Coverless Steganography for Digital Images Based on a Generative Model

In this paper,we propose a novel coverless image steganographic scheme based on a generative model.In our scheme,the secret image is first fed to the generative model database,to generate a meaning-normal and independent image different from the secret image.The generated image is then transmitted to the receiver and fed to the generative model database to generate another image visually the same as the secret image.Thus,we only need to transmit the meaning-normal image which is not related to the secret image,and we can achieve the same effect as the transmission of the secret image.This is the first time to propose the coverless image information steganographic scheme based on generative model,compared with the traditional image steganography.The transmitted image is not embedded with any information of the secret image in this method,therefore,can effectively resist steganalysis tools.Experimental results show that our scheme has high capacity,security and reliability.

Quantum Generative Model with Variable-Depth Circuit

In recent years,an increasing number of studies about quantum machine learning not only provide powerful tools for quantum chemistry and quantum physics but also improve the classical learning algorithm.The hybrid quantum-classical framework,which is constructed by a variational quantum circuit(VQC)and an optimizer,plays a key role in the latest quantum machine learning studies.Nevertheless,in these hybrid-framework-based quantum machine learning models,the VQC is mainly constructed with a fixed structure and this structure causes inflexibility problems.There are also few studies focused on comparing the performance of quantum generative models with different loss functions.In this study,we address the inflexibility problem by adopting the variable-depth VQC model to automatically change the structure of the quantum circuit according to the qBAS score.The basic idea behind the variable-depth VQC is to consider the depth of the quantum circuit as a parameter during the training.Meanwhile,we compared the performance of the variable-depth VQC model based on four widely used statistical distances set as the loss functions,including Kullback-Leibler divergence(KL-divergence),Jensen-Shannon divergence(JS-divergence),total variation distance,and maximum mean discrepancy.Our numerical experiment shows a promising result that the variable-depth VQC model works better than the original VQC in the generative learning tasks.

An inverse design method for supercritical airfoil based on conditional generative models

Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.

A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions

Short-term building energy predictions serve as one of the fundamental tasks in building operation management.While large numbers of studies have explored the value of various supervised machine learning techniques in energy predictions,few studies have addressed the potential data shortage problem in developing data-driven models.One promising solution is data augmentation,which aims to enrich existing building data resources for reliable predictive modeling.This study proposes a deep generative modeling-based data augmentation strategy for improving short-term building energy predictions.Two types of conditional variational autoencoders have been designed for synthetic energy data generation using fully connected and one-dimensional convolutional layers respectively.Data experiments have been designed to evaluate the value of data augmentation using actual measurements from 52 buildings.The results indicate that conditional variational autoencoders are capable of generating high-quality synthetic data samples,which in turns helps to enhance the accuracy in short-term building energy predictions.The average performance enhancement ratios in terms of CV-RMSE range between 12%and 18%.Practical guidelines have been obtained to ensure the validity and quality of synthetic building energy data.The research outcomes are valuable for enhancing the robustness and reliability of data-driven models for smart building operation management.

Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies

For reservoirs with complex non-Gaussian geological characteristics,such as carbonate reservoirs or reservoirs with sedimentary facies distribution,it is difficult to implement history matching directly,especially for the ensemble-based data assimilation methods.In this paper,we propose a multi-source information fused generative adversarial network(MSIGAN)model,which is used for parameterization of the complex geologies.In MSIGAN,various information such as facies distribution,microseismic,and inter-well connectivity,can be integrated to learn the geological features.And two major generative models in deep learning,variational autoencoder(VAE)and generative adversarial network(GAN)are combined in our model.Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation(ESMDA)method to conduct history matching.We tested the proposed method on two reservoir models with fluvial facies.The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features,which can promote the accuracy of history matching.

Designing natural product-like virtual libraries using deep molecule generative models

Natural products（NPs） have long been recognized as a valuable resource for drug discovery, and bringing NP-related features to virtual libraries is believed to be an effective way to increase the coverage of druggable chemical space. Here, deep learning-based molecule generative model, which is a recent technique in de novo molecule design, was applied to generate virtual libraries with NP-like properties. Results demonstrated that the model was effective in generating molecules that highly resemble NPs. Moreover, the model was also found to be capable of generating NP-like molecules that were also easy to synthesize, significantly increasing the practical value of the compound library.

