전이학습 기반 사출 성형품 burr 이미지 검출 시스템 개발

양동철,김종선,Yang, Dong-Cheol,Kim, Jong-Sun 한국금형공학회 2021 한국금형공학회지 Vol.15 No.3

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

Artificial Neural Network를 이용한 사출압력과 사출성형품의 무게 예측에 대한 연구

양동철,김종선 한국금형공학회 2019 한국금형공학회지 Vol.13 No.3

This paper presents Artificial Neural Network(ANN) method to predict maximum injection pressure of injection molding machine and weights of injection molding products. 5 hidden layers with 10 neurons is used in the ANN. The ANN was conducted with 5 Input parameters and 2 response data. The input parameters, i.e., melt temperature, mold temperature, fill time, packing pressure, and packing time were selected. The combination of the orthogonal array L27 data set and 23 randomly generated data set were applied in order to train and test for ANN. According to the experimental result, error of the ANN for weights was %. In case of maximum injection pressure, error of the ANN was %. This value showed that ANN can be successfully predict the injection pressure and the weights of injection molding products.

인공신경망 구조에 따른 사출 성형폼 품질의 예측성능 차이에 대한 비교 연구

양동철,이준한,김종선,Yang, Dong-Cheol,Lee, Jun-Han,Kim, Jong-Sun 한국금형공학회 2021 한국금형공학회지 Vol.15 No.1

The quality of products produced by injection molding process is greatly influenced by the process variables set on the injection molding machine during manufacturing. It is very difficult to predict the quality of injection molded product considering the stochastic nature of manufacturing process, because the process variables complexly affect the quality of the injection molded product. In the present study we predicted the quality of injection molded product using Artificial Neural Network (ANN) method specifically from Multiple Input Single Output (MISO) and Multiple Input Multiple Output (MIMO) perspectives. In order to train the ANN model a systematic plan was prepared based on a combination of orthogonal sampling and random sampling methods to represent various and robust patterns with small number of experiments. According to the plan the injection molding experiments were conducted to generate data that was separated into training, validation and test data groups to optimize the parameters of the ANN model and evaluate predicting performance of 4 structures (MISO1-2, MIMO1-2). Based on the predicting performance test, it was confirmed that as the number of output variables were decreased, the predicting performance was improved. The results indicated that it is effective to use single output model when we need to predict the quality of injection molded product with high accuracy.

인공신경망을 활용한 사출성형품의 질량과 치수 예측에 관한 연구

양동철,이준한,김종선,Yang, Dong-Cheol,Lee, Jun-Han,Kim, Jong-Sun 한국금형공학회 2020 한국금형공학회지 Vol.14 No.3

This paper predicts the mass and the length of injection-molded products through the Artificial Neural Network (ANN) method. The ANN was implemented with 5 input parameters and 2 output parameters(mass, length). The input parameters, such as injection time, melt temperature, mold temperature, packing pressure and packing time were selected. 44 experiments that are based on the mixed sampling method were performed to generate training data for the ANN model. The generated training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. A random search method was used to find the optimized hyper-parameter of the ANN model. After the ANN completed the training, the ANN model predicted the mass and the length of the injection-molded product. According to the result, average error of the ANN for mass was 0.3 %. In the case of length, the average deviation of ANN was 0.043 mm.

