• 산업공학
• /
• 제14권3호
• /
• 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.

• Journal of Computing Science and Engineering
• /
• 제10권3호
• /
• pp.95-101
• /
• 2016

In this study, we propose a new system for constructing parallel corpora for sign languages, which are generally under-resourced in comparison to spoken languages. In order to achieve scalability and accessibility regarding data collection and corpus construction, our system utilizes deep learning-based techniques and predicts depth information to perform pose estimation on hand information obtainable from video recordings by a single RGB camera. These estimated poses are then transcribed into expressions in SignWriting. We evaluate the accuracy of hand tracking and hand pose estimation modules of our system quantitatively, using the American Sign Language Image Dataset and the American Sign Language Lexicon Video Dataset. The evaluation results show that our transcription system has a high potential to be successfully employed in constructing a sizable sign language corpus using various types of video resources.

• 전자공학회논문지C
• /
• 제36C권4호
• /
• pp.54-64
• /
• 1999

본 논문에서는 실제 응용분야에서 사용될 수 있는 효율적인 필기 영어 단어 인식 방법을 제안한다. 필기 단어인식과 관련된 대부분의 응용분야에서 제공되는 사전의 활용을 극대화하기 위해 사전단어들을 인식의 초기 단계에서부터 사용한다. 초과 분할된 단어의 세크먼트들과 사전단어들 사이의 정합을 위해 동적 프로그래밍을 사용하며, 정합구간을 가변적으로 조정할 수 있도록 학습단계에서 추출한 문자 분할과 관련된 통계를 활용한다. 또한, 사전단어의 각 문자와 세그먼트들 사이의 정합 결과를 저장하여 반복되는 계산을 피한다. 제안하는 방법의 효용성을 입증하기 위해 다양한 서체를 갖는 실험용 필기 단어영상을 사용하여 실험을 수행한 결과, 사전에 기반한 단어 인식 과정을 최대로 활용하기 위한 가변정합구간 개념 및 문자단위 정합결과 저장 방법이 동적 프로그래밍과 함께 인식 속도 및 정확도 향상에 모두 크게 기여함을 확인하였다.

• 한국IT서비스학회지
• /
• 제3권1호
• /
• pp.21-41
• /
• 2004

The technical proposal suggested and published by MIC(Ministry of Information and Communication, henceforth MIC) contains too general assessment elements, which causes qualitative and subjective assessment of technical proposals. Thus, in terms of the technical proposal assessment. It lacks In fairness, validity and accuracy. Furthermore, it has a great deal of difficulty in assessment caused by the inconsistency between proposal planning and assessment methods. Also, each company has different writing format, so it is impossible to make use of its maneuvering data for the assessment. To overcome these weaknesses, our research focused on a quantitative evaluation on development organization, which is a part of organizational and administrative part of the technical proposal suggested and published by MIC. In this research, we divided development organization for the technical proposal into organization, teams, and team members, and then studied addition, deletion and merging for the assessment criteria. For the related study, we chose especially CMM(Capability Maturity Model) from a lot of international and national references, which is a model measuring the maturity of organization, and then we focused on Small-CMM which is available in the small-sized organization. We also suggested input form, description method, assessment elements for the quantitative assessment in the chosen developmental organization, and finally we proposed standard referencing criteria for the assessment. Our study concludes that our assessment method are valid and available in comparison with the previous Delphi method through a validity evaluation test.

• 한국정밀공학회지
• /
• 제24권4호
• /
• pp.153-158
• /
• 2007

Recently nano imprint lithography to fabricate photonic crystal on polymer is preferred because of its simplicity and short process time and ease of precise manufacturing. But, the technique requires the precise mold as an imprinting tool for good replication. These molds are made of the silicon, nickel and quartz. But this is not desirable due to complex fabrication process, high cost. So, we describe a simple, precise and low cost method of fabricating PDMS stamp to make the photonic crystals. In order to fabricate the PDMS mold, we make the original pattern with designed hole array by finding the optimal electron beam writing condition. And then, we have tried to fabricate PDMS mold by the replica molding with ultrasonic vibration and pressure system. We have used the cleaning process to solve the detaching problem on the interface. Using these methods, we acquired the PDMS mold for photonic crystals with characteristics of a good replication. And the accuracy of replication shows below 1% in 440nm at diameter and in 610nm at lattice constant by dimensional analysis by SEM and AFM.

