• Title/Summary/Keyword: Loss Estimation

Search Result 1,095, Processing Time 0.027 seconds

Multiple Inputs Deep Neural Networks for Bone Age Estimation Using Whole-Body Bone Scintigraphy

  • Nguyen, Phap Do Cong;Baek, Eu-Tteum;Yang, Hyung-Jeong;Kim, Soo-Hyung;Kang, Sae-Ryung;Min, Jung-Joon
    • Journal of Korea Multimedia Society
    • /
    • v.22 no.12
    • /
    • pp.1376-1384
    • /
    • 2019
  • The cosmetic and behavioral aspects of aging have become increasingly evident over the years. Physical aging in people can easily be observed on their face, posture, voice, and gait. In contrast, bone aging only becomes apparent once significant bone degeneration manifests through degenerative bone diseases. Therefore, a more accurate and timely assessment of bone aging is needed so that the determinants and its mechanisms can be more effectively identified and ultimately optimized. This study proposed a deep learning approach to assess the bone age of an adult using whole-body bone scintigraphy. The proposed approach uses multiple inputs deep neural network architectures using a loss function, called mean-variance loss. The data set was collected from Chonnam National University Hwasun Hospital. The experiment results show the effectiveness of the proposed method with a mean absolute error of 3.40 years.

A Study on Insertion Loss Estimation Formulas of Rectangular Silencers for Ships (선박용 사각 소음기의 삽입손실 추정식 연구)

  • Kim, Tae-Gyoung;Hong, Suk-Yoon;Song, Jee-Hun;Kwon, Hyun-Wung;Kong, Young-Mo
    • Transactions of the Korean Society for Noise and Vibration Engineering
    • /
    • v.26 no.7
    • /
    • pp.820-826
    • /
    • 2016
  • The acoustic performance estimation formulas for silencers are developed mainly by theoretical or empirical methods. However, the existing formulas are available only for a limited range of silencers. In this paper, the procedures for noise analysis of the silencers are established by comparing analytic results to experimental results. With the proven analysis procedures, impedances of the rectangular silencers for ships are adversely predicted from National Environmental Balancing Bureau (NEBB) data, and with the estimated impedances, insertion loss formulas for large silencers are developed using boundary element method (BEM). The developed formulas can be efficiently used for predicting acoustic performance of the silencers for ships.

Image Interpolation Using Iterative Error Elimination (반복적 오차 제거를 이용한 영상 보간법)

  • Kim, Won-Hee;Piao, Fengji;Kim, Jong-Nam;Moon, Kwang-Seok
    • Journal of Korea Multimedia Society
    • /
    • v.14 no.8
    • /
    • pp.1000-1009
    • /
    • 2011
  • Image interpolation is a technique which estimates the non-allocated pixel values on image scale-transform. It requires minimum computational complexity and minimum image quality degradation on the interpolated resultant images. In this paper we propose an image interpolation method using iterative error estimation. The proposed method consists of the following five steps: loss-information computational step, loss-information estimation step, loss-information application step, error computation step, and error application step. The experimental results obtained show that the average PSNR is increased by 3.3dB, subjective image quality is enhanced and the minimum computation complexity is decreased by 83%. The proposed image interpolation algorithm may be helpful in various applications such as image reconstruction and enlargement.

Development of a Formula for Acoustic Transmission Loss According to Partition Positions in a Simple Expansion Chamber (단순확장관 내부 파티션 위치에 따른 음향투과손실 계산식의 개발)

  • Park, Jeong-Pil;Bae, Kyeong-Won;Jeong, Weui-Bong;Ahn, Se-Jin
    • Transactions of the Korean Society for Noise and Vibration Engineering
    • /
    • v.25 no.2
    • /
    • pp.116-123
    • /
    • 2015
  • This paper proposed a new formula for predicting acoustic power transmission loss of simple expansion chamber with two internal partitions. Seventeen cases of computational results were performed and the database was constructed for the TL according to the various positions of internal partitions. Using this database, firstly, the formula for the peak values of TL at certain frequencies was developed using the least square estimation. Secondly, the formula for the TL curve could be obtained automatically with the input data of the positions of two internal partitions. The formula of TL developed in this paper showed good agreement with computational results. This formula will be helpful for the positioning of internal partitions to improve TL at target frequencies.

