Combination Of Optimization Methods Research Articles

A machine learning-based approach to ERα bioactivity and drug ADMET prediction.

By predicting ERα bioactivity and mining the potential relationship between Absorption, Distribution, Metabolism, Excretion, Toxicity (ADMET) attributes in drug research and development, the development efficiency of specific drugs for breast cancer will be effectively improved and the misjudgment rate of R&D personnel will be reduced. The quantitative prediction model of ERα bioactivity and classification prediction model of Absorption, Distribution, Metabolism, Excretion, Toxicity properties were constructed. The prediction results of ERα bioactivity were compared by XGBoot, Light GBM, Random Forest and MLP neural network. Two models with high prediction accuracy were selected and fused to obtain ERα bioactivity prediction model from Mean absolute error (MAE), mean squared error (MSE) and R2. The data were further subjected to model-based feature selection and FDR/FPR-based feature selection, respectively, and the results were placed in a voting machine to obtain Absorption, Distribution, Metabolism, Excretion, Toxicity classification prediction model. In this study, 430 molecular descriptors were removed, and finally 20 molecular descriptors with the most significant effect on biological activity obtained by the dual feature screening combined optimization method were used to establish a compound molecular descriptor prediction model for ERα biological activity, and further classification and prediction of the Absorption, Distribution, Metabolism, Excretion, Toxicity properties of the drugs were made. Eighty variables were selected by the model ExtraTreesClassifier Classifie, and 40 variables were selected by the model GradientBoostingClassifier to complete the model-based feature selection. At the same time, the feature selection method based on FDR/FPR is also selected, and the three classification models obtained by the two methods are placed into the voting machine to obtain the final model. The experimental results showed that the model's evaluation indexes and roc diagram were excellent and could accurately predict ERα bioactivity and Absorption, Distribution, Metabolism, Excretion, Toxicity properties. The model constructed in this study has high accuracy, fast convergence and robustness, has a very high accuracy for Absorption, Distribution, Metabolism, Excretion, Toxicity and ERα classification prediction, has bright prospects in the biopharmaceutical field, and is an important method for energy conservation and yield increase in the future.

A Comprehensive Study of Local, Global, and Combined Optimization Methods on Synthetic Seismic Refraction and Direct Current Resistivity Data

Most geophysical inversions face the problem of non-uniqueness, which poses a challenge in the mapping and delineation of the subsurface anomalies. To tackle this challenge, a combined local and global optimization approach is considered for jointly inverting two-dimensional direct current resistivity (DCR) and seismic refraction (SR) data that aim to estimate the corresponding physical model parameters. In this combined approach, the output of the local optimization method is used to determine the search space and tuning parameters for the global optimization algorithm. The multi-objective genetic algorithm (non-dominated sorting genetic algorithm) was utilized to jointly optimize the objective functions of two different methods. Because the genetic algorithm is a population-based optimization method, it requires numerous forward calculations. To deal with the expected high computational cost associated with this approach, parallel computing was utilized for the forward function evaluations to reduce the run time of the entire process. The proposed approach was tested using synthetic two-dimensional resistivity and velocity models that had three different types of anomalies (dyke, positive, and combined positive and negative). The results showed an improvement in the anomaly delineation in the output of the combined local and global optimization method compared with the local optimization method. Additionally, similar synthetic models were tested using only the single objective global optimization algorithm (conventional global optimization), which showed promising anomaly delineation.

A Dual-Arm Robot That Autonomously Lifts Up and Tumbles Heavy Plates Using Crane Pulley Blocks