Structural properties and generative model of non-giant connected components in social networks

Most previous studies have mainly focused on the analyses of one entire network(graph) or the giant connected components of networks. In this paper, we investigate the disconnected components(non-giant connected component) of some real social networks, and report some interesting discoveries about structural properties of disconnected components. We study three diverse, real networks and compute the significance profile of each component. We discover some similarities in the local structure between the giant connected component and disconnected components in diverse social networks. Then we discuss how to detect network attacks based on the local structure properties of networks. Furthermore, we propose an empirical generative model called i Friends to generate networks that follow our observed patterns.

Improved discriminative training for generative model

This article proposes a model combination method to enhance the discriminability of the generative model. Generative and discriminative models have different optimization objectives and have their own advantages and drawbacks. The method proposed in this article intends to strike a balance between the two models mentioned above. It extracts the discriminative parameter from the generative model and generates a new model based on a multi-model combination. The weight for combining is determined by the ratio of the inter-variance to the intra-variance of the classes. The higher the ratio is, the greater the weight is, and the more discriminative the model will be. Experiments on speech recognition demonstrate that the performance of the new model outperforms the model trained with the traditional generative method.

A brief introductory review to deep generative models for civil structural health monitoring

The use of deep generative models(DGMs)such as variational autoencoders,autoregressive models,flow-based models,energy-based models,generative adversarial networks,and diffusion models has been advantageous in various disciplines due to their high data generative skills.Using DGMs has become one of the most trending research topics in Artificial Intelligence in recent years.On the other hand,the research and development endeavors in the civil structural health monitoring(SHM)area have also been very progressive owing to the increasing use of Machine Learning techniques.As such,some of the DGMs have also been used in the civil SHM field lately.This short review communication paper aims to assist researchers in the civil SHM field in understanding the fundamentals of DGMs and,consequently,to help initiate their use for current and possible future engineering applications.On this basis,this study briefly introduces the concept and mechanism of different DGMs in a comparative fashion.While preparing this short review communication,it was observed that some DGMs had not been utilized or exploited fully in the SHM area.Accordingly,some representative studies presented in the civil SHM field that use DGMs are briefly overviewed.The study also presents a short comparative discussion on DGMs,their link to the SHM,and research directions.

Federated Learning Model for Auto Insurance Rate Setting Based on Tweedie Distribution

In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.

Modeling the effect of stand and site characteristics on the probability of mistletoe infestation in Scots pine stands using remote sensing data

Over the past decade,the presence of mistletoe(Viscum album ssp.austriacum)in Scots pine stands has increased in many European countries.Understanding the factors that influence the occurrence of mistletoe in stands is key to making appropriate forest management decisions to limit damage and prevent the spread of mistletoe in the future.Therefore,the main objective of this study was to determine the probability of mistletoe occurrence in Scots pine stands in relation to stand-related endogenous factors such as age,top height,and stand density,as well as topographic and edaphic factors.We used unmanned aerial vehicle(UAV)imagery from 2,247 stands to detect mistletoe in Scots pine stands,while majority stand and site characteristics were calculated from airborne laser scanning(ALS)data.Information on stand age and site type from the State Forest database were also used.We found that mistletoe infestation in Scots pine stands is influenced by stand and site characteristics.We documented that the densest,tallest,and oldest stands were more susceptible to mistletoe infestation.Site type and specific microsite conditions associated with topography were also important factors driving mistletoe occurrence.In addition,climatic water balance was a significant factor in increasing the probability of mistletoe occurrence,which is important in the context of predicted temperature increases associated with climate change.Our results are important for better understanding patterns of mistletoe infestation and ecosystem functioning under climate change.In an era of climate change and technological development,the use of remote sensing methods to determine the risk of mistletoe infestation can be a very useful tool for managing forest ecosystems to maintain forest sustainability and prevent forest disturbance.

