MKEAH:Multimodal knowledge extraction and accumulation based on hyperplane embedding for knowledge-based visual question answering

Background External knowledge representations play an essential role in knowledge-based visual question and answering to better understand complex scenarios in the open world.Recent entity-relationship embedding approaches are deficient in representing some complex relations,resulting in a lack of topic-related knowledge and redundancy in topic-irrelevant information.Methods To this end,we propose MKEAH:Multimodal Knowledge Extraction and Accumulation on Hyperplanes.To ensure that the lengths of the feature vectors projected onto the hyperplane compare equally and to filter out sufficient topic-irrelevant information,two losses are proposed to learn the triplet representations from the complementary views:range loss and orthogonal loss.To interpret the capability of extracting topic-related knowledge,we present the Topic Similarity(TS)between topic and entity-relations.Results Experimental results demonstrate the effectiveness of hyperplane embedding for knowledge representation in knowledge-based visual question answering.Our model outperformed state-of-the-art methods by 2.12%and 3.24%on two challenging knowledge-request datasets:OK-VQA and KRVQA,respectively.Conclusions The obvious advantages of our model in TS show that using hyperplane embedding to represent multimodal knowledge can improve its ability to extract topic-related knowledge.

Classification of aviation incident causes using LGBM with improved cross-validation

Aviation accidents are currently one of the leading causes of significant injuries and deaths worldwide. This entices researchers to investigate aircraft safety using data analysis approaches based on an advanced machine learning algorithm.To assess aviation safety and identify the causes of incidents, a classification model with light gradient boosting machine (LGBM)based on the aviation safety reporting system (ASRS) has been developed. It is improved by k-fold cross-validation with hybrid sampling model (HSCV), which may boost classification performance and maintain data balance. The results show that employing the LGBM-HSCV model can significantly improve accuracy while alleviating data imbalance. Vertical comparison with other cross-validation (CV) methods and lateral comparison with different fold times comprise the comparative approach. Aside from the comparison, two further CV approaches based on the improved method in this study are discussed:one with a different sampling and folding order, and the other with more CV. According to the assessment indices with different methods, the LGBMHSCV model proposed here is effective at detecting incident causes. The improved model for imbalanced data categorization proposed may serve as a point of reference for similar data processing, and the model’s accurate identification of civil aviation incident causes can assist to improve civil aviation safety.

Knowledge-Based Efficient N-1 Analysis Calculation Method for Urban Distribution Networks with CIM File Data

The N-1 criterion is a critical factor for ensuring the reliable and resilient operation of electric power distribution networks.However,the increasing complexity of distribution networks and the associated growth in data size have created a significant challenge for distribution network planners.To address this issue,we propose a fast N-1 verification procedure for urban distribution networks that combines CIM file data analysis with MILP-based mathematical modeling.Our proposed method leverages the principles of CIM file analysis for distribution network N-1 analysis.We develop a mathematical model of distribution networks based on CIM data and transfer it into MILP.We also take into account the characteristics of medium voltage distribution networks after a line failure and select the feeder section at the exit of each substation with a high load rate to improve the efficiency of N-1 analysis.We validate our approach through a series of case studies and demonstrate its scalability and superiority over traditional N-1 analysis and heuristic optimization algorithms.By enabling online N-1 analysis,our approach significantly improves the work efficiency of distribution network planners.In summary,our proposed method provides a valuable tool for distribution network planners to enhance the accuracy and efficiency of their N-1 analyses.By leveraging the advantages of CIM file data analysis and MILP-based mathematical modeling,our approach contributes to the development of more resilient and reliable electric power distribution networks.

基于Cross-Validation的小波自适应去噪方法

小波去噪算法中,阈值的选择非常关键.提出一种自适应阈值选择算法.该算法先通过Cross-Validation方法将噪声干扰信号分成两个子信号,一个用于阈值处理,一个用作参考信号;再采用最深梯度法来寻求一个最优去噪阈值.仿真和实验结果表明:在均方误差意义上,所提算法去噪效果优于Donoho等提出的VisuShrink和SureShrink两种去噪算法,且不需要带噪信号的任何'先验信息',适应于实际信号去噪处理.

Knowledge-Based Classification in Automated Soil Mapping

A machine-learning approach was developed for automated building of knowledgebases for soil resources mapping by using a classification tree to generate knowledge from trainingdata. With this method, building a knowledge base for automated soil mapping was easier than usingthe conventional knowledge acquisition approach. The knowledge base built by classification tree wasused by the knowledge classifier to perform the soil type classification of Longyou County,Zhejiang Province, China using Landsat TM bi-temporal images and CIS data. To evaluate theperformance of the resultant knowledge bases, the classification results were compared to existingsoil map based on a field survey. The accuracy assessment and analysis of the resultant soil mapssuggested that the knowledge bases built by the machine-learning method was of good quality formapping distribution model of soil classes over the study area.