• Advances in aircraft and spacecraft science
• /
• 제3권1호
• /
• pp.1-14
• /
• 2016

The Carrera Unified Formulation (CUF) is here extended to perform free-vibrational analyses of rotating structures. CUF is a hierarchical formulation, which enables one to obtain refined structural theories by writing the unknown displacement variables using generic functions of the cross-section coordinates (x, z). In this work, Taylor-like expansions are used. The increase of the theory order leads to three-dimensional solutions while, the classical beam models can be obtained as particular cases of the linear theory. The Finite Element technique is used to solve the weak form of the three-dimensional differential equations of motion in terms of "fundamental nuclei", whose forms do not depend on the adopted approximation. Including both gyroscopic and stiffening contributions, structures rotating about either transversal or longitudinal axis can be considered. In particular, the dynamic characteristics of thin-walled cylinders and composite blades are investigated to predict the frequency variations with the rotational speed. The results reveal that the present one-dimensional approach combines a significant accuracy with a very low computational cost compared with 2D and 3D solutions. The advantages are especially evident when deformable and composite structures are analyzed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4241-4254
• /
• 2019

The efficiency and accuracy of handwriting measurement could be improved by adopting digital image processing. This study developed a computer-based Korean Handwriting Assessment tool. Second graders participated in this study by performing writing tasks of consonants, vowels, words, and sentences. We extracted boundary parameters for each letter using digital image processing and calculated the variables of size, size coefficient of variation (CV), misalignment, inter-letter space, inter-word space, and ratio of inter-letter space to inter-word space. Children were also administered traditional handwriting and visuomotor tests. Digital variables from image processing were correlated with these previous tests. Using these correlations, we established a three-point scoring system that computed test scores for each variable. We analyzed inter-rater reliability between the computer rater and human rater and test-retest reliability between the first and second performances. The validity was examined by analyzing the relationship between the Korean Handwriting Assessment and previous handwriting and visuomotor tests. We suggested the Korean Handwriting Assessment to measure size, size consistency, misalignment, inter-letter space, inter-word space, and space ratio using digital image processing. This Korean Handwriting Assessment tool proved to have reliability and validity. It is expected to be useful for assessing children's handwriting.

• 한국인터넷방송통신학회논문지
• /
• 제18권6호
• /
• pp.151-156
• /
• 2018

필기체 숫자인식은 일반적으로 높은 인식률과 문맥 독립이 요구되고 있고, 쓰는 사람에 따라서 많은 차이점이 있어서 자유 필기체 숫자는 인식이나 알고리즘작성에 아직도 어려운 문제점이 있다. 본 연구에서는, 필기체 숫자의 특성을 분석하고, 구조적 특징기반 자유 필기체 숫자인식 알고리즘을 새롭게 제안한다. 주어진 필기 숫자에 대하여, 끝점과 분기점, 수평선과 함께 숫자의 구조적 특징을 연구한다. 이 방법은 확장된 구조적 특징 알고리즘으로 제안되어 강인하며, 그리고 본 연구에서 제안한 구조적 특징에 기반 한 결정 트리(decision tree)는 필기체 숫자 자동인식방법에 구조적으로 기여한다. 본 알고리즘이 다른 방법과 비교하여 인식률과 강인성이 우수함을 실험결과로 보여주었다.

• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1057-1070
• /
• 2021

Case-related news filtering is crucial in legal text mining and divides news into case-related and case-unrelated categories. Because case-related news originates from various fields and has different writing styles, it is difficult to establish complete filtering rules or keywords for data collection. In addition, the labeled corpus for case-related news is sparse; therefore, to train a high-performance classification model, it is necessary to annotate the corpus. To address this challenge, we propose topic-enhanced positive-unlabeled learning, which selects positive and negative samples guided by topics. Specifically, a topic model based on a variational autoencoder (VAE) is trained to extract topics from unlabeled samples. By using these topics in the iterative process of positive-unlabeled (PU) learning, the accuracy of identifying case-related news can be improved. From the experimental results, it can be observed that the F1 value of our method on the test set is 1.8% higher than that of the PU learning baseline model. In addition, our method is more robust with low initial samples and high iterations, and compared with advanced PU learning baselines such as nnPU and I-PU, we obtain a 1.1% higher F1 value, which indicates that our method can effectively identify case-related news.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.