Search

In many modern machine learning (ML) models, attention mechanisms (AMs) play a crucial role in processing data and identifying significant parts of the inputs, whether these are text or images. This selective focus enables subsequent stages of the model to achieve improved classification performance. Traditionally, AMs are applied as a preprocessing substructure before a neural network, such as in encoder/decoder architectures. In this paper, we extend the application of AMs to intermediate stages of data propagation within ML models. Specifically, we propose a generalized attention mechanism (GAM), which can be integrated before each layer of a neural network for classification tasks. The proposed GAM allows for at each layer/step of the ML architecture identification of the most relevant sections of the intermediate results. Our experimental results demonstrate that incorporating the proposed GAM into various ML models consistently enhances the accuracy of these models. This improvement is achieved with only a marginal increase in the number of parameters, which does not significantly affect the training time. [ABSTRACT FROM AUTHOR]

This document serves as a preface to a special issue of the International Journal on Artificial Intelligence Tools (IJAIT). The articles in this issue build upon papers presented at the 36th International Florida AI Research Society Conferences in May 2023. The lead article introduces the theme of the special issue, which is explainable, fair, and Trustworthy AI. Other articles in the issue cover topics such as improving the bounds of a neuron's Boolean function, ethical explanations and transparency in AI systems, fairness measurement and mitigation in deep learning systems, and the dynamics of human-agent collaboration in ad hoc teams. The paper emphasizes the importance of positive and negative contrastive explanations in enhancing motivation and performance. It also addresses the challenges of fairness and reliability in predictive policing systems, with a focus on reducing bias related to race, age, and sex. The authors propose tailoring predictive models to specific causal queries and utilizing causal structure instead of relying solely on pre-trained models. The paper also explores how machine learning models can balance accuracy and understandability, as well as ensure fairness. The findings indicate that more complex models tend to outperform current guidelines, but fair models have lower complexity. The paper concludes by expressing gratitude to the reviewers for their contributions and support. [Extracted from the article]

Retail demand forecasting is a highly intricate and multilevel problem as it may include numerous products, under multiple categories, and potentially sold in many different stores. Forecasts may also process products in isolation or collectively so as to detect mutual correlations. In technical terms, retail demand forecasting may be broken down to a multivariate time series forecasting problem where the time axis is prevalent and introduces added complexity which necessitates proper usage of advanced methodologies with machine/deep learning backgrounds. Popular boosting regressors, such as XGBoost and LightGBM, are excellent machine learning candidates with extensive bibliographic backgrounds covering multiple scientific fields and applications including generic multivariate time series forecasts. The Temporal Convolutional Network and the Temporal Fusion Transformer are recently proposed deep neural network architectures that found success in specific multivariate scenarios but are yet to be tested in a variety of related fields such as retail demand forecasting. Therefore, within this paper, these novel in-the-field models are compared to the aforementioned boosting approaches alongside popular statistical univariate methods, namely Exponential Smoothing and SARIMA. To properly compare the selected models and attempt to generalize their usability, two separate datasets are analyzed and forecasted; an item sales dataset with 500 time series and a category sales dataset with 540 time series. The findings suggest that the deep learning solutions are the better predictors, with the Transformer model surpassing the Boosting solutions by up to 16.8% sMAPE decrease and the statistical approaches by up to 28.6% decrease, further substantiating the notion that deep learning techniques are exceptionally promising in handling large-scale, non-linear and outlier data whilst suggesting that retail demand forecasting does benefit from multivariate approaches and the application of advanced machine learning methods. [ABSTRACT FROM AUTHOR]