Knowledge-based bridge detection from SAR images

Automatic bridge detection is an important application of SAR images. Differed from the classical CFAR method, a new knowledge-based bridge detection approach is proposed. The method not only uses the backscattering intensity difference between targets and background but also applies the contextual information and spatial relationship between objects. According to bridges＇ special characteristics and scattering properties in SAR images, the new knowledge-based method includes three processes： river segmentation, potential bridge areas detection and bridge discrimination. The application to AIRSAR data shows that the new method is not sensitive to rivers＇ shape. Moreover, this method can detect bridges successfully when river segmentation is not very exact and is more robust than the radius projection method.

New Knowledge-based Genetic Algorithm for Excavator Boom Structural Optimization

Due to the insufficiency of utilizing knowledge to guide the complex optimal searching, existing genetic algorithms fail to effectively solve excavator boom structural optimization problem. To improve the optimization efficiency and quality, a new knowledge-based real-coded genetic algorithm is proposed. A dual evolution mechanism combining knowledge evolution with genetic algorithm is established to extract, handle and utilize the shallow and deep implicit constraint knowledge to guide the optimal searching of genetic algorithm circularly. Based on this dual evolution mechanism, knowledge evolution and population evolution can be connected by knowledge influence operators to improve the conflgurability of knowledge and genetic operators. Then, the new knowledge-based selection operator, crossover operator and mutation operator are proposed to integrate the optimal process knowledge and domain culture to guide the excavator boom structural optimization. Eight kinds of testing algorithms, which include different genetic operators, arc taken as examples to solve the structural optimization of a medium-sized excavator boom. By comparing the results of optimization, it is shown that the algorithm including all the new knowledge-based genetic operators can more remarkably improve the evolutionary rate and searching ability than other testing algorithms, which demonstrates the effectiveness of knowledge for guiding optimal searching. The proposed knowledge-based genetic algorithm by combining multi-level knowledge evolution with numerical optimization provides a new effective method for solving the complex engineering optimization problem.

Structural Topology Design of Container Ship Based on Knowledge-Based Engineering and Level Set Method

Knowledge-Based Engineering （KBE） is introduced into the ship structural design in this paper. From the implementation of KBE, the design solutions for both Rules Design Method （RDM） and Interpolation Design Method （IDM） are generated. The corresponding Finite Element （FE） models are generated. Topological design of the longitudinal structures is studied where the Gaussian Process （GP） is employed to build the surrogate model for FE analysis. Multi-objective optimization methods inspired by Pareto Front are used to reduce the design tank weight and outer surface area simultaneously. Additionally, an enhanced Level Set Method （LSM） which employs implicit algorithm is applied to the topological design of typical bracket plate which is used extensively in ship structures. Two different sets of boundary conditions are considered. The proposed methods show satisfactory efficiency and accuracy.

Cross-Validation, Shrinkage and Variable Selection in Linear Regression Revisited

In deriving a regression model analysts often have to use variable selection, despite of problems introduced by data- dependent model building. Resampling approaches are proposed to handle some of the critical issues. In order to assess and compare several strategies, we will conduct a simulation study with 15 predictors and a complex correlation structure in the linear regression model. Using sample sizes of 100 and 400 and estimates of the residual variance corresponding to R2 of 0.50 and 0.71, we consider 4 scenarios with varying amount of information. We also consider two examples with 24 and 13 predictors, respectively. We will discuss the value of cross-validation, shrinkage and backward elimination (BE) with varying significance level. We will assess whether 2-step approaches using global or parameterwise shrinkage (PWSF) can improve selected models and will compare results to models derived with the LASSO procedure. Beside of MSE we will use model sparsity and further criteria for model assessment. The amount of information in the data has an influence on the selected models and the comparison of the procedures. None of the approaches was best in all scenarios. The performance of backward elimination with a suitably chosen significance level was not worse compared to the LASSO and BE models selected were much sparser, an important advantage for interpretation and transportability. Compared to global shrinkage, PWSF had better performance. Provided that the amount of information is not too small, we conclude that BE followed by PWSF is a suitable approach when variable selection is a key part of data analysis.

FAULT DIAGNOSIS OF ROTATING MACHINERY USING KNOWLEDGE-BASED FUZZY NEURAL NETWORK

A novel knowledge-based fuzzy neural network （KBFNN） for fault diagnosis is presented. Crude rules were extracted and the corresponding dependent factors and antecedent coverage factors were calculated firstly from the diagnostic sample based on rough sets theory. Then the number of rules was used to construct partially the structure of a fuzzy neural network and those factors were implemented as initial weights, with fuzzy output parameters being optimized by genetic algorithm. Such fuzzy neural network was called KBFNN. This KBFNN was utilized to identify typical faults of rotating machinery. Diagnostic results show that it has those merits of shorter training time and higher right diagnostic level compared to general fuzzy neural networks.

