• Journal of Biomedical Engineering Research
• /
• v.34 no.1
• /
• pp.8-13
• /
• 2013

Persons with sensorineural hearing impairment have troubles in hearing at noisy environments because of their deteriorated hearing levels and low-spectral resolution of the auditory system and therefore, they use hearing aids to compensate weakened hearing abilities. Various algorithms for hearing loss compensation and environmental noise reduction have been implemented in the hearing aid; however, the performance of these algorithms vary in accordance with external sound situations and therefore, it is important to tune the operation of the hearing aid appropriately in accordance with a wide variety of sound situations. In this study, a sound classification algorithm that can be applied to the hearing aid was suggested. The proposed algorithm can classify the different types of speech situations into four categories: 1) speech-only, 2) noise-only, 3) speech-in-noise, and 4) music-only. The proposed classification algorithm consists of two sub-parts: a feature extractor and a speech situation classifier. The former extracts seven characteristic features - short time energy and zero crossing rate in the time domain; spectral centroid, spectral flux and spectral roll-off in the frequency domain; mel frequency cepstral coefficients and power values of mel bands - from the recent input signals of two microphones, and the latter classifies the current speech situation. The experimental results showed that the proposed algorithm could classify the kinds of speech situations with an accuracy of over 94.4%. Based on these results, we believe that the proposed algorithm can be applied to the hearing aid to improve speech intelligibility in noisy environments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.187-193
• /
• 2015

The ICT healing platform sets a couple of goals including preventing chronic diseases and sending out early disease warnings based on personal information such as bio-signals and life habits. The 2-step open system(TOS) had a relay designed between the healing platform and the storage of personal health data. It also took into account a publish/subscribe(pub/sub) service based on large-scale connections to transmit(monitor) the data processing process in real time. In the early design of TOS pub/sub, however, the same buffers were allocated regardless of connection idling and type of message in order to encode connection messages into a deflate algorithm. Proposed in this study, the dynamic buffer allocation was performed as follows: the message transmission type of each connection was first put to queuing; each queue was extracted for its feature, computed, and converted into vector through tf-idf, then being entered into a k-means cluster and forming a cluster; connections categorized under a certain cluster would re-allocate the resources according to the resource table of the cluster; the centroid of each cluster would select a queuing pattern to represent the cluster in advance and present it as a resource reference table(encoding efficiency by the buffer sizes); and the proposed design would perform trade-off between the calculation resources and the network bandwidth for cluster and feature calculations to efficiently allocate the encoding buffer resources of TOS to the network connections, thus contributing to the increased tps(number of real-time data processing and monitoring connections per unit hour) of TOS.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.9 s.339
• /
• pp.85-96
• /
• 2005

A ' Virtual Private Network (YPN) over Internet' has the benefits of being cost-effective and flexible. However, given the increasing demands for high bandwidth Internet and for reliable services in a 'VPN over Intemet,' an IP/GMPLS over DWDM backbone network is regarded as a very favorable approach for the future 'Optical VPN (OVPN)' due to the benefits of transparency and high data rate. Nevertheless, OVPN still has survivability issues such that a temporary fault can lose a large amount of data in seconds, moreover unauthorized physical attack can also be made on purpose to eavesdrop the network through physical components. Also, logical attacks can manipulate or stop the operation of GMPLS control messages and menace the network survivability of OVPN. Thus, network survivability in OVPN (i.e. fault/attack tolerant recovery mechanism considering physical structure and optical components, and secured transmission of GMPLS control messages) is rising as a critical issue. In this Paper, we propose a new path establishment scheme under shared risk link group (SRLG) constraint for physical network survivability. And we also suggest a new logical survivability management mechanism by extending resource reservation protocol-traffic engineering extension (RSVP-TE+) and link management protocol (LMP). Finally, according to the results of our simulation, the proposed algorithms are revealed more effective in the view point of survivability.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.37-45
• /
• 2006

In this paper, we propose the development of MHLA(Modulatory Hippocampus Learning Algorithm) which remodel a principle of brain of hippocampus. Hippocampus takes charge auto-associative memory and controlling functions of long-term or short-term memory strengthening. We organize auto-associative memory based 3 steps system(DG, CA3, CAl) and improve speed of learning by addition of modulator to long-term memory learning. In hippocampal system, according to the 3 steps order, information applies statistical deviation on Dentate Gyrus region and is labelled to responsive pattern by adjustment of a good impression. In CA3 region, pattern is reorganized by auto-associative memory. In CAI region, convergence of connection weight which is used long-term memory is learned fast by neural networks which is applied modulator. To measure performance of MHLA, PCA(Principal Component Analysis) is applied to face images which are classified by pose, expression and picture quality. Next, we calculate feature vectors and learn by MHLA. Finally, we confirm cognitive rate. The results of experiments, we can compare a proposed method of other methods, and we can confirm that the proposed method is superior to the existing method.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.8
• /
• pp.535-542
• /
• 2013

