• Smart Media Journal
• /
• v.11 no.4
• /
• pp.38-45
• /
• 2022

Object detection models have become the current tool of choice for plant disease detection in precision agriculture. Most existing research improves the performance by ameliorating networks and optimizing the loss function. However, the data-centric part of a whole project also needs more investigation. In this paper, we proposed a systematic strategy with three different annotation methods for plant disease detection: local, semi-global, and global label. Experimental results on our paprika disease dataset show that a single class annotation with semi-global boxes may improve accuracy. In addition, we also studied the noise factor during the labeling process. An ablation study shows that annotation noise within 10% is acceptable for keeping good performance. Overall, this data-centric numerical analysis helps us to understand the significance of annotation methods, which provides practitioners a way to obtain higher performance and reduce annotation costs on plant disease detection tasks. Our work encourages researchers to pay more attention to label quality and the essential issues of labeling methods.

• Journal of Communications and Networks
• /
• v.11 no.3
• /
• pp.297-305
• /
• 2009

Multiprotocol label switching (MPLS) networks require dynamic flow admission control to guarantee end-to-end quality of service (QoS) for each Internet protocol (IP) traffic flow. In this paper, we propose to tackle the joint routing and admission control problem for the IP traffic flows in MPLS networks without rerouting already admitted flows. We propose two mathematical programming models for this problem. The first model includes end-to-end delay constraints and the second one, end-to-end packet loss constraints. These end-to-end QoS constraints are imposed not only for the new traffic flow, but also for all already admitted flows in the network. The objective function of both models is to minimize the end-to-end delay for the new flow. Numerical results show that considering end-to-end delay (or packet loss) constraints for all flows has a small impact on the flow blocking rate. Moreover, we reduces significantly the mean end-to-end delay (or the mean packet loss rate) and the proposed approach is able to make its decision within 250 msec.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.225-230
• /
• 2020

Machine learning is an algorithm which learns a computer based on the data so that the computer can identify the trend of the data and predict the output of new input data. Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a way of learning a machine with given label of data. In other words, a method of inferring a function of the system through a pair of data and a label is used to predict a result using a function inferred about new input data. If the predicted value is continuous, regression analysis is used. If the predicted value is discrete, it is used as a classification. A result of analysis, no. 8 (5, 3.4, setosa), 27 (5, 3.4, setosa), 41 (5, 3.5, setosa), 44 (5, 3.5, setosa) and 40 (5.1, 3.4, setosa) in Table 3 were classified as the most similar Iris flower. Therefore, theoretical practical are suggested.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7C
• /
• pp.677-684
• /
• 2002

Today's Internet does not have efficient traffic engineering mechanism to support QoS for the explosive increasing internet traffic such as various multimedia traffic. This functional shortage degrades prominently the quality of service, and makes it difficult to provide multi-media service and real-time service. Various technologies are under developed to solve these problems. IETF (Internet Engineering Task Force) developed the MPLS (Multi-Protocol Label Switching) technology that provides a good capabilities of traffic engineering and is independent layer 2 protocol, so MPLS is expected to be used in the Internet backbone network$\^$[1][2]/. The faults occurring in high-speed network such as MPLS, may cause massive data loss and degrade quality of service. So fast network restoration function is essential requirement. Because MPLS is independent to layer 2 protocol, the fault detection and reporting mechanism for restoration should also be independent to layer 2 protocol. In this paper, we present the experimental results of the MPLS OAM function for the performance monitoring and fault detection 'll'&'ll' notification, localization in MPLS network, based on the OPNET network simulator

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.489-489
• /
• 2000

Recently, Reinforcement Learning(RL) methods have been used far teaming problems in Partially Observable Markov Decision Process(POMDP) environments. Conventional RL-methods, however, have limited applicability to POMDP To overcome the partial observability, several algorithms were proposed [5], [7]. The aim of this paper is to extend our previous algorithm for POMDP, called Labeling Q-learning(LQ-learning), which reinforces incomplete information of perception with labeling. Namely, in the LQ-learning, the agent percepts the current states by pair of observation and its label, and the agent can distinguish states, which look as same, more exactly. Labeling is carried out by a hash-like function, which we call Labeling Function(LF). Numerous labeling functions can be considered, but in this paper, we will introduce several labeling functions based on only 2 or 3 immediate past sequential observations. We introduce the basic idea of LQ-learning briefly, apply it to maze problems, simple POMDP environments, and show its availability with empirical results, look better than conventional RL algorithms.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.2
• /
• pp.165-171
• /
• 2022