A variant of membrane computing models called Spiking Neural P systems (SNP systems) closely mimics the structure and behavior of biological neurons. As third-generation neural networks, SNP systems have flexible architectures allowing the design of bio-inspired machine learning algorithms. This paper proposes Modular Spiking Neural P (MSNP) systems to solve image classification problems, a novel SNP system to be applied in scenarios where hundreds or even thousands of different classes are considered. A main issue to face in such situations is related to the structural complexity of the network. MSNP systems devised in this work allow to approach the general classification problem by dividing it in smaller parts, that are then faced by single entities of the network. As a benchmark dataset, the Oxford Flowers 102 dataset is considered, consisting of more than 8000 pictures of flowers belonging to the 102 species commonly found in the UK. These classes sometimes present large variations within them, may be also very similar to one another, and different images of the same subject may differ a lot. The work describes the architecture of the MSNP system, based on modules focusing on a specific class, their training phase, and the evaluation of the model both concerning result accuracy as well as energy consumption. Experimental results on image classification problems show that the model achieves good results, but is strongly connected to image quality, mainly depending on the frequency of images, remarkable changes of pose, images not centered, and subject mostly not shown. [ABSTRACT FROM AUTHOR]

The Π -shaped open section girder is a very common section, which has been widely used in the construction of modern bridges. However, compared with a streamlined box girder, it is easy to cause vortex-induced vibration (VIV) in bridges due to its bluff section shape and poor aerodynamic stability. In this paper, a typical open section with a height–width ratio of 10:1 is taken as the research object. Through wind tunnel tests and numerical simulation technology, the time-history data of VIV of the Π -shaped section are obtained. By selecting three different neural network models to establish the relationship between external parameters (wind attack angle, wind speed, turbulence) and structural response parameters (the onset wind speed of VIV, the length of the lock-in interval). After comparing different machine learning methods, the most suitable machine learning model is selected to predict the VIV response characteristics of the main girder. The research results show that the typical open section has a serious VIV phenomenon. The BP neural network model has the best performance in predicting the VIV performance of the open section in terms of calculation speed, prediction accuracy and solving nonlinear adaptability. At the same time, it is found that different characteristic parameters of the incoming wind field have different influences on the prediction results of the VIV response. Among them, the wind attack angle is the key parameter that affects the onset wind speed of VIV, but the turbulence intensity has a greater impact on the maximum amplitude of VIV. At the same time, the optimized BP model can predict the characteristic parameters of VIV response under unknown wind fields. This paper provides a new idea to study the effect of different incoming flow parameters on the performance of section VIV and further improves people's understanding of VIV system. [ABSTRACT FROM AUTHOR]

Variable selection is one of the most important contents of machine learning research and a large number of variable selection methods have been proposed at present. From deep learning perspective, we propose a new variable selection method based on multi-layer artificial neural networks in this paper. The method propagates errors gained form a trained network model through the network from output layer to input layer and the values gained by input layer give information about the relative contribution. The variables with big contribution value are selected, which we call neural inverse propagation (NIP). Specifically, after training a neural network, the gained errors between the actual network outputs and the desired outputs go through the network from top to down and arrive at the input layer. The absolute values gained by input units provide information about the relative importance (contribution) of input units, which is that the larger the value is, the more important the corresponding input variable is. We remove k variables corresponding to the first k minimum absolute value gained by input units to the predictive variables, to perform variable selection. The efficiency of the proposed method is illustrated through its application to classification and regression tasks on a number of synthetic datasets and a real-world image classification dataset. [ABSTRACT FROM AUTHOR]

In this paper, we present a new method for Lane Detection (LD) to reduce the impact of some issues associated with Autonomous Driving Cars (ADCs). It relies on the fact that self-driving will be the getaway of the transportation future. The ADC technology has expanded as it does not require human assistance. For ACD to be fully utilized, Machine Learning (ML) tools, such as Deep Neural Networks (DNNs), are required. However, ACD technology uses tools like a camera, GPS, Ultrasonic Sensor (US), and others, which work together to produce accurate ACDs. While adopting ACD, several issues need to be addressed such as carves, blurry, unclean, shadow, sunlight, pedestrians, and weather conditions. The paper proposes a new method to detect when a portion of a road line is missing due to weather conditions or old marking, protecting pedestrians and cars. For lane detection, the DNN model and Hough transform are used. CULane datasets including training and testing samples were used in the experiments. The results show high accuracy levels of 92%, indicating the ability to detect road lanes. [ABSTRACT FROM AUTHOR]

