Multi-Head Attention Spatial-Temporal Graph Neural Networks for Traffic Forecasting

Accurate traffic prediction is crucial for an intelligent traffic system (ITS). However, the excessive non-linearity and complexity of the spatial-temporal correlation in traffic flow severely limit the prediction accuracy of most existing models, which simply stack temporal and spatial modules and fail to capture spatial-temporal features effectively. To improve the prediction accuracy, a multi-head attention spatial-temporal graph neural network (MSTNet) is proposed in this paper. First, the traffic data is decomposed into unique time spans that conform to positive rules, and valuable traffic node attributes are mined through an adaptive graph structure. Second, time and spatial features are captured using a multi-head attention spatial-temporal module. Finally, a multi-step prediction module is used to achieve future traffic condition prediction. Numerical experiments were conducted on an open-source dataset, and the results demonstrate that MSTNet performs well in spatial-temporal feature extraction and achieves more positive forecasting results than the baseline methods.

A Lightweight Convolutional Neural Network with Hierarchical Multi-Scale Feature Fusion for Image Classification

Convolutional neural networks (CNNs) are widely used in image classification tasks, but their increasing model size and computation make them challenging to implement on embedded systems with constrained hardware resources. To address this issue, the MobileNetV1 network was developed, which employs depthwise convolution to reduce network complexity. MobileNetV1 employs a stride of 2 in several convolutional layers to decrease the spatial resolution of feature maps, thereby lowering computational costs. However, this stride setting can lead to a loss of spatial information, particularly affecting the detection and representation of smaller objects or finer details in images. To maintain the trade-off between complexity and model performance, a lightweight convolutional neural network with hierarchical multi-scale feature fusion based on the MobileNetV1 network is proposed. The network consists of two main subnetworks. The first subnetwork uses a depthwise dilated separable convolution (DDSC) layer to learn imaging features with fewer parameters, which results in a lightweight and computationally inexpensive network. Furthermore, depthwise dilated convolution in DDSC layer effectively expands the field of view of filters, allowing them to incorporate a larger context. The second subnetwork is a hierarchical multi-scale feature fusion (HMFF) module that uses parallel multi-resolution branches architecture to process the input feature map in order to extract the multi-scale feature information of the input image. Experimental results on the CIFAR-10, Malaria, and KvasirV1 datasets demonstrate that the proposed method is efficient, reducing the network parameters and computational cost by 65.02% and 39.78%, respectively, while maintaining the network performance compared to the MobileNetV1 baseline.

A Kind of Second-Order Learning Algorithm Based on Generalized Cost Criteria in Multi-Layer Feed-Forward Neural Networks

A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than BP algorithm and the second order learning algorithm that was given by Karayiannis.

Learning Performance of Linear and Exponential Activity Function with Multi-layered Neural Networks

This paper presents a study on the improvement of MLNNs(multi-layer neural networks)performance by an activity function for multi logic training patterns.Our model network has L hidden layers of two inputs and three,four to six output training using BP(backpropagation)neural network.We used logic functions of XOR(exclusive OR),OR,AND,NAND(not AND),NXOR(not exclusive OR)and NOR(not OR)as the multi logic teacher signals to evaluate the training performance of MLNNs by an activity function for information and data enlargement in signal processing(synaptic divergence state).We specifically used four activity functions from which we modified one and called it L&exp.function as it could give the highest training abilities compared to the original activity functions of Sigmoid,ReLU and Step during simulation and training in the network.And finally,we propose L&exp.function as being good for MLNNs and it may be applicable for signal processing of data and information enlargement because of its performance training characteristics with multiple training logic patterns hence can be adopted in machine deep learning.

