• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1249-1256
• /
• 2019

In this paper, we propose a new algorithm to remove acoustic feedback and noise in hearing aids. Instead of using the conventional FIR structure, this algorithm is a deep learning algorithm using neural network adaptive prediction filter to improve the feedback and noise reduction performance. The feedback canceller first removes the feedback signal from the microphone signal and then removes the noise using the Wiener filter technique. Noise elimination is to estimate the speech from the speech signal containing noise using the linear prediction model according to the periodicity of the speech signal. In order to ensure stable convergence of two adaptive systems in a loop, coefficient updates of the feedback canceller and noise canceller are separated and converged using the residual error signal generated after the cancellation. In order to verify the performance of the feedback and noise canceller proposed in this study, a simulation program was written and simulated. Experimental results show that the proposed deep learning algorithm improves the signal to feedback ratio(: SFR) of about 10 dB in the feedback canceller and the signal to noise ratio enhancement(: SNRE) of about 3 dB in the noise canceller than the conventional FIR structure.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.2
• /
• pp.201-208
• /
• 2011

With the increase in the number of smartphone users, precise 3D positional information is required by various applications. The positioning accuracy using civilian single-frequency pseudoranges is at the level of 10 m or so, but most applications these days are asking for a sub-meter level Therefore, instead of an absolute positioning technique, the VRS-based differential approach is applied along with the correction of the double-differenced (DD) residual errors using FKP (Flachen-Korrektur-Parameter). The VRS (Virual Reference Station) is located close to the rover, and the measurements are generated by correcting the geometrical distance to those of the master reference station. Since the unmodeled errors are generally proportional to the length of the baselines, the correction parameters are estimated by fitting a plane to the DD pseudorange errors of the CORS network. The DD positioning accuracy using 24 hours of C/A code measurements provides the RMS errors of 37 cm, 28 cm for latitudinal and longitudinal direction, respectively, and 76 cm for height. The accuracy of the horizontal components is within ${\pm}0.5m$ for about 90% of total epochs, and in particular the biases are significantly decreased to the level of 2-3 cm due to the network-based error modeling. Consequently, it is possible to consistently achieve a sub-meter level accuracy from the single-frequency pseudoranges using the VRS and double-differenced error modeling.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.37 no.1
• /
• pp.12-22
• /
• 2000

This paper presents the window-based permit distribution scheme for efficient medium access control to support multiclass traffic in APON(ATM over passive optical network). The proposed MAC protocol considers the characteristics of QoS(Quality of Service) for various traffic classes. A periodic RAU(request access unit) in upstream direction, includes dedicative request fields for each traffic category within the request slot. The transmission of upstream cell is permitted by the proposed window-based spacing scheme which distributes the requested traffic into several segments in the unit of one spacing window. The delay sensitive traffic source such as CBR or VBR with the stringent requirements on CDV and delay, is allocated prior to any other class. In order to reduce the CDV, so that the permit arrival rate close to the cell arrival rate, Running-Window algorithm is applied to permit distribution processing for these classes. The ABR traffic, which has not-strict CDV or delay criteria, is allocated flexibly to the residual bandwidth in FIFO manner. UBR traffic is allocated with the lowest priority for the remaining capacity. The performance of proposed protocol is evaluated in terms of transfer delay and 1-point CDV according to various offered load. The simulation results show that our protocol has the prominent improvement on CDV and delay performance with compared to the previous protocol.

• Korean Journal of Ecology and Environment
• /
• v.49 no.3
• /
• pp.208-214
• /
• 2016

We analyzed research trend and public perception related with tap water to identify major factors affecting low consumption of tap water. 805 research articles were collected for text mining analysis and 1,000 on-line questionnaires were surveyed to find social variables influencing tap water intake. Based on the word network analysis, research topics were divided into 4 major categories, 1) drinking water quality, 2) water fluoridation, 3) residual chlorine, and 4) micro-organism management. Compared with these major research topics, scientific studies of drinking behavior, or social perception were rather limited. 22.4% of total respondents used tap water as drinking water source, and only 1% drank tap water without further treatments (i.e. boiling, filtering). Experience of quality control report (B=0.392, p=0.046) and level of policy trust (B=1.002, p<0.0001) were influential factors on tap water drinking behavior. Age (B=0.020, p=0.002) and gender (B= - 1.843, p<0.0001) also showed significant difference. To increase the frequency of drinking the tap water by social members, the more scientific information of tap water quality and the water policy management should be clearly shared with social members.

• Tunnel and Underground Space
• /
• v.30 no.5
• /
• pp.462-472
• /
• 2020

Rock classification is fundamental discipline of exploring geological and geotechnical features in a site, which, however, may not be easy works because of high diversity of rock shape and color according to its origin, geological history and so on. With the great success of convolutional neural networks (CNN) in many different image-based classification tasks, there has been increasing interest in taking advantage of CNN to classify geological material. In this study, a feasibility of the deep CNN is investigated for automatically and accurately identifying rock types, focusing on the condition of various shapes and colors even in the same rock type. It can be further developed to a mobile application for assisting geologist in classifying rocks in fieldwork. The structure of CNN model used in this study is based on a deep residual neural network (ResNet), which is an ultra-deep CNN using in object detection and classification. The proposed CNN was trained on 10 typical rock types with an overall accuracy of 84% on the test set. The result demonstrates that the proposed approach is not only able to classify rock type using images, but also represents an improvement as taking highly diverse rock image dataset as input.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.441-446
• /
• 2020

