• 말소리와 음성과학
• /
• 제8권3호
• /
• pp.31-38
• /
• 2016

Speech inversion (acoustic-to-articulatory mapping) is not a trivial problem, despite the importance, due to the highly non-linear and non-unique nature. This study aimed to investigate the performance of Deep Neural Network (DNN) compared to that of traditional Artificial Neural Network (ANN) to address the problem. The Wisconsin X-ray Microbeam Database was employed and the acoustic signal and articulatory pellet information were the input and output in the models. Results showed that the performance of ANN deteriorated as the number of hidden layers increased. In contrast, DNN showed lower and more stable RMS even up to 10 deep hidden layers, suggesting that DNN is capable of learning acoustic-articulatory inversion mapping more efficiently than ANN.

• 한국멀티미디어학회논문지
• /
• 제21권3호
• /
• pp.391-399
• /
• 2018

In this paper, we construct and compare various guitar chord classification systems using perceptron neural network and convolutional neural network without pre-processing other than Fourier transform to identify the optimal chord classification system. Conventional guitar chord classification schemes use, for better feature extraction, computationally demanding pre-processing techniques such as stochastic analysis employing a hidden markov model or an acoustic data filtering and hence are burdensome for real-time chord classifications. For this reason, we construct various perceptron neural networks and convolutional neural networks that use only Fourier tranform for data pre-processing and compare them with dataset obtained by playing an electric guitar. According to our comparison, convolutional neural networks provide optimal performance considering both chord classification acurracy and fast processing time. In particular, convolutional neural networks exhibit robust performance even when only small fraction of low frequency components of the data are used.

• Communications for Statistical Applications and Methods
• /
• 제18권6호
• /
• pp.837-849
• /
• 2011

본 연구에서는 자기조직화 신경망이 필요한 노드만을 가지고 최적화하여 정규혼합분포를 추정하는 모형을 제안한다. 제안한 모형은 SOMN모형과 벌점가능도를 사용한 모형을 결합한 것이다. SOMN의 장점은 수렴속도가 빠르고 표본의 크기가 작아도 발산하는 가능성이 낮다는 것이며, 벌점가능도를 사용한 모형은 필요없는 성분의 수를 줄일 수 있다는 것이다. 모의실험을 통하여 제안한 모형이 기대한 결과를 얻음을 확인하였다.

• 한국정밀공학회지
• /
• 제16권6호
• /
• pp.133-140
• /
• 1999

In this study, a monitoring method to detect chip disposal state in drilling system based on neural network was proposed and its performance was evaluated. If chip flow is bad during drilling, not only the static component but also the fluctuation of dynamic component of drilling. Drilling torque is indirectly measured by sensing spindle motor power through a AC spindle motor drive system. Spindle motor power being measured drilling, four quantities such as variance/mean, mean absolute deviation, gradient, event count were calculated as feature vectors and then presented to the neural network to make a decision on chip disposal state. The selected features are sensitive to the change of chip disposal state but comparatively insensitive to the change of drilling condition. The 3 layerd neural network with error back propagation algorithm has been used. Experimental results show that the proposed monitoring system can successfully recognize the chip disposal state over a wide range of drilling condition even though it is trained under a certain drilling condition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1209-1221
• /
• 2010

Three dimensional (3D) video is expected to be an important application for broadcast and IP streaming services. One of the main limitations for the transmission of 3D video over IP networks is network bandwidth mismatch due to the large size of 3D data, which causes fatal decoding errors and mosaic-like damage. This paper presents a novel selective frame discard method to address the problem. The main idea of the proposed method is the symmetrical discard of the two dimensional (2D) video frame and the depth map frame. Also, the frames to be discarded are selected after additional consideration of the playback deadline, the network bandwidth, and the inter-frame dependency relationship within a group of pictures (GOP). It enables the efficient utilization of the network bandwidth and high quality 3D IPTV service. The simulation results demonstrate that the proposed method enhances the media quality of 3D video streaming even in the case of bad network conditions.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2009년도 춘계학술발표논문집
• /
• pp.696-699
• /
• 2009

A VPN is a private network that uses a public network to connect remote sites or users together. As its popularity grows, companies, organization and even the government turned to it as a means of extending their own networks. To setup a Virtual Private a proper IP VPN Architecture must first be selected. In this paper, the types of IP Virtual Private Network Architecture like the MPLS-Based, IPSec-Based and the SSL/TLS-Based are discussed and compared. The comparison may serve as a guide for selecting the proper IP Virtual Private Network Architecture that is suitable for the company's needs.

• 전자공학회논문지B
• /
• 제33B권9호
• /
• pp.135-143
• /
• 1996

In this paper, we popose a neural network that detects edges of moving objects in an image using a neural network of hierarchical spatial filter with orientation selectivity. We modify the temporal difference network by adding a self loop to each neuraon cell to reduce the problems of phantom edge detected by the neural network proposed by kwon yool et al.. The modified neural network alleviates the phantom edges of moving objects, and also can detect edges of miving objects even for the noisy input. By computer simulation with real images, the proposed neural netowrk can extract edges of different orientation efficiently and also can reduce the phantom edges of moving objects.

• International Journal of Knowledge Content Development & Technology
• /
• 제8권2호
• /
• pp.23-36
• /
• 2018

Institutional repositories (IR) are promising to be extremely advantageous to scholars especially in developing countries. IR initiatives started in India during the late nineties and the popularity of this concept is growing rapidly in the higher educational and research institutions to disseminate newly emerging knowledge and expertise. The purpose of this paper is to critically analyze the network links of IR websites among four IITs that are registered in open DOAR (Directory of Open Access Repositories) web portal. The Institutional Repositories chosen for the study are IIT Delhi, IIT Hyderabad, IIT Bombay, and IIT Kanpur. The analysis of the study focused on standard graph and network cohesion metrics, such as density, diameter, eccentricity and distances, and clustering coefficient; for an even more detailed analysis advanced centrality measures and fast algorithms such as clique census are used.

• 한국IT서비스학회지
• /
• 제9권3호
• /
• pp.83-93
• /
• 2010

P2P streaming technology has advantages of scalability and availability comparing to the popular IP multicast. This paper proposes an approach to apply the P2P streaming technology to the delay-sensitive multimedia multicast applications. In order for the P2P streaming to be applied to the delay-sensitive applications, prior construction of delay-guaranteed overlay network is necessarily required. Moreover, the delay-guaranteed overlay network should be able to be kept even when the hand-overs occur owing to the departures of the intermediate P2P peers. This paper proposes a delay-guaranteed overlay network construction method by using the bandwidth and end-to-end delay based admission control and the backup peer based hand-over control mechanism.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1486-1501
• /
• 2021

The removal of accessories from the face is one of the essential pre-processing stages in the field of face recognition. However, despite its importance, a robust solution has not yet been provided. This paper proposes a network and dataset construction methodology to remove only the glasses from facial images effectively. To obtain an image with the glasses removed from an image with glasses by the supervised learning method, a network that converts them and a set of paired data for training is required. To this end, we created a large number of synthetic images of glasses being worn using facial attribute transformation networks. We adopted the conditional GAN (cGAN) frameworks for training. The trained network converts the in-the-wild face image with glasses into an image without glasses and operates stably even in situations wherein the faces are of diverse races and ages and having different styles of glasses.