Enhanced Deep Autoencoder Based Feature Representation Learning for Intelligent Intrusion Detection System

In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owing to the lack of accurately labeled network traffic data,many unsupervised feature representation learning models have been proposed with state-of-theart performance.Yet,these models fail to consider the classification error while learning the feature representation.Intuitively,the learnt feature representation may degrade the performance of the classification task.For the first time in the field of intrusion detection,this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder(DAE)for learning the robust feature representation and one-class support vector machine(OCSVM)for finding the more compact decision hyperplane for intrusion detection.Specially,the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously.This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection.Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model.First,the ablation evaluation on benchmark dataset,NSL-KDD validates the design decision of the proposed model.Next,the performance evaluation on recent intrusion dataset,UNSW-NB15 signifies the stable performance of the proposed model.Finally,the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.

Novel DDoS Feature Representation Model Combining Deep Belief Network and Canonical Correlation Analysis

Distributed denial of service(DDoS)attacks launch more and more frequently and are more destructive.Feature representation as an important part of DDoS defense technology directly affects the efficiency of defense.Most DDoS feature extraction methods cannot fully utilize the information of the original data,resulting in the extracted features losing useful features.In this paper,a DDoS feature representation method based on deep belief network(DBN)is proposed.We quantify the original data by the size of the network flows,the distribution of IP addresses and ports,and the diversity of packet sizes of different protocols and train the DBN in an unsupervised manner by these quantified values.Two feedforward neural networks(FFNN)are initialized by the trained deep belief network,and one of the feedforward neural networks continues to be trained in a supervised manner.The canonical correlation analysis(CCA)method is used to fuse the features extracted by two feedforward neural networks per layer.Experiments show that compared with other methods,the proposed method can extract better features.

A feature representation method for biomedical scientific data based on composite text description

Feature representation is one of the key issues in data clustering. The existing feature representation of scientific data is not sufficient, which to some extent affects the result of scientific data clustering. Therefore, the paper proposes a concept of composite text description(CTD) and a CTD-based feature representation method for biomedical scientific data. The method mainly uses different feature weight algorisms to represent candidate features based on two types of data sources respectively, combines and finally strengthens the two feature sets. Experiments show that comparing with traditional methods, the feature representation method is more effective than traditional methods and can significantly improve the performance of biomedcial data clustering.

HOG-VGG:VGG Network with HOG Feature Fusion for High-Precision PolSAR Terrain Classification

This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.

Feature Representation for Facial Expression Recognition Based on FACS and LBP

In expression recognition, feature representation is critical for successful recognition since it contains distinctive information of expressions. In this paper, a new approach for representing facial expression features is proposed with its objective to describe features in an effective and efficient way in order to improve the recognition performance. The method combines the facial action coding system(FACS) and 'uniform' local binary patterns(LBP) to represent facial expression features from coarse to fine. The facial feature regions are extracted by active shape models(ASM) based on FACS to obtain the gray-level texture. Then, LBP is used to represent expression features for enhancing the discriminant. A facial expression recognition system is developed based on this feature extraction method by using K nearest neighborhood(K-NN) classifier to recognize facial expressions. Finally, experiments are carried out to evaluate this feature extraction method. The significance of removing the unrelated facial regions and enhancing the discrimination ability of expression features in the recognition process is indicated by the results, in addition to its convenience.

Feature Representation in the Biclustering of Symptom-Herb Relationship in Chinese Medicine

Objective：To find an appropriate feature representation in the biclustering of symptom-herb relationship in Chinese medicine（CM）.Methods： Four different representation schemes were tested in identifying the complex relationship between symptoms and herbs using a biclustering algorithm on an insomnia data set.These representation schemes were effective count,binary value,relative success ratio,or modified relative success ratio.The comparison of the schemes was made on the number and size of biclusters with respect to different threshold values.Results and Conclusions：The modified relative success ratio scheme was the most appropriate feature representation among the four tested.Some of the biclusters selected from this representation scheme were known to follow the therapeutic principles of CM,while others may offer clues for further clinical investigations.

