An Adaptive-PSO-Based Self-Organizing RBF Neural Network

Transfer Learning Algorithm With Knowledge Division Level

One of the major challenges of transfer learning algorithms is the domain drifting problem where the knowledge of source scene is inappropriate for the task of target scene. To solve this problem, a transfer learning algorithm with knowledge division level (KDTL) is proposed to subdivide knowledge of source scene and leverage them with different drifting degrees. The main properties of KDTL are three folds. First, a comparative evaluation mechanism is developed to detect and subdivide the knowledge into three kinds-the ineffective knowledge, the usable knowledge, and the efficient knowledge. Then, the ineffective and usable knowledge can be found to avoid the negative transfer problem. Second, an integrated framework is designed to prune the ineffective knowledge in the elastic layer, reconstruct the usable knowledge in the refined layer, and learn the efficient knowledge in the leveraged layer. Then, the efficient knowledge can be acquired to improve the learning performance. Third, the theoretical analysis of the proposed KDTL is analyzed in different phases. Then, the convergence property, error bound, and computational complexity of KDTL are provided for the successful applications. Finally, the proposed KDTL is tested by several benchmark problems and some real problems. The experimental results demonstrate that this proposed KDTL can achieve significant improvement over some state-of-the-art algorithms.

SparseVoxNet: 3-D Object Recognition With Sparsely Aggregation of 3-D Dense Blocks

Automatic recognition of 3-D objects in a 3-D model by convolutional neural network (CNN) methods has been successfully applied to various tasks, e.g., robotics and augmented reality. Three-dimensional object recognition is mainly performed by analyzing the object using multi-view images, depth images, graphs, or volumetric data. In some cases, using volumetric data provides the most promising results. However, existing recognition techniques on volumetric data have many drawbacks, such as losing object details on converting points to voxels and the large size of the input volume data that leads to substantial 3-D CNNs. Using point clouds could also provide very promising results; however, point-cloud-based methods typically need sparse data entry and time-consuming training stages. Thus, using volumetric could be a more efficient and flexible recognizer for our special case in the School of Medicine, Shanghai Jiao Tong University. In this article, we propose a novel solution to 3-D object recognition from volumetric data using a combination of three compact CNN models, low-cost SparseNet, and feature representation technique. We achieve an optimized network by estimating extra geometrical information comprising the surface normal and curvature into two separated neural networks. These two models provide supplementary information to each voxel data that consequently improve the results. The primary network model takes advantage of all the predicted features and uses these features in Random Forest (RF) for recognition purposes. Our method outperforms other methods in training speed in our experiments and provides an accurate result as good as the state-of-the-art.

Predominant Cognitive Learning Particle Swarm Optimization for Global Numerical Optimization

Particle swarm optimization (PSO) has witnessed giant success in problem optimization. Nevertheless, its optimization performance seriously degrades when coping with optimization problems with a lot of local optima. To alleviate this issue, this paper designs a predominant cognitive learning particle swarm optimization (PCLPSO) method to effectively tackle complicated optimization problems. Specifically, for each particle, a new promising exemplar is constructed by letting its personal best position cognitively learn from a better personal experience randomly selected from those of others based on a novel predominant cognitive learning strategy. As a result, different particles preserve different guiding exemplars. In this way, the learning effectiveness and the learning diversity of particles are expectedly improved. To eliminate the dilemma that PCLPSO is sensitive to the involved parameters, we propose dynamic adjustment strategies, so that different particles preserve different parameter settings, which is further beneficial to promote the learning diversity of particles. With the above techniques, the proposed PCLPSO could expectedly compromise the search intensification and diversification in a good way to search the complex solution space properly to achieve satisfactory performance. Comprehensive experiments are conducted on the commonly adopted CEC 2017 benchmark function set to testify the effectiveness of the devised PCLPSO. Experimental results show that PCLPSO obtains considerably competitive or even much more promising performance than several representative and state-of-the-art peer methods.

Chain-Structure Echo State Network With Stochastic Optimization: Methodology and Application

In this article, a chain-structure echo state network (CESN) with stacked subnetwork modules is newly proposed as a new kind of deep recurrent neural network for multivariate time series prediction. Motivated by the philosophy of "divide and conquer," the related input vectors are first divided into clusters, and the final output results of CESN are then integrated by successively learning the predicted values of each clustered variable. Network structure, mathematical model, training mechanism, and stability analysis are, respectively, studied for the proposed CESN. In the training stage, least-squares regression is first used to pretrain the output weights in a module-by-module way, and stochastic local search (SLS) is developed to fine-tune network weights toward global optima. The loss function of CESN can be effectively reduced by SLS. To avoid overfitting, the optimization process is stopped when the validation error starts to increase. Finally, SLS-CESN is evaluated in chaos prediction benchmarks and real applications. Four different examples are given to verify the effectiveness and robustness of CESN and SLS-CESN.