Knowledge-based potentials in bioinformatics: From a physicist's viewpoint

Biological raw data are growing exponentially, providing a large amount of information on what life is. It is believed that potential functions and the rules governing protein behaviors can be revealed from analysis on known native structures of proteins. Many knowledge-based potentials for proteins have been proposed. Contrary to most existing review articles which mainly describe technical details and applications of various potential models, the main foci for the discussion here are ideas and concepts involving the construction of potentials, including the relation between free energy and energy, the additivity of potentials of mean force and some key issues in potential construction. Sequence analysis is briefly viewed from an energetic viewpoint.

A Knowledge-based System for the Analysis of the Ability of Paying back Loans

This paper describes the development of a knowledgebased system (KBS) for determining whether or not, and under what conditions, a bank Ioan officer should grant a business loan to a company. The prototype system developed focuses on what is bank loans risks management, how to prevent risk by the analysis of the ability of paying back loans. The paper makes the structural analysis involved in the system's decision situation, the structured situation diagram or model, dependency diagram and the document needed by the KBS prototype system thus are developed. Through testing the samples from loan business, the quality for the analysis of the ability of paying back loans can be effectively evaluated by the KBS prototype system.

Integration of Decision-Support and Knowledge-Based Techniques in a Problem-Solving Strategy for Selection Problems

The limitations of traditional approaches to selection problems are examined. A problemsolving strategy is presented in which decision-support and knowledge-based techniques play complementary roles. An approach to the representation of knowledge to support the problem-solving strategy is presented which avoids commitment to a specific programming language or implementation environment. The problem of choosing a home is used to illustrate the representation of knowledge in a specific problem domain. Techniques for implementation of the problem-solving strategy are described. Knowledge elicitation techniques and their implementation in a development shell for application of the problem-solving strategy to any selection problem are also described.

Yarn Quality Prediction and Diagnosis Based on Rough Set and Knowledge-Based Artificial Neural Network

In the spinning process, some key process parameters( i. e.,raw material index inputs) have very strong relationship with the quality of finished products. The abnormal changes of these process parameters could result in various categories of faulty products. In this paper, a hybrid learning-based model was developed for on-line intelligent monitoring and diagnosis of the spinning process. In the proposed model, a knowledge-based artificial neural network( KBANN) was developed for monitoring the spinning process and recognizing faulty quality categories of yarn. In addition,a rough set( RS)-based rule extraction approach named RSRule was developed to discover the causal relationship between textile parameters and yarn quality. These extracted rules were applied in diagnosis of the spinning process, provided guidelines on improving yarn quality,and were used to construct KBANN. Experiments show that the proposed model significantly improve the learning efficiency, and its prediction precision is improved by about 5. 4% compared with the BP neural network model.

MY PERSONAL STUDY ON KNOWLEDGE-BASED ECONOMY

The Financial Crisis in Asia is having a negative impacion the economic development of China, but it also enlightens us. It makes us consider and take measures to avoid such a crisis. I have put forward six measures, one of which is to promote the transformation of S&T knowledge into productive forces.

ON THE CONSISTENCY OF CROSS-VALIDATIONIN NONLINEAR WAVELET REGRESSION ESTIMATION

For the nonparametric regression model Y-ni = g(x(ni)) + epsilon(ni)i = 1, ..., n, with regularly spaced nonrandom design, the authors study the behavior of the nonlinear wavelet estimator of g(x). When the threshold and truncation parameters are chosen by cross-validation on the everage squared error, strong consistency for the case of dyadic sample size and moment consistency for arbitrary sample size are established under some regular conditions.

Research on Knowledge-based Connecting Elements Modeling

Steps of manipulation is required to complete the m od eling of the connection elements such as bolt, pin and the like in commerce CAD system. It leads to low efficiency, difficulty to assure the relative position, impossibility to express rules and knowledge. Based on the inner character analy sis of interpart, detail modification and assembly relation of mechanical connec ting element, the idea, which extends the feature modeling of part to the interp art feature modeling for assembly purpose, is presented, and virtual part based connecting element modeling is proposed. Virtual part is a complement set of lo cal modification of part to be connected. In assembly modeling, base part is mod ified by Boolean operation between base part and virtual part. The modeling and assembly is finished just in one operation, at the same time the rules and knowl edge of the connection elements are encapsulated through virtual part. According to this mechanism, a knowledge-based connecting elements rapid design module i s developed on commerce software package UG with satisfying results.

