• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1653-1671
• /
• 2022

Crop diseases affect crop production, more than 30 billion USD globally. We proposed a classification study of crop species and diseases using deep learning algorithms for corn, cucumber, pepper, and strawberry. Our study has three steps of species classification, disease detection, and disease classification, which is noteworthy for using captured images without additional processes. We designed deep learning approach of deep learning convolutional neural networks based on Mask R-CNN model to classify crop species. Inception and Resnet models were presented for disease detection and classification sequentially. For classification, we trained Mask R-CNN network and achieved loss value of 0.72 for crop species classification and segmentation. For disease detection, InceptionV3 and ResNet101-V2 models were trained for nodes of crop species on 1,500 images of normal and diseased labels, resulting in the accuracies of 0.984, 0.969, 0.956, and 0.962 for corn, cucumber, pepper, and strawberry by InceptionV3 model with higher accuracy and AUC. For disease classification, InceptionV3 and ResNet 101-V2 models were trained for nodes of crop species on 1,500 images of diseased label, resulting in the accuracies of 0.995 and 0.992 for corn and cucumber by ResNet101 with higher accuracy and AUC whereas 0.940 and 0.988 for pepper and strawberry by Inception.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.11 no.1
• /
• pp.55-63
• /
• 2001

There are many information objects and users in a large company. It is important issue how to control users access in order that only authorized user can access information objects, Traditional access control models do not properly reflect the characteristics of enterprise environment. This paper proposes an improved access control model for enterprise environment. The characteristics of access control in an enterprise are examined and a task role-based access control(T-RBAC) model founded on concept of classification of tasks is introduced. T-RBAC deals with each task differently according to its class, and supports task level access control and supervision role hierarchy.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.193-200
• /
• 2022

Unknown cryptographic communication protocols may have advantage of guaranteeing personal and data privacy, but when used for malicious purposes, it is almost impossible to identify and respond to using existing network security equipment. In particular, there is a limit to manually analyzing a huge amount of traffic in real time. Therefore, in this paper, we attempt to identify packets of unknown cryptographic communication protocols and separate fields comprising a packet by using machine learning techniques. Using sequential patterns analysis, hierarchical clustering, and Pearson's correlation coefficient, we found that the structure of packets can be automatically analyzed even for an unknown cryptographic communication protocol.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1374-1381
• /
• 2022

Existing research on security technology related to network attack response has focused on research using hardware network security technology, network attacks that wiretap and wiretap network packets, denial of service attack that consumes server resources to bring down the system, and network by identifying vulnerabilities before attack. It is classified as a scanning attack. In addition, methods for increasing network security, antivirus vaccines and antivirus systems have been mainly proposed and designed. In particular, many users do not fully utilize the security function of the router. In order to overcome this problem, it is classified according to the network security level to block external attacks through layered security management through layer-by-layer experiments. The scope of the study was presented by examining the security technology trends of edge routers, and suggested methods and implementation examples to protect from threats related to edge router-based network attacks.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.1
• /
• pp.15-23
• /
• 2010

This paper presents a method of constructing a large interlinked ontology network for the Web of Data through the mapping among typical ontologies. When an ontology is open to the public, and more easily shared and used by people, its value is increased more and more. By linking CoreOnto, an IT core ontology constructed in Korea, to the worldwide ontology network, CoreOnto can be open to abroad and enhanced its usability. YAGO is an ontology constructed by combining category information of Wikipedia and taxonomy of WordNet, and used as the backbone of DBpedia, an ontology constructed by analyzing Wikipedia structure. So a mapping method is suggested by linking CoreOnto to YAGO and DBpedia through the synset of WordNet.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.949-951
• /
• 2022

최근 키오스크의 사용률이 증가함에 따라 키오스크 사용의 어려움을 겪는 정보 취약계층이 존재한다. 키오스크 사용시 메뉴 선택을 키오스크 앞에서 하며, 절차 또한 복잡하다. 또한 키오스크의 높이가 고정되어 있어 휠체어를 타신분, 어린이 등 고정된 높이에 맞지 않는 사람은 사용이 어렵다. 이를 해결하기 위해 맞춤형 추천과 자동 높낮이 조절 키오스트에 대한 연구가 활발하다. 본 논문에서는 사용자 맞춤형 키오스크를 위한 얼굴 분석 기법의 성능 연구 결과를 제시하고 있다. 가장 대표적인 얼굴 분석 알고리즘들로 알려진 MS Azure 얼굴 분석 기법과 네이버 클로바 얼굴 인식 기법에 대한 비교 실험 결과 성별 인식의 경우 MS Azure 기법이 조금 우수했고 나이 분류의 경우에는 비슷한 성능을 보이는 것을 확인할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.889-892
• /
• 2008

