查看更多>>摘要：Many brain-computer interface (BCI) studies overlook the channel optimization due to its inherent complexity. However, a careful channel selection increases the performance and users' comfort while reducing the cost of the system. Evolutionary meta-heuristics, which have demonstrated their usefulness in solving complex problems, have not been fully exploited yet in this context. The purpose of the study is two-fold: (1) to propose a novel algorithm to find an optimal channel set for each user and compare it with other existing meta-heuristics; and (2) to establish guidelines for adapting these optimization strategies to this framework. A total of 3 single-objective (GA, BDE, BPSO) and 4 multiobjective (NSGA-II, BMOPSO, SPEA2, PEAIL) existing algorithms have been adapted and tested with 3 public databases: 'BCI competition III-dataset II', 'Center Speller' and 'RSVP Speller'. Dual-Front Sorting Algorithm (DFGA), a novel multi-objective discrete method especially designed to the BCI framework, is proposed as well. Results showed that all meta-heuristics outperformed the full set and the common 8-channel set for P300-based BCIs. DFGA showed a significant improvement of accuracy of 3.9% over the latter using also 8 channels; and obtained similar accuracies using a mean of 4.66 channels. A topographic analysis also reinforced the need to customize a channel set for each user. Thus, the proposed method computes an optimal set of solutions with different number of channels, allowing the user to select the most appropriate distribution for the next BCI sessions. (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
查看更多>>摘要：Multilabel classification is a supervised learning problem in which input instances belong to multiple output labels. In this paper, we propose noniterative randomization-based neural networks for multilabel classification. These multilabel neural networks are named as Multilabel Random Vector Functional Link Network (ML-RVFL), Multilabel Kernelized Random Vector Functional Link Network (ML-KRVFL), Multilabel Broad Learning System (ML-BLS), and Multilabel Fuzzy Broad Learning System (ML-FBLS). The output weights of these neural networks are computed using pseudoinverse. At the output layer, multilabel classification is performed by using an adaptive threshold function. The computation of output weights using pseudoinverse retains the faster computation power of these algorithms compared to iterative learning algorithms. The adaptive threshold function used in the proposed approach can consider the correlation among the output labels and the whole dataset for threshold computation. Five multilabel evaluation metrics evaluate the proposed multilabel neural networks on 12 benchmark datasets of various domains such as text, image, and genomics. The MLKRVFL provides the overall best Friedman rankings on five evaluation metrics followed by ML-RVFL, ML-FBLS, and ML-BLS, respectively. Based on the experimentation results, the proposed ML-KRVFL, ML-RVFL, ML-FBLS, and ML-BLS perform better than other relevant multilabel approaches in the mentioned order.The proposed approaches are faster than other state-of-the-art iterative approaches and noniterative approaches in terms of running time. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Fashion compatibility learning is of great practical significance to satisfy the needs of consumers and promote the development of the apparel industry. As a core task of it, fashion style modeling has received extensive attention. In this work, we apply a polylingual model, the PolyLDA, to discover the fashion style. To establish visual documents for fashion images, a pre-trained convolutional neural network, ResNet-50, which is trained on ImageNet, is employed in the model. The kernels in different layer of the network can encode different level of visual attributes (such as color, texture, pattern and etc.). Specifically, we can use a visual word (e.g., red, wavy, floral design and etc.) to express a particular kernel in a given layer. Therefore, to construct the visual document for a fashion image, all the kernels are directly treated as visual words and their activation is regarded as the appearance of the corresponding visual attribute. By minimizing the variance of style distribution on the training set given by PolyLDA, we train the weights of the visual attributes of each layer, and assign them to the visual attributes of different layers, so that the model can get better modeling ability than the comparative models. Our proposed method is completely unsupervised and cost saving. The experimental results show that the model can not only produce almost the same result as manual discrimination, but also achieve high satisfaction for similar style retrieval. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：This paper considers an optimal control problem of switched dynamical systems with control input and system state constraints. Unlike in traditional switched dynamical systems, the switching times cannot be specified directly and they are governed by a state-dependent switching condition. Thus, the existing methods cannot be directly used to solve this problem. To overcome this difficulty, the switching conditions are transformed into a continuous-time inequality constraint by introducing an integer constraint. Further, the original optimal control problem is approximated by using a sequence of constrained non-convex nonlinear parameter optimization problems by using a relaxation method, a control vector parameterization technique, and a time-scaling transformation. Following that, a penalty function-based intelligent optimization algorithm is proposed for obtaining a global optimal solution based on a more effective penalty function method and a more effective intelligent optimization algorithm. The convergence results show that the proposed method is globally convergent. Numerical simulation results show that the proposed method is lower time-consuming, has faster convergence speed, can obtain a better objective function value than the existing typical algorithms, and can achieve a stable and robust performance when considering the small perturbations in constraint conditions or the small perturbations of the model parameters. