• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2007년도 한국음성과학회 공동학술대회 발표논문집
• /
• pp.45-48
• /
• 2007

This paper proposes a flexible selection method of feature vectors for speaker identification. In speaker identification, overlapped region between speaker models lowers the accuracy. Recently, a method was proposed which discards overlapped feature vectors without regard to the source causing the overlap. We suggest a new method using both overlapped features among speakers and non-overlapped features to mitigate the overlap effects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권8호
• /
• pp.3169-3181
• /
• 2015

Nowadays, online word-of-mouth has become a powerful influencer to marketing and sales in business. Opinion mining and sentiment analysis is frequently adopted at market research and business analytics field for analyzing word-of-mouth content. However, there still remain several challengeable areas for 1) sentiment analysis aiming for Korean word-of-mouth content in film market, 2) availability of machine learning models only using linguistic features, 3) effect of the size of the feature set. This study took a sample of 10,000 movie reviews which had posted extremely negative/positive rating in a movie portal site, and conducted sentiment analysis with four machine learning algorithms: naïve Bayesian, decision tree, neural network, and support vector machines. We found neural network and support vector machine produced better accuracy than naïve Bayesian and decision tree on every size of the feature set. Besides, the performance of them was boosting with increasing of the feature set size.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.297-301
• /
• 2005

In this paper, we propose a method to estimate camera motion parameter based on invariant point features. Typically, feature information of image has drawbacks, it is variable to camera viewpoint, and therefore information quantity increases after time. The LM(Levenberg-Marquardt) method using nonlinear minimum square evaluation for camera extrinsic parameter estimation also has a weak point, which has different iteration number for approaching the minimal point according to the initial values and convergence time increases if the process run into a local minimum. In order to complement these shortfalls, we, first propose constructing feature models using invariant vector of geometry. Secondly, we propose a two-stage calculation method to improve accuracy and convergence by using homography and LM method. In the experiment, we compare and analyze the proposed method with existing method to demonstrate the superiority of the proposed algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권3호
• /
• pp.209-215
• /
• 2014

Sequence tagging is the task of predicting frame-wise labels for a given input sequence and has important applications to diverse domains. Conventional methods such as maximum likelihood (ML) learning matches global features in empirical and model distributions, rather than local features, which directly translates into frame-wise prediction errors. Recent probabilistic sequence models such as conditional random fields (CRFs) have achieved great success in a variety of situations. In this paper, we introduce a novel discriminative CRF learning algorithm to minimize local feature mismatches. Unlike overall data fitting originating from global feature matching in ML learning, our approach reduces the total error over all frames in a sequence. We also provide an efficient gradient-based learning method via gradient forward-backward recursion, which requires the same computational complexity as ML learning. For several real-world sequence tagging problems, we empirically demonstrate that the proposed learning algorithm achieves significantly more accurate prediction performance than standard estimators.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1662-1665
• /
• 2002

This paper proposes a novel semantic feature detection (SFD) method for real-time image transmission of sign language and finger spelling. We extract semantic information as an interlingua from input text by natural language processing, and then transmit the semantic feature detection, which actually is a parameterized action representation, to the 3-D articulated humanoid models prepared in each client in remote locations. Once the SFD is received, the virtual human will be animated by the synthesized SFD. The experimental results based on Japanese sign langauge and Chinese sign langauge demonstrate that this algorithm is effective in real-time image delivery of sign language and finger spelling.

• ETRI Journal
• /
• 제41권5호
• /
• pp.574-584
• /
• 2019

A new Mirai variant found recently was equipped with a dynamic update ability, which increases the level of difficulty for DDoS mitigation. Continuous development of 5G technology and an increasing number of Internet of Things (IoT) devices connected to the network pose serious threats to cyber security. Therefore, researchers have tried to develop better DDoS mitigation systems. However, the majority of the existing models provide centralized solutions either by deploying the system with additional servers at the host site, on the cloud, or at third party locations, which may cause latency. Since Internet service providers (ISP) are links between the internet and users, deploying the defense system within the ISP domain is the panacea for delivering an efficient solution. To cope with the dynamic nature of the new DDoS attacks, we utilized an unsupervised artificial neural network to develop a hierarchical two-layered self-organizing map equipped with a twofold feature selection for DDoS mitigation within the ISP domain.

