Population characteristic exploitation-based multi-orientation multi-objective gene selection for microarray data classification

Gene selection is a process of selecting discriminative genes from microarray data that helps to diagnose and classify cancer samples effectively. Swarm intelligence evolution-based gene selection algorithms can never circumvent the problem that the population is prone to local optima in the process of gene selection. To tackle this challenge, previous research has focused primarily on two aspects: mitigating premature convergence to local optima and escaping from local optima. In contrast to these strategies, this paper introduces a novel perspective by adopting reverse thinking, where the issue of local optima is seen as an opportunity rather than an obstacle. Building on this foundation, we propose MOMOGS-PCE, a novel gene selection approach that effectively exploits the advantageous characteristics of populations trapped in local optima to uncover global optimal solutions. Specifically, MOMOGS-PCE employs a novel population initialization strategy, which involves the initialization of multiple populations that explore diverse orientations to foster distinct population characteristics. The subsequent step involved the utilization of an enhanced NSGA-II algorithm to amplify the advantageous characteristics exhibited by the population. Finally, a novel exchange strategy is proposed to facilitate the transfer of characteristics between populations that have reached near maturity in evolution, thereby promoting further population evolution and enhancing the search for more optimal gene subsets. The experimental results demonstrated that MOMOGS-PCE exhibited significant advantages in comprehensive indicators compared with six competitive multi-objective gene selection algorithms. It is confirmed that the "reverse-thinking" approach not only avoids local optima but also leverages it to uncover superior gene subsets for cancer diagnosis.

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design

In the prediction of protein-ligand affinity, the traditional methods require a large amount of computing resources, and have certain limitations in predicting and simulating the structural changes. Although employing data-driven approaches can yield favorable outcomes in deep learning, it entails a lack of interpretability. Some methods may require additional structural information or domain knowledge to support the interpretation, which may limit their applicability. This paper proposes an affinity variational autoencoder (AffinityVAE) using interaction feature mapping and a variational autoencoder, which consists of a multi-objective model capable of end-to-end affinity prediction and drug discovery. In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high efficiency of the proposed model. The experimental results show that AffinityVAE has very high prediction performance, and it has the potential to enhance the diversity and the amount of protein-ligand binding data, which promotes the drug development.

Green infrastructure optimization considering spatial functional zoning in urban stormwater management

Green infrastructure (GI) is used as an alternative and complement to traditional urban drainage system for mitigating urban stormwater issues mainly caused by climate change and urbanization. The combination of hydrological model and optimization algorithm can automatically find the optimal solution under multiple objectives. Given the multi-functional characteristics of GI, choosing the optimization objectives of GI are critical for multiple stakeholders. This study proposes a GI optimization method considering spatial functional zoning. Based on the basic conditions, the study area is divided into the flood risk control zone (FRCZ) and the total runoff control zone (TRCZ). The integrated model coupling hydrological model and optimization algorithm is applied to obtain the Pareto fronts and corresponding non-dominated solutions. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method is used to support the decision-making process. The optimal solution obtained for the FRCZ achieves a flood risk reduction rate of 60.49% with an average life cycle cost per year of 0.20 × 108 Chinese Yuan (CNY); The optimal solution obtained for the TRCZ achieves a total runoff reduction rate of 22.83% with an average life cycle cost per year of 0.17 × 108 CNY. This study provides a reference for stakeholders in GI planning and design.

NSICA: Multi-objective imperialist competitive algorithm for feature selection in arrhythmia diagnosis

This study proposes a multi-objective, non-dominated, imperialist competitive algorithm (NSICA) to solve optimal feature selection problems. The NSICA is a multi-objective and discrete version of the original Imperialist Competitive Algorithm (ICA) that utilizes the competition between colonies and imperialists to solve optimization problems. This study focused on solving challenges such as discretization and elitism by modifying the original operations and using a non-dominated sorting approach. The proposed algorithm is independent of the application, and with customization, it could be employed to solve any feature selection problem. We evaluated the algorithm's efficiency using it as a feature selection system for diagnosing cardiac arrhythmias. The Pareto optimal selected features from NSICA were utilized to classify arrhythmias in binary and multi-class forms based on three essential objectives: accuracy, number of features, and false negativity. We applied NSICA to an ECG-based arrhythmia classification dataset from the UCI machine learning repository. The evaluation results indicate the efficiency of the proposed algorithm compared to other state-of-the-art algorithms.

MOCOVIDOA: a novel multi-objective coronavirus disease optimization algorithm for solving multi-objective optimization problems

A novel multi-objective Coronavirus disease optimization algorithm (MOCOVIDOA) is presented to solve global optimization problems with up to three objective functions. This algorithm used an archive to store non-dominated POSs during the optimization process. Then, a roulette wheel selection mechanism selects the effective archived solutions by simulating the frameshifting technique Coronavirus particles use for replication. We evaluated the efficiency by solving twenty-seven multi-objective (21 benchmarks & 6 real-world engineering design) problems, where the results are compared against five common multi-objective metaheuristics. The comparison uses six evaluation metrics, including IGD, GD, MS, SP, HV, and delta p (Δ P ). The obtained results and the Wilcoxon rank-sum test show the superiority of this novel algorithm over the existing algorithms and reveal its applicability in solving multi-objective problems.

Multi-objective synchronous calibration and Pareto optimality of runoff and sediment parameters in an arid and semi-arid watershed

Calibration methodologies must extract as much information as possible from available data, but it is not well understood in investigating the multi-objective synchronous calibration strategy by using multiple sources of information and by exploiting the data in better ways. The non-dominated sorting genetic algorithm II (NSGA-II) is introduced to study the calibration performance of runoff and sediment parameters under nine targeted scenarios, which considers the best choice to obtain high-cost performance results for decision makers through multi-objective optimization and the calculation of Pareto-optimal front with a high precision. (i) SWAT model has good adaptability in the runoff simulation of the Yanhe River watershed. Both the calibration results of NSGA-II and sequential uncertainty fitting approach-version 2 (SUFI-2) can meet the accuracy requirements of runoff simulation. Particularly, the NSGA-II based on multiple objective functions not only has strong applicability but also can better constrain the parameter process, making the calibrated model more in line with the physical conditions of the watershed. (ii) The two-site synchronous calibration of runoff or sediment can make full use of data information of different sites, reduce the impact of spatial heterogeneity on model parameters, and improve the calibration efficiency of the model. The single-site synchronous calibration of runoff and sediment based on NSGA-II not only has high calibration efficiency but also can avoid the tedious steps of calibrating runoff and sediment separately. (iii) The two-site synchronous calibration of runoff and sediment based on NSGA-II combines the advantages of the above synchronous calibration strategies, which can get Pareto-optimal front and represent the best trade-offs among different objectives, and its applicability is stronger than the traditional single-site or single-element calibration strategy. This study provides new and competing ways to evaluate hydrological models and their performance, and the multiple criteria approach for watershed modeling is one of the focuses in future research extensions.