Spiking Neural Networks (SNNs) help achieve brain-like efficiency and functionality by building neurons and synapses that mimic the human brain's transmission of electrical signals. However, optimal SNN implementation requires a precise balance of parametric values. To design such ubiquitous neural networks, a graphical tool for visualizing, analyzing, and explaining the internal behavior of spikes is crucial. Although some popular SNN simulators are available, these tools do not allow users to interact with the neural network during simulation. To this end, we have introduced the first runtime interactive simulator, called Runtime Analyzing and Visualization Simulator (RAVSim), developed to analyze and dynamically visualize the behavior of SNNs, allowing end-users to interact, observe output concentration reactions, and make changes directly during the simulation. In this paper, we present RAVSim with the current implementation of runtime interaction using the LIF neural model with different connectivity schemes, an image classification model using SNNs, and a dataset creation feature. Our main objective is to primarily investigate binary classification using SNNs with RGB images. We created a feed-forward network using the LIF neural model for an image classification algorithm and evaluated it by using RAVSim. The algorithm classifies faces with and without masks, achieving an accuracy of 91.8% using 1000 neurons in a hidden layer, 0.0758 MSE, and an execution time of ∼10 min on the CPU. The experimental results show that using RAVSim not only increases network design speed but also accelerates user learning capability. [ABSTRACT FROM AUTHOR]

This paper investigates the possibility for implementing machine learning-aided prediction in analyzing the buckling phenomena of ballasted railway tracks induced by extreme temperature. In this study, artificial neural networks (ANNs) have been developed to identify the relationship between various ballasted track conditions and outputs, namely safe temperature and buckling temperature. The variables included in the objective function of the optimization problems are the lateral resistance of ballasted track provided by ballast-sleeper interaction, torsional resistance provided by fastening systems, and misalignment of the track. Due to its complexity in parameter combinations, the objective of this study is to create predictive models with the aim of minimizing the usage of scarce resources. Thus, this paper is the first to develop a novel machine learning-aided prediction of railway track buckling due to extreme temperature. Comprehensively, all 353 datasets of the safe and buckling temperatures derived from previous finite element (FE) simulation results have been collected and trained. Note that the mean squared error (MSE) and the coefficient of determination ( R 2) are considered to quantify the performance of the ANN architectures. The optimal ANN architecture with a very high rate of accuracy has been determined and highlighted. Thus, the suggested neural network model can be applied conveniently to help estimate safe and buckling temperatures of the complex track models in order to improve track conditions and thus prevent track buckling in summer. [ABSTRACT FROM AUTHOR]

Aiming to solve the problem of tracking drift during movement, which was caused by the lack of discriminability of the feature information and the failure of a fixed template to adapt to the change of object appearance, the paper proposes an object tracking algorithm combining attention mechanism and correlation filter theory based on the framework of full convolutional Siamese neural networks. Firstly, the apparent information is processed by using the attention mechanism thought, where the object and search area features are optimized according to the spatial attention and channel attention module. At the same time, the cross-attention module is introduced to process the template branch and search area branch, respectively, which makes full use of the diversified context information of the search area. Then, the background perception correlation filter model with scale adaptation and learning rate adjustment is adopted into the model construction, using as a layer in the network model to realize the object template update. Finally, the optimal object location is determined according to the confidence map with similarity calculation. Experimental results show that the designed method in the paper can promote the object tracking performance under various challenging environments effectively; the success rate increases by 16.2%, and the accuracy rate increases by 16%. [ABSTRACT FROM AUTHOR]

