (PCA) on original time-dependent output. A new learning function and corresponding stopping criterion are developed as the guideline for selecting training samples at each iteration. The proposed learning function focuses on prediction accuracy over the entire time interval and the stopping criterion is directly linked to failure probability. Subsequently, fewer number of function evaluations is required compared with existing competitive works. Moreover, the key advantage of the proposed method is that it is a single-loop process, i.e., the selection of training samples, dimension reduction and Kriging modeling have been combined simultaneously at each iteration with adaptive manner. However, the existing competitive methods, generally, have two independent stages, i.e., stage one is collecting training samples and stage two is performing PCA and Kriging modelling for time-dependent reliability analysis. Thus, these methods cannot fully utilize the information provided by PCA to find optimal training samples. It is noteworthy that the dimension reduction is also an adaptive process in the proposed method, i.e., dimension reduction changes with the training samples at each iteration. The applicability, accuracy and efficiency of the proposed method are validated through three numerical examples and one engineering example.

Parity-check and G-matrix based intelligent early stopping criterion for belief propagation decoder for polar codes

The error correction performance of Belief Propagation (BP) decoding for polar codes is satisfactory compared with the Successive Cancellation (SC) decoding. Nevertheless, it has to complete a fixed number of iterations, which results in high computational complexity. This necessitates an intelligent identification of successful BP decoding for early termination of the decoding process to avoid unnecessary iterations and minimize the computational complexity of BP decoding. This paper proposes a hybrid technique that combines the “parity-check” with the “G-matrix” to reduce the computational complexity of BP decoder for polar codes. The proposed hybrid technique takes advantage of the parity-check to intelligently identify the valid codeword at an early stage and terminate the BP decoding process, which minimizes the overhead of the G-matrix and reduces the computational complexity of BP decoding. We explore a detailed mechanism incorporating the parity bits as outer code and prove that the proposed hybrid technique minimizes the computational complexity while preserving the BP error correction performance. Moreover, mathematical formulation for the proposed hybrid technique that minimizes the computation cost of the G-matrix is elaborated. The performance of the proposed hybrid technique is validated by comparing it with the state-of-the-art early stopping criteria for BP decoding. Simulation results show that the proposed hybrid technique reduces the iterations by about 90% of BP decoding in a high Signal-to-Noise Ratio (SNR) (i.e., 3.5 ∼ 4 ​dB), and approaches the error correction performance of G-matrix and conventional BP decoder for polar codes.

1283. Safety, Tolerability, and Pharmacokinetics of BRII-778, A Modified-Release Oral Formulation of Rilpivirine in Healthy Adult Subjects

Abstract Background BRII-778 is a modified release (MR) formulation of rilpivirine for once-weekly (QW) oral administration. BRII-778 aims to prolong oral absorption, lower Cmax, relatively, and reduce peak to trough ratio achieved with a MR formulation of rilpivirine, within the known efficacy and safety bounds established by once daily oral administration of rilpivirine. QW BRII-778 dosing may have advantages over once daily rilpirvirine in terms of patient convenience, and treatment adherence. Multiple MR formulations of rilpivirine were evaluated in healthy adult subjects in this Phase 1 study. Methods This was a Phase 1, randomized, double-blinded, placebo-controlled, study of single ascending dose (SAD) and multiple ascending dose (MAD) cohorts, evaluating the safety, tolerability, and PK of BRII-778. Three MR formulations of rilpivirine, BRII-778-A1, -A2, and -A3, were evaluated in this study. Rilpivirine PK profiles after single or multiple doses of the three BRII-778 formulations were characterized under the fed state over the dose range of 150 mg to 750 mg. Food effect was assessed after a single oral dose of BRII-778-A3 750 mg. Exploratory concentration-QTc (C-QTc) analysis was conducted using combined SAD and MAD data. Results BRII-778 as single dose or multiple doses was generally safe and well-tolerated when administered to healthy adult subjects. There were no Grade ≥3 AEs, SAEs or AEs leading to withdrawal in BRII-778 dosing arms. PK profiles of BRII-778 were consistent with slower oral absorption with MR formulation. The increase in exposure was less than dose proportional. Mild accumulation in plasma was observed after 3 QW BRII-778-A3 doses. BRII-778-A3 750 mg under the fed state enhanced bioavailability by improving gastric dissolution and/or subsequent absorption. Exploratory C-QTc analysis confirmed a concentration-dependent effect on the QTc interval with escalating doses of BRII-778, but the interpretations are limited by small sample size. There were no clinically significant EKG changes and no individual subject met QTc stopping criteria. Conclusion SAD and MAD administration of BRII-778 formulations were generally safe and well tolerated. Rilpivirine PK profiles post BRII-778 dosing supports further evaluation of BRII-778 for potential QW regimen. Disclosures David A. Margolis, MD MPH, Brii Biosciences: Stocks/Bonds Ji Ma, PhD, Brii Biosciences: Stocks/Bonds Michael Watkins, PharmD, Brii Biosciences: Stocks/Bonds Yujin Wang, M.Sc., Brii Biosciences: Stocks/Bonds Chetana Trivedi, B.A., Brii Biosciences: Stocks/Bonds Xuelian Wei, PhD, Brii Biosciences: Stocks/Bonds Lijie Zhong, PhD, Brii Biosciences: Stocks/Bonds Kamlesh Patel, PhD, Brii Biosciences: Stocks/Bonds Li Yan, MD PhD, Brii Biosciences: Stocks/Bonds Zhi Hong, PhD, Brii Biosciences: Ownership Interest Jean-Luc Girardet, PhD, Brii Biosciences: Stocks/Bonds Lianhong Xu, PhD, Brii Biosciences: Stocks/Bonds.

