The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite ...The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite its widespread success,training MLPs often encounter significant challenges,including susceptibility to local optima,slow convergence rates,and high sensitivity to initial weight configurations.To address these issues,this paper proposes a Latin Hypercube Opposition-based Elite Variation Artificial Protozoa Optimizer(LOEV-APO),which enhances both global exploration and local exploitation simultaneously.LOEV-APO introduces a hybrid initialization strategy that combines Latin Hypercube Sampling(LHS)with Opposition-Based Learning(OBL),thus improving the diversity and coverage of the initial population.Moreover,an Elite Protozoa Variation Strategy(EPVS)is incorporated,which applies differential mutation operations to elite candidates,accelerating convergence and strengthening local search capabilities around high-quality solutions.Extensive experiments are conducted on six classification tasks and four function approximation tasks,covering a wide range of problem complexities and demonstrating superior generalization performance.The results demonstrate that LOEV-APO consistently outperforms nine state-of-the-art metaheuristic algorithms and two gradient-based methods in terms of convergence speed,solution accuracy,and robustness.These findings suggest that LOEV-APO serves as a promising optimization tool for MLP training and provides a viable alternative to traditional gradient-based methods.展开更多
Objective:Prostate cancer(PCa)exhibits significant genomic differences between Western and Asian populations.This study aimed to design a predictive model applicable across diverse populations while selecting a limite...Objective:Prostate cancer(PCa)exhibits significant genomic differences between Western and Asian populations.This study aimed to design a predictive model applicable across diverse populations while selecting a limited set of genes suitable for clinical implementation.Methods:We utilized an integrated dataset of 1360 whole-exome and whole-genome sequences from Chinese and Western PCa cohorts to develop and evaluate the model.External validation was conducted using an independent cohort of patients.A graph neural network architecture,termed the pathway-aware multi-layered hierarchical network-Western and Asian(P-NETwa),was developed and trained on combined genomic profiles from Chinese and Western cohorts.The model employed a multilayer perceptron(MLP)to identify key signature genes from multiomics data,enabling precise prediction of PCa metastasis.Results:The model achieved an accuracy of 0.87 and an F1-score of 0.85 on Western population datasets.The application of integrated Chinese and Western population data improved the accuracy to 0.88,achieving an F1-score of 0.75.The analysis identified 18 signature genes implicated in PCa progression,including established markers(AR and TP53)and novel candidates(MUC16,MUC4,and ASB12).For clinical adoption,the model was optimized for commercially available gene panels while maintaining high classification accuracy.Additionally,a user-friendly web interface was developed to facilitate real-time prediction of primary versus metastatic status using the pre-trained P-NETwa-MLP model.Conclusion:The P-NETwa-MLP model integrates a query system that allows for efficient retrieval of prediction outcomes and associated genomic signatures via sample ID,enhancing its potential for seamless integration into clinical workflows.展开更多
Wind power forecasting plays a crucial role in optimizing the integration of wind energy into the grid by predicting wind patterns and energy output.This enhances the efficiency and reliability of renewable energy sys...Wind power forecasting plays a crucial role in optimizing the integration of wind energy into the grid by predicting wind patterns and energy output.This enhances the efficiency and reliability of renewable energy systems.Forecasting approaches inform energy management strategies,reduce reliance on fossil fuels,and support the broader transition to sustainable energy solutions.The primary goal of this study is to introduce an effective methodology for estimating wind power through temporal data analysis.This research advances an optimized Multilayer Perceptron(MLP)model using recently proposedmetaheuristic optimization algorithms,namely the FireHawk Optimizer(FHO)and the Non-Monopolize Search(NO).A modified version of FHO,termed FHONO,is developed by integrating NO as a local search mechanism to enhance the exploration capability and address the shortcomings of the original FHO.The developed FHONO is then employed to optimize the MLP for enhanced wind power prediction.The effectiveness of the proposed FHONO-MLP model is validated using renowned datasets from wind turbines in France.The results of the comparative analysis between FHONO-MLP,conventionalMLP,and other optimized versions of MLP show that FHONO-MLP outperforms the others,achieving an average RootMean Square Error(RMSE)of 0.105,Mean Absolute Error(MAE)of 0.082,and Coefficient of Determination(R^(2))of 0.967 across all datasets.These findings underscore the significant enhancement in predictive accuracy provided by FHONO and demonstrate its effectiveness in improving wind power forecasting.展开更多
With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on th...With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on the discriminating and emotion-related utterance-level representations extracted from speech.Moreover,sufficient data are required to model the relationship between emotional states and speech.Mainstream emotion recognition methods cannot avoid the influence of the silence period in speech,and environmental noise significantly affects the recognition performance.This study intends to supplement the silence periods with removed speech information and applies segmentwise multilayer perceptrons to enhance the utterance-level representation aggregation.In addition,improved semisupervised learning is employed to overcome the prob-lem of data scarcity.Particular experiments are conducted to evaluate the proposed method on the IEMOCAP corpus,which reveals that it achieves 68.0%weighted accuracy and 68.8%unweighted accuracy in four emotion classifications.The experimental results demonstrate that the proposed method aggregates utterance-level more effectively and that semisupervised learning enhances the performance of our method.展开更多
Multilayer complex dynamical networks,characterized by the intricate topological connections and diverse hierarchical structures,present significant challenges in determining complete structural configurations due to ...Multilayer complex dynamical networks,characterized by the intricate topological connections and diverse hierarchical structures,present significant challenges in determining complete structural configurations due to the unique functional attributes and interaction patterns inherent to different layers.This paper addresses the critical question of whether structural information from a known layer can be used to reconstruct the unknown intralayer structure of a target layer within general weighted output-coupling multilayer networks.Building upon the generalized synchronization principle,we propose an innovative reconstruction method that incorporates two essential components in the design of structure observers,the cross-layer coupling modulator and the structural divergence term.A key advantage of the proposed reconstruction method lies in its flexibility to freely designate both the unknown target layer and the known reference layer from the general weighted output-coupling multilayer network.The reduced dependency on full-state observability enables more deployment in engineering applications with partial measurements.Numerical simulations are conducted to validate the effectiveness of the proposed structure reconstruction method.展开更多