Analysis of the inflection points of height-diameter models

The inflection point is an important feature of sigmoidal height-diameter(H-D)models.It is often cited as one of the properties favoring sigmoidal model forms.However,there are very few studies analyzing the inflection points of H-D models.The goals of this study were to theoretically and empirically examine the behaviors of inflection points of six common H-D models with a regional dataset.The six models were the Wykoff(WYK),Schumacher(SCH),Curtis(CUR),HossfeldⅣ(HOS),von Bertalanffy-Richards(VBR),and Gompertz(GPZ)models.The models were first fitted in their base forms with tree species as random effects and were then expanded to include functional traits and spatial distribution.The distributions of the estimated inflection points were similar between the two-parameter models WYK,SCH,and CUR,but were different between the threeparameter models HOS,VBR,and GPZ.GPZ produced some of the largest inflection points.HOS and VBR produced concave H-D curves without inflection points for 12.7%and 39.7%of the tree species.Evergreen species or decreasing shade tolerance resulted in larger inflection points.The trends in the estimated inflection points of HOS and VBR were entirely opposite across the landscape.Furthermore,HOS could produce concave H-D curves for portions of the landscape.Based on the studied behaviors,the choice between two-parameter models may not matter.We recommend comparing seve ral three-parameter model forms for consistency in estimated inflection points before deciding on one.Believing sigmoidal models to have inflection points does not necessarily mean that they will produce fitted curves with one.Our study highlights the need to integrate analysis of inflection points into modeling H-D relationships.

Generative Adversarial Networks:Introduction and Outlook

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning idea.The goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that distribution.Since their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application fields.Then, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

Benchmarking deep learning-based models on nanophotonic inverse design problems

Photonic inverse design concerns the problem of finding photonic structures with target optical properties.However,traditional methods based on optimization algorithms are time-consuming and computationally expensive.Recently,deep learning-based approaches have been developed to tackle the problem of inverse design efficiently.Although most of these neural network models have demonstrated high accuracy in different inverse design problems,no previous study has examined the potential effects under given constraints in nanomanufacturing.Additionally,the relative strength of different deep learning-based inverse design approaches has not been fully investigated.Here,we benchmark three commonly used deep learning models in inverse design:Tandem networks,Variational Auto-Encoders,and Generative Adversarial Networks.We provide detailed comparisons in terms of their accuracy,diversity,and robustness.We find that tandem networks and Variational Auto-Encoders give the best accuracy,while Generative Adversarial Networks lead to the most diverse predictions.Our findings could serve as a guideline for researchers to select the model that can best suit their design criteria and fabrication considerations.In addition,our code and data are publicly available,which could be used for future inverse design model development and benchmarking.

Predicting Lung Cancers Using Epidemiological Data:A Generative-Discriminative Framework

Predictive models for assessing the risk of developing lung cancers can help identify high-risk individuals with the aim of recommending further screening and early intervention.To facilitate pre-hospital self-assessments,some studies have exploited predictive models trained on non-clinical data(e.g.,smoking status and family history).The performance of these models is limited due to not considering clinical data(e.g.,blood test and medical imaging results).Deep learning has shown the potential in processing complex data that combine both clinical and non-clinical information.However,predicting lung cancers remains difficult due to the severe lack of positive samples among follow-ups.To tackle this problem,this paper presents a generative-discriminative framework for improving the ability of deep learning models to generalize.According to the proposed framework,two nonlinear generative models,one based on the generative adversarial network and another on the variational autoencoder,are used to synthesize auxiliary positive samples for the training set.Then,several discriminative models,including a deep neural network(DNN),are used to assess the lung cancer risk based on a comprehensive list of risk factors.The framework was evaluated on over 55000 subjects questioned between January 2014 and December 2017,with 699 subjects being clinically diagnosed with lung cancer between January 2014 and August 2019.According to the results,the best performing predictive model built using the proposed framework was based on DNN.It achieved an average sensitivity of 76.54%and an area under the curve of 69.24%in distinguishing between the cases of lung cancer and normal cases on test sets.

Generative Trapdoors for Public Key Cryptography Based on Automatic Entropy Optimization

Trapdoor is a key component of public key cryptography design which is the essential security foundation of modern cryptography.Normally,the traditional way in designing a trapdoor is to identify a computationally hard problem,such as the NPC problems.So the trapdoor in a public key encryption mechanism turns out to be a type of limited resource.In this paper,we generalize the methodology of adversarial learning model in artificial intelligence and introduce a novel way to conveniently obtain sub-optimal and computationally hard trapdoors based on the automatic information theoretic search technique.The basic routine is constructing a generative architecture to search and discover a probabilistic reversible generator which can correctly encoding and decoding any input messages.The architecture includes a trapdoor generator built on a variational autoencoder(VAE)responsible for searching the appropriate trapdoors satisfying a maximum of entropy,a random message generator yielding random noise,and a dynamic classifier taking the results of the two generator.The evaluation of our construction shows the architecture satisfying basic indistinguishability of outputs under chosen-plaintext attack model(CPA)and high efficiency in generating cheap trapdoors.

