Query:
学者姓名:沈英
Refining:
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract :
Polarization can improve the autonomous reconnaissance capability of unmanned aerial vehicle, but it is easily interfered by the variation of detection angle and target materials, which affects the robustness of polarization detection. In this paper, a real-time low-altitude camouflaged target detection algorithm of YOLO-Polarization based on polarized images is proposed. The coded image fused with multi-polarization direction information is used as input, the 3D convolution module is applied to extract the connection features from the different polarization direction images, and a feature enhancement module (FEM) is introduced to further enhance the multi-level features. In addition, the cross-level feature aggregation network is adopted to make full use of the feature information of different scales to complete the effective aggregation of features, and finally combined with multi-channel feature information output detection results. A dataset consisting of polarized images of low-altitude camouflaged targets (PICO) which include 10 types of targets is constructed. The experimental results based on PICO dataset show that the proposed method can effectively detect the camouflaged targets, with mAP0. 5:0. 95 up to 52. 0% and mAP0. 5 up to 91. 5% . The detection rate achieves 55. 0 frames / s, which meets the requirement of real-time detection. © 2024 China Ordnance Industry Corporation. All rights reserved.
Keyword :
Aircraft detection Aircraft detection Antennas Antennas Deep learning Deep learning Feature extraction Feature extraction Image enhancement Image enhancement Polarization Polarization Signal detection Signal detection Unmanned aerial vehicles (UAV) Unmanned aerial vehicles (UAV)
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shen, Ying , Liu, Xiancai , Wang, Shu et al. Real-time Detection of Low-altitude Camouflaged Targets Based on Polarization Encoded Images [J]. | Acta Armamentarii , 2024 , 45 (5) : 1374-1383 . |
MLA | Shen, Ying et al. "Real-time Detection of Low-altitude Camouflaged Targets Based on Polarization Encoded Images" . | Acta Armamentarii 45 . 5 (2024) : 1374-1383 . |
APA | Shen, Ying , Liu, Xiancai , Wang, Shu , Huang, Feng . Real-time Detection of Low-altitude Camouflaged Targets Based on Polarization Encoded Images . | Acta Armamentarii , 2024 , 45 (5) , 1374-1383 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
The efficiency and dynamic response of air compressors are crucial for stability and lifespan of hydrogen fuel cells. A predictive control scheme with surge- and choke-constrained awareness is proposed to ensure safe and efficient operation of air compressors in this study. The proposed scheme consists of an efficiency enhancement model predictive control (EE-MPC), and an improved active disturbance rejection control (IADRC). Surge- and choke-constrained awareness is achieved by comparing predicted air flow with surge and choke limitations. Simultaneously, the EE-MPC is constrained with oxygen excess ratio (OER) and obtains optimal solution by searching active set. The reference flow and supply manifold pressure trajectories for IADRC are generated by EE-MPC. A designed piecewise differentiable nonlinear smoothing function is embedded in IADRC. The disturbances are estimated for coordinating flow and pressure control. Under China heavy-duty commercial vehicle test cycle for bus conditions, root-mean-squared errors (RMSEs) of flow and pressure are 3.27 g s-1 and 1.88 x 103 Pa, respectively, and the mean efficiency can be enhanced by 13.4% compared to the MPC with fixed OER. Finally, a controller hardware-in-the-loop test is conducted, with flow and pressure RMSEs of 2.48 g s-1 and 4.28 x 103 Pa between the test and simulation, respectively. This study proposes a predictive control scheme with surge- and choke-constrained awareness to guarantee safety and efficiency of air compressors. The reference flow and pressure trajectories are formulated by efficiency enhancement model predictive control, and further tracked by improved active disturbance rejection control. The proposed scheme can efficiently improve fuel cell air compressor isentropic efficiency and avoid surge and choke. image