Pedestrian attribute classification with multi-scale and multi-label convolutional neural networks

Pedestrian attribute classification from a pedestrian image captured in surveillance scenarios is challenging due to diverse clothing appearances,varied poses and different camera views. A multiscale and multi-label convolutional neural network( MSMLCNN) is proposed to predict multiple pedestrian attributes simultaneously. The pedestrian attribute classification problem is firstly transformed into a multi-label problem including multiple binary attributes needed to be classified. Then,the multi-label problem is solved by fully connecting all binary attributes to multi-scale features with logistic regression functions. Moreover,the multi-scale features are obtained by concatenating those featured maps produced from multiple pooling layers of the MSMLCNN at different scales. Extensive experiment results show that the proposed MSMLCNN outperforms state-of-the-art pedestrian attribute classification methods with a large margin.

Exponential stability of cellular neural networks with multiple time delays and impulsive effects

In this work, the stability issues of the equilibrium points of the cellular neural networks with multiple time delays and impulsive effects are investigated. Based on the stability theory of Lyapunov-Krasovskii, the method of linear matrix inequality （LMI） and parametrized first-order model transformation, several novel conditions guaranteeing the delaydependent and the delay-independent exponential stabilities are obtained. A numerical example is given to illustrate the effectiveness of our results.

Hausdorff Dimension of Multi-Layer Neural Networks

This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.

Mean Field Annealing Neural Network for the Optimal DS/CDMA Multiuser Detector *

In this paper, an optimal multi user detector in DS/CDMA communication systems based on the mean field annealing (MFA) neural network is proposed. It is shown that the NP complete problem of minimizing the objective function of the optimal multi user detector can be translated into minimizing an MFA network energy function. Numerical results show that the proposed detector offers significant performance gain relative to the conventional detector and decorrelating detector while it can be implemented easily in analog hardware.

Performance Comparison of Neural Networks for HRTFs Approximation

In order to approach to head related transfer functions (HRTFs), this paper employs and compares three kinds of one input neural network models, namely, multi layer perceptron (MLP) networks, radial basis function (RBF) networks and wavelet neural networks (WNN) so as to select the best network model for further HRTFs approximation. Experimental results demonstrate that wavelet neural networks are more efficient and useful.

DCFNet:An Effective Dual-Branch Cross-Attention Fusion Network for Medical Image Segmentation

Automatic segmentation of medical images provides a reliable scientific basis for disease diagnosis and analysis.Notably,most existing methods that combine the strengths of convolutional neural networks(CNNs)and Transformers have made significant progress.However,there are some limitations in the current integration of CNN and Transformer technology in two key aspects.Firstly,most methods either overlook or fail to fully incorporate the complementary nature between local and global features.Secondly,the significance of integrating the multiscale encoder features from the dual-branch network to enhance the decoding features is often disregarded in methods that combine CNN and Transformer.To address this issue,we present a groundbreaking dual-branch cross-attention fusion network(DCFNet),which efficiently combines the power of Swin Transformer and CNN to generate complementary global and local features.We then designed the Feature Cross-Fusion(FCF)module to efficiently fuse local and global features.In the FCF,the utilization of the Channel-wise Cross-fusion Transformer(CCT)serves the purpose of aggregatingmulti-scale features,and the Feature FusionModule(FFM)is employed to effectively aggregate dual-branch prominent feature regions from the spatial perspective.Furthermore,within the decoding phase of the dual-branch network,our proposed Channel Attention Block(CAB)aims to emphasize the significance of the channel features between the up-sampled features and the features generated by the FCFmodule to enhance the details of the decoding.Experimental results demonstrate that DCFNet exhibits enhanced accuracy in segmentation performance.Compared to other state-of-the-art(SOTA)methods,our segmentation framework exhibits a superior level of competitiveness.DCFNet’s accurate segmentation of medical images can greatly assist medical professionals in making crucial diagnoses of lesion areas in advance.