Since case-based reasoning(CBR) has many advantages, it has been used for supporting decision making in various areas including medical checkup, production planning, customer classification, and so on. However, there are several factors to be set by heuristics when designing effective CBR systems. Among these factors, this study addresses the issue of selecting appropriate neighbors in case retrieval step. As the criterion for selecting appropriate neighbors, conventional studies have used the preset number of neighbors to combine(i.e. k of k-nearest neighbor), or the relative portion of the maximum similarity. However, this study proposes to use the absolute similarity threshold varying from 0 to 1, as the criterion for selecting appropriate neighbors to combine. In this case, too small similarity threshold value may make the model rarely produce the solution. To avoid this, we propose to adopt the coverage, which implies the ratio of the cases in which solutions are produced over the total number of the training cases, and to set it as the constraint when optimizing the similarity threshold. To validate the usefulness of the proposed model, we applied it to a real-world target marketing case of an online shopping mall in Korea. As a result, we found that the proposed model might significantly improve the performance of CBR.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.6
• /
• pp.507-514
• /
• 2017

As BIM has been widely used in the field of architecture, efforts to apply BIM to civil engineering structures are increasing rapidly. Since commercial BIM softwares are focused on building structure, it is difficult to apply to alignment-based civil infrastructures. In this study, we proposed a method to generate an information model that reflects cant by sharing information between alignment-centered modeling tools and BIM authoring tools to manage information of railway track. The railway track modeling process consists of classifying structures into continuous and non-continuous structures, creating continuous structures by alignment-centered modeling tools, and using the shared alignment information to generate information model of the non-continuous structures. Non-continuous structures were generated by an algorithm that calculates the position and rotation information of each structure based on discretized railway alignment and cant information transmitted to the BIM authoring tools. The availabilities of proposed method were studied by applying to the osong test-line. Using the test model, it was shown that the objects were identified, the properties were extracted, and the quantities of each structure were calculated.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.10a
• /
• pp.169-169
• /
• 1999

최근 산업 플랜트의 공정제어 시스템은 복잡하고 대규모화되어 고장 발생시 경제적 손실과 위험성이 증폭되어 규정된 안정서와 신뢰성 확보가 필수적이라 할 수 있다. 고장검출 및 진단기법은 시스템의 신뢰성을 높이기 위한 효과적인 방안을 연구하는 것으로 현대에 들어서 많은 학자들의 관심을 끌고 있으며 실제 계통에 점차적으로 응용되고 있다. 현재까지 개발된 고장검출 및 진단기법은 사용된 프로세스 모델의 형태, 고장검출 진단 알고리즘에 따라 다양하게 분류 될 수 있으며 일반적으로 사용된 모델에 따라 크게 1) 정량적 모델에 근거한 해석적 기법, 2) 정성적 모델에 근거한 기법, 3) 지식기반 진단 기법으로 구분 할 수 있다. 이중 정량적 모델 기법은 대상계통의 수학적 모델에 근거하여 운전 데이터를 분석함으로서 고장검출 진단을 수행하는 해석적 기법으로서 근본적으로 계통의 정확한 수학적 모델을 요구하므로 불확실성을 포함한 계통 및 비선형성이 강한 계통등에는 적용이 곤란하다. 정성적 모델 및 지식기반 기법은 정량적 진단 기법과는 달리 대상 프로세스에 대한 수학적 모델 대신에 운전자의 경험과 프로세스 변수간의 상호 작용 및 고장의 전파과정, 고장원인과 증상과의 직접적인 관계에 대한 구조적 지식에 근거한 것으로 고장원인에 대한 계통의 동작을 추론 할 수 있으며, 상황 변화에 따른 영향을 예측할 수 있다. 본 논문에서는 정성적 모델 및 지식기반 기법에 근거한 고장검출 및 진단 기술을 화력 발전소 보일로 프로세스에 적용하여 정성적 시뮬레이션에 의한 설비의 고장을 조기에 발견하여 고장 파급으로 인한 발전 정지 및 설비의 손상 확대를 방지하고 고장 발생시 신속한 원인 규명 및 후속 조치관련 정보들을 운전원에게 제공할 목적으로 현재 전력원에서 개발중인 지능형 경보시스템에 대하여 기술하고자 한다.음과 같이 설명하였다. 서로 상반되는 것들이 다음과 같이 설명하였다. 서로 상반되는 것들이 부딛힘이 없이 공존하고 일상의 논리가 무시된다. 부정, 의심이 없고 확실한 것이 없다. 한 대상에 가졌던 생각이 다른 대상에 옮겨간다(displacement). 한 대상이 여러 대상이 갖고 있는 의미를 함축하고 있다(condensation). 시각적인 순서가 무시된다. 마음속의 생각과 외부의 실제적인 일을 구분하지 못한다. 시간 상의 순서가 있다가 없다가 한다. 차례로 일어나야 할 일이 동시에 한꺼번에 일어난다. 대상들이 서로 비슷해지고 동시에 있을 수 없는 대상들이 함께 나타난다. 사고의 정상적인 구조가 와해된다. Matte-Blance는 무의식에서는 여러 독립된 대상들간의 구분을 없애며, 주체와 객체를 하나로 보려는 대칭화(symmetrization)의 경향이 있기 때문에 이런 변화가 생긴다고 하였다. 또 대칭화가 진행되면 무한대의 느낌을 갖게 되어, 전지(moniscience), 전능(omnipotence), 무력감(impotence), 이상화(idealization)가 나타난다. 그러나 무의식에 대칭화만 있는 것은 아니며, 의식의 사고양식인 비대칭도 어느 정도 나타나며, 대칭화의 정도에 따라, 대상들이 잘 구분되어 있는 단계, 의식수준의 감정단계, 집단 내에서의 대칭화 단계, 집단간에서의 대칭화 단계, 구분이 없어지는 단계로 구분하였다.systems. We believe that this taxonomy is a significant contribution because it adds clarity, completeness, and "global perspective" to workflow architectural discussions. The vocabulary suggested here