In this paper, we propose the α-Feature Map Scaling (α-FMS) method which extends the FMS method that was designed to enhance the discriminative power of feature maps of deep neural networks in Speaker Verification (SV) systems. The FMS derives a scale vector from a feature map and then adds or multiplies them to the features, or sequentially apply both operations. However, the FMS method not only uses an identical scale vector for both addition and multiplication, but also has a limitation that it can only add a value between zero and one in case of addition. In this study, to overcome these limitations, we propose α-FMS to add a trainable parameter α to the feature map element-wise, and then multiply a scale vector. We compare the performance of the two methods: the one where α is a scalar, and the other where it is a vector. Both α-FMS methods are applied after each residual block of the deep neural network. The proposed system using the α-FMS methods are trained using the RawNet2 and tested using the VoxCeleb1 evaluation set. The result demonstrates an equal error rate of 2.47 % and 2.31 % for the two α-FMS methods respectively.

• The KIPS Transactions:PartC
• /
• v.16C no.2
• /
• pp.151-164
• /
• 2009

The importance of sensor networks as a base of ubiquitous computing realization is being highlighted, and espicially the security is recognized as an important research isuue, because of their characteristics.Several efforts are underway to provide security services in sensor networks, but most of them are preventive approaches based on cryptography. However, sensor nodes are extremely vulnerable to capture or key compromise. To ensure the security of the network, it is critical to develop security Intrusion Detection System (IDS) that can survive malicious attacks from "insiders" who have access to keying materials or the full control of some nodes, taking their charateristics into consideration. In this perper, we design a distributed and adaptive IDS architecture on sensor networks, respecting both of energy efficiency and IDS efficiency. Utilizing a modified HEED algorithm, a clustering algorithm, distributed IDS nodes (dIDS) are selected according to node's residual energy and degree. Then the monitoring results of dIDSswith detection codes are transferred to dIDSs in next round, in order to perform consecutive and integrated IDS process and urgent report are sent through high priority messages. With the simulation we show that the superiorities of our architecture in the the efficiency, overhead, and detection capability view, in comparison with a recent existent research, adaptive IDS.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.185-191
• /
• 2022

In this study, we propose a novel super-resolution neural network based on U-Net, residual neural network, and sub-pixel convolution. To prevent the loss of detailed information due to the max pooling of U-Net, we propose down-sampling and connection using sub-pixel convolution. This uses all pixels in the filter, unlike the max pooling that creates a new feature map with only the max value in the filter. As a 2×2 size filter passes, it creates a feature map consisting only of pixels in the upper left, upper right, lower left, and lower right. This makes it half the size and quadruple the number of feature maps. And we propose two methods to reduce the computation. The first uses sub-pixel convolution, which has no computation, and has better performance, instead of up-convolution. The second uses a layer that adds two feature maps instead of the connection layer of the U-Net. Experiments with a banchmark dataset show better PSNR values on all scale and benchmark datasets except for set5 data on scale 2, and well represent local area patterns.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.48-55
• /
• 2010

It has a falling off in speech quality, especially when consecutive packet loss occurs, even if a vocoder implemented in the packet network has its own packet loss concealment (PLC) algorithm. PLC algorithm is divided into transmitter and receiver algorithm. Algorithm in the transmitter gives superior quality by additional information. however it is impossible to provide mutual compatibility and it occurs extra delay and transmission rate. The method applied in the receiver does not require additional delay. However, it sets limits to improve the speech quality. In this paper, we propose a new method that puts extra information for PLC in a part of Extension Header Data which is not used in RTP Header. It can solve the problem and obtain enhanced speech quality. There is no extra delay occurred by the proposed algorithm because there is a jitter buffer to adjust network delay in a receiver. Extra information, 16 bits each frame for G.729 PLC, is allocated for MA filter index in LP synthesis, excitation signal, excitation signal gain and residual gain reconstruction. It is because a transmitter sends speech data each 20 ms when it transfers RTP payload. As a result, the proposed method shows superior performance about 13.5%.

• Journal of the Korea Concrete Institute
• /
• v.20 no.1
• /
• pp.13-22
• /
• 2008

The initiation and growth processes of cyclic ice body in porous systems are affected by the thermo-physical and mass transport properties, as well as gradients of temperature and chemical potentials. Furthermore, the diffusivity of deicing chemicals shows significantly higher value under cyclic freeze-thaw conditions. Consequently, the disintegration of concrete structures is aggravated at marine environments, higher altitudes, and northern areas. However, the properties of cyclic freeze-thaw with crack growth and the deterioration by the accumulated damages are hard to identify in tests. In order to predict the accumulated damages by cyclic freeze-thaw, a regression analysis by the response surface method (RSM) is used. The important parameters for cyclic freeze-thawdeterioration of concrete structures, such as water to cement ratio, entrained air pores, and the number of cycles of freezing and thawing, are used to compose the limit state function. The regression equation fitted to the important deterioration criteria, such as accumulated plastic deformation, relative dynamic modulus, or equivalent plastic deformations, were used as the probabilistic evaluations of performance for the degraded structural resistance. The predicted results of relative dynamic modulus and residual strains after 300 cycles of freeze-thaw show very good agreements with the experimental results. The RSM result can be used to predict the probability of occurrence for designer specified critical values. Therefore, it is possible to evaluate the life cycle management of concrete structures considering the accumulated damages due to the cyclic freeze-thaw using the proposed prediction method.