• International Journal of Computer Science & Network Security
• /
• 제24권5호
• /
• pp.212-216
• /
• 2024

Feature Selection have turned into the main point of investigations particularly in bioinformatics where there are numerous applications. Deep learning technique is a useful asset to choose features, anyway not all calculations are on an equivalent balance with regards to selection of relevant features. To be sure, numerous techniques have been proposed to select multiple features using deep learning techniques. Because of the deep learning, neural systems have profited a gigantic top recovery in the previous couple of years. Anyway neural systems are blackbox models and not many endeavors have been made so as to examine the fundamental procedure. In this proposed work a new calculations so as to do feature selection with deep learning systems is introduced. To evaluate our outcomes, we create relapse and grouping issues which enable us to think about every calculation on various fronts: exhibitions, calculation time and limitations. The outcomes acquired are truly encouraging since we figure out how to accomplish our objective by outperforming irregular backwoods exhibitions for each situation. The results prove that the proposed method exhibits better performance than the traditional methods.

• 정보보호학회논문지
• /
• 제34권3호
• /
• pp.439-449
• /
• 2024

최근 음성 생성 기술의 급격한 발전으로, 텍스트만으로도 자연스러운 음성 합성이 가능해졌다. 이러한 발전은 타인의 음성을 생성하여 범죄에 이용하는 보이스피싱과 같은 악용 사례를 증가시키는 결과를 낳고 있다. 음성 생성 여부를 탐지하는 모델은 많이 개발되고 있으며, 일반적으로 음성의 특징을 추출하고 이러한 특징을 기반으로 음성 생성 여부를 탐지한다. 본 논문은 생성 음성으로 인한 악용 사례에 대응하기 위해 새로운 음성 특징 추출 모델을 제안한다. 오디오를 입력으로 받는 딥러닝 기반 오디오 코덱 모델과 사전 학습된 자연어 처리 모델인 BERT를 사용하여 새로운 음성 특징 추출 모델을 제안하였다. 본 논문이 제안한 음성 특징 추출 모델이 음성 탐지에 적합한지 확인하기 위해 추출된 특징을 활용하여 4가지 생성 음성 탐지 모델을 만들어 성능평가를 진행하였다. 성능 비교를 위해 기존 논문에서 제안한 Deepfeature 기반의 음성 탐지 모델 3개와 그 외 모델과 정확도 및 EER을 비교하였다. 제안한 모델은 88.08%로 기존 모델보다 높은 정확도와 11.79%의 낮은 EER을 보였다. 이를 통해 본 논문에서 제안한 음성 특징 추출 방법이 생성 음성과 실제 음성을 판별하는 효과적인 도구로 사용될 수 있음을 확인하였다.

• KIEE International Transactions on Power Engineering
• /
• 제3A권3호
• /
• pp.139-147
• /
• 2003

The paper presents a novel approach of constructing the state matrix of the multi-machine power system for SSR (subsynchronous resonance) analysis using the linearized equations of individual devices including electrical transmission network dynamics. The machine models in the local d-q reference frame are integrated with the network models in the common R-I reference frame by simply transforming their output equations into the R-I frame where the transformed output is used as the input to the network dynamics or vice versa. The salient feature of the formulation is that it allows for modular construction of various component models without rearranging the overall state space formulation. This universal SSR small signal stability program provides a flexible tool for systematic analyses of SSR small-signal stability impacts of both conventional devices such as generation systems and novel devices such as power electronic apparatus and their controllers. The paper also presents its application results to IEEE benchmark models.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.268-281
• /
• 2022

The development of information technology is bringing many changes to everyday life, and machine learning can be used as a technique to solve a wide range of real-world problems. Analysis and utilization of data are essential processes in applying machine learning to real-world problems. As a method of processing data in machine learning, we propose an approach based on applying multiple linear regression models by interlacing data to the task of classifying similar software. Linear regression is widely used in estimation problems to model the relationship between input and output data. In our approach, multiple linear regression models are generated by training on interlaced feature data. A combination of these multiple models is then used as the prediction model for classifying similar software. Experiments are performed to evaluate the proposed approach as compared to conventional linear regression, and the experimental results show that the proposed method classifies similar software more accurately than the conventional model. We anticipate the proposed approach to be applied to various kinds of classification problems to improve the accuracy of conventional linear regression.