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.1
• /
• pp.75-83
• /
• 2008

We propose a welfare interface using multiple fecial features tracking, which can efficiently implement various mouse operations. The proposed system consist of five modules: face detection, eye detection, mouth detection, facial feature tracking, and mouse control. The facial region is first obtained using skin-color model and connected-component analysis(CCs). Thereafter the eye regions are localized using neutral network(NN)-based texture classifier that discriminates the facial region into eye class and non-eye class, and then mouth region is localized using edge detector. Once eye and mouth regions are localized they are continuously and correctly tracking by mean-shift algorithm and template matching, respectively. Based on the tracking results, mouse operations such as movement or click are implemented. To assess the validity of the proposed system, it was applied to the interface system for web browser and was tested on a group of 25 users. The results show that our system have the accuracy of 99% and process more than 21 frame/sec on PC for the $320{\times}240$ size input image, as such it can supply a user-friendly and convenient access to a computer in real-time operation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.127-133
• /
• 2014

In order to protect information asset from various malicious code, Honeypot system is implemented. Honeypot system is designed to elicit attacks so that internal system is not attacked or it is designed to collect malicious code information. However, existing honeypot system is designed for the purpose of collecting information, so it is designed to induce inflows of attackers positively by establishing disguised server or disguised client server and by providing disguised contents. In case of establishing disguised server, it should reinstall hardware in a cycle of one year because of frequent disk input and output. In case of establishing disguised client server, it has operating problem such as procuring professional labor force because it has a limit to automize the analysis of acquired information. To solve and supplement operating problem and previous problem of honeypot's hardware, this thesis suggested hybrid honeypot. Suggested hybrid honeypot has honeywall, analyzed server and combined console and it processes by categorizing attacking types into two types. It is designed that disguise (inducement) and false response (emulation) are connected to common switch area to operate high level interaction server, which is type 1 and low level interaction server, which is type 2. This hybrid honeypot operates low level honeypot and high level honeypot. Analysis server converts hacking types into hash value and separates it into correlation analysis algorithm and sends it to honeywall. Integrated monitoring console implements continuous monitoring, so it is expected that not only analyzing information about recent hacking method and attacking tool but also it provides effects of anticipative security response.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.388-396
• /
• 2017

Since there are many variables such as various poses, illuminations and occlusions in a face detection problem, a high performance detection system is required. Although CNN is excellent in image classification, CNN operatioin requires high-performance hardware resources. But low cost low power environments are essential for small and mobile systems. So in this paper, the CPU-FPGA integrated system is designed based on 3-stage cascade CNN architecture using small size FPGA. Adaptive Region of Interest (ROI) is applied to reduce the number of CNN operations using face information of the previous frame. We use a Field Programmable Gate Array(FPGA) to accelerate the CNN computations. The accelerator reads multiple featuremap at once on the FPGA and performs a Multiply-Accumulate (MAC) operation in parallel for convolution operation. The system is implemented on Altera Cyclone V FPGA in which ARM Cortex A-9 and on-chip SRAM are embedded. The system runs at 30FPS with HD resolution input images. The CPU-FPGA integrated system showed 8.5 times of the power efficiency compared to systems using CPU only.