• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.342-350
• /
• 2022

In this paper, actual drone noise samples are collected for speech processing in disaster environments to build noise-corrupted speech database, and speech enhancement performance is evaluated by applying spectrum subtraction and mask-based speech enhancement techniques. To improve the performance of VoiceFilter (VF), an existing deep neural network-based speech enhancement model, we apply the Self-Attention operation and use the estimated noise information as input to the Attention model. Compared to existing VF model techniques, the experimental results show 3.77%, 1.66% and 0.32% improvements for Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligence (STOI), respectively. When trained with a 75% mix of speech data with drone sounds collected from the Internet, the relative performance drop rates for SDR, PESQ, and STOI are 3.18%, 2.79% and 0.96%, respectively, compared to using only actual drone noise. This confirms that data similar to real data can be collected and effectively used for model training for speech enhancement in environments where real data is difficult to obtain.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.529-531
• /
• 2004

HLR 시스템은 mobile network에서 지속적으로 변하는 가입자의 위치 정보를 관리하는 통신 장비용 실시간 embedded system이다. 본 논문에서는 HLR 시스템 s/w 구조의 문제점을 제시하였다. 또한 HLR 시스템의 특성을 고려한 효율적인 s/w 구조를 제안하였다. 아울러 embedded system인 HLR 데이터베이스 시스템의 특성을 고려한 새로운 구조를 제안하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.11A
• /
• pp.1021-1033
• /
• 2008

In recent years, the growing interest in wireless sensor network has resulted in thousands of publications. Most of this research is concerned with delivering raw data such as temperature, pressure, or humidity. Recently, the focus of sensor network paradigm is changing for delivering multimedia contents. However, most existing routing protocols are not very practical for transmitting multimedia contents in resource constrained sensor networks. In this paper, we propose an optimized node-disjoint multi-path routing protocol for throughput enhancement and load balancing. We focused on how to allocate traffic to independent multiple end-to-end routes. Decentralized transmission using our node-disjoint multi-path routing scheme results in bandwidth aggregation and throughput enhancement. In addition, our scheme provides ways to remove link-joint routes for decreasing routing overhead.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.2
• /
• pp.141-146
• /
• 2009

In this paper, a novel harmonic control circuit has been proposed for the design of high-efficiency power amplifier with Si LDMOSFET. The proposed harmonic control circuit haying the short impedances for the second- and third-harmonic components has been used to design the in/output matching network. The efficiency enhancement effect of the proposed harmonic control circuit is superior to the class-F or inverse class-F harmonic control circuit. Also, when the proposed harmonic control circuit has been adapted to the input matching network as well as the output matching network, the of ficiency enhancement effect of the proposed power amplifier has increased all the more. The measured maximum power added efficiency (PAE) of the proposed power amplifier is 82.68% at 1.71GHz band. Compared with class-F and inverse class-F amplifiers, the measured maximum PAE of the proposed power amplifier has increased in $5.08{\sim}9.91%$.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.158-168
• /
• 2024

There is hardly any person in modern times who has not taken soft drinks instead of drinking water. The rate of people taking soft drinks being surprisingly high, researchers around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases and so on. Therefore, in this work an image-based tool is developed to monitor the nutritional information of soft drinks by using deep convolutional neural network with transfer learning. At first, visual saliency, mean shift segmentation, thresholding and noise reduction technique, collectively known as 'pre-processing' are adopted to extract the location of drinks region. After removing backgrounds and segment out only the desired area from image, we impose Discrete Wavelength Transform (DWT) based resolution enhancement technique is applied to improve the quality of image. After that, transfer learning model is employed for the classification of drinks. Finally, nutrition value of each drink is estimated using Bag-of-Feature (BoF) based classification and Euclidean distance-based ratio calculation technique. To achieve this, a dataset is built with ten most consumed soft drinks in Bangladesh. These images were collected from imageNet dataset as well as internet and proposed method confirms that it has the ability to detect and recognize different types of drinks with an accuracy of 98.51%.

• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.29 no.1
• /
• pp.149-159
• /
• 1999

Purpose: The purpose of this study was to evaluate cervical lymph node metastasis of oral squamous cell carcinoma patients by MRI film and neural network system. Materials and Methods: The oral squamous cell carcinoma patients(21 patients. 59 lymph nodes) who have visited SNU hospital and been taken by MRI. were included in this study. Neck dissection operations were done and all of the cervical lymph nodes were confirmed with biopsy. In MR images. each lymph node were evaluated by using 6 MR imaging criteria(size. roundness. heterogeneity. rim enhancement. central necrosis, grouping) respectively. Positive predictive value. negative predictive value. and accuracy of each MR imaging criteria were calculated. At neural network system. the layers of neural network system consisted of 10 input layer units. 10 hidden layer units and 1 output layer unit. 6 MR imaging criteria previously described and 4 MR imaging criteria (site I-node level II and submandibular area. site II-other node level. shape I-oval. shape II-bean) were included for input layer units. The training files were made of 39 lymph nodes(24 metastatic lymph nodes. 10 non-metastatic lymph nodes) and the testing files were made of other 20 lymph nodes(10 metastatic lymph nodes. 10 non-metastatic lymph nodes). The neural network system was trained with training files and the output level (metastatic index) of testing files were acquired. Diagnosis was decided according to 4 different standard metastatic index-68. 78. 88. 98 respectively and positive predictive values. negative predictive values and accuracy of each standard metastatic index were calculated. Results: In the diagnosis of using single MR imaging criteria. the rim enhancement criteria had highest positive predictive value (0.95) and the size criteria had highest negative predictive value (0.77). In the diagnosis of using single MR imaging criteria. the highest accurate criteria was heterogeneity (accuracy: 0.81) and the lowest one was central necrosis (accuracy: 0.59). In the diagnosis of using neural network systems. the highest accurate standard metastatic index was 78. and that time. the accuracy was 0.90. Neural network system was more accurate than any other single MR imaging criteria in evaluating cervical lymph node metastasis. Conclusion: Neural network system has been shown to be more useful than any other single MR imaging criteria. In future. Neural network system will be powerful aiding tool in evaluating cervical node metastasis.

• Journal of information and communication convergence engineering
• /
• v.8 no.2
• /
• pp.168-172
• /
• 2010

The Network-based handover still has problems such as the transmission delays and the packet losses in the case of macro mobility, though technological advances have been made in the wireless and mobile communication. For end-to-end handover, the link bandwidth has been reduced in the wireless network due to its burst errors and congestion control. To overcome such problems, we propose a new scheme of the macro handover according to the protocol layer. The proposed macro handover is implemented on the network layer to partially substitute wired signaling for wireless signaling, to flexibly employ buffers, and on the transport layer to postpone its retransmission time. We have performed extensive simulation using ns-2 and the result shows that our proposed scheme outperforms the other existing schemes in terms of transmission delay, packet loss, and data transfer rate during the handovers.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.4
• /
• pp.486-492
• /
• 2012

This paper presents a novel objective function for distribution system reconfiguration for reliability enhancement. When islanding operations of distributed generators is prohibited, faults in the feeder interrupt the operation of distributed generators. For this reason, we include the customer interruption cost as well as the distributed generator interruption cost in the objective function in the network reconfiguration algorithm. The network reconfiguration in which genetic algorithms are used is implemented by MATLAB. The effect of the proposed objective function in the network reconfiguration is analyzed and compared with existing objective functions through case studies. The network reconfiguration considering the proposed objective function is suitable for a distribution system that has a high penetration of distributed generators.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1898-1899
• /
• 2011

In this paper, we propose an obstacle avoidance algorithm for a network-based autonomous mobile robot. The obstacle avoidance algorithm is based on the VFH (Vector Field Histogram) algorithm and delay-compensative methods with the VFH algorithm are proposed for the network-based robot that is a unified system composed of distributed environmental sensors, mobile actuators, and the VFH controller. Firstly, the compensated readings of the sensors are used for building the polar histogram of the VFH algorithm. Secondly, a sensory fusion using the Kalman filter is proposed for the localization of the robot to compensate both the delay of the readings of an odometry sensor and the delay of the readings of the environmental sensors. The performance enhancements of the proposed obstacle avoidance algorithm from the viewpoint of efficient path generation and accurate goal positioning are also shown in this paper through some simulation experiments by the Marilou Robotics Studio Simulator.

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.773-783
• /
• 2016

Both coordinated multi-point transmission and frequency reuse are effective approaches to mitigate inter-cell interference and improve network coverage. The motivation of this work is to explore the manner to effectively utilize the spectrum resource by reasonably combining cooperation and frequency reuse. The $Mat{\acute{e}}rn$ cluster process, which is appropriate to model networks with hot spots, is used to model the spatial distribution of base stations. Two cooperative mechanisms, coherent and non-coherent joint transmission (JT), are analyzed and compared. We also evaluate the effect of multiple antennas and imperfect channel state information. The simulation reveals that the proposed approach to combine cooperation and frequency reuse is effective to improve the network coverage for users located at both the center and the boundary of the cooperative region.