Search

Cracks are the most common damage type on the pavement surface. Usually, pavement cracks, especially small cracks, are difficult to be accurately identified due to background interference. Accurate and fast automatic road crack detection play a vital role in assessing pavement conditions. Thus, this paper proposes an efficient lightweight encoder–decoder network for automatically detecting pavement cracks at the pixel level. Taking advantage of a novel encoder–decoder architecture integrating a new type of hybrid attention blocks and residual blocks (RBs), the proposed network can achieve an extremely lightweight model with more accurate detection of pavement crack pixels. An image dataset consisting of 789 images of pavement cracks acquired by a self‐designed mobile robot is built and utilized to train and evaluate the proposed network. Comprehensive experiments demonstrate that the proposed network performs better than the state‐of‐the‐art methods on the self‐built dataset as well as three other public datasets (CamCrack789, Crack500, CFD, and DeepCrack237), achieving F1 scores of 94.94%, 82.95%, 95.74%, and 92.51%, respectively. Additionally, ablation studies validate the effectiveness of integrating the RBs and the proposed hybrid attention mechanisms. By introducing depth‐wise separable convolutions, an even more lightweight version of the proposed network is created, which has a comparable performance and achieves the fastest inference speed with a model parameter size of only 0.57 M. The developed mobile robot system can effectively detect pavement cracks in real scenarios at a speed of 25 frames per second. [ABSTRACT FROM AUTHOR]

Multiobjective evolutionary algorithms (MOEAs) have progressed significantly in recent decades, but most of them are designed to solve unconstrained multiobjective optimization problems. In fact, many real-world multiobjective problems contain a number of constraints. To promote research on constrained multiobjective optimization, we first propose a problem classification scheme with three primary types of difficulty, which reflect various types of challenges presented by real-world optimization problems, in order to characterize the constraint functions in constrained multiobjective optimization problems (CMOPs). These are feasibility-hardness, convergence-hardness, and diversity-hardness. We then develop a general toolkit to construct difficulty adjustable and scalable CMOPs (DAS-CMOPs, or DAS-CMaOPs when the number of objectives is greater than three) with three types of parameterized constraint functions developed to capture the three proposed types of difficulty. In fact, the combination of the three primary constraint functions with different parameters allows the construction of a large variety of CMOPs, with difficulty that can be defined by a triplet, with each of its parameters specifying the level of one of the types of primary difficulty. Furthermore, the number of objectives in this toolkit can be scaled beyond three. Based on this toolkit, we suggest nine difficulty adjustable and scalable CMOPs and nine CMaOPs, to be called DAS-CMOP1-9 and DAS-CMaOP1-9, respectively. To evaluate the proposed test problems, two popular CMOEAs—MOEA/D-CDP (MOEA/D with constraint dominance principle) and NSGA-II-CDP (NSGA-II with constraint dominance principle) and two popular constrained many-objective evolutionary algorithms (CMaOEAs)—C-MOEA/DD and C-NSGA-III—are used to compare performance on DAS-CMOP1-9 and DAS-CMaOP1-9 with a variety of difficulty triplets, respectively. The experimental results reveal that mechanisms in MOEA/D-CDP may be more effective in solving convergence-hard DAS-CMOPs, while mechanisms of NSGA-II-CDP may be more effective in solving DAS-CMOPs with simultaneous diversity-, feasibility-, and convergence-hardness. Mechanisms in C-NSGA-III may be more effective in solving feasibility-hard CMaOPs, while mechanisms of C-MOEA/DD may be more effective in solving CMaOPs with convergence-hardness. In addition, none of them can solve these problems efficiently, which stimulates us to continue to develop new CMOEAs and CMaOEAs to solve the suggested DAS-CMOPs and DAS-CMaOPs. [ABSTRACT FROM AUTHOR]

This article considers the problem of velocity-free fixed-time attitude tracking control for rigid spacecraft. With the help of the homogeneity theorem, a semiglobal observer is introduced to estimate the unmeasured angular velocities within fixed time. Then, a velocity-free attitude tracking controller is designed to make the spacecraft attitude track a time-varying reference signal in finite time, which can be up bounded by a fixed number regardless of the initial conditions. Finally, numerical examples are provided to illustrate the efficiency of the present control scheme. [ABSTRACT FROM AUTHOR]

Summary: In this paper, the fixed‐time attitude coordination control for multiple rigid spacecraft under an undirected communication graph is investigated. By using the backstepping technique, the distributed fixed‐time observer, and the method of "adding a power integrator," a distributed fixed‐time attitude coordination control law is designed for a group of spacecraft. The proposed control scheme is nonsingular and can guarantee a group of rigid spacecraft simultaneously tracking a common desired attitude within fixed time even when the time‐varying reference attitude is available only to a subset of the group members. Rigorous analysis is provided to show that the attitude consensus tracking errors can converge to the origin in finite time which is bounded by a fixed constant independent of initial conditions. Numerical simulations are carried out to demonstrate the effectiveness of the proposed control law. [ABSTRACT FROM AUTHOR]

This paper proposes an improved epsilon constraint-handling mechanism and combines it with a decomposition-based multi-objective evolutionary algorithm (MOEA/D) to solve constrained multi-objective optimization problems (CMOPs). The proposed constrained multi-objective evolutionary algorithm (CMOEA) is named MOEA/D-IEpsilon. It adjusts the epsilon level dynamically according to the ratio of feasible to total solutions in the current population. In order to evaluate the performance of MOEA/D-IEpsilon, a new set of CMOPs with two and three objectives is designed, having large infeasible regions (relative to the feasible regions), and they are called LIR-CMOPs. Then, the 14 benchmarks, including LIR-CMOP1-14, are used to test MOEA/D-IEpsilon and four other decomposition-based CMOEAs, including MOEA/D-Epsilon, MOEA/D-SR, MOEA/D-CDP and CMOEA/D. The experimental results indicate that MOEA/D-IEpsilon is significantly better than the other four CMOEAs on all of the test instances, which shows that MOEA/D-IEpsilon is more suitable for solving CMOPs with large infeasible regions. Furthermore, a real-world problem, namely the robot gripper optimization problem, is used to test the five CMOEAs. The experimental results demonstrate that MOEA/D-IEpsilon also outperforms the other four CMOEAs on this problem. [ABSTRACT FROM AUTHOR]

