A Semi-Supervised Stacked Autoencoder Using the Pseudo Label for Classification Tasks.

The efficiency and cognitive limitations of manual sample labeling result in a large number of unlabeled training samples in practical applications. Making full use of both labeled and unlabeled samples is the key to solving the semi-supervised problem. However, as a supervised algorithm, the stacked autoencoder (SAE) only considers labeled samples and is difficult to apply to semi-supervised problems. Thus, by introducing the pseudo-labeling method into the SAE, a novel pseudo label-based semi-supervised stacked autoencoder (PL-SSAE) is proposed to address the semi-supervised classification tasks. The PL-SSAE first utilizes the unsupervised pre-training on all samples by the autoencoder (AE) to initialize the network parameters. Then, by the iterative fine-tuning of the network parameters based on the labeled samples, the unlabeled samples are identified, and their pseudo labels are generated. Finally, the pseudo-labeled samples are used to construct the regularization term and fine-tune the network parameters to complete the training of the PL-SSAE. Different from the traditional SAE, the PL-SSAE requires all samples in pre-training and the unlabeled samples with pseudo labels in fine-tuning to fully exploit the feature and category information of the unlabeled samples. Empirical evaluations on various benchmark datasets show that the semi-supervised performance of the PL-SSAE is more competitive than that of the SAE, sparse stacked autoencoder (SSAE), semi-supervised stacked autoencoder (Semi-SAE) and semi-supervised stacked autoencoder (Semi-SSAE).

IH-TCGAN: Time-Series Conditional Generative Adversarial Network with Improved Hausdorff Distance for Synthesizing Intention Recognition Data.

As military technology continues to evolve and the amount of situational information available on the battlefield continues to increase, data-driven deep learning methods are becoming the primary method for air target intention recognition. Deep learning is based on a large amount of high quality data; however, in the field of intention recognition, it often faces key problems such as low data volume and unbalanced datasets due to insufficient real-world scenarios. To address these problems, we propose a new method called time-series conditional generative adversarial network with improved Hausdorff distance (IH-TCGAN). The innovation of the method is mainly reflected in three aspects: (1) Use of a transverter to map real and synthetic data into the same manifold so that they have the same intrinsic dimension; (2) Addition of a restorer and a classifier in the network structure to ensure that the model can generate high-quality multiclass temporal data; (3) An improved Hausdorff distance is proposed that can measure the time order differences between multivariate time-series data and make the generated results more reasonable. We conduct experiments using two time-series datasets, evaluate the results using various performance metrics, and visualize the results using visualization techniques. The experimental results show that IH-TCGAN is able to generate synthetic data similar to the real data and has significant advantages in the generation of time series data.

A New Model of Interval-Valued Intuitionistic Fuzzy Weighted Operators and Their Application in Dynamic Fusion Target Threat Assessment.

Existing missile defense target threat assessment methods ignore the target timing and battlefield changes, leading to low assessment accuracy. In order to overcome this problem, a dynamic multi-time fusion target threat assessment method is proposed. In this method, a new interval valued intuitionistic fuzzy weighted averaging operator is proposed to effectively aggregate multi-source uncertain information; an interval-valued intuitionistic fuzzy entropy based on a cosine function (IVIFECF) is designed to determine the target attribute weight; an improved interval-valued intuitionistic fuzzy number distance measurement model is constructed to improve the discrimination of assessment results. Specifically, first of all, we define new interval-valued intuitionistic fuzzy operation rules based on algebraic operations. We use these rules to provide a new model of interval-valued intuitionistic fuzzy weighted arithmetic averaging (IVIFWAA) and geometric averaging (IVIFWGA) operators, and prove a number of algebraic properties of these operators. Then, considering the subjective and objective weights of the incoming target, a comprehensive weight model of target attributes based on IVIFECF is proposed, and the Poisson distribution method is used to solve the time series weights to process multi-time situation information. On this basis, the IVIFWAA and IVIFWGA operators are used to aggregate the decision information from multiple times and multiple decision makers. Finally, based on the improved TOPSIS method, the interval-valued intuitionistic fuzzy numbers are ordered, and the weighted multi-time fusion target threat assessment result is obtained. Simulation results of comparison show that the proposed method can effectively improve the reliability and accuracy of target threat assessment in missile defense.