Optimizing the atom types of proteins through iterative knowledge-based potentials

Knowledge-based scoring functions have been widely used for protein structure prediction, protein-small molecule, and protein-nucleic acid interactions, in which one critical step is to find an appropriate representation of protein structures. A key issue is to determine the minimal protein representations, which is important not only for developing of scoring func- tions but also for understanding the physics of protein folding. Despite significant progresses in simplifying residues into alphabets, few studies have been done to address the optimal number of atom types for proteins. Here, we have investigated the atom typing issue by classifying the 167 heavy atoms of proteins through 11 schemes with 1 to 20 atom types based on their physicochemical and functional environments. For each atom typing scheme, a statistical mechanics-based iterative method was used to extract atomic distance-dependent potentials from protein structures. The atomic distance-dependent pair potentials for different schemes were illustrated by several typical atom pairs with different physicochemical proper- ties. The derived potentials were also evaluated on a high-resolution test set of 148 diverse proteins for native structure recognition. It was found that there was a crossover around the scheme of four atom types in terms of the success rate as a function of the number of atom types, which means that four atom types may be used when investigating the basic folding mechanism of proteins. However, it was revealed by a close examination of typical potentials that 14 atom types were needed to describe the protein interactions at atomic level. The present study will be beneficial for the development of protein related scoring functions and the understanding of folding mechanisms.

Using Multiple Risk Factors and Generalized Linear Mixed Models with 5-Fold Cross-Validation Strategy for Optimal Carotid Plaque Progression Prediction

Background Cardiovascular diseases are closely linked to atherosclerotic plaque development and rupture.Plaque progression prediction is of fundamental significance to cardiovascular research and disease diagnosis,prevention,and treatment.Generalized linear mixed models(GLMM)is an extension of linear model for categorical responses while considering the correlation among observations.Methods Magnetic resonance image(MRI)data of carotid atheroscleroticplaques were acquired from 20 patients with consent obtained and 3D thin-layer models were constructed to calculate plaque stress and strain for plaque progression prediction.Data for ten morphological and biomechanical risk factors included wall thickness(WT),lipid percent(LP),minimum cap thickness(MinCT),plaque area(PA),plaque burden(PB),lumen area(LA),maximum plaque wall stress(MPWS),maximum plaque wall strain(MPWSn),average plaque wall stress(APWS),and average plaque wall strain(APWSn)were extracted from all slices for analysis.Wall thickness increase(WTI),plaque burden increase(PBI)and plaque area increase(PAI) were chosen as three measures for plaque progression.Generalized linear mixed models(GLMM)with 5-fold cross-validation strategy were used to calculate prediction accuracy for each predictor and identify optimal predictor with the highest prediction accuracy defined as sum of sensitivity and specificity.All 201 MRI slices were randomly divided into 4 training subgroups and 1 verification subgroup.The training subgroups were used for model fitting,and the verification subgroup was used to estimate the model.All combinations(total1023)of 10 risk factors were feed to GLMM and the prediction accuracy of each predictor were selected from the point on the ROC(receiver operating characteristic)curve with the highest sum of specificity and sensitivity.Results LA was the best single predictor for PBI with the highest prediction accuracy(1.360 1),and the area under of the ROC curve(AUC)is0.654 0,followed by APWSn(1.336 3)with AUC=0.6342.The optimal predictor among all possible combinations for PBI was the combination of LA,PA,LP,WT,MPWS and MPWSn with prediction accuracy=1.414 6(AUC=0.715 8).LA was once again the best single predictor for PAI with the highest prediction accuracy(1.184 6)with AUC=0.606 4,followed by MPWSn(1. 183 2)with AUC=0.6084.The combination of PA,PB,WT,MPWS,MPWSn and APWSn gave the best prediction accuracy(1.302 5)for PAI,and the AUC value is 0.6657.PA was the best single predictor for WTI with highest prediction accuracy(1.288 7)with AUC=0.641 5,followed by WT(1.254 0),with AUC=0.6097.The combination of PA,PB,WT,LP,MinCT,MPWS and MPWS was the best predictor for WTI with prediction accuracy as 1.314 0,with AUC=0.6552.This indicated that PBI was a more predictable measure than WTI and PAI. The combinational predictors improved prediction accuracy by 9.95%,4.01%and 1.96%over the best single predictors for PAI,PBI and WTI(AUC values improved by9.78%,9.45%,and 2.14%),respectively.Conclusions The use of GLMM with 5-fold cross-validation strategy combining both morphological and biomechanical risk factors could potentially improve the accuracy of carotid plaque progression prediction.This study suggests that a linear combination of multiple predictors can provide potential improvement to existing plaque assessment schemes.

A knowledge-based decision support system for engineering design

A knowledge-based decision supporting system, used for engineering design is introduced by describing the architecture, function, workflow of the system and its way of implementation. Based upon information composed of knowledge, models, data, cases, methods, etc, the system is designed to use such methods as knowledge-based reasoning, case-based reasoning, and multi-criteria evaluation techniques to provide effective tools to support the decision-making process.