Generative Neural Network Based Spectrum Sharing Using Linear Sum Assignment Problems

Spectrum management and resource allocation(RA)problems are challenging and critical in a vast number of research areas such as wireless communications and computer networks.The traditional approaches for solving such problems usually consume time and memory,especially for large-size problems.Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems,especially the generative model of the deep neural networks.In this work,we propose a resource allocation deep autoencoder network,as one of the promising generative models,for enabling spectrum sharing in underlay device-to-device(D2D)communication by solving linear sum assignment problems(LSAPs).Specifically,we investigate the performance of three different architectures for the conditional variational autoencoders(CVAE).The three proposed architecture are the convolutional neural network(CVAECNN)autoencoder,the feed-forward neural network(CVAE-FNN)autoencoder,and the hybrid(H-CVAE)autoencoder.The simulation results show that the proposed approach could be used as a replacement of the conventional RA techniques,such as the Hungarian algorithm,due to its ability to find solutions of LASPs of different sizes with high accuracy and very fast execution time.Moreover,the simulation results reveal that the accuracy of the proposed hybrid autoencoder architecture outperforms the other proposed architectures and the state-of-the-art DNN techniques.

Diagnostics in generalized nonlinear models based on maximum L_q-likelihood estimation

In order to detect whether the data conforms to the given model, it is necessary to diagnose the data in the statistical way. The diagnostic problem in generalized nonlinear models based on the maximum Lq-likelihood estimation is considered. Three diagnostic statistics are used to detect whether the outliers exist in the data set. Simulation results show that when the sample size is small, the values of diagnostic statistics based on the maximum Lq-likelihood estimation are greater than the values based on the maximum likelihood estimation. As the sample size increases, the difference between the values of the diagnostic statistics based on two estimation methods diminishes gradually. It means that the outliers can be distinguished easier through the maximum Lq-likelihood method than those through the maximum likelihood estimation method.

A Generalized Layered Radiative Transfer Model in the Vegetation Canopy

In this paper, a generalized layered model for radiation transfer in canopy with high vertical resolution is developed. Differing from the two-stream approximate radiation transfer model commonly used in the land surface models, the generalized model takes into account the effect of complicated canopy morphology and inhomogeneous optical properties of leaves on radiation transfer within the canopy. In the model, the total leaf area index （LAI） of the canopy is divided into many layers. At a given layer, the influences of diffuse radiation angle distributions and leaf angle distributions on radiation transfer within the canopy are considered. The derivation of equations serving the model are described in detail, and these can deal with various diffuse radiation transfers in quite broad categories of canopy with quite inhomogeneons vertical structures and uneven leaves with substantially different optical properties of adaxial and abaxial faces of the leaves. The model is used to simulate the radiation transfer for canopies with horizontal leaves to validate the generalized model. Results from the model are compared with those from the two-stream scheme, and differences between these two models are discussed.

Optimization of environmental variables in habitat suitability modeling for mantis shrimp Oratosquilla oratoria in the Haizhou Bay and adjacent waters

Habitat suitability index(HSI)models have been widely used to analyze the relationship between species abundance and environmental factors,and ultimately inform management of marine species.The response of species abundance to each environmental variable is different and habitat requirements may change over life history stages and seasons.Therefore,it is necessary to determine the optimal combination of environmental variables in HSI modelling.In this study,generalized additive models(GAMs)were used to determine which environmental variables to be included in the HSI models.Significant variables were retained and weighted in the HSI model according to their relative contribution(%)to the total deviation explained by the boosted regression tree(BRT).The HSI models were applied to evaluate the habitat suitability of mantis shrimp Oratosquilla oratoria in the Haizhou Bay and adjacent areas in 2011 and 2013–2017.Ontogenetic and seasonal variations in HSI models of mantis shrimp were also examined.Among the four models(non-optimized model,BRT informed HSI model,GAM informed HSI model,and both BRT and GAM informed HSI model),both BRT and GAM informed HSI model showed the best performance.Four environmental variables(bottom temperature,depth,distance offshore and sediment type)were selected in the HSI models for four groups(spring-juvenile,spring-adult,falljuvenile and fall-adult)of mantis shrimp.The distribution of habitat suitability showed similar patterns between juveniles and adults,but obvious seasonal variations were observed.This study suggests that the process of optimizing environmental variables in HSI models improves the performance of HSI models,and this optimization strategy could be extended to other marine organisms to enhance the understanding of the habitat suitability of target species.