• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.549-561
• /
• 2022

In the Khmer writing system, the Khmer script is the official letter of Cambodia, written from left to right without a space separator; it is complicated and requires more analysis studies. Without clear standard guidelines, a space separator in the Khmer language is used inconsistently and informally to separate words in sentences. Therefore, a segmented method should be discussed with the combination of the future Khmer natural language processing (NLP) to define the appropriate rule for Khmer sentences. The critical process in NLP with the capability of extensive data language analysis necessitates applying in this scenario. One of the essential components in Khmer language processing is how to split the word into a series of sentences and count the words used in the sentences. Currently, Microsoft Word cannot count Khmer words correctly. So, this study presents a systematic library to segment Khmer phrases using the bi-directional maximal matching (BiMM) method to address these problematic constraints. In the BiMM algorithm, the paper focuses on the Bidirectional implementation of forward maximal matching (FMM) and backward maximal matching (BMM) to improve word segmentation accuracy. A digital or prefix tree of data structure algorithm, also known as a trie, enhances the segmentation accuracy procedure by finding the children of each word parent node. The accuracy of BiMM is higher than using FMM or BMM independently; moreover, the proposed approach improves dictionary structures and reduces the number of errors. The result of this study can reduce the error by 8.57% compared to FMM and BFF algorithms with 94,807 Khmer words.

• Korean Journal of Cognitive Science
• /
• v.27 no.2
• /
• pp.325-353
• /
• 2016

The visual span refers to the number of letters that can be accurately recognized without moving one's eyes. The size of the visual span is affected by sensory factors such as perimetric complexity, crowding, and mislocation of letters. Korean Hangul utilizes rather unique alphabetic-syllabary writing system, quite different from English and Chinese writing systems. Due to this combinatorial nature of the script, the visual span for Hangul characters can also be affected by the letter type (e.g., CV vs CVCC). The present study examined the effect of syllable complexity on the visual span for Hangul by comparing letter recognition accuracy across four letter type conditions (C only, CV, CVC, and CVCC). We also aimed to determine the meaningful letter type(s) that is associated with differences in reading abilities in Korean. Using a trigram presentation method, we found that overall recognition accuracy declined as syllable complexity increased. However, the visual span for CVC type was greater than that for CV type, suggesting that the effect is not necessarily linear, and that there might be other factors affecting the visual span for these types of letters. C and CV type showed fairly strong positive correlations with reading comprehension, suggesting that these might be the meaningful units for measuring visual span in relating to reading abilities.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.173-180
• /
• 2009

The purpose of developing an automated scoring system for English composition is to score English writing tests and to give diagnostic feedback to the test-takers without human's efforts. The system developed through our research detects grammatical errors of a single sentence on morphological, syntactic and semantic stages, respectively, and those errors are calculated into the final score. The error detecting stages are independent from one another, which causes duplicating the identical errors with different labels at different stages. These duplicated errors become a hindering factor to calculating an accurate score. This paper presents a solution to detecting the duplicated errors and improving an accuracy in calculating the final score by eliminating one of the errors.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.2 s.314
• /
• pp.1-10
• /
• 2007

Branch prediction accuracy is critical for the overall system performance. Branch miss-prediction penalty is the one of the significant performance limiters for improving processor performance, as the pipeline deepens and the instruction issued per cycle increases. In this paper, we propose "Dynamic Per-Branch History Length Fitting Method" by tracking the data dependencies among the register writing instructions. The proposed solution first identifies the key branches, and then it selectively uses the histories of the key branches. To support this mechanism, we provide a history length adjustment algorithm and a required hardware module. As the result of simulation, the proposed mechanism outperforms the previous fixed static method, up to 5.96% in prediction accuracy. Furthermore, our method introduces the performance improvement, compared to the profiled results which are generally considered as the optimal ones.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.521-528
• /
• 2021

Existing image analysis systems in use in the military field are carried out by readers analyzing and identifying images themselves, writing and disseminating related content, and in this process, repetitive tasks are frequent, resulting in workload. In this paper, to solve the previous problem, we proposed an algorithm that can operate the Seq2Seq model on a word basis, which operates on a sentence basis, and applied the Attention technique to improve accuracy. In addition, by applying the Beam Search technique, we would like to recommend various current identification sentences based on the past identification contents of a specific area. It was confirmed through experiments that the Beam Search technique recommends sentences more effectively than the existing greedy Search technique, and confirmed that the accuracy of recommendation increases when the size of Beam is large.