Deep learning is a popular topic among machine learning researchers nowadays, with great strides being made in recent years to develop robust artificial neural networks for faster convergence to a reasonable accuracy. Network architecture and hyperparameters of the model are fundamental aspects of model convergence. One such important parameter is the initial values of weights, also known as weight initialization. In this paper, we perform two research tasks concerned with the weights of neural networks. First, we develop three novel weight initialization algorithms inspired by the neuroscientific construction of the mammalian brains and then test them on benchmark datasets against other algorithms to compare and assess their performance. We call these algorithms the lognormal weight initialization, modified lognormal weight initialization, and skewed weight initialization. We observe from our results that these initialization algorithms provide state-of-the-art results on all of the benchmark datasets. Second, we analyze the influence of training an artificial neural network on its weight distribution by measuring the correlation between the quantitative metrics of skewness and kurtosis against the model accuracy using linear regression for different weight initializations. Results indicate a positive correlation between network accuracy and skewness of the weight distribution but no affirmative relation between accuracy and kurtosis. This analysis provides further insight into understanding the inner mechanism of neural network training using the shape of weight distribution. Overall, the works in this paper are the first of their kind in incorporating neuroscientific knowledge into the domain of artificial neural network weights. [ABSTRACT FROM AUTHOR]

With the limitation of air traffic and the rapid increase in the number of flights, flight delay is becoming more frequent. Flight delay leads to financial and time losses for passengers and increases operating costs for airlines. Therefore, the establishment of an accurate prediction model for flight delay becomes vital to build an efficient airline transportation system. The air transportation system has a huge amount of data and complex operation modes, which is suitable for analysis by using machine learning methods. This paper discusses the factors that may affect the flight delay, and presents a new flight delay prediction model. The five warning levels are defined based on flight delay database by using K-means clustering algorithm. After extracting the key factors related to flight operation by the grey relational analysis (GRA) algorithm, an improved machine learning algorithm called GRA — Genetic algorithm (GA) — back propagation neural network, GRA-GA-BP, is introduced, which is optimized by GA. The calculation results show that, compared with models before optimization and other two algorithms in previous papers, the proposed prediction model based on GRA-GA-BP algorithm shows a higher prediction accuracy and more stability. In terms of operation efficiency and memory consumption, it also has good performance. The analysis presented in this paper indicates that this model can provide effective early warnings for flight delay, and can help airlines to intervene in flights with abnormal trend in advance. [ABSTRACT FROM AUTHOR]

EEG has been proved to be an effective tool for researchers' cognition and mental workload by detecting the changes of brain activity potential. The mental workload of pilots in aviation flight is closely related to the characteristics of flight tasks. The previous methods have problems such as lack of objectivity, low EEG analysis ability and lack of real-time analysis ability. In order to solve these problems, this paper proposes a multi-dimensional data fusion brain workload calculation method based on flight effect evaluation, which integrates vision, operational behavior and visual gaze, and classifies and analyzes them in combination with EEG data. This method evaluates the mental workload of pilots from three aspects: visual gaze behavior, control behavior and flight effect in the simulated flight experimental environment, and realizes a more objective mental workload analysis. Then, the synchronously collected EEG data are segmented and sampled to form a dataset, and an LSTM neural network model integrating attention mechanism is established, in which the attention mechanism is used to improve the feature processing ability of the network model for the classification of complex EEG data. After machine learning training, the final model can achieve 94% detection accuracy for 2-s EEG data, and has the ability of real-time analysis in the application environment. Compared with the previous similar LSTM model, the accuracy is improved by 6%, which also shows the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving high classification performance are gaining momentum. Spiking neural P systems (SN P systems) are a class of membrane computing models and third-generation neural networks that are based on the behavior of biological neural cells and have been used in various engineering applications. Furthermore, SN P systems are characterized by a highly flexible structure that enables the design of a machine learning algorithm by mimicking the structure and behavior of biological cells without the over-simplification present in neural networks. Based on this aspect, this paper proposes a novel type of SN P system, namely, layered SN P system (LSN P system), to solve classification problems by supervised learning. The proposed LSN P system consists of a multi-layer network containing multiple weighted fuzzy SN P systems with adaptive weight adjustment rules. The proposed system employs specific ascending dimension techniques and a selection method of output neurons for classification problems. The experimental results obtained using benchmark datasets from the UCI machine learning repository and MNIST dataset demonstrated the feasibility and effectiveness of the proposed LSN P system. More importantly, the proposed LSN P system presents the first SN P system that demonstrates sufficient performance for use in addressing real-world classification problems. [ABSTRACT FROM AUTHOR]