The strong vertical discontinuities pose a fundamental challenge to optimizing stimulated reservoir volume(SRV)in multilayered reservoirs.This research proposes a radial borehole-assisted horizontal well fracturing te...The strong vertical discontinuities pose a fundamental challenge to optimizing stimulated reservoir volume(SRV)in multilayered reservoirs.This research proposes a radial borehole-assisted horizontal well fracturing technology,which is expected to achieve effective vertical stimulation and commingled production across multiple pay zones.Under different geological and engineering conditions,the vertical propagation behavior of hydraulic fractures guided by radial boreholes can be determined by adjusting the interlayered lithologies and radial borehole configurations in experimental samples.Experimental results reveal four fracture network patterns:passivated,cross-layer,skip-layer,and hybrid fractures in the radial borehole fracturing.The radial boreholes perform better fracture guiding performances in the high-brittleness interlayers,which form cross-layer and hybrid fracture networks to improve the growth height.Hydraulic fractures tend to propagate from high-strength to low-strength layers under radial borehole guidance.When radial boreholes interconnect multiple lithology layers,hydraulic fractures initiate preferentially in lower-strength zones rather than remaining confined to borehole root ends.Increased radial borehole length and diameter facilitate fracture skip-layer initiation and cross-layer propagation,while multiple borehole branches enhance fracture penetration across high-strength interlayers.Radial boreholes with inclination angles below 30°enhance fracture height by generating cross-layer and hybrid fracture networks.Furthermore,an inter-borehole phase angle of less than 180°facilitates single-wing fracture cross-layer propagation.Fracture height is primarily governed by radial borehole length,followed by quantity,inclination angle,and diameter.Based on the geometric similarity criteria,the recommended parameters for radial borehole-assisted fracturing in a 5 1/2-inch horizontal well include a length>15 m,an inclination angle<30°,and a diameter>52 mm to ensure effective stimulation across three or more pay zones.Finally,the field-scale numerical model was developed to simulate the optimized radial borehole fracturing and demonstrate the technical superiority.These findings are expected to provide an in-depth understanding of the effective stimulation in multilayered reservoirs.展开更多
To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with ad...To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.展开更多
The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical c...The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical characteristics. The temporal organization of the ECG signal offers a basis for composing a machine learning feature set. The four attributes of the feature set are derived through software automation enabled by Python. These four attributes are the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum and the Q wave minimum and S wave minimum relative to the R wave maximum. The multilayer perceptron neural network was applied and evaluated in terms of classification accuracy and time to develop the model. Superior performance was achieved with respect to a reduced feature set considering only the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum by comparison to all four attributes applied to the feature set and the temporal differential of the Q wave minimum and S wave minimum relative to the R wave maximum. With these preliminary findings and the advent of portable and wearable devices for the acquisition of the ECG signal, the temporal organization of the ECG signal offers robust potential for the field of biometrics.展开更多
A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed ...A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed by Rumelhart et al with the Newton learning method. Finally, the hybrid learning algorithm is compared with the backpropagation algorithm by some illustrations, and the results show that this hybrid leaming algorithm bas the characteristics of rapid convergence.展开更多
This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and f...This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and frequency domains, and color space transformations. First system used rotational signatures based on a correlation operator;minimum distance was used for the classification task. Second system computed the seven Hu invariants from binary images;these descriptors fed to a Multi-Layer Perceptron (MLP) in order to recognize the 9 different classes. First system achieves 100% of recognition rate with leaving-one-out validation and second experiment performs 96.7% of recognition rate with Hu moments and 100% using 36 normalized moments and k-fold cross validation.展开更多
The healthcare data requires accurate disease detection analysis,real-timemonitoring,and advancements to ensure proper treatment for patients.Consequently,Machine Learning methods are widely utilized in Smart Healthca...The healthcare data requires accurate disease detection analysis,real-timemonitoring,and advancements to ensure proper treatment for patients.Consequently,Machine Learning methods are widely utilized in Smart Healthcare Systems(SHS)to extract valuable features fromheterogeneous and high-dimensional healthcare data for predicting various diseases and monitoring patient activities.These methods are employed across different domains that are susceptible to adversarial attacks,necessitating careful consideration.Hence,this paper proposes a crossover-based Multilayer Perceptron(CMLP)model.The collected samples are pre-processed and fed into the crossover-based multilayer perceptron neural network to detect adversarial attacks on themedical records of patients.Once an attack is detected,healthcare professionals are promptly alerted to prevent data leakage.The paper utilizes two datasets,namely the synthetic dataset and the University of Queensland Vital Signs(UQVS)dataset,from which numerous samples are collected.Experimental results are conducted to evaluate the performance of the proposed CMLP model,utilizing various performancemeasures such as Recall,Precision,Accuracy,and F1-score to predict patient activities.Comparing the proposed method with existing approaches,it achieves the highest accuracy,precision,recall,and F1-score.Specifically,the proposedmethod achieves a precision of 93%,an accuracy of 97%,an F1-score of 92%,and a recall of 92%.展开更多