De novo drug design based on Stack-RNN with multi-objective reward-weighted sum and reinforcement learning

CONTEXT

In recent decades, drug development has become extremely important as different new diseases have emerged. However, drug discovery is a long and complex process with a very low success rate, and methods are needed to improve the efficiency of the process and reduce the possibility of failure. Among them, drug design from scratch has become a promising approach. Molecules are generated from scratch, reducing the reliance on trial and error and prefabricated molecular repositories, but the optimization of its molecular properties is still a challenging multi-objective optimization problem.

METHODS

In this study, two stack-augmented recurrent neural networks were used to compose a generative model for generating drug-like molecules, and then reinforcement learning was used for optimization to generate molecules with desirable properties, such as binding affinity and the logarithm of the partition coefficient between octanol and water. In addition, a memory storage network was added to increase the internal diversity of the generated molecules. For multi-objective optimization, we proposed a new approach which utilized the magnitude of different attribute reward values to assign different weights to molecular optimization. The proposed model not only solves the problem that the properties of the generated molecules are extremely biased towards a certain attribute due to the possible conflict between the attributes, but also improves various properties of the generated molecules compared with the traditional weighted sum and alternating weighted sum, among which the molecular validity reaches 97.3%, the internal diversity is 0.8613, and the desirable molecules increases from 55.9 to 92%.

Multi-user multi-objective computation offloading for medical image diagnosis

Computation offloading has effectively solved the problem of terminal devices computing resources limitation in hospitals by shifting the medical image diagnosis task to the edge servers for execution. Appropriate offloading strategies for diagnostic tasks are essential. However, the risk awareness of each user and the multiple expenses associated with processing tasks have been ignored in prior works. In this article, a multi-user multi-objective computation offloading for medical image diagnosis is proposed. First, the prospect theoretic utility function of each user is designed considering the delay, energy consumption, payment, and risk awareness. Second, the computation offloading problem including the above factors is defined as a distributed optimization problem, which with the goal of maximizing the utility of each user. The distributed optimization problem is then transformed into a non-cooperative game among the users. The exact potential game proves that the non-cooperative game has Nash equilibrium points. A low-complexity computation offloading algorithm based on best response dynamics finally is proposed. Detailed numerical experiments demonstrate the impact of different parameters and convergence in the algorithm on the utility function. The result shows that, compare with four benchmarks and four heuristic algorithms, the proposed algorithm in this article ensures a faster convergence speed and achieves only a 1.14% decrease in the utility value as the number of users increases.

Dual graph characteristics of water distribution networks-how optimal are design solutions?

Urban water infrastructures are an essential part of urban areas. For their construction and maintenance, major investments are required to ensure an efficient and reliable function. Vital parts of the urban water infrastructures are water distribution networks (WDNs), which transport water from the production (sources) to the spatially distributed consumers (sinks). To minimize the costs and at the same time maximize the resilience of such a system, multi-objective optimization procedures (e.g., meta-heuristic searches) are performed. Assessing the hydraulic behavior of WDNs in such an optimization procedure is no trivial task and is computationally demanding. Further, deciding how close to optimal design solutions the current solutions are, is difficult to assess and often results in an unnecessary extent of experiment. To tackle these challenges, an answer to the questions is sought: when is an optimization stage achieved from which no further improvements can be expected, and how can that be assessed? It was found that graph characteristics based on complex network theory (number of dual graph elements) converge towards a certain threshold with increasing number of generations. Furthermore, a novel method based on network topology and the demand distribution in WDNs, specifically based on changes in 'demand edge betweenness centrality', for identifying that threshold is developed and successfully tested. With the proposed novel approach, it is feasible, prior to the optimization, to determine characteristics that optimal design solutions should fulfill, and thereafter, test them during the optimization process. Therewith, numerous simulation runs of meta-heuristic search engines can be avoided.

Multi-objective data enhancement for deep learning-based ultrasound analysis

Recently, Deep Learning based automatic generation of treatment recommendation has been attracting much attention. However, medical datasets are usually small, which may lead to over-fitting and inferior performances of deep learning models. In this paper, we propose multi-objective data enhancement method to indirectly scale up the medical data to avoid over-fitting and generate high quantity treatment recommendations. Specifically, we define a main and several auxiliary tasks on the same dataset and train a specific model for each of these tasks to learn different aspects of knowledge in limited data scale. Meanwhile, a Soft Parameter Sharing method is exploited to share learned knowledge among models. By sharing the knowledge learned by auxiliary tasks to the main task, the proposed method can take different semantic distributions into account during the training process of the main task. We collected an ultrasound dataset of thyroid nodules that contains Findings, Impressions and Treatment Recommendations labeled by professional doctors. We conducted various experiments on the dataset to validate the proposed method and justified its better performance than existing methods.

Analyses on ICU and non-ICU capacity of government hospitals during the COVID-19 outbreak via multi-objective linear programming: An evidence from Istanbul

The current infectious disease outbreak, a novel acute respiratory syndrome [SARS]-CoV-2, is one of the greatest public health concerns that the humanity has been struggling since the end of 2019. Although, dedicating the majority of hospital-based resources is an effective method to deal with the upsurge in the number of infected individuals, its drastic impact on routine healthcare services cannot be underestimated. In this study, the proposed multi-objective, multi-period linear programming model optimizes the distribution decision of infected patients and the evacuation rate of non-infected patients simultaneously. Moreover, the presented model determines the number of new COVID-19 intensive care units, which are established by using existing hospital-based resources. Three objectives are considered: (1) minimization of total distance travelled by infected patients, (2) minimization of the maximum evacuation rate of non-infected patients and (3) minimization of the infectious risk of healthcare professionals. A case study is performed for the European side of Istanbul, Turkey. The effect of the uncertain length of the stay of infected patients is demonstrated via sensitivity analyses.