Linking genotype to phenotype in multi-omics data of small sample.

BACKGROUND: Genome-wide association studies (GWAS) that link genotype to phenotype represent an effective means to associate an individual genetic background with a disease or trait. However, single-omics data only provide limited information on biological mechanisms, and it is necessary to improve the accuracy for predicting the biological association between genotype and phenotype by integrating multi-omics data. Typically, gene expression data are integrated to analyze the effect of single nucleotide polymorphisms (SNPs) on phenotype. Such multi-omics data integration mainly follows two approaches: multi-staged analysis and meta-dimensional analysis, which respectively ignore intra-omics and inter-omics associations. Moreover, both approaches require omics data from a single sample set, and the large feature set of SNPs necessitates a large sample size for model establishment, but it is difficult to obtain multi-omics data from a single, large sample set. RESULTS: To address this problem, we propose a method of genotype-phenotype association based on multi-omics data from small samples. The workflow of this method includes clustering genes using a protein-protein interaction network and gene expression data, screening gene clusters with group lasso, obtaining SNP clusters corresponding to the selected gene clusters through expression quantitative trait locus data, integrating SNP clusters and corresponding gene clusters and phenotypes into three-layer network blocks, analyzing and predicting based on each block, and obtaining the final prediction by taking the average. CONCLUSIONS: We compare this method to others using two datasets and find that our method shows better results in both cases. Our method can effectively solve the prediction problem in multi-omics data of small sample, and provide valuable resources for further studies on the fusion of more omics data.

Distance-Based Knowledge Measure for Intuitionistic Fuzzy Sets with Its Application in Decision Making.

Much attention has been paid to construct an applicable knowledge measure or uncertainty measure for Atanassov's intuitionistic fuzzy set (AIFS). However, many of these measures were developed from intuitionistic fuzzy entropy, which cannot really reflect the knowledge amount associated with an AIFS well. Some knowledge measures were constructed based on the distinction between an AIFS and its complementary set, which may lead to information loss in decision making. In this paper, knowledge amount of an AIFS is quantified by calculating the distance from an AIFS to the AIFS with maximum uncertainty. Axiomatic properties for the definition of knowledge measure are extended to a more general level. Then the new knowledge measure is developed based on an intuitionistic fuzzy distance measure. The properties of the proposed distance-based knowledge measure are investigated based on mathematical analysis and numerical examples. The proposed knowledge measure is finally applied to solve the multi-attribute group decision-making (MAGDM) problem with intuitionistic fuzzy information. The new MAGDM method is used to evaluate the threat level of malicious code. Experimental results in malicious code threat evaluation demonstrate the effectiveness and validity of proposed method.

Threat Assessment Method of Low Altitude Slow Small (LSS) Targets Based on Information Entropy and AHP.

In order to deal with the new threat of low altitude slow small (LSS) targets in air defense operations and provide support for LSS target interception decision, we propose a simple and reliable LSS target threat assessment method. Based on the detection capability of LSS targets and their threat characteristics, this paper proposes a threat evaluation factor and threat degree quantization function in line with the characteristics of LSS targets. LSS targets not only have the same threat characteristics as traditional air targets but also have the unique characteristics of flexible mobility and dynamic mission planning. Therefore, we use analytic hierarchy process (AHP) and information entropy to determine the subjective and objective threat factor weights of LSS targets and use the optimization model to combine them to obtain more reliable evaluation weights. Finally, the effectiveness and credibility of the proposed method are verified by experimental simulation.

An Entropy-Based Knowledge Measure for Atanassov's Intuitionistic Fuzzy Sets and Its Application to Multiple Attribute Decision Making.

