Application of graph neural network and feature information enhancement in relation inference of sparse knowledge graph

At present,knowledge embedding methods are widely used in the field of knowledge graph(KG)reasoning,and have been successfully applied to those with large entities and relationships.However,in research and production environments,there are a large number of KGs with a small number of entities and relations,which are called sparse KGs.Limited by the performance of knowledge extraction methods or some other reasons(some common-sense information does not appear in the natural corpus),the relation between entities is often incomplete.To solve this problem,a method of the graph neural network and information enhancement is proposed.The improved method increases the mean reciprocal rank(MRR)and Hit@3 by 1.6%and 1.7%,respectively,when the sparsity of the FB15K-237 dataset is 10%.When the sparsity is 50%,the evaluation indexes MRR and Hit@10 are increased by 0.8%and 1.8%,respectively.

IMM/MHT FUSING FEATURE INFORMATION IN VISUAL TRACKING

In multi-target tracking,Multiple Hypothesis Tracking (MHT) can effectively solve the data association problem. However,traditional MHT can not make full use of motion information. In this work,we combine MHT with Interactive Multiple Model (IMM) estimator and feature fusion. New algorithm greatly improves the tracking performance due to the fact that IMM estimator provides better estimation and feature information enhances the accuracy of data association. The new algorithm is tested by tracking tropical fish in fish container. Experimental result shows that this algorithm can significantly reduce tracking lost rate and restrain the noises with higher computational effectiveness when compares with traditional MHT.

Data compensation based on the additional feature information for collaborative interactive operation with optical human motion capture system

As the effective capture region of optical motion capture system is limited by quantity,installation mode,resolution and focus of infrared cameras,the reflective markers on certain body parts(such as wrists,elbows,etc.)of multi-actual trainees may be obscured when they perform the collaborative interactive operation.To address this issue,motion data compensation method based on the additional feature information provided by the electromagnetic spatial position tracking equipment is proposed in this paper.The main working principle and detailed realization process of the proposed method are introduced step by step,and the practical implementation is presented to illustrate its validity and efficiency.The results show that the missing capture data and motion information of relevant obscured markers on arms can be retrieved with the proposed method,which can avoid the simulation motions of corresponding virtual operators being interrupted and deformed during the collaborative interactive operation process performed by multiactual trainees with optical human motion capture system in a limited capture range.

Exploiting Human Pose and Scene Information for Interaction Detection

Identifying human actions and interactions finds its use in manyareas, such as security, surveillance, assisted living, patient monitoring, rehabilitation,sports, and e-learning. This wide range of applications has attractedmany researchers to this field. Inspired by the existing recognition systems,this paper proposes a new and efficient human-object interaction recognition(HOIR) model which is based on modeling human pose and scene featureinformation. There are different aspects involved in an interaction, includingthe humans, the objects, the various body parts of the human, and the backgroundscene. Themain objectives of this research include critically examiningthe importance of all these elements in determining the interaction, estimatinghuman pose through image foresting transform (IFT), and detecting the performedinteractions based on an optimizedmulti-feature vector. The proposedmethodology has six main phases. The first phase involves preprocessing theimages. During preprocessing stages, the videos are converted into imageframes. Then their contrast is adjusted, and noise is removed. In the secondphase, the human-object pair is detected and extracted from each image frame.The third phase involves the identification of key body parts of the detectedhumans using IFT. The fourth phase relates to three different kinds of featureextraction techniques. Then these features are combined and optimized duringthe fifth phase. The optimized vector is used to classify the interactions in thelast phase. TheMSRDaily Activity 3D dataset has been used to test this modeland to prove its efficiency. The proposed system obtains an average accuracyof 91.7% on this dataset.

Optimization method for a radar situation interface from error-cognition to information feature mapping

With the rapid development of digital and intelligent information systems, display of radar situation interface has become an important challenge in the field of human-computer interaction. We propose a method for the optimization of radar situation interface from error-cognition through the mapping of information characteristics. A mapping method of matrix description is adopted to analyze the association properties between error-cognition sets and design information sets. Based on the mapping relationship between the domain of error-cognition and the domain of design information, a cross-correlational analysis is carried out between error-cognition and design information.We obtain the relationship matrix between the error-cognition of correlation between design information and the degree of importance among design information. Taking the task interface of a warfare navigation display as an example, error factors and the features of design information are extracted. Based on the results, we also propose an optimization design scheme for the radar situation interface.

