Correction: Advantages of Task-Specific Multi-Objective Optimisation in Evolutionary Robotics.
Ontology highlight
ABSTRACT:
SUBMITTER: Trianni V
PROVIDER: S-EPMC4591986 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The application of multi-objective optimisation to evolutionary robotics is receiving increasing attention. A survey of the literature reveals the different possibilities it offers to improve the automatic design of efficient and adaptive robotic systems, and points to the successful demonstrations available for both task-specific and task-agnostic approaches (i.e., with or without reference to the specific design problem to be tackled). However, the advantages of multi-objective approaches over single-objective ones have not been clearly spelled out and experimentally demonstrated. This paper fills this gap for task-specific approaches: starting from well-known results in multi-objective optimisation, we discuss how to tackle commonly recognised problems in evolutionary robotics. In particular, we show that multi-objective optimisation (i) allows evolving a more varied set of behaviours by exploring multiple trade-offs of the objectives to optimise, (ii) supports the evolution of the desired behaviour through the introduction of objectives as proxies, (iii) avoids the premature convergence to local optima possibly introduced by multi-component fitness functions, and (iv) solves the bootstrap problem exploiting ancillary objectives to guide evolution in the early phases. We present an experimental demonstration of these benefits in three different case studies: maze navigation in a single robot domain, flocking in a swarm robotics context, and a strictly collaborative task in collective robotics.
| S-EPMC4546428 | biostudies-literature
Project description:An unsettled question in the use of robotics for post-stroke gait rehabilitation is whether task-specific locomotor training is more effective than targeting individual joint impairments to improve walking function. The paretic ankle is implicated in gait instability and fall risk, but is difficult to therapeutically isolate and refractory to recovery. We hypothesize that in chronic stroke, treadmill-integrated ankle robotics training is more effective to improve gait function than robotics focused on paretic ankle impairments.Participants with chronic hemiparetic gait were randomized to either six weeks of treadmill-integrated ankle robotics (n?=?14) or dose-matched seated ankle robotics (n?=?12) videogame training. Selected gait measures were collected at baseline, post-training, and six-week retention. Friedman, and Wilcoxon Sign Rank and Fisher's exact tests evaluated within and between group differences across time, respectively. Six weeks post-training, treadmill robotics proved more effective than seated robotics to increase walking velocity, paretic single support, paretic push-off impulse, and active dorsiflexion range of motion. Treadmill robotics durably improved gait dorsiflexion swing angle leading 6/7 initially requiring ankle braces to self-discarded them, while their unassisted paretic heel-first contacts increased from 44 % to 99.6 %, versus no change in assistive device usage (0/9) following seated robotics.Treadmill-integrated, but not seated ankle robotics training, durably improves gait biomechanics, reversing foot drop, restoring walking propulsion, and establishing safer foot landing in chronic stroke that may reduce reliance on assistive devices. These findings support a task-specific approach integrating adaptive ankle robotics with locomotor training to optimize mobility recovery.NCT01337960. https://clinicaltrials.gov/ct2/show/NCT01337960?term=NCT01337960&rank=1.
| S-EPMC4890526 | biostudies-literature
Project description:ObjectiveTo support school foods programmes by evaluating the relationship between nutritional quality, cost, student consumption and the environmental impacts of menus.DesignUsing linear programming and data from previously served menu items, the relationships between the nutritional quality, cost, student consumption and the environmental impacts of lunch menus were investigated. Optimised lunch menus with the maximum potential student consumption and nutritional quality and lowest costs and environmental impacts were developed and compared with previously served menus (baseline).SettingBoston Public Schools (BPS), Boston Massachusetts, USA.ParticipantsMenu items served on the 2018-2019 BPS lunch menu (n 142).ResultsUsing single-objective models, trade-offs were observed between most interests, but the use of multi-objective models minimised these trade-offs. Compared with the current weekly menus offered, multi-objective models increased potential caloric intake by up to 27 % and Healthy Eating Index scores by up to 19 % and reduced costs and environmental impacts by up to 13 % and 71 %, respectively. Improvements were made by reducing the frequency of beef and cheese entrées and increasing the frequency of fish and legume entrées on weekly menus.ConclusionsThis work can be extrapolated to monthly menus to provide further direction for school districts, and the methods can be employed with different recipes and constraints. Future research should test the implementation of optimised menus in schools and consider the broader implications of implementation.