The Multilayer Perceptron Neural Network (MLPNN) induction technique has been successfully applied to a variety of machine learning tasks, including the extraction and classification of image features. However, not mu...The Multilayer Perceptron Neural Network (MLPNN) induction technique has been successfully applied to a variety of machine learning tasks, including the extraction and classification of image features. However, not much has been done in the application of MLPNN on images obtained by remote sensing. In this article, two automatic classification systems used in image feature extraction and classification from remote sensing data are presented. The first is a combination of two models: a MLPNN induction technique, integrated under ENVI (Environment for Visualizing Images) platform for classification, and a pre-processing model including dark subtraction for the calibration of the image, the Principal Components Analysis (PCA) for band selections and Independent Components Analysis (ICA) as blind source separator for feature extraction of the Landsat image. The second classification system is a MLPNN induction technique based on the Keras platform. In this case, there was no need for pre-processing model. Experimental results show the two classification systems to outperform other typical feature extraction and classification methods in terms of accuracy for some lithological classes including Granite1 class with the highest class accuracies of 96.69% and 92.69% for the first and second classification system respectively. Meanwhile, the two classification systems perform almost equally with the overall accuracies of 53.01% and 49.98% for the first and second models respectively </span><span style="font-family:Verdana;">though the keras model has the advantage of not integrating the pre-processing</span><span style="font-family:Verdana;"> model, hence increasing its efficiency. The application of these two systems to the study area resulted in the generation of an updated geological mapping with six lithological classes detected including the Gneiss, the Micaschist, the Schist and three versions of Granites (Granite1, Granite2 and Granite3).展开更多
In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a c...In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a class of multilayered perceptrons with threshold functions is proposed by using statistical approach. Furthermore, the formula to calculate the robustness of the networks is also given. The result of computer simulation indicates the correctness of the algorithm.展开更多
This paper examines the relationship between fatal road traffic accidents and potential predictors using multilayer perceptron artificial neural network (MLANN) models. The initial analysis employed twelve potential p...This paper examines the relationship between fatal road traffic accidents and potential predictors using multilayer perceptron artificial neural network (MLANN) models. The initial analysis employed twelve potential predictors, including traffic volume, prevailing weather conditions, roadway characteristics and features, drivers’ age and gender, and number of lanes. Based on the output of the model and the variables’ importance factors, seven significant variables are identified and used for further analysis to improve the performance of models. The model is optimized by systematically changing the parameters, including the number of hidden layers and the activation function of both the hidden and output layers. The performances of the MLANN models are evaluated using the percentage of the achieved accuracy, R-squared, and Sum of Square Error (SSE) functions.展开更多
The field of sentiment analysis(SA)has grown in tandem with the aid of social networking platforms to exchange opinions and ideas.Many people share their views and ideas around the world through social media like Face...The field of sentiment analysis(SA)has grown in tandem with the aid of social networking platforms to exchange opinions and ideas.Many people share their views and ideas around the world through social media like Facebook and Twitter.The goal of opinion mining,commonly referred to as sentiment analysis,is to categorise and forecast a target’s opinion.Depending on if they provide a positive or negative perspective on a given topic,text documents or sentences can be classified.When compared to sentiment analysis,text categorization may appear to be a simple process,but number of challenges have prompted numerous studies in this area.A feature selection-based classification algorithm in conjunction with the firefly with levy and multilayer perceptron(MLP)techniques has been proposed as a way to automate sentiment analysis(SA).In this study,online product reviews can be enhanced by integrating classification and feature election.The firefly(FF)algorithm was used to extract features from online product reviews,and a multi-layer perceptron was used to classify sentiment(MLP).The experiment employs two datasets,and the results are assessed using a variety of criteria.On account of these tests,it is possible to conclude that the FFL-MLP algorithm has the better classification performance for Canon(98%accuracy)and iPod(99%accuracy).展开更多
In this paper,we theoretically study the Lamb wave in a multilayered piezoelectric semiconductor(PSC)plate,where each layer is an n-type PSC with the symmetry of transverse isotropy.Based on the extended Stroh formali...In this paper,we theoretically study the Lamb wave in a multilayered piezoelectric semiconductor(PSC)plate,where each layer is an n-type PSC with the symmetry of transverse isotropy.Based on the extended Stroh formalism and dual-variable and position(DVP)method,the general solution of the coupled fields for the Lamb wave is derived,and then the dispersion equation is obtained by the application of the boundary conditions.First,the influence of semiconducting properties on the dispersion behavior of the Lamb wave in a single-layer PSC plate is analyzed.Then,the propagation characteristics of the Lamb wave in a sandwich plate are investigated in detail.The numerical results show that the wave speed and attenuation depend on the stacking sequence,layer thickness,and initial carrier density,the Lamb wave can propagate without a cut-off frequency in both the homogeneous and multilayer PSC plates due to the semiconducting properties,and the Lamb wave without attenuation can be achieved by carefully selecting the semiconductor property in the upper and lower layers.These new features could be very helpful as theoretical guidance for the design and performance optimization of PSC devices.展开更多
Lightweight,high-strength,and heat-resistant protective structures have consistently been crucial for applications in extreme environments,such as aerospace,semiconductors,and nuclear power industries.Multilayered TC4...Lightweight,high-strength,and heat-resistant protective structures have consistently been crucial for applications in extreme environments,such as aerospace,semiconductors,and nuclear power industries.Multilayered TC4/TB8 titanium(Ti)laminates,inspired by theheterostructures of natural biological shells,were fabricated using a hybrid diffusion bonding-hot rolling process followed by an aging treatment,resulting in an architected micro structure.The laminate achieves an ultra-high yield stress of 1020 MPa and proper uniform elongation of 4.2%at 500℃.The TB8 layers with high-density nano-precipitates and dislocations act as hard zone,contributing to high strength.The TC4 layers,with their bimodal structure consisting of coarse and fine grains characterized by equiaxed and lamellar structures,experience more plastic strain than the TB8 layers.The hetero deformation associated with the detwinning ofαgrains in the TC4 layer induces toughening at high temperatures.展开更多