As the complementary concept of intuitionistic fuzzy entropy, the knowledge measure of Atanassov's intuitionistic fuzzy sets (AIFSs) has attracted more attention and is still an open topic. The amount of knowledge is important to evaluate intuitionistic fuzzy information. An entropy-based knowledge measure for AIFSs is defined in this paper to quantify the knowledge amount conveyed by AIFSs. An intuitive analysis on the properties of the knowledge amount in AIFSs is put forward to facilitate the introduction of axiomatic definition of the knowledge measure. Then we propose a new knowledge measure based on the entropy-based divergence measure with respect for the difference between the membership degree, the non-membership degree, and the hesitancy degree. The properties of the new knowledge measure are investigated in a mathematical viewpoint. Several examples are applied to illustrate the performance of the new knowledge measure. Comparison with several existing entropy and knowledge measures indicates that the proposed knowledge has a greater ability in discriminating different AIFSs and it is robust in quantifying the knowledge amount of different AIFSs. Lastly, the new knowledge measure is applied to the problem of multiple attribute decision making (MADM) in an intuitionistic fuzzy environment. Two models are presented to determine attribute weights in the cases that information on attribute weights is partially known and completely unknown. After obtaining attribute weights, we develop a new method to solve intuitionistic fuzzy MADM problems. An example is employed to show the effectiveness of the new MADM method.

First Molecular Detection and Genotype Identification of Toxoplasma gondii in Chickens from Farmers' Markets in Fujian Province, Southeastern China.

Toxoplasma gondii is an opportunistic pathogenic protozoan that can infect all nucleated cells in almost all warm-blooded animals, including humans. T. gondii infection has been reported in many food animals worldwide. However, the prevalence and genotypes of T. gondii in chickens from farmers' markets in Fujian province in southeastern China remain unreported. In the present study, four tissue samples from each of the 577 chickens (namely, the heart, liver, lungs, and muscles) were collected from farmers' markets in five regions of Fujian province (Zhangzhou, Sanming, Quanzhou, Fuzhou, and Longyan). We first analyzed the prevalence and genotypes of T. gondii using PCR targeting of the B1 gene of T. gondii. Of the 577 chickens, thirty-two (5.5%) tested positive for the B1 gene. Among the five regions, Sanming had the highest infection rate (16.8%, 16/95), followed by Quanzhou (8.0%, 8/100), Longyan (5.0%, 5/100), Zhangzhou (1.1%, 2/182), and Fuzhou (1.0%, 1/100). Among these thirty-two T. gondii-positive chickens, the infection rates of the lungs, heart, liver, and muscles were 68.8% (22/32), 34.4% (11/32), 28.1% (9/32), and 9.4% (3/32), respectively. Significant differences in prevalence were found among the different regions (χ2 = 35.164, p < 0.05) and tissues (χ2 = 25.874, p < 0.05). A total of 128 tissue and organ samples of the thirty-two T. gondii-positive chickens from the different regions were analyzed using PCR-restriction fragment length polymorphism (PCR-RFLP) on the basis of 10 genetic markers. Seven tissue samples (lung samples from five chickens, heart samples from one chicken, and liver samples from one chicken) underwent successful amplification at all the genetic markers, and all the T. gondii genotypes were identified as genotype I (ToxoDB #10). These findings serve as a foundation for evaluating the risk of T. gondii contamination in chicken products intended for human consumption and offer insight into preventing the transmission of the parasite from chickens to humans.

First report of prevalence and assemblage analysis of Giardia duodenalis in pigs from Guangxi Zhuang Autonomous Region, southern China.

Giardia duodenalis is a common intestinal protozoan that can cause diarrhea and intestinal disease in animals and in humans. However, the prevalence and assemblages of G. duodenalis in pigs from Guangxi Zhuang Autonomous Region have not been reported. In this study, a total of 724 fecal samples (201 from nursery pigs, 183 from piglets, 175 from breeding pigs, and 165 from fattening pigs) were obtained in four areas of the region (Nanning, Yulin, Hezhou, and Guigang). The gene of the small subunit ribosomal RNA (SSU rRNA) of G. duodenalis was amplified by nested PCR. The results show that the prevalence of G. duodenalis in pigs was 3.59% (26/724), of which 14 samples belonged to assemblage A (53.85%) and 12 samples belonged to assemblage E (46.15%). The infection rates of G. duodenalis in Hezhou, Yulin, Nanning, and Guigang were 0%, 0.7%, 10.8% and 1.1%, respectively (χ2 = 45.616, p < 0.01); whereas 5.1% of breeding pigs, 6.0% of piglets, 2.4% of fattening pigs, and 1.0% of nursery pigs were infected with G. duodenalis (χ2 = 8.874, p < 0.05). The SSU rRNA-positive samples were amplified by PCR based on the ß-giardin (bg), glutamate dehydrogenase (gdh), and triphosphate isomerase (tpi) genes. Ten, eight and seven positive samples were detected, respectively. Based on phylogenetic analysis of the three genetic loci sequences, a multilocus genotyping A1 was found. The findings of this study provide basic data for the development of prevention and control of G. duodenalis infections in pigs and humans in the Guangxi Zhuang Autonomous Region.

