• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.85-92
• /
• 2023

Recently, interest in artificial intelligence has increased due to the development of artificial intelligence fields such as ChatGPT and self-driving cars. However, there are still many unknown elements in training process of artificial intelligence, so that optimizing the model requires more time and effort than it needs. Therefore, there is a need for a tool or methodology that can analyze the weight changes during the training process of artificial intelligence and help out understatnding those changes. In this research, I propose a visualization system which helps people to understand the accumulated weight changes. The system calculates the weights for each training period to accumulates weight changes and stores accumulated weight changes to plot them in 3D space. This research will allow us to explore different aspect of artificial intelligence learning process, such as understanding how the model get trained and providing us an indicator on which hyperparameters should be changed for better performance. These attempts are expected to explore better in artificial intelligence learning process that is still considered as unknown and contribute to the development and application of artificial intelligence models.

• Membrane Journal
• /
• v.33 no.6
• /
• pp.362-368
• /
• 2023

This research article explores the application of Polymer of Intrinsic Microporosity (PIM-1) as a cutting-edge material for CO₂ gas separation membranes in response to the escalating global concern over climate change and the imperative to reduce greenhouse gas emissions. The study delves into the synthesis, molecular weight control, and fabrication of PIM-1 membranes, providing comprehensive insights through various characterization techniques. The intrinsic microporosity of PIM-1, arising from its unique crosslinked and rigid structure, is harnessed for selective gas permeation, particularly of carbon dioxide. The article emphasizes the tunable chemical properties of PIM-1, allowing for customization and optimization of gas separation membranes. By controlling the molecular weight, higher molecular weight (H-PIM-1) membranes are demonstrated to exhibit superior CO₂ permeability and selectivity compared to lower molecular weight counterparts (L-PIM-1). The study's findings highlight the critical role of molecular weight in tailoring PIM-1 membrane properties, contributing to the advancement of next-generation membrane technologies for efficient and selective CO₂ capture-an essential step in addressing the pressing global challenge of climate change.

• Journal of Bio-Environment Control
• /
• v.33 no.1
• /
• pp.1-11
• /
• 2024

In this study, five artificial intelligence (AI) models: Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc were used to classify tea leaf diseases. Eight image categories were used: healthy, algal leaf spot, anthracnose, bird's eye spot, brown blight, gray blight, red leaf spot, and white spot. Software used in this study was Orange 3 which functions as a Python library for visual programming, that operates through an interface that generates workflows to visually manipulate and analyze the data. The precision of each AI model was recorded to select the ideal AI model. All models were trained using the Adam solver, rectified linear unit activation function, 100 neurons in the hidden layers, 200 maximum number of iterations in the neural network, and 0.0001 regularizations. To extend the functionality of Orange 3, new add-ons can be installed and, this study image analytics add-on was newly added which is required for image analysis. For the training model, the import image, image embedding, neural network, test and score, and confusion matrix widgets were used, whereas the import images, image embedding, predictions, and image viewer widgets were used for the prediction. Precisions of the neural networks of the five AI models (Inception v3, SqueezeNet (local), VGG-16, Painters, and DeepLoc) were 0.807, 0.901, 0.780, 0.800, and 0.771, respectively. Finally, the SqueezeNet (local) model was selected as the optimal AI model for the detection of tea diseases using tea leaf images owing to its high precision and good performance throughout the confusion matrix.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.12
• /
• pp.157-167
• /
• 2009

Recently, the leakage of confidential information and personal information is taking place on the Internet more frequently than ever before. Most of such online security incidents are caused by attacks on vulnerabilities in web applications developed carelessly. It is impossible to detect an attack on a web application with existing firewalls and intrusion detection systems. Besides, the signature-based detection has a limited capability in detecting new threats. Therefore, many researches concerning the method to detect attacks on web applications are employing anomaly-based detection methods that use the web traffic analysis. Much research about anomaly-based detection through the normal web traffic analysis focus on three problems - the method to accurately analyze given web traffic, system performance needed for inspecting application payload of the packet required to detect attack on application layer and the maintenance and costs of lots of network security devices newly installed. The UTM(Unified Threat Management) system, a suggested solution for the problem, had a goal of resolving all of security problems at a time, but is not being widely used due to its low efficiency and high costs. Besides, the web filter that performs one of the functions of the UTM system, can not adequately detect a variety of recent sophisticated attacks on web applications. In order to resolve such problems, studies are being carried out on the web application firewall to introduce a new network security system. As such studies focus on speeding up packet processing by depending on high-priced hardware, the costs to deploy a web application firewall are rising. In addition, the current anomaly-based detection technologies that do not take into account the characteristics of the web application is causing lots of false positives and false negatives. In order to reduce false positives and false negatives, this study suggested a realtime anomaly detection method based on the analysis of the length of parameter value contained in the web client's request. In addition, it designed and suggested a WAF(Web Application Firewall) that can be applied to a low-priced system or legacy system to process application data without the help of an exclusive hardware. Furthermore, it suggested a method to resolve sluggish performance attributed to copying packets into application area for application data processing, Consequently, this study provide to deploy an effective web application firewall at a low cost at the moment when the deployment of an additional security system was considered burdened due to lots of network security systems currently used.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.769-771
• /
• 2005