Abstract A novel cyber-physical-social system (CPSS) with parallel learning is presented for distributed energy management (DEM) of a microgrid. CPSS is developed by extending the conventional cyber-physical system to the social space with human participation and interaction. Each energy supplier or each energy demander is regarded as a human in the social space, who is able to learn the knowledge, co-operate with others, and make a decision with various preference behaviors. The correlated equilibrium (CE) based general-sum game is employed for realizing the human interaction on the complex optimization subtask, while the novel adaptive consensus algorithm is used for achieving that on the simple optimization subtask with multi-energy balance constraints. A real-world system and multiple virtual artificial systems are introduced for parallel and interactive execution based on the small world network, thus a higher quality optimum of DEM can be rapidly emerged with a high probability. Case studies of a microgrid with 11 energy suppliers and 7 energy demanders demonstrate that the proposed technique can effectively achieve the human-computer collaboration and rapidly obtain a higher quality optimum of DEM compared with other centralized heuristic algorithms. Highlights • A cyber-physical-social system is constructed for distributed energy management. • A game theory with various decision behaviors is proposed for human interaction. • Energy suppliers or demanders can reach a consensus on the incremental cost. • The parallel interactive systems can lead to a lower total operating cost. • The proposed method outperforms other centralized heuristic algorithms for DEM. [ABSTRACT FROM AUTHOR]

A novel series of ZnAl 2 O 4 :Eu3+ aerogels (ZAE) and mullite ceramic phase reinforced ZnAl 2 O 4 :Eu3+ aerogels (MZAE) with high fluorescence thermal stability have been firstly synthesized for the encapsulation of high-power optical devices. However, due to the intrinsic structural brittleness of the aerogel, the structure of ZAE tends to collapse during the heat treatment and the fluorescence performance falls short of expectations. To this end, we propose a simple and effective strategy to enhance the structural rigidity of fluorescent aerogels by introducing the mullite ceramic phase into the network structure of ZAE. This can effectively suppress the agglomeration of Eu3+ caused by the collapse of the structure during the heat treatment, thus enhancing the optical properties of the aerogel. Compared with ZAE, MZAE has higher fluorescence thermal stability. The fluorescence intensity of MZAE at 498 K is still 75 % of that at 298 K, and the chromaticity shift is only 22 × 10−3. [ABSTRACT FROM AUTHOR]

The increase in global wind power installations has also increased the wind turbine density in wind farms. This has made the wake interactions between neighbouring turbines more significant and difficult to describe. Understanding wakes is important to predict the energy production and assess their environmental impacts. Although existing wake description methods can predict the average wind turbine wake under a high wind turbine density, they are unable to identify the wake boundary with an acceptable accuracy and computational cost. Consequently, the role of wake boundaries in modern wind farms has become unclear. To deal with this problem, this paper presents a comprehensive discussion on wind turbine wakes, especially the role of boundary identification in the wind farm planning stage. After a review of existing methods, an approach based on a newly derived mathematical formulation of the velocity field is proposed. Lidar-based field measurements and large-eddy simulations along with actuator line model-based numerical simulations were used to compare different wake boundary identification methods. The results show that the new approach is computationally cost-effective with a 5% increase in accuracy. The new approach also offers significant advantages as wake boundaries become increasingly complex. • The importance of wind turbine wake boundary identification is discussed. • Various wake boundary identification methods are compared for different purposes. • A cost-effective method is presented and demonstrated for its advantages. • The more complicated the wakes, the easier the new method's advantage is shown. [ABSTRACT FROM AUTHOR]

Assembly flow shop scheduling problem (AFSP) in a single factory has attracted widespread attention over the past decades; however, the distributed AFSP with DPm → 1 layout considering uncertainty is seldom investigated. In this study, a distributed assembly flow shop scheduling problem with fuzzy makespan minimization (FDAFSP) is considered, and an efficient artificial bee colony algorithm (EABC) is proposed. In EABC, an adaptive population division method based on evolutionary quality of subpopulation is presented; a competitive employed bee phase and a novel onlooker bee phase are constructed, in which diversified combinations of global search and multiple neighborhood search are executed; the historical optimization data set and a new scout bee phase are adopted. The proposed EABC is verified on 50 instances from the literature and compared with some state-of-the-art algorithms. Computational results demonstrate that EABC performs better than the comparative algorithms on over 74% instances. [ABSTRACT FROM AUTHOR]

Detecting the shape of the non-rigid molten metal during welding, so-called weld pool visual sensing, is one of the central tasks for automating arc welding processes. It is challenging due to the strong interference of the high-intensity arc light and spatters as well as the lack of robust approaches to detect and represent the shape of the nonrigid weld pool. We propose a solution using active contours including an prior for the weld pool boundary composition. Also, we apply Adaboost to select a small set of features that captures the relevant information. The proposed method is applied to weld pool tracking and the presented results verified its feasibility. [ABSTRACT FROM AUTHOR]

At present there is a wide range of evolutionary algorithms available to researchers and practitioners. Despite the great diversity of these algorithms, virtually all of the algorithms share one feature: they have been manually designed. A fundamental question is “are there any algorithms that can design evolutionary algorithms automatically?” A more complete definition of the question is “can computer construct an algorithm which will generate algorithms according to the requirement of a problem?” In this paper, a novel evolutionary algorithm based on automatic designing of genetic operators is presented to address these questions. The resulting algorithm not only explores solutions in the problem space like most traditional evolutionary algorithms do, but also automatically generates genetic operators in the operator space. In order to verify the performance of the proposed algorithm, comprehensive experiments on 23 well-known benchmark optimization problems are conducted. The results show that the proposed algorithm can outperform standard differential evolution algorithm in terms of convergence speed and solution accuracy which shows that the algorithm designed automatically by computers can compete with the algorithms designed by human beings. [ABSTRACT FROM AUTHOR]