Title: Premier rapport sur la prévalence et l'analyse des assemblages de Giardia duodenalis chez les porcs de la région autonome Zhuang du Guangxi, dans le sud de la Chine. Abstract: Giardia duodenalis est un protozoaire intestinal commun qui peut provoquer des diarrhées et des maladies intestinales chez les animaux et les humains. Cependant, la prévalence et les assemblages de G. duodenalis chez les porcs de la région autonome Zhuang du Guangxi n'ont pas été rapportés. Dans cette étude, un total de 724 échantillons fécaux (201 provenant de jeunes porcelets, 183 de porcelets, 175 de porcs reproducteurs et 165 de porcs à l'engrais) ont été obtenus dans quatre zones de la région (Nanning, Yulin, Hezhou et Guigang). Le gène de la petite sous-unité de l'ARN ribosomal (ARNr SSU) de G. duodenalis a été amplifié par PCR nichée. Les résultats ont montré que la prévalence de G. duodenalis chez les porcs était de 3,59 % (26/724), dont 14 échantillons appartenaient à l'assemblages A (53,85 %) et 12 échantillons à l'assemblage E (46,15 %). Les taux d'infection par G. duodenalis à Hezhou, Yulin, Nanning et Guigang étaient respectivement de 0, 0,7 %, 10,8 % et 1,1 % (χ2 = 45,616, p < 0,01), alors que 5,1 % des porcs reproducteurs, 6,0 % des porcelets, 2,4 % de porcs à l'engrais et 1,0 % des jeunes porcelets étaient infectés par G. duodenalis (χ2 = 8,874, p < 0,05). Les échantillons positifs pour l'ARNr SSU ont été amplifiés par PCR basée sur les gènes de la ß-giardine (bg), de la glutamate déshydrogénase (gdh) et de la triphosphate isomérase (tpi), et dix, huit et sept échantillons positifs ont été détectés, respectivement. Sur la base de l'analyse phylogénétique des trois séquences de loci génétiques, un génotypage multilocus A1 a été trouvé. Les résultats de cette étude fournissent des données de base pour le développement de la prévention et du contrôle des infections à G. duodenalis chez les porcs et les humains dans la région autonome Zhuang du Guangxi.

Network Intrusion Detection Technology Based on Convolutional Neural Network and BiGRU.

To solve the problem of low accuracy and high false-alarm rate of existing intrusion detection models for multiple classifications of intrusion behaviors, a network intrusion detection model incorporating convolutional neural network and bidirectional gated recurrent unit is proposed. To solve the problems of many dimensions of features and imbalance of positive and negative samples in the original traffic data, sampling processing is performed with the help of a hybrid sampling algorithm combining ADASYN and RENN, and feature selection is performed by combining random forest algorithm and Pearson correlation analysis; after that, spatial features are extracted by the convolutional neural network, and further features are extracted by incorporating average pooling and max pooling, and then BiGRU is used to extracts long-distance dependent information features to achieve comprehensive and effective feature learning. Finally, the Softmax function is used for classification. In this paper, the proposed model is evaluated on the UNSW_NB15, NSL-KDD, and CIC-IDS2017 data sets with an accuracy of 85.55%, 99.81%, and 99.70%, which is 1.25%, 0.59%, and 0.27% better than the same type model of CNN-GRU.

Network Intrusion Detection Method Based on FCWGAN and BiLSTM.