Keyword :
air compressor predictive control air compressor predictive control compressor isentropic efficiency enhancement compressor isentropic efficiency enhancement coordinated control coordinated control fuel cell fuel cell surge- and choke-constrained awareness surge- and choke-constrained awareness
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Ye, Wangcheng , Zhong, Shunbin , Shen, Ying et al. Predictive Control Scheme for Fuel Cell Air Compressor Efficiency Enhancement with Surge- and Choke-Constrained Awareness [J]. | ADVANCED THEORY AND SIMULATIONS , 2024 . |
MLA | Ye, Wangcheng et al. "Predictive Control Scheme for Fuel Cell Air Compressor Efficiency Enhancement with Surge- and Choke-Constrained Awareness" . | ADVANCED THEORY AND SIMULATIONS (2024) . |
APA | Ye, Wangcheng , Zhong, Shunbin , Shen, Ying , Zhang, Xuezhi , Wang, Ya-Xiong . Predictive Control Scheme for Fuel Cell Air Compressor Efficiency Enhancement with Surge- and Choke-Constrained Awareness . | ADVANCED THEORY AND SIMULATIONS , 2024 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
偏振可以提高无人机的自主侦察能力,但易受到探测角度和目标材质的影响,从而降低偏振检测的鲁棒性。为此,提出一种基于偏振图像的低空伪装目标实时检测算法YOLO-P,采用融合多偏振方向信息的编码图像作为输入,应用三维卷积模块提取不同偏振方向图像之间的联系特征;引入特征增强模块对多层次特征进行进一步增强;采用跨层级特征聚合网络,充分利用不同尺度的特征信息,完成特征的有效聚合,最终联合多通道特征信息输出检测结果。构建包含10类目标的低空伪装目标偏振图像数据集PICO(Polarization Image of Camouflaged Objects)。在PICO数据集上的实验结果表明,新方法可以有效检测伪装目标,mAP_(0.5:0.95)达到52.0%,mAP_(0.5)达到91.5%,检测速率达到55.0帧/s,满足实时性要求。
Keyword :
伪装目标检测 伪装目标检测 偏振成像 偏振成像 无人机 无人机 深度学习 深度学习 特征增强 特征增强 特征聚合 特征聚合
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 沈英 , 刘贤财 , 王舒 et al. 基于偏振编码图像的低空伪装目标实时检测 [J]. | 兵工学报 , 2024 , 45 (05) : 1374-1383 . |
MLA | 沈英 et al. "基于偏振编码图像的低空伪装目标实时检测" . | 兵工学报 45 . 05 (2024) : 1374-1383 . |
APA | 沈英 , 刘贤财 , 王舒 , 黄峰 . 基于偏振编码图像的低空伪装目标实时检测 . | 兵工学报 , 2024 , 45 (05) , 1374-1383 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Deployment of deep convolutional neural networks (CNNs) in single image super-resolution (SISR) for edge computing devices is mainly hampered by the huge computational cost. In this work, we propose a lightweight image super-resolution (SR) network based on a reparameterizable multibranch bottleneck module (RMBM). In the training phase, RMBM efficiently extracts high-frequency information by utilizing multibranch structures, including bottleneck residual block (BRB), inverted bottleneck residual block (IBRB), and expand-squeeze convolution block (ESB). In the inference phase, the multibranch structures can be combined into a single 3 x 3 convolution to reduce the number of parameters without incurring any additional computational cost. Furthermore, a novel peak-structure-edge (PSE) loss is proposed to resolve the problem of oversmoothed reconstructed images while significantly improving image structure similarity. Finally, we optimize and deploy the algorithm on the edge devices equipped with the rockchip neural processor unit (RKNPU) to achieve real-time SR reconstruction. Extensive experiments on natural image datasets and remote sensing image datasets show that our network outperforms advanced lightweight SR networks regarding objective evaluation metrics and subjective vision quality. The reconstruction results demonstrate that the proposed network can achieve higher SR performance with a 98.1 K model size, which can be effectively deployed to edge computing devices.