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Flight test tasks arrangement is one of the most significant problems in the development of new civil aircraft. Normally, there are many factors restraining flight test tasks arrangement, including characteristics of experimental aircraft, requirements of tasks themselves, and logical relationships among them, leading to increased development period and costs. Hence, flight test tasks arrangement is generally viewed as a multi-constraint nonlinear optimization problem. To improve flight test efficiency, a multi-level optimization model of flight test tasks allocation and sequencing is introduced in this paper, where flight test period is the main optimization objective, and a penalty function evaluating tasks testing dates is the minor optimization objective. A flight test tasks sequence oriented improved genetic algorithm (FTTSOIGA) is proposed to solve the model. Firstly, a tasks allocation algorithm is designed to establish the mapping between tasks sequence and tasks arrangement result, which is independent of feasible sequence. Then, the arrangement result is optimized by optimizing the tasks sequence using the genetic algorithm. Furthermore, a tasks sequence adjustment strategy is applied to accelerate algorithm convergence. Simulation cases of 3 experimental aircraft and 80 flight test tasks demonstrate the efficiency of FTTSOIGA. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Machine learning methods are promising to predict key properties of concrete and expedite design of advanced concrete, but the existing methods have limitations in accuracy and generalization performance, because limited dataset size and anomalous data are used to train predictive models. This study presents an auto-tune learning framework for predicting compressive strength, flexural strength, workability, and porosity of ultra-high-performance concrete (UHPC). The presented framework has three features: (1) Structured and unstructured data are combined. (2) Anomalies and inappropriate variables in the dataset are identified and removed using an unsupervised anomaly detection method based on isolation forest and combined mutual information and univariate linear regression. (3) The hyperparameters of machine learning models are optimized using tree-structured Parzen estimator with k-fold cross-validation. Auto-tune predictive models are developed by integrating the presented learning framework and Light Gradient Boosting Machine (LightGBM). The results showed that the developed method achieved high prediction accuracy. The auto-tune models are used to study the effects of mixture design variables on the properties. This research will greatly promote material development by reducing experiments. (C) 2021 Elsevier B.V. All rights reserved.
Rubio-Solis, AdrianMartinez-Hernandez, UrielNava-Balanzar, LucianoGarcia-Valdovinos, Luis G....
20页
查看更多>>摘要：In marine missions that involve 3D path following tasks, the overall goal of Underwater Vehicles (UVs) is the successful completion of a path previously specified by the operator. This implies that the path must be followed by the UV as closely as possible and arrive at a location for collection by a vessel. In this paper, an Online Interval Type-2 Fuzzy Extreme Learning Machine (OIT2-FELM) is suggested to achieve a robust following behaviour along a predefined 3D path using a Remotely Operated Underwater Vehicle (ROV). The proposed machine is a fast sequential learning scheme to the training of a more generalised model of TSK Interval Type-2 Fuzzy Inference Systems (TSK IT2 FISs) equivalent to Single Layer Feedforward Neural Networks (SLFNs). Learning new input data in the OIT2-FELM can be done one-by-one or chunk-by-chunk with a fixed or varying size. The OIT2-FELM is implemented in a hierarchical navigation strategy (HNS) as the main guidance mechanism to infer local control motions and to provide the ROV with the necessary autonomy to complete a predefined 3D path. For local path-planning, the OIT2-FELM performs signal classification for obstacle avoidance and target detection based on data collected by an on-board scan sonar. To evaluate the performance of the proposed OIT2-FELM, two different experiments are suggested. First, a number of benchmark problems in the field of non-linear system identification, regression and classification problems are used. Secondly, a number of experiments to the completion of a predefined 3D path using an ROV is implemented. Compared to other fuzzy strategies, the OIT2-FELM offered two significant capabilities. On the one hand, the OIT2-FELM provides a better treatment of uncertainty and noisy signals in underwater environments while improving the ROV's performance. Secondly, online learning in OIT2-FELM allows continuous knowledge discovery from survey data to infer the surroundings of the ROV. Experiment results to the completion of 3D paths show the effectiveness of the proposed approach to handle uncertainty and produce reasonable classification predictions (similar to 90.5% accuracy in testing data). (C) 2021 Published by Elsevier B.V.