The admittance feature representation and impact sound feature extraction in the material identification of ribbed plates

The admittance features representing the physical attributes are used as the in termediates to extract the materialattributesrelated impact sound features of ribbed plates. Firstly, the admittance feature representations of metal ribbed plates attributes are obtained and the relationship between the admittance features and the impact sound features are established via correlation analysis method. Then, materialattributesrelated impact sound features are obtained indirectly. Finally, the performances of different sound features for the material recognition of ribbedmetal plates are verified through the Support Vector Machine classifier. The results indicate that the obtained four sets of features can effectively identify the materials of the metal ribbed plates, while the accuracy of a single feature depends on the separable degree of the corresponding material attribute. And the features extracted based on admittance functions have higher average accuracy than that of timbre features. Therefore, the proposed sound feature extraction method based on admittance features is valid, and the extracted sound features can effectively reflect the physical attributes.

Automatically extracting sheet-metal features from solid model

With the development of modern industry, sheet-metal parts in mass production have been widely applied in mechanical, communication, electronics, and light industries in recent decades; but the advances in sheet-metal part design and manufacturing remain too slow compared with the increasing importance of sheet-metal parts in modern industry. This paper proposes a method for automatically extracting features from an arbitrary solid model of sheet-metal parts; whose characteristics are used for classification and graph-based representation of the sheet-metal features to extract the features embodied in a sheet-metal part. The extracting feature process can be divided for valid checking of the model geometry, feature matching, and feature relationship. Since the extracted features include abundant geometry and engineering information, they will be effective for downstream application such as feature rebuilding and stamping process planning.

Remaining Time Prediction for Business Processes with Concurrency Based on Log Representation

Remaining time prediction of business processes plays an important role in resource scheduling and plan making.The structural features of single process instance and the concurrent running of multiple process instances are the main factors that affect the accuracy of the remaining time prediction.Existing prediction methods does not take full advantage of these two aspects into consideration.To address this issue,a new prediction method based on trace representation is proposed.More specifically,we first associate the prefix set generated by the event log to different states of the transition system,and encode the structural features of the prefixes in the state.Then,an annotation containing the feature representation for the prefix and the corresponding remaining time are added to each state to obtain an extended transition system.Next,states in the extended transition system are partitioned by the different lengths of the states,which considers concurrency among multiple process instances.Finally,the long short-term memory(LSTM)deep recurrent neural networks are applied to each partition for predicting the remaining time of new running instances.By extensive experimental evaluation using synthetic event logs and reallife event logs,we show that the proposed method outperforms existing baseline methods.

An improved algorithm for weighting keywords in web documents

In this paper, an improved algorithm, web-based keyword weight algorithm （WKWA）, is presented to weight keywords in web documents. WKWA takes into account representation features of web documents and advantages of the TF＊IDF, TFC and ITC algorithms in order to make it more appropriate for web documents. Meanwhile, the presented algorithm is applied to improved vector space model （IVSM）. A real system has been implemented for calculating semantic similarities of web documents. Four experiments have been carried out. They are keyword weight calculation, feature item selection, semantic similarity calculation, and WKWA time performance. The results demonstrate accuracy of keyword weight, and semantic similarity is improved.

Bi-GAE:A Bidirectional Generative Auto-Encoder

Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by in the reconstruction of 512*512 images.

Relational Topology-based Heterogeneous Network Embedding for Predicting Drug-Target Interactions

Predicting interactions between drugs and target proteins has become an essential task in the drug discovery process.Although the method of validation via wet-lab experiments has become available,experimental methods for drug-target interaction(DTI)identification remain either time consuming or heavily dependent on domain expertise.Therefore,various computational models have been proposed to predict possible interactions between drugs and target proteins.However,most prediction methods do not consider the topological structures characteristics of the relationship.In this paper,we propose a relational topologybased heterogeneous network embedding method to predict drug-target interactions,abbreviated as RTHNE_DTI.We first construct a heterogeneous information network based on the interaction between different types of nodes,to enhance the ability of association discovery by fully considering the topology of the network.Then drug and target protein nodes can be represented by the other types of nodes.According to the different topological structure of the relationship between the nodes,we divide the relationship in the heterogeneous network into two categories and model them separately.Extensive experiments on the realworld drug datasets,RTHNE_DTI produces high efficiency and outperforms other state-of-the-art methods.RTHNE_DTI can be further used to predict the interaction between unknown interaction drug-target pairs.