Nitrosamine is a carcinogenic chemical used as a preservative in red meat whose identification is an ordeal. This paper presents a computer vision-based non-destructive method for identifying quality disparities between preservative treated and untreated (control) red meat. To access the discrepancy in the quality of red meat, both traditional machine learning and deep learning-based methods have been used. Support vector machine (SVM) classifier and artificial neural network (ANN) models have been used to detect the presence of nitrosamine in test samples. The paper also made use of different pre-trained deep convolutional neural networks (DCNN) with transfer learning approach such as ResNet-34, ResNet-50, ResNet-101, VGG-16, VGG-19, AlexNet and MobileNetv2 to examine the presence of nitrosamine in the food samples. While the ANN classifier performed better in comparison to the SVM classifier, the highest testing accuracy and F1-score were obtained using the deep learning model, ResNet-101 with 95.45% and 96.54%, respectively. The experimental results demonstrate an improved performance in comparison to the existing methods; indicating the feasibility of the proposed work for food quality control in real-time applications. [ABSTRACT FROM AUTHOR]

Real-time detection of possible deforestation of urban landscapes is an essential task for many urban forest monitoring services. Computational methods emerge as a rapid and efficient solution to evaluate bird's-eye-view images taken by satellites, drones, or even street-view photos captured at the ground level of the urban scenery. Identifying unhealthy trees requires detecting the tree itself and its constituent parts to evaluate certain aspects that may indicate unhealthiness, being street-level images a cost-effective and feasible resource to support the fieldwork survey. This paper proposes detecting trees and their specific parts on street-view images through a Convolutional Neural Network model based on the well-known You Only Look Once network with a MobileNet as the backbone for feature extraction. Essentially, from a photo taken from the ground, the proposed method identifies trees, isolates them through their bounding boxes, identifies the crown and stem, and then estimates the height of the trees by using a specific handheld object as a reference in the images. Experiment results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In contrast to the previous artificial neural networks (ANNs), spiking neural networks (SNNs) work based on temporal coding approaches. In the proposed SNN, the number of neurons, neuron models, encoding method, and learning algorithm design are described in a correct and pellucid fashion. It is also discussed that optimizing the SNN parameters based on physiology, and maximizing the information they pass leads to a more robust network. In this paper, inspired by the "center-surround" structure of the receptive fields in the retina, and the amount of overlap that they have, a robust SNN is implemented. It is based on the Integrate-and-Fire (IF) neuron model and uses the time-to-first-spike coding to train the network by a newly proposed method. The Iris and MNIST datasets were employed to evaluate the performance of the proposed network whose accuracy, with 60 input neurons, was 96.33% on the Iris dataset. The network was trained in only 45 iterations indicating its reasonable convergence rate. For the MNIST dataset, when the gray level of each pixel was considered as input to the network, 600 input neurons were required, and the accuracy of the network was 90.5%. Next, 14 structural features were used as input. Therefore, the number of input neurons decreased to 210, and accuracy increased up to 95%, meaning that an SNN with fewer input neurons and good skill was implemented. Also, the ABIDE1 dataset is applied to the proposed SNN. Of the 184 data, 79 are used for healthy people and 105 for people with autism. One of the characteristics that can differentiate between these two classes is the entropy of the existing data. Therefore, Shannon entropy is used for feature extraction. Applying these values to the proposed SNN, an accuracy of 84.42% was achieved by only 120 iterations, which is a good result compared to the recent results. [ABSTRACT FROM AUTHOR]