查看更多>>摘要：Covid-19 is a new infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Given the seriousness of the situation, the World Health Organization declared a global pandemic as the Covid-19 rapidly around the world. Among its applications, chest X-ray images are frequently used for an early diagnostic/screening of Covid-19 disease, given the frequent pulmonary impact in the patients, critical issue to prevent further complications caused by this highly infectious disease. In this work, we propose 4 fully automatic approaches for the classification of chest X-ray images under the analysis of 3 different categories: Covid-19, pneumonia and healthy cases. Given the similarity between the pathological impact in the lungs between Covid-19 and pneumonia, mainly during the initial stages of both lung diseases, we performed an exhaustive study of differentiation considering different pathological scenarios. To address these classification tasks, we evaluated 6 representative state-of-the-art deep network architectures on 3 different public datasets: (I) Chest X-ray dataset of the Radiological Society of North America (RSNA); (II) Covid-19 Image Data Collection; (III) SIRM dataset of the Italian Society of Medical Radiology. To validate the designed approaches, several representative experiments were performed using 6,070 chest X-ray radiographs. In general, satisfactory results were obtained from the designed approaches, reaching a global accuracy values of 0.9706 +/- 0.0044, 0.9839 +/- 0.0102, 0.9744 +/- 0.0104 and 0.9744 +/- 0.0104, respectively, thus helping the work of clinicians in the diagnosis and consequently in the early treatment of this relevant pandemic pathology. (C) 2021 The Authors. Published by Elsevier B.V.
查看更多>>摘要：This article presents Coraline, which is a new table-understanding proposal. Its novelty lies in a coral-reef optimisation algorithm that addresses the problem of feature selection in synchrony with a clustering technique and some custom heuristics that help extract information in a totally unsupervised manner. Our experimental analysis was performed on a large collection of tables with a variety of layouts, encoding problems, and formatting alternatives. Coraline could achieve an F-1 score as high as 0.90 and took 7.07 CPU seconds per table, which improves on the best supervised proposal by 6.67% regarding effectiveness and 40.54% regarding efficiency; it also improves on the best unsupervised proposal by 11.11% regarding effectiveness while it remains very competitive regarding efficiency. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Coronavirus Disease 2019 (COVID-19) had already spread worldwide, and healthcare services have become limited in many countries. Efficient screening of hospitalized individuals is vital in the struggle toward COVID-19 through chest radiography, which is one of the important assessment strategies. This allows researchers to understand medical information in terms of chest X-ray (CXR) images and evaluate relevant irregularities, which may result in a fully automated identification of the disease. Due to the rapid growth of cases every day, a relatively small number of COVID-19 testing kits are readily accessible in health care facilities. Thus it is imperative to define a fully automated detection method as an instant alternate treatment possibility to limit the occurrence of COVID-19 among individuals. In this paper, a two-step Deep learning (DL) architecture has been proposed for COVID-19 diagnosis using CXR. The proposed DL architecture consists of two stages, "feature extraction and classification". The "Multi-Objective Grasshopper Optimization Algorithm (MOGOA)" is presented to optimize the DL network layers; hence, these networks have named as "Multi-COVID-Net". This model classifies the Non-COVID-19, COVID-19, and pneumonia patient images automatically. The Multi-COVID-Net has been tested by utilizing the publicly available datasets, and this model provides the best performance results than other state-of-the-art methods. (C) 2021 Elsevier B.V. All rights reserved.
NSTL
Elsevier