Geometric prior guided hybrid deep neural network for facial beauty analysis

Facial beauty analysis is an important topic in human society.It may be used as a guidance for face beautification applications such as cosmetic surgery.Deep neural networks(DNNs)have recently been adopted for facial beauty analysis and have achieved remarkable performance.However,most existing DNN-based models regard facial beauty analysis as a normal classification task.They ignore important prior knowledge in traditional machine learning models which illustrate the significant contribution of the geometric features in facial beauty analysis.To be specific,landmarks of the whole face and facial organs are introduced to extract geometric features to make the decision.Inspired by this,we introduce a novel dual-branch network for facial beauty analysis:one branch takes the Swin Transformer as the backbone to model the full face and global patterns,and another branch focuses on the masked facial organs with the residual network to model the local patterns of certain facial parts.Additionally,the designed multi-scale feature fusion module can further facilitate our network to learn complementary semantic information between the two branches.In model optimisation,we propose a hybrid loss function,where especially geometric regulation is introduced by regressing the facial landmarks and it can force the extracted features to convey facial geometric features.Experiments performed on the SCUT-FBP5500 dataset and the SCUT-FBP dataset demonstrate that our model outperforms the state-of-the-art convolutional neural networks models,which proves the effectiveness of the proposed geometric regularisation and dual-branch structure with the hybrid network.To the best of our knowledge,this is the first study to introduce a Vision Transformer into the facial beauty analysis task.

Using deep neural networks coupled with principal component analysis for ore production forecasting at open-pit mines

Ore production is usually affected by multiple influencing inputs at open-pit mines.Nevertheless,the complex nonlinear relationships between these inputs and ore production remain unclear.This becomes even more challenging when training data(e.g.truck haulage information and weather conditions)are massive.In machine learning(ML)algorithms,deep neural network(DNN)is a superior method for processing nonlinear and massive data by adjusting the amount of neurons and hidden layers.This study adopted DNN to forecast ore production using truck haulage information and weather conditions at open-pit mines as training data.Before the prediction models were built,principal component analysis(PCA)was employed to reduce the data dimensionality and eliminate the multicollinearity among highly correlated input variables.To verify the superiority of DNN,three ANNs containing only one hidden layer and six traditional ML models were established as benchmark models.The DNN model with multiple hidden layers performed better than the ANN models with a single hidden layer.The DNN model outperformed the extensively applied benchmark models in predicting ore production.This can provide engineers and researchers with an accurate method to forecast ore production,which helps make sound budgetary decisions and mine planning at open-pit mines.

Big Model Strategy for Bridge Structural Health Monitoring Based on Data-Driven, Adaptive Method and Convolutional Neural Network (CNN) Group

This study introduces an innovative“Big Model”strategy to enhance Bridge Structural Health Monitoring(SHM)using a Convolutional Neural Network(CNN),time-frequency analysis,and fine element analysis.Leveraging ensemble methods,collaborative learning,and distributed computing,the approach effectively manages the complexity and scale of large-scale bridge data.The CNN employs transfer learning,fine-tuning,and continuous monitoring to optimize models for adaptive and accurate structural health assessments,focusing on extracting meaningful features through time-frequency analysis.By integrating Finite Element Analysis,time-frequency analysis,and CNNs,the strategy provides a comprehensive understanding of bridge health.Utilizing diverse sensor data,sophisticated feature extraction,and advanced CNN architecture,the model is optimized through rigorous preprocessing and hyperparameter tuning.This approach significantly enhances the ability to make accurate predictions,monitor structural health,and support proactive maintenance practices,thereby ensuring the safety and longevity of critical infrastructure.

Application of Bayesian Analysis Based on Neural Network and Deep Learning in Data Visualization

This study aims to explore the application of Bayesian analysis based on neural networks and deep learning in data visualization.The research background is that with the increasing amount and complexity of data,traditional data analysis methods have been unable to meet the needs.Research methods include building neural networks and deep learning models,optimizing and improving them through Bayesian analysis,and applying them to the visualization of large-scale data sets.The results show that the neural network combined with Bayesian analysis and deep learning method can effectively improve the accuracy and efficiency of data visualization,and enhance the intuitiveness and depth of data interpretation.The significance of the research is that it provides a new solution for data visualization in the big data environment and helps to further promote the development and application of data science.

