Feature dependence graph based source code loophole detection method by Hongyu YANG, Haiyun YANG, Liang ZHANG, Xiang CHENG

“…Given the problem that the existing source code loophole detection methods did not explicitly maintain the semantic information related to the loophole in the source code, which led to the difficulty of feature extraction of loo-phole statements and the high false positive rate of loophole detection, a source code loophole detection method based on feature dependency graph was proposed.First, extracted the candidate loophole statements in the function slice, and gen-erated the feature dependency graph by analyzing the control dependency chain and data dependency chain of the candi-date loophole statements.Secondly, the word vector model was used to generate the initial node representation vector of the feature dependency graph.Finally, a loophole detection neural network oriented to feature dependence graph was constructed, in which the graph learning network learned the heterogeneous neighbor node information of the feature de-pendency graph and the detection network extracted global features and performed loophole detection.The experimental results show that the recall rate and F1 score of the proposed method are improved by 1.50%～22.32% and 1.86%～16.69% respectively, which is superior to the existing method.…”
Get full text

Feature dependence graph based source code loophole detection method by Hongyu YANG, Haiyun YANG, Liang ZHANG, Xiang CHENG

“…Given the problem that the existing source code loophole detection methods did not explicitly maintain the semantic information related to the loophole in the source code, which led to the difficulty of feature extraction of loo-phole statements and the high false positive rate of loophole detection, a source code loophole detection method based on feature dependency graph was proposed.First, extracted the candidate loophole statements in the function slice, and gen-erated the feature dependency graph by analyzing the control dependency chain and data dependency chain of the candi-date loophole statements.Secondly, the word vector model was used to generate the initial node representation vector of the feature dependency graph.Finally, a loophole detection neural network oriented to feature dependence graph was constructed, in which the graph learning network learned the heterogeneous neighbor node information of the feature de-pendency graph and the detection network extracted global features and performed loophole detection.The experimental results show that the recall rate and F1 score of the proposed method are improved by 1.50%～22.32% and 1.86%～16.69% respectively, which is superior to the existing method.…”
Get full text

A Novel Feature Extraction Method for Nonintrusive Appliance Load Monitoring by Khaled Chahine, Khalil El Khamlichi Drissi

“…This system captures the signals from the aggregate consumption, extracts the features from these signals and classifies the extracted features in order to identify the switched-on appliances. …”
Get full text

Food Security of Kuzbass Region Population in 1905-1907: Local Features by A. Y. Karpinets

Get full text

Bearing Fault Diagnosis based on Feature Visualization and Depth Adaptive Network by Hong Jiang, Yu Feng, Rong Fu

“…Aiming at the problem that feature extraction in bearing fault diagnosis needs to rely heavily on manual experience and expert knowledge，a bearing fault diagnosis method based on Gramian angle field（GAF） transformation and adaptive depth network is proposed. …”
Get full text

Speaker verification method based on cross-domain attentive feature fusion by Zhen YANG, Tianlang WANG, Haiyan GUO, Tingting WANG

“…Aiming at the problem that the lack of structure information among speech signal sample in the front-end acoustic features of speaker verification system, a speaker verification method based on cross-domain attentive feature fusion was proposed.Firstly, a feature extraction method based on the graph signal processing (GSP) was proposed to extract the structural information of speech signals, each sample point in a speech signal frame was regarded as a graph node to construct the speech graph signal and the graph frequency information of the speech signal was extracted through the graph Fourier transform and filter banks.Then, an attentive feature fusion network with the residual neural network and the squeeze-and- excitation block was proposed to fuse the features in the traditional time-frequency domain and those in the graph frequency domain to promote the speaker verification system performance.Finally, the experiment was carried out on the VoxCeleb, SITW, and CN-Celeb datasets.The experimental results show that the proposed method performs better than the baseline ECAPA-TDNN model in terms of equal error rate (EER) and minimum detection cost function (min-DCF).…”
Get full text

Speaker verification method based on cross-domain attentive feature fusion by Zhen YANG, Tianlang WANG, Haiyan GUO, Tingting WANG

