• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.6
• /
• pp.1149-1154
• /
• 2017

To obtain good recognition performance of speech recognition system under background noise, it is very important to select appropriate feature parameters of speech. The feature parameter used in this paper is Mel frequency cepstral coefficient (MFCC) with the human auditory characteristics applied to Wiener filter method. That is, the feature parameter proposed in this paper is a new method to extract the parameter of clean speech signal after removing background noise. The proposed method implements the speaker recognition by inputting the proposed modified MFCC feature parameter into a multi-layer perceptron network. In this experiments, the speaker independent recognition experiments were performed using the MFCC feature parameter of the 14th order. The average recognition rates of the speaker independent in the case of the noisy speech added white noise are 94.48%, which is an effective result. Comparing the proposed method with the existing methods, the performance of the proposed speaker recognition is improved by using the modified MFCC feature parameter.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.9
• /
• pp.1673-1678
• /
• 2016

In the area of the speech recognition processing, background noises are caused the incorrect response to the speech input, therefore the speech recognition rates are decreased by the background noises. Accordingly, a more high level noise processing techniques are required since these kinds of noise countermeasures are not simple. Therefore, this paper proposes an algorithm to distinguish between the stationary background noises or non-stationary background noises and the speech signal having short time duration in the noisy environments. The proposed algorithm uses the characteristic parameter of the improved speech signal as an important measure in order to distinguish different types of the background noises and the speech signals. Next, this algorithm estimates various kinds of the background noises using a multi-layer perceptron neural network. In this experiment, it was experimentally clear the estimation of the background noises and the speech signals.

• Journal of Advanced Marine Engineering and Technology
• /
• v.35 no.8
• /
• pp.1098-1104
• /
• 2011

Data communications networks at sea can be modelled by multi-layered networks with traditional carriers (RF, satellites), and BWA (wireless LAN, WiBro, LTE), which partially makes it possible the high speed communication services (WWW, VoIP) at sea. In this paper, a novel routing scheme (CPR) is proposed which selects an optimal carrier for each hop in routes based on carrier preferences (CP). The carrier preferences are measured proactively depending on the feasibility of transmission characteristics (transmission rate, cost, and latency time) of the carriers for each application. Performance was compared with that of the OMH-MW (Optimal Medium per Hop based on Max-Win) routing scheme.

• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.1-10
• /
• 2020

In this paper, we propose a new pornographic content detection scheme using bi-directional relationships between neighboring auditory signals in order to accurately detect sound-centered obscene contents that are rapidly spreading via the Internet. To capture the bi-directional relationships between neighboring signals, we design a multilayered bi-directional dilated-causal convolution network by stacking several dilated-causal convolution blocks each of which performs bi-directional dilated-causal convolution operations. To verify the performance of the proposed scheme, we compare its accuracy to those of the previous two schemes each of which uses simple auditory feature vectors with a support vector machine and uses only the forward relationships in audio signals by a previous stack of dilated-causal convolution layers. As the results, the proposed scheme produces an accuracy of up to 84.38% that is superior performance up to 25.80% than other two comparison schemes.

• Journal of Convergence for Information Technology
• /
• v.8 no.1
• /
• pp.139-145
• /
• 2018

Ransomeware is a kind of malware. Computers infected with Ransomware have limited system access. It is a malicious program that must provide a money to the malicious code maker in order to release it. On May 12, 2017, with the largest Ransomware attack ever, concerns about the Internet security environment are growing. The types of Ransomware and countermeasures to prevent cyber terrorism are discussed. Ransomware, which has a strong infectious nature and has been constantly attacked in recent years, is typically in the form of Locky, Petya, Cerber, Samam, and Jigsaw. As of now, Ransomware defense is not 100% free. However, it can counter to Ransomware through automatic updates, installation of vaccines, and periodic backups. There is a need to find a multi-layered approach to minimize the risk of reaching the network and the system. Learn how to prevent Ransomware from corporate and individual users.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.45-52
• /
• 2017

Drifter is an equipment for observing the characteristics of seawater in the ocean, and it can be used to predict effluent oil diffusion and to observe ocean currents. In this paper, we design models or the prediction of drifter trajectory using machine learning. We propose methods for estimating the trajectory of drifter using support vector regression, radial basis function network, Gaussian process, multilayer perceptron, and recurrent neural network. When the propose mothods were compared with the existing MOHID numerical model, performance was improve on three of the four cases. In particular, LSTM, the best performed method, showed the imporvement by 47.59% Future work will improve the accuracy by weighting using bagging and boosting.

