Mesh representation matters:investigating the influence of different mesh features on perceptual and spatial fidelity of deep 3D morphable models

Background Deep 3D morphable models(deep 3DMMs)play an essential role in computer vision.They are used in facial synthesis,compression,reconstruction and animation,avatar creation,virtual try-on,facial recognition systems and medical imaging.These applications require high spatial and perceptual quality of synthesised meshes.Despite their significance,these models have not been compared with different mesh representations and evaluated jointly with point-wise distance and perceptual metrics.Methods We compare the influence of different mesh representation features to various deep 3DMMs on spatial and perceptual fidelity of the reconstructed meshes.This paper proves the hypothesis that building deep 3DMMs from meshes represented with global representations leads to lower spatial reconstruction error measured with L_(1) and L_(2) norm metrics and underperforms on perceptual metrics.In contrast,using differential mesh representations which describe differential surface properties yields lower perceptual FMPD and DAME and higher spatial fidelity error.The influence of mesh feature normalisation and standardisation is also compared and analysed from perceptual and spatial fidelity perspectives.Results The results presented in this paper provide guidance in selecting mesh representations to build deep 3DMMs accordingly to spatial and perceptual quality objectives and propose combinations of mesh representations and deep 3DMMs which improve either perceptual or spatial fidelity of existing methods.

Classification of Conversational Sentences Using an Ensemble Pre-Trained Language Model with the Fine-Tuned Parameter

Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.

Chaos game representation walk model for the protein sequences

A new chaos game representation of protein sequences based on the detailed hydrophobic-hydrophilic （HP） model has been proposed by Yu et al （Physica A 337（2004） 171）. A CGR-walk model is proposed based on the new CGR coordinates for the protein sequences from complete genomes in the present paper. The new CCR coordinates based on the detailed HP model are converted into a time series, and a long-memory ARFIMA（p, d, q） model is introduced into the protein sequence analysis. This model is applied to simulating real CCR-walk sequence data of twelve protein sequences. Remarkably long-range correlations are uncovered in the data and the results obtained from these models are reasonably consistent with those available from the ARFIMA（p, d, q） model.

Research on system-of-systems combat simulation model formal specification and representation

To makesystem-of-systems combat simulation models easy to be developed and reused, simulation model formal specification and representation are researched. According to the view of system-of-systems combat simulation, and based on DEVS, the simulation model＇s fundamental formalisms are explored. It includes entity model, system-of-systems model and experiment model. It also presents rigorous formal specification. XML data exchange standard is combined to design the XML based language, SCSL, to support simulation model representation. The corresponding relationship between SCSL and simulation model formalism is discussed and the syntax and semantics of elements in SCSL are detailed. Based on simulation model formal specification, the abstract simulation algorithm is given and SCSL virtual machine, which is capable of automatically interpreting and executing simulation model represented by SCSL, is designed. Finally an application case is presented, which can show the validation of the theory and verification of SCSL.

An iterative data-driven turbulence modeling framework based on Reynolds stress representation

Data-driven turbulence modeling studies have reached such a stage that the basic framework is settled,but several essential issues remain that strongly affect the performance.Two problems are studied in the current research:(1)the processing of the Reynolds stress tensor and(2)the coupling method between the machine learning model and flow solver.For the Reynolds stress processing issue,we perform the theoretical derivation to extend the relevant tensor arguments of Reynolds stress.Then,the tensor representation theorem is employed to give the complete irreducible invariants and integrity basis.An adaptive regularization term is employed to enhance the representation performance.For the coupling issue,an iterative coupling framework with consistent convergence is proposed and then applied to a canonical separated flow.The results have high consistency with the direct numerical simulation true values,which proves the validity of the current approach.

