• 한국지능시스템학회논문지
• /
• 제3권1호
• /
• pp.90-96
• /
• 1993

• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 1994년도 종합학술발표회논문집
• /
• pp.303-315
• /
• 1994

• International Journal of Contents
• /
• 제13권2호
• /
• pp.66-74
• /
• 2017

Patent classification is becoming more critical as patent filings have been increasing over the years. Despite comprehensive studies in the area, there remain several issues in classifying patents on IPC hierarchical levels. Not only structural complexity but also shortage of patents in the lower level of the hierarchy causes the decline in classification performance. Therefore, we propose a new method of classification based on different criteria that are categories defined by the domain's experts mentioned in trend analysis reports, i.e. Patent Landscape Report (PLR). Several experiments were conducted with the purpose of identifying type of features and weighting methods that lead to the best classification performance using Support Vector Machine (SVM). Two types of features (noun and noun phrases) and five different weighting schemes (TF-idf, TF-rf, TF-icf, TF-icf-based, and TF-idcef-based) were experimented on.

• Korean Chemical Engineering Research
• /
• 제58권3호
• /
• pp.493-497
• /
• 2020

Hazardous area classification is designed to prevent chemical plant explosions in advance. Generally, the duration of the explosive atmosphere is used for zone type classification. Herein, IEC code, a quantitative zone type classification methodology, was used to achieve Zone 2 NE, which indicates a practical non-explosion condition. This study analyzed the operating pressure of a vessel handling propane to achieve Zone 2 NE by applying the IEC code via MATLAB. The resulting zone type and hazardous area grades were compared with the results from other design standards, namely API and EI codes. According to the IEC code, the operating pressure of vessels handling propane should be between 101325-116560.59 Pa. In contrast, the zone type classification criteria used by API and EI codes are abstract. Therefore, since these codes could interpret excessively explosive atmospheres, care is required while using them for hazardous area classification design.

• 대한임베디드공학회논문지
• /
• 제13권4호
• /
• pp.215-223
• /
• 2018

Recently, as interest of wearable devices has increased, commercially available smart wristbands and applications have been used as a tool for personal healthy management. However most previous studies have focused on evaluating the accuracy and reliability of the technical problems of wearable devices, especially step counts, walking distance, and energy consumption measured from the smart wristbands. In this study, we propose a physical activity evaluation model using classification rules, induced from the associative classification mining approach. These rules associated with five physical activities were generated by considering activities and walking times in target heart rate zones such as 'Out-of Zone', 'Fat Burn Zone', 'Cardio Zone', and 'Peak Zone'. In the experiment, we evaluated the prediction power of classification rules and verified its effectiveness by comparing classification accuracies between the proposed model and support vector machine.

• Geomechanics and Engineering
• /
• 제35권1호
• /
• pp.67-80
• /
• 2023

Due to the nature of the conjunctive Cone Penetration Test(CPT), which does not verify the actual sample directly, geotechnical engineers commonly classify the underground geomaterials using CPT results with the classification diagrams proposed by various researchers. However, such classification diagrams may fail to reflect local geotechnical characteristics, potentially resulting in misclassification that does not align with the actual stratification in regions with strong local features. To address this, this paper presents an objective method for more accurate local CPT soil classification criteria, which utilizes C4.5 decision tree models trained with the CPT results from the clay-dominant southern coast of Korea and the sand-dominant region in South Carolina, USA. The results and analyses demonstrate that the C4.5 algorithm, in conjunction with oversampling, outlier removal, and pruning methods, can enhance and optimize the decision tree-based CPT soil classification model.

• Clinics in Shoulder and Elbow
• /
• 제21권2호
• /
• pp.82-86
• /
• 2018

Background: Although a common shoulder disease, there are no accepted classification criteria for frozen shoulder (FS). This study therefore aimed to evaluate the accuracy of the conventionally used FS classification system. Methods: Primary FS patients (n=168) who visited our clinic from January 2010 to July 2015 were included in the study. After confirming restrictions of the glenohumeral joint motion and absence of history of systemic disease, trauma, shoulder surgery, shoulder muscle weakness, or specific x-ray abnormalities, the Zuckerman and Rokito's classification was employed for diagnosing primary FS. Following clinical diagnosis, each patient underwent a shoulder magnetic resonance imaging (MRI) and blood tests (lipid profile, glucose, hemoglobin A1c, and thyroid function). Based on the results of the blood tests and MRIs, the patients were reclassified, using the criteria proposed by Zuckerman and Rokito. Results: New diagnoses were ascertained including blood test results (16 patients with diabetes, 43 with thyroid abnormalities, and 149 with dyslipidemia), and MRI revealed intra-articular lesions in 81 patients (48.2%). After re-categorization based on the above findings, only 5 patients (3.0%) were classified having primary FS. The remaining 163 patients (97.0%) had either undiagnosed systemic or intrinsic abnormalities (89 patients), whereas 74 patients had both. Conclusions: These findings demonstrate that most patients clinically diagnosed with primary FS had undiagnosed systemic abnormalities and/or intra-articular pathologies. Therefore, a modification of the Zuckerman and Rokito's classification system for FS may be required to include the frequent combinations, rather than having a separate representation of systemic abnormalities and intrinsic causes.

