Multi-task global optimization-based method for vascular landmark detection

Vascular landmark detection plays an important role in medical analysis and clinical treatment. However, due to the complex topology and similar local appearance around landmarks, the popular heatmap regression based methods always suffer from the landmark confusion problem. Vascular landmarks are connected by vascular segments and have special spatial correlations, which can be utilized for performance improvement. In this paper, we propose a multi-task global optimization-based framework for accurate and automatic vascular landmark detection. A multi-task deep learning network is exploited to accomplish landmark heatmap regression, vascular semantic segmentation, and orientation field regression simultaneously. The two auxiliary objectives are highly correlated with the heatmap regression task and help the network incorporate the structural prior knowledge. During inference, instead of performing a max-voting strategy, we propose a global optimization-based post-processing method for final landmark decision. The spatial relationships between neighboring landmarks are utilized explicitly to tackle the landmark confusion problem. We evaluated our method on a cerebral MRA dataset with 564 volumes, a cerebral CTA dataset with 510 volumes, and an aorta CTA dataset with 50 volumes. The experiments demonstrate that the proposed method is effective for vascular landmark localization and achieves state-of-the-art performance.

Fast EM-driven nature-inspired optimization of antenna input characteristics using response features and variable-resolution simulation models

Utilization of optimization technique is a must in the design of contemporary antenna systems. Often, global search methods are necessary, which are associated with high computational costs when conducted at the level of full-wave electromagnetic (EM) models. In this study, we introduce an innovative method for globally optimizing reflection responses of multi-band antennas. Our approach uses surrogates constructed based on response features, smoothing the objective function landscape processed by the algorithm. We begin with initial parameter space screening and surrogate model construction using coarse-discretization EM analysis. Subsequently, the surrogate evolves iteratively into a co-kriging model, refining itself using accumulated high-fidelity EM simulation results, with the infill criterion focusing on minimizing the predicted objective function. Employing a particle swarm optimizer (PSO) as the underlying search routine, extensive verification case studies showcase the efficiency and superiority of our procedure over benchmarks. The average optimization cost translates to just around ninety high-fidelity EM antenna analyses, showcasing excellent solution repeatability. Leveraging variable-resolution simulations achieves up to a seventy percent speedup compared to the single-fidelity algorithm.

Advancing forensic-based investigation incorporating slime mould search for gene selection of high-dimensional genetic data

Modern medicine has produced large genetic datasets of high dimensions through advanced gene sequencing technology, and processing these data is of great significance for clinical decision-making. Gene selection (GS) is an important data preprocessing technique that aims to select a subset of feature information to improve performance and reduce data dimensionality. This study proposes an improved wrapper GS method based on forensic-based investigation (FBI). The method introduces the search mechanism of the slime mould algorithm in the FBI to improve the original FBI; the newly proposed algorithm is named SMA_FBI; then GS is performed by converting the continuous optimizer to a binary version of the optimizer through a transfer function. In order to verify the superiority of SMA_FBI, experiments are first executed on the 30-function test set of CEC2017 and compared with 10 original algorithms and 10 state-of-the-art algorithms. The experimental results show that SMA_FBI is better than other algorithms in terms of finding the optimal solution, convergence speed, and robustness. In addition, BSMA_FBI (binary version of SMA_FBI) is compared with 8 binary algorithms on 18 high-dimensional genetic data from the UCI repository. The results indicate that BSMA_FBI is able to obtain high classification accuracy with fewer features selected in GS applications. Therefore, SMA_FBI is considered an optimization tool with great potential for dealing with global optimization problems, and its binary version, BSMA_FBI, can be used for GS tasks.

Predictive modeling of deep vein thrombosis risk in hospitalized patients: A Q-learning enhanced feature selection model

Deep vein thrombosis (DVT) represents a critical health concern due to its potential to lead to pulmonary embolism, a life-threatening complication. Early identification and prediction of DVT are crucial to prevent thromboembolic events and implement timely prophylactic measures in high-risk individuals. This study aims to examine the risk determinants associated with acute lower extremity DVT in hospitalized individuals. Additionally, it introduces an innovative approach by integrating Q-learning augmented colony predation search ant colony optimizer (QL-CPSACO) into the analysis. This algorithm, then combined with support vector machines (SVM), forms a bQL-CPSACO-SVM feature selection model dedicated to crafting a clinical risk prognostication model for DVT. The effectiveness of the proposed algorithm's optimization and the model's accuracy are assessed through experiments utilizing the CEC 2017 benchmark functions and predictive analyses on the DVT dataset. The experimental results reveal that the proposed model achieves an outstanding accuracy of 95.90% in predicting DVT. Key parameters such as D-dimer, normal plasma prothrombin time, prothrombin percentage activity, age, previously documented DVT, leukocyte count, and thrombocyte count demonstrate significant value in the prognostication of DVT. The proposed method provides a basis for risk assessment at the time of patient admission and offers substantial guidance to physicians in making therapeutic decisions.

Enhanced PSO feature selection with Runge-Kutta and Gaussian sampling for precise gastric cancer recurrence prediction

Gastric cancer (GC), characterized by its inconspicuous initial symptoms and rapid invasiveness, presents a formidable challenge. Overlooking postoperative intervention opportunities may result in the dissemination of tumors to adjacent areas and distant organs, thereby substantially diminishing prospects for patient survival. Consequently, the prompt recognition and management of GC postoperative recurrence emerge as a matter of paramount urgency to mitigate the deleterious implications of the ailment. This study proposes an enhanced feature selection model, bRSPSO-FKNN, integrating boosted particle swarm optimization (RSPSO) with fuzzy k-nearest neighbor (FKNN), for predicting GC. It incorporates the Runge-Kutta search, for improved model accuracy, and Gaussian sampling, enhancing the search performance and helping to avoid locally optimal solutions. It outperforms the sophisticated variants of particle swarm optimization when evaluated in the CEC 2014 test suite. Furthermore, the bRSPSO-FKNN feature selection model was introduced for GC recurrence prediction analysis, achieving up to 82.082 % and 86.185 % accuracy and specificity, respectively. In summation, this model attains a notable level of precision, poised to ameliorate the early warning system for GC recurrence and, in turn, advance therapeutic options for afflicted patients.

Scan-Free and Fully Automatic Tracking of Native Knee Anatomy from Dynamic Stereo-Radiography with Statistical Shape and Intensity Models

Kinematic tracking of native anatomy from stereo-radiography provides a quantitative basis for evaluating human movement. Conventional tracking procedures require significant manual effort and call for acquisition and annotation of subject-specific volumetric medical images. The current work introduces a framework for fully automatic tracking of native knee anatomy from dynamic stereo-radiography which forgoes reliance on volumetric scans. The method consists of three computational steps. First, captured radiographs are annotated with segmentation maps and anatomic landmarks using a convolutional neural network. Next, a non-convex polynomial optimization problem formulated from annotated landmarks is solved to acquire preliminary anatomy and pose estimates. Finally, a global optimization routine is performed for concurrent refinement of anatomy and pose. An objective function is maximized which quantifies similarities between masked radiographs and digitally reconstructed radiographs produced from statistical shape and intensity models. The proposed framework was evaluated against manually tracked trials comprising dynamic activities, and additional frames capturing a static knee phantom. Experiments revealed anatomic surface errors routinely below 1.0 mm in both evaluation cohorts. Median absolute errors of individual bone pose estimates were below 1.0∘ or mm for 15 out of 18 degrees of freedom in both evaluation cohorts. Results indicate that accurate pose estimation of native anatomy from stereo-radiography may be performed with significantly reduced manual effort, and without reliance on volumetric scans.