Application of Cochlear Model in Speech Analysis/Synthesis Using Sinusoidal Representation

A sinusoidal representation of speech and a cochlear model are used to extract speech parameters in this paper, and a speech analysis/synthesis system controlled by the auditory spectrum is developed with the model. The computer simulation shows that speech can be synthesized with only 12 parameters per frame on the average. The method has the advantages of few parameters, low complexity and high performance of speech representation. The synthetic speech has high intelligibility.

A Parameterization of Cooling Rate Calculation under the Non-LTE Condition: Multi-Level Model

Calculations of cooling rate by CO2 15 μm band in the earth's upper mesosphere and lower thermosphere be-come very difficult because of the non-LTE. This is primarily due to the nonlinear vibration-vibrational (VV) transition processes between CO, molecules in different states. This paper suggests that the non-LTE source function be parameterized as a linear combination of two limiting source functions. One limiting source function neglects the VV transitions while the other limiting source function assumes VV transitions being dominant. These two limiting source functions can be derived by linear models. The parameterization schemes proposed here can be applied to the general circulation models including those non-LTE regions.

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

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

Using Vector Representation of Propositions and Actions for STRIPS Action Model Learning

Action model learning has become a hot topic in knowledge engineering for automated planning.A key problem for learning action models is to analyze state changes before and after action executions from observed"plan traces".To support such an analysis,a new approach is proposed to partition propositions of plan traces into states.First,vector representations of propositions and actions are obtained by training a neural network called Skip-Gram borrowed from the area of natural language processing(NLP).Then,a type of semantic distance among propositions and actions is defined based on their similarity measures in the vector space.Finally,k-means and k-nearest neighbor(kNN)algorithms are exploited to map propositions to states.This approach is called state partition by word vector(SPWV),which is implemented on top of a recent action model learning framework by Rao et al.Experimental results on the benchmark domains show that SPWV leads to a lower error rate of the learnt action model,compared to the probability based approach for state partition that was developed by Rao et al.

Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

Stance detection is the task of attitude identification toward a standpoint.Previous work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level abstracting.Moreover,because the target is not always mentioned in the text,most methods have ignored target information.In order to solve these problems,we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory(LSTM)and the excellent extracting performance of convolutional neural networks(CNNs).The method can obtain multi-level features that consider both local and global features.We also introduce attention mechanisms to magnify target information-related features.Furthermore,we employ sparse coding to remove noise to obtain characteristic features.Performance was improved by using sparse coding on the basis of attention employment and feature extraction.We evaluate our approach on the SemEval-2016Task 6-A public dataset,achieving a performance that exceeds the benchmark and those of participating teams.

A Phrase Topic Model Based on Distributed Representation

Traditional topic models have been widely used for analyzing semantic topics from electronic documents.However,the obvious defects of topic words acquired by them are poor in readability and consistency.Only the domain experts are possible to guess their meaning.In fact,phrases are the main unit for people to express semantics.This paper presents a Distributed Representation-Phrase Latent Dirichlet Allocation(DR-Phrase LDA)which is a phrase topic model.Specifically,we reasonably enhance the semantic information of phrases via distributed representation in this model.The experimental results show the topics quality acquired by our model is more readable and consistent than other similar topic models.

Knowledge representation and rule-based solution system for dynamic programming model

A knowledge representation has been proposed using the state space theory of Artificial Intelligence for Dynamic Programming Model, in which a model can be defined as a six tuple M=(I,G,O,T,D,S). A building block modeling method uses the modules of a six tuple to form a rule based solution model. Moreover, a rule based system has been designed and set up to solve the Dynamic Programming Model. This knowledge based representation can be easily used to express symbolical knowledge and dynamic characteristics for Dynamic Programming Model, and the inference based on the knowledge in the process of solving Dynamic Programming Model can also be conveniently realized in computer.