This paper proposes a combined planning and optimization method that enables a dual-arm robot to lift up and flip heavy plates using crane pulley blocks. The problem is motivated by the low payload of modern collaborative robots. Instead of directly manipulating heavy plates that collaborative robots cannot afford, the paper develops a planner for collaborative robots to operate crane pulley blocks. The planner assumes a target plate is pre-attached to the crane hook. It optimizes dual-arm action sequences and plans the robot’s dual-arm motion that pulls the rope of the crane pulley blocks to lift up the plate. The crane pulley blocks reduce the payload that each robotic arm needs to bear. When the plate is lifted up to a satisfying pose, the planner plans a sliding-pushing motion for one of the robot arms to tumble over the plate while considering force and moment constraints. The article presents the technical details of the planner and several experiments and analysis carried out using a dual-arm robot made by two Universal Robots UR3 arms. The influence of various parameters and optimization goals are investigated and compared in depth. The results show that the proposed planner is flexible and efficient. This paper is motivated by a cleaning process in a factory that produces sewage press machines. The pressboard of sewage press machines could be as heavy as 1000 kg. Human workers need to flip and clean both sides of the board before installing them to the main axis of a sewage machine. Their solution is using a gantry crane. They attach the board to the crane hook using bearing belts, activate the crane to lift up the board. When the board is raised to a satisfying pose, the workers turn the board over by pushing it. Motivated by human workers’ actions, we developed the planner presented in this paper. We assumed crane pulley blocks in the experiments and analysis, but in practice, they may be replaced with electronic ones to improve effort and efficiency. Using the electronic ones will be a sub-problem since there is no need for pulling ropes. The proposed method is expected to help a company’s technicians better judge if they need a heavy payload manipulator or keep their current crane equipment while employing several intelligent collaborative robots to operate them. As a result, it may help to accelerate the upgrade of manufacturing sites while reducing reforming budgets. Note to Practitioners—This paper is motivated by a cleaning process in a factory that produces sewage press machines. The pressboard of sewage press machines could be as heavy as 1000 kg. Human workers need to flip and clean both sides of the board before installing them to the main axis of a sewage machine. Their solution is using a gantry crane. They attach the board to the crane hook using bearing belts, activate the crane to lift up the board. When the board is raised to a satisfying pose, the workers turn the board over by pushing it. Motivated by human workers’ actions, we developed the planner presented in this paper. We assumed crane pulley blocks in the experiments and analysis, but in practice, they may be replaced with electronic ones to improve effort and efficiency. Using the electronic ones will be a sub-problem since there is no need for pulling ropes. The proposed method is expected to help a company’s technicians better judge if they need a heavy payload manipulator or keep their current crane equipment while employing several intelligent collaborative robots to operate them. As a result, it may help to accelerate the upgrade of manufacturing sites while reducing reforming budgets.

Hybrid inverse design of photonic structures by combining optimization methods with neural networks

Over the past decades, classical optimization methods, including gradient-based topology optimization and the evolutionary algorithm, have been widely employed for the inverse design of various photonic structures and devices, while very recently neural networks have emerged as one powerful tool for the same purpose. Although these techniques have demonstrated their superiority to some extent compared to the conventional numerical simulations, each of them still has its own imitations. To fully exploit the potential of intelligent optical design, researchers have proposed to integrate optimization methods with neural networks, so that they can work coordinately to further boost the efficiency, accuracy and capability for more complicated design tasks. In this mini-review, we will highlight some representative examples of the hybrid models to show their working principles and unique proprieties.

Process parameter modeling and multi-response optimization of wire electrical discharge machining NiTi shape memory alloy

In the present work, the effects of different wire electrical discharge machining (WEDM) process parameters on nickel titanium shape memory alloy (NiTi-SMA) properties were investigated. Based on the orthogonal experimental design of the Taguchi method, the influence of five process parameters including peak current, discharge frequency, wire tension, flushing pressure, wire speed on the cutting speed (CS) and kerf width (KW) was analyzed. After 27 experimental runs, a multiple regression (MLR) model and a back-propagation neural network (BPNN) model were established to predict the CS and KW properties under different input conditions of process parameters. Utilize the programming language R for statistical testing of models and determination of important control factors. The Bat Algorithm (BA) searches for the best combination of process parameters. The experimental results and the proposed optimization method show that the prediction errors of the two combined optimization methods of MLR-BA and BPNN-BA are controlled by ± 2%. It has been proved that these two combined optimization methods are practical tools for optimizing the processing parameters of WEDM. Statistical analysis and observation results show that the peak current is the main parameter affecting the machining efficiency and surface quality of WEDM.