Imbalanced datasets greatly affect the analysis capability of intrusion detection models, biasing their classification results toward normal behavior and leading to high false-positive and false-negative rates. To alleviate the impact of class imbalance on the detection accuracy of network intrusion detection models and improve their effectiveness, this paper proposes a method based on a feature selection-conditional Wasserstein generative adversarial network (FCWGAN) and bidirectional long short-term memory network (BiLSTM). The method uses the XGBoost algorithm with Spearman's correlation coefficient to select the data features, filters out useless and redundant features, and simplifies the data structure. A conditional WGAN (CWGAN) is used to generate a small number of samples in the dataset, add them to the original training set to supplement the dataset samples, and apply BiLSTM to complete the training of the model and realize the classification. In comparative tests based on the NSL-KDD and UNSW-NB15 datasets, the accuracy of the proposed model reached 99.57% and 85.59%, respectively, which is 1.44% and 2.98% higher than that of the same type of CWGAN and deep neural network (CWGAN-DNN) model, respectively.

Using expression quantitative trait loci data and graph-embedded neural networks to uncover genotype-phenotype interactions.

Motivation: A central goal of current biology is to establish a complete functional link between the genotype and phenotype, known as the so-called genotype-phenotype map. With the continuous development of high-throughput technology and the decline in sequencing costs, multi-omics analysis has become more widely employed. While this gives us new opportunities to uncover the correlation mechanisms between single-nucleotide polymorphism (SNP), genes, and phenotypes, multi-omics still faces certain challenges, specifically: 1) When the sample size is large enough, the number of omics types is often not large enough to meet the requirements of multi-omics analysis; 2) each omics' internal correlations are often unclear, such as the correlation between genes in genomics; 3) when analyzing a large number of traits (p), the sample size (n) is often smaller than p, n << p, hindering the application of machine learning methods in the classification of disease outcomes. Results: To solve these issues with multi-omics and build a robust classification model, we propose a graph-embedded deep neural network (G-EDNN) based on expression quantitative trait loci (eQTL) data, which achieves sparse connectivity between network layers to prevent overfitting. The correlation within each omics is also considered such that the model more closely resembles biological reality. To verify the capabilities of this method, we conducted experimental analysis using the GSE28127 and GSE95496 data sets from the Gene Expression Omnibus (GEO) database, tested various neural network architectures, and used prior data for feature selection and graph embedding. Results show that the proposed method could achieve a high classification accuracy and easy-to-interpret feature selection. This method represents an extended application of genotype-phenotype association analysis in deep learning networks.

Weighted Decoding for the Competence Reliability Problem of ECOC Multiclass Classification.

Error-Correcting Output Codes has become a well-known, established technique for multiclass classification due to its simplicity and efficiency. Each binary split contains different original classes. A noncompetent classifier emerges when it classifies an instance whose real class does not belong to the metasubclasses which is used to learn the classifier. How to reduce the error caused by the noncompetent classifiers under diversity big enough is urgent for ECOC classification. The weighted decoding strategy can be used to reduce the error caused by the noncompetence contradiction through relearning the weight coefficient matrix. To this end, a new weighted decoding strategy taking the classifier competence reliability into consideration is presented in this paper, which is suitable for any coding matrix. Support Vector Data Description is applied to compute the distance from an instance to the metasubclasses. The distance reflects the competence reliability and is fused as the weight in the base classifier combination. In so doing, the effect of the competent classifiers on classification is reinforced, while the bias induced by the noncompetent ones is decreased. Reflecting the competence reliability, the weights of classifiers for each instance change dynamically, which accords with the classification practice. The statistical simulations based on benchmark datasets indicate that our proposed algorithm outperforms other methods and provides new thought for solving the noncompetence problem.

Malicious Code Variant Identification Based on Multiscale Feature Fusion CNNs.

