• Journal of Information Processing Systems
• /
• v.4 no.1
• /
• pp.17-26
• /
• 2008

This research proposes a new strategy where documents are encoded into string vectors and modified version of KNN to be adaptable to string vectors for text categorization. Traditionally, when KNN are used for pattern classification, raw data should be encoded into numerical vectors. This encoding may be difficult, depending on a given application area of pattern classification. For example, in text categorization, encoding full texts given as raw data into numerical vectors leads to two main problems: huge dimensionality and sparse distribution. In this research, we encode full texts into string vectors, and modify the supervised learning algorithms adaptable to string vectors for text categorization.

• Journal of information and communication convergence engineering
• /
• v.18 no.1
• /
• pp.33-38
• /
• 2020

Elasticsearch is an open source search and analytics engine that can search petabytes of data in near real time. It is designed as a distributed system horizontally scalable and highly available. It provides RESTful APIs, thereby making it programming-language agnostic. Full text search of multilingual text requires language-specific analyzers and field mappings appropriate for indexing and searching multilingual text. Additionally, a language detector can be used in conjunction with the analyzers to improve the multilingual text search. Elasticsearch provides more than 40 language analysis plugins that can process text and extract language-specific tokens and language detector plugins that can determine the language of the given text. This study investigates three different approaches to index and search Chinese, Japanese, and Korean (CJK) text (single analyzer, multi-fields, and language detector-based), and identifies the advantages of the language detector-based approach compared to the other two.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.3
• /
• pp.405-415
• /
• 2020

With the increase in smartphone user, mobile forensics has become an essential element in modern digital forensic investigation. Mobile messenger data is very important data in mobile forensics because it can acquire information such as user's life pattern and mental state. In order to analyze messenger data, a decryption technique of an encrypted messenger data is required. Since most messengers provide a message deleting function, a technique for recovering deleted messages is required. WeChat Messenger, a messenger used by about 1 billion people around the world, uses IMEI (International Mobile Equipment Identity) information to encrypt data and provides message deletion function. In this paper, we propose a data decryption method in the absence of IMEI information and propose a method for recovering deleted messages using FTS (Full Text Search) database created for full-text search function of SQLite database.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.20 no.6
• /
• pp.43-51
• /
• 2010

It is meaningful to investigate data in unallocated space because we can investigate the deleted data. Consecutively complete file recovery using the File Carving is possible in unallocated area, but noncontiguous or incomplete data recovery is impossible. Typically, the analysis of the data fragments are needed because they should contain large amounts of information. Microsoft Word, Excel, PowerPoint and PDF document file's text are stored using compression or specific document format. If the part of aforementioned document file was stored in unallocated data fragment, text extraction is possible using specific document format. In this paper, we suggest the method of extracting a particular document file text in unallocated data fragment.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.785-792
• /
• 2021

Since the Fourth Industrial Revolution, various changes have occurred in society as a whole due to advance in technologies such as artificial intelligence and big data. The amount of data that can be collect in the process of applying important technologies tends to increase rapidly. Especially in academia, existing generated literature data is analyzed in order to grasp research trends, and analysis of these literature organizes the research flow and organizes some research methodologies and themes, or by grasping the subjects that are currently being talked about in academia, we are making a lot of contributions to setting the direction of future research. However, it is difficult to access whether data collection is necessary for the analysis of document data without the expertise of ordinary programs. In this paper, propose a text mining-based topic modeling Web application model. Even if you lack specialized knowledge about data analysis methods through the proposed model, you can perform various tasks such as collecting, storing, and text-analyzing research papers, and researchers can analyze previous research and research trends. It is expect that the time and effort required for data analysis can be reduce order to understand.