Energy and economic assessment of a hybrid solar/gas heating system using a combined statistical-based multi-objective optimization method

The hybrid solar/gas heating systems are considered as promising technologies to reduce energy consumption and ecological impact, for a more sustainable environment. However, the complexity related to the process of hybridization often calls for multi-objective optimization problems to deal with the constraining objectives. In this paper, a multi-objective optimization methodology combining genetic algorithm, design of experiments and dynamic simulations is proposed. The present work is carried out to maximize the primary energy saving ratio (PESR), solar fraction (SF) and to minimize the levelized cost of heat of a hybrid solar/gas heating system intended for an office building located in Algiers, Algeria. The performance analysis of three control strategy modes showed how important the control strategies can improve the SF and the PESR. The suggested control mode demonstrated a seasonal SF and PESR of 40.31% and 31.32%, respectively. The proposed multi-objective optimization approach gave a better comprehensive energy and economic performance by identifying the pareto fronts. The Linear Programming Technique for Multidimensional Analysis of Preference decision-making technique was employed to determine the best optimal solution. The optimized system exhibited SF of 72.65%, PESR of 42.07% and the Levelized Cost of Heat of 0.054 $/kWh as per the design parameters, collector area of 10 m2, tank volume of 1.7 m3 and a flow rate of 0.2 kg s−1. Overall, the results showed that the proposed methodology is time-efficient and can be applied to optimize hybrid solar/gas systems.

Chemical signatures to identify the origin of solid ashes for efficient recycling using machine learning

Solid ashes constitute the world's leading environmental problem and their efficient recycling requires specific origin information. Chemical signatures encode the physicochemical and structural characteristics may reveal their origins. In this study, we collected 310 solid ash samples from various continents, countries, and origins and combined particle swarm optimization, random forest (RF), and novel interpretation methods to build an accurate ash origin detection system. The RF model took major oxides as inputs, without further feature-engineering, and automatically classified the solid ash into four origins. Our model predicted solid ash origins with 98.5% accuracy on a training set and with 91.5% accuracy on an independent testing set, even without expert knowledge of the operating conditions. Our approach also demonstrated feature importance and interpreted the decision-making mechanisms underlying optimum RF models. These results demonstrated the feasibility of the proposed modeling framework as a blueprint for automated machine-learning origin detection of solid ashes.

Research on the Combination Optimization Method of Aircraft Climb Parameters Considering the Influence of Pollution Emissions

In order to find the optimum climb parameters for decreasing aircraft pollution emissions, we establish a calculation model of aircraft pollutant emissions to thoroughly examine the economy of aircraft operation and its impact on the environment, based on the International Civil Aviation Organization reference emission data and Boeing Method 2 which can calculate pollutant emissions in different flight phases by correcting the ICAO emission data. Firstly, we propose the concept of integrated flight cost considering the effect of emissions and establish its calculation model. Secondly, we establish the climb speed optimization models based on the traditional flight cost and integrated flight cost. Then, we analyze the effect of climb performance on the integrated flight cost. Next, we establish a combined optimization model of indicated airspeed and thrust using the genetic algorithm. The model simulation and result analysis are carried out using a wide-body aircraft. Finally, we analyze the effect of the optimization parameters and the sensitivity of the pollution index. The results show that the decrease in the flight speed and thrust effectively reduces the cost of pollutant emission during flight. The combination of (Vc, Tr) with the smallest integrated flight cost reduces the integrated flight cost by 1.28% and emission cost by 4.56%.

THE SYSTEMATIZATION OF METHODOLOGICAL TOOLS OF THE COST MANAGEMENT SYSTEM OF THE ENTERPRISE

The article presents the main components of the methodological tools, which made it possible to systematize it for effective cost management. The main purpose of the study is to improve the functioning of the cost management system of the enterprise by systematizing the tools depending on the methods of cost management.
 The research of literary sources and scientific approaches to solving the problem of determining the effective methodological tools of the cost management system of the enterprise showed that this issue remains unresolved and requires systematization of tools interacting with the methods and elements of the cost management system, which will improve its efficiency of its operation.
 The relevance of solving the scientific problem is that the optimal combination of methods and tools of cost management will increase the efficiency of the functional components of the cost management system, which affects the increasing the competitiveness of enterprise products on the basis of cost optimization.
 The most common cost management methods are listed, including ABC-method, direct-costing, standard-costing, absorption-costing, CVP-analysis, target-costing, cost-killing, LCC-analysis, benchmarking, VCC-method, kaizen-costing. The substantiation of the proposed classification of cost management tools depending on the specified methods is proved.
 In addition, it is proposed the grouping of cost management tools into general, which have a wide range of applications and specific, applied mainly in the process of cost management. Keeping such grouping, the interaction of tools and elements (functional components) of the cost management system of the enterprise is shown.
 The results of the study may be of practical importance for managers of manufacturing enterprises from the standpoint of forming a cost management system