최근 이동 중에도 인터넷을 사용하고자하는 사용자의 요구에 맞추어 노드의 이동성을 제공하기 위한 기술들이 개발되고 있다. 그 중 대표적인 기술이 네트워크 계층에서의 이동성 관리 기법인 Mobile IP 기술이다. Mobile IP 기술은 크게 두 가지 분류로 나눌 수 있다. 하나는 호스트가 직접 핸드오프에 대한 시그널링을 수행하는 호스트 기반 이동성 관리 기술이고, 다른 하나는 네트워크 엔터티가 호스트를 대신하여 호스트의 이동에 따른 시그널링을 수행하는 네트워크 기반 이동성 관리 기술이다. 전자의 대표적인 프로토콜은 Mobile IPv6, Fast Mobile IPv6, Hierarchical Mobile IPv6가 있고, 후자의 대표적인 프로토콜은 Proxy Mobile IPv6 기법이 있다. 그 중, 최근 가장 주목 받고 있는 기술은 Proxy Mobile IPv6이다. 네트워크 기반 이동성 관리라는 개념이 서비스 제공자와 기기 제조사에게 모두 이득을 주는 방식이기 때문이다. 하지만 Proxy Mobile IPv6는 아직 개발 중인 기법이라 최적화에 대한 논의가 끝나지 않았다. 특히 Proxy Mobile IPv6 도메인 내에서의 라우팅 최적화에 대한 논의는 활발하게 이루어지고 있다. 본 논문에서는 Proxy Mobile IPv6의 네트워크 엔터티인 Mobile Access Gateway의 라우팅 테이블을 이용한 라우팅 최적화 기법을 제안한다. 또한 제안한 기법이 가져오는 성능향상과 효과에 대해 분석한다.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.20 no.3
• /
• pp.113-120
• /
• 2014

Packaging has played important function on marketing as a silent salesman. As an interface of consumer and products, packaging fulfills several functions such as protection, sales promotion, communication and convenience during the distribution process. For the appearance of self-service sales method, packaging could be regarded as important salesman influencing consumers' preference on shelf in the shop. In this study, Vitamin water was selected as the proper target product for lower impact of prices and brands. With previous studies, Vitamin water packaging elements were classified as 'packaging material', 'packaging shape', 'label color', 'logo layout', then each packaging element was consist of details. To measure the influence of each packaging element on consumers' preference quantitatively and to minimize respondent's subjective judgment, Analytic Hierarchy Process (AHP) was used as a tool. Through AHP result, packaging element of the most influence on consumers' preference is 'label color (0.370)', and 'container shape (0.246)', 'container material (0.230)', 'logo layout (0.154)' was in order. Among the detail packaging element, 'plastic (0.405)' has the greatest influence in 'container material' and 'cylinder (0.423)' in 'container shape', 'magenta (0.329)' in 'label color', 'vertical layout (0.572)' in 'logo layout'.

• Korean Journal of Social Welfare Studies
• /
• v.48 no.3
• /
• pp.171-208
• /
• 2017

The purpose of this study is to classify the underlying and parsimonious types of child maltreatment and examine whether the effects of risk factors on child maltreatment recurrence differ by type of maltreatment. We utilized the multiyear national administrative data from the National Child Maltreatment Information System collected by Child Protection Agency in Korea. Of 26,921 child maltreatment victims reported and substantiated on or after January 1, 2012, 1,447 children who had recurrence of child maltreatment until December 31, 2015 were selected as maltreatment recurrence group and 4,580 children who had not experienced maltreatment since first substantiation were assigned as maltreatment non-recurrence group. Latent class analysis(LCA) and latent transition analysis(LTA) were used to group children with similar maltreatment subtypes into discrete classes of child maltreatment recurrence. Logistic regression is employed to examine the association between the child maltreatment predominant types and risk factors for recurrence. Results of LCA and LTA showed four latent classes representing predominant type of child maltreatment: 'physical abuse predominant type', 'emotional abuse predominant type', 'sexual abuse predominant type', and 'neglect type'. Significant differences in the effect of risk factors among latent classes were found in child's age and gender, perpetrator's gender, family poverty, biological parent as the perpetrator, domestic violence toward partner, perpetrator's alcoholic problem, insufficient parenting skills, and out-of-home care service, Based on these findings, results suggested how the typology can be used to guide decision about who to target in prevention and intervention programs, and which features of risk factors to target. Practice and policy implications as well as further research tasks were discussed in the lights of searching for useful and important strategies to prevent recurrence of child maltreatment.