Search

Transfer learning methods exploit similarities between different datasets to improve the performance of the target task by transferring knowledge from source tasks to the target task. "What to transfer" is a main research issue in transfer learning. The existing transfer learning method generally needs to acquire the shared parameters by integrating human knowledge. However, in many real applications, an understanding of which parameters can be shared is unknown beforehand. Transfer learning model is essentially a special multi-objective optimization problem. Consequently, this paper proposes a novel auto-sharing parameter technique for transfer learning based on multi-objective optimization and solves the optimization problem by using a multi-swarm particle swarm optimizer. Each task objective is simultaneously optimized by a sub-swarm. The current best particle from the sub-swarm of the target task is used to guide the search of particles of the source tasks and vice versa. The target task and source task are jointly solved by sharing the information of the best particle, which works as an inductive bias. Experiments are carried out to evaluate the proposed algorithm on several synthetic data sets and two real-world data sets of a school data set and a landmine data set, which show that the proposed algorithm is effective. [ABSTRACT FROM AUTHOR]

Industry 4.0 leads to a strong digitalization of industrial processes, but also a significant increase in communication and cooperation between the machines that make it up. This is the case with autonomous industrial vehicles (AIVs) and other cooperative mobile robots which are multiplying in factories, often in the form of fleets of vehicles, and whose intelligence and autonomy are increasing. While the autonomy of autonomous vehicles has been well characterized in the field of road and road transport, this is not the case for the autonomous vehicles used in industry. The establishment and deployment of AIV fleets raises several challenges, all of which depend on the actual level of autonomy of the AIVs: acceptance by employees, vehicle location, traffic fluidity, collision detection, or vehicle perception of changing environments. Thus, simulation serves to account for the constraints and requirements formulated by the manufacturers and future users of AIVs. In this paper, after having proposed a broad state of the art on the problems to be solved in order to simulate AIVs before proceeding to experiments in real conditions, we present a method to estimate positions of AIVs moving in a closed industrial environment, the extension of a collision detection algorithm to deal with the obstacle avoidance issue, and the development of an agent-based simulation platform for simulating these two methods and algorithms. The resulting/final/subsequent simulation will allow us to experiment in real conditions. [ABSTRACT FROM AUTHOR]

In classification tasks, feature selection (FS) can reduce the data dimensionality and may also improve classification accuracy, both of which are commonly treated as the two objectives in FS problems. Many meta-heuristic algorithms have been applied to solve the FS problems and they perform satisfactorily when the problem is relatively simple. However, once the dimensionality of the datasets grows, their performance drops dramatically. This paper proposes a self-adaptive multi-objective genetic algorithm (SaMOGA) for FS, which is designed to maintain a high performance even when the dimensionality of the datasets grows. The main concept of SaMOGA lies in the dynamic selection of five different crossover operators in different evolution process by applying a self-adaptive mechanism. Meanwhile, a search stagnation detection mechanism is also proposed to prevent premature convergence. In the experiments, we compare SaMOGA with five multi-objective FS algorithms on sixteen datasets. According to the experimental results, SaMOGA yields a set of well converged and well distributed solutions on most data sets, indicating that SaMOGA can guarantee classification performance while removing many features, and the advantage over its counterparts is more obvious when the dimensionality of datasets grows. [ABSTRACT FROM AUTHOR]

This paper presents a novel multi-stage perception system for collision avoidance in mobile robots. In the here considered scenario, a mobile robot stands in a workspace with a set of potential targets to reach or interact with. When a human partner appears gesturing to the target, the robot must plan a collision-free trajectory to reach the goal. To solve this problem, a full-perception system composed of consecutive convolutional neural networks in parallel and processing stages is proposed for generating a collision-free trajectory according to the desired goal. This system is evaluated at each step in real environments and through several performance tests, proving to be a robust and fast system suitable for real-time applications. [ABSTRACT FROM AUTHOR]