Water Quality Indicator Interval Prediction in Wastewater Treatment Process Based on the Improved BES-LSSVM Algorithm

This paper proposes a novel interval prediction method for effluent water quality indicators (including biochemical oxygen demand (BOD) and ammonia nitrogen (NH3-N)), which are key performance indices in the water quality monitoring and control of a wastewater treatment plant. Firstly, the effluent data regarding BOD/NH3-N and their necessary auxiliary variables are collected. After some basic data pre-processing techniques, the key indicators with high correlation degrees of BOD and NH3-N are analyzed and selected based on a gray correlation analysis algorithm. Next, an improved IBES-LSSVM algorithm is designed to predict the BOD/NH3-N effluent data of a wastewater treatment plant. This algorithm relies on an improved bald eagle search (IBES) optimization algorithm that is used to find the optimal parameters of least squares support vector machine (LSSVM). Then, an interval estimation method is used to analyze the uncertainty of the optimized LSSVM model. Finally, the experimental results demonstrate that the proposed approach can obtain high prediction accuracy, with reduced computational time and an easy calculation process, in predicting effluent water quality parameters compared with other existing algorithms.

Particle Swarm Optimization Algorithm With Self-Organizing Mapping for Nash Equilibrium Strategy in Application of Multiobjective Optimization

In this article, the Nash equilibrium strategy is used to solve the multiobjective optimization problems (MOPs) with the aid of an integrated algorithm combining the particle swarm optimization (PSO) algorithm and the self-organizing mapping (SOM) neural network. The Nash equilibrium strategy addresses the MOPs by comparing decision variables one by one under different objectives. The randomness of the PSO algorithm gives full play to the advantages of parallel computing and improves the rate of comparison calculation. In order to avoid falling into local optimal solutions and increase the diversity of particles, a nonlinear recursive function is introduced to adjust the inertia weight, which is called the adaptive particle swarm optimization (APSO). In addition, the neighborhood relations of current particles are constructed by SOM, and the leading particles are selected from the neighborhood to guide the local and global search, so as to achieve convergence. Compared with several advanced algorithms based on the eight multiobjective standard test functions with different Pareto solution sets and Pareto front characteristics in examples, the proposed algorithm has a better performance.

A Complex Chained P System Based on Evolutionary Mechanism for Image Segmentation

A new clustering membrane system using a complex chained P system (CCP) based on evolutionary mechanism is designed, developed, implemented, and tested. The purpose of CCP is to solve clustering problems. In CCP, two kinds of evolution rules in different chained membranes are used to enhance the global search ability. The first kind of evolution rules using traditional and modified particle swarm optimization (PSO) clustering techniques are used to evolve the objects. Another based on differential evolution (DE) is introduced to further improve the global search ability. The communication rules are adopted to accelerate the convergence and avoid prematurity. Under the control of evolution-communication mechanism, the CCP can effectively search for the optimal partitioning and improve the clustering performance with the help of the distributed parallel computing model. This proposed CCP is compared with four existing PSO clustering approaches on eight real-life datasets to verify the validity. The computational results on tested images also clearly show the effectiveness of CCP in solving image segmentation problems.

Broad Colorization

The scribble- and example-based colorization methods have fastidious requirements for users, and the training process of deep neural networks for colorization is quite time-consuming. We instead proposed an automatic colorization approach with no dependence on user input and no need to endure long training time, which combines local features and global features of the input gray-scale images. Low-, mid-, and high-level features are united as local features representing cues existed in the gray-scale image. The global feature is regarded as data prior to guiding the colorization process. The local broad learning system is trained for getting the chrominance value of each pixel from the local features, which could be expressed as a chrominance map according to the position of pixels. Then, the global broad learning system is trained to refine the chrominance map. There are no requirements for users in our approach, and the training time of our framework is an order of magnitude faster than the traditional methods based on deep neural networks. To increase the user's subjective initiative, our system allows users to increase training data without retraining the system. Substantial experimental results have shown that our approach outperforms state-of-the-art methods.

A Phase Angle-Modulated Bat Algorithm with Application to Antenna Topology Optimization

This paper proposes a phase angle-modulated bat algorithm (P-AMBA) for high-dimensional binary optimization. The idea was to reduce the optimization time by introducing angle modulation technology to reduce the optimization dimensions. Different from the original angle-modulated bat algorithm (AMBA), the control of the trigonometric generating function cosine wave is by introducing new parameters, thereby improving the perturbation ability of the function curve near the x-axis. P-AMBA can explore more 0/1 solutions, and it has advantages in optimizing convergence speed and global search capabilities. The numerical results of the 0–1 knapsack problem tests show that P-AMBA is superior to the contrast algorithms on optimization ability and optimization time. Finally, the experimental result of a compact dual-band planar monopole antenna design showed the effectiveness of P-AMBA in engineering applications.