This paper investigates the issue of evolutionary design of controllers for hybrid mechatronic systems. Finite State Automaton (FSA) is selected as the representation for a discrete controller due to its interpretability, fast execution speed and natural extension to a statechart, which is very popular in industrial applications. A case study of a two-tank system is used to demonstrate that the proposed evolutionary approach can lead to a successful design of an FSA controller for the hybrid mechatronic system, represented by a hybrid bond graph. Generalisation of the evolved FSA controller to unknown control targets is also tested. Further, a comparison with another type of controller, a lookahead controller, is conducted, with advantages and disadvantages of each discussed. The comparison sheds light on which type of controller representation is a better choice to use in various stages of the evolutionary design of controllers for hybrid mechatronic systems. Finally, some important future research directions are pointed out, leading to the major work of the succeeding part of the research. [ABSTRACT FROM PUBLISHER]

Considering green scheduling and sustainable manufacturing, the energy-efficient hybrid flow shop scheduling problem (EHFSP) with a variable speed constraint is investigated, and a novel multi-population artificial bee colony algorithm (MPABC) is developed to minimize makespan, total tardiness and total energy consumption (TEC), simultaneously. It is necessary for manufacturers to fully understand the notion of symmetry in balancing economic and environmental indicators. To improve the search efficiency, the population was randomly categorized into a number of subpopulations, then several groups were constructed based on the quality of subpopulations. A different search strategy was executed in each group to maintain the population diversity. The historical optimization data were also used to enhance the quality of solutions. Finally, extensive experiments were conducted. The results demonstrate that MPABC can achieve an outstanding performance on three metrics D I R , c and n d for the considered EHFSP. [ABSTRACT FROM AUTHOR]

This paper suggests a unified and automated design methodology for synthesizing designs for multi-domain systems, such as mechatronic systems. A multi-domain dynamic system includes a mixture of electrical, mechanical, hydraulic, pneumatic, and/or thermal components, making it difficult use a single design tool to design a system to meet specified performance goals. The multi-domain design approach is not only efficient for mixed-domain problems, but is also useful for addressing separate single-domain design problems with a single tool. Bond graphs (BGs) are domain independent, allow free composition, and are efficient for classification and analysis of models, allowing rapid determination of various types of acceptability or feasibility of candidate designs. This can sharply reduce the time needed for analysis of designs that are infeasible or otherwise unattractive. Genetic programming is well recognized as a powerful tool for open-ended search. The combination of these two powerful methods is therefore an appropriate target for a better system for synthesis of complex multi-domain systems. The approach described here will evolve new designs (represented as BGs) with ever-improving performance, in an iterative loop of synthesis, analysis, and feedback to the synthesis process. The suggested design methodology has been applied here to three design examples. The first is a domain-independent eigenvalue placement design problem that is tested for some sample target sets of eigenvalues. The second is in the electrical domain––design of analog filters to achieve specified performance over a given frequency range. The third is in the electromechanical domain––redesign of a printer drive system to obtain desirable steady-state position of a rotational load. [Copyright &y& Elsevier]

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. The codes of this work are available at https://github.com/96jhwei/Genetic-U-Net. [ABSTRACT FROM AUTHOR]

Automatic crack detection from images is an important task that is adopted to ensure road safety and durability for Portland cement concrete (PCC) and asphalt concrete (AC) pavement. Pavement failure depends on a number of causes including water intrusion, stress from heavy loads, and all the climate effects. Generally, cracks are the first distress that arises on road surfaces and proper monitoring and maintenance to prevent cracks from spreading or forming is important. Conventional algorithms to identify cracks on road pavements are extremely time-consuming and high cost. Many cracks show complicated topological structures, oil stains, poor continuity, and low contrast, which are difficult for defining crack features. Therefore, the automated crack detection algorithm is a key tool to improve the results. Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. Crack characteristics with multiple context information are automatically able to learn and perform end-to-end crack detection. Then, a multi-dilation module embedded in an encoder-decoder architecture is proposed. The crack features of multiple context sizes can be integrated into the multi-dilation module by dilation convolution with different dilatation rates, which can obtain much more cracks information. Finally, the hierarchical feature learning module is designed to obtain a multi-scale features from the high to low- level convolutional layers, which are integrated to predict pixel-wise crack detection. Some experiments on public crack databases using 118 images were performed and the results were compared with those obtained with other methods on the same images. The results show that the proposed U-HDN method achieves high performance because it can extract and fuse different context sizes and different levels of feature maps than other algorithms. [ABSTRACT FROM AUTHOR]

6D object pose estimation is an important application of computer vision and a basic module in robotic manipulation, but dealing with occlusion in a cluttered environment, handling symmetries, and textureless surfaces, are real issues. Other issues with such systems are accuracy and efficiency. The recent two-stage methods perform well in terms of accuracy; however, a linear increase in their runtimes occurs due to the increase in the number of objects in a scene. This paper proposes a fully convolutional and parallel architecture that obtains the 3D translation and orientation for object poses from the same pixel-wise dense estimation. It exploits the same voting block for inliers for multiple instances, final 3D translation estimation, and quaternions aggregation. Only the center point estimation of the objects decreases the model’s running time, while still useful for occlusions and texturelessness. Symmetries and varieties are handled with a loss function based on shape matching and the pose of the object. Our proposed approach has fewer parameters and takes less time to train and evaluate, achieving great accuracy. Experiments on LINEMOD and occlusion LINEMOD datasets using ADD (-S) and 2D projection evaluation metrics show that the proposed method outperforms state-of-the-art approaches for 6D pose estimation. [ABSTRACT FROM AUTHOR]

Quadrotor unmanned aerial vehicles (UAVs) often encounter intricate environmental and dynamic limitations in real-world applications, underscoring the significance of proficient trajectory planning for ensuring both safety and efficiency during flights. To tackle this challenge, we introduce an innovative approach that harmonizes sophisticated environmental insights with the dynamic state of a UAV within a potential field framework. Our proposition entails a quadrotor trajectory planner grounded in a kinodynamic gene regulation network potential field. The pivotal contribution of this study lies in the amalgamation of environmental perceptions and kinodynamic constraints within a newly devised gene regulation network (GRN) potential field. By enhancing the gene regulation network model, the potential field becomes adaptable to the UAV's dynamic conditions and its surroundings, thereby extending the GRN into a kinodynamic GRN (K-GRN). The trajectory planner excels at charting courses that guide the quadrotor UAV through intricate environments while taking dynamic constraints into account. The amalgamation of environmental insights and kinodynamic constraints within the potential field framework bolsters the adaptability and stability of the generated trajectories. Empirical results substantiate the efficacy of our proposed methodology. [ABSTRACT FROM AUTHOR]