Multi-level biomechanical models for rehabilitation engineering

Rehabilitation engineering aims in the upmost degree to restore the lost functions for those persons with physical disability. Biomechanical modeling has been widely used for different purposes in rehabilitation engineering to understand the bio-

Effect of Aluminum Hydroxide Adjuvant on the Immunogenicity of the 2009 Pandemic Influenza A/H1N1 Vaccine:Multi-level Modeling of Data with Repeated Measures

Objective To evaluate the effect of the aluminum hydroxide （Al-OH） adjuvant on the 2009 pandemic influenza A/H1N1 （pH1N1） vaccine. Methods In a multicenter, double-blind, randomized, placebo-controlled trial, participants received two doses of split-virion formulation containing 15 ug hemagglutinin antigen, with or without aluminum hydroxide （N-OH）. We classified the participants into six age categories （〉61 years, 41-60 years, 19-40 years, 13-18 years, 8-12 years, and 3-7 years） and obtained four blood samples from each participant on days 0, 21, 35, and 42 following the first dose of immunization. We assessed vaccine immunogenicity by measuring the geometric mean titer （GMT） of hemagglutination inhibiting antibody. We used a two-level model to evaluate the fixed effect of aluminum Al-OH and other factors, accounting for repeated measures. Results The predictions of repeated measurement on GMTs of formulations with or without Al-OH, were 80.35 and 112.72, respectively. Al-OH significantly reduced immunogenicity after controlling for time post immunization, age-group and gender. Conclusion The Al-OH adjuvant does not increase but actually reduces the immunogenicity of the split-virion pH1N1 vaccine.

A General Representation of Geometrical Solution Model for Predicting Ternary Thermodynamic Properties

The existing geometrical solution models for predicting ternary thermodynamic properties from relevant binary ones have been analysed,and a general representation was proposed in an integral form on the bases of these models.

Explicit Algebraic Stress Model for Three-Dimensional Turbulent Buoyant Flows Derived Using Tensor Representation

An explicit algebraic stress model (EASM) has been formulated for two-dimensional turbulent buoyant flows using a five-term tensor representation in a prior study. The derivation was based on partitioning the buoyant flux tensor into a two-dimensional and a three-dimensional component. The five-term basis was formed with the two-dimensional component of the buoyant flux tensor. As such, the derived EASM is limited to two-dimensional flows only. In this paper, a more general approach using a seven-term representation without partitioning the buoyant flux tensor is used to derive an EASM valid for two- and three-dimensional turbulent buoyant flows. Consequently, the basis tensors are formed with the fully three-dimensional buoyant flux tensor. The derived EASM has the two-dimensional flow as a special case. The matrices and the representation coefficients are further simplified using a four-term representation. When this four-term representation model is applied to calculate two-dimensional homogeneous buoyant flows, the results are essentially identical with those obtained previously using the two-dimensional component of the buoyant flux tensor. Therefore, the present approach leads to a more general EASM formulation that is equally valid for two- and three-dimensional turbulent buoyant flows.

Solid model edit distance: a multi-application and multi-level schema for CAD model retrieval

We present the solid model edit distance(SMED),a powerful and flexible paradigm for exploiting shape similarities amongst CAD models.It is designed to measure the magnitude of distortions between two CAD models in boundary representation(B-rep).We give the formal definition by analogy with graph edit distance,one of the most popular graph matching methods.To avoid the expensive computational cost potentially caused by exact computation,an approximate procedure based on the alignment of local structure sets is provided in addition.In order to verify the flexibility,we make intensive investigations on three typical applications in manufacturing industry,and describe how our method can be adapted to meet the various requirements.Furthermore,a multilevel method is proposed to make further improvements of the presented algorithm on both effectiveness and efficiency,in which the models are hierarchically segmented into the configurations of features.Experiment results show that SMED serves as a reasonable measurement of shape similarity for CAD models,and the proposed approach provides remarkable performance on a real-world CAD model database.