• Journal of the Korea Convergence Society
• /
• v.8 no.10
• /
• pp.1-8
• /
• 2017

Accurate forecasting enables to effectively prepare for future phenomenon. Especially, meteorological phenomenon is closely related with human life, and it can prevent from damage such as human life and property through forecasting of weather and disaster that can occur. To respond quickly and effectively to oil spill accidents, it is important to accurately predict the movement of oil spills and the weather in the surrounding waters. In this paper, we selected four representative machine learning techniques: support vector machine, Gaussian process, multilayer perceptron, and radial basis function network that have shown good performance and predictability in the previous studies related to oil spill detection and prediction in meteorology such as wind, rainfall and ozone. we suggest the applicability of oil spill prediction model based on machine learning.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.153-160
• /
• 2010

We optimized the Si(substrate)/$SiO_2$(cladding)/$Si_3N_4$(antiresonant cladding)/$SiO_2$(core)/air multi-layers rib-optical waveguides of antiresonant reflecting optical waveguide (ARROW) for integrated optical biosensor structure utilizing beam propagation method (BPM). Thickness of anti-resonant cladding was derived to minimize the propagation loss and leaky field mode deeply related with evanescent mode was theoretically derived. Depth, width, refractive index and cladding thickness of anti-resonant cladding were numerically calculated into 2.3${\mu}m$, 5${\mu}m$, 1.488, and 0.11${\mu}m$ respectively to minimize propagation loss using the BPM simulation tool. Finally one- and two-dimensional propagation characteristics of ARROW was confirmed.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.07a
• /
• pp.223-224
• /
• 2007

광기록의 역사는 1980년대초 Sony와 Philips가 공동 개발한 CD (compact disc: 640MB)의 출현으로부터 시작하여 1996년의 DVD (digital versatile disc: 4.7GB)를 거쳐 최근의 BD (Blu-ray disc: >20GB)에까지 이르고 있다. Read-only memory, recordable, rewritable 등 다양한 저장 및 재생방식이 존재하는데, 이는 레이저 조사에 의한 기록매체의 특성변화의 가역성 (reversibility)에 의존하므로 저장 및 재생방식에 따라 저장매체 또한 다르게 된다. 기록용량의 증가는 레이저의 파장이 짧아지고 동시에 사용된 렌즈의 개구수 (NA: Numerical aperture)가 증가함에 따른 빔 spot size의 감소에 기인한다. 회절한계를 극복하여 빔의 spot size를 줄이고자 하는 연구는 현재도 전세계적으로 활발히 이루어지고 있고 이러한 노력의 일환으로 어느 정도의 추가적인 저장용량 증가는 가능할 수 있으나, 2차원 방식으로는 대용량 광정보기록 (수백 GB ${\sim}$ TB급)의 실현은 불가능하다는 것이 일반적인 예상이다. 한편 장기적으로 기존의 2차원 정보기록방식을 대체하고 저장용량을 획기적으로 증가시킬 수 있는 bit-type 3차원 광정보기록의 개념이 1990년을 전.후로 처음으로 제시되었다. 이는 2차원 bit 정보가 수십 내지 수백 개의 다층 (multi-layer) 형태로 기록되는 방식인데, 그동안 산업체의 관심이 상대적으로 높지 않았던 이유는 영화, 음악 등 엔터테인먼트 시장성 확대를 위해 Blu-ray disc나 HD-DVD에 대한 연구개발에 치중해왔기 때문이다. 하지만 최근 급변하는 정보시스템 서비스 환경 속에서 정보유통량이 기하급수적으로 증가하고 있고 개인이 취급하는 정보량도 2010년경에는 수백 GB 단위가 될 것으로 예상되고 있으며 디지털 방송, 네트워크를 기반으로 한 서비스 수요 뿐 만 아니라 전자도서관이나 VOD (Video on Demand) 서비스 사업에 필수적인 수 TB급의 대용량 저장장치에 대한 수요 또한 크게 증가할 것으로 전망된다. 이에 따라 점차 그 물리적 한계에 다다르고 있는 기존의2차원 정보저장방식을 대체하고 저장용량을 획기적으로 증가시킬 수 있는3차원 정보기록(> $10^{13}$ $bits/cm^3$)에 대한 필요성이 대두된다.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.472-477
• /
• 2018

In this paper, we develop interactive content services for preventing depression of users through an intelligent Internet of Things(IoT) mirror system. For interactive content services, an IoT mirror device measures attention and meditation data from an EEG headset device and also measures facial expression data such as "sad", "angery", "disgust", "neutral", " happy", and "surprise" classified by a multi-layer perceptron algorithm through an webcam. Then, it sends the measured data to an oneM2M-compliant IoT server. Based on the collected data in the IoT server, a machine learning model is built to classify three levels of depression (RED, YELLOW, and GREEN) given by a proposed merge labeling method. It was verified that the k-nearest neighbor (k-NN) model could achieve about 93% of accuracy by experimental results. In addition, according to the classified level, a social network service agent sent a corresponding alert message to the family, friends and social workers. Thus, we were able to provide an interactive content service between users and caregivers.