As an important part of the internet of things (IoTs) and cyber-physical systems (CPS), Micro-Electro-Mechanical-Systems (MEMS) is playing more and more irreplaceable role in current industrial community and the forthcoming era of the Industry 4.0. The limitations of some frequently used design methods for MEMS design optimization are analyzed in this review. In order to overcome these difficulties, a recent trend in design optimization of MEMS is inspired by the natural evolution mechanism. Many powerful techniques, especially the evolutionary computation (EC), have been used for the design optimization of MEMS. This paper presents a review of the achievements in this promising research area which utilizes EC methods for the design optimization of MEMS and also proposes three open issues that it is facing. [ABSTRACT FROM AUTHOR]

Automated and accurate segmentation of retinal vessels in fundus images is an important step for screening and diagnosing various ophthalmologic diseases. However, many factors, including the variations of vessels in color, shape and size, make this task become an intricate challenge. One kind of the most popular methods for vessel segmentation is U-Net based methods. However, in the U-Net based methods, the size of the convolution kernels is generally fixed. As a result, the receptive field for an individual convolution operation is single, which is not conducive to the segmentation of retinal vessels with various thicknesses. To overcome this problem, in this paper, we employed self-calibrated convolutions to replace the traditional convolutions for the U-Net, which can make the U-Net learn discriminative representations from different receptive fields. Besides, we proposed an improved spatial attention module, instead of using traditional convolutions, to connect the encoding part and decoding part of the U-Net, which can improve the ability of the U-Net to detect thin vessels. The proposed method has been tested on Digital Retinal Images for Vessel Extraction (DRIVE) database and Child Heart and Health Study in England Database (CHASE DB1). The metrics used to evaluate the performance of the proposed method are accuracy (ACC), sensitivity (SE), specificity (SP), F1-score (F1) and the area under the receiver operating characteristic curve (AUC). The ACC, SE, SP, F1 and AUC obtained by the proposed method are 0.9680, 0.8036, 0.9840, 0.8138 and 0.9840 respectively on DRIVE database, and 0.9756, 0.8118, 0.9867, 0.8068 and 0.9888 respectively on CHASE DB1, which are better than those obtained by the traditional U-Net (the ACC, SE, SP, F1 and AUC obtained by U-Net are 0.9646, 0.7895, 0.9814, 0.7963 and 0.9791 respectively on DRIVE database, and 0.9733, 0.7817, 0.9862, 0.7870 and 0.9810 respectively on CHASE DB1). The experimental results indicate that the proposed modifications in the U-Net are effective for vessel segmentation. [ABSTRACT FROM AUTHOR]

Evolutionary programming has been widely implemented as a continuous optimization algorithm. Prior studies have come to a bottleneck because most of the evolutionary programming algorithms are unable to robustly solve different types of optimization problems. We argue that such a bottleneck results from the existing mutation strategies' making little use of the population information. Inspired by a psychological model which describes how a person optimizes his/her social activities by conformity behavior, this study proposes a variation vector of the mutation to simulate the conformity behavior with behavior-reference, majority-impact, and distinctive-impact factors. These factors, respectively, correspond with three types of population information for each mutated individual: heuristic information, optimal gradient, and population diversity. We use the proposed vector to design an improved evolutionary programming with a simulated-conformist mutation strategy. The results show that the population information produced by the three factors enhance the robustness of the performance of evolutionary programming in solving both uni- and multimodal functions. The finding is verified by empirical analyses of two sets of benchmark functions proposed in 1998 and 2013. The numerical results indicate that the proposed algorithm performs significantly better on average than the existing EPs and some other algorithms with similar strategies. [ABSTRACT FROM AUTHOR]

In this paper, we propose two multi-objective memetic algorithms (MOMAs) using two different adaptive mechanisms to address combinatorial optimization problems (COPs). One mechanism adaptively selects solutions for local search based on the solutions' convergence toward the Pareto front. The second adaptive mechanism uses the convergence and diversity information of an external set (dominance archive), to guide the selection of promising solutions for local search. In addition, simulated annealing is integrated in this framework as the local refinement process. The multi-objective memetic algorithms with the two adaptive schemes (called uMOMA-SA and aMOMA-SA) are tested on two COPs and compared with some well-known multi-objective evolutionary algorithms. Experimental results suggest that uMOMA-SA and aMOMA-SA outperform the other algorithms with which they are compared. The effects of the two adaptive mechanisms are also investigated in the paper. In addition, uMOMA-SA and aMOMA-SA are compared with three single-objective and three multi-objective optimization approaches on software next release problems using real instances mined from bug repositories (Xuan et al. IEEE Trans Softw Eng 38(5):1195-1212, 2012). The results show that these multi-objective optimization approaches perform better than these single-objective ones, in general, and that aMOMA-SA has the best performance among all the approaches compared. [ABSTRACT FROM AUTHOR]

Evolutionary search has been widely implemented for the adjustment of controllers’ parameters. Nevertheless, the structure of controllers, which has a more important role in control systems, has been seldom studied. To this end, an evolutionary design method of controllers is proposed to optimize both structures and parameters simultaneously in this article. A controller is made up of a combination of some basic controller components and relevant parameters. The design of controllers can be transformed into an optimization problem involving the structure (represented by discrete vectors) and parameters (represented by real numbers). A generalized structure encoding/decoding scheme is developed. Guided by the performance indicators, intelligent algorithms for both combinatorial and numerical optimization are employed to iteratively and cooperatively evolve the controller structure and parameters, respectively. In order to effectively reduce some redundant or infeasible solutions, a set of generation rules for the controller structure are put forward, which also ensures the feasibility of the structure. Furthermore, this method is applied to a magnetic levitation ball system with nonlinear dynamics and external disturbance. Both simulation and experiment results demonstrate the effectiveness and practicability of the proposed method. [ABSTRACT FROM AUTHOR]

