• 한국음향학회지
• /
• 제41권3호
• /
• pp.342-350
• /
• 2022

본 논문에서는 재난 환경과 같은 환경에서의 음성 처리를 위해 실제 드론 소음 데이터를 수집하여 오염 음성 데이터베이스를 구축하고 음성 향상 기법인 스펙트럼 차감법과 심층 신경망을 이용한 마스크 기반 음성 향상 기법을 적용하여 성능을 평가한다. 기존의 심층 신경망 기반의 음성 향상 모델인 VoiceFilter(VF)의 성능 향상을 위해 Self-Attention 연산을 적용하고 추정한 잡음 정보를 Attention 모델의 입력으로 이용한다. 기존 VF 모델 기법과 비교하여 Source to Distortion Ratio(SDR), Perceptual Evaluation of Speech Quality(PESQ), Short-Time Objective Intelligibility(STOI)에 대해 각각 3.77 %, 1.66 %, 0.32 % 향상된 결과를 나타낸다. 인터넷에서 수집한 오염 음성 데이터를 75 % 혼합하여 훈련한 경우, 실제 드론 소음만을 사용한 경우에 비해 상대적인 성능 하락률 평균이 SDR, PESQ, STOI에 대해 각각 3.18 %, 2.79 %, 0.96 %를 나타낸다. 이는 실제 데이터를 취득하기 어려운 환경에서 실제 데이터와 유사한 데이터를 수집하여 음성 향상을 위한 모델 훈련에 효과적으로 활용할 수 있음을 확인해준다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2004년도 봄 학술발표논문집 Vol.31 No.1 (A)
• /
• 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.

• 한국통신학회논문지
• /
• 제33권11A호
• /
• pp.1021-1033
• /
• 2008

최근 무선 센서 네트워크를 통해 멀티미디어 데이터를 전송하고자 하는 노력이 늘고 있다. 무선 센서 네트워크는 저 전력 소형 노드를 이용하며, 낮은 전송 속도를 갖는 네트워크이다. 하지만 멀티미디어 데이터는 비교적 큰 용량을 가지며, 전송 시 지연에 민감한 특성을 갖는다. 그러므로 무선 센서 네트워크를 이용하여 멀티미디어 데이터를 전송하는 것은 어려운 일이 아닐 수 없다. 따라서 본 논문에서는 무선 센서 네트워크 환경에서 멀티미디어 데이터 전송을 위해 경로의 겹침이 없는 노드 독립적인 (Node-Disjoint) Multi-path Routing방법을 제안한다. 대용량의 데이터 전송 시 기존의 Single-path Routing 방법은 하나의 경로만을 사용하기 때문에 특정 노드에 부하를 가중시켜 데이터 손실이나 지연을 야기 시킬 수 있지만, 본 논문에서 제안하는 TinyONDMR(Tiny Optimized Node-Disjoint Multi-path Routing)방법은 서로 분리된 다른 경로에 데이터를 분산시켜 전송함으로써, 네트워크의 성능을 향상시킨다. 또한 Multi-path를 찾기 위한 라우팅 과정에서 발생하는 라우팅 오버헤드를 줄여 네트워크 부하를 감소시킨다.

• 대한전자공학회논문지TC
• /
• 제46권2호
• /
• pp.141-146
• /
• 2009

본 논문에서는 새로운 고조파 조절 회로를 이용한 Si LDMOSFET 고효율 전력증폭기를 구현하였다. 본 고조파 조절 회로는 2차, 3차 고조파 성분에 대하여 단락 임피던스를 갖으며, 입출력 정합 회로를 설계하기 위하여 사용된다. 제안된 고조파 조절 회로의 효율 개선 효과가 class-F 혹은 inverse class-F 고조파 조절 회로 보다 우수하다는 것을 증명하였다. 또한, 고조파 조절 회로가 출력 정합 회로뿐만 아니라, 입력 정합 회로에도 사용될 경우, 제안된 전력증폭기의 효율은 더욱 더 개선된다. 제안된 전력증폭기의 최대 전력 효율 (PAE)의 측정값은 1.71 GHz의 주파수 대역에서 82.68%이다. Class-F와 inverse class-F 전력증폭기와 비교할 때, 제안된 전력증폭기의 최대 PAE 측정값은 $5.08\;{\sim}\;9.91\;%$ 향상된다.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• 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%.

• 치과방사선
• /
• 제29권1호
• /
• 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
• /
• 제8권2호
• /
• 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
• /
• 제7권4호
• /
• 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.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• 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
• /
• 제18권5호
• /
• 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.