To overcome the shortage of complex equipment,large volume,and high energy consumption in space capsule manufacturing,a novel sliding pressure Joule heat fuse additive manufacturing technique with reduced volume and l...To overcome the shortage of complex equipment,large volume,and high energy consumption in space capsule manufacturing,a novel sliding pressure Joule heat fuse additive manufacturing technique with reduced volume and low energy consumption was proposed.But the unreasonable process parameters may lead to the inferior consistency of the forming quality of single-channel multilayer in Joule heat additive manufacturing process,and it is difficult to reach the condition for forming thinwalled parts.Orthogonal experiments were designed to fabricate single-channel multilayer samples with varying numbers of layers,and their forming quality was evaluated.The influence of printing current,forming speed,and contact pressure on the forming quality of the single-channel multilayer was analyzed.The optimal process parameters were obtained and the quality characterization of the experiment results was conducted.Results show that the printing current has the most significant influence on the forming quality of the single-channel multilayer.Under the optimal process parameters,the forming section is well fused and the surface is continuously smooth.The surface roughness of a single-channel 3-layer sample is 0.16μm,and the average Vickers hardness of cross section fusion zone is 317 HV,which lays a foundation for the subsequent use of Joule heat additive manufacturing technique to form thinwall parts.展开更多
The vascular network is integral to the developmental and metabolic processes of various tissues and functions as a systemic circulatory system that also interconnects organs throughout the body.In this study,we descr...The vascular network is integral to the developmental and metabolic processes of various tissues and functions as a systemic circulatory system that also interconnects organs throughout the body.In this study,we describe a multilayered microfluidic organ-on-a-chip platform designed for reproducing various three-dimensional(3D)vascularized microtissue models for biological applications.This platform utilizes a porous membrane as a physical barrier and leverages capillary action for hydrogel self-filling.Its high flow resistance mitigates the risk of gel bursting into the medium channels and facilitates the delivery of substances to generate a wide range of interstitial flow and biochemical factor concentration gradients.This study demonstrated that this platform can be used to accurately replicate 3D microenvironments for vasculogenesis,angiogenesis,and vascularized tumor modeling.We also investigated the critical role of multiple microenvironmental regulations in vascular formation on a chip.Moreover,we reproduced the process of tumor angiogenesis,including primary solid tumor features and the inhibitory effects of antitumor drugs on tumor growth and tumor vasculature before and after angiogenesis.Hence,our multilayered microfluidic platform is valuable for exploring multiple vascular mechanisms and constructing specific microtissues that closely mimic in vivo physiological conditions,providing new strategies for cancer research.Furthermore,the multilayered configuration improves design flexibility and scalability,providing the potential for a multi-organ interconnected platform for high-throughput drug screening.展开更多
Electron doping has been established as an effective method to enhance the superconducting transition temperature and superconducting energy gap of FeSe thin films on strontium titanate(SrTiO_(3))substrates.Previous s...Electron doping has been established as an effective method to enhance the superconducting transition temperature and superconducting energy gap of FeSe thin films on strontium titanate(SrTiO_(3))substrates.Previous studies have demonstrated that electron/hole doping can be achieved through the adsorption of metal phthalocyanine(MPc,M=Co,Cu,Mn,Fe,and Ni)molecules on surfaces.This work explores the electron doping induced by the adsorption of MPc molecules,specifically cobalt phthalocyanine(CoPc)and copper phthalocyanine(CuPc),onto FeSe monolayer and multilayers.Utilizing first-principles calculations based on density functional theory,we demonstrate that charge rearrangement occurs when MPc molecules adsorb on the FeSe substrate,contributing to an accumulation of electrons at the interface.In the CoPc/FeSe systems,the electron accumulation increases with the layer number of FeSe substrate,converging for substrates with 3-5 layers.The analysis of the integrated planar charge difference up to the position with zero integrated charge transfer reveals that all the five MPc molecules donate electrons to the uppermost FeSe layer.The electron donation suggests that MPc adsorption can be a promising strategy to modulate the superconductivity of FeSe layers.展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.62376089,62302153,62302154)the Key Research and Development Program of Hubei Province,China(Grant No.2023BEB024)+1 种基金the Young and Middle-Aged Scientific and Technological Innovation Team Plan in Higher Education Institutions in Hubei Province,China(Grant No.T2023007)the National Natural Science Foundation of China(Grant No.U23A20318).
文摘The Multilayer Perceptron(MLP)is a fundamental neural network model widely applied in various domains,particularly for lightweight image classification,speech recognition,and natural language processing tasks.Despite its widespread success,training MLPs often encounter significant challenges,including susceptibility to local optima,slow convergence rates,and high sensitivity to initial weight configurations.To address these issues,this paper proposes a Latin Hypercube Opposition-based Elite Variation Artificial Protozoa Optimizer(LOEV-APO),which enhances both global exploration and local exploitation simultaneously.LOEV-APO introduces a hybrid initialization strategy that combines Latin Hypercube Sampling(LHS)with Opposition-Based Learning(OBL),thus improving the diversity and coverage of the initial population.Moreover,an Elite Protozoa Variation Strategy(EPVS)is incorporated,which applies differential mutation operations to elite candidates,accelerating convergence and strengthening local search capabilities around high-quality solutions.Extensive experiments are conducted on six classification tasks and four function approximation tasks,covering a wide range of problem complexities and demonstrating superior generalization performance.The results demonstrate that LOEV-APO consistently outperforms nine state-of-the-art metaheuristic algorithms and two gradient-based methods in terms of convergence speed,solution accuracy,and robustness.These findings suggest that LOEV-APO serves as a promising optimization tool for MLP training and provides a viable alternative to traditional gradient-based methods.