Gene selection for microarray data classification via multi-objective graph theoretic-based method

In recent decades, the improvement of computer technology has increased the growth of high-dimensional microarray data. Thus, data mining methods for DNA microarray data classification usually involve samples consisting of thousands of genes. One of the efficient strategies to solve this problem is gene selection, which improves the accuracy of microarray data classification and also decreases computational complexity. In this paper, a novel social network analysis-based gene selection approach is proposed. The proposed method has two main objectives of the relevance maximization and redundancy minimization of the selected genes. In this method, on each iteration, a maximum community is selected repetitively. Then among the existing genes in this community, the appropriate genes are selected by using the node centrality-based criterion. The reported results indicate that the developed gene selection algorithm while increasing the classification accuracy of microarray data, will also decrease the time complexity.

Lexicase Selection for Multi-Task Evolutionary Robotics

In Evolutionary Robotics, Lexicase selection has proven effective when a single task is broken down into many individual parameterizations. Evolved individuals have generalized across unique configurations of an overarching task. Here, we investigate the ability of Lexicase selection to generalize across multiple tasks, with each task again broken down into many instances. There are three objectives: to determine the feasibility of introducing additional tasks to the existing platform; to investigate any consequential effects of introducing these additional tasks during evolutionary adaptation; and to explore whether the schedule of presentation of the additional tasks over evolutionary time affects the final outcome. To address these aims we use a quadruped animat controlled by a feed-forward neural network with joint-angle, bearing-to-target, and spontaneous sinusoidal inputs. Weights in this network are trained using evolution with Lexicase-based parent selection. Simultaneous adaptation in a wall crossing task (labelled wall-cross) is explored when one of two different alternative tasks is also present: turn-and-seek or cargo-carry. Each task is parameterized into 100 distinct variants, and these variants are used as environments for evaluation and selection with Lexicase. We use performance in a single-task wall-cross environment as a baseline against which to examine the multi-task configurations. In addition, the objective sampling strategy (the manner in which tasks are presented over evolutionary time) is varied, and so data for treatments implementing uniform sampling, even sampling, or degrees of generational sampling are also presented. The Lexicase mechanism successfully integrates evolution of both turn-and-seek and cargo-carry with wall-cross, though there is a performance penalty compared to single task evolution. The size of the penalty depends on the similarity of the tasks. Complementary tasks (wallcross/turn-and-seek) show better performance than antagonistic tasks (wall-cross/cargo-carry). In complementary tasks performance is not affected by the sampling strategy. Where tasks are antagonistic, uniform and even sampling strategies yield significantly better performance than generational sampling. In all cases the generational sampling requires more evaluations and consequently more computational resources. The results indicate that Lexicase is a viable mechanism for multitask evolution of animat neurocontrollers, though the degree of interference between tasks is a key consideration. The results also support the conclusion that the naive, uniform random sampling strategy is the best choice when considering final task performance, simplicity of implementation, and computational efficiency.

CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation

The scaphoid is located in the carpals. Owing to the body structure and location of the scaphoid, scaphoid fractures are common and it is difficult to heal. Three-dimensional reconstruction of scaphoid fracture can accurately display the fracture surface and provide important support for the surgical plan involving screw placement. To achieve this goal, in this study, the cross-scale residual network (CSR-Net) is proposed for scaphoid fracture segmentation. In the CSR-Net, the features of different layers are used to achieve fusion through cross-scale residual connection, which realizes scale and channel conversions between the features of different layers. It can establish close connections between different scale features. The structures of the output layer and channel are designed to establish the CSR-Net as a multi-objective architecture, which can realize scaphoid fracture and hand bone segmentations synchronously. In this study, 65 computed tomography images of scaphoid fracture are tested. Quantitative metrics are used for assessment, and the results obtained show that the CSR-Net achieves higher performance in hand bone and scaphoid fracture segmentations. In the visually detailed display, the fracture surface is clearer and more intuitive than those obtained from other methods. Therefore, the CSR-Net can achieve accurate and rapid scaphoid fracture segmentation. Its multi-objective design provides not only an accurate digital model, but also a prerequisite for navigation in the hand bone.

Longitudinal bibliometric analysis applied to home care services

The aim of this study is to present a new methodology to explore a field of research and exercise this technique to find good mathematical models to solve the problem of territorial alignment applied to health services. For this purpose we show a methodology that combines three methods of analysis: social network analysis, longitudinal analysis, and mapping change analysis. In this paper, we applied the mapping change method, originally used in large networks, to small and medium ones, and used the Tabu search scheme instead of simulated annealing. Finally, to highlight the significant changes over time of keywords networks, an alluvial diagram is used to show the significance clusterings through the subperiods studied. The work reports on the most relevant authors on the subject and the most widely used mathematical models applied to solve the problem.

Multi-objective cutting parameter optimization model of multi-pass turning in CNC machines for sustainable manufacturing

Sustainable manufacturing has grown widely owing to recent environmental issues. This study aims to develop a multi-objective multi-pass turning optimization model to determine the optimal cutting parameters, including spindle rotation speed, feed rate, depth of cut, and number of roughing passes. The optimization model considers several criteria in the key metrics of sustainable manufacturing, i.e., energy consumption, carbon emissions, production time, and production cost. A numerical example is provided to show the application of the model, including sensitivity analysis, to study the effects of several cutting parameters on the objective functions. The model can be used by manufacturing industries to improve their manufacturing process efficiency and simultaneously produce products that support sustainable manufacturing.

Multi-objective simulated annealing for hyper-parameter optimization in convolutional neural networks

In this study, we model a CNN hyper-parameter optimization problem as a bi-criteria optimization problem, where the first objective being the classification accuracy and the second objective being the computational complexity which is measured in terms of the number of floating point operations. For this bi-criteria optimization problem, we develop a Multi-Objective Simulated Annealing (MOSA) algorithm for obtaining high-quality solutions in terms of both objectives. CIFAR-10 is selected as the benchmark dataset, and the MOSA trade-off fronts obtained for this dataset are compared to the fronts generated by a single-objective Simulated Annealing (SA) algorithm with respect to several front evaluation metrics such as generational distance, spacing and spread. The comparison results suggest that the MOSA algorithm is able to search the objective space more effectively than the SA method. For each of these methods, some front solutions are selected for longer training in order to see their actual performance on the original test set. Again, the results state that the MOSA performs better than the SA under multi-objective setting. The performance of the MOSA configurations are also compared to other search generated and human designed state-of-the-art architectures. It is shown that the network configurations generated by the MOSA are not dominated by those architectures, and the proposed method can be of great use when the computational complexity is as important as the test accuracy.