Anticoagulation Strategies in Non–Critically Ill Patients with Covid-19

BackgroundOptimal thromboprophylaxis for hospitalized patients with coronavirus disease 2019 (Covid-19) is uncertain.MethodsIn an open-label, adaptive platform trial, we randomly assigned hospitalized adults with Covid-19 to low-dose low-molecular-weight heparin thromboprophylaxis or intermediate-dose or low-dose plus aspirin. In response to external evidence, the aspirin intervention was discontinued and a therapeutic-dose arm added. The primary end point was death or the requirement for new organ support by day 28, analyzed with a Bayesian logistic model. Enrolment was closed as a result of operational constraints.ResultsBetween February 2021 and March 2022, 1574 patients were randomly assigned. Among 1526 participants included in the analysis (India, n=1273; Australia and New Zealand, n=138; and Nepal, n=115), the primary outcome occurred in 35 (5.9%) of 596 in low-dose, 25 (4.2%) of 601 in intermediate-dose, 20 (7.2%) of 279 in low-dose plus aspirin, and 7 (14%) of 50 in therapeutic-dose anticoagulation. Compared with low-dose thromboprophylaxis, the median adjusted odds ratio for the primary outcome for intermediate-dose was 0.74 (95% credible interval [CrI], 0.43 to 1.27; posterior probability of effectiveness [adjusted odds ratio<1; Pr], 86%), for low-dose plus aspirin 0.88 (95% CrI, 0.47 to 1.64; Pr, 65%), and for therapeutic-dose anticoagulation 2.22 (95% CrI, 0.77 to 6.20; Pr, 7%). Overall thrombotic and bleeding rates were 0.8% and 0.4%, respectively. There were 10 serious adverse reactions related to anticoagulation strategy, of which nine were grade 1 or 2 across study interventions and one grade 4 episode of retroperitoneal hematoma in a patient receiving intermediate-dose anticoagulation.ConclusionsIn hospitalized non–critically ill adults with Covid-19, compared with low-dose, there was an 86% posterior probability that intermediate-dose, 65% posterior probability that low-dose plus aspirin, and a 7% posterior probability that therapeutic-dose anticoagulation reduced the odds of death or requirement for organ support. No treatment strategy met prespecified stopping criteria before trial closure, precluding definitive conclusions. (Funded by Australian National Health and Medical Research Council or Medical Research Future Fund Investigator and Practitioner Grants and others; ClinicalTrials.gov number, NCT04483960.)

Combined baseline HBcrAg and end-of-treatment HBsAg predict HBV relapse after entecavir or tenofovir cessation.

For patients with chronic hepatitis B (CHB), the optimal stopping criteria for entecavir or tenofovir disoproxil fumarate treatment remain unclear. This study recruited CHB patients with levels of hepatitis B surface antigen (HBsAg) <100 IU/mL at the end of treatment (EOT) from Kaohsiung (n = 190) and Linkou (n = 188) Chang Gung Memorial Hospitals for use as development and validation groups, respectively. In the development group, 108 patients with HBsAg ≤40 IU/mL were used for analysis of predictors of HBV relapse and HBsAg loss. Multivariate analysis showed that age, nucleos(t)ide analogue (NA)-experienced status, baseline hepatitis B core-related antigen (HBcrAg) and HBsAg at EOT were associated independently with virological and clinical relapse. An HBsAg level of 20 IU/mL at EOT was the best cut-off value for minimizing HBV relapse. Patients with EOT HBsAg ≤20 IU/mL had lower virological and clinical relapse rates and higher HBsAg loss rates than those with EOT HBsAg 21-40 IU/mL and HBsAg 41-100 IU/mL in the development and validation groups. The virological and clinical relapse rates were very low (5-year rates: 6.5% and 0%, respectively) and HBsAg loss rate was very high (5-year rate: 81.7%) in patients with a combination of baseline HBcrAg ≤4 log U/mL and EOT HBsAg ≤20 IU/mL in the development group. A combination of baseline HBcrAg ≤4 log U/mL and EOT HBsAg level ≤20 IU/mL might reduce the risk of HBV relapse and increase HBsAg loss rate, and might be helpful for off-NA follow-up strategy.