NeurstrucEnergy:A bi-directional GNN model for energy prediction of neural networks in IoT

A significant demand rises for energy-efficient deep neural networks to support power-limited embedding devices with successful deep learning applications in IoT and edge computing fields.An accurate energy prediction approach is critical to provide measurement and lead optimization direction.However,the current energy prediction approaches lack accuracy and generalization ability due to the lack of research on the neural network structure and the excessive reliance on customized training dataset.This paper presents a novel energy prediction model,NeurstrucEnergy.NeurstrucEnergy treats neural networks as directed graphs and applies a bi-directional graph neural network training on a randomly generated dataset to extract structural features for energy prediction.NeurstrucEnergy has advantages over linear approaches because the bi-directional graph neural network collects structural features from each layer's parents and children.Experimental results show that NeurstrucEnergy establishes state-of-the-art results with mean absolute percentage error of 2.60%.We also evaluate NeurstrucEnergy in a randomly generated dataset,achieving the mean absolute percentage error of 4.83%over 10 typical convolutional neural networks in recent years and 7 efficient convolutional neural networks created by neural architecture search.Our code is available at https://github.com/NEUSoftGreenAI/NeurstrucEnergy.git.

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network

The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.

Intelligent geochemical interpretation of mass chromatograms:Based on convolution neural network

Gas chromatography-mass spectrometry(GC-MS)is an extremely important analytical technique that is widely used in organic geochemistry.It is the only approach to capture biomarker features of organic matter and provides the key evidence for oil-source correlation and thermal maturity determination.However,the conventional way of processing and interpreting the mass chromatogram is both timeconsuming and labor-intensive,which increases the research cost and restrains extensive applications of this method.To overcome this limitation,a correlation model is developed based on the convolution neural network(CNN)to link the mass chromatogram and biomarker features of samples from the Triassic Yanchang Formation,Ordos Basin,China.In this way,the mass chromatogram can be automatically interpreted.This research first performs dimensionality reduction for 15 biomarker parameters via the factor analysis and then quantifies the biomarker features using two indexes(i.e.MI and PMI)that represent the organic matter thermal maturity and parent material type,respectively.Subsequently,training,interpretation,and validation are performed multiple times using different CNN models to optimize the model structure and hyper-parameter setting,with the mass chromatogram used as the input and the obtained MI and PMI values for supervision(label).The optimized model presents high accuracy in automatically interpreting the mass chromatogram,with R2values typically above 0.85 and0.80 for the thermal maturity and parent material interpretation results,respectively.The significance of this research is twofold:(i)developing an efficient technique for geochemical research;(ii)more importantly,demonstrating the potential of artificial intelligence in organic geochemistry and providing vital references for future related studies.

Multi-Material Topology Optimization of 2D Structures Using Convolutional Neural Networks

In recent years,there has been significant research on the application of deep learning(DL)in topology optimization(TO)to accelerate structural design.However,these methods have primarily focused on solving binary TO problems,and effective solutions for multi-material topology optimization(MMTO)which requires a lot of computing resources are still lacking.Therefore,this paper proposes the framework of multiphase topology optimization using deep learning to accelerate MMTO design.The framework employs convolutional neural network(CNN)to construct a surrogate model for solving MMTO,and the obtained surrogate model can rapidly generate multi-material structure topologies in negligible time without any iterations.The performance evaluation results show that the proposed method not only outputs multi-material topologies with clear material boundary but also reduces the calculation cost with high prediction accuracy.Additionally,in order to find a more reasonable modeling method for MMTO,this paper studies the characteristics of surrogate modeling as regression task and classification task.Through the training of 297 models,our findings show that the regression task yields slightly better results than the classification task in most cases.Furthermore,The results indicate that the prediction accuracy is primarily influenced by factors such as the TO problem,material category,and data scale.Conversely,factors such as the domain size and the material property have minimal impact on the accuracy.

Mixed-decomposed convolutional network:A lightweight yet efficient convolutional neural network for ocular disease recognition

Eye health has become a global health concern and attracted broad attention.Over the years,researchers have proposed many state-of-the-art convolutional neural networks(CNNs)to assist ophthalmologists in diagnosing ocular diseases efficiently and precisely.However,most existing methods were dedicated to constructing sophisticated CNNs,inevitably ignoring the trade-off between performance and model complexity.To alleviate this paradox,this paper proposes a lightweight yet efficient network architecture,mixeddecomposed convolutional network(MDNet),to recognise ocular diseases.In MDNet,we introduce a novel mixed-decomposed depthwise convolution method,which takes advantage of depthwise convolution and depthwise dilated convolution operations to capture low-resolution and high-resolution patterns by using fewer computations and fewer parameters.We conduct extensive experiments on the clinical anterior segment optical coherence tomography(AS-OCT),LAG,University of California San Diego,and CIFAR-100 datasets.The results show our MDNet achieves a better trade-off between the performance and model complexity than efficient CNNs including MobileNets and MixNets.Specifically,our MDNet outperforms MobileNets by 2.5%of accuracy by using 22%fewer parameters and 30%fewer computations on the AS-OCT dataset.