Municipal regulation of residential landscapes across US cities: Patterns and implications for landscape sustainability

Local regulations on residential landscapes (yards and gardens) can facilitate or constrain ecosystem services and disservices in cities. To our knowledge, no studies have undertaken a comprehensive look at how municipalities regulate residential landscapes to achieve particular goals and to control management practices. Across six U.S. cities, we analyzed 156 municipal ordinances to examine regional patterns in local landscape regulations and their implications for sustainability. Specifically, we conducted content analysis to capture regulations aimed at: 1) goals pertaining to conservation and environmental management, aesthetics and nuisance avoidance, and health and wellbeing, and 2) management actions including vegetation maintenance, water and waste management, food production, and chemical inputs. Our results reveal significant variation in local and regional regulations. While regulatory goals stress stormwater management and nuisance avoidance, relatively few municipalities explicitly regulate residential yards to maintain property values, mitigate heat, or avoid allergens. Meanwhile, biological conservation and water quality protection are common goals, yet regulations on yard management practices (e.g., non-native plants or chemical inputs) sometimes contradict these purposes. In addition, regulations emphasizing aesthetics and the maintenance of vegetation, mowing of grass and weeds, as well as the removal of dead wood, may inhibit wildlife-friendly yards. As a whole, landscaping ordinances largely ignore tradeoffs between interacting goals and outcomes, thereby limiting their potential to support landscape sustainability. Recommendations therefore include coordinated, multiobjective planning through partnerships among planners, developers, researchers, and non-government entities at multiple scales.

Reverse logistics network design for medical waste management in the epidemic outbreak of the novel coronavirus (COVID-19)

The recent pandemic triggered by the outbreak of the novel coronavirus boosted the demand for medical services and protective equipment, causing the generation rate of infectious medical waste (IMW) to increase rapidly. Designing an efficient and reliable IMW reverse logistics network in this situation can help to control the spread of the virus. Studies on this issue are limited, and minimization of costs and the risks associated with the operations of this network consisting of different types of medical waste generation centers (MWGC) are rarely considered. In this research, a linear programming model with three objective functions is developed to minimize the total costs, the risk associated with the transportation and treatment of IMW, and the maximum amount of uncollected waste in MWGCs. Also, multiple functions that calculate the amount of generated waste according to the parameters of the current epidemic outbreak are proposed. Revised Multi-Choice Goal Programming method is employed to solve the multi-objective model, and a real case study from Iran is examined to illustrate the validation of the proposed model. The final results show that the model can create a balance between three considered objectives by determining the flow between centers, deciding to install two new temporary treatment centers, and allowing the network to only have uncollected waste in the first two periods in some MWGCs. Also, managerial insights for health organization authorities extracted from the final results and sensitivity analyses are presented for adequately handling the IMW network.

Scenarios for handling the impact of COVID-19 based on food supply network through regional food hubs under uncertainty

This paper discusses an optimization model for handling the impact of the COVID-19 pandemic based on food supply network through regional food hubs (RFHs) under uncertainty. To this end, uncertainty is assumed in the demand and production data. During the Pandemic COVID-19 period, uncertainty has increased and the food supply chain system has changed. Thus, a new configuration of the food supply network requires analysis. In this paper, the concept of RFH is introduced to connect producers in rural areas and customers in urban areas. This paper determines the location and capacity of RFHs, the food supply network, the sum of maximum food supplies, and minimum logistics cost. This is done via a Multi-Objective Many-to-Many Location-Routing Problem model. Furthermore, since the conditions of the COVID-19 pandemic is uncertain, robust optimization is employed to handle uncertainties. During the current pandemic, red zones are defined to indicate the severity of the pandemic in a region. In this paper, the numerical experiment is considered for three scenarios: when a region is in large-scale social distancing, partial social distancing, or normal conditions. This social distancing situation is based on the defined red zones. The optimal food supply network is obtained for the three scenarios and the best scenario among the three is identified.

Calibration of a management-oriented greenhouse gas emission model for lakes and reservoirs under different distribution of environmental data

The management-oriented CICLAR lumped model for carbon dynamics and Greenhouse Gas (GHG) emission assessment, is presented. A metaheuristic calibration, through a Pareto based multi-objective particle swarm optimization (PSO), is used to automatically calibrate the model with data from the Capivari reservoir (southern Brazil). Two types of calibration are implemented: (1) with carbon dioxide (CO₂), methane (CH₄) flux, and carbon stock changes, and (2) with synthetic data based on a solution selected from (1). The calibration's performance was assessed by Nash-Sutcliffe and root means squared errors. Three synthetic scenarios are used to analyze the data distribution influence on calibration and GHG fluxes output. The results show that the spread of solutions is higher when the model is calibrated with less data (using only measured values) when compared to the ones obtained from the synthetic data series. Although there are differences between solutions calibrated with different scenarios, all of them characterized the reservoir, through the Global Warming Potential index (GWP), as a sinkhole of equivalent CO₂. Moreover, the similarity among accumulated probability distribution obtained from those different scenarios, suggest that the model can be calibrated regardless of the temporal scopes of measurements.

Integration of multi-objective PSO based feature selection and node centrality for medical datasets

In the past decades, the rapid growth of computer and database technologies has led to the rapid growth of large-scale medical datasets. On the other, medical applications with high dimensional datasets that require high speed and accuracy are rapidly increasing. One of the dimensionality reduction approaches is feature selection that can increase the accuracy of the disease diagnosis and reduce its computational complexity. In this paper, a novel PSO-based multi objective feature selection method is proposed. The proposed method consists of three main phases. In the first phase, the original features are showed as a graph representation model. In the next phase, feature centralities for all nodes in the graph are calculated, and finally, in the third phase, an improved PSO-based search process is utilized to final feature selection. The results on five medical datasets indicate that the proposed method improves previous related methods in terms of efficiency and effectiveness.

A reverse supply chain for medical waste: A case study in Babol healthcare sector

Medical waste generation is rapidly rising, which may cause a serious risk for both humans and environment if it is not properly managed. Designing an efficient and reliable medical waste reverse supply chain (MWRSC) is extremely beneficial to society. Most studies on this issue have only considered the generated waste and have not reported the uncertainty in the amount of medical waste generation and other MWRSC parameters. Sustainability criteria and environmental issues in choosing treatment technology are rarely considered as well. In this research, a linear programming model under uncertainty is developed to design an MWRSC. The proposed model is multi-item and multi-period with three objective functions. The first objective function minimizes total costs, the second objective function is relevant to the best treatment technology selection and the third objective function minimizes the total medical waste stored. A robust possibilistic programming approach is utilized to handle imprecise parameters in the model and a fuzzy goal programming method is employed to build up a multi-objective model. A real case study is conducted to illustrate the potential of the proposed model which involves different attributes and problems, such as the location and capacity of facilities, and the type of treatment technology. Furthermore, the transferring amount of medical waste among different nodes is calculated.

Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks

Early classification of 2019 novel coronavirus disease (COVID-19) is essential for disease cure and control. Compared with reverse-transcription polymerase chain reaction (RT-PCR), chest computed tomography (CT) imaging may be a significantly more trustworthy, useful, and rapid technique to classify and evaluate COVID-19, specifically in the epidemic region. Almost all hospitals have CT imaging machines; therefore, the chest CT images can be utilized for early classification of COVID-19 patients. However, the chest CT-based COVID-19 classification involves a radiology expert and considerable time, which is valuable when COVID-19 infection is growing at rapid rate. Therefore, an automated analysis of chest CT images is desirable to save the medical professionals' precious time. In this paper, a convolutional neural networks (CNN) is used to classify the COVID-19-infected patients as infected (+ve) or not (-ve). Additionally, the initial parameters of CNN are tuned using multi-objective differential evolution (MODE). Extensive experiments are performed by considering the proposed and the competitive machine learning techniques on the chest CT images. Extensive analysis shows that the proposed model can classify the chest CT images at a good accuracy rate.

Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks

Early classification of 2019 novel coronavirus disease (COVID-19) is essential for disease cure and control. Compared with reverse-transcription polymerase chain reaction (RT-PCR), chest computed tomography (CT) imaging may be a significantly more trustworthy, useful, and rapid technique to classify and evaluate COVID-19, specifically in the epidemic region. Almost all hospitals have CT imaging machines; therefore, the chest CT images can be utilized for early classification of COVID-19 patients. However, the chest CT-based COVID-19 classification involves a radiology expert and considerable time, which is valuable when COVID-19 infection is growing at rapid rate. Therefore, an automated analysis of chest CT images is desirable to save the medical professionals' precious time. In this paper, a convolutional neural networks (CNN) is used to classify the COVID-19-infected patients as infected (+ve) or not (-ve). Additionally, the initial parameters of CNN are tuned using multi-objective differential evolution (MODE). Extensive experiments are performed by considering the proposed and the competitive machine learning techniques on the chest CT images. Extensive analysis shows that the proposed model can classify the chest CT images at a good accuracy rate.

Relationship between manual air valve positioning, water quality and energy usage in activated sludge processes

Diffused aeration is the most implemented method for oxygen transfer in municipal activated sludge systems and governs the economics of the entire treatment process. Empirical observations are typically used to regulate airflow distribution through the adjustment of manual valves. However, due to the associated degrees of freedom, the identification of a combination of manual valves that optimizes all performance criteria is a complex task. For the first time a multi-criteria optimization algorithm was used to minimize effluent constituents and energy use by parametrizing manual valves positions. Data from a full-scale facility in conjunction with specific model assumptions were used to develop a base-case facility consisting of a detailed air supply model, a bio-kinetic model and a clarification model. Compared to the base-case condition, trade-offs analysis showed potential energy savings of up to 13.6% and improvement of effluent quality for NH₄⁺ (up to 68.5%) and NO_x (up to 81.6%). Based on two different tariff structures of a local power utility, maximum costs savings of 12800 USD mo^-1 to 19000 USD mo^-1 were estimated compared to baseline condition.

Comparison of two multi-objective optimization methods for composite radiation shielding materials

Combining the SCE algorithm (Shuffled Complex Evolution), MOEA/D algorithm (Multi-Objective Evolutionary Algorithm based on Decomposition), MCNP program and several prediction models, two multi-objective optimization methods (priori method and posteriori method) for radiation shielding material, which considering the shielding, mass, volume, mechanical and thermal properties are established. The material is in the form of resin matrix composite. The shielding performance of the material is simulated by MCNP program. The mechanical property and thermal property are calculated by some widely used prediction models. Several materials are optimized by the two methods respectively, and comparisons among the materials are made. The results show that, both the two methods could achieve synergistic optimization of shielding, mass, volume, mechanical properties and thermal properties of material. Differently, the priori method only obtains one solution corresponding to its weight values, while the posteriori method obtains the whole Pareto-optimal set. These two methods have their own advantages and disadvantages, which should be selected according to the actual situation.

Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks

Early classification of 2019 novel coronavirus disease (COVID-19) is essential for disease cure and control. Compared with reverse-transcription polymerase chain reaction (RT-PCR), chest computed tomography (CT) imaging may be a significantly more trustworthy, useful, and rapid technique to classify and evaluate COVID-19, specifically in the epidemic region. Almost all hospitals have CT imaging machines; therefore, the chest CT images can be utilized for early classification of COVID-19 patients. However, the chest CT-based COVID-19 classification involves a radiology expert and considerable time, which is valuable when COVID-19 infection is growing at rapid rate. Therefore, an automated analysis of chest CT images is desirable to save the medical professionals' precious time. In this paper, a convolutional neural networks (CNN) is used to classify the COVID-19-infected patients as infected (+ve) or not (-ve). Additionally, the initial parameters of CNN are tuned using multi-objective differential evolution (MODE). Extensive experiments are performed by considering the proposed and the competitive machine learning techniques on the chest CT images. Extensive analysis shows that the proposed model can classify the chest CT images at a good accuracy rate.

A multi-objective framework for multidimensional vulnerability assessment - Case of a coastal district of West Bengal, India

Vulnerability assessment for disaster studies pertaining to natural hazards has evolved as a discipline in itself. The multidimensional approach for the design of a vulnerability framework is widely accepted and used, where the prevalently used dimensions are economic, social, physical, environmental. Although the dimensions of vulnerability are distinct, these are commonly aggregated together to compute the overall vulnerability of a place (i.e. composite vulnerability). It is observed this practice leads to loss of information and averaging out of scores obtained from individual dimensions of vulnerability. This study proposes a new framework for assessing multidimensional vulnerability of a region in a multi-objective framework. Individual dimension of vulnerability is computed using a new aggregator function proposed in the study. The proposed methodology has been demonstrated using the case study of a coastal district (South 24 Parganas) in West Bengal, India. It is one of the most impoverished districts of the state and has been exposed to multiple incidences of catastrophic events like tropical cyclones, storm surges and flooding. The vulnerability indices for each dimension of vulnerability were calculated using the proposed aggregator function. Pareto optimality conditions were used to obtain a Pareto frontier from where the Blocks having highest overall vulnerability were selected. This method was repeatedly used to sort the vulnerabilities of all the constituent Blocks of the district in varying levels of vulnerabilities. It was observed that Gosaba, Patharprotima, Kultali, Canning-II, Namkhana and Sagar were the most vulnerable Blocks in the district. This methodology posits that the hierarchy-based clustering system obtained from non-weighted Pareto optimality conditions is better in terms of evaluating the vulnerability of a region. It provides a system of evaluation which is free from decision maker's prejudices and guards it against loss of information - thus eliminating two weaknesses of conventional aggregation methods. It also makes it easier to arrive at specific disaster management policies.