The increasing volume and types of malwares bring a great threat to network security. The malware binary detection with deep convolutional neural networks (CNNs) has been proved to be an effective method. However, the existing malware classification methods based on CNNs are unsatisfactory to this day because of their poor extraction ability, insufficient accuracy of malware classification, and high cost of detection time. To solve these problems, a novel approach, namely, multiscale feature fusion convolutional neural networks (MFFCs), was proposed to achieve an effective classification of malware based on malware visualization utilizing deep learning, which can defend against malware variants and confusing malwares. The approach firstly converts malware code binaries into grayscale images, and then, these images will be normalized in size by utilizing the MFFC model to identify malware families. Comparative experiments were carried out to verify the performance of the proposed method. The results indicate that the MFFC stands out among the recent advanced methods with an accuracy of 98.72% and an average cost of 5.34 milliseconds on the Malimg dataset. Our method can effectively identify malware and detect variants of malware families, which has excellent feature extraction capability and higher accuracy with lower detection time.

Ordinal Multi-Task Part Segmentation With Recurrent Prior Generation.

Semantic object part segmentation is a fundamental task in object understanding and geometric analysis. The clear understanding of part relationships can be of great use to the segmentation process. In this work, we propose a novel Ordinal Multi-task Part Segmentation (OMPS) approach which explicitly models the part ordinal relationship to guide the segmentation process in a recurrent manner. Quantitative and qualitative experiments are conducted first to explore the mutual impacts among object parts and then an ordinal part inference algorithm is formulated via experimental observations. Specifically, our framework is mainly composed of two modules, the forward module to segment multiple parts as individual subtasks with prior knowledge, and the recurrent module to generate appropriate part priors with the ordinal inference algorithm. These two modules work iteratively to optimize the segmentation performance and the network parameters. Experimental results show that our approach outperforms the state-of-the-art models on human and vehicle part parsing benchmarks. Comprehensive evaluations are conducted to demonstrate the effectiveness of our approach in object part segmentation.

A GRU-Based Method for Predicting Intention of Aerial Targets.

Since a target's operational intention in air combat is realized by a series of tactical maneuvers, its state presents the characteristics of temporal and dynamic changes. Depending only on a single moment to take inference, the traditional combat intention recognition method is neither scientific nor effective enough. Based on a gated recurrent unit (GRU), a bidirectional propagation mechanism and attention mechanism are introduced in a proposed aerial target combat intention recognition method. The proposed method constructs an air combat intention characteristic set through a hierarchical approach, encodes into numeric time-series characteristics, and encapsulates domain expert knowledge and experience in labels. It uses a bidirectional gated recurrent units (BiGRU) network for deep learning of air combat characteristics and adaptively assigns characteristic weights using an attention mechanism to improve the accuracy of aerial target combat intention recognition. In order to further shorten the time for intention recognition and with a certain predictive effect, an air combat characteristic prediction module is introduced before intention recognition to establish the mapping relationship between predicted characteristics and combat intention types. Simulation experiments show that the proposed model can predict enemy aerial target combat intention one sampling point ahead of time based on 89.7% intent recognition accuracy, which has reference value and theoretical significance for assisting decision-making in real-time intention recognition.

Learning From Large-Scale Noisy Web Data With Ubiquitous Reweighting for Image Classification.

Many important advances of deep learning techniques have originated from the efforts of addressing the image classification task on large-scale datasets. However, the construction of clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that can learn an image classification model from noisy web data. By observing the web data, we find that there are five key challenges, i.e., imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. With these challenges in mind, we assume every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags, and the labels. In this manner, the influence of bias and noise in the data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the WebVision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks first place in the image classification task.

Geodesic propagation for semantic labeling.

This paper presents a semantic labeling framework with geodesic propagation (GP). Under the same framework, three algorithms are proposed, including GP, supervised GP (SGP) for image, and hybrid GP (HGP) for video. In these algorithms, we resort to the recognition proposal map and select confident pixels with maximum probability as the initial propagation seeds. From these seeds, the GP algorithm iteratively updates the weights of geodesic distances until the semantic labels are propagated to all pixels. On the contrary, the SGP algorithm further exploits the contextual information to guide the direction of propagation, leading to better performance but higher computational complexity than the GP. For video labeling, we further propose the HGP algorithm, in which the geodesic metric is used in both spatial and temporal spaces. Experiments on four public data sets show that our algorithms outperform several state-of-the-art methods. With the GP framework, convincing results for both image and video semantic labeling can be obtained.