Two-Stream Temporal Convolutional Networks for Skeleton-Based Human Action Recognition

With the growing popularity of somatosensory interaction devices,human action recognition is becoming attractive in many application scenarios.Skeleton-based action recognition is effective because the skeleton can represent the position and the structure of key points of the human body.In this paper,we leverage spatiotemporal vectors between skeleton sequences as input feature representation of the network,which is more sensitive to changes of the human skeleton compared with representations based on distance and angle features.In addition,we redesign residual blocks that have different strides in the depth of the network to improve the processing ability of the temporal convolutional networks(TCNs)for long time dependent actions.In this work,we propose the two-stream temporal convolutional networks(TSTCNs)that take full advantage of the inter-frame vector feature and the intra-frame vector feature of skeleton sequences in the spatiotemporal representations.The framework can integrate different feature representations of skeleton sequences so that the two feature representations can make up for each other’s shortcomings.The fusion loss function is used to supervise the training parameters of the two branch networks.Experiments on public datasets show that our network achieves superior performance and attains an improvement of 1.2%over the recent GCN-based(BGC-LSTM)method on the NTU RGB+D dataset.

DiscoStyle:Multi-level Logistic Ranking for Personalized Image Style Preference Inference

Learning based on facial features for detection and recognition of people′s identities,emotions and image aesthetics has been widely explored in computer vision and biometrics.However,automatic discovery of users′preferences to certain of faces(i.e.,style),to the best of our knowledge,has never been studied,due to the subjective,implicative,and uncertain characteristic of psychological preference.Therefore,in this paper,we contribute to an answer to whether users′psychological preference can be modeled and computed after observing several faces.To this end,we first propose an efficient approach for discovering the personality preference related facial features from only a very few anchors selected by each user,and make accurate predictions and recommendations for users.Specifically,we propose to discover the style of faces(DiscoStyle)for human′s psychological preference inference towards personalized face recommendation system/application.There are four merits of our DiscoStyle:1)Transfer learning is exploited from identity related facial feature representation to personality preference related facial feature.2)Appearance and geometric landmark feature are exploited for preference related feature augmentation.3)A multi-level logistic ranking model with on-line negative sample selection is proposed for on-line modeling and score prediction,which reflects the users′preference degree to gallery faces.4)A large dataset with different facial styles for human′s psychological preference inference is developed for the first time.Experiments show that our proposed DiscoStyle can well achieve users′preference reasoning and recommendation of preferred facial styles in different genders and races.

Multiresolution Free Form Object Modeling with PointSampled Geometry

In this paper an efficient framework for the creation of 3D digital contentwith point sampled ge-ometry is proposed. A new hierarchy of shape representations with three levelsis adopted in this framework. Based on this new hierarchical shape representation, the proposedframework offers concise integration of various volumetric- and surface-based modeling techniques,such as Boolean operation, offset, blending, free-form defor-mation, parameterization and texturemapping, and thus simplifies the complete modeling process. Previously to achieve the same goal,several separated algorithms had to be used independently with inconsistent volumetric and surfacerepresentations of the free-form object. Both graphics and industrial applications are presented todemonstrate the effectiveness and efficiency of the proposed framework.

Advance on large scale near-duplicate video retrieval

Emerging Internet services and applications attract increasing users to involve in diverse video-related activities,such as video searching,video downloading,video sharing and so on.As normal operations,they lead to an explosive growth of online video volume,and inevitably give rise to the massive near-duplicate contents.Near-duplicate video retrieval(NDVR)has always been a hot topic.The primary purpose of this paper is to present a comprehensive survey and an updated review of the advance on large-scale NDVR to supply guidance for researchers.Specifically,we summarize and compare the definitions of near-duplicate videos(NDVs)in the literature,analyze the relationship between NDVR and its related research topics theoretically,describe its generic framework in detail,investigate the existing state-of-the-art NDVR systems.Finally,we present the development trends and research directions of this topic.

