查看更多>>摘要：The coronavirus disease 2019 (COVID-19) pandemic caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has led to a sharp increase in hospitalized patients with multiorgan disease pneumonia. Early and automatic diagnosis of COVID-19 is essential to slow down the spread of this epidemic and reduce the mortality of patients infected with SARS-CoV-2. In this paper, we propose a joint multi-center sparse learning (MCSL) and decision fusion scheme exploiting chest CT images for automatic COVID-19 diagnosis. Specifically, considering the inconsistency of data in multiple centers, we first convert CT images into histogram of oriented gradient (HOG) images to reduce the structural differences between multi-center data and enhance the generalization performance. We then exploit a 3-dimensional convolutional neural network (3D-CNN) model to learn the useful information between and within 3D HOG image slices and extract multi-center features. Furthermore, we employ the proposed MCSL method that learns the intrinsic structure between multiple centers and within each center, which selects discriminative features to jointly train multi-center classifiers. Finally, we fuse these decisions made by these classifiers. Extensive experiments are performed on chest CT images from five centers to validate the effectiveness of the proposed method. The results demonstrate that the proposed method can improve COVID-19 diagnosis performance and outperform the state-of-the-art methods. (C) 2021 Published by Elsevier B.V.
查看更多>>摘要：The concept of performance-based engineering in the seismic design and performance evaluation of structures has gained a significant development over the past few decades. The sample performance levels in current building codes are categorized into two levels that represent incipient damage and incipient collapse. Therefore, the performance limits of buildings involve numerous uncertainties such as the lack of clarity in their definition and ambiguity in the individual judgments. The main objective of this paper is to properly address the uncertainties in the performance levels and loading conditions through the evaluation process. The limit state for each performance level is defined as fuzzy numbers to model the fuzziness inherent in their interpretation. Moreover, the fuzzy set theory is adopted to estimate the desired fuzzy structural responses, considering the uncertainty involved in loading conditions within the analysis process. In addition, a novel fuzzy decision-making approach, which includes a comparison of the developed fuzzy sets (i.e., fuzzy structural response and fuzzy performance levels), is proposed to ensure a comprehensive assessment of the building performance. Numerical examples are also given to establish the application of the proposed method. The results demonstrate that the new comparing approach can make a reliable judgment, particularly in questionable cases of decision-making that are in line with the embedded context. (c) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Modern elevator systems are controlled by the elevator group controllers that assign moving and stopping policies to the elevator cars. Designing an adequate elevator group control (EGC) policy is challenging for a number of reasons, one of them being conflicting optimization objectives. We address this task by formulating a corresponding constrained multiobjective optimization problem, and, in contrast to most studies in this domain, approach it using true multiobjective optimization methods capable of finding approximations for Pareto-optimal solutions. Specifically, we apply five multiobjective optimization algorithms with default constraint handling techniques and demonstrate their performance in optimizing EGC for nine elevator systems of various complexity. The experimental results confirm the scalability of the proposed methodology and suggest that NSGA-II equipped with the constrained-domination principle is the best performing algorithm on the test EGC systems. The proposed problem formulation and methodology allow for better understanding of the EGC design problem and provide insightful information to the stakeholders involved in deciding on elevator system configurations and control policies. (c) 2021 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