Keyword :
edge computing device edge computing device lightweight image super-resolution lightweight image super-resolution PSE loss PSE loss reparameterizable multibranch bottleneck module reparameterizable multibranch bottleneck module
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shen, Ying , Zheng, Weihuang , Huang, Feng et al. Reparameterizable Multibranch Bottleneck Network for Lightweight Image Super-Resolution [J]. | SENSORS , 2023 , 23 (8) . |
MLA | Shen, Ying et al. "Reparameterizable Multibranch Bottleneck Network for Lightweight Image Super-Resolution" . | SENSORS 23 . 8 (2023) . |
APA | Shen, Ying , Zheng, Weihuang , Huang, Feng , Wu, Jing , Chen, Liqiong . Reparameterizable Multibranch Bottleneck Network for Lightweight Image Super-Resolution . | SENSORS , 2023 , 23 (8) . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
The fusion of spectral-polarimetric information can improve the autonomous reconnaissance capability of unmanned aerial vehicles (UAVs) in detecting artificial targets. However, the current spectral and polarization imaging systems typically suffer from low image sampling resolution, which can lead to the loss of target information. Most existing segmentation algorithms neglect the similarities and differences between multimodal features, resulting in reduced accuracy and robustness of the algorithms. To address these challenges, a real-time spectral-polarimetric segmentation algorithm for artificial targets based on an efficient attention fusion network, called ESPFNet (efficient spectral-polarimetric fusion network) is proposed. The network employs a coordination attention bimodal fusion (CABF) module and a complex atrous spatial pyramid pooling (CASPP) module to fuse and enhance low-level and high-level features at different scales from the spectral feature images and the polarization encoded images, effectively achieving the segmentation of artificial targets. Additionally, the introduction of the residual dense block (RDB) module refines feature extraction, further enhancing the network's ability to classify pixels. In order to test the algorithm's performance, a spectral-polarimetric image dataset of artificial targets, named SPIAO (spectral-polarimetric image of artificial objects) is constructed, which contains various camouflaged nets and camouflaged plates with different properties. The experimental results on the SPIAO dataset demonstrate that the proposed method accurately detects the artificial targets, achieving a mean intersection-over-union (MIoU) of 80.4%, a mean pixel accuracy (MPA) of 88.1%, and a detection rate of 27.5 frames per second, meeting the real-time requirement. The research has the potential to provide a new multimodal detection technique for enabling autonomous reconnaissance by UAVs in complex scenes.
Keyword :
camouflaged target segmentation camouflaged target segmentation dual modal feature fusion dual modal feature fusion multiscale features multiscale features polarization imaging polarization imaging spectral imaging spectral imaging unmanned aerial vehicles unmanned aerial vehicles
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shen, Ying , Liu, Xiancai , Zhang, Shuo et al. Real-Time Segmentation of Artificial Targets Using a Dual-Modal Efficient Attention Fusion Network [J]. | REMOTE SENSING , 2023 , 15 (18) . |
MLA | Shen, Ying et al. "Real-Time Segmentation of Artificial Targets Using a Dual-Modal Efficient Attention Fusion Network" . | REMOTE SENSING 15 . 18 (2023) . |
APA | Shen, Ying , Liu, Xiancai , Zhang, Shuo , Xu, Yixuan , Zeng, Dawei , Wang, Shu et al. Real-Time Segmentation of Artificial Targets Using a Dual-Modal Efficient Attention Fusion Network . | REMOTE SENSING , 2023 , 15 (18) . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
In order to achieve rapid and non-destructive detection of the astaxanthin content in Haematococcus pluvialis, a snapshot multispectral imaging method was proposed in this paper. An imaging system was built by using two snapshot multispectral cameras with visible spectral ranges of 480~635 nm and near-infrared spectral ranges of 665~950 nm, respectively. The spectral data of H. pluvialis samples in different growth periods was collected. To optimize the model prediction, a great variety of methods were compared, including different spectral ranges, three preprocessing methods, two characteristic wavelength selection methods and two modeling methods. The results indicated that the combination of both visible and near-infrared spectroscopy achieved the optimial prediction performance with the pretreatment of first derivation (FD), and the characteristic band selection method of competitive adaptive reweighting sampling (CARS) and modeling method of back propagation (BP) neural network, the prediction set correlation coefficient (Rp) of 0.9622, the root mean square error (RMSEP) of 0.5126 and the residual prediction error (RPD) of 3.6726, which was superior to the visible alone (Rp of 0.9467, RMSEP of 0.6065 and RPD of 3.1042). These indicated that it was feasible to detect the content of astaxanthin in H. pluvialis by the snapshot multispectral imaging technique, and the combination of both visible and near-infrared spectroscopy could be more effective. © 2023 Editorial Department of Science and Technology of Food Science. All rights reserved.