基金supported by the National Key R&D Program of China(2022YFA1305700 to Li J)the“Dawn”Program of Shanghai Education Commission,China(21SG33 to Li J)The National Natural Science Foundation of China(82272793 to Gao X).
文摘Objective:Prostate cancer(PCa)exhibits significant genomic differences between Western and Asian populations.This study aimed to design a predictive model applicable across diverse populations while selecting a limited set of genes suitable for clinical implementation.Methods:We utilized an integrated dataset of 1360 whole-exome and whole-genome sequences from Chinese and Western PCa cohorts to develop and evaluate the model.External validation was conducted using an independent cohort of patients.A graph neural network architecture,termed the pathway-aware multi-layered hierarchical network-Western and Asian(P-NETwa),was developed and trained on combined genomic profiles from Chinese and Western cohorts.The model employed a multilayer perceptron(MLP)to identify key signature genes from multiomics data,enabling precise prediction of PCa metastasis.Results:The model achieved an accuracy of 0.87 and an F1-score of 0.85 on Western population datasets.The application of integrated Chinese and Western population data improved the accuracy to 0.88,achieving an F1-score of 0.75.The analysis identified 18 signature genes implicated in PCa progression,including established markers(AR and TP53)and novel candidates(MUC16,MUC4,and ASB12).For clinical adoption,the model was optimized for commercially available gene panels while maintaining high classification accuracy.Additionally,a user-friendly web interface was developed to facilitate real-time prediction of primary versus metastatic status using the pre-trained P-NETwa-MLP model.Conclusion:The P-NETwa-MLP model integrates a query system that allows for efficient retrieval of prediction outcomes and associated genomic signatures via sample ID,enhancing its potential for seamless integration into clinical workflows.
基金the Deanship of Graduate Studies and Scientific Research at University of Bisha,Saudi Arabia for funding this research work through the Promising Program under Grant Number(UB-Promising-42-1445).
文摘Wind power forecasting plays a crucial role in optimizing the integration of wind energy into the grid by predicting wind patterns and energy output.This enhances the efficiency and reliability of renewable energy systems.Forecasting approaches inform energy management strategies,reduce reliance on fossil fuels,and support the broader transition to sustainable energy solutions.The primary goal of this study is to introduce an effective methodology for estimating wind power through temporal data analysis.This research advances an optimized Multilayer Perceptron(MLP)model using recently proposedmetaheuristic optimization algorithms,namely the FireHawk Optimizer(FHO)and the Non-Monopolize Search(NO).A modified version of FHO,termed FHONO,is developed by integrating NO as a local search mechanism to enhance the exploration capability and address the shortcomings of the original FHO.The developed FHONO is then employed to optimize the MLP for enhanced wind power prediction.The effectiveness of the proposed FHONO-MLP model is validated using renowned datasets from wind turbines in France.The results of the comparative analysis between FHONO-MLP,conventionalMLP,and other optimized versions of MLP show that FHONO-MLP outperforms the others,achieving an average RootMean Square Error(RMSE)of 0.105,Mean Absolute Error(MAE)of 0.082,and Coefficient of Determination(R^(2))of 0.967 across all datasets.These findings underscore the significant enhancement in predictive accuracy provided by FHONO and demonstrate its effectiveness in improving wind power forecasting.
文摘With the increasing popularity of mobile internet devices,speech emotion recognition has become a convenient and valuable means of human-computer interaction.The performance of speech emotion recognition depends on the discriminating and emotion-related utterance-level representations extracted from speech.Moreover,sufficient data are required to model the relationship between emotional states and speech.Mainstream emotion recognition methods cannot avoid the influence of the silence period in speech,and environmental noise significantly affects the recognition performance.This study intends to supplement the silence periods with removed speech information and applies segmentwise multilayer perceptrons to enhance the utterance-level representation aggregation.In addition,improved semisupervised learning is employed to overcome the prob-lem of data scarcity.Particular experiments are conducted to evaluate the proposed method on the IEMOCAP corpus,which reveals that it achieves 68.0%weighted accuracy and 68.8%unweighted accuracy in four emotion classifications.The experimental results demonstrate that the proposed method aggregates utterance-level more effectively and that semisupervised learning enhances the performance of our method.
基金Project supported by the National Natural Science Foun-dation of China(Grant No.62373197)the Natural Science Foundation of the Higher Education Institutions of Jiangsu Province,China(Grant No.23KJB120010)+1 种基金the Industry-University-Research Cooperation Project of Jiangsu Province,China(Grant No.BY20251038)the Cultivation and In-cubation Project of the College of Automation,Nanjing Uni-versity of Posts and Telecommunications.
文摘Multilayer complex dynamical networks,characterized by the intricate topological connections and diverse hierarchical structures,present significant challenges in determining complete structural configurations due to the unique functional attributes and interaction patterns inherent to different layers.This paper addresses the critical question of whether structural information from a known layer can be used to reconstruct the unknown intralayer structure of a target layer within general weighted output-coupling multilayer networks.Building upon the generalized synchronization principle,we propose an innovative reconstruction method that incorporates two essential components in the design of structure observers,the cross-layer coupling modulator and the structural divergence term.A key advantage of the proposed reconstruction method lies in its flexibility to freely designate both the unknown target layer and the known reference layer from the general weighted output-coupling multilayer network.The reduced dependency on full-state observability enables more deployment in engineering applications with partial measurements.Numerical simulations are conducted to validate the effectiveness of the proposed structure reconstruction method.
