• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2101-2123
• /
• 2023

Recent studies have shown that the neural network-based binary code similarity detection technology performs well in vulnerability mining, plagiarism detection, and malicious code analysis. However, existing cross-architecture methods still suffer from insufficient feature characterization and low discrimination accuracy. To address these issues, this paper proposes a cross-architecture binary function similarity detection method based on composite feature model (SDCFM). Firstly, the binary function is converted into vector representation according to the proposed composite feature model, which is composed of instruction statistical features, control flow graph structural features, and application program interface calling behavioral features. Then, the composite features are embedded by the proposed hierarchical embedding network based on a graph neural network. In which, the block-level features and the function-level features are processed separately and finally fused into the embedding. In addition, to make the trained model more accurate and stable, our method utilizes the embeddings of predecessor nodes to modify the node embedding in the iterative updating process of the graph neural network. To assess the effectiveness of composite feature model, we contrast SDCFM with the state of art method on benchmark datasets. The experimental results show that SDCFM has good performance both on the area under the curve in the binary function similarity detection task and the vulnerable candidate function ranking in vulnerability search task.

• Journal of Biomedical Engineering Research
• /
• v.22 no.3
• /
• pp.217-222
• /
• 2001

This paper proposes the new method based on fuzzy logic which recognizes between normal, and abnormal(two types of abnormal : follicular neoplastic, and papillary neoplastic) of thyroid gland cells from pre-obtained 16 feature parameters of image data. This paper applies the genetic algorithms to obtain the dominant feature parameters which have a great influence on discrimination between normal and abnormal cells. This paper shows the effectiveness of proposed method to 240 thyroid gland cells(60 normal cells, 120 follicular neoplastic cells and 60 papillary neoplastic cells) and new dominant feature parameters obtained by genetic algorithms. As a consequence of using the proposed method, average recognition rate of 88.75 % was obtained.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.6
• /
• pp.60-65
• /
• 1994

A study on phonemic feature changes is accomplished by human perception of the discrimination of the phonemic feature of Korean edited speech waveform which is partially elimination or exchange. We found that speech waveforms has tarnsitional, stationary. equivalent and critical phonemic parts.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.502-510
• /
• 2016

Considering video copy transform diversity, a multi-feature video copy detection algorithm based on a Speeded-Up Robust Features (SURF) local descriptor is proposed in this paper. Video copy coarse detection is done by an ordinal measure (OM) algorithm after the video is preprocessed. If the matching result is greater than the specified threshold, the video copy fine detection is done based on a SURF descriptor and a box filter is used to extract integral video. In order to improve video copy detection speed, the Hessian matrix trace of the SURF descriptor is used to pre-match, and dimension reduction is done to the traditional SURF feature vector for video matching. Our experimental results indicate that video copy detection precision and recall are greatly improved compared with traditional algorithms, and that our proposed multiple features algorithm has good robustness and discrimination accuracy, as it demonstrated that video detection speed was also improved.

• The KSFM Journal of Fluid Machinery
• /
• v.15 no.6
• /
• pp.31-38
• /
• 2012

Rotor of rotating machinery is the highly damaged part. Fault of 7 different types was confirmed as the main causes of rotor damage from the pump failure history data in domestic and U.S. nuclear. For each fault types, simulation testing was performed and fault signals were collected form the sensors. To calculate the statistical parameters of time-domain & frequency-domain, measured signals were analyzed by using the discrete wavelet transform, fast fourier transform, statistical analysis. Total 84 parameters were obtained. And Effectiveness factor were used to evaluate the discrimination capacity of each parameter. From the effectiveness factor, RAW-P4/RAW-P7/WT2-NNL/WT2-EE/WT1-P1 showed high ranking. Finally, these parameters were selected as the feature parameters of intelligent fault diagnostics for rotor.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.12
• /
• pp.2761-2768
• /
• 2010