Keyword :
astaxanthin content astaxanthin content multispectrum imaging multispectrum imaging rapid detection rapid detection snapshot snapshot visible/near-infrared visible/near-infrared
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shen, Y. , Zhan, X. , Huang, C. et al. Rapid Determination of Visible/Near-infrared Snapshot Multispectral Imaging Astaxanthin Content of Haematococcus pluvialis; [可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量] [J]. | Science and Technology of Food Industry , 2023 , 44 (16) : 313-320 . |
MLA | Shen, Y. et al. "Rapid Determination of Visible/Near-infrared Snapshot Multispectral Imaging Astaxanthin Content of Haematococcus pluvialis; [可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量]" . | Science and Technology of Food Industry 44 . 16 (2023) : 313-320 . |
APA | Shen, Y. , Zhan, X. , Huang, C. , Xie, Y. , Huang, F. . Rapid Determination of Visible/Near-infrared Snapshot Multispectral Imaging Astaxanthin Content of Haematococcus pluvialis; [可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量] . | Science and Technology of Food Industry , 2023 , 44 (16) , 313-320 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
为了实现快速、无损检测雨生红球藻虾青素含量,本文提出一种快照式多光谱成像检测方法。利用可见光光谱范围480~635 nm和近红光谱范围665~950 nm的2台快照式多光谱相机搭建成像系统,采集了不同生长周期下的雨生红球藻样品光谱数据。为了优化预测模型,对比了不同处理方法的组合,包括不同光谱范围、3种预处理方法、2种特征波长选择算法和2种建模方法。结果表明,可见与近红外联用光谱经一阶导数(first derivation,FD)预处理、竞争自适应重加权采样(competitive adaptive reweighted sampling,CARS)选择特征波长和反向传播(back propagation,BP)神经网络建模所构建的模型预测效果最佳,预测集相关系数(Rp)为0.9622,预测集均方根误差(root mean square error of prediction,RMSEP)为0.5126,剩余预测偏差(residual predictive deviation,RPD)为3.6726,优于仅用可见光光谱(Rp为0.9467, RMSEP为0.6065,RPD为3.1042)。说明快照式多光谱成像技术检测雨生红球藻虾青素含量是可行的,并且可见与近红外光谱联用效果更好。
Keyword :
可见/近红外 可见/近红外 多光谱成像 多光谱成像 快照式 快照式 快速检测 快速检测 虾青素含量 虾青素含量
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 沈英 , 占秀兴 , 黄春红 et al. 可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量 [J]. | 食品工业科技 , 2023 : 1-8 . |
MLA | 沈英 et al. "可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量" . | 食品工业科技 (2023) : 1-8 . |
APA | 沈英 , 占秀兴 , 黄春红 , 谢友坪 , 黄峰 . 可见/近红外快照式多光谱成像快速测定雨生红球藻虾青素含量 . | 食品工业科技 , 2023 , 1-8 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
赤潮是一种由海洋藻类引发的水质污染,部分赤潮藻有毒性,对海洋渔业发展有严重危害。快速、准确地鉴定赤潮藻种及其细胞浓度对污染的控制和治理具有重要意义。传统的显微镜检测和基因测序等方法时效性低,遥感检测易受到环境干扰导致精度低,荧光光谱检测因设备昂贵无法大范围推广,高光谱成像(HSI)技术为赤潮藻种提供了一种快速、无损的检测方法。搭建了HSI检测系统,针对福建地区常见的甲藻(强壮前沟藻)、硅藻(中肋骨条藻和三角褐指藻)和针胞藻(赤潮异湾藻)构建了大量高光谱样本库,分别采用2种分类方法和3种回归方法建立藻种鉴别和细胞浓度测量模型,并比较了7种光谱预处理(标准化、归一化、多元散射校正、变量标准化、 Savitzky-Golay平滑、基于SG的一阶导数、基于SG的二阶导数)和2种波段提取方法(遗传算法和连续投影算法)对建模精度的影响。结果表明:基于SG的二阶导数(SG+2~(nd))预处理方法可以提高波段筛选和建模的准确率,遗传算法(GA)所提取特征波段更具代表性和有效性。SG+2~(nd)-GA组合所提取特征波段(644.7、 547.8、 562.6、 829.4、 832 nm)与所选藻类中特定色素的吸收光谱波段相对应,再结合支持向量机(SVM)或反向传播神经网络(BPNN)建模实现了利用高光谱成像技术有效鉴别强壮前沟藻、赤潮异湾藻、中肋骨条藻、三角褐指藻。在细胞浓度测量中,支持向量回归(SVR)建模效果优于多元线性回归(MLR)和偏最小二乘算法(PLS),四种藻SG+2~(nd)-GA-SVR细胞浓度预测模型的决定系数(R~2)均大于0.98。其中强壮前沟藻和中肋骨条藻模型浓度预测范围分别在1.05×10~3~1.05×10~4和1.13×10~4~2.38×10~5 cells·mL~(-1),最低测量浓度达到该藻种发生赤潮时的基准浓度。三角褐指藻模型浓度预测范围为1.06×10~5~4.36×10~6 cells·mL~(-1),最低测量浓度低于现有光谱技术对其测量的浓度。本研究为快速、准确、无损探测赤潮提供了新方法。