Objective: Nonspecific low back pain (NSLBP) is experienced worldwide by many age groups. Yoga is recommended as an exercise to reduce back pain and stress because it is a breathing exercise, posture, and meditation as key elements. The aim of this study is to compare the effects of yoga and stabilization exercise on pain intensity, function, and depression. Design: An open-label, parallel arm, randomized controlled trial Methods: Twenty-four participants were allocated to the experimental and the control group in a ratio of 1:1. Yoga (experimental group) and stabilization exercise (control group) were received twice a week for 6 weeks Participants were assessed at baseline and post-intervention for pain intensity (numeric pain rating scale), function (Aberdeen low back pain scale, flexibility,and strength), and depression (Beck depression inventory). Results: When the experimental group (Yoga) and control group (stabilization exercise) were performed twice a week for 6 weeks, numeric pain rating scale, Aberdeen low back pain scale, and flexibility in post-intervention showed significant improvement in both groups (P<0.05), However, in all variables, the experimental group showed a positive benefit compared to the control group (P<0.05). Conclusions: The results of this study show that yoga has more positive benefits compared to stabilization exercise in pain intensity, function, and depression in individuals with NSLBP.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.1059-1063
• /
• 2009

모바일 폰의 메뉴 구조는 하이퍼텍스트 형태로 정보를 제공하며 링크의 연결로 페이지 정보를 전달하거나 하부 카테고리로 연결하는 역할을 한다. 모바일 폰 사용자는 메뉴 조작을 통해 기능을 실행하며, 이 과정에서 선형구조, 계층형 구조, 대화형 구조, 데이터베이스 구조, 혼합구조와 같은 다양한 형태를 경험하게 된다. 사용자는 모바일 폰의 다양한 기능을 사용하면서 추상적 개념의 공간 인지를 구체적인 공간으로 이해하려 한다. 즉 UI, GUI에서 제시하고 있는 Label이나 방향표시를 따라 상하좌우라는 공간적 개념으로 은유하여 이해하는 것이다. 하드키 단말의 경우는 상하좌우키를 이용하여 공간을 이해했다면 최근에는 터치 및 제스처 동작 인식이 가능한 폰이 등장하면서 좌우 flick, 상하 flick 등과 같은 구체적인 행동으로 디바이스 화면에서 공간이 이동하는 것으로 이해하고 있다. 본 논문에서 사용자의 공간 은유를 이해하기 위해 상위 depth로 이동하는 [이전] 키의 기능을 중심으로 살펴보고자 한다. 첫째, 기능을 수행하기 위해 순차적으로 진행하는 방법보다는 [취소]를 이용하여 depth를 이동하는 것이 사용자의 모바일 폰의 공간 은유 파악에 더욱 도움을 줄 수 있을 것이라고 예상되기 때문이다. 둘째, [이전], [취소]라는 Label이 가지고 있는 모호성 때문이다. 모바일 폰의 다양한 기능 중에서 [이전]는 전체 사용에 있어 아주 작은 요소에 불과하지만 사용자는 정해진 순서의 process에 따라 기능을 수행할 때와는 다르게 역 방향 Process를 사용하면서 모바일 폰의 구조를 이해하고 모바일 공간을 인지하는 중요한 요소로 사용될 수 있을 것이라고 예상된다. 본 논문에서는 이전으로 돌아가는 [이전]의 기능을 통해 사용자가 메뉴의 층위 구조 및 공간 인지에 영향을 미칠 수 있을 것이다라는 가설을 설정하여 이를 실험을 통해 증명하고자 한다. 실험을 위해 모바일 폰을 자주 사용하고 있는 20~30대 남녀 10명의 피험자에게 전화번호부, 앨범, 문자메시지의 목록화면과 상세보기 화면을 제시한 후 마지막 상세보기 화면에서 실험에서 제시하는 제시어를 보고 어느 화면으로 이동하게 될 것인지를 예상하는 질문을 하였으며, 그러한 이유에 대해서는 인터뷰를 통해 확인하였다. 이 실험을 통해 사용자의 모바일 폰 공간인지는 동일한 레벨의 단계 즉 상세보기의 경우는 수평의 관계라고 보고 있으며, 목록화면과 상세화면의 관계는 상하의 관계라고 이해하고 있다. 이러한 이유를 인터뷰를 통해 질문하였을 때, 상세화면에서 좌우 방향표시가 존재하기 때문이라는 응답이 높았으며, 상세보기 화면이 좌우라고 인식하면 목록화면은 상하의 관계로 이해하고 있다고 응답하였다. 즉 하나의 정해진 공간인지를 통해 다른 공간을 유추하여 생각하고 있다고 볼 수 있다. 또한 결과적으로 실제 단말에서 [이전] 기능을 상위 depth로 이동하도록 설계하였다면 [한단계위]라는 Label 또는 e번과 같은 상위의 개념을 포함한 아이콘을 사용한다면 혼란을 줄일 수 있는 방법으로 활용될 수 있을 것으로 예상된다. 현재 논문에서는 [이전]라는 기능으로만 사용자의 공간 개념을 예측할 수 있었지만, 터치스크린의 등장과 함께 플릭과 같은 다양한 제스처에 의한 인터렉션이 가능한 현 시점에서 추상적인 공간은 방향성을 가진 제스처에 의해 구체적인 물리적 공간으로 인식하는 경향이 더욱 뚜렷이 나타나고 있다. 이러한 시점에서 사용자의 공간인지에 도움을 줄 수 있는 Label과 방향성 표시는 더욱 절실히 요구되고 있는 시점이며, 이후 모바일 환경에서 사용자의 공간인지에 대한 구체적인 연구가 필요하리라고 예상된다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12C
• /
• pp.225-232
• /
• 2001