Multi-Objective Optimization and Analysis Model of Sintering Process Based on BP Neural Network

A multi-objective optimization and analysis model of the sintering process based on BP neural network is presented. Genetic algorithms are combined to simplify the BP neural network, which can reduce the learning time and increase the forecasting accuracy of the network model. This model has been experimented in the sintering process, and the production cost, the energy consumption, the quality （revolving intensity）, and the output are considered at the same time. Moreover, the relation between some factors and the multi-objectives has been analyzed, and the results are consistent with the process. Different objectives are emphasized at different practical periods, and this can provide a theoretical basis for the manager.

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network

This paper proposes a co-evolutionary recurrent neural network （CERNN） for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets： the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.

Modelling and Multi-Objective Optimal Control of Batch Processes Using Recurrent Neuro-fuzzy Networks

In this paper, the modelling and multi-objective optimal control of batch processes, using a recurrent neuro-fuzzy network, are presented. The recurrent neuro-fuzzy network, forms a ＂global＂ nonlinear long-range prediction model through the fuzzy conjunction of a number of ＂local＂ linear dynamic models. Network output is fed back to network input through one or more time delay units, which ensure that predictions from the recurrent neuro-fuzzy network are long-range. In building a recurrent neural network model, process knowledge is used initially to partition the processes non-linear characteristics into several local operating regions, and to aid in the initialisation of corresponding network weights. Process operational data is then used to train the network. Membership functions of the local regimes are identified, and local models are discovered via network training. Based on a recurrent neuro-fuzzy network model, a multi-objective optimal control policy can be obtained. The proposed technique is applied to a fed-batch reactor.

Identification and Prediction of Internet Traffic Using Artificial Neural Networks

This paper presents the development of an artificial neural network (ANN) model based on the multi-layer perceptron (MLP) for analyzing internet traffic data over IP networks. We applied the ANN to analyze a time series of measured data for network response evaluation. For this reason, we used the input and output data of an internet traffic over IP networks to identify the ANN model, and we studied the performance of some training algorithms used to estimate the weights of the neuron. The comparison between some training algorithms demonstrates the efficiency and the accu-racy of the Levenberg-Marquardt (LM) and the Resilient back propagation (Rp) algorithms in term of statistical crite-ria. Consequently, the obtained results show that the developed models, using the LM and the Rp algorithms, can successfully be used for analyzing internet traffic over IP networks, and can be applied as an excellent and fundamental tool for the management of the internet traffic at different times.

Application of artificial neural networks for operating speed prediction at horizontal curves: a case study in Egypt

Horizontal alignment greatly affects the speedof vehicles at rural roads. Therefore, it is necessary toanalyze and predict vehicles speed on curve sections.Numerous studies took rural two-lane as research subjectsand provided models for predicting operating speeds.However, less attention has been paid to multi-lane highwaysespecially in Egypt. In this research, field operatingspeed data of both cars and trucks on 78 curve sections offour multi-lane highways is collected. With the data, correlationbetween operating speed （V85） and alignment isanalyzed. The paper includes two separate relevant analyses.The first analysis uses the regression models toinvestigate the relationships between V85 as dependentvariable, and horizontal alignment and roadway factors asindependent variables. This analysis proposes two predictingmodels for cars and trucks. The second analysisuses the artificial neural networks （ANNs） to explore theprevious relationships. It is found that the ANN modelinggives the best prediction model. The most influential variableon V85 for cars is the radius of curve. Also, for V85 fortrucks, the most influential variable is the median width.Finally, the derived models have statistics within theacceptable regions and they are conceptually reasonable.

Non-Minimum Phase Nonlinear System Predictive Control Based on Local Recurrent Neural Networks

After a recursive multi-step-ahead predictor for nonlinear systems based on local recurrent neural networks is introduced, an intelligent FID controller is adopted to correct the errors including identified model errors and accumulated errors produced in the recursive process. Characterized by predictive control, this method can achieve a good control accuracy and has good robustness. A simulation study shows that this control algorithm is very effective.