A numerical compass for experiment design in chemical kinetics and molecular property estimation

Kinetic process models are widely applied in science and engineering, including atmospheric, physiological and technical chemistry, reactor design, or process optimization. These models rely on numerous kinetic parameters such as reaction rate, diffusion or partitioning coefficients. Determining these properties by experiments can be challenging, especially for multiphase systems, and researchers often face the task of intuitively selecting experimental conditions to obtain insightful results. We developed a numerical compass (NC) method that integrates computational models, global optimization, ensemble methods, and machine learning to identify experimental conditions with the greatest potential to constrain model parameters. The approach is based on the quantification of model output variance in an ensemble of solutions that agree with experimental data. The utility of the NC method is demonstrated for the parameters of a multi-layer model describing the heterogeneous ozonolysis of oleic acid aerosols. We show how neural network surrogate models of the multiphase chemical reaction system can be used to accelerate the application of the NC for a comprehensive mapping and analysis of experimental conditions. The NC can also be applied for uncertainty quantification of quantitative structure-activity relationship (QSAR) models. We show that the uncertainty calculated for molecules that are used to extend training data correlates with the reduction of QSAR model error. The code is openly available as the Julia package KineticCompass.

Fully automatic tracking of native knee kinematics from stereo-radiography with digitally reconstructed radiographs

Precise measurement of joint-level motion from stereo-radiography facilitates understanding of human movement. Conventional procedures for kinematic tracking require significant manual effort and are time intensive. The current work introduces a method for fully automatic tracking of native knee kinematics from stereo-radiography sequences. The framework consists of three computational steps. First, biplanar radiograph frames are annotated with segmentation maps and key points using a convolutional neural network. Next, initial bone pose estimates are acquired by solving a polynomial optimization problem constructed from annotated key points and anatomic landmarks from digitized models. A semidefinite relaxation is formulated to realize the global minimum of the non-convex problem. Pose estimates are then refined by registering computed tomography-based digitally reconstructed radiographs to masked radiographs. A novel rendering method is also introduced which enables generating digitally reconstructed radiographs from computed tomography scans with inconsistent slice widths. The automatic tracking framework was evaluated with stereo-radiography trials manually tracked with model-image registration, and with frames which capture a synthetic leg phantom. The tracking method produced pose estimates which were consistently similar to manually tracked values; and demonstrated pose errors below 1.0 degree or millimeter for all femur and tibia degrees of freedom in phantom trials. Results indicate the described framework may benefit orthopaedics and biomechanics applications through acceleration of kinematic tracking.

Recalibrating the Experimentally Derived Structure of the Metastable Surface Oxide on Copper via Machine Learning-Accelerated In Silico Global Optimization

The oxidation of copper and its surface oxides are gaining increasing attention due to the enhanced CO2 reduction reaction (CO2RR) activity exhibited by partially oxidized copper among the copper-based catalysts. The "8" surface oxide on Cu(111) is seen as a promising structure for further study due to its resemblance to the highly active Cu2O(110) surface in the C-C coupling of the CO2RR, setting it apart from other O/Cu(111) surface oxides resembling Cu2O(111). However, recent X-ray photoelectron spectroscopy analysis challenges the currently accepted atomic structure of the "8" surface oxide, prompting a need for reevaluation. This study highlights the limitations of conventional methods when addressing such challenges, leading us to adopt global optimization search techniques. After a rigorous process to ensure robustness, the unbiased global minimum of the "8" surface oxide is identified. Interestingly, this configuration differs significantly from other surface oxides and also from previous "8" models while retaining similarities to the Cu2O(110) surface.

Accurate multilevel thresholding image segmentation via oppositional Snake Optimization algorithm: Real cases with liver disease

Liver-related diseases significantly contribute to global mortality rates. Accurate segmentation of liver disease from CT scans is essential for early diagnosis and treatment selection, particularly in computer-aided diagnosis (CAD) systems. To address challenges posed by inconsistent liver presence and unclear boundaries, an enhanced Snake Optimization (SO) algorithm is proposed that integrates with opposition-based learning (OBL) called (SO-OBL), proving effective in global optimization and multilevel image segmentation. Experiments using CEC'2022 test functions compare SO-OBL with eleven recent and state-of-the-art metaheuristic algorithms, demonstrating its superior performance. Additionally, an advanced liver disease segmentation model based on SO-OBL incorporates an optimized multilevel thresholding technique, leveraging Otsu's function. Notable segmentation metric results, including FSIM = 0.947, SSIM = 0.941, PSNR = 24.876, MSE = 236.88, and execution time = 0.281, underscore the model's efficiency and potential for accurate diagnosis in CAD systems.

Bayesian Optimization in Drug Discovery

Drug discovery deals with the search for initial hits and their optimization toward a targeted clinical profile. Throughout the discovery pipeline, the candidate profile will evolve, but the optimization will mainly stay a trial-and-error approach. Tons of in silico methods have been developed to improve and fasten this pipeline. Bayesian optimization (BO) is a well-known method for the determination of the global optimum of a function. In the last decade, BO has gained popularity in the early drug design phase. This chapter starts with the concept of black box optimization applied to drug design and presents some approaches to tackle it. Then it focuses on BO and explains its principle and all the algorithmic building blocks needed to implement it. This explanation aims to be accessible to people involved in drug discovery projects. A strong emphasis is made on the solutions to deal with the specific constraints of drug discovery. Finally, a large set of practical applications of BO is highlighted.

Two-timescale projection neural networks in collaborative neurodynamic approaches to global optimization and distributed optimization

In this paper, we propose a two-timescale projection neural network (PNN) for solving optimization problems with nonconvex functions. We prove the convergence of the PNN with sufficiently different timescales to a local optimal solution. We develop a collaborative neurodynamic approach with multiple such PNNs to search for global optimal solutions. In addition, we develop a collaborative neurodynamic approach with multiple PNNs connected via a directed graph for distributed global optimization. We elaborate on four numerical examples to illustrate the characteristics of the approaches.

An event-triggered collaborative neurodynamic approach to distributed global optimization

In this paper, we propose an event-triggered collaborative neurodynamic approach to distributed global optimization in the presence of nonconvexity. We design a projection neural network group consisting of multiple projection neural networks coupled via a communication network. We prove the convergence of the projection neural network group to Karush-Kuhn-Tucker points of a given global optimization problem. To reduce communication bandwidth consumption, we adopt an event-triggered mechanism to liaise with other neural networks in the group with the Zeno behavior being precluded. We employ multiple projection neural network groups for scattered searches and re-initialize their states using a meta-heuristic rule in the collaborative neurodynamic optimization framework. In addition, we apply the collaborative neurodynamic approach for distributed optimal chiller loading in a heating, ventilation, and air conditioning system.