Hydrologic model predictability improves with spatially explicit calibration using remotely sensed evapotranspiration and biophysical parameters

A hydrologic model, calibrated using only streamflow data, can produce acceptable streamflow simulation at the watershed outlet yet unrealistic representations of water balance across the landscape. Recent studies have demonstrated the potential of multi-objective calibration using remotely sensed evapotranspiration (ET) and gaged streamflow data to spatially improve the water balance. However, methodological clarity on how to "best" integrate ET data and model parameters in multi-objective model calibration to improve simulations is lacking. To address these limitations, we assessed how a spatially explicit, distributed calibration approach that uses (1) remotely sensed ET data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and (2) frequently overlooked biophysical parameters can improve the overall predictability of two key components of the water balance: streamflow and ET at different locations throughout the watershed. We used the Soil and Water Assessment Tool (SWAT), previously modified to represent hydrologic transport and filling-spilling of landscape depressions, in a large watershed of the Prairie Pothole Region, United States. We employed a novel stepwise series of calibration experiments to isolate the effects (on streamflow and simulated ET) of integrating biophysical parameters and spatially explicit remotely sensed ET data into model calibration. Results suggest that the inclusion of biophysical parameters involving vegetation dynamics and energy utilization mechanisms tend to increase model accuracy. Furthermore, we found that using a lumped, versus a spatially explicit, approach for integrating ET into model calibration produces a sub-optimal model state with no potential improvement in model performance across large spatial scales. However, when we utilized the same MODIS ET datasets but calibrated each sub-basin in the spatially explicit approach, water yield prediction uncertainty decreased, including a distinct improvement in the temporal and spatial accuracy of simulated ET and streamflow. This further resulted in a more realistic simulation of vegetation growth when compared to MODIS Leaf-Area Index data. These findings afford critical insights into the efficient integration of remotely sensed "big data" into hydrologic modeling and associated watershed management decisions. Our approach can be generalized and potentially replicated using other hydrologic models and remotely sensed data resources - and in different geophysical settings of the globe.

A sustainable manufacturing system design: A fuzzy multi-objective optimization model

In the past decade, there has been a growing concern about the environmental protection in public society as governments almost all over the world have initiated certain rules and regulations to promote energy saving and minimize the production of carbon dioxide (CO₂) emissions in many manufacturing industries. The development of sustainable manufacturing systems is considered as one of the effective solutions to minimize the environmental impact. Lean approach is also considered as a proper method for achieving sustainability as it can reduce manufacturing wastes and increase the system efficiency and productivity. However, the lean approach does not include environmental waste of such as energy consumption and CO₂ emissions when designing a lean manufacturing system. This paper addresses these issues by evaluating a sustainable manufacturing system design considering a measurement of energy consumption and CO₂ emissions using different sources of energy (oil as direct energy source to generate thermal energy and oil or solar as indirect energy source to generate electricity). To this aim, a multi-objective mathematical model is developed incorporating the economic and ecological constraints aimed for minimization of the total cost, energy consumption, and CO₂ emissions for a manufacturing system design. For the real world scenario, the uncertainty in a number of input parameters was handled through the development of a fuzzy multi-objective model. The study also addresses decision-making in the number of machines, the number of air-conditioning units, and the number of bulbs involved in each process of a manufacturing system in conjunction with a quantity of material flow for processed products. A real case study was used for examining the validation and applicability of the developed sustainable manufacturing system model using the fuzzy multi-objective approach.

Analyzing the carbon mitigation potential of tradable green certificates based on a TGC-FFSRO model: A case study in the Beijing-Tianjin-Hebei region, China

Contradictions of increasing carbon mitigation pressure and electricity demand have been aggravated significantly. A heavy emphasis is placed on analyzing the carbon mitigation potential of electric energy systems via tradable green certificates (TGC). This study proposes a tradable green certificate (TGC)-fractional fuzzy stochastic robust optimization (FFSRO) model through integrating fuzzy possibilistic, two-stage stochastic and stochastic robust programming techniques into a linear fractional programming framework. The framework can address uncertainties expressed as stochastic and fuzzy sets, and effectively deal with issues of multi-objective tradeoffs between the economy and environment. The proposed model is applied to the major economic center of China, the Beijing-Tianjin-Hebei region. The generated results of proposed model indicate that a TGC mechanism is a cost-effective pathway to cope with carbon reduction and support the sustainable development pathway of electric energy systems. In detail, it can: (i) effectively promote renewable power development and reduce fossil fuel use; (ii) lead to higher CO₂ mitigation potential than non-TGC mechanism; and (iii) greatly alleviate financial pressure on the government to provide renewable energy subsidies. The TGC-FFSRO model can provide a scientific basis for making related management decisions of electric energy systems.

Core Hunter 3: flexible core subset selection

Background

Core collections provide genebank curators and plant breeders a way to reduce size of their collections and populations, while minimizing impact on genetic diversity and allele frequency. Many methods have been proposed to generate core collections, often using distance metrics to quantify the similarity of two accessions, based on genetic marker data or phenotypic traits. Core Hunter is a multi-purpose core subset selection tool that uses local search algorithms to generate subsets relying on one or more metrics, including several distance metrics and allelic richness.

Results

In version 3 of Core Hunter (CH3) we have incorporated two new, improved methods for summarizing distances to quantify diversity or representativeness of the core collection. A comparison of CH3 and Core Hunter 2 (CH2) showed that these new metrics can be effectively optimized with less complex algorithms, as compared to those used in CH2. CH3 is more effective at maximizing the improved diversity metric than CH2, still ensures a high average and minimum distance, and is faster for large datasets. Using CH3, a simple stochastic hill-climber is able to find highly diverse core collections, and the more advanced parallel tempering algorithm further increases the quality of the core and further reduces variability across independent samples. We also evaluate the ability of CH3 to simultaneously maximize diversity, and either representativeness or allelic richness, and compare the results with those of the GDOpt and SimEli methods. CH3 can sample equally representative cores as GDOpt, which was specifically designed for this purpose, and is able to construct cores that are simultaneously more diverse, and either are more representative or have higher allelic richness, than those obtained by SimEli.