基金supported by the National Natural Science Foundation of China(Nos.U24B6001,52421002,52474016,and 52020105001)Research on Key Technologies for Exploration and Development of Dry Geothermal Resources(No.2022DJ5503)Deep-land National Science and Technology Major Project of China(No.2024ZD1003504).
文摘The strong vertical discontinuities pose a fundamental challenge to optimizing stimulated reservoir volume(SRV)in multilayered reservoirs.This research proposes a radial borehole-assisted horizontal well fracturing technology,which is expected to achieve effective vertical stimulation and commingled production across multiple pay zones.Under different geological and engineering conditions,the vertical propagation behavior of hydraulic fractures guided by radial boreholes can be determined by adjusting the interlayered lithologies and radial borehole configurations in experimental samples.Experimental results reveal four fracture network patterns:passivated,cross-layer,skip-layer,and hybrid fractures in the radial borehole fracturing.The radial boreholes perform better fracture guiding performances in the high-brittleness interlayers,which form cross-layer and hybrid fracture networks to improve the growth height.Hydraulic fractures tend to propagate from high-strength to low-strength layers under radial borehole guidance.When radial boreholes interconnect multiple lithology layers,hydraulic fractures initiate preferentially in lower-strength zones rather than remaining confined to borehole root ends.Increased radial borehole length and diameter facilitate fracture skip-layer initiation and cross-layer propagation,while multiple borehole branches enhance fracture penetration across high-strength interlayers.Radial boreholes with inclination angles below 30°enhance fracture height by generating cross-layer and hybrid fracture networks.Furthermore,an inter-borehole phase angle of less than 180°facilitates single-wing fracture cross-layer propagation.Fracture height is primarily governed by radial borehole length,followed by quantity,inclination angle,and diameter.Based on the geometric similarity criteria,the recommended parameters for radial borehole-assisted fracturing in a 5 1/2-inch horizontal well include a length>15 m,an inclination angle<30°,and a diameter>52 mm to ensure effective stimulation across three or more pay zones.Finally,the field-scale numerical model was developed to simulate the optimized radial borehole fracturing and demonstrate the technical superiority.These findings are expected to provide an in-depth understanding of the effective stimulation in multilayered reservoirs.
基金This work was partially supported by the research grant of the National University of Singapore(NUS),Ministry of Education(MOE Tier 1).
文摘To improve the performance of multilayer perceptron(MLP)neural networks activated by conventional activation functions,this paper presents a new MLP activated by univariate Gaussian radial basis functions(RBFs)with adaptive centers and widths,which is composed of more than one hidden layer.In the hidden layer of the RBF-activated MLP network(MLPRBF),the outputs of the preceding layer are first linearly transformed and then fed into the univariate Gaussian RBF,which exploits the highly nonlinear property of RBF.Adaptive RBFs might address the issues of saturated outputs,low sensitivity,and vanishing gradients in MLPs activated by other prevailing nonlinear functions.Finally,we apply four MLP networks with the rectified linear unit(ReLU),sigmoid function(sigmoid),hyperbolic tangent function(tanh),and Gaussian RBF as the activation functions to approximate the one-dimensional(1D)sinusoidal function,the analytical solution of viscous Burgers’equation,and the two-dimensional(2D)steady lid-driven cavity flows.Using the same network structure,MLP-RBF generally predicts more accurately and converges faster than the other threeMLPs.MLP-RBF using less hidden layers and/or neurons per layer can yield comparable or even higher approximation accuracy than other MLPs equipped with more layers or neurons.
文摘The attributes of the ECG signal signifying the unique electrical properties of the heart offer the opportunity to expand the realm of biometrics, which pertains the identification of an individual based on physical characteristics. The temporal organization of the ECG signal offers a basis for composing a machine learning feature set. The four attributes of the feature set are derived through software automation enabled by Python. These four attributes are the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum and the Q wave minimum and S wave minimum relative to the R wave maximum. The multilayer perceptron neural network was applied and evaluated in terms of classification accuracy and time to develop the model. Superior performance was achieved with respect to a reduced feature set considering only the temporal differential of the P wave maximum and T wave maximum relative to the R wave maximum by comparison to all four attributes applied to the feature set and the temporal differential of the Q wave minimum and S wave minimum relative to the R wave maximum. With these preliminary findings and the advent of portable and wearable devices for the acquisition of the ECG signal, the temporal organization of the ECG signal offers robust potential for the field of biometrics.
文摘A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed by Rumelhart et al with the Newton learning method. Finally, the hybrid learning algorithm is compared with the backpropagation algorithm by some illustrations, and the results show that this hybrid leaming algorithm bas the characteristics of rapid convergence.
文摘This paper presents two systems for recognizing static signs (digits) from American Sign Language (ASL). These systems avoid the use color marks, or gloves, using instead, low-pass and high-pass filters in space and frequency domains, and color space transformations. First system used rotational signatures based on a correlation operator;minimum distance was used for the classification task. Second system computed the seven Hu invariants from binary images;these descriptors fed to a Multi-Layer Perceptron (MLP) in order to recognize the 9 different classes. First system achieves 100% of recognition rate with leaving-one-out validation and second experiment performs 96.7% of recognition rate with Hu moments and 100% using 36 normalized moments and k-fold cross validation.
基金funded by King Saud University through Researchers Supporting Program Number (RSP2024R499).