Deep learning algorithms have shown superior performance than traditional algorithms when dealing with computationally intensive tasks in many fields. The algorithm model based on deep learning has good performance and can improve the recognition accuracy in relevant applications in the field of computer vision. TensorFlow is a flexible opensource machine learning platform proposed by Google, which can run on a variety of platforms, such as CPU, GPU, and mobile devices. TensorFlow platform can also support current popular deep learning models. In this paper, an image recognition toolkit based on TensorFlow is designed and developed to simplify the development process of more and more image recognition applications. The toolkit uses convolutional neural networks to build a training model, which consists of two convolutional layers: one batch normalization layer before each convolutional layer, and the other pooling layer after each convolutional layer. The last two layers of the model use the full connection layer to output recognition results. Batch gradient descent algorithm is adopted in the optimization algorithm, and it integrates the advantages of both the gradient descent algorithm and the stochastic gradient descent algorithm, which greatly reduces the number of convergence iterations and has little influence on the convergence effect. The total training parameters of the toolkit model reach 1.7 million. In order to prevent overfitting problems, the dropout layer before each full connection layer is added and the threshold of 0.5 is set in the design. The convolution neural network model is trained and tested by the MNIST set on TensorFlow. The experimental result shows that the toolkit achieves the recognition accuracy of 99% on the MNIST test set. The development of the toolkit provides powerful technical support for the development of various image recognition applications, reduces its difficulty, and improves the efficiency of resource utilization. [ABSTRACT FROM AUTHOR]

The 3D measurement system based on line-structured light uses a camera to capture laser stripes due to changing in the shape of an object, and uses the acquired pixel coordinates for 3D reconstruction. System calibration is an important step in 3D measurement. The current camera calibration algorithm research mainly focuses on improving the algorithm itself, and there is less research on the influence of external factors. This paper proposes a coplanar hybrid calibration algorithm based on the error screening model by combining the error screening model, mathematical model and neural network model. It is mainly divided into two steps. The first step is to use the radial array constraint calibration algorithm based on the error screening model to solve the camera's internal and external parameters. The second step uses the camera internal and external parameters obtained in the first step to convert the pixel coordinates into real three-dimensional coordinates, and compares the calculated three-dimensional coordinates with the actual coordinates. Using machine learning to establish a compensation network, get a compensation function, and use the resulting 3D world coordinates to perform point cloud stitching. Experiments show that compared with the traditional calibration algorithm, the calibration algorithm has a small error and reduces the calibration error by about 6.5%. [ABSTRACT FROM AUTHOR]

With the outstanding performance in 2014 at the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14), an effective convolutional neural network (CNN) model named GoogLeNet has drawn the attention of the mainstream machine learning field. In this paper we plan to take an insight into the application of the GoogLeNet in the Handwritten Chinese Character Recognition (HCCR) on the database HCL2000 and CASIA-HWDB with several necessary adjustments and also state-of-the-art improvement methods for this end-to-end approach. Through the experiments we have found that the application of the GoogLeNet for the Handwritten Chinese Character Recognition (HCCR) results into significant high accuracy, to be specific more than 99% for the final version, which is encouraging for us to further research. [ABSTRACT FROM AUTHOR]

The lack of research on the metering characteristics of electricity power meters under complex conditions is a major obstacle to the on-site verification of electrical energy metering equipment. Establishing a predictive model for electricity power meter errors offers an effective way of dealing with this issue. Deep learning has been proven to have the capacity to reduce end-to-end dimensionality and improve recognition. Through the analysis of the back propagation process in residual networks, an improved residual network is set out in this paper. While preserving the advantages of residual network gradient propagation, it adds an adjustable shortcut and designs a convex k -parameter strategy that can be improved according to different processing objects. Experimental results show that the predicted errors produced by the proposed technique are significantly lower than in a comparable model. At the same time, the improved residual network does not increase the network's complexity. [ABSTRACT FROM AUTHOR]