Exploiting Channel Polarization for Reliable Wide-Area Backscatter Networks

A long-standing vision of backscatter networks is to provide long-range connectivity and high-speed transmissions for batteryless Internet-of-Things (IoT). Recent years have seen major innovations in designing backscatter networks toward this goal. Yet, they either operate at a very short range, or experience extremely low throughput. This paper takes one step further towards breaking this stalemate, by presenting PolarScatter that exploits channel polarization in long-range backscatter networks. We transform backscatter channels into nearly noiseless virtual channels through channel polarization, and convey bits with extremely low error probability. Specifically, we propose a new polar code scheme that automatically adapts itself to different channel quality, and design a low-cost encoder to accommodate polar codes on resource-constrained backscatter tags. Furthermore, we devise a new metric to calculate log-likelihood ratio for accurate decoding, and present a stopping criterion of iterations to reduce decoding latency. We build a prototype PCB tag, and our experiments show that it achieves up to 11.5× throughput improvement over the state-of-the-art long-range backscatter solution. We also simulate an IC design in TSMC 65 nm LP CMOS process. Compared with traditional encoders, our encoder reduces storage overhead by three orders of magnitude, and lowers the power consumption to tens of microwatts.

ProS: data series progressive k-NN similarity search and classification with probabilistic quality guarantees

Existing systems dealing with the increasing volume of data series cannot guarantee interactive response times, even for fundamental tasks such as similarity search. Therefore, it is necessary to develop analytic approaches that support exploration and decision making by providing progressive results, before the final and exact ones have been computed. Prior works lack both efficiency and accuracy when applied to large-scale data series collections. We present and experimentally evaluate ProS, a new probabilistic learning-based method that provides quality guarantees for progressive nearest neighbor (NN) query answering. We develop our method for k-NN queries and demonstrate how it can be applied with the two most popular distance measures, namely Euclidean and dynamic time warping. We provide both initial and progressive estimates of the final answer that are getting better during the similarity search, as well suitable stopping criteria for the progressive queries. Moreover, we describe how this method can be used in order to develop a progressive algorithm for data series classification (based on a k-NN classifier), and we additionally propose a method designed specifically for the classification task. Experiments with several and diverse synthetic and real datasets demonstrate that our prediction methods constitute the first practical solutions to the problem, significantly outperforming competing approaches.

Information Theory-based Evolution of Neural Networks for Side-channel Analysis

Profiled side-channel analysis (SCA) leverages leakage from cryptographic implementations to extract the secret key. When combined with advanced methods in neural networks (NNs), profiled SCA can successfully attack even those cryptocores assumed to be protected against SCA. Despite the rise in the number of studies devoted to NN-based SCA, a range of questions has remained unanswered, namely: how to choose an NN with an adequate configuration, how to tune the NN’s hyperparameters, when to stop the training, etc. Our proposed approach, “InfoNEAT,” tackles these issues in a natural way. InfoNEAT relies on the concept of neural structure search, enhanced by information-theoretic metrics to guide the evolution, halt it with novel stopping criteria, and improve time-complexity and memory footprint. The performance of InfoNEAT is evaluated by applying it to publicly available datasets composed of real side-channel measurements. In addition to the considerable advantages regarding the automated configuration of NNs, InfoNEAT demonstrates significant improvements over other approaches for effective key recovery in terms of the number of epochs (e.g.,x6 faster) and the number of attack traces compared to both MLPs and CNNs (e.g., up to 1000s fewer traces to break a device) as well as a reduction in the number of trainable parameters compared to MLPs (e.g., by the factor of up to 32). Furthermore, through experiments, it is demonstrated that InfoNEAT’s models are robust against noise and desynchronization in traces.

Surrogate modeling method for multi-objective optimization of the inlet channel and the basin of a gravitational water vortex hydraulic turbine

This work presents a high-fidelity surrogate model for generating a multi-objective genetic algorithm to allow the search for the optimal geometry of the inlet channel and the basin of a gravitational water vortex hydraulic turbine. Six parameters were considered for the optimization: the relations between the basin diameter (D) and the basin height (H), H/D; the wrap-around angle (γ), the outlet diameter (d) and D, d/D; the inlet channel width (w) and D, w/D; the inlet channel height (h) and D, h/D; and the inlet channel length (L) and D, L/D. Two conflicting objectives were studied: maximizing the vortex strength (Γ) and minimizing the volume flow rate (Q). The multi-objective optimization problem was resolved by applying the gamultiobj function in Matlab R2018b software. The optimization combines the genetic algorithm with Kriging interpolation to obtain the Pareto front. To train the gamultiobj function, an initial population of 40 individuals was used. As a stopping criterion, the maximum generation of 500 individuals was established. To improve the Pareto front, 20 optimization cycles (60 new samples) were required, reaching a final population of 100 individuals. It was found from the Pareto front that the values of the six variables providing the compromise solution, between Γ and Q, were H/D=1.572, L/D=1.518, h/D=0.565, w/D=0.361, d/D=0.108, and γ=92.141°. This solution reaches a Q of 0.00305 m3/s and a Γ of 1.699 m2/s. The results of this study were compared with the results reported by other authors, who optimized this type of turbine by applying the response surface methodology. The difference between these results was less than 9.61%.