| S-EPMC10410403 | biostudies-literature
Project description:Data classification is a fundamental task in data mining. Within this field, the classification of multi-labeled data has been seriously considered in recent years. In such problems, each data entity can simultaneously belong to several categories. Multi-label classification is important because of many recent real-world applications in which each entity has more than one label. To improve the performance of multi-label classification, feature selection plays an important role. It involves identifying and removing irrelevant and redundant features that unnecessarily increase the dimensions of the search space for the classification problems. However, classification may fail with an extreme decrease in the number of relevant features. Thus, minimizing the number of features and maximizing the classification accuracy are two desirable but conflicting objectives in multi-label feature selection. In this article, we introduce a multi-objective optimization algorithm customized for selecting the features of multi-label data. The proposed algorithm is an enhanced variant of a decomposition-based multi-objective optimization approach, in which the multi-label feature selection problem is divided into single-objective subproblems that can be simultaneously solved using an evolutionary algorithm. This approach leads to accelerating the optimization process and finding more diverse feature subsets. The proposed method benefits from a local search operator to find better solutions for each subproblem. We also define a pool of genetic operators to generate new feature subsets based on old generation. To evaluate the performance of the proposed algorithm, we compare it with two other multi-objective feature selection approaches on eight real-world benchmark datasets that are commonly used for multi-label classification. The reported results of multi-objective method evaluation measures, such as hypervolume indicator and set coverage, illustrate an improvement in the results obtained by the proposed method. Moreover, the proposed method achieved better results in terms of classification accuracy with fewer features compared with state-of-the-art methods.
| S-EPMC7924502 | biostudies-literature
Project description:As one of the essential topological structures in complex networks, community structure has significant theoretical and application value and has attracted the attention of researchers in many fields. In a social network, individuals may belong to different communities simultaneously, such as a workgroup and a hobby group. Therefore, overlapping community discovery can help us understand and model the network structure of these multiple relationships more accurately. This article proposes a two-stage multi-objective evolutionary algorithm for overlapping community discovery problem. First, using the initialization method to divide the central node based on node degree, combined with the cross-mutation evolution strategy of the genome matrix, the first stage of non-overlapping community division is completed on the decomposition-based multi-objective optimization framework. Then, based on the result set of the first stage, appropriate nodes are selected from each individual's community as the central node of the initial population in the second stage, and the fuzzy threshold is optimized through the fuzzy clustering method based on evolutionary calculation and the feedback model, to find reasonable overlapping nodes. Finally, tests are conducted on synthetic datasets and real datasets. The statistical results demonstrate that compared with other representative algorithms, this algorithm performs optimally on test instances and has better results.
| S-EPMC11323150 | biostudies-literature
Project description:The design and construction of network structures oriented towards different applications has attracted much attention recently. The existing studies indicated that structural heterogeneity plays different roles in promoting cooperation and robustness. Compared with rewiring a predefined network, it is more flexible and practical to construct new networks that satisfy the desired properties. Therefore, in this paper, we study a method for constructing robust cooperative networks where the only constraint is that the number of nodes and links is predefined. We model this network construction problem as a multi-objective optimization problem and propose a multi-objective evolutionary algorithm, named MOEA-Netrc, to generate the desired networks from arbitrary initializations. The performance of MOEA-Netrc is validated on several synthetic and real-world networks. The results show that MOEA-Netrc can construct balanced candidates and is insensitive to the initializations. MOEA-Netrc can find the Pareto fronts for networks with different levels of cooperation and robustness. In addition, further investigation of the robustness of the constructed networks revealed the impact on other aspects of robustness during the construction process.