Progress analysis of a multi-recombinative evolution strategy on the highly multimodal Rastrigin function

A first and second order progress rate analysis was conducted for the intermediate multi-recombinative Evolution Strategy (μ/μI, λ)-ES with isotropic scale-invariant mutations on the highly multimodal Rastrigin test function. Closed-form analytic solutions for the progress rates are obtained in the limit of large dimensionality and large populations. The first order results are able to model the one-generation progress including local attraction phenomena. Furthermore, a second order progress rate is derived yielding additional correction terms and further improving the progress model. The obtained results are compared to simulations and show good agreement, even for moderately large populations and dimensionality. The progress rates are applied within a dynamical systems approach, which models the evolution using difference equations. The obtained dynamics are compared to real averaged optimization runs and yield good agreement. The results improve further when dimensionality and population size are increased. Local and global convergence is investigated within given model showing that large mutations are needed to maximize the probability of global convergence, which comes at the expense of efficiency. An outlook regarding future research goals is provided.

An optimized machine learning method for predicting wogonin therapy for the treatment of pulmonary hypertension

Human health is at risk from pulmonary hypertension (PH), characterized by decreased pulmonary vascular resistance and constriction of the pulmonary vessels, resulting in right heart failure and dysfunction. Thus, preventing PH and monitoring its progression before treating it is vital. Wogonin, derived from the leaves of Scutellaria baicalensis Georgi, exhibits remarkable pharmacological activity. In this study, we examined the effectiveness of wogonin in mitigating the progression of PH in mice using right heart catheterization and hematoxylin-eosin (HE) staining. As an alternative to minimize the possibility of harming small animals, we present a scientifically effective feature selection method (BSCDWOA-KELM) that will allow us to develop a novel simpler noninvasive prediction method for wogonin in treating PH. In this method, we use the proposed enhanced whale optimizer (SCDWOA) in conjunction with the kernel extreme learning machine (KELM). Initially, we let SCDWOA perform global optimization experiments on the IEEE CEC2014 benchmark function set to verify its core advantages. Lastly, 12 public and PH datasets are examined for feature selection experiments using BSCDWOA-KELM. As shown in the experimental results for global optimization, the proposed SCDWOA has better convergence performance. Meanwhile, the proposed binary SCDWOA (BSCDWOA) significantly improves the ability of KELM to classify data. By utilizing the BSCDWOA-KELM, key indicators such as the Red blood cell (RBC), the Haemoglobin (HGB), the Lymphocyte percentage (LYM%), the Hematocrit (HCT), and the Red blood cell distribution width-size distribution (RDW-SD) can be efficiently screened in the Pulmonary hypertension dataset, and one of its most essential points is its accuracy of greater than 0.98. Consequently, the BSCDWOA-KELM introduced in this study can be used to predict wogonin therapy for treating pulmonary hypertension in a simple and noninvasive manner.

Fully automatic tracking of native glenohumeral kinematics from stereo-radiography

The current work introduces a system for fully automatic tracking of native glenohumeral kinematics in stereo-radiography sequences. The proposed method first applies convolutional neural networks to obtain segmentation and semantic key point predictions in biplanar radiograph frames. Preliminary bone pose estimates are computed by solving a non-convex optimization problem with semidefinite relaxations to register digitized bone landmarks to semantic key points. Initial poses are then refined by registering computed tomography-based digitally reconstructed radiographs to captured scenes, which are masked by segmentation maps to isolate the shoulder joint. A particular neural net architecture which exploits subject-specific geometry is also introduced to improve segmentation predictions and increase robustness of subsequent pose estimates. The method is evaluated by comparing predicted glenohumeral kinematics to manually tracked values from 17 trials capturing 4 dynamic activities. Median orientation differences between predicted and ground truth poses were 1.7∘ and 8.6∘ for the scapula and humerus, respectively. Joint-level kinematics differences were less than 2∘ in 65%, 13%, and 63% of frames for XYZ orientation DoFs based on Euler angle decompositions. Automation of kinematic tracking can increase scalability of tracking workflows in research, clinical, or surgical applications.

Prediction of fractional flow reserve with enhanced ant lion optimized support vector machine

The evaluation of coronary morphology provides important guidance for the treatment of coronary heart disease (CHD). A chaotic Gaussian mutation antlion optimizer algorithm (CGALO) is proposed in the paper, and it is combined with SVM to construct a classification prediction model for Fractional flow reserve (FFR). To overcome the limitations of the original antlion optimizer (ALO) algorithm, the chaotic Gaussian mutation strategy is introduced, which leads to an improvement in its convergence speed and accuracy. To evaluate the proposed algorithm's performance, comparative experiments were conducted on 23 benchmark functions alongside 12 other cutting-edge optimization algorithms. The experimental outcomes demonstrate that the proposed algorithm achieves superior convergence accuracy and speed compared to the alternative comparison algorithms. Additionally, it is combined with SVM and FS to construct a hierarchical FFR classification model, which is utilized to make effective predictions for 84 patients at the affiliated hospital of medical school, Ningbo university. The experimental results demonstrate that the proposed model achieves an average accuracy of 92%. Moreover, it concludes that smoking history, number of lesion vessels, lesion location, diffuse lesions and ST segment changes, and other factors are the most critical indicators for FFR. Therefore, the model that has been established is a new FFR intelligent classification prediction technology that can effectively assist doctors in making corresponding decisions and evaluation plans.

Enhanced crow search algorithm with multi-stage search integration for global optimization problems

Crow search algorithm (CSA), as a new swarm intelligence algorithm that simulates the crows' behaviors of hiding and tracking food in nature, performs well in solving many optimization problems. However, while handling complex and high-dimensional global optimization problems, CSA is apt to fall into evolutionary stagnation and has slow convergence speed, low accuracy, and weak robustness. This is mainly because it only utilizes a single search stage, where position updating relies on random following among individuals or arbitrary flight of individuals. To address these deficiencies, a CSA with multi-stage search integration (MSCSA) is presented. Chaos and multiple opposition-based learning techniques are first introduced to improve original population quality and ergodicity. The free foraging stage based on normal random distribution and Lévy flight is designed to conduct local search for enhancing the solution accuracy. And the following stage using mixed guiding individuals is presented to perform global search for expanding the search space through tracing each other among individuals. Finally, the large-scale migration stage based on the best individual and mixed guiding individuals concentrates on increasing the population diversity and helping the population jump out of local optima by moving the population to a promising area. All of these strategies form multi-level and multi-granularity balances between global exploration and local exploitation throughout the evolution. The proposed MSCSA is compared with a range of other algorithms, including original CSA, three outstanding variants of CSA, two classical meta-heuristics, and six state-of-the-art meta-heuristics covering different categories. The experiments are conducted based on the complex and high-dimensional benchmark functions CEC 2017 and CEC 2010, respectively. The experimental and statistical results demonstrate that MSCSA is competitive for tackling large-scale complicated problems, and is significantly superior to the competitors.