An Improved SPSA Algorithm for System Identification Using Fuzzy Rules for Training Neural Networks

Simultaneous perturbation stochastic approximation （SPSA） belongs to the class of gradient-free optimization methods that extract gradient information from successive objective function evaluation. This paper describes an improved SPSA algorithm, which entails fuzzy adaptive gain sequences, gradient smoothing, and a step rejection procedure to enhance convergence and stability. The proposed fuzzy adaptive simultaneous perturbation approximation （FASPA） algorithm is particularly well suited to problems involving a large number of parameters such as those encountered in nonlinear system identification using neural networks （NNs）. Accordingly, a multilayer perceptron （MLP） network with popular training algorithms was used to predicate the system response. We found that an MLP trained by FASPSA had the desired accuracy that was comparable to results obtained by traditional system identification algorithms. Simulation results for typical nonlinear systems demonstrate that the proposed NN architecture trained with FASPSA yields improved system identification as measured by reduced time of convergence and a smaller identification error.

Grid Side Distributed Energy Storage Cloud Group End Region Hierarchical Time-Sharing Configuration Algorithm Based onMulti-Scale and Multi Feature Convolution Neural Network

There is instability in the distributed energy storage cloud group end region on the power grid side.In order to avoid large-scale fluctuating charging and discharging in the power grid environment and make the capacitor components showa continuous and stable charging and discharging state,a hierarchical time-sharing configuration algorithm of distributed energy storage cloud group end region on the power grid side based on multi-scale and multi feature convolution neural network is proposed.Firstly,a voltage stability analysis model based onmulti-scale and multi feature convolution neural network is constructed,and the multi-scale and multi feature convolution neural network is optimized based on Self-OrganizingMaps(SOM)algorithm to analyze the voltage stability of the cloud group end region of distributed energy storage on the grid side under the framework of credibility.According to the optimal scheduling objectives and network size,the distributed robust optimal configuration control model is solved under the framework of coordinated optimal scheduling at multiple time scales;Finally,the time series characteristics of regional power grid load and distributed generation are analyzed.According to the regional hierarchical time-sharing configuration model of“cloud”,“group”and“end”layer,the grid side distributed energy storage cloud group end regional hierarchical time-sharing configuration algorithm is realized.The experimental results show that after applying this algorithm,the best grid side distributed energy storage configuration scheme can be determined,and the stability of grid side distributed energy storage cloud group end region layered timesharing configuration can be improved.

Neural Network Based Multi-level Fuzzy Evaluation Model for Mechanical Kinematic Scheme

To implement a quantificational evaluation for mechanical kinematic scheme more effectively,a multi-level and multi-objective evaluation model is presented using neural network and fuzzy theory. Firstly,the structure of evaluation model is constructed according to evaluation indicator system. Then evaluation samples are generated and provided to train this model. Thus it can reflect the relation between attributive value and evaluation result,as well as the weight of evaluation indicator. Once evaluation indicators of each candidate are fuzzily quantified and fed into the trained network model,the corresponding evaluation result is outputted and the best alternative can be selected. Under this model,expert knowledge can be effectively acquired and expressed,and the quantificational evaluation can be implemented for kinematic scheme with multi-level evaluation indicator system. Several key problems on this model are discussed and an illustration has demonstrated that this model is feasible and can be regarded as a new idea for solving kinematic scheme evaluation.

Double Glow Plasma Surface Alloying Process Modeling Using Artificial Neural Networks

A model is developed for predicting the correlation between processing parameters and the technical target of double glow by applying artificial neural network (ANN). The input parameters of the neural network (NN) are source voltage, workplace voltage, working pressure and distance between source electrode and workpiece. The output of the NN model is three important technical targets, namely the gross element content, the thickness of surface alloying layer and the absorption rate (the ratio of the mass loss of source materials to the increasing mass of workpiece) in the processing of double glow plasma surface alloying. The processing parameters and technical target are then used as a training set for an artificial neural network. The model is based on multiplayer feedforward neural network. A very good performance of the neural network is achieved and the calculated results are in good agreement with the experimental ones.