Optimization modeling of real-world application problems usually involves noise from various sources. Noisy optimization imposes challenges to optimization methods since the objective values can be different for multiple evaluations. In this article, we propose a novel online population size learning (OPL) technique of evolution strategies for handling noisy optimization problems. By re-evaluating a fraction of the candidates, we measure the strength of noise level of the re-evaluated candidate solutions and adapt the population size according to the noise level. The proposed OPL combines the advantages of both explicit averaging by re-evaluations and the implicit averaging by large population size and overcomes their limitations. We incorporate it with the covariance matrix adaptation evolution strategy (CMA-ES) and obtain OPL-CMA-ES. Compared with the existing noise handling technique, the proposed OPL is much simpler in both concepts and computation. We conduct comprehensive experiments to evaluate the algorithm’s performance on standard problems with Gaussian noise. We further evaluate the performance of OPL-CMA-ES on the black-box optimization benchmarks (BBOBs) noisy testbed, which is a standard platform for comparing black-box optimization algorithms, compared with the state-of-the-art noise-handling algorithms. The experimental results show that OPL-CMA-ES achieves remarkable performance and outperforms the compared variants. [ABSTRACT FROM AUTHOR]

Automatic and accurate estimation of choroidal thickness plays a very important role in a computer-aided system for eye diseases. One of the most common methods for automatic estimation of choroidal thickness is segmentation-based methods, in which the boundaries of the choroid are first detected from optical coherence tomography (OCT) images. The choroidal thickness is then computed based on the detected boundaries. A shortcoming in the segmentation-based methods is that the estimating precision greatly depends on the segmentation results. To avoid the dependence on the segmentation step, in this paper, we propose a direct method based on convolutional neural networks (CNNs) for estimating choroidal thickness without segmentation. Concretely, a B-scan image is first cropped into several patches. A trained CNN model is then used to estimate the choroidal thickness for each patch. The mean thickness of the choroid in the B-scan is obtained by taking the average of the choroidal thickness on each patch. Then, 150 OCT volumes are collected to evaluate the proposed method. The experiments show that the results obtained by the proposed method are very competitive with those obtained by segmentation-based methods, which indicates that direct estimation of choroidal thickness is very promising. [ABSTRACT FROM AUTHOR]

This paper proposes an improved memetic algorithm relying on ring neighborhood topology for constrained optimization problems based on our previous work in Cai et al. (Soft Comput (in press), ). The main motivation of using ring neighborhood topology is to provide a good balance between effective exploration and efficient exploitation, which is a very important design issue for memetic algorithms. More specifically, a novel variant of invasive weed optimization (IWO) as the local refinement procedure is proposed in this paper. The proposed IWO variant adopts a neighborhood-based dispersal operator to achieve more fine-grained local search through the estimation of neighborhood fitness information relying on the ring neighborhood topology. Furthermore, a modified version of differential evolution (DE), known as 'DE/current-to-best/1', is integrated into the improved memetic algorithm with the aim of providing a more effective exploration. Performance of the improved memetic algorithm has been comprehensively tested on 13 well-known benchmark test functions and four engineering constrained optimization problems. The experimental results show that the improved memetic algorithm obtains greater competitiveness when compared with the original memetic approach Cai et al. in (Soft Comput (in press), ) and other state-of-the-art algorithms. The effectiveness of the modification of each component in the proposed approach is also discussed in the paper. [ABSTRACT FROM AUTHOR]

This paper presents a novel memetic algorithm, named as IWO_DE, to tackle constrained numerical and engineering optimization problems. In the proposed method, invasive weed optimization (IWO), which possesses the characteristics of adaptation required in memetic algorithm, is firstly considered as a local refinement procedure to adaptively exploit local regions around solutions with high fitness. On the other hand, differential evolution (DE) is introduced as the global search model to explore more promising global area. To accommodate the hybrid method with the task of constrained optimization, an adaptive weighted sum fitness assignment and polynomial distribution are adopted for the reproduction and the local dispersal process of IWO, respectively. The efficiency and effectiveness of the proposed approach are tested on 13 well-known benchmark test functions. Besides, our proposed IWO_DE is applied to four well-known engineering optimization problems. Experimental results suggest that IWO_DE can successfully achieve optimal results and is very competitive compared with other state-of-art algorithms. [ABSTRACT FROM AUTHOR]

This article is concerned with the stabilization problem for a class of networked systems subject to successive packet losses. Different from the input delay approach used in some existing literature, the continuous‐time system under consideration is first converted into a discrete‐time stochastic system with system matrices subject to stochastic characteristic. In order to deal with the difficulties in the calculations of mathematical expectations of both matrix exponential and integral of matrix exponential function, the upper bound of successive packet losses and packet drop rate are assumed to be known and then the probabilities of the number of successive packet losses taking each value in a bounded set are calculated. Based on this, stability criteria are derived by recurring to the law of total expectation, which guarantee the exponential mean‐square stability of resulting closed‐loop discrete‐time stochastic system with a prescribed H∞ performance. Moreover, a controller design procedure is then proposed. Finally, to verify the analysis results and testify the effectiveness and applicability of the designed algorithm, a numerical simulation example is given. [ABSTRACT FROM AUTHOR]

Aiming at the shortcomings of the existing control law based on the global information, this article studies the coverage problem of a given region in the plane using a team of USVs. The coverage goal, which is to cover a given search domain using multiple mobile sensors so that each point is surveyed until a certain preset level is achieved, is formulated in a mathematically precise problem statement. The adaptive control law is presented which enables multi-USV to navigate in a complex environment in the presence of unknown obstacles and guarantees that a fully connected multi-USV system attains the coverage goal. In particular, the dangerous area was divided into two different parts in order to enhance the searching efficiency. Finally, simulation results are presented to validate the feasibility and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Tidal current is a promising renewable energy source. Previous studies have investigated the influence of surface waves on tidal turbines in many aspects. However, the turbine wake development in a surface wave environment, which is crucial for power extraction in a turbine array, remains elusive. In this study, we focus on the wake evolution behind a single turbine and its interaction with surface waves. A numerical solver is developed to study the effects of surface waves on an industrial-size turbine. A case without surface wave and two cases with waves and different rotor depths are investigated. We obtain three-dimensional flow field descriptions near the free surface, around the rotor, and in the near- and far-wake. In a comparative analysis, the time-averaged and instantaneous flow fields are examined for various flow characteristics, including momentum restoration, power output, free surface elevation and vorticity dynamics. A model reduction technique is employed to identify the coherent flow structures and investigate the spatial and temporal characteristics of the wave–wake interactions. The results indicate the effect of surface waves in augmenting wake restoration and reveal the interactions between the surface waves and the wake structure, through a series of dynamic processes and the Kelvin–Helmholtz instability. [ABSTRACT FROM AUTHOR]