Gaussian bare-bone slime mould algorithm: performance optimization and case studies on truss structures

The slime mould algorithm (SMA) is a new meta-heuristic algorithm recently proposed. The algorithm is inspired by the foraging behavior of polycephalus slime moulds. It simulates the behavior and morphological changes of slime moulds during foraging through adaptive weights. Although the original SMA's performance is better than most swarm intelligence algorithms, it still has shortcomings, such as quickly falling into local optimal values and insufficient exploitation. This paper proposes a Gaussian barebone mutation enhanced SMA (GBSMA) to alleviate the original SMA's shortcomings. First of all, the Gaussian function in the Gaussian barebone accelerates the convergence while also expanding the search space, which improves the algorithm exploration and exploitation capabilities. Secondly, the differential evolution (DE) update strategy in the Gaussian barebone, using rand as the guiding vector. It also enhances the algorithm's global search performance to a certain extent. Also, the greedy selection is introduced on this basis, which prevents individuals from performing invalid position updates. In the IEEE CEC2017 test function, the proposed GBSMA is compared with a variety of meta-heuristic algorithms to verify the performance of GBSMA. Besides, GBSMA is applied to solve truss structure optimization problems. Experimental results show that the convergence speed and solution accuracy of the proposed GBSMA are significantly better than the original SMA and other similar products.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10462-022-10370-7.

A modified reptile search algorithm for global optimization and image segmentation: Case study brain MRI images

In this paper, we proposed an enhanced reptile search algorithm (RSA) for global optimization and selected optimal thresholding values for multilevel image segmentation. RSA is a recent metaheuristic optimization algorithm depending on the hunting behavior of crocodiles. RSA is inclined to inadequate diversity, local optima, and unbalanced exploitation abilities as other metaheuristic algorithms. The RUNge Kutta optimizer (RUN) is a novel metaheuristic algorithm that has demonstrated effectiveness in solving real-world optimization problems. The enhanced solution quality (ESQ) in RUN utilizes the thus-far best solution to promote the quality of solutions, improve the convergence speed, and effectively balance the exploration and exploitation steps. Also, the Scale factor (SF) has a randomized adaptation nature, which helps RUN in further improving the exploration and exploitation steps. This parameter ensures a smooth transition from exploration to exploitation. In order to mitigate the drawbacks of the RSA algorithm, this paper proposed a modified RSA (mRSA), which combines the RSA algorithm with the RUN. The ESQ mechanism and the scale factor boost the original RSA's performance, enhance convergence speed, bypass local optimum, and enhance the balance between exploitation and exploration. The validity of mRSA was verified using two experimental sequences. First, we applied mRSA to CEC'2020 benchmark functions of various types and dimensions, showing that mRSA has more robust search capabilities than the original RSA and popular counterpart algorithms concerning statistical, convergence, and diversity measurements. The second experiment evaluated mRSA for a real-world application to solve magnetic resonance imaging (MRI) brain image segmentation. Overall experimental results confirm that the mRSA has a strong optimization ability. Also, mRSA method is a more successful multilevel thresholding segmentation and outperforms comparison methods according to different performance measures.

Crisscross Harris Hawks Optimizer for Global Tasks and Feature Selection

Harris Hawks Optimizer (HHO) is a recent well-established optimizer based on the hunting characteristics of Harris hawks, which shows excellent efficiency in solving a variety of optimization issues. However, it undergoes weak global search capability because of the levy distribution in its optimization process. In this paper, a variant of HHO is proposed using Crisscross Optimization Algorithm (CSO) to compensate for the shortcomings of original HHO. The novel developed optimizer called Crisscross Harris Hawks Optimizer (CCHHO), which can effectively achieve high-quality solutions with accelerated convergence on a variety of optimization tasks. In the proposed algorithm, the vertical crossover strategy of CSO is used for adjusting the exploitative ability adaptively to alleviate the local optimum; the horizontal crossover strategy of CSO is considered as an operator for boosting explorative trend; and the competitive operator is adopted to accelerate the convergence rate. The effectiveness of the proposed optimizer is evaluated using 4 kinds of benchmark functions, 3 constrained engineering optimization issues and feature selection problems on 13 datasets from the UCI repository. Comparing with nine conventional intelligence algorithms and 9 state-of-the-art algorithms, the statistical results reveal that the proposed CCHHO is significantly more effective than HHO, CSO, CCNMHHO and other competitors, and its advantage is not influenced by the increase of problems' dimensions. Additionally, experimental results also illustrate that the proposed CCHHO outperforms some existing optimizers in working out engineering design optimization; for feature selection problems, it is superior to other feature selection methods including CCNMHHO in terms of fitness, error rate and length of selected features.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s42235-022-00298-7.

MLAGO: machine learning-aided global optimization for Michaelis constant estimation of kinetic modeling

BACKGROUND

Kinetic modeling is a powerful tool for understanding the dynamic behavior of biochemical systems. For kinetic modeling, determination of a number of kinetic parameters, such as the Michaelis constant (K_m), is necessary, and global optimization algorithms have long been used for parameter estimation. However, the conventional global optimization approach has three problems: (i) It is computationally demanding. (ii) It often yields unrealistic parameter values because it simply seeks a better model fitting to experimentally observed behaviors. (iii) It has difficulty in identifying a unique solution because multiple parameter sets can allow a kinetic model to fit experimental data equally well (the non-identifiability problem).

RESULTS

To solve these problems, we propose the Machine Learning-Aided Global Optimization (MLAGO) method for K_m estimation of kinetic modeling. First, we use a machine learning-based K_m predictor based only on three factors: EC number, KEGG Compound ID, and Organism ID, then conduct a constrained global optimization-based parameter estimation by using the machine learning-predicted K_m values as the reference values. The machine learning model achieved relatively good prediction scores: RMSE = 0.795 and R² = 0.536, making the subsequent global optimization easy and practical. The MLAGO approach reduced the error between simulation and experimental data while keeping K_m values close to the machine learning-predicted values. As a result, the MLAGO approach successfully estimated K_m values with less computational cost than the conventional method. Moreover, the MLAGO approach uniquely estimated K_m values, which were close to the measured values.

CONCLUSIONS

MLAGO overcomes the major problems in parameter estimation, accelerates kinetic modeling, and thus ultimately leads to better understanding of complex cellular systems. The web application for our machine learning-based K_m predictor is accessible at https://sites.google.com/view/kazuhiro-maeda/software-tools-web-apps , which helps modelers perform MLAGO on their own parameter estimation tasks.

A review of recent advances in quantum-inspired metaheuristics

Quantum-inspired metaheuristics emerged by combining the quantum mechanics principles with the metaheuristic algorithms concepts. These algorithms extend the diversity of the population, which is a primary key to proper global search and is guaranteed using the quantum bits' probabilistic representation. In this work, we aim to review recent quantum-inspired metaheuristics and to cover the merits of linking the quantum mechanics notions with optimization techniques and its multiplicity of applications in real-world problems and industry. Moreover, we reported the improvements and modifications of proposed algorithms and identified the scope's challenges. We gathered proposed algorithms of this scope between 2017 and 2022 and classified them based on the sources of inspiration. The source of inspiration for most quantum-inspired metaheuristics are the Genetic and Evolutionary algorithms, followed by swarm-based algorithms, and applications range from image processing to computer networks and even multidisciplinary fields such as flight control and structural design. The promising results of quantum-inspired metaheuristics give hope that more conventional algorithms can be combined with quantum mechanics principles in the future to tackle optimization problems in numerous disciplines.