A Development of Granular Input Space in System Modeling

In this paper, we elaborate on a new design approach to the development and analysis of granular input spaces and ensuing granular modeling. Given a numeric model (no matter what specific design methodology has been used to construct it and what architecture has been adopted), we form a granular input space through allocating a certain level of information granularity across the input variables. The formation of granular input space helps us gain a better insight into the ranking of input variables with respect to their precision (the variables with a lower level of information granularity need to be specified in a precise way when estimating the inputs). As a consequence, for granular inputs, the outputs of the granular model are also information granules (say, intervals, fuzzy sets, rough sets, etc.). It is shown that the process of forming granular input space can be sought as an optimization of allocation of information granularity across the input variables so that the specificity of the corresponding granular outputs of the granular model becomes the highest while coverage of data becomes maximized. The construction of granular input space dwells upon two fundamental principles of granular computing-the principle of justifiable granularity and the optimal allocation of information granularity. The quality of the granular input space is quantified in terms of the two conflicting criteria, that is, the specificity of the results produced by the granular model and the coverage of experimental data delivered by this model. In the ensuing optimization problem, one maximizes a product of specificity and coverage. Differential evolution is engaged in this optimization task. The experimental studies involve both synthetic dataset and data coming from the machine learning repository.

Utilization of Time Series Tools in Life-sciences and Neuroscience

Time series tools are part and parcel of modern day research. Their usage in the biomedical field; specifically, in neuroscience, has not been previously quantified. A quantification of trends can tell about lacunae in the current uses and point towards future uses. We evaluated the principles and applications of few classical time series tools, such as Principal Component Analysis, Neural Networks, common Auto-regression Models, Markov Models, Hidden Markov Models, Fourier Analysis, Spectral Analysis, in addition to diverse work, generically lumped under time series category. We quantified the usage from two perspectives, one, information technology professionals', other, researchers utilizing these tools for biomedical and neuroscience research. For understanding trends from the information technology perspective, we evaluated two of the largest open source question and answer databases of Stack Overflow and Cross Validated. We quantified the trends in their application in the biomedical domain, and specifically neuroscience, by searching literature and application usage on PubMed. While the use of all the time series tools continues to gain popularity in general biomedical and life science research, and also neuroscience, and so have been the total number of questions asked on Stack overflow and Cross Validated, the total views to questions on these are on a decrease in recent years, indicating well established texts, algorithms, and libraries, resulting in engineers not looking for what used to be common questions a few years back. The use of these tools in neuroscience clearly leaves room for improvement.

Dead Sea Water Levels Analysis Using Artificial Neural Networks and Firefly Algorithm

In this study, the performance of adaptive multilayer perceptron neural network (MLPNN) for predicting the Dead Sea water level is discussed. Firefly Algorithm (FFA), as an optimization algorithm is used for training the neural networks. To propose the MLPNN-FFA model, Dead Sea water levels over the period 1810–2005 are applied to train MLPNN. Statistical tests evaluate the accuracy of the hybrid MLPNN-FFA model. The predicted values of the proposed model were compared with the results obtained by another method. The results reveal that the artificial neural network (ANN) models exhibit high accuracy and reliability for the prediction of the Dead Sea water levels. The results also reveal that the Dead Sea water level would be around -450 until 2050.

Toward Enhanced State of Charge Estimation of Lithium-ion Batteries Using Optimized Machine Learning Techniques

State of charge (SOC) is a crucial index used in the assessment of electric vehicle (EV) battery storage systems. Thus, SOC estimation of lithium-ion batteries has been widely investigated because of their fast charging, long-life cycle, and high energy density characteristics. However, precise SOC assessment of lithium-ion batteries remains challenging because of their varying characteristics under different working environments. Machine learning techniques have been widely used to design an advanced SOC estimation method without the information of battery chemical reactions, battery models, internal properties, and additional filters. Here, the capacity of optimized machine learning techniques are presented toward enhanced SOC estimation in terms of learning capability, accuracy, generalization performance, and convergence speed. We validate the proposed method through lithium-ion battery experiments, EV drive cycles, temperature, noise, and aging effects. We show that the proposed method outperforms several state-of-the-art approaches in terms of accuracy, adaptability, and robustness under diverse operating conditions.