유비쿼터스 컴퓨팅의 기반 설비인 센서 네트워크는 많은 수의 센서 노드들로 구성되며, 각 센서 노드의 하드웨어는 매우 작은 규모이다. 또한 최소한의 전력 소모를 위하여 센서 노드들은 동적으로 재구성되며, 노드들 간의 통신은 무선 네트워크를 통하여 이루어진다. 센서 네트워크는 구축 목적에 따라 네트워크 토폴로지 및 라우팅 방식이 결정되어야 하고, 이와 더불어 센서 노드의 하드웨어와 소프트웨어도 필요에 따라 다양하게 변경되어야 한다. 따라서 센서 네트워즈가 구현되기 전에 시스템 동작과 성능을 예측할 수 있고 소프트웨어 개발 환경도 제공해주는 시뮬레이터가 사용 가능하다면, 시스템 개발 기간을 크게 단축시킬 수 있을 것이다. 기존의 센서 네트워크 시뮬레이터들은 특별한 응용을 위한 특정 기반의 하드웨어와 운영체제에 국한되어 개발되었기 때문에 다양한 센서 네트워크 환경을 지원하기에는 한계가 있으며, 센서 네트워크 설계상의 주요 요소인 전력 소모량 분석이 포함되지 않았다. 따라서 본 연구에서는 특정한 응용이나 운영체제에 제한을 받지 않으면서 다양하게 센서 네트워크 환경을 설계 및 검증할 수 있고 전력 소모량 추정도 가능한 시뮬레이터를 개발하는 것을 목표로 하였다. 본 연구에서 개발한 시뮬레이터는 기계명령어-레일(machine instruction-level)의 이산-사건 시뮬레이션(discrete-event simulation) 기법을 이용함으로써 실제 센서 노드의 프로그램 실행 및 관련 동작들을 세부적으로 예측하는 데 사용될 수 있도록 하였다. 시뮬레이션의 작업부하(Workload)인 명령어 트레이스(instruction trace)로는 ATmega128L 마이크로컨트롤러용으로 크로스 컴파일된 인텔 헥스-레코드 형식(.hex) 또는 S-레코드 형식(.srec)의 파일을 사용한다.들을 해결하고자 프라이버시보호에 새로운 키 생성 방법을 통한 강력한 프로토콜을 제안 한다.하였으나 사료효율은 증진시켰으며, 후자(사양, 사료)와의 상호작용은 나타나지 않았다. 이상의 결과는 거세비육돈에서 1) androgen과 estrogen은 공히 자발적인 사료섭취와 등지방 침적을 억제하고 IGF-I 분비를 증가시키며, 2) 성선스테로이드호르몬의 이 같은 성장에 미치는 효과의 일부는 IGF-I을 통해 매개될 수도 있을을 시사한다. 약 $70 {\~} 90\%$의 phenoxyethanol이 유상에 존재하였다. 또한, 미생물에 대한 항균력도 phenoxyethanol이 수상에 많이 존재할수록 증가하는 경향을 나타내었다. 따라서, 제형 내 oil tomposition을 변화시킴으로써 phenoxyethanol의 사용량을 줄일 수 있을 뿐만 아니라, 피부 투과를 감소시켜 보다 피부 자극이 적은 저자극 방부시스템 개발이 가능하리라 보여 진다. 첨가하여 제조한 curd yoghurt는 저장성과 관능적인 면에서 우수한 상품적 가치가 인정되는 새로운 기능성 신제품의 개발에 기여할 수 있을 것으로 사료되었다. 여자의 경우 0.8이상이 되어서 심혈관계 질환의 위험 범위에 속하는 수준이었다. 삼두근의 두겹 두께는 남녀 각각 $20.2\pm8.58cm,\;22.2\pm4.40mm$으로 남녀간에 유의한 차이는 없었다. 조사대상자의 식습관 상태는 전체 대상자의 $84.4\%$가 대부분이 하루 세끼 식사를 규칙적으로 하고 있었으며 식사속도는 허겁지겁 빨리 섭취하는 경우가 남자는 $31.0\%$, 여자는 $21.4\%$로 나타났고 이들을 제외한 나머지 사람들은 보통 속도 혹은 충분한 시간을 가지고 식사를 하였