Estimating the optimal linear combination of predictors using spherically constrained optimization

BACKGROUND

In the context of a binary classification problem, the optimal linear combination of continuous predictors can be estimated by maximizing the area under the receiver operating characteristic curve. For ordinal responses, the optimal predictor combination can similarly be obtained by maximization of the hypervolume under the manifold (HUM). Since the empirical HUM is discontinuous, non-differentiable, and possibly multi-modal, solving this maximization problem requires a global optimization technique. Estimation of the optimal coefficient vector using existing global optimization techniques is computationally expensive, becoming prohibitive as the number of predictors and the number of outcome categories increases.

RESULTS

We propose an efficient derivative-free black-box optimization technique based on pattern search to solve this problem, which we refer to as Spherically Constrained Optimization Routine (SCOR). Through extensive simulation studies, we demonstrate that the proposed method achieves better performance than existing methods including the step-down algorithm. Finally, we illustrate the proposed method to predict the severity of swallowing difficulty after radiation therapy for oropharyngeal cancer based on radiation dose to various structures in the head and neck.

CONCLUSIONS

Our proposed method addresses an important challenge in combining multiple biomarkers to predict an ordinal outcome. This problem is particularly relevant to medical research, where it may be of interest to diagnose a disease with various stages of progression or a toxicity with multiple grades of severity. We provide the implementation of our proposed SCOR method as an R package, available online at https://CRAN.R-project.org/package=SCOR .

Progress Rate Analysis of Evolution Strategies on the Rastrigin Function: First Results

A first order progress rate is derived for the intermediate multi-recombinative Evolution Strategy (μ/μI, λ)-ES on the highly multimodal Rastrigin test function. The progress is derived within a linearized model applying the method of so-called noisy order statistics. To this end, the mutation-induced variance of the Rastrigin function is determined. The obtained progress approximation is compared to simulations and yields strengths and limitations depending on mutation strength and distance to the optimizer. Furthermore, the progress is iterated using the dynamical systems approach and compared to averaged optimization runs. The property of global convergence within given approximation is discussed. As an outlook, the need of an improved first order progress rate as well as the extension to higher order progress including positional fluctuations is explained.

A new unmanned aerial vehicle intrusion detection method based on belief rule base with evidential reasoning

With the growing security demands in the public, civil and military fields, unmanned aerial vehicle (UAV) intrusion detection has attracted increasing attention. In view of the shortcomings of the current UAV intrusion detection model using Wi-Fi data traffic in terms of detection accuracy, sample size reduction, and model interpretability, this paper proposes a new detection algorithm for UAV intrusion. This paper presents an interpretable intrusion detection model for UAVs based on the belief rule base (BRB). BRB can effectively use various types of information to establish any nonlinear relationship between the model input and output. It can model and simulate any nonlinear model and optimize the model parameters. However, the rule combination explosion problem is encountered in BRB if there are too many attributes. Therefore, an evidential reasoning (ER) algorithm is proposed for solving this problem. By combining the capabilities of the ER and the BRB methodologies, a new evaluation model, named the EBRB-based model, is proposed here for predicting UAV intrusion detection, even in the case of a massive number of attributes. The global optimization of the model is ensured. A new interpretable and globally optimized UAV intrusion detection model is proposed, which is the main contribution of this paper. An experimental case is used to demonstrate the implementation and application of the proposed UAV intrusion detection method.

Brain-inspired chaotic backpropagation for MLP

Backpropagation (BP) algorithm is one of the most basic learning algorithms in deep learning. Although BP has been widely used, it still suffers from the problem of easily falling into the local minima due to its gradient dynamics. Inspired by the fact that the learning of real brains may exploit chaotic dynamics, we propose the chaotic backpropagation (CBP) algorithm by integrating the intrinsic chaos of real neurons into BP. By validating on multiple datasets (e.g. cifar10), we show that, for multilayer perception (MLP), CBP has significantly better abilities than those of BP and its variants in terms of optimization and generalization from both computational and theoretical viewpoints. Actually, CBP can be regarded as a general form of BP with global searching ability inspired by the chaotic learning process in the brain. Therefore, CBP not only has the potential of complementing or replacing BP in deep learning practice, but also provides a new way for understanding the learning process of the real brain.

A new hybrid method based on Aquila optimizer and tangent search algorithm for global optimization

Since no single algorithm can provide the optimal solutions for all problems, new metaheuristic methods are always being proposed or developed by combining current algorithms or creating adaptable versions. Metaheuristic methods should have a balanced exploitation and exploration stages. One of these two talents may be sufficient in some metaheuristic methods, while the other may be insufficient. By integrating the strengths of the two algorithms and hybridizing them, a more efficient algorithm can be formed. In this paper, the Aquila optimizer-tangent search algorithm (AO-TSA) is proposed as a new hybrid approach that uses the intensification stage of the tangent search algorithm (TSA) instead of the limited exploration stage to improve the Aquila optimizer's exploitation capabilities (AO). In addition, the local minimum escape stage of TSA is applied in AO-TSA to avoid the local minimum stagnation problem. The performance of AO-TSA is compared with other current metaheuristic algorithms using a total of twenty-one benchmark functions consisting of six unimodal, six multimodal, six fixed-dimension multimodal, and three modern CEC 2019 benchmark functions according to different metrics. Furthermore, two real engineering design problems are also used for performance comparison. Sensitivity analysis and statistical test analysis are also performed. Experimental results show that hybrid AO-TSA gives promising results and seems an effective method for global solution search and optimization problems.

An adaptive dimension differential evolution algorithm based on ranking scheme for global optimization

In recent years, evolutionary algorithms based on swarm intelligence have drawn much attention from researchers. This kind of artificial intelligent algorithms can be utilized for various applications, including the ones of big data information processing in nowadays modern world with heterogeneous sensor and IoT systems. Differential evolution (DE) algorithm is one of the important algorithms in the field of optimization because of its powerful and simple characteristics. The DE has excellent development performance and can approach global optimal solution quickly. At the same time, it is also easy to get into local optimal, so it could converge prematurely. In the view of these shortcomings, this article focuses on the improvement of the algorithm of DE and proposes an adaptive dimension differential evolution (ADDE) algorithm that can adapt to dimension updating properly and balance the search and the development better. In addition, this article uses the elitism to improve the location update strategy to improve the efficiency and accuracy of the search. In order to verify the performance of the new ADDE, this study carried out experiments with other famous algorithms on the CEC2014 test suite. The comparison results show that the ADDE is more competitive.