A combined multi-pathlength and wavelength optimization method for accurate detection of platelet count

Spectrometry has progressed in the rapid detection of blood components, but due to their complexity, meeting clinical detection standards remains challenging. To improve the accuracy of spectroscopic detection of blood components, this paper collected the spectra of 390 blood samples at three positions in a cuvette, and calculated the absorption spectra of three different optical path lengths. Then, using platelet count as the target component, the wavelength was optimized by the PLS least square (PLS) method. The experimental results show that the multi-pathlength joint modeling outperformed the single-pathlength modeling, and the detection accuracy is further improved after the multi-pathlength spectrum is processed by wavelength optimization. The correlation coefficients of calibration and prediction are 0.925 and 0.901, and the root mean square errors (RMSE) are 23.43 and 25.28, respectively for the two sets. The experiment shows that the combination of multi-pathlength modeling and wavelength optimization can provide a new reference for improving the accuracy of complex liquid solution components by spectroscopy.

A multiobjective discrete combination optimization method for dynamics design of engineering structures

AbstractThis paper presents a new multiobjective discrete optimization method for the engineering design of dynamic problems. A discrete combinatorial optimization problem is solved using a particle swarm optimization algorithm coupled with a stair‐form interpolation model. To address multiobjective optimization issues, a weighted average approach is implemented to convert the multiobjective optimization problem into an equivalent single‐objective optimization problem. Design constraints are taken into consideration by using the penalty function strategy. The proposed method is first verified with a 10‐bar truss structure design problem, where the cross‐sectional area of each bar is optimized to minimize both volume and node displacement. Second, the dynamic issue for hybrid composite laminates is investigated by maximizing the fundamental frequency and minimizing the cost. The results reveal that the optimized results generated by the proposed method agree well with those from other approaches.

Structural Design and Parameter Optimization of Linear Explosive Forming Projectile

AbstractThe development of new warhead structures is an important means to enhance the destructive ability of projectiles. Compared with the traditional projectiles, the shaped charge warhead has a better destructive effect. Based on the traditional optimization method, a multi‐objective optimization method based on an approximate model is used for the structural design of linear explosive forming projectile (LEFP). In this paper, four different methods are applied to optimize the structure of LEFP. Numerical simulations of penetration into steel target are carried out for the optimization results, and the reliability of the numerical results are verified by experiments. The results indicate that: 1) the optimization method can improve the molding effect and penetration ability of LEFP reliably; 2) the combined optimization method has obvious advantages in promoting the performance of LEFP over the single one.

Empirical Low‐Frequency Earthquakes Synthesized From Tectonic Tremor Records

AbstractTectonic tremor and low‐frequency earthquakes (LFEs) are two different representations of the high‐frequency (>1 Hz) components of broadband slow earthquakes, which have been discovered in various tectonic regions. Although LFEs are considered building blocks of tremor, it is difficult to find constituent LFEs for some long‐duration tremor sequences. Here we introduce a new scheme to synthesize an impulsive response from a tremor source, or empirical LFE (eLFE), from complex tremor sequences. The eLFE is constructed by maximizing the absolute amplitude (L∞ norm) of the normalized and stacked waveforms of many tremor sequences at many stations. This problem includes a highly multimodal objective function, which is maximized via a combined optimization method that incorporates a genetic algorithm and iterative improvements. We first apply this method to several validation tests using synthetic tremor waveforms and real LFEs, and then tremor activities where few nearby LFEs have been detected. One example is the Okayama tremor, which has been known to be extraordinarily sensitive to tidal stress. The eLFE is helpful in determining the accurate hypocentral location and recovering the long‐term comprehensive tremor activity via a matched‐filter analysis. The well‐constrained depth of the Okayama tremor sources is less than 30 km, which suggests that the subducting Philippine Sea Plate is very shallow at this distant location from the trench axis. This eLFE scheme highlights the fact that tremor sequences may be composed of random fluctuations that are not necessarily impulsive and emphasizes the importance of characterizing such randomness to better understand slow earthquake behavior.