Keyword :
浓度测量 浓度测量 藻种鉴别 藻种鉴别 赤潮 赤潮 高光谱成像 高光谱成像
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 沈英 , 吴盼 , 黄峰 et al. 基于高光谱成像技术的赤潮藻种鉴别和浓度测量方法 [J]. | 光谱学与光谱分析 , 2023 , 43 (11) : 3629-3636 . |
MLA | 沈英 et al. "基于高光谱成像技术的赤潮藻种鉴别和浓度测量方法" . | 光谱学与光谱分析 43 . 11 (2023) : 3629-3636 . |
APA | 沈英 , 吴盼 , 黄峰 , 郭翠霞 . 基于高光谱成像技术的赤潮藻种鉴别和浓度测量方法 . | 光谱学与光谱分析 , 2023 , 43 (11) , 3629-3636 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
Algal bloom, a water pollution caused by marine algae, may threaten the development of fisheries due to some toxic algal species. Rapid and accurate identification of red tide algal species and their cell concentrations is important for pollution control and management. Traditional detection methods such as microscope and gene sequencing have low timeliness, remote sensing is susceptible to environmental interference resulting in low accuracy, and fluorescence spectroscopy is too expensive for widespread use. Hyperspectral imaging (HSI) technology provides a rapid and non-destructive method for detecting red tide algae species. In this study, a HSI detection system was built to establish a large amount of hyperspectral sample libraries constituted of dinophyta (Amphidinium carterae), bacillariophyta (Skeletonema costatumand Phaeodactylum tricornutum) and raphidophyceae (Heterosigma akashiwo). Two classification methods and three regression methods were used to construct models for algal species identification and cell concentration measurement, respectively, and the effects of seven spectral pretreatment methods (Autoscaling, Normalization, Multiplicative Scatter Correction, Standard Normalized Variate, Savitzky-Golay Smoothing, First Derivative Based on Savitzky-Golay, and Second Derivative Based on Savitzky-Golay) and two band extraction methods (Genetic Algorithms and Successive Projections Algorithm) on the accuracy of modelling were investigated. The results showed that the Second Derivative Based on Savitzky-Golay (SG+2(nd)) pretreatment method can improve the accuracy of band extraction and modelling, and that the feature bands selected by the genetic algorithm (GA) are more representative and effective. The feature bands (644.7, 547.8, 562.6, 829.4, 832 nm) extracted SG+2(nd)-GA correspond to the absorption spectral bands of specific pigments in the selected algae, combined with Support Vector Machine (SVM) or Back Propagation Neural