Automated Machine Learning Algorithm Using Recurrent Neural Network to Perform Long-Term Time Series Forecasting

Long-term time series forecasting stands as a crucial research domain within the realm of automated machine learning(AutoML).At present,forecasting,whether rooted in machine learning or statistical learning,typically relies on expert input and necessitates substantial manual involvement.This manual effort spans model development,feature engineering,hyper-parameter tuning,and the intricate construction of time series models.The complexity of these tasks renders complete automation unfeasible,as they inherently demand human intervention at multiple junctures.To surmount these challenges,this article proposes leveraging Long Short-Term Memory,which is the variant of Recurrent Neural Networks,harnessing memory cells and gating mechanisms to facilitate long-term time series prediction.However,forecasting accuracy by particular neural network and traditional models can degrade significantly,when addressing long-term time-series tasks.Therefore,our research demonstrates that this innovative approach outperforms the traditional Autoregressive Integrated Moving Average(ARIMA)method in forecasting long-term univariate time series.ARIMA is a high-quality and competitive model in time series prediction,and yet it requires significant preprocessing efforts.Using multiple accuracy metrics,we have evaluated both ARIMA and proposed method on the simulated time-series data and real data in both short and long term.Furthermore,our findings indicate its superiority over alternative network architectures,including Fully Connected Neural Networks,Convolutional Neural Networks,and Nonpooling Convolutional Neural Networks.Our AutoML approach enables non-professional to attain highly accurate and effective time series forecasting,and can be widely applied to various domains,particularly in business and finance.

Alternative Method of Constructing Granular Neural Networks

Utilizing granular computing to enhance artificial neural network architecture, a newtype of network emerges—thegranular neural network (GNN). GNNs offer distinct advantages over their traditional counterparts: The ability toprocess both numerical and granular data, leading to improved interpretability. This paper proposes a novel designmethod for constructing GNNs, drawing inspiration from existing interval-valued neural networks built uponNNNs. However, unlike the proposed algorithm in this work, which employs interval values or triangular fuzzynumbers for connections, existing methods rely on a pre-defined numerical network. This new method utilizesa uniform distribution of information granularity to granulate connections with unknown parameters, resultingin independent GNN structures. To quantify the granularity output of the network, the product of two commonperformance indices is adopted: The coverage of numerical data and the specificity of information granules.Optimizing this combined performance index helps determine the optimal parameters for the network. Finally,the paper presents the complete model construction and validates its feasibility through experiments on datasetsfrom the UCIMachine Learning Repository. The results demonstrate the proposed algorithm’s effectiveness andpromising performance.

HVAC Optimal Control Based on the Sensitivity Analysis:An Improved SA Combination Method Based on a Neural Network

Aiming at optimizing the energy consumption of HVAC,an energy conservation optimization method was proposed for HVAC systems based on the sensitivity analysis(SA),named the sensitivity analysis combination method(SAC).Based on the SA,neural network and the related settings about energy conservation of HVAC systems,such as cooling water temperature,chilled water temperature and supply air temperature,were optimized.Moreover,based on the data of the existing HVAC system,various optimal control methods ofHVAC systems were tested and evaluated by a simulated HVAC system in TRNSYS.The results show that the proposed SA combination method can reduce significant computational load while maintaining an equivalent energy performance compared with traditional optimal control methods.

Structural Damage Identification Using Ensemble Deep Convolutional Neural Network Models

The existing strategy for evaluating the damage condition of structures mostly focuses on feedback supplied by traditional visualmethods,which may result in an unreliable damage characterization due to inspector subjectivity or insufficient level of expertise.As a result,a robust,reliable,and repeatable method of damage identification is required.Ensemble learning algorithms for identifying structural damage are evaluated in this article,which use deep convolutional neural networks,including simple averaging,integrated stacking,separate stacking,and hybridweighted averaging ensemble and differential evolution(WAE-DE)ensemblemodels.Damage identification is carried out on three types of damage.The proposed algorithms are used to analyze the damage of 4585 structural images.The effectiveness of the ensemble learning techniques is evaluated using the confusion matrix.For the testing dataset,the confusion matrix achieved an accuracy of 94 percent and a minimum recall of 92 percent for the best model(WAE-DE)in distinguishing damage types as flexural,shear,combined,or undamaged.

