Search

Background: Model based design plays a fundamental role in synthetic biology. Exploiting modularity, i.e. using biological parts and interconnecting them to build new and more complex biological circuits is one of the key issues. In this context, mathematical models have been used to generate predictions of the behavior of the designed device. Designers not only want the ability to predict the circuit behavior once all its components have been determined, but also to help on the design and selection of its biological parts, i.e. to provide guidelines for the experimental implementation. This is tantamount to obtaining proper values of the model parameters, for the circuit behavior results from the interplay between model structure and parameters tuning. However, determining crisp values for parameters of the involved parts is not a realistic approach. Uncertainty is ubiquitous to biology, and the characterization of biological parts is not exempt from it. Moreover, the desired dynamical behavior for the designed circuit usually results from a trade-off among several goals to be optimized. Results: We propose the use of a multi-objective optimization tuning framework to get a model-based set of guidelines for the selection of the kinetic parameters required to build a biological device with desired behavior. The design criteria are encoded in the formulation of the objectives and optimization problem itself. As a result, on the one hand the designer obtains qualitative regions/intervals of values of the circuit parameters giving rise to the predefined circuit behavior; on the other hand, he obtains useful information for its guidance in the implementation process. These parameters are chosen so that they can effectively be tuned at the wet-lab, i.e. they are effective biological tuning knobs. To show the proposed approach, the methodology is applied to the design of a well known biological circuit: a genetic incoherent feed-forward circuit showing adaptive behavior. Conclusion: The proposed multi-objective optimization design framework is able to provide effective guidelines to tune biological parameters so as to achieve a desired circuit behavior. Moreover, it is easy to analyze the impact of the context on the synthetic device to be designed. That is, one can analyze how the presence of a downstream load influences the performance of the designed circuit, and take it into account. [ABSTRACT FROM AUTHOR]

Soft sensors are mathematical models that estimate hard-to-measure variables given easy-to-measure ones. This field of study has given the industry a valuable tool to enable a better control of different plants and processes. With such models, quality indicators and other variables that usually demand costly or slow sensors can be predicted in real time. However, one important factor for application in industry is model interpretability. Moreover, regression models have an inherent trade-off between bias and variance, which is not considered by usual learning algorithms. Therefore, this work proposes a novel multi-objective least squares based on evolutionary feature selection and regularization, which incorporates feature selection and regularization, as well as the search for a better trade-off between bias and variance, using evolutionary multi-objective optimization algorithms. Experiments on two famous soft sensor benchmark problems, the debutanizer column and the sulfur recovery unit, indicate that the proposed algorithm can train more robust interpretable linear models than the commonly used partial least squares and least absolute shrinkage and selection operator. • Feature selection and regularization is addressed for soft sensor development. • A holistic multi-objective optimization design procedure is employed for the task. • An evolutionary multi-objective optimization algorithm builds stronger soft sensors. • The proposed method builds stronger interpretable models than other tested algorithms. • Case studies include a debutanizer column and a sulfur recovery unit. [ABSTRACT FROM AUTHOR]

Including designer preferences in every phase of the resolution of a multi-objective optimization problem is a fundamental issue to achieve a good quality in the final solution. To consider preferences, the proposal of this paper is based on the definition of what we call a preference basis that shows the preferred optimization directions in the objective space. Associated to this preference basis a new basis in the objective space—dominance basis—is computed. With this new basis the meaning of dominance is reinterpreted to include the designer's preferences. In this paper, we show the effect of changing the geometric properties of the underlying structure of the Euclidean objective space by including preferences. This way of incorporating preferences is very simple and can be used in two ways: by redefining the optimization problem and/or in the decision-making phase. The approach can be used with any multi-objective optimization algorithm. An advantage of including preferences in the optimization process is that the solutions obtained are focused on the region of interest to the designer and the number of solutions is reduced, which facilitates the interpretation and analysis of the results. The article shows an example of the use of the preference basis and its associated dominance basis in the reformulation of the optimization problem, as well as in the decision-making phase. [ABSTRACT FROM AUTHOR]

Streamflow series forecasting composes a fundamental step in planning electric energy production for hydroelectric plants. In Brazil, such plants produce almost 70% of the total energy. Therefore, it is of great importance to improve the quality of streamflow series forecasting by investigating state-of-the-art time series forecasting algorithms. To this end, this work proposes the development of ensembles of unorganized machines, namely Extreme Learning Machines (ELMs) and Echo State Networks (ESNs). Two primary contributions are proposed: (1) a new training logic for ESNs that enables the application of bootstrap aggregation (bagging); and (2) the employment of multi-objective optimization to select and adjust the weights of the ensemble's base models, taking into account the trade-off between bias and variance. Experiments are conducted on streamflow series data from five real-world Brazilian hydroelectric plants, namely those in Sobradinho , Serra da Mesa , Jiraú , Furnas and Água Vermelha. The statistical results for four different prediction horizons (1, 3, 6, and 12 months ahead) indicate that the ensembles of unorganized machines achieve better results than autoregressive (AR) models in terms of the Nash–Sutcliffe model efficiency coefficient (NSE), root mean squared error (RMSE), coefficient of determination (R 2), and RMSE-observations standard deviation ratio (RSR). In such results, the ensembles with ESNs and the multi-objective optimization design procedure achieve the best scores. • Streamflow forecasting of five hydroelectric plants is addressed. • Ensembles of Echo State Networks and Extreme Learning Machines are employed. • A new Echo State Network training logic is proposed to enable bootstrap aggregation. • Multi-objective optimization is used for selecting and weighting base models. • Results confirm the advantages of using the proposed technique. [ABSTRACT FROM AUTHOR]