GroupNet:Learning to group corner for object detection in remote sensing imagery

Due to the attractive potential in avoiding the elaborate definition of anchor attributes,anchor-free-based deep learning approaches are promising for object detection in remote sensing imagery.Corner Net is one of the most representative methods in anchor-free-based deep learning approaches.However,it can be observed distinctly from the visual inspection that the Corner Net is limited in grouping keypoints,which significantly impacts the detection performance.To address the above problem,a novel and effective approach,called Group Net,is presented in this paper,which adaptively groups corner specific to the objects based on corner embedding vector and corner grouping network.Compared with the Corner Net,the proposed approach is more effective in learning the semantic relationship between corners and improving remarkably the detection performance.On NWPU dataset,experiments demonstrate that our Group Net not only outperforms the Corner Net with an AP of 12.8%,but also achieves comparable performance to considerable approaches with 83.4%AP.

A Coarse-to-Fine Method for Shape Recognition

In this paper the deformation invariant curve matching problem is addressed. The proposed approach exploits an image pyramid to constrain correspondence search at a finer level with those at a coarser level. In comparison to previous methods, this approach conveys much richer information： curve topology, affine geometry and local intensity are combined together to seek correspondences. In experiments, the method is tested in two applications, contour matching and shape recognition, and the results show that the approach is effective under perspective and articulated deformations.

An effective global learning framework for hyperspectral image classification based on encoder-decoder architecture

Most deep learning methods in hyperspectral image(HSI)classification use local learning methods,where overlapping areas between pixels can lead to spatial redundancy and higher computational cost.This paper proposes an efficient global learning(EGL)framework for HSI classification.The EGL framework was composed of universal global random stratification(UGSS)sampling strategy and a classification model BrsNet.The UGSS sampling strategy was used to solve the problem of insufficient gradient variance resulted from limited training samples.To fully extract and explore the most distinguishing feature representation,we used the modified linear bottleneck structure with spectral attention as a part of the BrsNet network to extract spectral spatial information.As a type of spectral attention,the shuffle spectral attention module screened important spectral features from the rich spectral information of HSI to improve the classification accuracy of the model.Meanwhile,we also designed a double branch structure in BrsNet that extracted more abundant spatial information from local and global perspectives to increase the performance of our classification framework.Experiments were conducted on three famous datasets,IP,PU,and SA.Compared with other classification methods,our proposed method produced competitive results in training time,while having a greater advantage in test time.

WEDeepT3: predicting type Ⅲ secreted effectors based on word embedding and deep learning

Background:The type Ⅲ secreted effectors(T3SEs)are one of the indispensable proteins in the growth and reproduction of Gram-negative bacteria.In particular,the pathogenesis of Gram-negative bacteria depends on the type Ⅲ secreted effectors,and by injecting T3SEs into a host cell,the host cell's immunity can be destroyed.The high diversity of T3SE sequences and the lack of defined secretion signals make it difficult to identify and predict.Moreover,the related study of the pathological system associated with T3SE remains a hot topic in bioinformatics.Some computational tools have been developed to meet the growing demand for the recognition of T3SEs and the studies of type Ⅲ secretion systems(T3SS).Although these tools can help biological experiments in certain procedures,there is still room for improvement,even for the current best model,as the existing methods adopt handdesigned feature and traditional machine learning methods.Methods:In this study,we propose a powerful predictor based on deep learning methods,called WEDeepT3.Our work consists mainly of three key steps.First,we train word embedding vectors for protein sequences in a large-scale amino acid sequence database.Second,we combine the word vectors with traditional features extracted from protein sequences,like PSSM,to construct a more comprehensive feature representation.Finally,we construct a deep neural network model in the prediction of type Ⅲ secreted effectors.Results:The feature representation of WEDeepT3 consists of both word embedding and position-specific features.Working together with convolutional neural networks,the new model achieves superior performance to the state-ofthe-art methods,demonstrating the effectiveness of the new feature representation and the powerful learning ability of deep models.Conclusion:WEDeepT3 exploits both semantic information of Ar-mer fragments and evolutional information of protein sequences to accurately difYerentiate between T3SEs and non-T3SEs.WEDeepT3 is available at bcmi.sjtu.edu.cn/~yangyang/WEDeepT3.html.