Conclusions

In version 3, Core Hunter has been updated to include two new core subset selection metrics that construct cores for representativeness or diversity, with improved performance. It combines and outperforms the strengths of other methods, as it (simultaneously) optimizes a variety of metrics. In addition, CH3 is an improvement over CH2, with the option to use genetic marker data or phenotypic traits, or both, and improved speed. Core Hunter 3 is freely available on http://www.corehunter.org.

Optimization of storage tank locations in an urban stormwater drainage system using a two-stage approach

Storage is important for flood mitigation and non-point source pollution control. However, to seek a cost-effective design scheme for storage tanks is very complex. This paper presents a two-stage optimization framework to find an optimal scheme for storage tanks using storm water management model (SWMM). The objectives are to minimize flooding, total suspended solids (TSS) load and storage cost. The framework includes two modules: (i) the analytical module, which evaluates and ranks the flooding nodes with the analytic hierarchy process (AHP) using two indicators (flood depth and flood duration), and then obtains the preliminary scheme by calculating two efficiency indicators (flood reduction efficiency and TSS reduction efficiency); (ii) the iteration module, which obtains an optimal scheme using a generalized pattern search (GPS) method based on the preliminary scheme generated by the analytical module. The proposed approach was applied to a catchment in CZ city, China, to test its capability in choosing design alternatives. Different rainfall scenarios are considered to test its robustness. The results demonstrate that the optimal framework is feasible, and the optimization is fast based on the preliminary scheme. The optimized scheme is better than the preliminary scheme for reducing runoff and pollutant loads under a given storage cost. The multi-objective optimization framework presented in this paper may be useful in finding the best scheme of storage tanks or low impact development (LID) controls.

Preference adjustable multi-objective NMPC: An unreachable prioritized point tracking method

This paper proposes a new preference adjustable multi-objective model predictive control (PA-MOMPC) law for constrained nonlinear systems. With this control law, a reasonable prioritized optimal solution can be directly derived without constructing the Pareto front by solving a minimal optimization problem, which is a novel development of recently proposed utopia tracking approaches by additionally considering objective preferences with more flexible terminal and stability constraints. The tracking point of the proposed PA-MOMPC law is represented by a parametric vector with the parameters adjustable on the basis of objective preferences. The main result of this paper is that the solution obtained through the proposed PA-MOMPC law is demonstrated to have two important properties. One is the inherent Pareto optimality, and the other is the priority consistency between the solution and the tuning parametric vector. This combination makes the objective priorities tuning process transparent and efficient. The proposed PA-MOMPC law is supported by feasibility analyses, proof of nominal stability, and a numerical case study.

Dynamic optimization of biological networks under parametric uncertainty

BACKGROUND

Micro-organisms play an important role in various industrial sectors (including biochemical, food and pharmaceutical industries). A profound insight in the biochemical reactions inside micro-organisms enables an improved biochemical process control. Biological networks are an important tool in systems biology for incorporating microscopic level knowledge. Biochemical processes are typically dynamic and the cells have often more than one objective which are typically conflicting, e.g., minimizing the energy consumption while maximizing the production of a specific metabolite. Therefore multi-objective optimization is needed to compute trade-offs between those conflicting objectives. In model-based optimization, one of the inherent problems is the presence of uncertainty. In biological processes, this uncertainty can be present due to, e.g., inherent biological variability. Not taking this uncertainty into account, possibly leads to the violation of constraints and erroneous estimates of the actual objective function(s). To account for the variance in model predictions and compute a prediction interval, this uncertainty should be taken into account during process optimization. This leads to a challenging optimization problem under uncertainty, which requires a robustified solution.

RESULTS

Three techniques for uncertainty propagation: linearization, sigma points and polynomial chaos expansion, are compared for the dynamic optimization of biological networks under parametric uncertainty. These approaches are compared in two case studies: (i) a three-step linear pathway model in which the accumulation of intermediate metabolites has to be minimized and (ii) a glycolysis inspired network model in which a multi-objective optimization problem is considered, being the minimization of the enzymatic cost and the minimization of the end time before reaching a minimum extracellular metabolite concentration. A Monte Carlo simulation procedure has been applied for the assessment of the constraint violations. For the multi-objective case study one Pareto point has been considered for the assessment of the constraint violations. However, this analysis can be performed for any Pareto point.

CONCLUSIONS

The different uncertainty propagation strategies each offer a robustified solution under parametric uncertainty. When making the trade-off between computation time and the robustness of the obtained profiles, the sigma points and polynomial chaos expansion strategies score better in reducing the percentage of constraint violations. This has been investigated for a normal and a uniform parametric uncertainty distribution. The polynomial chaos expansion approach allows to directly take prior knowledge of the parametric uncertainty distribution into account.

Multi-objective models of waste load allocation toward a sustainable reuse of drainage water in irrigation

The present study proposes a waste load allocation (WLA) framework for a sustainable quality management of agricultural drainage water (ADW). Two multi-objective models, namely, abatement-performance and abatement-equity-performance, were developed through the integration of a water quality model (QAUL2Kw) and a genetic algorithm, by considering (1) the total waste load abatement, and (2) the inequity among waste dischargers. For successfully accomplishing modeling tasks, we developed a comprehensive overall performance measure (E wla ) reflecting possible violations of Egyptian standards for ADW reuse in irrigation. This methodology was applied to the Gharbia drain in the Nile Delta, Egypt, during both summer and winter seasons of 2012. Abatement-performance modeling results for a target of E wla = 100 % corresponded to the abatement ratio of the dischargers ranging from 20.7 to 75.6 % and 29.5 to 78.5 % in summer and in winter, respectively, alongside highly shifting inequity values. Abatement-equity-performance modeling results for a target of E wla = 90 % unraveled the necessity of increasing treatment efforts in three out of five dischargers during summer, and four out of five in winter. The trade-off curves obtained from WLA models proved their reliability in selecting appropriate WLA procedures as a function of budget constraints, principles of social equity, and desired overall performance level. Hence, the proposed framework of methodologies is of great importance to decision makers working toward a sustainable reuse of the ADW in irrigation.