마약류 자기사용죄에 있어서의 공소사실의 특정 -모발감정의 증거능력ㆍ증명력과 관련하여-

양동철 경희대학교 법학연구소 2009 경희법학 Vol.44 No.1

Article 254 (4) of the Criminal Procedure Act provides that “The Facts constituting the crime shall be stated clearly by specifying the time & date, place, and method of crime”. In case the facts constituting the crime(count) is not be stated clearly, the public prosecution shall be dismissed by judgement. The legislative purport of ‘count specification’ is not only set limits to object of trials, but also protect the procedural rights of defendants. For that reason the time & date, place, and method of crime in the prosecution shall be stated clearly for defendants so as to exert their procedural rights without difficulty. In the ‘illegal drug use case’, however, not a few suspects deny their crimes. In such circumstances, prosecutors have no choice but to presume the date of crime just basing urine analysis or hair analysis. So, the facts constituting the crime have to be stated generally. The Supreme Court tended to take a generous stand on the issue of ‘count specification’ in illegal drug use cases before the 2000s. However, in 1999, the Supreme Court dismissed ‘illegal drug use case’ just based on hair analysis. [Supreme Court Decision 1998Do3293 Delivered on June 11, 1999 [Violation of the Act on the Control of Narcotics, etc. (Psychotropic)]. After that, the Supreme Court tends to judge illegal drug use cases on a case by case basis. Therefore, it is necessary to analyze the standpoint of the Supreme Court and suggest a manifest criterion on that issue. Issues of this paper are admissibility & reliability of hair analysis as an evidence, count specification & object of trials in the ‘illegal drug use case’ and related problems. This paper reviews leading precedents on the issues and suggests possible solutions to the problems. Article 254 (4) of the Criminal Procedure Act provides that “The Facts constituting the crime shall be stated clearly by specifying the time & date, place, and method of crime”. In case the facts constituting the crime(count) is not be stated clearly, the public prosecution shall be dismissed by judgement. The legislative purport of ‘count specification’ is not only set limits to object of trials, but also protect the procedural rights of defendants. For that reason the time & date, place, and method of crime in the prosecution shall be stated clearly for defendants so as to exert their procedural rights without difficulty. In the ‘illegal drug use case’, however, not a few suspects deny their crimes. In such circumstances, prosecutors have no choice but to presume the date of crime just basing urine analysis or hair analysis. So, the facts constituting the crime have to be stated generally. The Supreme Court tended to take a generous stand on the issue of ‘count specification’ in illegal drug use cases before the 2000s. However, in 1999, the Supreme Court dismissed ‘illegal drug use case’ just based on hair analysis. [Supreme Court Decision 1998Do3293 Delivered on June 11, 1999 [Violation of the Act on the Control of Narcotics, etc. (Psychotropic)]. After that, the Supreme Court tends to judge illegal drug use cases on a case by case basis. Therefore, it is necessary to analyze the standpoint of the Supreme Court and suggest a manifest criterion on that issue. Issues of this paper are admissibility & reliability of hair analysis as an evidence, count specification & object of trials in the ‘illegal drug use case’ and related problems. This paper reviews leading precedents on the issues and suggests possible solutions to the problems.

JIT-MTA 방식을 이용한 웹 메일링 시스템의 개발

양동철,김대범,김채수 대한산업공학회 2000 대한산업공학회 추계학술대회논문집 Vol.2000 No.11

JIT-MTA 방식을 이용한 웹 메일링 시스템의 개발

양동철,김대범,김채수 대한산업공학회 2000 대한산업공학회 추계학술대회논문집 Vol.2000 No.-

해외불법정보에 대한 규제의 현황과 개선방향

양동철 대한변호사협회 2007 人權과 正義 : 大韓辯護士協會誌 Vol.- No.365

인터넷에서 유통되는 불법정보를 효율적으로 규제하기 위하여 정부를 비롯한 사회 각계에서는 인터넷 실명제 등을 비롯한 새로운 대책을 강구하고 있다. 그러나 사이버 폭력을 비롯한 각종 불법정보의 확산은 기존 법체계나 몇 가지 새로운 정보통신 법률만으로 대처하기 어려운 실정이다. 더욱이 어떤 불법정보 유통방지대책도 해외로부터 국내로 전송되는 불법정보를 차단하지 못한다면 그 효과가 반감될 수밖에 없다. 이 논문은 현행 법제 아래서의 해외 서버 인터넷사이트의 불법정보에 대한 규제현황과 절차를 살펴보고, 아울러 관련 입법의 방향을 제시하는 데 그 목적을 둔다. 해외불법정보의 국내유통의 현황 및 실제사례를 살펴보고, 나아가 이에 대한 효율적 대처방안을 검토하되, 주로 법률적 관점에서 접근하여 우선 인터넷 불법정보에 대한 현행법의 규제규정을 중심으로 이 규정들의 해외불법정보에 대한 적용상의 문제점을 살펴본다. 그리고 더욱 효율적인 입법 방향을 제시한다. 결론을 요약하면, 해외불법정보에 대해 국내법을 적용함에 있어 입법적 미비가 없도록 형법 총칙이나 개별 법규를 개정하되, 세계화라는 관점에서 외국의 입법도 충분히 고려하여 공조의 방법을 모색 하여야 한다. 다음, ISP 사업자에 대하여 해외불법정보의 차단을 명할 수 있는 정보통신부장관의 시정명령권을 규정한 전기통신사업법의 미비점을 보완하고 그 기준과 절차도 정비하여야 할 것이다. 아울러 ISP 사업자의 자율규제와 책임범위도 확장하여야 하며 국가 간 불법의 기준과 규제절차의 접근, 기술협력 등 긴밀한 국제공조가 절실하다.