At present, the application of deep learning algorithms in two-dimensional color image detection is being continuously innovated and broken. With the popularity of depth cameras, color image detection methods with depth information need to be upgraded. To solve this problem, a multi-target detection algorithm based on 3D DSF R-CNN (Double Stream Faster R-CNN, Convolution Neural Network based on Candidate Region) is proposed in this paper. The RGB information and the depth information of the image are given to two input elements of the convolution network with the same structure and weight sharing, and an optimal fusion weight algorithm is used to determine the weight of the fusion target in accordance with the recognition accuracy of the recognition targets under the single modal information, so as to ensure the most efficient fusion result. After several convolution operations, the independent features are extracted and the two networks are fused according to the optimal weights in the convolution layer. With the conducting of convolution and extract the fused features, and finally get the output through the full link layer. Compared with the previous two-dimensional convolution network algorithm, this algorithm improves the detection rate and success rate while ensuring the detection time. The experimental result shows that this method has strong robustness for complex illumination and partial occlusion, and has excellent detection results under non-restrictive conditions. [ABSTRACT FROM AUTHOR]

In this paper, we investigated the customer churn prediction problem in the Internet funds industry. We designed a novel feature embedded convolutional neural networks (FE-CNN) method that can automatically learn features from both the dynamic customer behavioral data and static customer demographic data and can utilize the advantage of convolutional neural networks to automatically learn features that capture the structured information. Our results show that our FE-CNN model outperforms the other traditional machine learning models with hand-crafted features, such as logistic regression (LR), support vector machines (SVM), random forests (RF) and neural networks (NN) in terms of accuracy, area under the receiver operating characteristics curve (AUC) and top-decile lift. Furthermore, we found that after adding the demographic data feature to the basic CNN model, the performance of the FE-CNN model improved. Overall, we found that the FE-CNN is the most powerful way to solve the problem of customer churn prediction in the Internet funds industry. Our FE-CNN method can also be applied to other fields that have both dynamic data and static data. [ABSTRACT FROM AUTHOR]

This paper intends to propose an integrated hybrid algorithm for training radial basis function neural network (RBFNN) learning. The proposed integrated of particle swarm and genetic algorithm based optimization (IPGO) algorithm is composed of two approaches based on particle swarm optimization (PSO) and genetic algorithm (GA) for gathering both their virtues to improve the learning performance of RBFNN. The diversity of individuals results in higher chance to search in the direction of global optimal instead of being confined to local optimal particularly in problem with higher complexity. The IPGO algorithm with PSO-based and GA-based approaches has shown promising results in some benchmark problems with three continuous test functions. After proposing the algorithm for these problems with result providing its outperforming performance, this paper supplements a practical application case for the papaya milk sales forecasting to expound the superiority of the IPGO algorithm. In addition, model evaluation results of the case have showed that the IPGO algorithm outperforms other algorithms and auto-regressive moving average (ARMA) models in terms of forecasting accuracy and execution time. [ABSTRACT FROM AUTHOR]

Data stream learning in non-stationary environments and skewed class distributions has been receiving more attention in machine learning communities. This paper proposes a novel ensemble classification method (ECSDS) for classifying data streams with skewed class distributions. In the proposed ensemble method, back-propagation neural network is selected as the base classifier. In order to demonstrate the effectiveness of our proposed method, we choose three baseline methods based on ECSDS and evaluate their overall performance on ten datasets from UCI machine learning repository. Moreover, the performance of incremental learning is also evaluated by these datasets. The experimental results show our proposed method can effectively deal with classification problems on non-stationary data streams with class imbalance. [ABSTRACT FROM AUTHOR]

Radial basis function (RBF) is combined with fuzzy C-means algorithms and its learning process made by projection-based learning (PBL) has been proposed in this paper, which is pointed out as PBL-fuzzy radial basis function (PBL-FRBF). The proposed method PBL-FRBF is producing good performances by selecting appropriate center and its width in order to achieve it by unsupervised classification algorithms instead of random selection. The PBL decreases the learning time, finds optimum output weight by its energy function and prefers smallest amount of samples for testing. Performance analysis is evaluated by benchmark datasets for classification problem taken from the UCI machine learning repository. The performance of the proposed PBL-FRBF has produced superior results when compared with FRBF and RBF for classification problems. [ABSTRACT FROM AUTHOR]