Membrane computing models are parallel and distributed natural computing models. These models are often referred to as P systems. This paper proposes a novel multi-behaviors co-ordination controller model using enzymatic numerical P systems for autonomous mobile robots navigation in unknown environments. An environment classifier is constructed to identify different environment patterns in the maze-like environment and the multi-behavior co-ordination controller is constructed to coordinate the behaviors of the robots in different environments. Eleven sensory prototypes of local environments are presented to design the environment classifier, which needs to memorize only rough information, for solving the problems of poor obstacle clearance and sensor noise. A switching control strategy and multi-behaviors coordinator are developed without detailed environmental knowledge and heavy computation burden, for avoiding the local minimum traps or oscillation problems and adapt to the unknown environments. Also, a serial behaviors control law is constructed on the basis of Lyapunov stability theory aiming at the specialized environment, for realizing stable navigation and avoiding actuator saturation. Moreover, both environment classifier and multi-behavior coordination controller are amenable to the addition of new environment models or new behaviors due to the modularity of the hierarchical architecture of P systems. The simulation of wheeled mobile robots shows the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

A customized version of Fish School Search (FSS) algorithm and the innovative volitive operator of FSS (which is incorporated into the regular particle swarm optimization (PSO) algorithm) are applied to the finite element model (FEM) updating problem. These algorithms are tested on the updating of two real structures namely; an unsymmetrical H-shaped beam and a GARTEUR SM-AG19 structure. The results thereof are compared with results of two other metaheuristic algorithms: Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) on the same structures. The GA and PSO algorithms being the most popular metaheuristic algorithms used in the model updating area. It is observed that on average, the FSS and PSO algorithms produce more accurate results than the GA. In this paper we confirm that the FSSb (i.e. a customised version of the FSS algorithm, with minor modifications) and the hybrid algorithm - the Volitive PSO (i.e. the volitive operator of FSS into PSO) - are also more effective in this optimization task, producing superior results when updating the underlining Finite Element Model of both structures. [ABSTRACT FROM AUTHOR]

It seems clear that general adoption of electric vehicles is coming in the near future. But this adoption will bring new challenges as, for example, that of recharging the batteries of a large fleet of electric vehicles under power and other technological constraints of the charging infrastructure. Among others, these will require solving challenging scheduling problems as well. In this paper, we study one of such problems derived from a charging station designed to be installed in community parks, which consists in scheduling a set of jobs on a single machine with varying capacity over time and exhibits high computational complexity. We propose the use of meta-heuristics as a means to solving the problem efficiently. Concretely, we propose a memetic algorithm, that combines a genetic algorithm with a local search method specifically designed for the problem. The contributions are analyzed theoretically, with formal proofs of their properties, and evaluated empirically. Experimental results show that the proposed memetic algorithm is very effective at solving the problem, while keeping running times reasonably low. [ABSTRACT FROM AUTHOR]

The problem of blind sparse analysis of electrogram (EGM) signals under atrial fibrillation (AF) conditions is considered in this paper. A mathematical model for the observed signals that takes into account the multiple foci typically appearing inside the heart during AF is firstly introduced. Then, a reconstruction model based on a fixed dictionary is developed and several alternatives for choosing the dictionary are discussed. In order to obtain a sparse solution, which takes into account the biological restrictions of the problem at the same time, the paper proposes using a Least Absolute Shrinkage and Selection Operator (LASSO) regularization followed by a post-processing stage that removes low amplitude coefficients violating the refractory period characteristic of cardiac cells. Finally, spectral analysis is performed on the clean activation sequence obtained from the sparse learning stage in order to estimate the number of latent foci and their frequencies. Simulations on synthetic signals and applications on real data are provided to validate the proposed approach. [ABSTRACT FROM AUTHOR]

Scheduling problems involving physical machines and human resources are frequent in real production environments. In this paper, we tackle a problem in which a set of tasks must be performed on a set of machines under the assistance of human operators, subject to some constraints such as precedence relations on the tasks, limited capacity of machines and operators, and skills of the operators to assist the processing of tasks. We analyze the problem and propose a generic schedule builder that may be adapted to build schedules in different dominant and non-dominant search spaces. The schedule builder was exploited as a decoder in a genetic algorithm. All the proposals were evaluated on a benchmark set with instances of different characteristics. The experimental study revealed useful insights of practical interest and showed substantial improvements of the genetic algorithm over existing methods in the literature. [ABSTRACT FROM AUTHOR]