• Membrane Journal
• /
• v.28 no.2
• /
• pp.113-120
• /
• 2018

Global warming due to indiscriminate carbon dioxide emissions has a profound impact on human life by causing abnormal climate change and ecosystem destruction. As a way to reduce carbon dioxide emissions, in this study, we presented a polymeric membrane prepared by blending a self-crosslinkable P(GMA-g-PPG)-co-POEM (SP) copolymer and commercial polymer polyvinylpyrrolidone (PVP). As the content of PVP increased, it was observed that the gas permeance decreased and $CO_2/N_2$ selectivity increased. At 30 wt% PVP content, the $CO_2$ permeance of the membrane decreased from 72.9 GPU of pure SP polymer to 12.6 GPU, while $CO_2/N_2$ selectivity improved by 79% from 28.1 to 50.4. It results from the hydrogen bonding between the SP copolymer and PVP, leading to more compact structure of the polymer chains, which was confirmed by FT-IR, TGA, XRD and SEM analysis. Therefore, we suggest that the permeance and selectivity of the membranes can be easily adjusted as desired by controlling the PVP content in the SP/PVP polymer blend.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.3
• /
• pp.175-183
• /
• 2008

In wireless sensor networks with ad hoc networking capability, sensor nodes are battery operated and are usually disposable once deployed. As a result, each sensor node senses and communicates with limited energy and, thus, energy efficiency has been studied as a key design factor which determines lifetime of a wireless sensor network, and it is more improved recently by using so-called cross-layer optimization technique. In this paper, we propose and implement a new energy saving mechanism that reduces energy consumption during data collection by controlling transmission power at sensor nodes and then measure its performance in terms of lifetime improvement for the wireless sensor network platform ZigbeX. When every sensor node transmits sensed data to its clusterhead, it controls its transmission power down to as low level as communication is possible, resulting in energy saving. Each sensor node controls its transmission power based on RSSI(Received Signal Strength Indicator) of the packet received from its clusterhead. In other words, the sensor node can save energy by controlling its transmission power down to an appropriate level that its clusterhead safely receives the packet it transmits. According to the repetitive experiment of the proposed scheme on the ZigbeX platform using the packet analyzer developed by us, it is observed that the network lifetime is prolonged by up to 21.9% by saying energy during the data collection occupying most amount of network traffic.

• Membrane Journal
• /
• v.27 no.4
• /
• pp.358-366
• /
• 2017

The most important factor in the performances of polymer electrolyte membranes for fuel cells is how fast hydrogen ions can be transported along the water channel formed inside the electrolyte membrane. Since the morphology of the water channel and the diffusivity of the protons are very important factors for the proton transport behavior, various molecular dynamics simulation studies are being carried out to clarify this. The force-field is an important variable parameterizing the movement and interaction of each atom in molecular dynamics simulation. In this study, proton diffusivities of the 3D models of polymer electrolyte membranes were calculated in order to analyze the effects of various types of force-fields on the molecular simulation. It has been found that the charge value determining the non-bonding interaction plays a very important role in the formation of the water channel morphology, and the COMPASS force-field can calculate the accurate proton diffusion behavior. Accordingly, for molecular dynamics simulation of polymer electrolyte membranes, the proper selection of the force-field is very important due to its great effect on the proton diffusion as well as the final molecular structure.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.409-416
• /
• 1999