文摘The healthcare data requires accurate disease detection analysis,real-timemonitoring,and advancements to ensure proper treatment for patients.Consequently,Machine Learning methods are widely utilized in Smart Healthcare Systems(SHS)to extract valuable features fromheterogeneous and high-dimensional healthcare data for predicting various diseases and monitoring patient activities.These methods are employed across different domains that are susceptible to adversarial attacks,necessitating careful consideration.Hence,this paper proposes a crossover-based Multilayer Perceptron(CMLP)model.The collected samples are pre-processed and fed into the crossover-based multilayer perceptron neural network to detect adversarial attacks on themedical records of patients.Once an attack is detected,healthcare professionals are promptly alerted to prevent data leakage.The paper utilizes two datasets,namely the synthetic dataset and the University of Queensland Vital Signs(UQVS)dataset,from which numerous samples are collected.Experimental results are conducted to evaluate the performance of the proposed CMLP model,utilizing various performancemeasures such as Recall,Precision,Accuracy,and F1-score to predict patient activities.Comparing the proposed method with existing approaches,it achieves the highest accuracy,precision,recall,and F1-score.Specifically,the proposedmethod achieves a precision of 93%,an accuracy of 97%,an F1-score of 92%,and a recall of 92%.
文摘The Multilayer Perceptron Neural Network (MLPNN) induction technique has been successfully applied to a variety of machine learning tasks, including the extraction and classification of image features. However, not much has been done in the application of MLPNN on images obtained by remote sensing. In this article, two automatic classification systems used in image feature extraction and classification from remote sensing data are presented. The first is a combination of two models: a MLPNN induction technique, integrated under ENVI (Environment for Visualizing Images) platform for classification, and a pre-processing model including dark subtraction for the calibration of the image, the Principal Components Analysis (PCA) for band selections and Independent Components Analysis (ICA) as blind source separator for feature extraction of the Landsat image. The second classification system is a MLPNN induction technique based on the Keras platform. In this case, there was no need for pre-processing model. Experimental results show the two classification systems to outperform other typical feature extraction and classification methods in terms of accuracy for some lithological classes including Granite1 class with the highest class accuracies of 96.69% and 92.69% for the first and second classification system respectively. Meanwhile, the two classification systems perform almost equally with the overall accuracies of 53.01% and 49.98% for the first and second models respectively </span><span style="font-family:Verdana;">though the keras model has the advantage of not integrating the pre-processing</span><span style="font-family:Verdana;"> model, hence increasing its efficiency. The application of these two systems to the study area resulted in the generation of an updated geological mapping with six lithological classes detected including the Gneiss, the Micaschist, the Schist and three versions of Granites (Granite1, Granite2 and Granite3).
基金National Science Foundation of Chinathe Doctoral Fund of the State Education Commission of China
文摘In this paper, based on a stochastic mode! for inputs and weights, and in view of the disturbance of correlative and large input and weight errors, a general algorithm to obtain the output error characteristics of a class of multilayered perceptrons with threshold functions is proposed by using statistical approach. Furthermore, the formula to calculate the robustness of the networks is also given. The result of computer simulation indicates the correctness of the algorithm.
文摘This paper examines the relationship between fatal road traffic accidents and potential predictors using multilayer perceptron artificial neural network (MLANN) models. The initial analysis employed twelve potential predictors, including traffic volume, prevailing weather conditions, roadway characteristics and features, drivers’ age and gender, and number of lanes. Based on the output of the model and the variables’ importance factors, seven significant variables are identified and used for further analysis to improve the performance of models. The model is optimized by systematically changing the parameters, including the number of hidden layers and the activation function of both the hidden and output layers. The performances of the MLANN models are evaluated using the percentage of the achieved accuracy, R-squared, and Sum of Square Error (SSE) functions.
文摘The field of sentiment analysis(SA)has grown in tandem with the aid of social networking platforms to exchange opinions and ideas.Many people share their views and ideas around the world through social media like Facebook and Twitter.The goal of opinion mining,commonly referred to as sentiment analysis,is to categorise and forecast a target’s opinion.Depending on if they provide a positive or negative perspective on a given topic,text documents or sentences can be classified.When compared to sentiment analysis,text categorization may appear to be a simple process,but number of challenges have prompted numerous studies in this area.A feature selection-based classification algorithm in conjunction with the firefly with levy and multilayer perceptron(MLP)techniques has been proposed as a way to automate sentiment analysis(SA).In this study,online product reviews can be enhanced by integrating classification and feature election.The firefly(FF)algorithm was used to extract features from online product reviews,and a multi-layer perceptron was used to classify sentiment(MLP).The experiment employs two datasets,and the results are assessed using a variety of criteria.On account of these tests,it is possible to conclude that the FFL-MLP algorithm has the better classification performance for Canon(98%accuracy)and iPod(99%accuracy).
基金Project supported by the National Natural Science Foundation of China(Nos.U21A20430 and 12302202)the Hebei Natural Science Foundation of China(No.A2023210040)+1 种基金the Science and Technology Project of Hebei Education Department of China(No.BJ2025005)the Hebei Provincial Department of Human Resources and Social Security of China(No.C20220324)。
文摘In this paper,we theoretically study the Lamb wave in a multilayered piezoelectric semiconductor(PSC)plate,where each layer is an n-type PSC with the symmetry of transverse isotropy.Based on the extended Stroh formalism and dual-variable and position(DVP)method,the general solution of the coupled fields for the Lamb wave is derived,and then the dispersion equation is obtained by the application of the boundary conditions.First,the influence of semiconducting properties on the dispersion behavior of the Lamb wave in a single-layer PSC plate is analyzed.Then,the propagation characteristics of the Lamb wave in a sandwich plate are investigated in detail.The numerical results show that the wave speed and attenuation depend on the stacking sequence,layer thickness,and initial carrier density,the Lamb wave can propagate without a cut-off frequency in both the homogeneous and multilayer PSC plates due to the semiconducting properties,and the Lamb wave without attenuation can be achieved by carefully selecting the semiconductor property in the upper and lower layers.These new features could be very helpful as theoretical guidance for the design and performance optimization of PSC devices.
