• Journal of Periodontal and Implant Science
• /
• v.53 no.1
• /
• pp.38-53
• /
• 2023

Purpose: The current Classification of Periodontal and Peri-Implant Diseases and Conditions, published and disseminated in 2018, involves some difficulties and causes diagnostic conflicts due to its criteria, especially for inexperienced clinicians. The aim of this study was to design a decision system based on machine learning algorithms by using clinical measurements and radiographic images in order to determine and facilitate the staging and grading of periodontitis. Methods: In the first part of this study, machine learning models were created using the Python programming language based on clinical data from 144 individuals who presented to the Department of Periodontology, Faculty of Dentistry, Süleyman Demirel University. In the second part, panoramic radiographic images were processed and classification was carried out with deep learning algorithms. Results: Using clinical data, the accuracy of staging with the tree algorithm reached 97.2%, while the random forest and k-nearest neighbor algorithms reached 98.6% accuracy. The best staging accuracy for processing panoramic radiographic images was provided by a hybrid network model algorithm combining the proposed ResNet50 architecture and the support vector machine algorithm. For this, the images were preprocessed, and high success was obtained, with a classification accuracy of 88.2% for staging. However, in general, it was observed that the radiographic images provided a low level of success, in terms of accuracy, for modeling the grading of periodontitis. Conclusions: The machine learning-based decision system presented herein can facilitate periodontal diagnoses despite its current limitations. Further studies are planned to optimize the algorithm and improve the results.

• Journal of the Korean Society of Safety
• /
• v.30 no.5
• /
• pp.108-113
• /
• 2015

Plastic injection moulding machine is widely used for many industrial field. It is classified into mandatory safety certification machinery in Industrial Safety and Health Act because of its high hazard. In order to prevent industrial accidents by plastic injection moulding machine, it is necessary for designer to identify hazardous factors and assess the failure modes to mitigate them. This study tabulates the failure modes of main parts of plastic injection moulding machine and how their failure has affect on the machine being considered. Failure Mode & Effect Analysis(FMEA) method has been used to assess the hazard on plastic injection moulding machine. Risk and risk priority number(RPN) has been calculated in order to estimate the hazard of failures using severity, probability and detection. Accidents caused by plastic injection moulding machine is compared with the RPN which was estimated by main regions such as injection unit, clamping unit, hydraulic and system units to find out the most dangerous region. As the results, the order of RPN is injection unit, clamping unit, hydraulic unit and system units. Barrel is the most dangerous part in the plastic injection moulding machine.

• Korean Journal of Agricultural Science
• /
• v.40 no.2
• /
• pp.163-167
• /
• 2013

Objective of the study was to compare reflectance spectrum in the blade and the vein parts of cabbage and kale leaves. A total 6 cabbage and kale leaves were taken from a plant factory in Chungnam National University, Korea. Spectra data were collected with a UV/VIS/NIR spectrometer (model: USB2000, Ocean Optics, FL, USA) in the wavelength region of 190 - 1130 nm. Median filter smoothing method was selected to preprocess the obtained spectra data. We computed reflectance difference by subtraction of averaged spectrum from individual spectrum. To estimate correlation at different parts of cabbage and kale leaves, cross - correlation method was used. Differences between cabbage and kale leaves are clearly manifested in the green, red and near - infrared ranges. The percent reflectance of cabbage leaves in the NIR wavelength band was higher than that of kale leaves. Reflectance in the blade part was higher than in the vein part by 18%. Reflectance difference in the different parts of cabbage and kale leaves were clear in all of the wavelength bands. Standard deviation of reflectance difference in the vein part was greater for kale, while the value in the blade part was greater for cabbage leaves. Standard deviation of cross - correlation increased from 0.092 in the first sensor (UV/VIS) and 0.007 in the second sensor (NIR) to 0.099 and 0.015, respectively.