Research on Deep Knowledge Tracking Incorporating Rich Features and Forgetting Behaviors

The individualization of education and teaching through the computer⁃aided education system provides students with personalized learning,so that each student can obtain the knowledge they need.At this stage,there are a lot of intelligent tutoring systems.In these systems,students􀆳learning actions are tracked in real⁃time,and there are a lot of available data.From these data,personalized education that suits each student can be mined.To improve the quality of education,some models for predicting students􀆳next practice have been produced,such as Bayesian Knowledge Tracing(BKT),Performance Factor Analysis(PFA),and Deep Knowledge Tracing(DKT)with the development of deep learning.However,the model only considers the knowledge component and correctness of the problem,ignoring the breadth of other characteristics of the information collected by the intelligent tutoring system,the lag time of the previous interaction,the number of past attempts to a problem,and situations that students have forgotten the knowledge.Although some studies consider forgetting and rich information when modeling student knowledge,they often ignore student learning sequences.The main contribution of this paper is in two aspects.One is to transform the input into a position feature vector by introducing an auto⁃encoding network layer and to carry out multiple sets of bad political combinations.The other is to consider repeated time intervals,sequence time intervals,and the number of attempts to simulate forgetting behavior.This paper proposes an adaptive algorithm for the original DKT model.By using the stacked auto⁃encoder network,the input dimension is reduced to half of the original and the original features are retained and consider the forgetting memory behavior according to the time sequence of students􀆳learning.The model proposed in this paper has been experimented on two public data sets to improve the original accuracy.

Coherent Point Drift Registration Combined with Image Feature and its Application

A key step of constructing active appearance model is requiring a set of appropriate training shapes with well-defined correspondences.In this paper,we introduce a novel point correspondence method(FB-CPD),which can improve the accuracy of coherent point drift(CPD) by using the information of image feature.The objective function of the proposed method is defined by both of geometric spatial information and image feature information,and the origin Gaussian mixture model in CPD is modified according to the image feature of points.FB-CPD is tested on the 3D prostate and liver point sets through the simulation experiments.The registration error can be reduced efficiently by FB-CPD.Moreover,the active appearance model constructed by FB-CPD can obtain fine segmentation in 3D CT prostate image.Compared with the original CPD,the overlap ratio of voxels was improved from 88.7% to 90.2% by FB-CPD.

Diabetes Prediction Using Derived Features and Ensembling of Boosting Classifiers

Diabetes is increasing commonly in people’s daily life and represents an extraordinary threat to human well-being.Machine Learning(ML)in the healthcare industry has recently made headlines.Several ML models are developed around different datasets for diabetic prediction.It is essential for ML models to predict diabetes accurately.Highly informative features of the dataset are vital to determine the capability factors of the model in the prediction of diabetes.Feature engineering(FE)is the way of taking forward in yielding highly informative features.Pima Indian Diabetes Dataset(PIDD)is used in this work,and the impact of informative features in ML models is experimented with and analyzed for the prediction of diabetes.Missing values(MV)and the effect of the imputation process in the data distribution of each feature are analyzed.Permutation importance and partial dependence are carried out extensively and the results revealed that Glucose(GLUC),Body Mass Index(BMI),and Insulin(INS)are highly informative features.Derived features are obtained for BMI and INS to add more information with its raw form.The ensemble classifier with an ensemble of AdaBoost(AB)and XGBoost(XB)is considered for the impact analysis of the proposed FE approach.The ensemble model performs well for the inclusion of derived features provided the high Diagnostics Odds Ratio(DOR)of 117.694.This shows a high margin of 8.2%when compared with the ensemble model with no derived features(DOR=96.306)included in the experiment.The inclusion of derived features with the FE approach of the current state-of-the-art made the ensemble model performs well with Sensitivity(0.793),Specificity(0.945),DOR(79.517),and False Omission Rate(0.090)which further improves the state-of-the-art results.

Intertextile Beijing Features More Informative programme of seminars and trend forums add value to fair

Intertextile Beijing Apparel Fabrics,will be held from 29-31 March 2009 at the China International Exhibition Centre,will showcase the latest textiles from around the world on 48,000 sqm of exhibition space.The event has confirmed 1100 exhibitors from 14 countries and regions including

A new method for the prediction of network security situations based on recurrent neural network with gated recurrent unit

Purpose-The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations(NSS).Because the conventional methods for the prediction of NSS,such as support vector machine,particle swarm optimization,etc.,lack accuracy,robustness and efficiency,in this study,the authors propose a new method for the prediction of NSS based on recurrent neural network(RNN)with gated recurrent unit.Design/methodology/approach-This method extracts internal and external information features from the original time-series network data for the first time.Then,the extracted features are applied to the deep RNN model for training and validation.After iteration and optimization,the accuracy of predictions of NSS will be obtained by the well-trained model,and the model is robust for the unstable network data.Findings-Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models.Although the deep RNN models need more time consumption for training,they guarantee the accuracy and robustness of prediction in return for validation.Originality/value-In the prediction of NSS time-series data,the proposed internal and external information features are well described the original data,and the employment of deep RNN model will outperform the state-of-the-arts models.