• A new taxonomy for multi-objective ensemble learning is proposed. • A holistic study on multi-objective ensemble learning is performed. • A collection of imbalanced data sets is used for comparison purposes. • An imbalanced real-world drinking-water quality anomaly detection is solved. • Results indicate the success of multi-objective ensemble learning. Ensemble learning methods have already shown to be powerful techniques for creating classifiers. However, when dealing with real-world engineering problems, class imbalance is usually found. In such scenario, canonical machine learning algorithms may not present desirable solutions, and techniques for overcoming this problem must be used. In addition to using learning algorithms that alleviate the imbalance between classes, multi-objective optimization design (MOOD) approaches can be used to improve the prediction performance of ensembles of classifiers. This paper proposes a study of different MOOD approaches for ensemble learning. First, a taxonomy on multi-objective ensemble learning (MOEL) is proposed. In it, four types of existing approaches are defined: multi-objective ensemble member generation, multi-objective ensemble member selection, multi-objective ensemble member combination, and multi-objective ensemble member selection and combination. Additionally, new approaches can be derived by combining the previous ones, such as multi-objective ensemble member generation and selection, multi-objective ensemble member generation and combination and multi-objective ensemble member generation, selection and combination. With the given taxonomy, two experiments are conducted for comparing (1) the performance of the MOEL techniques for generating and aggregating base models on several imbalanced benchmark problems and (2) the performance of MOEL techniques against other machine learning techniques in a real-world imbalanced drinking-water quality anomaly detection problem. Finally, results indicate that MOOD is able to improve the predictive performance of existing ensemble learning techniques. [ABSTRACT FROM AUTHOR]

• A multi-criteria method for designing shading devices of buildings is presented. • The method is based on: search of non-dominated solutions and physical programming. • Physical programming allows finding a ranking containing the preferred solutions. • Design objectives are related to Energy Efficiency, Daylighting and Fading Protection. • A Pixel Counting based tool allows evaluating more complex shading devices. Multi-criteria design techniques applied to the analysis of shading devices of buildings have arisen as useful tools for architects. Even though several techniques have been applied to shading devices with simple geometries, they usually require numerous simulations to suitably complete the analysis, making the optimization process time-consuming. Since shading devices should prevent damage to furnishings and materials, performance indicators may not be related exclusively to thermal comfort, energy consumption and daylight performance, but also to other important criteria, such as fading protection. To overcome these limitations, this study aims to present a multi-criteria method for the design of shading devices, including fading protection as an evaluation criterion, regardless of geometry complexity. The method is applied to perforated shading devices of a room office, considering as the design objectives the energy savings, daylight availability on the work plane and solar beam incidence on interior surfaces. As a novelty, a more practical approach is proposed based on two main steps: search process, for obtaining a set of non-dominated solutions, and physical programming method, in which the solutions are ranked according to the preferences of decision makers. Besides, the solar beam incidence on interior surfaces is evaluated by using a pixel counting based method, which was emerged as a powerful algorithm due its capacity to simulate any geometry with accuracy and low computational cost. The results have shown that the proposed method is an effective process in designing of the optimal shading devices to reduce energy consumption, and improve the daylight use and the fading protection, regardless of the geometry complexity. [ABSTRACT FROM AUTHOR]

In the last few years, machine learning techniques have been successfully applied to solve engineering problems. However, owing to certain complexities found in real-world problems, such as class imbalance, classical learning algorithms may not reach a prescribed performance. There can be situations where a good result on different conflicting objectives is desirable, such as true positive and true negative ratios, or it is important to balance model's complexity and prediction score. To solve such issues, the application of multi-objective optimization design procedures can be used to analyze various trade-offs and build more robust machine learning models. Thus, the creation of ensembles of predictive models using such procedures is addressed in this work. First, a set of diverse predictive models is built by employing a multi-objective evolutionary algorithm. Next, a second multi-objective optimization step selects the previous models as ensemble members, resulting on several non-dominated solutions. A final multi-criteria decision making stage is applied to rank and visualize the resulting ensembles. To analyze the proposed methodology, two different experiments are conducted for binary classification. The first case study is a famous classification problem through which the proposed procedure is illustrated. The second one is a challenging real-world problem related to water quality monitoring, where the proposed procedure is compared to four classical ensemble learning algorithms. Results on this second experiment show that the proposed technique is able to create robust ensembles that can outperform other ensemble methods. Overall, the authors conclude that the proposed methodology for ensemble generation creates competitive models for real-world engineering problems. • A new multi-objective optimization approach for ensemble generation is proposed. • The methodology is composed of two separate multi-objective problems. • A final multi-criteria decision making step is applied to select the final ensemble. • The proposed methodology is applied on a real-world competition problem. • Results show that the proposed methodology outperforms classical ensemble methods. [ABSTRACT FROM AUTHOR]

Abstract: The multi-objective optimization strategy called physical programming (PP) provides engineers with a flexible tool to express design preferences with a ‘physical’ meaning. For each objective or specification design, preferences are established through linguistic categories to which numerical values are assigned. In PP, this mapping is made using preference functions as piecewise splines whose curvatures are calculated with an expensive and iterative algorithm. However, mapping between design parameter space and objective space may be largely non-convex and is uninfluenced by the use of gradient-based methods for solving the optimization problem. In this paper, the philosophy of the PP method has been used, but two components have been totally redesigned: a simpler algorithm is used for the construction of preference functions; and the optimizer is replaced by a genetic algorithm that avoids possible local minima problems. Three engineering applications are shown to illustrate the value of this new method. [ABSTRACT FROM AUTHOR]