Image dehazing can improve image clarity and visual effect, which plays a pivotal role in many computer vision tasks. Existing dehazing methods are mostly based on a single feature stream and tend to ignore the low-frequency characteristics of haze. In this paper, we propose a dual stream network for image dehazing. To enhance the edge information and texture detail of the image, we construct a frequency stream based on attention octave convolution. We decompose the features into high and low-frequency branches in the frequency stream to obtain different structural information. By adding a residual channel attention block, the attention octave convolution can extract frequency features more efficiently and effectively. Due to the lower resolution of low-frequency features in the frequency stream, the frequency stream features alone are insufficient for recovering the overall content of the image. Therefore, a content stream was added to compensate for the information lost in the frequency stream. By fusing the outputs of two feature streams, the network achieves an enhanced dehazing performance. The results show that our method is superior to other state-of-the-art algorithms in quantitative evaluation and visual impact. • A significant difference between hazy and clear images after low-pass filtering. • Prior information indicates that haze is closer to low-frequency information. • Spatial features are decomposed into high and low-frequency components by Att OctConv. • The content stream uses RCAB to filter out redundant low-frequency information. • Our method is also excellent for underwater image restoration. [ABSTRACT FROM AUTHOR]

A novel dual-transformer-based full-bridge (DT-FB) converter with a current doubler rectifier (CDR), which can solve the drawbacks of existing FB converters, is proposed in this article. In the primary side of the proposed converter, two switching legs, two transformers, and two blocking capacitors form two half-bridge inverters. The secondary side composes of two output filter inductors and four power diodes, which connect with the form of the CDR. By employing this structure, a wide range of zero-voltage switching for leading-leg and zero-current switching for lagging-leg can be achieved. In the proposed converter, the output power is shared by two small-sized transformers and inductors instead of large-sized ones, which contributes to the improvement of power density and efficiency. Compared with the traditional FB converter, the proposed converter can obtain higher voltage gain, better rectified voltage, and lower current ripple. The operation principle, theoretical analysis, and design considerations of the proposed converter are described in this article. A prototype with 300–380 V input and 100 V/ 10 A output is designed and tested to confirm the effectiveness of the proposed converter. [ABSTRACT FROM AUTHOR]

Glaucoma is a chronic disease that threatens eye health and can cause permanent blindness. Since there is no cure for glaucoma, early screening and detection are crucial for the prevention of glaucoma. Therefore, a novel method for automatic glaucoma screening that combines clinical measurement features with image-based features is proposed in this paper. To accurately extract clinical measurement features, an improved UNet++ neural network is proposed to segment the optic disc and optic cup based on region of interest (ROI) simultaneously. Some important clinical measurement features, such as optic cup to disc ratio, are extracted from the segmentation results. Then, the increasing field of view (IFOV) feature model is proposed to fully extract texture features, statistical features, and other hidden image-based features. Next, we select the best feature combination from all the features and use the adaptive synthetic sampling approach to alleviate the uneven distribution of training data. Finally, a gradient boosting decision tree (GBDT) classifier for glaucoma screening is trained. Experimental results based on the ORIGA dataset show that the proposed algorithm achieves excellent glaucoma screening performance with sensitivity of 0.894, accuracy of 0.843, and AUC of 0.901, which is superior to other existing methods. Graphical abstract [ABSTRACT FROM AUTHOR]

Purpose: To develop a deep learning (DL) model for automated detection of glaucoma and to compare diagnostic capability against hand-craft features (HCFs) based on spectral domain optical coherence tomography (SD-OCT) peripapillary retinal nerve fiber layer (pRNFL) images. Methods: A DL model with pre-trained convolutional neural network (CNN) based was trained using a retrospective training set of 1501 pRNFL OCT images, which included 690 images from 153 glaucoma patients and 811 images from 394 normal subjects. The DL model was further tested in an independent test set of 50 images from 50 glaucoma patients and 52 images from 52 normal subjects. A customized software was used to extract and measure HCFs including pRNFL thickness in average and four different sectors. Area under the receiver operator characteristics (AROC) curves was calculated to compare the diagnostic capability between DL model and hand-crafted pRNFL parameters. Results: In this study, the DL model achieved an AROC of 0.99 [CI: 0.97 to 1.00] which was significantly larger than the AROC values of all other HCFs (AROCs 0.661 with 95% CI 0.549 to 0.772 for temporal sector, AROCs 0.696 with 95% CI 0.549 to 0.799 for nasal sector, AROCs 0.913 with 95% CI 0.855 to 0.970 for superior sector, AROCs 0.938 with 95% CI 0.894 to 0.982 for inferior sector, and AROCs 0.895 with 95% CI 0.832 to 0.957 for average). Conclusion: Our study demonstrated that DL models based on pre-trained CNN are capable of identifying glaucoma with high sensitivity and specificity based on SD-OCT pRNFL images. [ABSTRACT FROM AUTHOR]

Abstract There are a number of government directives and regulations as well as many public schemes on the recycling of batteries, in spite of this; the quantity of batteries that are actually recycled is still very low. Current production capacity cannot meet projected demand of Lithium-ion batteries. To counter this, the reclamation and repurposing of metals like cadmium, Lithium and Zinc from used or spent batteries is the only viable scheme. This is both environmentally friendly and economically feasible. An alternative is the selective chemical leaching in the presence of Sulfuric acid and Sodium metabisulfite. In this paper, the effect of these chemicals as well as the solid-to-liquid ratio and time of retention is comprehensively studied. Experiments are designed for the recovery of Zinc and cadmium from the spend Lithium-ion batteries mix. To maximize the recovery of Zinc and cadmium, the combined genetic programming and simulated annealing approach is proposed. Genetic programming is used for the formulation of functional relationship between recovered metals Zinc and cadmium and the inputs (Solid/Liquid ratio, concentration of Sulfuric acid, mass of Sodium metabisulfite and retention time). The optimal input conditions determined using the simulated annealing algorithm includes Solid/Liquid ratio of 11.7%, 0.86 M Sulfuric acid, 0.56 g/g of Sodium metabisulfite and 45 min of retention time. Three dimensions surface analysis reveals that a lower value of Solid/Liquid ratio favours a better yield. The optimal conditions are validated using experiments. This confirms the efficacy of simulated annealing aided genetic programming techniques as well as the optimal conditions of the metal extraction. Highlights • Problem of maximum extraction of Cadmium and Zinc from spent battery mix is undertaken. • Combined genetic programming and simulated annealing approach is proposed. • Genetic programming models fits the cadmium and zinc output very well. • Simulated annealing optimizes the Genetic programming model to obtain the optimum inputs. [ABSTRACT FROM AUTHOR]