Non-Singular Fast Terminal Sliding Mode Control of High-Speed Train Network System Based on Improved Particle Swarm Optimization Algorithm

This paper proposes a non-singular fast terminal sliding mode control strategy based on the self-organizing radial basis function neural network (RBFNN) approximation for the train key network system to realize the safe and reliable operation of the train. In order to improve the RBFNN approximation performance and speed, an improved multi-strategy particle swarm optimization (IMPSO) algorithm, which utilizes multi-strategy evolution ways with a nonlinear deceasing inertia weight to improve the global optimizing performance of particle swarm, is proposed to optimize the structure and parameters for better mapping the highly nonlinear characteristics of train traction braking. In addition, the IMPSO is also introduced into a non-singular fast terminal sliding mode (NFTSM) controller to obtain the most appropriate tuning parameters of the controller and suppresses the chattering phenomenon from sliding mode controller. The stability characteristic of the system under the proposed NFTSM controller is studied based on the Lyapunov theory. Further combined with effective delay prediction and delay compensation methods, the NFTSM high-precision control of the train key nonlinear network system is implemented. The simulation results show that the proposed method has more efficient and robust tracking performance and real-time performance compared with other control methods, which can provide effective means for realizing the symmetrical bus control by automatic train operation (ATO) at both ends of the train, with the safe operation of the train under every complex motion condition.

On-line prediction of ferrous ion concentration in goethite process based on self-adjusting structure RBF neural network

Outlet ferrous ion concentration is an essential indicator to manipulate the goethite process in the zinc hydrometallurgy plant. However, it cannot be measured on-line, which leads to the delay of this feedback information. In this study, a self-adjusting structure radial basis function neural network (SAS-RBFNN) is developed to predict the outlet ferrous ion concentration on-line. First, a supervised cluster algorithm is proposed to initialize the RBFNN. Then, the network structure is adjusted by the developed self-adjusting structure mechanism. This mechanism can merge or divide the hidden neurons according to the distance of the clusters to achieve the adaptability of the RBFNN. Finally, the connection weights are determined by the gradient-based algorithm. The convergence of the SAS-RBFNN is analyzed by the Lyapunov criterion. A simulation for a benchmark problem shows the effectiveness of the proposed network. The SAS-RBFNN is then applied to predict the outlet ferrous ion concentration in the goethite process. The results demonstrate that this network can provide a more accurate prediction than the mathematical model, even under the fluctuating production condition.

Contour-Seed Pairs Learning-Based Framework for Simultaneously Detecting and Segmenting Various Overlapping Cells/Nuclei in Microscopy Images

In this paper, we propose a novel contour-seed pairs learning-based framework for robust and automated cell/nucleus segmentation. Automated granular object segmentation in microscopy images has significant clinical importance for pathology grading of the cell carcinoma and gene expression. The focus of the past literature is dominated by either segmenting a certain type of cells/nuclei or simply splitting the clustered objects without contours inference of them. Our method addresses these issues by formulating the detection and segmentation tasks in terms of a unified regression problem, where a cascade sparse regression chain model is trained and then applied to return object locations and entire boundaries of clustered objects. In particular, we first learn a set of online convolutional features in each layer. Then, in the proposed cascade sparse regression chain, with the input from the learned features, we iteratively update the locations and clustered object boundaries until convergence. In this way, the boundary evidences of each individual object can be easily delineated and be further fed to a complete contour inference procedure optimized by the minimum description length principle. For any probe image, our method enables to analyze free-lying and overlapping cells with complex shapes. Experimental results show that the proposed method is very generic and performs well on contour inferences of various cell/nucleus types. Compared with the current segmentation techniques, our approach achieves state-of-the-art performances on four challenging datasets, i.e., the kidney renal cell carcinoma histopathology dataset, Drosophila Kc167 cellular dataset, differential interference contrast red blood cell dataset, and cervical cytology dataset.

Radial Basis Functions With Adaptive Input and Composite Trend Representation for Portfolio Selection

We propose a set of novel radial basis functions with adaptive input and composite trend representation (AICTR) for portfolio selection (PS). Trend representation of asset price is one of the main information to be exploited in PS. However, most state-of-the-art trend representation-based systems exploit only one kind of trend information and lack effective mechanisms to construct a composite trend representation. The proposed system exploits a set of RBFs with multiple trend representations, which improves the effectiveness and robustness in price prediction. Moreover, the input of the RBFs automatically switches to the best trend representation according to the recent investing performance of different price predictions. We also propose a novel objective to combine these RBFs and select the portfolio. Extensive experiments on six benchmark data sets (including a new challenging data set that we propose) from different real-world stock markets indicate that the proposed RBFs effectively combine different trend representations and AICTR achieves state-of-the-art investing performance and risk control. Besides, AICTR withstands the reasonable transaction costs and runs fast; hence, it is applicable to real-world financial environments.