액체/고체 경계면에 레일레이각으로 초음파 pulse를 입사시키면 입사된 에너지의 상당 부분이 고체쪽으로 침투여 표면으로부터 약 1.5 파장 깊이 정도까지 에너지 분포를 가지고 고체 표면을 따라 전파하는 레일레 이파로 전환되며, 이러한 입사각에서는 기하학적인 거울 반사가 일어나지 않고 반사파의 중심이 Schoch 변위만큼 전방으로 이동되고, 또 입사 방향으로 후반 산란되는 초음파의 신호가 급격히 증가하는 현상이 관찰된다. 만일 고체에서 초음파의 감쇠가 산란에 의해 크게 영향을 받고, 레일레이각에서 고체 쪽으로 침투한 에너지의크기를 $E_0$라고 하면, 고체 표면과 표면 근처를 전파하는 레일레이파의 산란파 에너지, $E_S$는 Schoch 변위, ${\Delta}_S$와 산란에 의한 감쇠계수 ${\alpha}_S$에 비례하는 관계가 있음을 이론적으로 구하였다. 입사 방향으로 후방산란되는 초음파는 산란파의 일부이므로 후방산란 초음파 에너지, E_{Bs}도 이와 같은 관계를 가진다. 그러므로, 레일레이각으로 입사된 초음파의 후방산란 에너지, $E_{B_S}$ 산란체(e.g. grain)의 평균 크기, D와 주파수 f와는 레일레이 산란 영역과 Stochastic 산란 영역에 대해 각각 $E_{B_S}\;\propto\;D^{3}f^{3}$와 $E_{B_S}\;\propto\;D\;f$인 관계를 가지는 것으로 얻어졌다. 이것은 액체/고체 경계면에서 레일레이각으로 입사되어 레일레이파로 전환된 초음파가 다시 액체로 그 에너지를 누설하여 그 산란 영역이 Schoch 변위 내에서 일어나기 때문이며, 이러한 영향에 의해서일반적인 산란에서의 주파수 의존성과는 달리 각 산란 영역에서 그 지수는 1씩 작은 값을 갖는다.향에 따라 음장변화가 크게 다를 것이 예상되므로 이를 규명하기 위해서는 궁극적으로 3차원적인 음장분포 연구가 필요하다. 음향센서를 해저면에 매설할 경우 수충의 수온변화와 센서 주변의 수온변화 사이에는 어느 정도의 시간지연이 존재하게 되므로 이에 대한 영향을 규명하는 것도 센서의 성능예측을 위해서 필요하리라 사료된다.가지는 심부 가스의 개발 성공률을 증가시키기 위하여 심부 가스가 존재하는 지역의 지질학적 부존 환경 및 조성상의 특성과 생산시 소요되는 생산비용을 심도에 따라 분석하고 생산에 수반되는 기술적 문제점들을 정리하였으며 마지막으로 향후 요구되는 연구 분야들을 제시하였다. 또한 참고로 현재 심부 가스의 경우 미국이 연구 개발 측면에서 가장 활발한 활동을 전개하고 있으며 그 결과 다수의 신뢰성 있는 자료들을 확보하고 있으므로 본 논문은 USGS와 Gas Research Institute(GRI)에서 제시한 자료에 근거하였다.ऀĀ耀Ā삱?⨀؀Ā Ā?⨀ጀĀ耀Ā?돀ꢘ?⨀硩?⨀ႎ?⨀?⨀넆돐쁖잖⨀쁖잖⨀／ࠐ?⨀焆덐瀆倆Āⶇ퍟ⶇ퍟ĀĀĀĀ磀鲕좗?⨀肤?⨀⁅Ⴅ?⨀쀃잖⨀䣙熸ጁ↏?⨀

• Journal of Navigation and Port Research
• /
• v.34 no.6
• /
• pp.479-485
• /
• 2010

To handle container effectively is one of the most important factors in a port because working time is linked soon into cost. Since the middle of 1990s, RMGC(Rail-Mounted Gantry Crane) and RTGC(Rubber-Tired Gantry Crane) have been developed and widely used to operate containers in the yard. The RTGC is more difficult than RMGC in the automatic control system design. Although, the RTGC is largely advantaged to free driving environment, it has some considerable disadvantages in the system operating. In general, the problems are due to tire slip and lack of tire pressure etc. Therefore, a desirable research result has not been shown in this time. So, in this paper, we propose a new approach to design tracking control system for the RTGC in which the mathematical modeling is included. From the simulation results, the control performance of the designed control systems is evaluated.