An efficient rotational direction heap-based optimization with orthogonal structure for medical diagnosis

The heap-based optimizer (HBO) is an optimization method proposed in recent years that may face local stagnation problems and show slow convergence speed due to the lack of detailed analysis of optimal solutions and a comprehensive search. Therefore, to mitigate these drawbacks and strengthen the performance of the algorithm in the field of medical diagnosis, a new MGOHBO method is proposed by introducing the modified Rosenbrock's rotational direction method (MRM), an operator from the grey wolf optimizer (GWM), and an orthogonal learning strategy (OL). The MGOHBO is compared with eleven famous and improved optimizers on IEEE CEC 2017. The results on benchmark functions indicate that the boosted MGOHBO has several significant advantages in terms of convergence accuracy and speed of the process. Additionally, this article analyzed the diversity and balance of MGOHBO in detail. Finally, the proposed MGOHBO algorithm is utilized to optimize the kernel extreme learning machines (KELM), and a new MGOHBO-KELM is proposed. To validate the performance of MGOHBO-KELM, seven disease diagnostic questions were introduced for testing in this work. In contrast to advanced models such as HBO-KELM and BP, it can be concluded that the MGOHBO-KELM model can achieve optimal results, which also proves that it has practical significance in solving medical diagnosis problems.

Chaotic simulated annealing multi-verse optimization enhanced kernel extreme learning machine for medical diagnosis

Classification models such as Multi-Verse Optimization (MVO) play a vital role in disease diagnosis. To improve the efficiency and accuracy of MVO, in this paper, the defects of MVO are mitigated and the improved MVO is combined with kernel extreme learning machine (KELM) for effective disease diagnosis. Although MVO obtains some relatively good results on some problems of interest, it suffers from slow convergence speed and local optima entrapment for some many-sided basins, especially multi-modal problems with high dimensions. To solve these shortcomings, in this study, a new chaotic simulated annealing overhaul of MVO (CSAMVO) is proposed. Based on MVO, two approaches are adopted to offer a relatively stable and efficient convergence speed. Specifically, a chaotic intensification mechanism (CIP) is applied to the optimal universe evaluation stage to increase the depth of the universe search. After obtaining relatively satisfactory results, the simulated annealing algorithm (SA) is employed to reinforce the capability of MVO to avoid local optima. To evaluate its performance, the proposed CSAMVO approach was compared with a wide range of classical algorithms on thirty-nine benchmark functions. The results show that the improved MVO outperforms the other algorithms in terms of solution quality and convergence speed. Furthermore, based on CSAMVO, a hybrid KELM model termed CSAMVO-KELM is established for disease diagnosis. To evaluate its effectiveness, the new hybrid system was compared with a multitude of competitive classifiers on two disease diagnosis problems. The results demonstrate that the proposed CSAMVO-assisted classifier can find solutions with better learning potential and higher predictive performance.

Orientation, pattern center refinement and deformation state extraction through global optimization algorithms

Global optimization algorithms have been adopted to the simultaneously refinement of orientation and pattern center for electron backscatter diffraction patterns as well as deformation state extraction. The hyperparameter space and mutation schemes of differential evolution (DE) algorithm has been thoroughly investigated and showed to be a more efficient algorithm than the particle swarm optimization (PSO) algorithm. The optimal hyperparameters for DE generally depend on conditions such as the number of variables to be optimized and the size of bounded search space but reasonably close initial values for crossover probability is 0.9, mutation factor is 0.5, population size is ten times the number of variables, and number of iterations is at least 100. Validation on a set of simulated undeformed single crystal nickel patterns reveals a mean accuracy of ≈0.03° and ≈0.01% detector width across a large field of view. In addition, validation using noisy simulated deformed patterns with known deformation state and pattern center shows that the mean accuracy of shear strain and rotation components is ≈0.001 and for the normal strain ≈0.002.

GloMPO (Globally Managed Parallel Optimization): a tool for expensive, black-box optimizations, application to ReaxFF reparameterizations

In this work we explore the properties which make many real-life global optimization problems extremely difficult to handle, and some of the common techniques used in literature to address them. We then introduce a general optimization management tool called GloMPO (Globally Managed Parallel Optimization) to help address some of the challenges faced by practitioners. GloMPO manages and shares information between traditional optimization algorithms run in parallel. We hope that GloMPO will be a flexible framework which allows for customization and hybridization of various optimization ideas, while also providing a substitute for human interventions and decisions which are a common feature of optimization processes of hard problems. GloMPO is shown to produce lower minima than traditional optimization approaches on global optimization test functions, the Lennard-Jones cluster problem, and ReaxFF reparameterizations. The novel feature of forced optimizer termination was shown to find better minima than normal optimization. GloMPO is also shown to provide qualitative benefits such a identifying degenerate minima, and providing a standardized interface and workflow manager.

Differential evolution-assisted salp swarm algorithm with chaotic structure for real-world problems

There is a new nature-inspired algorithm called salp swarm algorithm (SSA), due to its simple framework, it has been widely used in many fields. But when handling some complicated optimization problems, especially the multimodal and high-dimensional optimization problems, SSA will probably have difficulties in convergence performance or dropping into the local optimum. To mitigate these problems, this paper presents a chaotic SSA with differential evolution (CDESSA). In the proposed framework, chaotic initialization and differential evolution are introduced to enrich the convergence speed and accuracy of SSA. Chaotic initialization is utilized to produce a better initial population aim at locating a better global optimal. At the same time, differential evolution is used to build up the search capability of each agent and improve the sense of balance of global search and intensification of SSA. These mechanisms collaborate to boost SSA in accelerating convergence activity. Finally, a series of experiments are carried out to test the performance of CDESSA. Firstly, IEEE CEC2014 competition fuctions are adopted to evaluate the ability of CDESSA in working out the real-parameter optimization problems. The proposed CDESSA is adopted to deal with feature selection (FS) problems, then five constrained engineering optimization problems are also adopted to evaluate the property of CDESSA in dealing with real engineering scenarios. Experimental results reveal that the proposed CDESSA method performs significantly better than the original SSA and other compared methods.

Rank-driven salp swarm algorithm with orthogonal opposition-based learning for global optimization

Salp swarm algorithm (SSA) is a relatively new and straightforward swarm-based meta-heuristic optimization algorithm, which is inspired by the flocking behavior of salps when foraging and navigating in oceans. Although SSA is very competitive, it suffers from some limitations including unbalanced exploration and exploitation operation, slow convergence. Therefore, this study presents an improved version of SSA, called OOSSA, to enhance the comprehensive performance of the basic method. In preference, a new opposition-based learning strategy based on optical lens imaging principle is proposed, and combined with the orthogonal experimental design, an orthogonal lens opposition-based learning technique is designed to help the population jump out of a local optimum. Next, the scheme of adaptively adjusting the number of leaders is embraced to boost the global exploration capability and improve the convergence speed. Also, a dynamic learning strategy is applied to the canonical methodology to improve the exploitation capability. To confirm the efficacy of the proposed OOSSA, this paper uses 26 standard mathematical optimization functions with various features to test the method. Alongside, the performance of the proposed methodology is validated by Wilcoxon signed-rank and Friedman statistical tests. Additionally, three well-known engineering optimization problems and unknown parameters extraction issue of photovoltaic model are applied to check the ability of the OOSA algorithm to obtain solutions to intractable real-world problems. The experimental results reveal that the developed OOSSA is significantly superior to the standard SSA, currently popular SSA-based algorithms, and other state-of-the-artmeta-heuristic algorithms for solving numerical optimization, real-world engineering optimization, and photovoltaic model parameter extraction problems. Finally, an OOSSA-based path planning approach is developed for creating the shortest obstacle-free route for autonomous mobile robots. Our introduced method is compared with several successful swarm-based metaheuristic techniques in five maps, and the comparative results indicate that the suggested approach can generate the shortest collision-free trajectory as compared to other peers.