查看更多>>摘要：In this paper, an adaptive sliding mode control with hysteresis compensation-based neuroevolution (ACNE) is proposed for precise motion tracking of the piezoelectric actuator (PEA) in the presence of uncertainties, disturbances, and nonlinearity hysteresis characteristics. Firstly, a new memetic differential evolution (MeDE) algorithm is proposed to optimize the weights of a 3-layer neural network (called neuroevolution or NE). In MeDE, a differential evolution algorithm is used as a global search scheme and the Jaya algorithm is used as local search exploitation. Secondly, an inverse hysteresis model of PEA is identified by the neuroevolution model to provide a feed-forward NE control signal to compensate for the hysteresis behavior of PEA system. Thirdly, an adaptive neural sliding mode control plus feedforward NE (ACNE) control is designed to enhance the quality control and guarantee asymptotical stability for PEA system. Based on the Lyapunov method, the stability of the closed-loop system is analyzed and proved. Finally, the experimental Thorlabs piezoelectric actuator (PEA) is set up to verify the robustness and effectiveness of the proposed approach. Results show that the identified MeDE-Neuroevolution model has successfully applied to model the inverse hysteretic of PEA system and the performance of MeDE has better than Jaya, DE, and PSO in terms of best, worst, average, and standard deviation. Furthermore, in motion tracking control, the performance of proposed ACNE control has more accurate than a classical PID control, a feedforward control, a hybrid feedback-feedforward control, and an adaptive neural sliding mode control without a compensator. (c) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Dynamic traffic management (DTM) systems are used to reduce the negative externalities of traffic congestion, such as air pollution in urban areas. They require traffic and environmental monitoring infrastructures. In this paper we present a prototype of a low-cost Internet of Things (IoT) system for monitoring traffic flow and the Air Quality Index (AQI). The computation of the traffic flows is based on processing video in the compressed domain. Only using motion vectors as input, traffic flow is computed in real-time over an embedded architecture. An estimation of the AQI is supported by machine learning regression techniques, using different feature data obtained from the IoT device. These automatic learning techniques overcome the need for complex calibration and other limitations of embedded devices in making the needed measurements of the pollutant gases for the computation of the actual AQI. The experimentation with the data obtained from different cities representing different scenarios with a variety of climate and traffic conditions, allows validating the proposed architecture. As regressors, Linear Regression (LR), Gaussian Process Regression (GPR) and Random Forest (RF) are compared using the performance metrics R-2, MSE, MAE and MRE resulting in a relevant improvement of the AQI estimations of our proposal. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：In this paper, a new interval type-2 fuzzy neural network able to construct non-separable fuzzy rules with various shapes is introduced for function approximation problems. To reflect the uncertainty, the shape of fuzzy sets is considered to be uncertain. Therefore, a new form of shapeable interval type-2 fuzzy sets based on a general Gaussian model able to construct different shapes (including triangular, bell-shaped, trapezoidal) is proposed. To consider the interactions among input variables, input vectors are transformed to new feature spaces with uncorrelated variables proper for defining each fuzzy rule. Next, the new features are fed to a fuzzification layer using proposed interval type-2 fuzzy sets with adaptive shapes. Consequently, interval type-2 non-separable fuzzy rules with proper shapes, considering the local interactions of variables and the uncertainty are formed. For type reduction, the contribution of the upper and lower firing strengths of each fuzzy rule is adaptively selected separately. To train different parameters of the network, the Levenberg-Marquardt optimization method is utilized. The performance of the proposed method is investigated on clean and noisy datasets to show the ability to consider the uncertainty. Moreover, the proposed paradigm is successfully applied to real-world time-series predictions, regression problems, and nonlinear system identification. According to the experimental results, the performance of our proposed model outperforms other methods with a more parsimonious structure. Based on several experiments, the test RMSE of the proposed method is equal to 0.0243 for noisy McGlass time series prediction, 1.92 for Santa-Fe Laser prediction, 0.0301 for Box Jenkins system identification, 0.0569 for Poland electricity load forecasting, 4.22 for Google stock price tracking, and 13.22 for Sydney stock price tracking. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：This paper considers a task planning problem, which dispatches multiple unmanned surface vehicles (USVs) to visit a set of targets located in ocean environments. The problem is modeled as a bi-level optimization to reduce the total and the individual navigation costs simultaneously. The upper-level allocates targets and schedules target visitation sequences, while the lower-level plans safe and economical paths between two targets under the current influence. Subsequently, a novel nested strategy is proposed to solve the bi-level problem, which modifies each level initialization process and can adaptively give the lower-level function evaluation number according to the problem complexity. Besides, the proposed