• 한국정보시스템학회지:정보시스템연구
• /
• 제31권4호
• /
• pp.01-23
• /
• 2022

Purpose This study aims to propose a deep learning-based fake review detection model by combining authors' linguistic features and semantic information of reviews. Design/methodology/approach This study used 358,071 review data of Yelp to develop fake review detection model. We employed linguistic inquiry and word count (LIWC) to extract 24 linguistic features of authors. Then we used deep learning architectures such as multilayer perceptron(MLP), long short-term memory(LSTM) and transformer to learn linguistic features and semantic features for fake review detection. Findings The results of our study show that detection models using both linguistic and semantic features outperformed other models using single type of features. In addition, this study confirmed that differences in linguistic features between fake reviewer and authentic reviewer are significant. That is, we found that linguistic features complement semantic information of reviews and further enhance predictive power of fake detection model.

• Asia pacific journal of information systems
• /
• 제31권3호
• /
• pp.335-357
• /
• 2021

As reproduction of images can be done with ease, copy detection has increasingly become important. In the duplication process, image modifications are likely to occur and some alterations are deliberate and can be viewed as attacks. A wide range of copy detection techniques has been proposed. In our study, content-based copy detection, which basically applies DCT-based features for images, namely, pixel values, edges, texture information and frequency-domain component distribution, is employed. Experiments are carried out to evaluate robustness and sensitivity of DCT-based features from attacks. As different types of DCT-based features hold different pieces of information, how features and attacks are related can be shown in their robustness and sensitivity. Rather than searching for proper features, use of robustness and sensitivity is proposed here to realize how the attacked features have changed when an image attack occurs. The experiments show that, out of ten attacks, the neural networks are able to detect seven attacks namely, Gaussian noise, S&P noise, Gamma correction (high), blurring, resizing (big), compression and rotation with mostly related to their sensitive features.

• 말소리와 음성과학
• /
• 제1권4호
• /
• pp.127-132
• /
• 2009

The feature vectors which are used in conventional speaker recognition (SR) systems may have many correlations between their neighbors. To improve the performance of the SR, many researchers adopted linear transformation method like principal component analysis (PCA). In general, the linear transformation of the feature vectors is based on concatenated form of the static features and their dynamic features. However, the linear transformation which based on both the static features and their dynamic features is more complex than that based on the static features alone due to the high order of the features. To overcome these problems, we propose an efficient method that applies linear transformation and temporal information of the features to reduce complexity and improve the performance in speaker verification (SV). The proposed method first performs a linear transformation by PCA coefficients. The delta parameters for temporal information are then obtained from the transformed features. The proposed method only requires 1/4 in the size of the covariance matrix compared with adding the static and their dynamic features for PCA coefficients. Also, the delta parameters are extracted from the linearly transformed features after the reduction of dimension in the static features. Compared with the PCA and conventional methods in terms of equal error rate (EER) in SV, the proposed method shows better performance while requiring less storage space and complexity.

• 말소리와 음성과학
• /
• 제1권4호
• /
• pp.29-38
• /
• 2009

This study investigated the interaction between consonants and vowels in Korean syllable perception using a speeded classification task (Garner, 1978). Experiment 1 examined whether listeners analytically perceive the component phonemes in CV monosyllables when classification is based on the component phonemes (a consonant or a vowel) and observed a significant redundancy gain and a Garner interference effect. These results imply that the perception of the component phonemes in a CV syllable is not linear. Experiment 2 examined the further relation between consonants and vowels at a subphonemic level comparing classification times based on glottal features (aspiration and lax), on place of articulation features (labial and coronal), and on vowel features (front and back). Across all feature classifications, there were significant but asymmetric interference effects. Glottal feature.based classification showed the least amount of interference effect, while vowel feature.based classification showed moderate interference, and place of articulation feature-based classification showed the most interference. These results show that glottal features are more independent to vowels, but place features are more dependent to vowels in syllable perception. To examine the three-way interaction among glottal, place of articulation, and vowel features, Experiment 3 featured a modified Garner task. The outcome of this experiment indicated that glottal consonant features are independent to both the place of articulation and vowel features, but the place of articulation features are dependent to glottal and vowel features. These results were interpreted to show that speech perception is not abstract and discrete, but nonlinear, and that the perception of features corresponds to the hierarchical organization of articulatory features which is suggested in nonlinear phonology (Clements, 1991; Browman and Goldstein, 1989).