“…Aiming at the problem that the lack of structure information among speech signal sample in the front-end acoustic features of speaker verification system, a speaker verification method based on cross-domain attentive feature fusion was proposed.Firstly, a feature extraction method based on the graph signal processing (GSP) was proposed to extract the structural information of speech signals, each sample point in a speech signal frame was regarded as a graph node to construct the speech graph signal and the graph frequency information of the speech signal was extracted through the graph Fourier transform and filter banks.Then, an attentive feature fusion network with the residual neural network and the squeeze-and- excitation block was proposed to fuse the features in the traditional time-frequency domain and those in the graph frequency domain to promote the speaker verification system performance.Finally, the experiment was carried out on the VoxCeleb, SITW, and CN-Celeb datasets.The experimental results show that the proposed method performs better than the baseline ECAPA-TDNN model in terms of equal error rate (EER) and minimum detection cost function (min-DCF).…”
Get full text

CHILDREN TRANSPORTATION BY BUSES IN INTERCITY TRANSFERS TAKING INTO ACCOUNT AGE FEATURES by O. E. Yanuchkova, M. R. Yanuchkov, N. V. Yakunina

“…The paper is devoted to the problem of organized children transfers by road transport (buses) in intercity connection. …”
Get full text

Enhancing Robustness in Feature Importance Methods with NAFIC and CESHAP for Improved Interpretability by Grigorios Tzionis, Georgia Kougka, Ilias Gialampoukidis, Stefanos Vrochidis, Ioannis Kompatsiaris, Maro Vlachopoulou

“…To address this problem, we introduce the Complexity and Interaction Enhanced SHAP (CESHAP), a novel feature importance method that incorporates model complexity and feature interactions. …”
Get full text

The Impact of Feature Extraction in Random Forest Classifier for Fake News Detection by Dhani Ariatmanto, Anggi Muhammad Rifai

“…The influence of fake news has become a pressing social problem, shaping public opinion in important events such as elections. …”
Get full text

Features of civic consciousness of university students at the present stage of educational development by I. V. Koltsova, V. V. Dolganina, M. I. Plugina

“…Aim. To study the features of civic consciousness among modern university students.Material and methods. …”
Get full text

Real-time Semantic Segmentation Method Based on Improved Feature Fusion by WANG Xiao yu, LI Zhi bin

“… Aiming at the problem that both location information and semantic information need to be considered in real-time semantic segmentation tasks, we proposed a real-time semantic segmentation method based on improved feature fusion. …”
Get full text

A text classification model for dynamic fusion of global and local features by ZHENG Wenjun, ZHANG Shunxiang

“…From the analysis of the ablation experiment, the dynamic fusion enhancement module fully makes the global temporal features and local semantic features of the text fused together, effectively solving the problem of insufficient use of global and local information in the text classification model.…”
Get full text

Theoretical model of effective elastic moduli of composites considering the inclusion features by Xuqian Liu, Zhangyu Wu, Shuohui Chen

“…Quantifying the effect of composition on the two-phase composite’s mechanical properties is crucial for the life prediction and durability design of the whole structure. Features of inclusions, especially shape and size, affect the two-phase composites’ effective elastic moduli significantly. …”
Get full text

Structural-Semantic Features of Parenthetical Constructions (by Material of Modern English Fiction) by I. S. Shishkina, A. Yu. Mironina

Get full text

Explorative Binary Gray Wolf Optimizer with Quadratic Interpolation for Feature Selection by Yijie Zhang, Yuhang Cai

“…This paper proposes a novel binary Gray Wolf Optimization algorithm to address the feature selection problem in classification tasks. …”
Get full text

Texture Analysis and Classification using Local Binary Patterns and Statistical Features by Hasan Maher

Get full text

Acoustic fault diagnosis of traction motor bearing based on fusion feature by YANG Gang, WEI Yuqian, LI Fu

“…Aiming at the problem that a small number of features cannot fully characterize the bearing fault when applying machine learning to acoustic fault diagnosis, this paper proposes to superimpose and fuse the Gramian angular field (GAF) and wavelet time-frequency figure to form a six channel fusion feature map to effectively characterize the bearing fault. …”
Get full text

Two-branch Shape Complement Network for Feature Missing Splicing Mode by SUNJin, MAHaotian, LEIZhenting, LIANGLi

“…By decoding the global features , the target skeleton point cloud is obtained , and the global features of the point cloud are guaranteed. …”
Get full text

Unified Depth-Guided Feature Fusion and Reranking for Hierarchical Place Recognition by Kunmo Li, Yongsheng Ou, Jian Ning, Fanchang Kong, Haiyang Cai, Haoyang Li

“…Prevailing VPR methods predominantly employ RGB-based features for query image retrieval and correspondence establishment. …”
Get full text