• 한국전자통신학회논문지
• /
• 제11권12호
• /
• pp.1237-1244
• /
• 2016

차량의 윤폭과 윤거 정보를 산출하는 답판 센서는 국내 유로 도로의 차종 분류 장치에서 일반적으로 사용 된다. 답판 센서는 차량 정보를 생성하기 위하여, 주행 중인 차랑의 바퀴와 접촉이 필요하며 따라서 이때 발생하는 충격을 견디기 위해 높은 내구성이 요구된다. 최근 한국도로공사가 요금소에서 화물차 고속 차로의 운영을 시작함에 따라, 화물차가 고속 주행할 때 발생하는 설계 기준 이상의 충격으로 인한 답판의 파손과 이에 따른 유지보수 및 관리 비용의 증가가 염려되고 있다. 본 논문에서는 물리적 충격에 대한 내구성을 향상 시킨 무접점 답판 센서를 사용해서, 통과 차량의 차종을 분류하는 알고리즘을 제안하였다. 이는 한국도로공사 6종 분류 방식을 기준으로 하였고, 지방도 1020호선의 창원 요금소를 통과하는 1892대를 대상으로 한 실험에서 99.5%의 분류 정확도를 나타내었고, 무접점 답판을 사용한 차종 분류 장치가 국내 유료 도로에 효과적으로 적용이 가능함을 확인하였다.

• 한국산업보건학회지
• /
• 제17권4호
• /
• pp.322-334
• /
• 2007

This study covers the investigation of the actual condition in the workplace to produce plastics products using synthetic resins and the investigation on the trends amount of the domestic production of thermoplastic resins. To analyze the monomers included in thermoplastic resins frequently used in the workplace, we analyzed thermal characteristics for test compounds using thermogravimetric analysis and did the qualitative analysis using Pyrolyzer GC-MSD & TDS GC-MSD. And then we classified the health hazard of monomers based on GHS classification criteria using information toxicity & carcinogenicity. The number of the workplace to produce plastics products among all domestic manufacturers of 73,884 was 4,391 (5.94%). The number of workers to produce plastics products among all workers of 2,522,750 in all domestic manufacturers was 104,971 (4.16%). The amount of production per year for thermoplastic resins is in the order of PP, HDPE, LDPE, PVC, ABS, PS and such compounds was producing over 1 Million ton per year each. The classification result based on GHS classification criteria for 22 main compounds included thermoplastic resins says 2 compounds of acrylonitrile, naphthalene are in Acute oral category 3 and benzene is in Acute dermal category 1. The classification results of health hazard of carcinogenicity based on IARC & ACGIH carcinogen classification says 2 compounds of benzene, vinyl chloride are in category 1A (known to be human carcinogens).

• Journal of Oral Medicine and Pain
• /
• 제41권3호
• /
• pp.91-98
• /
• 2016

Purpose: Oral lichen planus (OLP) has generated many discussions and been associated with much controversy for a long time. A reliable diagnosis of OLP has proven challenging and significant disagreements concerning its diagnosis has continued. Therefore, the aim of this study was to apprehend newly proposed diagnostic criteria of OLP and oral lichenoid lesion (OLL) and to evaluate difference of final diagnosis of OLP and OLL in accordance with type of diagnostic criteria. Also, direct immunofluorescence (DIF) was compared to evaluate the value of DIF between two groups. Methods: Fifty-two patients with DIF result were retrospectively reviewed. The selected patients were classified by the modified World Health Organization (WHO) diagnostic criteria of OLP and OLL and by criteria proposed by American Academy of Oral and Maxillofacial Pathology (AAOMP). Results of DIF in OLP and OLL were classified by deposition intensity or pattern of fibrinogen. The classification of fluorescence pattern in each specimen was graded as positive, possibly positive or negative. Results: Patients diagnosed as OLP were a few more when the modified WHO diagnostic criteria were used than when criteria proposed by AAOMP were used. There was no statistical difference of DIF between OLP and OLL by applying the WHO modification criteria or criteria proposed by AAOMP. Conclusions: The final diagnosis of OLP could be changed in accordance with type of diagnostic criteria and difference of DIF between OLP and OLL was not found.