통고처분에 따른 범칙금납부의 효력과 일사부재리에 관한 연구

양동철 경희대학교 법학연구소 2012 경희법학 Vol.47 No.1

Penalty notification disposition system according to Road Traffic Act or Punishment of Minor Offense Act has so many problems in spite of its merits. Article 164 (3) of Road Traffic Act provides that “Anyone who pays a penalty pursuant to the provision of paragraph (1) or (2) shall not be punished any further again for the selfsame offense”. Also, Article 7 (3) of Punishment of Minor Offense Act provides that “Anyone who pays a penalty pursuant to the provision of paragraph (1) or (2) shall not be punished again for the offense”. With reference to those issues, many sincere arguments are raised. And Supreme Court has released meaningful precedents, like [Supreme Court Decision 2001Do849], [Supreme Court Decision 2002Do2642] and so on. Especially, those precedents released contradictory conclusions in concerned with the effect of double jeopardy Therefore, it is necessary to analyze the standpoint of the Supreme Court and suggest a manifest criterion on that issue. So, This Article starts with analysis of [Supreme Court Decision 2001Do849] and [Supreme Court Decision 2002Do2642] and treats the relevant cases. Secondly, it studies related issues, especially, the effect of double jeopardy. Finally, it suggests criteria on that issue and possible solutions to the problems. 도로교통법 등의 경미한 법규위반에 대하여 범칙금을 납부한 사람은 그 범칙행위에 대하여 다시 벌 받지 아니하고, 범칙금의 납부에 대하여는 확정재판의 효력에 준하는 효력, 즉 일사부재리의 효력이 인정된다. 그러나 우리나라의 통고처분제도는 통일적인 개념과 기준 아래 정비되지 못하고, 개별법규마다 그 법의 목적이나 행정 편의에 따라 입법되고 있을 뿐 아니라, 형사범죄행위까지 통고처분에 의하여 처리되도록 함으로써 경미한 법규위반을 비범죄화하려는 본래의 취지를 몰각하고 죄형법정주의나 헌법의 기본권 보호 이념에 역행하는 부작용이 초래될 위험성이 높다. 이런 문제점들은 통고처분제도의 통일적 정비 등 입법에 의하여 해결되는 것이 바람직하겠지만 우선 해석론을 통하여나마 시급한 문제점을 해결하여 나감으로써 제도적 개선에 진일보할 수 있으리라 생각된다. 이 논문에서는 통고처분제도의 일반적 문제점이나 개선방안을 논하기 보다는 우선 경범죄처벌법 및 도로교통법에 따른 범칙금납부 제도 나아가 즉결심판 제도의 문제점과 이에 대한 일사부재리의 효력에 관한 통일적인 해석 방안을 검토하는 것을 목적으로 한다. 요약하자면 경범죄처벌법이나 도로교통법에 따른 범칙금 납부가 이루어졌다고 하더라도 범칙금의 납부에 확정판결에 준하는 효력이 인정됨에 따라 다시 벌 받지 아니하게 되는 행위사실은 범칙금 통고의 이유에 기재된 당해 범칙행위 자체 및 그 범칙행위와 동일성이 인정되는 범칙행위에 한정된다고 해석함이 상당하다. 그렇지 않다 하더라도 범칙행위와 형사절차에서의 범죄사실의 동일성 여부를 판단함에 있어서는 규범적 요소를 적극 고려하여 범칙행위에 대한 일사부재리의 효력이 형사범죄에까지 미치지 않도록 제한 해석하여야 한다. 나아가 범칙금 통고처분에서 이행된 즉결심판과 관련하여서도 수정된 기본적 사실동일설의 입장에서 규범적 요소의 범위를 대폭 확장하여 음주소란 등과 같은 경범죄처벌법 소정의 즉결심판 대상 행위와 상해 등 형사범죄와의 사이에 공소사실의 동일성을 부정하는 것이 옳다고 생각된다.

일부상소와 상소심의 심판범위 - 판례에 대한 분석과 비판적 고찰을 중심으로 -

양동철 경희대학교 법학연구소 2010 경희법학 Vol.45 No.3

Article 342 (1) of the Criminal Procedure Act provides that “An Appeal may be filed against part of decision.”Part of decision does not mean part of its subjective scope but its objective one. And appeal against part of decision is not against part of a count but against part of decision of the criminal procedure in which court examine consolidated case like concurrent crimes In case appeal against part of decision is filed, the part shall be transferred to court of appeals and shall be its object of trial. On the other hand, the other part is not transferred but settled in principle. However, there are some exceptions. Article 342 (2) of the Criminal Procedure Act provides that “An Appeal which is taken against one part shall be deemed to have effect over the other part which is indispeably connected that part.”With reference to those issues, many sincere arguments are raised. And Supreme Court has released many meaningful precedents, like [Supreme Court Decision 1991Do1402], [Supreme Court Decision 1990Do2820] and so on. Therefore, it is necessary to analyze the standpoint of the Supreme Court and suggest a manifest criterion on that issue. This Article starts with a review of general theory about “Appeal against Part of Decision” and major issues Secondly, it analyzes leading judicial precedents and theories of domestic and abroad. Finally, it suggests criteria on that issue and possible solutions to the problems.