Multi-Layer Deep Sparse Representation for Biological Slice Image Inpainting

Biological slices are an effective tool for studying the physiological structure and evolutionmechanism of biological systems.However,due to the complexity of preparation technology and the presence of many uncontrollable factors during the preparation processing,leads to problems such as difficulty in preparing slice images and breakage of slice images.Therefore,we proposed a biological slice image small-scale corruption inpainting algorithm with interpretability based on multi-layer deep sparse representation,achieving the high-fidelity reconstruction of slice images.We further discussed the relationship between deep convolutional neural networks and sparse representation,ensuring the high-fidelity characteristic of the algorithm first.A novel deep wavelet dictionary is proposed that can better obtain image prior and possess learnable feature.And multi-layer deep sparse representation is used to implement dictionary learning,acquiring better signal expression.Compared with methods such as NLABH,Shearlet,Partial Differential Equation(PDE),K-Singular Value Decomposition(K-SVD),Convolutional Sparse Coding,and Deep Image Prior,the proposed algorithm has better subjective reconstruction and objective evaluation with small-scale image data,which realized high-fidelity inpainting,under the condition of small-scale image data.And theOn2-level time complexitymakes the proposed algorithm practical.The proposed algorithm can be effectively extended to other cross-sectional image inpainting problems,such as magnetic resonance images,and computed tomography images.

Model Predictive Control Strategy of Multi-Port Interline DC Power Flow Controller

There are issues with flexible DC transmission system such as a lack of control freedom over power flow.In order to tackle these issues,a DC power flow controller(DCPFC)is incorporated into a multi-terminal,flexible DC power grid.In recent years,a multi-port DC power flow controller based on a modular multi-level converter has become a focal point of research due to its simple structure and robust scalability.This work proposes a model predictive control(MPC)strategy for multi-port interline DC power flow controllers in order to improve their steady-state dynamic performance.Initially,the mathematical model of a multi-terminal DC power grid with a multi-port interline DC power flow controller is developed,and the relationship between each regulated variable and control variable is determined;The power flow controller is then discretized,and the cost function and weight factor are built with numerous control objectives.Sub module sorting method and nearest level approximation modulation regulate the power flow controller;Lastly,theMATLAB/Simulink simulation platformis used to verify the correctness of the establishedmathematicalmodel and the control performance of the suggestedMPC strategy.Finally,it is demonstrated that the control strategy possesses the benefits of robust dynamic performance,multiobjective control,and a simple structure.

State Accurate Representation and Performance Prediction Algorithm Optimization for Industrial Equipment Based on Digital Twin

The combination of the Industrial Internet of Things(IIoT)and digital twin(DT)technology makes it possible for the DT model to realize the dynamic perception of equipment status and performance.However,conventional digital modeling is weak in the fusion and adjustment ability between virtual and real information.The performance prediction based on experience greatly reduces the inclusiveness and accuracy of the model.In this paper,a DT-IIoT optimization model is proposed to improve the real-time representation and prediction ability of the key equipment state.Firstly,a global real-time feedback and the dynamic adjustment mechanism is established by combining DT-IIoT with algorithm optimization.Secondly,a strong screening dual-model optimization(SSDO)prediction method based on Stacking integration and fusion is proposed in the dynamic regulation mechanism.Lightweight screening and multi-round optimization are used to improve the prediction accuracy of the evolution model.Finally,tak-ing the boiler performance of a power plant in Shanxi as an example,the accurate representation and evolution prediction of boiler steam quantity is realized.The results show that the real-time state representation and life cycle performance prediction of large key equipment is optimized through these methods.The self-lifting ability of the Stacking integration and fusion-based SSDO prediction method is 15.85%on average,and the optimal self-lifting ability is 18.16%.The optimization model reduces the MSE loss from the initial 0.318 to the optimal 0.1074,and increases R2 from the initial 0.731 to the optimal 0.9092.The adaptability and reliability of the model are comprehensively improved,and better prediction and analysis results are achieved.This ensures the stable operation of core equipment,and is of great significance to comprehensively understanding the equipment status and performance.