In this paper, we studied the use of the foreground and background features and SVM classifier to improve the accuracy of offline handwritten numeral recognition. The foreground features are two directional features: directional gradient feature by Kirsch operators and directional stroke feature by projection runlength, and the background feature is concavity feature which is extracted from the convex hull of the numeral, where concavity feature functions as complement to the directional features. During classification of the numeral, these three features are combined to obtain good discrimination power. The efficiency of our feature sets was tested by recognition experiments on the handwritten numeral database CENPARMI, where we used SVM with RBF kernel as a classifier. The experimental results showed that each combination of two or three features gave a better performance than a single feature. This means that each single feature works with a different discriminating power and cooperates with other features to enhance the recognition accuracy. By using the composite feature of the three features, we achieved a recognition rate of 98.90%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.3
• /
• pp.203-216
• /
• 2003

In this paper a new feature extraction and target classification method is proposed for the recognition part of FLIR(Forwar Looking Infrared)-image-based ATR system. Proposed feature extraction method is "cluster(=set of classes)-based"version of previous fisherfaces method that is known by its robustness to illumination changes in face recognition. Expecially introduced class clustering and cluster-based projection method maximizes the performance of fisherfaces method. Proposed target image classification method is based on the mixture of experts model which consists of RBF-type experts and MLP-type gating networks. Mixture of experts model is well-suited with ATR system because it should recognizee various targets in complexed feature space by variously mixed conditions. In proposed classification method, one expert takes charge of one cluster and the separated structure with experts reduces the complexity of feature space and achieves more accurate local discrimination between classes. Proposed feature extraction and classification method showed distinguished performances in recognition test with customized. FLIR-vehicle-image database. Expecially robustness to pixelwise sensor noise and un-wanted intensity variations was verified by simulation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.6
• /
• pp.323-330
• /
• 2021

Visual object tracking is a challenging area of study in the field of computer vision due to many difficult problems, including a fast variation of target shape, occlusion, and arbitrary ground truth object designation. In this paper, we focus on the reinforced feature of the dynamic search area to get better performance than conventional discriminative model prediction trackers on the condition when the accuracy deteriorates since low feature discrimination. We propose a reinforced input feature method shown like the spotlight effect on the dynamic search area of the target tracking. This method can be used to improve performances for deep learning based discriminative model prediction tracker, also various types of trackers which are used to infer the center of the target based on the visual object tracking. The proposed method shows the improved tracking performance than the baseline trackers, achieving a relative gain of 38% quantitative improvement from 0.433 to 0.601 F-score at the visual object tracking evaluation.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.541-548
• /
• 2016

The use of social media is already essential as a source of information for listening user's various opinions and monitoring. We define social 'risks' that issues effect negative influences for public opinion in social media. This paper aims to discriminate various linguistic features and reveal their effects for building an automatic classification model of social risks. Expecially we adopt a word embedding technique for representation of linguistic clues in risk sentences. As a preliminary experiment to analyze characteristics of individual features, we revise errors in automatic linguistic analysis. At the result, the most important feature is NE (Named Entity) information and the best condition is when combine basic linguistic features. word embedding, and word clusters within core predicates. Experimental results under the real situation in social bigdata - including linguistic analysis errors - show 92.08% and 85.84% in precision respectively for frequent risk categories set and full test set.

• Korean Journal of Remote Sensing
• /
• v.21 no.2
• /
• pp.145-162
• /
• 2005

To improve the accuracy of land-cover discrimination in SAB data classification, this paper presents a methodology that includes feature extraction and fusion steps with multi-temporal SAR data. Three features including average backscattering coefficient, temporal variability and coherence are extracted from multi-temporal SAR data by considering the temporal behaviors of backscattering characteristics of SAR sensors. Dempster-Shafer theory of evidence(D-S theory) and fuzzy logic are applied to effectively integrate those features. Especially, a feature-driven heuristic approach to mass function assignment in D-S theory is applied and various fuzzy combination operators are tested in fuzzy logic fusion. As experimental results on a multi-temporal Radarsat-1 data set, the features considered in this paper could provide complementary information and thus effectively discriminated water, paddy and urban areas. However, it was difficult to discriminate forest and dry fields. From an information fusion methodological point of view, the D-S theory and fuzzy combination operators except the fuzzy Max and Algebraic Sum operators showed similar land-cover accuracy statistics.