Scheduling is a frequently studied combinatorial optimisation problem that often needs to be solved under dynamic conditions and to optimise multiple criteria. The most commonly used method for solving dynamic problems are dispatching rules (DRs), simple constructive heuristics that build the schedule incrementally. Since it is difficult to design DRs manually, they are often created automatically using genetic programming. Although such rules work well, their performance is still limited and various methods, especially ensemble learning, are used to improve them. So far, ensembles have only been used in the context of single-objective scheduling problems. This study aims to investigate the possibility of constructing ensembles of DRs for solving multi-objective (MO) scheduling problems. To this end, an existing ensemble construction method called SEC is adapted by extending it with non-dominated sorting to construct Pareto fronts of ensembles for a given MO problem. In addition, the algorithms NSGA-II and NSGA-III were adapted to construct ensembles and compared with the SEC method to demonstrate their effectiveness. All methods were evaluated on four MO problems with different number of criteria to be optimised. The results show that ensembles of DRs achieve better Pareto fronts compared to individual DRs. Moreover, the results show that SEC achieves equally good or even slightly better results than NSGA-II and NSGA-III when constructing ensembles, while it is simpler and slightly less computationally expensive. This shows the potential of using ensembles to increase the performance of individual DRs for MO problems. [ABSTRACT FROM AUTHOR]

To guarantee their locomotion, biped robots need to walk stably. The latter is achieved by a high performance in joint control. This article addresses this issue by proposing a novel human-simulated fuzzy (HF) membrane control system of the joint angles. The proposed control system, human-simulated fuzzy membrane controller (HFMC), contains several key elements. The first is an HF algorithm based on human-simulated intelligent control (HSIC). This HF algorithm incorporates elements of both multi-mode proportional-derivative (PD) and fuzzy control, aiming at solving the chattering problem of multi-mode switching while improving control accuracy. The second is a membrane architecture that makes use of the natural parallelisation potential of membrane computing to improve the real-time performance of the controller. The proposed HFMC is utilised as the joint controller for a biped robot. Numerical tests in a simulation are carried out with the planar and slope walking of a five-link biped robot, and the effectiveness of the HFMC is verified by comparing and evaluating the results of the designed HFMC, HSIC and PD. Experimental results demonstrate that the proposed HFMC not only retains the advantages of traditional PD control but also improves control accuracy, real-time performance and stability. [ABSTRACT FROM AUTHOR]

This article studies a tri-objective formulation of the inventory routing problem, extending the recently studied biobjective formulation. As compared to distance cost and inventory cost, which were discussed in previous work, it also considers stockout cost as a third objective. Demand is modeled as a Poisson random variable. State-of-the-art evolutionary multi-objective optimization algorithms and a new method based on swarm intelligence are used to compute approximation of the 3-D Pareto front. A benchmark previously used in bi-objective inventory routing is extended by incorporating a stochastic demand model with an expected value that equals the average demand of the original benchmark. The results provide insights into the shape of the optimal trade-off surface. Based on this the dependences between different objectives are clarified and discussed. Moreover, the performances of the four different algorithmic methods are compared and due to the consistency in the results, it can be concluded that a near optimal approximation to the Pareto front can be found for problems of practically relevant size. [ABSTRACT FROM AUTHOR]

Several engineering optimization problems like routing, freight transportation, exploration, or layout design in their more complex and realistic versions present a series of characteristics that make them very difficult to solve. Among these we find the absence of centralized updated information about all the variables, due to the spread out nature of the problems or lack of appropriate communications, or the dynamism of real-time operation. In fact, most optimization approaches assume that the problems they address are static, meaning that there is an optimal solution that does not change in time, but this is not always the case and there are problems that require following an optimum that changes in time. Distributed population-based techniques, such as swarms, have provided promising results in this context. They obtain a solution through the concurrent behavior of several adequately constructed processing elements. However, constructing these swarms is not straightforward, and most approaches have just mimicked swarm behaviors found in nature, adapting them to particular problems. The objective of this work is to study the application of a novel evolutionary paradigm, distributed Embodied Evolution (dEE), to obtain heterogeneous swarms that solve a set of realistic problems. In particular, we address here non-separable dynamic fitness landscapes, where interdependences between individuals imply that the contribution provided by one of them to the whole depends on the behavior of the others. This study is carried out applying a canonical version of dEE, which has been developed to generalize the main features of this type of evolutionary paradigm. We analyze the canonical dEE response in a series of scenarios of increasing complexity related to two highly representative dynamic engineering problems: a Dynamic Fleet Size and Mix Vehicle Routing Problem with Time Windows (DFSMVRPTW) and a collective surveillance task with realistic location degradation. [ABSTRACT FROM AUTHOR]