基金financially supported by the Natural Science Foundation of Changsha,China(No.kq2402015)the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIP)(Nos.NRF-2021R1A2C3006662 and NRF-2022R1A5A1030054)supported by Brain Pool Program through the NRF of Korea,funded by the Ministry of Science and ICT(No.NRF-RS_(2)02300263999)
文摘Lightweight,high-strength,and heat-resistant protective structures have consistently been crucial for applications in extreme environments,such as aerospace,semiconductors,and nuclear power industries.Multilayered TC4/TB8 titanium(Ti)laminates,inspired by theheterostructures of natural biological shells,were fabricated using a hybrid diffusion bonding-hot rolling process followed by an aging treatment,resulting in an architected micro structure.The laminate achieves an ultra-high yield stress of 1020 MPa and proper uniform elongation of 4.2%at 500℃.The TB8 layers with high-density nano-precipitates and dislocations act as hard zone,contributing to high strength.The TC4 layers,with their bimodal structure consisting of coarse and fine grains characterized by equiaxed and lamellar structures,experience more plastic strain than the TB8 layers.The hetero deformation associated with the detwinning ofαgrains in the TC4 layer induces toughening at high temperatures.
基金Shaanxi Province Qin Chuangyuan“Scientist+Engineer”Team Construction Project(2022KXJ-071)2022 Qin Chuangyuan Achievement Transformation Incubation Capacity Improvement Project(2022JH-ZHFHTS-0012)+1 种基金Shaanxi Province Key Research and Development Plan-“Two Chains”Integration Key Project-Qin Chuangyuan General Window Industrial Cluster Project(2023QCY-LL-02)Xixian New Area Science and Technology Plan(2022-YXYJ-003,2022-XXCY-010)。
文摘To overcome the shortage of complex equipment,large volume,and high energy consumption in space capsule manufacturing,a novel sliding pressure Joule heat fuse additive manufacturing technique with reduced volume and low energy consumption was proposed.But the unreasonable process parameters may lead to the inferior consistency of the forming quality of single-channel multilayer in Joule heat additive manufacturing process,and it is difficult to reach the condition for forming thinwalled parts.Orthogonal experiments were designed to fabricate single-channel multilayer samples with varying numbers of layers,and their forming quality was evaluated.The influence of printing current,forming speed,and contact pressure on the forming quality of the single-channel multilayer was analyzed.The optimal process parameters were obtained and the quality characterization of the experiment results was conducted.Results show that the printing current has the most significant influence on the forming quality of the single-channel multilayer.Under the optimal process parameters,the forming section is well fused and the surface is continuously smooth.The surface roughness of a single-channel 3-layer sample is 0.16μm,and the average Vickers hardness of cross section fusion zone is 317 HV,which lays a foundation for the subsequent use of Joule heat additive manufacturing technique to form thinwall parts.
基金supported by grants from the Interdisciplinary Program of Shanghai Jiao Tong University(No.YG2023LC04)the National Natural Science Foundation of China(Nos.32471473,62231025,and 82171011)+1 种基金the Research Program of Shanghai Science and Technology Committee(Nos.24141900900 and 25JC3201100)Chongqing Natural Science Foundation(No.CSTB2022NSCQ-MSX0767)
文摘The vascular network is integral to the developmental and metabolic processes of various tissues and functions as a systemic circulatory system that also interconnects organs throughout the body.In this study,we describe a multilayered microfluidic organ-on-a-chip platform designed for reproducing various three-dimensional(3D)vascularized microtissue models for biological applications.This platform utilizes a porous membrane as a physical barrier and leverages capillary action for hydrogel self-filling.Its high flow resistance mitigates the risk of gel bursting into the medium channels and facilitates the delivery of substances to generate a wide range of interstitial flow and biochemical factor concentration gradients.This study demonstrated that this platform can be used to accurately replicate 3D microenvironments for vasculogenesis,angiogenesis,and vascularized tumor modeling.We also investigated the critical role of multiple microenvironmental regulations in vascular formation on a chip.Moreover,we reproduced the process of tumor angiogenesis,including primary solid tumor features and the inhibitory effects of antitumor drugs on tumor growth and tumor vasculature before and after angiogenesis.Hence,our multilayered microfluidic platform is valuable for exploring multiple vascular mechanisms and constructing specific microtissues that closely mimic in vivo physiological conditions,providing new strategies for cancer research.Furthermore,the multilayered configuration improves design flexibility and scalability,providing the potential for a multi-organ interconnected platform for high-throughput drug screening.
基金support from the National Natural Science Foundation of China(Grant No.62488201)the National Key Research and Development Program of China(Grant No.2022YFA1204100).
文摘Electron doping has been established as an effective method to enhance the superconducting transition temperature and superconducting energy gap of FeSe thin films on strontium titanate(SrTiO_(3))substrates.Previous studies have demonstrated that electron/hole doping can be achieved through the adsorption of metal phthalocyanine(MPc,M=Co,Cu,Mn,Fe,and Ni)molecules on surfaces.This work explores the electron doping induced by the adsorption of MPc molecules,specifically cobalt phthalocyanine(CoPc)and copper phthalocyanine(CuPc),onto FeSe monolayer and multilayers.Utilizing first-principles calculations based on density functional theory,we demonstrate that charge rearrangement occurs when MPc molecules adsorb on the FeSe substrate,contributing to an accumulation of electrons at the interface.In the CoPc/FeSe systems,the electron accumulation increases with the layer number of FeSe substrate,converging for substrates with 3-5 layers.The analysis of the integrated planar charge difference up to the position with zero integrated charge transfer reveals that all the five MPc molecules donate electrons to the uppermost FeSe layer.The electron donation suggests that MPc adsorption can be a promising strategy to modulate the superconductivity of FeSe layers.