• Journal of the Korea Furniture Society
• /
• v.23 no.1
• /
• pp.95-102
• /
• 2012

The objective of this study was to conduct the species identification and tree-ring dating of Lotus Pedestal of the Amitabha Statue at Ssangbong-Temple in Hwasun. The six wood blocks used for the Lotus Pedestal were hard pines (Pinus spp.; diploxilon) except one piece which was ginkgo (Ginkgo biloba L.). The lotus leaves surrounding the pedestal body were also made of ginkgo. Tree-ring patterns of 3 blocks were synchronized and a 133 years chronology was made. The chronology was crossdated well with the master chronology of Japanese red pine in South Korea. It dated back to A. D. 1551~1683, i.e. the last ring dated A. D. 1683. Through the estimation of the number of sapwood rings removed during carving, the felling year was calculated A. D. $1704{\pm}10$. The calligraphic writing on the Pedestal indicated that this statue was made in A. D. 1694. Therefore, the accuracy of the tree-ring dating has been proven.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.703-713
• /
• 2016

In this paper, we present a segmentation-based method for offline Farsi handwritten word recognition. Although most segmentation-based systems suffer from segmentation errors within the first stages of recognition, using the inherent features of the Farsi writing script, we have segmented the words into sub-words. Instead of using a single complex classifier with many (N) output classes, we have created N simple recurrent neural network classifiers, each having only true/false outputs with the ability to recognize sub-words. Through the extraction of the number of sub-words in each word, and labeling the position of each sub-word (beginning/middle/end), many of the sub-word classifiers can be pruned, and a few remaining sub-word classifiers can be evaluated during the sub-word recognition stage. The candidate sub-words are then joined together and the closest word from the lexicon is chosen. The proposed method was evaluated using the Iranshahr database, which consists of 17,000 samples of Iranian handwritten city names. The results show the high recognition accuracy of the proposed method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.616-619
• /
• 2003

In this paper, we develop an input device equipped with accelerometers and gyroscopes. The installed sensors measure the inertial measurements i.e., accelerations and angular rates produced by the movement of the system when a user is writing on the plane surface or in the three dimensional space. The gyroscope measurement are integrated once to give the attitude of the system and consequently used to remove the gravity included in the acceleration measurements. The compensated accelerations bin doubly integrated to yield the position of the system. Due to the integration processes involved in recovering the users'motions, the accuracy of the position estimation significantly deteriorates with time. Among various error sources of the system incorrect estimation of attitude causes the largest portion of the positioning error since the gravity is not fully cancelled. In order to solve this problem, we propose a Kalman filler-based attitude estimation algorithm which fuses measurement data from accelerometers and gyroscopes by fuzzy logic approach. In addition, the online calibration of the gyroscope biases are performed in parallel with the attitude estimation to give more accurate attitude estimation. The effectiveness and the feasibility of the presented system is demonstrated through computer simulations and actual experiments.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1131-1135
• /
• 2010

The development of modern civilization result from the abundance of material. Yet modern people live with chronic mild stress. Excessive chronic mild stress leads to various diseases. From the risk of the disease in order to protect our bodies need to manage chronic mild stress. The purpose of this study is to inspection the effectiveness of detecting in chronic mild stress using the Multi-sensor system. The Multi-sensor system is designed that can be measure three kinds of vital signals of chronic mild stress for the detection. First Photoplethysmogram(PPG), second Electro Dermal Activity(EDA), third Skin Temperature(SKT). The ages and occupations exposed to chronic mild stress, people often use out of this system was applied to dairy products(Pen). In addition, vital signals that occur when the variety of noise was used to remove the accelerometer. Chronic mild stress by the analysis of measured vital signals from Multi-sensor system to the measurement information to a PC to a wireless transmission(Bluetooth). In this study, using Multi-sensor system writing conditions and a variety of situations in the movement to measure vital signals and measurement results verified the accuracy and reliability. Through this measure chronic mild stress in everyday life and managing to maintain will help more healthy lifestyle.

• IE interfaces
• /
• v.14 no.3
• /
• pp.247-254
• /
• 2001

As current postal automation is limited to dispatch and arrival sorting, delivery sequence sorting is performed manually by each postman. It not only acts as a bottleneck process in the overall mailing process but is expensive operation. To cope with this problem effectively, delivery sequence sorting automation is required. The important components of delivery sequence sorting automation system are sequence sorter and Hangul OCR which function is to extract the address of delivery point. DSI database will be interfaced to both Hangul OCR and sequence sorter for finding the accurate delivery sequence number and stacker number. The objectives of this research are to develop DSI(Delivery Sequence Information) database prototype and client application for managing information effectively. For database requirements collection and analysis, we draw all possible sorting plans, and apply the AHP(Analytic Hierarchy Process) method to determine the optimal one. And then, we design DSI database schema based on the optimal one and implement it using Oracle RDBMS. In addition, as address information in DIS database consist of hierarchical structure which has its correspondence sequence number, so it is important to reorganize sequence information accurately when address information is inserted, deleted or updated. To increase delivery accuracy, we reflect this point in writing application.