Summary: The mechanisms in proton‐exchange membrane fuel cells (PEMFCs) cannot be explicitly represented by a mathematical function because the PEMFC system is multi‐dimensional and complex and represents uncertainty in operation variables, which cannot be modeled by experiments or by trial‐and‐error approach. Therefore, this work proposes to study the coupled and interactive influence of stack current (SC), stack temperature (ST), oxygen excess ratio (OER), hydrogen excess ratio (HER), and inlet air humidity (IAH) for optimizing the power output of PEMFC. The data obtained from the experiments have been inserted into architecture of automated neural‐network search, which automates the selection of error function, activation function, uncertainties in inputs and number of hidden neurons in formulation of a robust and accurate model for power density as a function of five operational variables. Among the operational variables, the correlation coefficient between the SC and the output power is the highest, followed by OER, and the ST. However, for HER and IAH, the power output follows negative nonlinear relation. The optimization converged at 130th iteration results in maximum power output of 3410 W for an optimum value of SC (51A), ST (59°C), OER (3:2), HER (1:10), and IAH (0.8). Schematic of proposed methodology to investigate the effect of uncontrollable parameters (stack current, stack temperature, oxygen excess ratio, hydrogen excess ratio, and inlet air humidity) on the power of PEMFC. [ABSTRACT FROM AUTHOR]

Abstract To achieve an effective coordination between the secondary control and the tertiary control of load frequency control (LFC), a new optimal active power control (OAPC) is constructed for real-timely changing the operating points of distributed energy resources (DERs) and thermostatically controlled loads (TCLs) in an islanded microgrid. A large number of TCLs are integrated as a load aggregator (LA) for participating the secondary control of LFC, which can enhance the dynamic response performance due to their much faster response speeds compared with that of distributed generators. Since OAPC is a nonsmooth and nonlinear optimization with a quite short implementation period, a novel model-free ensemble learning (EL) is proposed to rapidly obtain a high-quality optimal solution for it. EL based OAPC is composed of multiple sub-optimizers and a learning concentrator, where each sub-optimizer is responsible for providing the exploitation and exploration samples to the learning concentrator, while the reinforcement learning based concentrator is mainly used for knowledge learning and knowledge transfer. Case studies are thoroughly carried out to verify the performance of EL based OAPC in an islanded microgrid with 12 DERs and 900 TCLs. Highlights • A new optimal active power control (OAPC) is constructed for an islanded microgrid. • Various thermostatically controlled loads are used for secondary frequency control. • A novel ensemble learning (EL) can rapidly obtain a high-quality optimal solution. • The secondary control and tertiary control are effectively coordinated by OAPC. • The EL based OAPC can achieve a high dynamic response performance of a microgrid. [ABSTRACT FROM AUTHOR]

At present many hospitals have to deal with the patient’s care and nursing for Acute Hypotensive Episodes (AHE) occurring in Intensive Care Units. AHE can cause fainting or shock suddenly, leading to irreversibility organ damage, and even death. Therefore, forecasting of occurrence of AHE is of practical value. However, the prediction of clinical AHE largely depends on the doctors’ experience, which cannot guarantee the high rate of success. It is thus very meaningful for the clinical care to use appropriate methods to predict the AHE with an automatic and reliable method. In this study, a Probability Distribution Patterns Analysis (PDPA) method is presented to solve the time series prediction problem of AHE. In the first phase, the features are extracted from the PDPA in the global and integral time series, and the partial local time series in the fixed time window. In the second phase, the proposed algorithm combining Genetic Algorithm (GA) and Support Vector Machine (SVM), namely GA-SVM is adopted to select the vital features for the effective classification. In order to demonstrate the generality of our method, we also conduct experiments on a classical time series problem-Control Chart Patterns (CCPs) multi-class time series, which is a benchmark problem in the process control. For CCPs problem, the experimental results demonstrate that the proposed method outperforms several traditional methods. The obtained accuracy is 98.65%, which is superior to listed previous works using the same CCPs model. For AHE classification and forecasting, the methodology is applied in two data sets, a small data set (37 records) and a big one (2892 records). The test accuracy of 89.19%, sensitivity of 91.67%, specificity of 88% in the small data set, and a test accuracy of 80.76%, sensitivity of 78.19%, specificity of 81.51% in the big data set are achieved with the classification model. [ABSTRACT FROM AUTHOR]

Acute hypotensive episodes (AHEs) are one of the hemodynamic instabilities with high mortality rate that is frequent among many groups of patients. This study presents a methodology to predict AHE for ICU patients based on big data time series. The experimental data we used is mean arterial pressure (MAP), which is transformed from arterial blood pressure (ABP) data. Then, the Hilbert-Huang transform method was used to calculate patient’s MAP time series and some features, which are the bandwidth of the amplitude modulation, the frequency modulation, and the power of intrinsic mode function (IMF), were extracted. Finally, the multiple genetic programming (Multi-GP) is used to build the classification models for detection of AHE. The methodology is applied in the datasets of the 10th PhysioNet and Computers Cardiology Challenge in 2009 and Multiparameter Intelligent Monitoring for Intensive Care (MIMIC-II). We achieve the accuracy of 83.33% in the training set and 91.89% in the testing set of the 2009 challenge’s dataset and the 84.13% in the training set and 82.41% in the testing set of the MIMIC-II dataset. [ABSTRACT FROM AUTHOR]