• Human Ecology Research
• /
• v.61 no.4
• /
• pp.687-707
• /
• 2023

This study was conducted to obtain useful information on the development of the future second-hand fashion market by obtaining information on the current situation through unstructured text data distributed as news articles related to 'purchase of second-hand clothing' and 'purchase of second-hand luxury goods'. Text-based unstructured data was collected on a daily basis from Naver news from January 1st to December 31st, 2022, using 'purchase of second-hand clothing' and 'purchase of second-hand luxury goods' as collection keywords. This was analyzed using text mining, and the results are as follows. First, looking at the frequency, the collection data related to the purchase of second-hand luxury goods almost quadrupled compared to the data related to the purchase of second-hand clothing, indicating that the purchase of second-hand luxury goods is receiving more social attention. Second, there were common words between the data obtained by the two collection keywords, but they had different words. Regarding second-hand clothing, words related to donations, sharing, and compensation sales were mainly mentioned, indicating that the purchase of second-hand clothing tends to be recognized as an eco-friendly transaction. In second-hand luxury goods, resale and genuine controversy related to the transaction of second-hand luxury goods, second-hand trading platforms, and luxury brands were frequently mentioned. Third, as a result of clustering, data related to the purchase of second-hand clothing were divided into five groups, and data related to the purchase of second-hand luxury goods were divided into six groups.

• The Korean Journal of Applied Statistics
• /
• v.27 no.7
• /
• pp.1207-1217
• /
• 2014

2011 Korean Economic Census is the first economic census in Korea, which contains text data on menus served by Korean-food restaurants as well as structured data on characteristics of restaurants including area, opening year and total sales. In this paper, we applied text mining to the text data and investigated statistical and technical issues and characteristics of Korean text mining. Pork belly roast was the most popular menu across provinces and/or restaurant types in year 2010, and the number of restaurants per 10000 people was especially high in Kangwon-do and Daejeon metropolitan city. Beef tartare and fried pork cutlet are popular menus in start-up restaurants while whole chicken soup and maeuntang (spicy fish stew) are in long-lived restaurants. These results can be used as a guideline for menu development to restaurant owners, and for government policy-making process that lead small restaurants to choose proper menus for successful business.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.41-49
• /
• 2024

Speech recognition technology is continuously advancing and widely used in various fields. In this study, we aimed to investigate the impact of speech data quality on speech recognition models by dividing the dataset into the entire dataset and the top 70% based on Signal-to-Noise Ratio (SNR). Utilizing Seamless M4T and Google Cloud Speech-to-Text, we examined the text transformation results for each model and evaluated them using the Levenshtein Distance. Experimental results revealed that Seamless M4T scored 13.6 in models using data with high SNR, which is lower than the score of 16.6 for the entire dataset. However, Google Cloud Speech-to-Text scored 8.3 on the entire dataset, indicating lower performance than data with high SNR. This suggests that using data with high SNR during the training of a new speech recognition model can have an impact, and Levenshtein Distance can serve as a metric for evaluating speech recognition models.

• Journal of Computing Science and Engineering
• /
• v.5 no.3
• /
• pp.161-166
• /
• 2011

We present a fast algorithm for Korean text extraction and segmentation from subway signboards using smart phone sensors in order to minimize computational time and memory usage. The algorithm can be used as preprocessing steps for optical character recognition (OCR): binarization, text location, and segmentation. An image of a signboard captured by smart phone camera while holding smart phone by an arbitrary angle is rotated by the detected angle, as if the image was taken by holding a smart phone horizontally. Binarization is only performed once on the subset of connected components instead of the whole image area, resulting in a large reduction in computational time. Text location is guided by user's marker-line placed over the region of interest in binarized image via smart phone touch screen. Then, text segmentation utilizes the data of connected components received in the binarization step, and cuts the string into individual images for designated characters. The resulting data could be used as OCR input, hence solving the most difficult part of OCR on text area included in natural scene images. The experimental results showed that the binarization algorithm of our method is 3.5 and 3.7 times faster than Niblack and Sauvola adaptive-thresholding algorithms, respectively. In addition, our method achieved better quality than other methods.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.761-772
• /
• 2020

This paper presents an automatic proficiency assessment method for a non-native Korean read utterance using bidirectional long short-term memory (BLSTM)-based acoustic models (AMs) and speech data augmentation techniques. Specifically, the proposed method considers two scenarios, with and without prompted text. The proposed method with the prompted text performs (a) a speech feature extraction step, (b) a forced-alignment step using a native AM and non-native AM, and (c) a linear regression-based proficiency scoring step for the five proficiency scores. Meanwhile, the proposed method without the prompted text additionally performs Korean speech recognition and a subword un-segmentation for the missing text. The experimental results indicate that the proposed method with prompted text improves the performance for all scores when compared to a method employing conventional AMs. In addition, the proposed method without the prompted text has a fluency score performance comparable to that of the method with prompted text.