Application of multi-objective controller to optimal tuning of PID gains for a hydraulic turbine regulating system using adaptive grid particle swam optimization

A hydraulic turbine regulating system (HTRS) is one of the most important components of hydropower plant, which plays a key role in maintaining safety, stability and economical operation of hydro-electrical installations. At present, the conventional PID controller is widely applied in the HTRS system for its practicability and robustness, and the primary problem with respect to this control law is how to optimally tune the parameters, i.e. the determination of PID controller gains for satisfactory performance. In this paper, a kind of multi-objective evolutionary algorithms, named adaptive grid particle swarm optimization (AGPSO) is applied to solve the PID gains tuning problem of the HTRS system. This newly AGPSO optimized method, which differs from a traditional one-single objective optimization method, is designed to take care of settling time and overshoot level simultaneously, in which a set of non-inferior alternatives solutions (i.e. Pareto solution) is generated. Furthermore, a fuzzy-based membership value assignment method is employed to choose the best compromise solution from the obtained Pareto set. An illustrative example associated with the best compromise solution for parameter tuning of the nonlinear HTRS system is introduced to verify the feasibility and the effectiveness of the proposed AGPSO-based optimization approach, as compared with two another prominent multi-objective algorithms, i.e. Non-dominated Sorting Genetic Algorithm II (NSGAII) and Strength Pareto Evolutionary Algorithm II (SPEAII), for the quality and diversity of obtained Pareto solutions set. Consequently, simulation results show that this AGPSO optimized approach outperforms than compared methods with higher efficiency and better quality no matter whether the HTRS system works under unload or load conditions.

MoDock: A multi-objective strategy improves the accuracy for molecular docking

BACKGROUND

As a main method of structure-based virtual screening, molecular docking is the most widely used in practice. However, the non-ideal efficacy of scoring functions is thought as the biggest barrier which hinders the improvement of the molecular docking method.

RESULTS

A new multi-objective strategy for molecular docking, named as MoDock, is presented to further improve the docking accuracy with available scoring functions. Instead of simple combination of multiple objectives with fixed weight factors, an aggregate function is adopted to approximate the real solution of the original multi-objective and multi-constraint problem, which will simultaneously smooth the energy surface of the combined scoring functions. Then, method of centers and genetic algorithm are used to find the optimal solution. Tests of MoDock against the GOLD test data set reveal the multi-objective strategy improves the docking accuracy over the individual scoring functions. Meanwhile, a 70% ratio of the good docking solutions with the RMSD value below 1.0 Å outperforms other 6 commonly used docking programs, even with a flexible receptor docking program included.

CONCLUSIONS

The results show MoDock is an effective strategy to overcome the deviations brought by single scoring function, and improves the prediction power of molecular docking.

Application of analytical hierarchy process for effective selection of agricultural best management practices

In this study an analytical hierarchy process (AHP) was used for ranking best management practices (BMPs) in the Saginaw River Watershed based on environmental, economic and social factors. Three spatial targeting methods were used for placement of BMPs on critical source areas (CSAs). The environment factors include sediment, total nitrogen, and total phosphorus reductions at the subbasin level and the watershed outlet. Economic factors were based on total BMP cost, including installation, maintenance, and opportunity costs. Social factors were divided into three favorability rankings (most favorable, moderately favorable, and least favorable) based on area allocated to each BMP. Equal weights (1/3) were considered for the three main factors while calculating the BMP rank by AHP. In this study three scenarios were compared. A comprehensive approach in which environmental, economic, and social aspects are simultaneously considered (Scenario 1) versus more traditional approaches in which both environmental and economic aspects were considered (Scenario 2) or only environmental aspects (sediment, TN, and TP) were considered (Scenario 3). In Scenario 1, only stripcropping (moderately favorable) was selected on all CSAs at the subbasin level, whereas stripcropping (49-69% of CSAs) and residue management (most favorable, 31-51% of CSAs) were selected by AHP based on the watershed outlet and three spatial targeting methods. In Scenario 2, native grass was eliminated by moderately preferable BMPs (stripcropping) both at the subbasin and watershed outlet levels due the lower BMP implementations cost compared to native grass. Finally, in Scenario 3, at subbasin level, the least socially preferable BMP (native grass) was selected in 100% of CSAs due to greater pollution reduction capacity compared to other BMPs. At watershed level, nearly 50% the CSAs selected stripcropping, and the remaining 50% of CSAs selected native grass and residue management equally.

Multi-objective evolutionary optimization for greywater reuse in municipal sewer systems

Sustainable design and implementation of greywater reuse (GWR) has to achieve an optimum compromise between costs and potable water demand reduction. Studies show that GWR is an efficient tool for reducing potable water demand. This study presents a multi-objective optimization model for estimating the optimal distribution of different types of GWR homes in an existing municipal sewer system. Six types of GWR homes were examined. The model constrains the momentary wastewater (WW) velocity in the sewer pipes (which is responsible for solids movement). The objective functions in the optimization model are the total WW flow at the outlet of the neighborhoods sewer system and the cost of the on-site GWR treatment system. The optimization routing was achieved by an evolutionary multi-objective optimization coupled with hydrodynamic simulations of a representative sewer system of a neighborhood located at the coast of Israel. The two non-dominated best solutions selected were the ones having either the smallest WW flow discharged at the outlet of the neighborhood sewer system or the lowest daily cost. In both solutions most of the GWR types chosen were the types resulting with the smallest water usage. This lead to only a small difference between the two best solutions, regarding the diurnal patterns of the WW flows at the outlet of the neighborhood sewer system. However, in the upstream link a substantial difference was depicted between the diurnal patterns. This difference occurred since to the upstream links only few homes, implementing the same type of GWR, discharge their WW, and in each solution a different type of GWR was implemented in these upstream homes. To the best of our knowledge this is the first multi-objective optimization model aimed at quantitatively trading off the cost of local/onsite GW spatially distributed reuse treatments, and the total amount of WW flow discharged into the municipal sewer system under unsteady flow conditions.

Development of antibiotic regimens using graph based evolutionary algorithms

This paper examines the use of evolutionary algorithms in the development of antibiotic regimens given to production animals. A model is constructed that combines the lifespan of the animal and the bacteria living in the animal's gastro-intestinal tract from the early finishing stage until the animal reaches market weight. This model is used as the fitness evaluation for a set of graph based evolutionary algorithms to assess the impact of diversity control on the evolving antibiotic regimens. The graph based evolutionary algorithms have two objectives: to find an antibiotic treatment regimen that maintains the weight gain and health benefits of antibiotic use and to reduce the risk of spreading antibiotic resistant bacteria. This study examines different regimens of tylosin phosphate use on bacteria populations divided into Gram positive and Gram negative types, with a focus on Campylobacter spp. Treatment regimens were found that provided decreased antibiotic resistance relative to conventional methods while providing nearly the same benefits as conventional antibiotic regimes. By using a graph to control the information flow in the evolutionary algorithm, a variety of solutions along the Pareto front can be found automatically for this and other multi-objective problems.