A Study on the Estimation of Prestress Losses in Prestressed Concrete Box Girder Bridges (프리스트레스트 콘크리트 박스 거더 교량의 프리스트레스 손실 추정에 관한 연구)

  • Oh, Byung-Hwan;Yang, In-Hwan;Kim, Ji-Sang
    • Journal of the Korea institute for structural maintenance and inspection
    • /
    • v.5 no.2
    • /
    • pp.111-120
    • /
    • 2001
  • This paper aims at estimating instantaneous prestress losses by measuring the actual prestress forces in prestressed concrete (PSC) box girder bridges. Measurement were taken to study initial prestress losses such as friction losses and slip losses. A new strain gauge system was developed to measure strains in internal tendons. The system was installed on a total of 20 tendons in a PSC box girder bridges. The variation of prestress forces were monitored during prestressing tendon and after prestress transfer. The prestress losses are also calculated including friction losses and slip losses. The measured data were compared with the theoretical values. The result shows that the measured prestress forces agree well with the theoretical values. It is shown that prestress force of each strand in the same tendon is a bit different. This study also shows that prestress losses of continuity tendons during prestress transfer are significantly different each other, which results from the variety of buttress location and tendon profile. The present study provides realistic information on the estimation of actual prestress forces and losses in PSC box girder bridges.

  • PDF

Robust speech quality enhancement method against background noise and packet loss at voice-over-IP receiver (배경잡음 및 패킷손실에 강인한 voice-over-IP 수신단 기반 음질향상 기법)

  • Kim, Gee Yeun;Kim, Hyoung-Gook
    • The Journal of the Acoustical Society of Korea
    • /
    • v.37 no.6
    • /
    • pp.512-517
    • /
    • 2018
  • Improving voice quality is a major concern in telecommunications. In this paper, we propose a robust speech quality enhancement against background noise and packet loss at VoIP (Voice-over-IP) receiver. The proposed method combines network jitter estimation based on hybrid Markov chain, adaptive playout scheduling using the estimated jitter, and speech enhancement based on restoration of amplitude and phase to enhance the quality of the speech signal arriving at the VoIP receiver over IP network. The experimental results show that the proposed method removes the background noise added to the speech signal before encoding at the sender side and provides the enhanced speech quality in an unstable network environment.

Compressed Sensing Techniques for Millimeter Wave Channel Estimation (밀리미터파 채널 추정을 위한 압축 센싱 기법)

  • Han, Yonghee;Lee, Jungwoo
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.42 no.1
    • /
    • pp.25-30
    • /
    • 2017
  • Millimeter wave (mmWave) bands are expected to improve date rate of 5G systems due to the wide available bandwidth. While severe path loss in those bands has impeded the utilization, short wavelength enables a large number of antennas packed in a compact form, which can mitigate the path loss. However, estimating the channel with a conventional scheme requires a huge training overhead, hence an efficient estimation scheme operating with a small overhead needs to be developed. The sparsity of mmWave channels caused by the limited scatterers can be exploited to reduce the overhead by utilizing compressed sensing. In this paper, we introduce compressed sensing techniques for mmWave channel estimation. First, we formulate wideband channel estimation into a sparse recovery problem. We also analyze the characteristics of random measurement matrix constructed using quantized phase shifters in terms of mutual incoherence.

A Study on Mid-amble based V2X Channel Estimation Techniques Using Bidirectional Averaging (양방향 평균화를 이용한 새로운 Mid-amble 기반 V2X 채널추정 기법에 관한 연구)

  • Kim, Ju-Hyeok;Song, Changick
    • Journal of IKEEE
    • /
    • v.26 no.2
    • /
    • pp.287-291
    • /
    • 2022
  • In general, as the amplitude and phase information of the physical layer channel impulse response change rapidly in time and frequency according to the high-speed movement of the vehicles in V2X communication systems, it is difficult to accurately estimate these channels at the receiving end. In order to effectively overcome this problem, midamble-based channel estimation methods in which mid-ambles are periodically inserted into a packet have been recently considered. However, as the number of midambles increases, we suffer from the spectral efficiency loss. To relieve such a loss, in this paper, we propose a new bidirectional averaging channel estimation method that combines the existing data pilot-based channel estimation methods and the mid-ambles. Finally, through the simulation results, we demonstrate that the proposed method outperforms the existing mid-amble method in terms of packet error rate with fewer number of mid-ambles.