This paper addresses some issues on the weighted linear integration of modular neural networks (MNN: a paradigm of hybrid multi-learning machines). First, from the general meaning of variable weights and variable elements synthesis, three basic kinds of integrated models are discussed that are intrinsic-factors-determined, extrinsic-factors-determined, and hybrid-factors-determined. The authors point out: integrations dominated by both of the internal and external elements are highly correlative with not only the historical quality of the sub-networks, but also with the environment in which the information is processed. In the sense of the mean of square error (MSE), several sufficient conditions to improve the whole system's performance are given while deleting one/some sub-networks in all the networks population. Meanwhile, when the whole performance of the current MNN system possesses is unsatisfactory, a corresponding improved strategy which need add one/some sub-networks is presented. For the optimal weights vector under the framework of the weighted sum of the sub-networks' outputs, we point out some constraints forms of the sub-networks' integrated weights are unreasonable and present a general form while the corresponding computational algorithms are described briefly. The authors present a new training algorithm of sub-networks named “'Expert in one thing and good at many' (EOGM).” In this algorithm, every sub-network is trained on a primary dataset with some of its near neighbors as the accessorial datasets. Simulated results with a kind of dynamic integration methods show the effectiveness of these algorithms, where the performance of the algorithm with EOGM is better than that of the algorithm with a common training method. [ABSTRACT FROM AUTHOR]

The sensor virus is a serious threat, as an attacker can simply send a single packet to compromise the entire sensor network. Epidemics become drastic with link additions among sensors when the small world phenomena occur. Two immunization strategies, uniform immunization and temporary immunization, are conducted on small worlds of tree-based wireless sensor networks to combat the sensor viruses. With the former strategy, the infection extends exponentially, although the immunization effectively reduces the contagion speed. With the latter strategy, recurrent contagion oscillations occur in the small world when the spatial-temporal dynamics of the epidemic are considered. The oscillations come from the small-world structure and the temporary immunization. Mathematical analyses on the small world of the Cayley tree are presented to reveal the epidemic dynamics with the two immunization strategies. [ABSTRACT FROM AUTHOR]

Abstract: The efficient expression of exogenous gene in mitochondria of photosynthetic organism has been an insurmountable problem. In this study, the pBsLPNCG was constructed by inserting the egfp gene into a site between TERMINVREP-Left repeats and the cob gene in a fragment of mitochondrial DNA of Chlamydomonas reinhardtii CC-124 and introduced into the mitochondria of respiratory deficient dum-1 mutation of C. reinhardtii CC-2654. Sequencing and DNA Southern analyses revealed that egfp gene had been integrated into the mitochondrial genome of transgenic algae as expected and no other copy of egfp existed in their nucleic genome. Both the fluorescence detection and Western blot analysis confirmed the presence of eGFP protein in the transgenic algae; it indicated that the egfp gene was successfully expressed in the mitochondria of C. reinhardtii. [Copyright &y& Elsevier]

Abstract: Modular neural network is a popular neural network model which has many successful applications. In this paper, a sequential Bayesian learning (SBL) is proposed for modular neural networks aiming at efficiently aggregating the outputs of members of the ensemble. The experimental results on eight benchmark problems have demonstrated that the proposed method can perform information aggregation efficiently in data modeling. [Copyright &y& Elsevier]

Phase-sensitive optical time domain reflectometer (Φ-OTDR) can detect the occurrence of external vibration, but lacks of ability to classify multiple similar events. With the help of machine learning method, the events can be basically classified. An event recognition method based on deep learning and traditional classifier is proposed in this paper to further improve the classification accuracy. Firstly, the temporal-spatial data matrix from Φ-OTDR is directly sent to convolutional neural network (CNN) and the data features can be obtained automatically. Then these data features are transmitted to a traditional classifier for further classification. The traditional classifier can find a better classification hyperplane to improve the classification accuracy. In this paper, the most suitable classifier is support vector machine (SVM). As CNN works as a black box, T-distributed stochastic neighbor embedding (T-SNE) method and gradient-weighted class activation mapping (Grad-CAM) method are applied to visualize CNN's working process, which illustrates the correctness of feature extraction. Experimental results based on 11,997 images under eight event categories show that the classification accuracy can be improved by the traditional classifier. The CNN+SVM strategy performs the best and reaches 94.17 % accuracy, which offers 2.04 % improvement compared with using CNN alone. [ABSTRACT FROM AUTHOR]

• Propose a sampling-based asymptotically optimal path planning algorithm. • The proposed algorithm guarantees a fast convergence rate. • Theoretical proof of asymptotic optimality and fast convergence rate is given. During the last decade, sampling-based algorithms for path planning have gained considerable attention. The RRT*, a variant of RRT (rapidly-exploring random trees), is of particular concern to researchers due to its asymptotic optimality. However, the limits of the slow convergence rate of RRT* makes it inefficient for applications. For the purposes of overcoming these limitations, this paper proposes a novel algorithm, PQ-RRT*, which combines the strengths of P-RRT* (potential functions based RRT*) and Quick-RRT*. PQ-RRT* guarantees a fast convergence to an optimal solution and generates a better initial solution. The asymptotic optimality and fast convergence of the proposed algorithm are proved in this paper. Comparisons of PQ-RRT* with P-RRT* and Quick-RRT* in four benchmarks verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

This paper proposed a method for discriminating two close perturbations, whose interval is less than spatial resolution, in Φ-OTDR system. The mathematical model under two close perturbations is studied and the frequency features of temporal signal from every sensing positions are obtained. The model shows that if the two close perturbations have different frequencies, they can be distinguished through spatial-frequency analysis. When the two perturbations have even the same frequency, they can still be distinguished by inspecting higher-order harmonic frequencies. Both computer simulation and experiments have been carried out to support the effectiveness of this method. [ABSTRACT FROM AUTHOR]

Phase-sensitive optical time domain reflectometer (Φ-OTDR) based distributed optical fiber sensing system has been widely used in many fields such as long range pipeline pre-warning, perimeter security and structure health monitoring. However, the lack of event recognition ability is always being the bottleneck of Φ-OTDR in field application. An event recognition method based on deep learning is proposed in this paper. This method directly uses the temporal-spatial data matrix from Φ-OTDR as the input of a convolutional neural network (CNN). Only a simple bandpass filtering and a gray scale transformation are needed as the pre-processing, which achieves real-time. Besides, an optimized network structure with small size, high training speed and high classification accuracy is built. Experiment results based on 5644 events samples show that this network can achieve 96.67% classification accuracy in recognition of 5 kinds of events and the retraining time is only 7 min for a new sensing setup. [ABSTRACT FROM AUTHOR]