| S-EPMC5278550 | biostudies-literature
Project description:In the compressed processing of hyperspectral images, orthogonal matching pursuit algorithm (OMP) can be used to obtain sparse decomposition results. Aimed at the time-complex and difficulty in applying real-time processing, an evolutionary multi-objective optimization sparse decomposition algorithm for hyperspectral images is proposed. Instead of using OMP for the matching process to search optimal atoms, the proposed algorithm explores the idea of reference point non-dominated sorting genetic algorithm (NSGA) to optimize the matching process of OMP. Take two objective function to establish the multi-objective sparse decomposition optimization model, including the largest inner product of matching atoms and image residuals, and the smallest correlation between atoms. Utilize NSGA-III with advantage of high accuracy to solve the optimization model, and the implementation process of NSGA-III-OMP is presented. The experimental results and analysis carried on four hyperspectral datasets demonstrate that, compared with the state-of-the-art algorithms, the proposed NSGA-III-OMP algorithm has effectively improved the sparse decomposition performance and efficiency, and can effectively solve the sparse decomposition optimization problem of hyperspectral images.
| S-EPMC9053777 | biostudies-literature
Project description:Single-nucleotide polymorphisms (SNPs), as disease-related biogenetic markers, are crucial in elucidating complex disease susceptibility and pathogenesis. Due to computational inefficiency, it is difficult to identify high-dimensional SNP interactions efficiently using combinatorial search methods, so the spherical evolutionary multi-objective (SEMO) algorithm for detecting multi-locus SNP interactions was proposed. The algorithm uses a spherical search factor and a feedback mechanism of excellent individual history memory to enhance the balance between search and acquisition. Moreover, a multi-objective fitness function based on the decomposition idea was used to evaluate the associations by combining two functions, K2-Score and LR-Score, as an objective function for the algorithm's evolutionary iterations. The performance evaluation of SEMO was compared with six state-of-the-art algorithms on a simulated dataset. The results showed that SEMO outperforms the comparative methods by detecting SNP interactions quickly and accurately with a shorter average run time. The SEMO algorithm was applied to the Wellcome Trust Case Control Consortium (WTCCC) breast cancer dataset and detected two- and three-point SNP interactions that were significantly associated with breast cancer, confirming the effectiveness of the algorithm. New combinations of SNPs associated with breast cancer were also identified, which will provide a new way to detect SNP interactions quickly and accurately.
| S-EPMC10815643 | biostudies-literature
Project description:The protein structure prediction (PSP) problem is concerned with the prediction of the folded, native, tertiary structure of a protein given its sequence of amino acids. It is a challenging and computationally open problem, as proven by the numerous methodological attempts and the research effort applied to it in the last few years. The potential energy functions used in the literature to evaluate the conformation of a protein are based on the calculations of two different interaction energies: local (bond atoms) and non-local (non-bond atoms). In this paper, we show experimentally that those types of interactions are in conflict, and do so by using the potential energy function Chemistry at HARvard Macromolecular Mechanics. A multi-objective formulation of the PSP problem is introduced and its applicability studied. We use a multi-objective evolutionary algorithm as a search procedure for exploring the conformational space of the PSP problem.
| S-EPMC1629082 | biostudies-literature
Project description:Developing liquid chromatography tandem mass spectrometry (LC-MS/MS) analyses of (bio)chemicals is both time consuming and challenging, largely because of the large number of LC and MS instrument parameters that need to be optimized. This bottleneck significantly impedes our ability to establish new (bio)analytical methods in fields such as pharmacology, metabolomics and pesticide research. We report the development of a multi-platform, user-friendly software tool MUSCLE (multi-platform unbiased optimization of spectrometry via closed-loop experimentation) for the robust and fully automated multi-objective optimization of targeted LC-MS/MS analysis. MUSCLE shortened the analysis times and increased the analytical sensitivities of targeted metabolite analysis, which was demonstrated on two different manufacturer's LC-MS/MS instruments.
| S-EPMC4380028 | biostudies-literature