strategy can adopt general metaheuristics as optimizers. Thus, two upperlevel and five lower-level algorithms are employed in combination, which covers most kinds of metaheuristics. Finally, the ten combinations of algorithms are tested on three large-scale and complex cases, and the results verify the effectiveness of the proposed model and strategy. (c) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Semantics has become a key topic of research in Genetic Programming (GP). Semantics refers to the outputs (behaviour) of a GP individual when this is run on a dataset. The majority of works that focus on semantic diversity in single-objective GP indicates that it is highly beneficial in evolutionary search. Surprisingly, there is minuscule research conducted in semantics in Multi-objective GP (MOGP). In this work we make a leap beyond our understanding of semantics in MOGP and propose SDO: Semantic-based Distance as an additional criteriOn. This naturally encourages semantic diversity in MOGP. To do so, we find a pivot in the less dense region of the first Pareto front (most promising front). This is then used to compute a distance between the pivot and every individual in the population. The resulting distance is then used as an additional criterion to be optimised to favour semantic diversity. We also use two other semantic-based methods as baselines, called Semantic Similarity-based Crossover and Semantic-based Crowding Distance. Furthermore, we also use the Non-dominated Sorting Genetic Algorithm II and the Strength Pareto Evolutionary Algorithm 2 for comparison too. We use highly unbalanced binary classification problems and consistently show how our proposed SDO approach produces more non-dominated solutions and better diversity, leading to better statistically significant results, using the hypervolume results as evaluation measure, compared to the rest of the other four methods. (C) 2021 Elsevier B.V. All rights reserved.
查看更多>>摘要：Sparse filtering (SF), as a recently emerging unsupervised feature learning method, has drawn much attention in intelligent fault diagnosis of rotating machinery. Generally, SF implements feature extraction by the trained basis vectors. However, similar features may be extracted by SF due to the lack of effective restrictions on the basis vectors during training, which leads to an adverse effect on the diagnostic performance. To address this drawback, reconstruction sparse filtering (RSF) is proposed based on SF, which explicitly constrains the basis vectors via a soft-reconstruction penalty (SRP). In particular, SRP enables RSF to learn a group of independent basis vectors so as to extract dissimilar and diverse features. These features contain comprehensive and rich fault information that can precisely describe the rotating machinery health conditions, so RSF can perform significantly better. Based on RSF, an intelligent diagnosis method is developed, and it is evaluated through experiments on a gear and two bearing datasets. The results testify that RSF is able to extract dissimilar features from the vibration signals, and it has better feature learning ability than SF and nine other popular unsupervised feature learning methods. Moreover, the superiority of the developed diagnosis method is verified by comparing with several state-of-the-art intelligent diagnosis methods on two famous bearing datasets. (C) 2021 Published by Elsevier B.V.
查看更多>>摘要：Over the last years, pervasive wearable technology has spread to people's daily lives, unobtrusively acquiring large amounts of data. Such devices contain biomedical sensors, prone to contribute for the improvement of the user's quality of life through artificial intelligence algorithms (e.g. health monitoring and emotion recognition). Physiological signals are the basis of such applications, and critical problems are data (un)labeling and incorrect metadata about the source. We propose a framework for the automatic identification of the type of physiological data source, namely Respiration, Electrocardiography, Electrodermal Activity, and Blood Volume Pulse data through the application of Supervised Learning on different representation spaces (feature-based and dissimilarity-based), in both an Online and Offline setting. We build our model through a comprehensive study of (1) Supervised Learning classifiers; (2) Similarity metrics; (3) Data representation; and lastly, (4) Sample aggregation techniques for the creation of the prototypes that will translate the data into the dissimilarity-based space. We explore the aforementioned techniques on two unexplored databases. The experimental results led to accuracies superior to 92% for the online setting, and 96% for the offline setting, attaining competitive results with the current state of the art. Our work paves the way to the development of systems capable of automatically identifying sensor types and subsequently applying the most appropriate data processing, analysis and classification workflows. (c) 2021 Elsevier B.V. All rights reserved.
NSTL
Elsevier