• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Journal of the Korean Society for Library and Information Science
• /
• v.33 no.3
• /
• pp.63-86
• /
• 1999

This article investigates the general characteristics and developments of the MARC format for holdings data. It also analyzes the record structure, content designation, and the content of it, mainly based on USMARC and KORMARC formats. Structure and content designation of them are almost same with those of the bibliographic and authority formats. The data fields divided into functional blocks based on their functions, but only 0XX, 5XX, 8XX fields are used in the holdings formats. Record contents of the data in the 008 fields include more elements related to the holdings and acquisition information. Variable fields can be grouped into several blocks, including those for numbers and codes; for notes fields, for location , and for holdings data. Holdings data fields include caption and pattern fields, enumeration and chronology fields, textual holdings fields, and item information fields. This article analyzes the content in each data fields in detail.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.259-261
• /
• 2016

Cable is very essential material for ship operation as connecting element for whole electrical facilities of ship. The material cost and installation man-hour increment caused by re-installation is unavoidable if cable route has some problem. The purpose of this study is to suggest methods to implement the cable visualization functionality for verifying whether cable route is accurate or not in design phase. This functionality is conducted by representing color of 3D model for strong visibility by refer to textual cable routing information. The electrical engineer can provide cable route information more accurate and on time for cable installation department. As a result, the material cost and installation man-hour reduce due to decreasing ratio of re-installation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• 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.

• Journal of the Korean Society for information Management
• /
• v.40 no.3
• /
• pp.99-118
• /
• 2023

The objective of this study is to identify performance factors in the automatic classification of records by utilizing metadata that contains the contextual information of records. For this study, we collected 97,064 records of original textual information from Korean central administrative agencies in 2022. Various classification algorithms, data selection methods, and feature extraction techniques are applied and compared with the intent to discern the optimal performance-inducing technique. The study results demonstrated that among classification algorithms, Random Forest displayed higher performance, and among feature extraction techniques, the TF method proved to be the most effective. The minimum data quantity of unit tasks had a minimal influence on performance, and the addition of features positively affected performance, while their removal had a discernible negative impact.

• Journal of KIISE
• /
• v.44 no.2
• /
• pp.139-147
• /
• 2017

Most of the information prevailing in the Internet space consists of textual information. So one of the main topics regarding the huge document analyses that are required in the "big data" era is the development of an automated understanding system for textual data; accordingly, the automation of the keyword extraction for text summarization and abstraction is a typical research problem. But the simple listing of a few keywords is insufficient to reveal the complex semantic structures of the general texts. In this paper, a text-visualization method that constructs a graph by computing the related degrees from the selected keywords of the target text is developed; therefore, two construction models that provide the edge relation are proposed for the computing of the relation degree among keywords, as follows: influence-interval model and word- distance model. The finally visualized graph from the keyword-derived edge relation is more flexible and useful for the display of the meaning structure of the target text; furthermore, this abstract graph enables a fast and easy understanding of the target text. The authors' experiment showed that the proposed abstract-graph model is superior to the keyword list for the attainment of a semantic and comparitive understanding of text.

• Journal of Information Technology Services
• /
• v.13 no.1
• /
• pp.43-55
• /
• 2014

More and more people are gravitating to reading products reviews prior to making purchasing decisions. As a number of reviews that vary in usefulness are posted every day, much attention is being paid to measuring their helpfulness. The goal of this paper is to investigate firstly various determinants of the helpfulness of reviews, and intends to examine the moderating effect of product type, i.e., search or experience goods on the product sales, helpfulness and helpfulness votes of online reviews. The determinants include product data, review characteristics, and textual characteristics of reviews. The results indicate that the direct effect exists for the determinants of product sales, helpfulness, and helpfulness votes. Further, the moderating effects of product type exist for these determinants on three dependent variables. The results of study will identify helpful online review and design review sites effectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.137-139
• /
• 2019

본 논문은 다양한 음성 특징과 텍스트를 이용한 멀티 모드 순환신경망 네트워크를 사용하여 음성을 통한 범주형(categorical) 분류 방법과 Arousal-Valence(AV) 도메인에서의 분류방법을 통해 감정인식 결과를 제시한다. 본 연구에서는 음성 특징으로는 MFCC, Energy, Velocity, Acceleration, Prosody 및 Mel Spectrogram 등의 다양한 특징들의 조합을 이용하였고 이에 해당하는 텍스트 정보를 순환신경망 기반 네트워크를 통해 융합하여 범주형 분류 방법과 과 AV 도메인에서의 분류 방법을 이용해 감정을 이산적으로 분류하였다. 실험 결과, 음성 특징의 조합으로 MFCC Energy, Velocity, Acceleration 각 13 차원과 35 차원의 Prosody 의 조합을 사용하였을 때 범주형 분류 방법에서는 75%로 다른 특징 조합들 보다 높은 결과를 보였고 AV 도메인 에서도 같은 음성 특징의 조합이 Arousal 55.3%, Valence 53.1%로 각각 가장 높은 결과를 보였다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.54-59
• /
• 2010

Special-purpose microcontrollers PLCs have been widely used in the area of industrial automation. For the research of analysis and verification for PLC programs, first of all we have to specify formal sematics of PLC programming languages. This paper defines formally the operational semantics of LD language. After we transform the graphical language LD into its textual representation Symbolic LD, we give semantics of Symbolic LD since LD language is a graphical language. This paper defines the natural sematics of Symbolic LD and formalizes it in Coq proof assistant.

• Journal for History of Mathematics
• /
• v.33 no.4
• /
• pp.181-222
• /
• 2020

《Xiangming Suanfa》 is a mathematics text published in 1373. The preface and postscript of the block books 《Xiangming Suanfa》 in the Joseon Dynasty were published as they had been in the original text from China. It can be considered to be based on 《Xiangming Suanfa》 was published in Mingjingtang. The five different block books which is published in Korea, possessed in Yonsei University Library, Sanghuh Memorial Library of Konkuk University and the National Library of Korea, were compared. Through recension-correction of the text, this thesis is intended to help researchers in utilizing the research by providing fine print.