• 한국콘텐츠학회논문지
• /
• 제22권2호
• /
• pp.326-336
• /
• 2022

본 연구는 한국 대학생들의 미국 영어 모음 발화를 자질적으로 분석하여 한국인의 영어 모음 발화의 특성을 알아보는 것을 목적으로 한다. 즉 영어 모음의 분절음 정확도 뿐만 아니라 혀의 전후설성, 혀높이, 원순성, 긴장성과 같은 모음의 자질적 특성들을 분석하여 한국인 학습자가 비교적 쉽게 습득할 수 있는 자질들과 어려워하는 영어모음의 자질들을 밝히고자 했다. 영어 비전공자 대학생들이 11개의 영어 모음 /i, ɪ, eɪ, ɛ, æ, ɑ, oʊ, ɔ, ʊ, u, ʌ/가 포함된 1음절 영어 단어를 발화한 음성자료를 통해, 분절음 정확도 뿐만 아니라 이를 4개의 모음 자질로 분석하였다. 자질 분석 결과, 모든 모음을 통해 전후설성이 가장 쉽게 발화한 자질로 확인된 반면 혀높이와 긴장성 자질은 발화에 어려움이 있는 자질로 확인되었다. 전반적으로 후설모음과 중저모음이 전설모음과 고모음 보다 혀높이와 원순성 자질에서 발화의 어려움을 나타냈다. 개별모음을 볼 때 이중모음 /eɪ/가 모든 자질에서 가장 높은 정확도를 보여 쉽게 습득되는 모음으로 확인되었다. 반면 /ɑ, ɔ, ʌ/는 혀높이와 원순성에서 공통적으로 발화의 어려움을 보였고 고모음 /i, ʊ, u/는 긴장성 자질에서 어려움을 보였다. 각 자질들 사이의 상관관계를 분석한 결과에서는 혀높이-원순성, 그리고 혀높이-긴장성 두 자질쌍이 강한 상관성을 나타냈다. 이와 같은 연구 결과를 바탕으로 실제 교실 학습에 적용할 수 있는 교육적인 함축점도 논의되었다.

• 헤리티지:역사와 과학
• /
• 제43권3호
• /
• pp.26-47
• /
• 2010

발굴유구에서 보존은 보존에 복원을 포괄하는 개념이며, 여기서 복원은 유구 원래의 원형으로 복원하는 것을 의미하는 것이 아니라, 발굴 당시의 모습 그대로 복원하는 것을 의미한다. 즉 발굴유구 보존은 수리복원의 개념이 함께 포함된 것이다. 발굴유구는 보존하는 위치에 따라 크게 현장보존과 이전보존으로 나눌 수 있다. 현장보존은 발굴유구를 현장에 그대로 보존하는 것으로 유구의 훼손을 방지하기 위해 복토하는 복토 현장보존법과 유구를 노출된 상태 그대로 보존하는 노출 현장보존법이 있다. 유구가 발굴된 장소에서 다른 장소로 이전하는 것을 전제로 한 보존방법을 이전보존이라 하며, 세부방법으로 원형이전, 전사이전, 복제이전, 해체이전으로 나눌 수 있다. 원형이전은 유구의 원형을 그대로 다른 곳에 이전하는 방법이고, 전사이전은 유구 표면의 일정부분을 떼어내어 이전하는 것이다. 복제이전은 발굴된 유구의 형태를 본떠 이전할 곳에서 다시 복원하는 방법이며, 해체이전은 유구를 구성하고 있는 부재를 해체 이전하여 해체의 역순으로 복원하는 방법이다. 발굴유구의 보존에서 가장 기본이 되는 것은 발굴유구의 원형을 그대로 보존하는 것이지만 실제로는 발굴유구를 둘러싼 여러 가지 환경 즉 사회 경제 문화 지역 상황에 따라 보존방법이 결정되는 경향이 있다. 앞으로 더 효과적인 발굴유구 보존을 위해 보존방법별로 좀 더 세분화되고 전문화된 방안을 도출하고, 인접학문과의 교류 및 발전하는 과학기술을 접목시켜 발굴유구를 가장 효과적으로 보존할 수 있는 방법에 대한 지속적인 연구가 필요하다.

• 한국의류학회지
• /
• 제30권11호
• /
• pp.1560-1571
• /
• 2006

The purpose of this study is to analyze relations between digital characteristics and formative features of fashion design in digital era, to find out the best way to make desirable clothes in the future affected by digital characteristics. The methods of this study are documentary research of previous studies and case study. For the study of formative features of fashion design, 100 kinds of pictures have been selected from photographs in fashion magazines, professional books and internet sites. In the theoretical study, digital characteristics are limitless repetition, compressibility, interactivity, ease of deformation and mobility. And formative features of digital design are plasticity & geometry, assemblage, joints & connections, transparency and deformation. The results of analysis are as follow. Formative features of fashion design in digital era are classified nonlinearity, variability and hybrid. There are organic relations between digital characteristics and formative features of fashion design as well as between digital characteristics and formative features of digital design. Also, there is significant similarity between formative features of digital design and formative features of fashion design in digital era.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• 디지털융복합연구
• /
• 제8권4호
• /
• pp.177-184
• /
• 2010

모바일 환경에서 사용자들은 실시간으로 언제 어디서나 스마트 폰 서비스를 이용할 수 있을 뿐만 아니라 사용자의 상황에 적합한 정보를 제공받을 수 있다. 이러한 스마트 폰 서비스의 고유한 특성을 반영한 학계의 연구가 부족한 실정임을 감안하여 본 연구에서는 스마트 폰 서비스의 특성들과 사용자 특성에 관해 탐색적 연구를 수행하였다. 연구결과 스마트 폰 서비스 특성과 사용자 특성을 분류하면 다음과 같다. 스마트 폰 서비스 특성은 즉시접속성, 상황 의존성으로, 스마트 폰 사용자 특성은 사용자 친숙도, 사용자 혁신성, 그리고 스마트 폰 기술 특성은 보안성, 연결성으로 분류되었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.