Network (BPNN) modellingrealized the effective identification of dinophyta, bacillariophyta and raphidophyceae using HSI technology. Compared to Multiple Linear Regression (MLR) and Partial Least Squares (PLS) algorithms, Support Vector Regression (SVR) modelling achieved higher accuracy incell concentration measurements. The coefficients of determination (R-2) of the four algal SG+2(nd)-GA-SVR cellconcentrations prediction models were all greater than 0.98. Among them, the predicted concentrations of A. carterae e and S. costatumranged from 1.05x10(3)similar to 1.05x10(4) and 1.13x10(4)similar to 2.38x10(5) cells center dot mL(-1), with the lowest measured concentrations reaching the benchmark concentrations for this algae species in the event of red tide. The predicted concentrations of P. tricornutum ranged from 1.06x10(5)similar to 4.36x10(6) cells center dot mL(-1), with the lowest measured concentrations being lower than those of existing spectroscopic techniques. This study provides a new method for rapid, accurate, non-destructive algal blooms detection.
Keyword :
Algal blooms Algal blooms Concentration measurement Concentration measurement Hyperspectral imaging Hyperspectral imaging Species identification Species identification
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | Shen Ying , Wu Pan , Huang Feng et al. Identification of Species and Concentration Measurement of Microalgae Based on Hyperspectral Imaging [J]. | SPECTROSCOPY AND SPECTRAL ANALYSIS , 2023 , 43 (11) : 3629-3636 . |
MLA | Shen Ying et al. "Identification of Species and Concentration Measurement of Microalgae Based on Hyperspectral Imaging" . | SPECTROSCOPY AND SPECTRAL ANALYSIS 43 . 11 (2023) : 3629-3636 . |
APA | Shen Ying , Wu Pan , Huang Feng , Guo Cui-xia . Identification of Species and Concentration Measurement of Microalgae Based on Hyperspectral Imaging . | SPECTROSCOPY AND SPECTRAL ANALYSIS , 2023 , 43 (11) , 3629-3636 . |
Export to | NoteExpress RIS BibTex |
Version :
Abstract :
本发明提出一种基于嵌入式实时操作系统的滤光片转轮快速成像控制系统及其控制方法,包括嵌入式系统、精准时间输出模块、精准电机和相机控制模块、实时操作系统模块等部分;其中,精准时间输出模块包括滤光片颜色查表、曝光时间、电机加速、减速和停止总时间三部分;精准电机和相机控制模块包括串口、步进电机驱动器及步进电机、相机以及编码器四部分;实时操作系统模块包括时间管理、任务切换以及任务调度三部分。本发明有效的对滤光片转轮的到位时间进行精准控制,进而通过相机进行图像输出,实现了基于嵌入式实时操纵系统的滤光片转轮快速成像系统。
Cite:
Copy from the list or Export to your reference management。
GB/T 7714 | 林忠麟 , 庄嘉权 , 沈英 et al. 基于嵌入式实时操作系统的滤光片转轮快速成像控制系统及其控制方法 : CN202111311028.3[P]. | 2021-11-08 00:00:00 . |
MLA | 林忠麟 et al. "基于嵌入式实时操作系统的滤光片转轮快速成像控制系统及其控制方法" : CN202111311028.3. | 2021-11-08 00:00:00 . |
APA | 林忠麟 , 庄嘉权 , 沈英 , 黄峰 , 吴衔誉 , 王威雄 . 基于嵌入式实时操作系统的滤光片转轮快速成像控制系统及其控制方法 : CN202111311028.3. | 2021-11-08 00:00:00 . |
Export to | NoteExpress RIS BibTex |
Version :
Export
Results: |
Selected to |
Format: |