• Title/Summary/Keyword: Efficient channel attention

Search Result 23, Processing Time 0.023 seconds

Turbulent-image Restoration Based on a Compound Multibranch Feature Fusion Network

  • Banglian Xu;Yao Fang;Leihong Zhang;Dawei Zhang;Lulu Zheng
    • Current Optics and Photonics
    • /
    • v.7 no.3
    • /
    • pp.237-247
    • /
    • 2023
  • In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

On the improved MIMO-OFDM system for the wireless environments (무선 환경에서 OFDM 성능향상을 위한 MIMO System)

  • 박창현;권혁일;양윤기
    • Proceedings of the IEEK Conference
    • /
    • 2003.07a
    • /
    • pp.481-484
    • /
    • 2003
  • OFDM(Orthogonall Frequency Division Multiplexing) is an efficient transmission techniques for the frequency selective fading wireless channel where conventional modulations suffer from severe performance degradation. Recently, more efficient techniques for the OFDM are paid much attention such as adaptive modulation for each subcarrier, since more bit rate has been required for the wireless data network [1-3]. The proposed system employs the adaptive modulation between transmitter and receiver in each subcarrier, where the bit and power is properly allocated. Also multiple antenna system called MIMO is considered, which result in robustness in channel delay, improved power efficiency and improved bit SNR for the given BER.

  • PDF

DIRECT NUMERICAL SIMULATION OF IMMISCIBLE GAS BUBBLE DISPLACEMENT IN 2D CHANNEL (2차원 관내 유동에서 불활성 기체 제거과정의 직접 수치 해석)

  • Shin, S.
    • Journal of computational fluids engineering
    • /
    • v.12 no.3
    • /
    • pp.41-46
    • /
    • 2007
  • Dynamic behavior of immiscible gas bubble attached to the wall in channel flow plays very important role in many engineering applications. Special attention has been paid to micro direct methanol fuel cell(${\mu}$DMFC) where surface tension becomes dominant factor with minor gravitational effect due to its reduced size. Therefore, displacement of $CO_2$ bubble generating on a cathode side in ${\mu}$DMFC can be very difficult and efficient removal of $CO_2$ bubbles will affect the overall machine performance considerably. We have focused our efforts on studying the dynamic behavior of immiscible bubble attached to the one side of the wall on 2D rectangular channel subject to external shear flow. We used Level Contour Reconstruction Method(LCRM) which is the simplified version of front tracking method to track the bubble interface motion. Effects of Reynolds number, Weber number, advancing/receding contact angle and property ratio on bubble detachment characteristic has been numerically identified.

Modeling and Characterization of Low Voltage Access Network for Narrowband Powerline Communications

  • Masood, Bilal;Haider, Arsalan;Baig, Sobia
    • Journal of Electrical Engineering and Technology
    • /
    • v.12 no.1
    • /
    • pp.443-450
    • /
    • 2017
  • Nowadays, Power Line Communication (PLC) is gaining high attention from industry and electric supply companies for the services like demand response, demand side management and Advanced Metering Infrastructure (AMI). The reliable services to consumers using PLC can be provided by utilizing an efficient PLC channel for which sophisticated channel modeling is very important. This paper presents characterization of a Low Voltage (LV) access network for Narrowband Power Line Communications (NB-PLC) using transmission line (TL) theory and a Simulink model. The TL theory analysis not only includes the constant parameters but frequency selectivity is also introduced in these parameters such as resistance, conductance and impedances. However, the proposed Simulink channel model offers an analysis and characterization of capacitive coupler, network impedance and channel transfer function for NB-PLC. Analysis of analytical and simulated results shows a close agreement of the channel transfer function. In the absence of a standardized NBPLC channel model, this research work can prove significant in improving the efficiency and accuracy of NB-PLC communication transceivers for Smart Grid communications.

The Implementation of MAP decoder for Turbo codes (터보 부호를 위한 MAP 복호기의 구현)

  • Lee, Jung-Won;Kim, Jong-Tae
    • Proceedings of the KIEE Conference
    • /
    • 2000.07d
    • /
    • pp.3148-3150
    • /
    • 2000
  • Turbo codes that have attracted a great attention in recent years are applied to wireless communication networks that require variable quality of service and transmit over unknown fading channel. A MAP decoder is the constituent of turbo decoder. In this paper, we propose a high speed architecture of MAP decoder and a new normalization technique, In conclusion, this paper presents the efficient implementation of serial block MAP decoder for turbo codes.

  • PDF

Multiple Differential Feedback Detection of M-ary DPSK Signal in Shadowed Rician Fading Channel (쉐도우 라이시안 페이딩 채널에서 M-ary DPSK 신호의 다중 차동 궤환 검파)

  • 박문수;김환용
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.7 no.1
    • /
    • pp.61-70
    • /
    • 1996
  • M-ary differential phase shift keying(DPSK)is a bandwidth efficient digital modulation technique and recently has attracted increased attention in mobile satellite communication application where the available radio bandwidth is limited. Coherent detection offers good BER performance in AWGN channel. However, it requires long acquisition times in fading environment. In this paper, we analyze the BER performance of M-ary DPSK signal using the Multiple Differ- ential Feedback Detection(MDFD) technique in Rician fading and shadowed Rician fading channel. MDFD is an efficient scheme to decrease the performance gap between differential and coherent reception by increasing the complexity of the conventional differential receiver to some extent. Compared to the multiple symbol maximum likelihood detection technique, the multiple differential feedback detection technique has a much simpler structure for hardware implementation. Espe- cially, this technique has application to land mobile satellite channel which can vary in time and space between AWGN and rapidly fading channel.