Influencing factor analysis of interception probability and classification-regression neural network based estimation

The interception probability of a single missile is the basis for combat plan design and weapon performance evaluation,while its influencing factors are complex and mutually coupled.Existing calculation methods have very limited analysis of the influence mechanism of influencing factors,and none of them has analyzed the influence of the guidance law.This paper considers the influencing factors of both the interceptor and the target more comprehensively.Interceptor parameters include speed,guidance law,guidance error,fuze error,and fragment killing ability,while target performance includes speed,maneuverability,and vulnerability.In this paper,an interception model is established,Monte Carlo simulation is carried out,and the influence mechanism of each factor is analyzed based on the model and simulation results.Finally,this paper proposes a classification-regression neural network to quickly estimate the interception probability based on the value of influencing factors.The proposed method reduces the interference of invalid interception data to valid data,so its prediction accuracy is significantly better than that of pure regression neural networks.

Serum Sodium Fluctuation Prediction among ICU Patients Using Neural Network Algorithm:Analysis of the MIMIC-IV Database

Sodium homeostasis disorder is one of the most common abnormal symptoms of elderly patients in intensive care unit(ICU),which may lead to physiological disorders of many organs.The current prediction of serum sodium in ICU is mainly based on the subjective judgment of doctors’experience.This study aims at this problem by studying the clinical retrospective electronic medical record data of ICU to establish a machine learning model to predict the short-term serum sodium value of ICU patients.The data set used in this study is the open-source intensive care medical information set Medical Information Mart for Intensive Care(MIMIC)-IV.The time point of serum sodium detection was selected from the ICU clinical records,and the ICU records of 25risk factors related to serum sodium were extracted from the patients within the first 12 h for statistical analysis.A prediction model of serum sodium value within 48 h was established using a feedforward neural network,and compared with previous methods.Our research results show that the neural network learning model can predict the development of serum sodium in patients using physiological indicators recorded in clinical electronic medical records within 12 h,and has better prediction effect than the serum sodium formula and other machine learning models.

Structural reliability analysis using enhanced cuckoo search algorithm and artificial neural network

The present study proposed an enhanced cuckoo search(ECS) algorithm combined with artificial neural network(ANN) as the surrogate model to solve structural reliability problems. In order to enhance the accuracy and convergence rate of the original cuckoo search(CS) algorithm, the main parameters namely, abandon probability of worst nests paand search step sizeα0 are dynamically adjusted via nonlinear control equations. In addition, a global-best guided equation incorporating the information of global best nest is introduced to the ECS to enhance its exploitation. Then, the proposed ECS is linked to the well-trained ANN model for structural reliability analysis. The computational capability of the proposed algorithm is validated using five typical structural reliability problems and an engineering application. The comparison results show the efficiency and accuracy of the proposed algorithm.

Structural Reliability Analysis Based on Support Vector Machine and Dual Neural Network Direct Integration Method

Aiming at the reliability analysis of small sample data or implicit structural function,a novel structural reliability analysis model based on support vector machine(SVM)and neural network direct integration method(DNN)is proposed.Firstly,SVM with good small sample learning ability is used to train small sample data,fit structural performance functions and establish regular integration regions.Secondly,DNN is approximated the integral function to achieve multiple integration in the integration region.Finally,structural reliability was obtained by DNN.Numerical examples are investigated to demonstrate the effectiveness of the present method,which provides a feasible way for the structural reliability analysis.

Application of neural network merging model in dam deformation analysis

In order to improve the prediction accuracy and test the generalization ability of the dam deformation analysis model, the back-propagation（BP） neural network model for dam deformation analysis is studied, and the merging model is built based on the neural network BP algorithm and the traditional statistical model. The three models mentioned above are calculated and analyzed according to the long-term deformation observation data in Chencun Dam. The analytical results show that the average prediction accuracies of the statistical model and the BP neural network model are ~ 0.477 and ＋- 0.390 mm, respectively, while the prediction accuracy of the merging model is ~0. 318 mm, which is improved by 33% and 18% compared to the other two models, respectively. And the merging model has a better generalization ability and broad applicability.

Numerical‐discrete‐scheme‐incorporated recurrent neural network for tasks in natural language processing

A variety of neural networks have been presented to deal with issues in deep learning in the last decades.Despite the prominent success achieved by the neural network,it still lacks theoretical guidance to design an efficient neural network model,and verifying the performance of a model needs excessive resources.Previous research studies have demonstrated that many existing models can be regarded as different numerical discretizations of differential equations.This connection sheds light on designing an effective recurrent neural network(RNN)by resorting to numerical analysis.Simple RNN is regarded as a discretisation of the forward Euler scheme.Considering the limited solution accuracy of the forward Euler methods,a Taylor‐type discrete scheme is presented with lower truncation error and a Taylor‐type RNN(T‐RNN)is designed with its guidance.Extensive experiments are conducted to evaluate its performance on statistical language models and emotion analysis tasks.The noticeable gains obtained by T‐RNN present its superiority and the feasibility of designing the neural network model using numerical methods.