From demand forecasting to inventory ordering decisions for red blood cells through integrating machine learning, statistical modeling, and inventory optimization.

The demand and supply of blood are highly variable over time. Blood inventory management that relies heavily on experience-based decisions may not be adaptive to real demand, leading to high operational costs, wastage, and shortages. We combined statistical modeling, machine learning, and optimization methods to develop a data-driven demand forecasting and inventory management strategy for red blood cells (RBCs). We then used the strategy to inform daily blood orders. A secondary semi-weekly (twice per week) ordering strategy was developed to handle the last-mile split delivery problem for blood suppliers, characterized by multi-deliveries to the same location multiple times during a short period of time. Both strategies were evaluated using the TRUST database including all patient data across four hospitals in Hamilton, Ontario. We identified 227,944 RBC transfusions for 40,787 patients in Hamilton, Ontario from 2012 to 2018. The predicted daily demand from the hybrid demand forecasting model was not significantly different from the actual daily demand (paired t-test p-value=0.163); however, the proposed daily ordering quantity from the model was significantly lower than the actual ordering quantity (p-value <0.001). The proposed daily ordering strategy reduced inventory levels by 38.4% without risk of shortages, leading to an overall cost reduction of 43.0% (95% confidence interval [CI]: 42.3%, 43.7%) compared with the actual cost. The semi-weekly ordering strategy reduced ordering frequency by 62.6% (95% CI: 61.5%, 63.7%). The proposed data-driven ordering strategy combining demand forecasting and inventory optimization can achieve significant cost savings for healthcare systems and blood suppliers.

Evaluating environmental and economic trade-offs in cattle feed strategies using multiobjective optimization

CONTEXTReducing livestock greenhouse gas (GHG) emissions is now central to sustainable agricultural production strategies. Feedlot systems are a significant part of the production process in many countries, and associated feeding plans can influence product emission intensity significantly. Feed formulation can be used to target several objectives including animal productive performance, direct emissions from enteric fermentation and manure decomposition, and pre-farm gate emissions associated with the feed life cycles. OBJECTIVETo explore the environmental and economic trade-offs in feed formulation for beef cattle using multiobjective optimization. METHODSWe develop a multiobjective model to derive the efficient frontier between profit maximization and environmental impact minimization in diet formulation for beef cattle in a typical French feedlot system. The nonlinear profit function includes animal performance, animal selling price, and feeding costs. The environmental impact accounts for the feed ingredient life cycles (non-renewable energy consumption, phosphorus demand, soil acidification, soil eutrophication, climate change potential, and land requirement), and for methane and nitrous oxide emissions from enteric fermentation and manure decomposition. The model is solved using a combination of optimization methods and for two scenarios with different weights representing the environmental impacts: a low carbon scenario (minimizing only CO2eq emissions), and a balanced impacts scenario (minimizing the sum of impacts with an arbitrary choice of weights derived from the literature). RESULTS AND CONCLUSIONSWe show that optimal cost-effective mitigation arises from a combined strategy, concurrently: increasing animal performance by 20% and reducing daily emissions from the feed life cycle by 50% and from enteric fermentation and manure decomposition emissions by 43%. With this strategy, both scenarios present similar maximum GHG reduction in the feedlot phase – around 42% compared to the maximum-profit solution. The similar behaviour of both scenarios shows that environmental impact transference only occurs in more extreme solutions. Finally, about 50% of the total potential reduction can be achieved at a cost of 22 € / kg CO2eq / kg CWE. SIGNIFICANCEResults suggest that significant GHG emissions reduction can be obtained solely from manipulating animal diets. Achieving these reductions cost-effectively derives from a combination of well-known strategies rather than focusing on any one individually.