  • PDF

CAttNet: A Compound Attention Network for Depth Estimation of Light Field Images

  • Dingkang Hua;Qian Zhang;Wan Liao;Bin Wang;Tao Yan
    • Journal of Information Processing Systems
    • /
    • v.19 no.4
    • /
    • pp.483-497
    • /
    • 2023
  • Depth estimation is one of the most complicated and difficult problems to deal with in the light field. In this paper, a compound attention convolutional neural network (CAttNet) is proposed to extract depth maps from light field images. To make more effective use of the sub-aperture images (SAIs) of light field and reduce the redundancy in SAIs, we use a compound attention mechanism to weigh the channel and space of the feature map after extracting the primary features, so it can more efficiently select the required view and the important area within the view. We modified various layers of feature extraction to make it more efficient and useful to extract features without adding parameters. By exploring the characteristics of light field, we increased the network depth and optimized the network structure to reduce the adverse impact of this change. CAttNet can efficiently utilize different SAIs correlations and features to generate a high-quality light field depth map. The experimental results show that CAttNet has advantages in both accuracy and time.

Structural and Electrical Features of Solution-Processed Li-doped ZnO Thin Film Transistor Post-Treated by Ambient Conditions

  • Kang, Tae-Sung;Koo, Jay-Hyun;Kim, Tae-Yoon;Hong, Jin-Pyo
    • Proceedings of the Korean Vacuum Society Conference
    • /
    • 2012.08a
    • /
    • pp.242-242
    • /
    • 2012
  • Transparent oxide semiconductors are increasingly becoming one of good candidates for high efficient channel materials of thin film transistors (TFTs) in large-area display industries. Compare to the conventional hydrogenated amorphous silicon channel layers, solution processed ZnO-TFTs can be simply fabricated at low temperature by just using a spin coating method without vacuum deposition, thus providing low manufacturing cost. Furthermore, solution based oxide TFT exhibits excellent transparency and enables to apply flexible devices. For this reason, this process has been attracting much attention as one fabrication method for oxide channel layer in thin-film transistors (TFTs). But, poor electrical characteristic of these solution based oxide materials still remains one of issuable problems due to oxygen vacancy formed by breaking weak chemical bonds during fabrication. These electrical properties are expected due to the generation of a large number of conducting carriers, resulting in huge electron scattering effect. Therefore, we study a novel technique to effectively improve the electron mobility by applying environmental annealing treatments with various gases to the solution based Li-doped ZnO TFTs. This technique was systematically designed to vary a different lithium ratio in order to confirm the electrical tendency of Li-doped ZnO TFTs. The observations of Scanning Electron Microscopy, Atomic Force Microscopy, and X-ray Photoelectron Spectroscopy were performed to investigate structural properties and elemental composition of our samples. In addition, I-V characteristics were carried out by using Keithley 4,200-Semiconductor Characterization System (4,200-SCS) with 4-probe system.

  • PDF

Photoluminescence Characteristics of p-Phenylene Vinylene and Its Derivatives in Solution and in Nanoaggregates

  • Eom, Intae;Lim, Seon Jeong;Park, Soo Young;Joo, Taiha
    • Rapid Communication in Photoscience
    • /
    • v.4 no.3
    • /
    • pp.70-72
    • /
    • 2015
  • Oligomers of p-phenylene vinylene and its derivatives have drawn much attention due to their unusual emission characteristics of showing increased emission when they form into nanoparticles. We have investigated the optical properties of the oligo-(p-phenylene vinylene) and its cyano-substituted derivatives in solution and in nanoaggregate media by femtosecond and picosecond time resolved fluorescence as well as stationary spectroscopies. All the spectroscopic data are consistent with the conclusion that the cyano substitution on the ${\beta}$-position of oligo-(p-phenylene vinylene) leads to breakage of the otherwise planar structure of cyano-unsubstituted molecules, which opens up an extremely efficient, as fast as 100 fs, non-radiative relaxation channel of the excited state. Formation of the nanoaggregates reverts the effect to make the molecules planar and to block the non-radiative relaxation channel. Therefore, concerning the applications in organic electroluminescent devices and organic light emitting diodes, substitution by the cyano group is not advantageous, although such modification should be useful in respect of controlling fluorescence intensity in different media.

An Efficient Downlink MAC Protocol for Multi-User MIMO WLANs

  • Liu, Kui;Li, Changle;Guo, Chao;Chen, Rui
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.11 no.9
    • /
    • pp.4242-4263
    • /
    • 2017
  • Multi-User Multiple-Input Multiple-Output (MU-MIMO) technology has recently attracted significant attention from academia and industry because of it is increasingly important role in improving networks' capacity and data rate. Moreover, MU-MIMO systems for the Fifth Generation (5G) have already been researched. High Quality of Service (QoS) and efficient operations at the Medium Access Control (MAC) layer have become key requirements. In this paper, we propose a downlink MU-MIMO MAC protocol based on adaptive Channel State Information (CSI) feedback (called MMM-A) for Wireless Local Area Networks (WLANs). A modified CSMA/CA mechanism using new frame formats is adopted in the proposed protocol. Specifically, the CSI is exchanged between stations (STAs) in an adaptive way, and a packet selection strategy which can guarantee a fairer QoS for scenarios with differentiated traffic is also included in the MMM-A protocol. We then derive the expressions of the throughput and access delay, and analyze the performance of the protocol. It is easy to find that the MMM-A protocol outperforms the commonly used protocols in terms of the saturated throughput and access delay through simulation and analysis results.