Improved interval methods for solving circle packing problems in the unit square

In this work computer-assisted optimality proofs are given for the problems of finding the densest packings of 31, 32, and 33 non-overlapping equal circles in a square. In a study of 2005, a fully interval arithmetic based global optimization method was introduced for the problem class, solving the cases 28, 29, 30. Until now, these were the largest problem instances solved on a computer. Using the techniques of that paper, the estimated solution time for the next three cases would have been 3-6 CPU months. In the present paper this former method is improved in both its local and global search phases. We discuss a new interval-based polygon representation of the core local method for eliminating suboptimal regions, which has a simpler implementation, easier proof of correctness, and faster behaviour than the former one. Furthermore, a modified strategy is presented for the global phase of the search, including improved symmetry filtering and tile pattern matching. With the new method the cases n = 31 , 32 , 33 have been solved in 26, 61, and 13 CPU hours, giving high precision enclosures for all global optimizers and the optimum value. After eliminating the hardware and compiler improvements since the former study, the new proof technique became roughly about 40-100 times faster than the previous one. In addition, the new implementation is suitable for solving the next few circle packing instances with similar computational effort.

A global neural network learning machine: Coupled integer and fractional calculus operator with an adaptive learning scheme

Find the global optimal solution of the model is one promising research topic in computational intelligent community. Dependent on analogies to natural processes, the evolutionary swarm intelligent algorithms are widely used for solving global optimization problems which directed by the fitness values. In this paper, we propose one efficient fractional global learning machine (Fragmachine) which includes two stages (descending and ascending) to determine the optimal search path. The neural network model is used to approach the given fitness value. Specifically, for the descending stage, the integer gradient of the network output with respect the current location is employed to find the next descending point, while for the ascending stage, the fractional gradient is implemented to climb and escape from the local optimal point. We further propose one adaptive learning rate during training which relies on both the current gradient (integer or fractional) information and the fitness value. Finally, a series of numerical experiments verify the effectiveness of the proposed algorithm, Fragmachine.

Docking Paradigm in Drug Design

Docking is in demand for the rational computer aided structure based drug design. A review of docking methods and programs is presented. Different types of docking programs are described. They include docking of non-covalent small ligands, protein-protein docking, supercomputer docking, quantum docking, the new generation of docking programs and the application of docking for covalent inhibitors discovery. Taking into account the threat of COVID-19, we present here a short review of docking applications to the discovery of inhibitors of SARS-CoV and SARS-CoV-2 target proteins, including our own result of the search for inhibitors of SARS-CoV-2 main protease using docking and quantum chemical post-processing. The conclusion is made that docking is extremely important in the fight against COVID-19 during the process of development of antivirus drugs having a direct action on SARS-CoV-2 target proteins.

Automated Biocircuit Design with SYNBADm

SYNBADm is a Matlab toolbox for the automated design of biocircuits using a model-based optimization approach. It enables the design of biocircuits with pre-defined functions starting from libraries of biological parts. SYNBADm makes use of mixed integer global optimization and allows both single and multi-objective design problems. Here we describe a basic protocol for the design of synthetic gene regulatory circuits. We illustrate step-by-step how to solve two different problems: (1) the (single objective) design of a synthetic oscillator and (2) the (multi-objective) design of a circuit with switch-like behavior upon induction, with a good compromise between performance and protein production cost.

An Experimental and Computational Protocol to Study Cell Proliferation in Human Acute Myeloid Leukemia Xenografts

Acute myeloid leukemia (AML) is a highly frequent hematological malignancy, characterized by clinical and biological diversity, along with high relapse and mortality rates. The inherent functional and genetic intra-tumor heterogeneity in AML is thought to play an important role in disease recurrence and resistance to chemotherapy. Patient-derived xenograft (PDX) models preserve important features of the original tumor, allowing, at the same time, experimental manipulation and in vivo amplification of the human cells. Here we present a detailed protocol for the generation of fluorescently labeled AML PDX models to monitor cell proliferation kinetics in vivo, at the single-cell level. Although experimental protocols for cell proliferation studies are well established and widespread, they are not easily applicable to in vivo contexts, and the analysis of related time-series data is often complex to achieve. To overcome these limitations, model-driven approaches can be exploited to investigate different aspects of cell population dynamics. Among the existing approaches, the ProCell framework is able to perform detailed and accurate stochastic simulations of cell proliferation, relying on flow cytometry data. In particular, by providing an initial and a target fluorescence histogram, ProCell automatically assesses the validity of any user-defined scenario of intra-tumor heterogeneity, that is, it is able to infer the proportion of various cell subpopulations (including quiescent cells) and the division interval of proliferating cells. Here we explain the protocol in detail, providing a description of our methodology for the conditional expression of H2B-GFP in human AML xenografts, data processing by flow cytometry, and the final elaboration in ProCell.

Optimal control analysis and Practical NMPC applied to refrigeration systems

This work is focused on optimal control of mechanical compression refrigeration systems. A reduced-order state-space model based on the moving boundary approach is proposed for the canonical cycle, which eases the controller design. The optimal cycle (that satisfying the cooling demand while maximizing efficiency) is defined by three variables, but only two inputs are available, therefore the controllability of the proposed model is studied. It is shown through optimization simulations how optimal cycles for a range of the cooling demand turn out not to be achieved by keeping the degree of superheating to a minimum. The Practical NMPC and a well-known feedback-plus-feedforward strategy from the literature are compared in simulation, both showing trouble in reaching the optimal cycle, which agrees with the controllability study.

Reliability of semiempirical and DFTB methods for the global optimization of the structures of nanoclusters

In this work, we explore the possibility of using computationally inexpensive electronic structure methods, such as semiempirical and DFTB calculations, for the search of the global minimum (GM) structure of chemical systems. The basic prerequisite that these inexpensive methods will need to fulfill is that their lowest energy structures can be used as starting point for a subsequent local optimization at a benchmark level that will yield its GM. If this is possible, one could bypass the global optimization at the expensive method, which is currently impossible except for very small molecules. Specifically, we test our methods with clusters of second row elements including systems of several bonding types, such as alkali, metal, and covalent clusters. The results reveal that the DFTB3 method yields reasonable results and is a potential candidate for this type of applications. Even though the DFTB2 approach using standard parameters is proven to yield poor results, we show that a re-parametrization of only its repulsive part is enough to achieve excellent results, even when applied to larger systems outside the training set.

DOMINO: Data-driven Optimization of bi-level Mixed-Integer NOnlinear Problems

The Data-driven Optimization of bi-level Mixed-Integer NOnlinear problems (DOMINO) framework is presented for addressing the optimization of bi-level mixed-integer nonlinear programming problems. In this framework, bi-level optimization problems are approximated as single-level optimization problems by collecting samples of the upper-level objective and solving the lower-level problem to global optimality at those sampling points. This process is done through the integration of the DOMINO framework with a grey-box optimization solver to perform design of experiments on the upper-level objective, and to consecutively approximate and optimize bi-level mixed-integer nonlinear programming problems that are challenging to solve using exact methods. The performance of DOMINO is assessed through solving numerous bi-level benchmark problems, a land allocation problem in Food-Energy-Water Nexus, and through employing different data-driven optimization methodologies, including both local and global methods. Although this data-driven approach cannot provide a theoretical guarantee to global optimality, we present an algorithmic advancement that can guarantee feasibility to large-scale bi-level optimization problems when the lower-level problem is solved to global optimality at convergence.