Estimation of Heavy Metal(Loid) Contents in Agricultural Soil of the Suzi River Basin Using Optimal Spectral Indices

For agricultural production and food safety, it is important to accurately and extensively estimate the heavy metal(loid) pollution contents in farmland soil. Remote sensing technology provides a feasible method for the rapid determination of heavy metal(loid) contents. In this study, the contents of Ni, Hg, Cr, Cu, and As in the agricultural soil of the Suzi River Basin in Liaoning Province were taken as an example. The spectral data, with Savitzky–Golay smoothing, were taken as the original spectra (OR), and the spectral transformation was achieved by continuum removal (CR), reciprocal (1/R), root means square (R), first-order differential (FDR), and second-order differential (SDR) methods. Then the spectral indices were calculated by the optimal band combination algorithm. The correlation between Ni, Hg, Cr, Cu, and As contents and spectral indices was analyzed, and the optimal spectral indices were selected. Then, multiple linear regression (MLR), partial least squares regression (PLSR), random forest regression (RFR), and adaptive neuro-fuzzy reasoning system (ANFIS) were used to establish the estimation model based on the combined optimal spectral indices method. The results show that the combined optimal spectral indices method improves the correlation between spectra and heavy metal(loid), the MLR model produces the best estimation effect for Ni and Cu (R2=0.713 and 0.855, RMSE = 5.053 and 8.113, RPD = 1.908 and 2.688, respectively), and the PLSR model produces the best effect for Hg, Cr, and As (R2= 0.653, 0.603, and 0.775, RMSE = 0.074, 23.777, and 1.923, RPD = 1.733, 1.621, and 2.154, respectively). Therefore, the combined optimal spectral indices method is feasible for heavy metal(loid) estimation in soils and could provide technical support for large-scale soil heavy metal(loid) content estimation and pollution assessment.

Research on Real-time Sensing Technology of Aerospace Interactive Behavior Based on Infrared Array Force Tactile

Aerospace robots can replace astronauts to complete dangerous work in the expanded space. How to efficiently and reliably interact with robots in complex and harsh space environment has become an urgent problem and technical challenge. Based on the infrared array force tactile technology, an infrared point force touch detection system is developed to realize the intention sensing of aerospace human-robot interaction. Based on multipoint positioning technology combined with image method and global combined optimal tracking method, the control software is designed, and the effective human-robot interaction in the process of cooperation is realized. Finally, the touch panel test effect of the system is given. This research can provide a theoretical basis for the practical application of aerospace human-robot interaction.

A Gradient-Free Topology Optimization Strategy for Continuum Structures with Design-Dependent Boundary Loads

In this paper, the topology optimization of continuum structures with design-dependent loads is studied with a gradient-free topology optimization method in combination with adaptive body-fitted finite element mesh. The material-field series-expansion (MFSE) model represents the structural topology using a bounded material field with specified spatial correlation and provides a crisp structural boundary description. This feature makes it convenient to identify the loading surface for the application of the design-dependent boundary loads and to generate a body-fitted mesh for structural analysis. Using the dimension reduction technique, the number of design variables is significantly decreased, which enables the use of an efficient Kriging-based algorithm to solve the topology optimization problem. The effectiveness of the proposed method is demonstrated using several numerical examples, among which a design problem with geometry and contact nonlinearity is included.

Modeling and Optimization of Wind Turbines in Wind Farms for Solving Multi-Objective Reactive Power Dispatch Using a New Hybrid Scheme

Reactive Power Dispatch is one of the main problems in energy systems, particularly for the power industry, and a multi-objective framework should be proposed to solve it. In this study, we present a multi-objective framework for the optimization of wind turbines in wind farms. We investigate a new combined optimization method with Chaotic Local Search, Fuzzy Interactive Honey Bee Mating Optimization, Data-Sharing technique and Modified Gray Code for discrete variables. We use the proposed model to select optimal energy system parameters. The optimization process is based on simultaneous optimization of three functions. Finally, we improve a new method based on Pareto-optimal solutions to select the best one among all candidate solutions. The presented model and methodology are validated on energy systems with wind turbines. The evaluated efficiency is compared with the real system.

Design of low-frequency broadband flextensional transducers based on combined particle swarm optimization and finite element method

For designing underwater acoustic transducers, it is usually very difficult and time-consuming to determine multiple parameters simultaneously. Therefore, a novel design method that combines the particle swarm optimization (PSO) and finite element method (FEM) is proposed for low-frequency broadband flextensional transducers (FTs). This method can optimize multiple structural dimensions simultaneously and maximize the bandwidth performance of FTs efficiently. The validity of the PSO-FEM approach was verified by the optimization design and experiments of a class IV FT. Compared with previously reported design methods of FTs, this method is more efficient and avoids tedious operations. This work also provides a powerful and handy tool for the design of other underwater acoustic transducers.