In this paper, we describe a mechanism that supports the mobility service for VPN(Virtual Private Network) users on MPLS(Multiprotocol Label Switching) network. The MPLS VPN considered in this study is controlled by CE(Customer Edge) routers. In such a VPN, CE routers have additional functions to support mobile VPN users, i.e., Home Agent function, foreign Agent function, Correspondent Agent function. This mechanism is applied when a VPN node moves to other site of the saute VPN, or when it moves to other site of a different VPN, or to a non-VPN site. We perform a simulation study to compare the performance of CE based MPLS VPN with that of PE(Provider Edge) based MPLS VPN with mobility support.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.77-88
• /
• 2017

Recently, with the advent of knowledge based society where information and knowledge make values, patents which are the representative form of intellectual property have become important, and the number of the patents follows growing trends. Thus, it needs to classify the patents depending on the technological topic of the invention appropriately in order to use a vast amount of the patent information effectively. IPC (International Patent Classification) is widely used for this situation. Researches about IPC automatic classification have been studied using data mining and machine learning algorithms to improve current IPC classification task which categorizes patent documents by hand. However, most of the previous researches have focused on applying various existing machine learning methods to the patent documents rather than considering on the characteristics of the data or the structure of patent documents. In this paper, therefore, we propose to use two structural fields, technical field and background, considered as having impacts on the patent classification, where the two field are selected by applying of the characteristics of patent documents and the role of the structural fields. We also construct multi-label classification model to reflect what a patent document could have multiple IPCs. Furthermore, we propose a method to classify patent documents at the IPC subclass level comprised of 630 categories so that we investigate the possibility of applying the IPC multi-label classification model into the real field. The effect of structural fields of patent documents are examined using 564,793 registered patents in Korea, and 87.2% precision is obtained in the case of using title, abstract, claims, technical field and background. From this sequence, we verify that the technical field and background have an important role in improving the precision of IPC multi-label classification in IPC subclass level.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.5
• /
• pp.1279-1284
• /
• 2014

The binding of TATA-binding protein (TBP) to the TATA-box containing promoter region is aided by many other transcriptional factors including TFIIA and TFIIB. The mechanistic insight into the assembly of RNA polymerase II preinitation complex (PIC) has been gained by either directly altering a function of target protein or perturbing molecular interactions using drugs, RNAi, or aptamers. Aptamers have been found particularly useful for studying a role of a subset of PIC on transcription for their ability to inhibit specific molecular interactions. One major hurdle to the wide use of aptamers as specific inhibitors arises from the difficulty with traditional assays to validate and determine specificity, affinity, and binding epitopes for aptamers against targets. Here, using a technique called the bio-layer interferometry (BLI) designed for a label-free, real-time, and multiplexed detection of molecular interactions, we studied the assembly of a subset of PIC, TBP binding to TATA DNA, and two distinct classes of aptamers against TPB in regard to their ability to inhibit TBP binding to TFIIA or TATA DNA. Using BLI, we measured not only equilibrium binding constants ($K_D$), which were overall in close agreement with those obtained by electrophoretic mobility shift assay, but also kinetic constants of binding ($k_{on}$ and $k_{off}$), differentiating aptamers of comparable KDs by their difference in binding kinetics. The assay developed in this study can readily be adopted for high throughput validation of candidate aptamers for specificity, affinity, and epitopes, providing both equilibrium and kinetic information for aptamer interaction with targets.