• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1583-1598
• /
• 2019

Recently, software has increased in complexity and been applied in various industrial fields. As a result, the presence of software bugs cannot be avoided. Various bug severity prediction methodologies have been proposed, but their performance needs to be further improved. In this study, we propose a novel technique for bug severity prediction in cross projects such as Eclipse, Mozilla, WireShark, and Xamarin by using topic modeling and similarity (i.e., KL-divergence). First, we construct topic models from bug repositories in cross projects using Latent Dirichlet Allocation (LDA). Then, we find topics in each project that contain the most numerous similar bug reports by using a new bug report. Next, we extract the bug reports belonging to the selected topics and input them to a Naïve Bayes Multinomial (NBM) algorithm. Finally, we predict the bug severity in the new bug report. In order to evaluate the performance of our approach and to verify the difference between cross projects and single project, we compare it with the Naïve Bayes Multinomial approach; the Lamkanfi methodology, which is a well-known bug severity prediction approach; and an emotional similarity-based bug severity prediction approach. Our approach exhibits a better performance than the compared methods.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.3
• /
• pp.216-221
• /
• 2010

In this paper, we propose speaker verification method using Support Vector Machine (SVM) kernel with Gaussian Mixture Model (GMM)-supervector based on the Mahalanobis distance. The proposed GMM-supervector SVM kernel method is combined GMM with SVM. The GMM-supervectors are generated by GMM parameters of speaker and other speaker utterances. A speaker verification threshold of GMM-supervectors is decided by SVM kernel based on Mahalanobis distance to improve speaker verification accuracy. The experimental results for text-independent speaker verification using 20 speakers demonstrates the performance of the proposed method compared to GMM, SVM, GMM-supervector SVM kernel based on Kullback-Leibler (KL) divergence, and GMM-supervector SVM kernel based on Bhattacharyya distance.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.83-89
• /
• 2023

The clustering technique using RF fingerprint extracts the characteristic signature of the transmitters which are embedded in the transmission waveforms. The output of the RF-Fingerprint feature extraction algorithm for clustering identical DMR(Digital Mobile Radios) is a high-dimensional feature, typically consisting of 512 or more dimensions. While such high-dimensional features may be effective for the classifiers, they are not suitable to be used as inputs for the clustering algorithms. Therefore, this paper proposes a dimension reduction algorithm that effectively reduces the dimensionality of the multidimensional RF-Fingerprint features while maintaining the fingerprinting characteristics of the DMRs. Additionally, it proposes a clustering algorithm that can effectively cluster the reduced dimensions. The proposed clustering algorithm reduces the multi-dimensional RF-Fingerprint features using t-SNE, based on KL Divergence, and performs clustering using Density Peaks Clustering (DPC). The performance analysis of the DMR clustering algorithm uses a dataset of 3000 samples collected from 10 Motorola XiR and 10 Wintech N-Series DMRs. The results of the RF-Fingerprinting-based clustering algorithm showed the formation of 20 clusters, and all performance metrics including Homogeneity, Completeness, and V-measure, demonstrated a performance of 99.4%.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.167-175
• /
• 2021

Semi-supervised learning uses both labeled data and unlabeled data. Recently consistency regularization is very popular in semi-supervised learning. Unsupervised data augmentation (UDA) that uses unlabeled data augmentation is also based on the consistency regularization. The Kullback-Leibler divergence is used for the loss of unlabeled data and cross-entropy for the loss of labeled data through UDA learning. UDA uses techniques such as training signal annealing (TSA) and confidence-based masking to promote performance. In this study, we propose to use Jensen-Shannon divergence instead of Kullback-Leibler divergence, reverse-TSA and not to use confidence-based masking for performance improvement. Through experiment, we show that the proposed technique yields better performance than those of UDA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.5
• /
• pp.1463-1478
• /
• 2012

Based on the theory of local-world network, the composition self-similarity (CSS) of network traffic is presented for the first time in this paper for the study of DoS detection. We propose the concept of composition distribution graph and design the relative operations. The $(R/S)^d$ algorithm is designed for calculating the Hurst parameter. Based on composition distribution graph and Kullback Leibler (KL) divergence, we propose the composition self-similarity anomaly detection (CSSD) method for the detection of DoS attacks. We evaluate the effectiveness of the proposed method. Compared to other entropy based anomaly detection methods, our method is more accurate and with higher sensitivity in the detection of DoS attacks.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2633-2648
• /
• 2015

The problem of visual words' synonymy and ambiguity always exist in the conventional bag of visual words (BoVW) model based object category methods. Besides, the noisy visual words, so-called "visual stop-words" will degrade the semantic resolution of visual dictionary. In view of this, a novel bag of visual words method based on PLSA and chi-square model for object category is proposed. Firstly, Probabilistic Latent Semantic Analysis (PLSA) is used to analyze the semantic co-occurrence probability of visual words, infer the latent semantic topics in images, and get the latent topic distributions induced by the words. Secondly, the KL divergence is adopt to measure the semantic distance between visual words, which can get semantically related homoionym. Then, adaptive soft-assignment strategy is combined to realize the soft mapping between SIFT features and some homoionym. Finally, the chi-square model is introduced to eliminate the "visual stop-words" and reconstruct the visual vocabulary histograms. Moreover, SVM (Support Vector Machine) is applied to accomplish object classification. Experimental results indicated that the synonymy and ambiguity problems of visual words can be overcome effectively. The distinguish ability of visual semantic resolution as well as the object classification performance are substantially boosted compared with the traditional methods.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.41-43
• /
• 2024

본 연구에서는 Vision Transformer 기반의 Anomaly Detection and Localization (VT-ADL) 모델에 초점을 맞추고, 손실 함수의 변경이 MVTec 데이터셋에 대한 이상 검출 및 지역화 성능에 미치는 영향을 비교 분석한다. 기존의 손실 함수를 KL Divergence와 Log-Likelihood Loss의 조합인 VAE Loss로 대체하여, 성능 변화를 심층적으로 조사했다. 실험을 통해 VAE Loss로의 전환은 VT-ADL 모델의 이상 검출 능력을 현저히 향상시키며, 특히 PRO-score에서 기존 대비 약 5%의 개선을 보였다는 점을 확인하였다. 이러한 결과는 손실 함수의 최적화가 VT-ADL 모델의 전반적인 성능에 중요한 영향을 미칠 수 있음을 시사한다. 또한, 이 연구는 Vision Transformer 기반 모델의 이상 검출과 지역화 작업에 있어서 손실 함수 선택의 중요성을 강조하며, 향후 관련 연구에 유용한 기준을 제공할 수 있을 것으로 기대된다.