Subset selection via continuous optimization with applications to network design

Choosing a subset of representative items from a set of alternatives is an important problem in many scientific fields such as environmental science and statistics. For most practical problems, however, a computationally efficient solution method is not known to exist. While this problem has attracted a significant amount of attention, the majority of specifically designed algorithms do not scale well with respect to the problem size or do not provide a usable open-source package. In this study, we show that any global continuous optimization technique can be used for solving the representative subset selection problem. The latter is achieved by designing a simple transformation which embeds the problem's discrete space into a larger continuous space. The proposed methodology is applied to design problems in environmental and statistical domains. We evaluate the proposed method using several open-source global optimization packages, and show that this technique compares favorably with existing direct methods.

An open-source tool for the validation of finite element models using three-dimensional full-field measurements

Three-dimensional (3D) full-field measurements provide a comprehensive and accurate validation of finite element (FE) models. For the validation, the result of the model and measurements are compared based on two respective point-sets and this requires the point-sets to be registered in one coordinate system. Point-set registration is a non-convex optimization problem that has widely been solved by the ordinary iterative closest point algorithm. However, this approach necessitates a good initialization without which it easily returns a local optimum, i.e. an erroneous registration. The globally optimal iterative closest point (Go-ICP) algorithm has overcome this drawback and forms the basis for the presented open-source tool that can be used for the validation of FE models using 3D full-field measurements. The capability of the tool is demonstrated using an application example from the field of biomechanics. Methodological problems that arise in real-world data and the respective implemented solution approaches are discussed.

Global Optimization of Dielectric Metasurfaces Using a Physics-Driven Neural Network

We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it initially generates a distribution of devices that broadly samples the design space and then shifts and refines this distribution toward favorable design space regions over the course of optimization. Training is performed by calculating the forward and adjoint electromagnetic simulations of outputted devices and using the subsequent efficiency gradients for backpropagation. With metagratings operating across a range of wavelengths and angles as a model system, we show that devices produced from the trained generative network have efficiencies comparable to or better than the best devices produced by adjoint-based topology optimization, while requiring less computational cost. Our reframing of adjoint-based optimization to the training of a generative neural network applies generally to physical systems that can utilize gradients to improve performance.

Accurate and reliable estimation of kinetic parameters for environmental engineering applications: A global, multi objective, Bayesian optimization approach

Accurate and reliable predictions of bacterial growth and metabolism from unstructured kinetic models are critical to the proper operation and design of engineered biological treatment and remediation systems. As such, parameter estimation has progressed into a routine challenge in the field of Environmental Engineering. Among the main issues identified with parameter estimation, the model-data calibration approach is a crucial, yet an often overlooked and difficult optimization problem. Here, a novel and rigorous global, multi objective, and fully Bayesian optimization approach that overcomes challenges associated with multi-variate, sparse and noisy data, as well as highly non-linear model structures commonly encountered in Environmental Engineering practice is presented. This optimization approach allows an improved definition and targeting of the compromise solution space for all multivariate problems, allowing efficient convergence, and a Bayesian component to thoroughly explore parameter and model prediction uncertainty. This global optimization approach outperformed, in terms of parameter accuracy and precision, standard, local non-linear regression routines and overcomes issues associated with premature convergence and addresses overfitting of different variables in the calibration process. •A sequential single, multi-objective, and Bayesian optimization workflow was developed to accurately and reliably estimate unstructured kinetic model parameters.•The global, single objective approach defines the global optimum (the best compromise solution) and "extreme" parameter solutions for each variable, while the global, multi-objective approach confirms the "best" compromise solution space for the Bayesian search to target and convergence is assessed using the single objective results.•The Approximate Bayesian Computational approach fully explores parameter and model prediction uncertainty targeting the compromise solution space previously identified.

Global optimization of distillation columns using surrogate models

Surrogate-based optimization of distillation columns using an iterative Kriging approach is investigated. Focus is on deterministic global optimization to avoid suboptimal local minima. The determination of optimal setups and operating conditions for ideal and non-ideal distillation columns, leading to mixed-integer nonlinear programming problems, serve as case studies. It is found that the optimization using the adapted Kriging approach yields similar results compared to the direct global optimization of the original problem in the ideal case, while it leads to a huge improvement compared to a multistart local optimization approach in the non-ideal case.

Global optimization using Gaussian processes to estimate biological parameters from image data

Parameter estimation is a major challenge in computational modeling of biological processes. This is especially the case in image-based modeling where the inherently quantitative output of the model is measured against image data, which is typically noisy and non-quantitative. In addition, these models can have a high computational cost, limiting the number of feasible simulations, and therefore rendering most traditional parameter estimation methods unsuitable. In this paper, we present a pipeline that uses Gaussian process learning to estimate biological parameters from noisy, non-quantitative image data when the model has a high computational cost. This approach is first successfully tested on a parametric function with the goal of retrieving the original parameters. We then apply it to estimating parameters in a biological setting by fitting artificial in-situ hybridization (ISH) data of the developing murine limb bud. We expect that this method will be of use in a variety of modeling scenarios where quantitative data is missing and the use of standard parameter estimation approaches in biological modeling is prohibited by the computational cost of the model.

Reliability of joint kinematic calculations based on direct kinematic and inverse kinematic models in obese children

BACKGROUND

In recent years, the reliability of inverse (IK) and direct kinematic (DK) models in gait analysis have been assessed intensively, but mainly for lean populations. However, obesity is a growing issue. So far, the sparse results available for the reliability of clinical gait analysis in obese populations are limited to direct kinematic models. Reliability error-margins for inverse kinematic models in obese populations have not been reported yet.

RESEARCH QUESTIONS

Is there a difference in the reliability of IK models compared with a DK model in obese children? Are there any differences in the joint kinematic output between IK and DK models?

METHODS

A test-retest study was conducted using three-dimensional gait analysis data from two obese female and eight obese male participants from an earlier study. Data were analyzed using a DK model and two OpenSim-based IK models. Test-retest reliability was compared by calculating the Standard Error of Measurement (SEM) along with similar absolute reliability measures. A Friedman Test was used to assess whether there were any significant differences in the reliability between the models. Kinematic output of the models was compared by using Statistical Parametric Mapping (SPM).

RESULTS

No significant differences were found in the reliability between the DK and IK models. The SPM analysis indicated several significant differences between both IK models and the DK approach. Most of these differences were continuous offsets.

SIGNIFICANCE

Reliability values showed clinically acceptable error-margins and were comparable between all models. Therefore, our results support the careful use of IK models in overweight or obese populations, e.g. for musculoskeletal modelling studies. The inconsistent kinematic output can mainly be explained by different model conventions and anatomical segment coordinate frame definitions.