Multi-Instance Multi-Label learning (MIML) is a popular framework for supervised classification where an example is described by multiple instances and associated with multiple labels. Previous MIML approaches have focused on predicting labels for instances. The idea of tackling the problem is to identify its equivalence in the traditional supervised learning framework. Motivated by the recent advancement in deep learning, in this paper, we still consider the problem of predicting labels and attempt to model deep learning in MIML learning framework. The proposed approach enables us to train deep convolutional neural network with images from social networks where images are well labeled, even labeled with several labels or uncorrelated labels. Experiments on real-world datasets demonstrate the effectiveness of our proposed approach. [ABSTRACT FROM AUTHOR]

With the development of intelligent computation technology, the intelligent evolution algorithms have been widely applied to solve optimization problem in the real world. As a novel evolution algorithm, fruit fly optimization algorithm (FOA) has the advantages of simple operation and high efficiency. However, FOA also has some disadvantages, such as trapping into local optimal solution easily, failing to traverse the problem domain and limiting the universality. In order to cope with the disadvantages of FOA while retain it merits, this paper proposes AFOA, an adaptive fruit fly optimization algorithm. AFOA adjusts the swarm range parameter V dynamically and adaptively according to the historical memory of each iteration of the swarm, and adopts the more accurate elitist strategy, which is therefore very effective in both accelerating the convergence of the swarm to the global optimal front and maintaining diversity of the solutions. The convergence of the algorithm is firstly analyzed theoretically, and then 14 benchmark functions with different characteristics are executed to compare the performance among AFOA, PSO, FOA, and LGMS-FOA. The experimental results have shown that, AFOA algorithm is a new algorithm with global optimizing capability and high universality. [ABSTRACT FROM AUTHOR]

Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However, the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this paper, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on five classification problems achieving significantly better results than ANGN and competitive results with ANN approaches. [ABSTRACT FROM AUTHOR]

This paper proposes universal coarse-grained reconfigurable computing architecture for hardware implementation of decision trees (DTs), artificial neural networks (ANNs), and support vector machines (SVMs), suitable for both field programmable gate arrays (FPGA) and application specific integrated circuits (ASICs) implementation. Using this universal architecture, two versions of DTs (functional DT and axis-parallel DT), two versions of SVMs (with polynomial and radial kernel) and two versions of ANNs (multi layer perceptron ANN and radial basis ANN) machine learning classifiers, have been implemented in FPGA. Experimental results, based on 18 benchmark datasets of standard UCI machine learning repository database, show that FPGA implementation provides significant improvement (1-2 orders of magnitude) in the average instance classification time, in comparison with software implementations based on R project. [ABSTRACT FROM AUTHOR]

Feature ordering is a significant data preprocessing method in incremental attribute learning (IAL), where features are gradually trained according to a given order. Previous research showed feature ordering is crucial to the IAL performance. It is relevant to each feature's discrimination ability, which can be calculated by single discriminability (SD). However, when feature dimensions increase, feature discrimination ability should also be calculated incrementally, because discrimination ability in lower dimensional spaces is different from that in higher spaces. Thus based on SD, accumulative discriminability (AD), a new statistical metric for incremental feature discrimination ability estimation, is designed. Moreover, a criterion that summarizes all the produced values of AD is employed to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. In addition, in order to reduce the time consumption, an effective feature ordering approach is developed. Compared with the feature ordering obtained by other approaches, the method outlined in this paper obtained good final classification results, which indicates that, firstly, feature discrimination ability should be incrementally estimated in IAL; and secondly, feature ordering derived by AD and its corresponding approaches are applicable with IAL. [ABSTRACT FROM AUTHOR]

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA. [ABSTRACT FROM AUTHOR]