• Journal of Korean Ophthalmic Optics Society
• /
• v.16 no.2
• /
• pp.107-115
• /
• 2011

Purpose: To design and fabricate the distributed auto edging machine for the development. Methods: We got the necessary data needed in design by using CAD. Based on the these data, we fabricated the trial product for the development of the distributed auto edging machine. Results: The patternless mode could be operated by receiving the eyesize data from the auto lay-outer with the RS232C transmission system and the pattern mode could be operated by setting the pattern on the left side of the machine. The distributed auto edging machine were composed with combinations of many elements; head, auto arm, pattern clamp and grinding wheels. The head part controlled the grinding of ophthalmic lens by operating the vertical and horizontal motors. The wheels part was comprised of glass mode, plastic mode, V-bevel mode and polish mode. The slide in the auto arm was equipped on the below of the patten and the slide could hold up the pattern which was rotated by fixed shaft. The pattern clamp could move the head part to the up and down or right or left way by the manual operation of optometrists. Conclusions: We could succeed in making the trial product by applying it to the development of the distributed auto edging machine which could be used as the patternless mode and pattern mode, selectively. Therefore, it was confidently expected that this product was very helpful for the optometrists to dispense the ophthalmic lens because of its cost-efficiency and convenience.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.82-87
• /
• 2004

Experimental modal analysis is an effective tool to investigate the dynamic behavior of machining centers. This paper presents the measurement system and experimental investigation on the modal analysis of machining centers. The modal analysis shows the weak part of the machining center. An important local model of spindle in our experiment, which influences the dynamics of machining process, is proposed in this paper. The results provide the foundation of structure modification for good dynamic behaviors.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.5
• /
• pp.538-544
• /
• 2012

In this paper, design optimization of C-frame of a precision drilling and autorivet machine has been performed. The machine, Autoriveter has been developed by Korea Aerospace Industry (KAI), For current autoriveter, it is hard to achieve high efficiency because of heavy weight of the machine. In this paper, we suggest new structure of the current C-frame, a part of autoriveter, by optimization. The result of the study can give much profit for mass-production of the machine.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.12 no.3
• /
• pp.184-191
• /
• 2004

In this study, an inspection system for automotive parts using machine vision has been developed and presented. The system is comprised of six analog CCD cameras, frame grabber, and mechanism that loads the automotive parts to the system for the inspection. An Image processing algorithm for detecting eight different types of defects of oil-seals are developed, and the effectiveness of the algorithm is experimentally verified. Inspection process is completed in 1 second with acceptable accuracy. It is envisaged that this inspection system will have a wide application in the automotive part manufacturing industry in the future.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.05a
• /
• pp.145-153
• /
• 1999

We consider a Direct Input Output Manufacturing System(DIOMS) which has a munber of machine centers placed along a built-in Automated Storage/Retrieval System(AS/RS). The Storage/Retrieval (S/R) machine handles parts placed on pallets for the machine centers located at either one or both sides of the As/Rs. This report studies the operational aspect of DIOMS and determines the optimal operating policy by combining computer simulation and genetic algorithm. The operational problem includes: input sequencing control, dispatching rule of the S/R machine, machine center-based part type selection rule, and storage assignment policy. For each operating policy, several different policies are considered based on the known research results. In this report, using the computer simulation and genetic algorithm we suggest a method which gives the optimal configuration of operating policies within reasonable computation time.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.10a
• /
• pp.369-374
• /
• 2004

Web-based analysis programs for reliability assessment of machine tools were developed in this study. First, the reliability data analysis program was developed to search for failure rate using failure data and reliability test data of mechanical part. Second, failure mode analysis was developed through performance tests like circular movement test vibration test for machine tools. This analysis program shows correlation between failure mode and performance test result. Third, tool life was predicted by correlation between flank wear and cutting time, using the extended Taylor tool life equation in turning data and the equivalently converted equation in order to apply ball endmill data to Taylor tool life equation in milling data. All the information related to input and result data can be stored in theses programs.

• 한국기계연구소 소보
• /
• s.18
• /
• pp.29-35
• /
• 1988

When low sliding velocities in the boundary lubrication range are operating, irregular movements frequently occur which are a result of the stick-slip phenomenon. Such slide motions are undesirable in precision machine tools, particularly with feed back systems used in numerical and adaptive control machine tools. Accordingly, this paper reports analytical and experimental studies in the stick-slip characteristic of machine tool feeding system. The main conclusions of this study are as follows; The tendency towards stick-slip effects may be reduced by; 1). Reducing the drop in friction coefficient in the Stribeck curve(on the rising part of the friction characteristic at higher sliding speeds, the system is stable all the time) 2). Reducing the transition velocity by the use of a higher viscosity lubricating oil. 3). Increasing the stiffness(Damping)and reducing normal load(Sliding mass) Therefore, the Critical velocity is decided from the above conclusions and in designing of machine tool, feed rates(sliding velocity)must be design the more than critical velocity.