基于音频特征的工程车辆工况识别研究

高效率地使用工程车辆是工程项目管理中节约成本的有效方法，无人监管环境下工程车辆的工况识别，是实现工程车辆高效率使用的有效手段。目前以GPS等技术为核心的车辆智能管理系统未对工程车辆进行工况识别，提出一种基于GRU循环神经网络的工程车辆工况识别方法，通过对工程车辆在不同工况下产生的音频信号进行分析，从中提取Mel倒谱系数作为主要特征，构建GRU循环神经网络模型进行训练和识别。实验结果表明，该方法可以实现对工程车辆工况的有效识别。     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

No-reference quality assessment of dynamic sports videos based on a spatiotemporal motion model

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.     

A recurrent neural network using historical data to predict time series indoor PM2.5 concentrations for residential buildings

Due to the severe outdoor PM2.5 pollution in China, many people have installed air-cleaning systems in homes. To make the systems run automatically and intelligently, we developed a recurrent neural network (RNN) that uses historical data to predict the future indoor PM2.5 concentration. The RNN architecture includes an autoencoder and a recurrent part. We used data measured in an apartment over the course of an entire year to train and test the RNN. The data include indoor/outdoor PM2.5 concentration, environmental parameters and time of day. By comparing three different input strategies, we found that a strategy employing historical PM2.5 and time of day as inputs performed best. With this strategy, the model can be applied to predict the relatively stable trend of indoor PM2.5 concentration in advance. When the input length is 2 h and the prediction horizon is 30 min, the median prediction error is 8.3 µg/m³ for the whole test set. For times with indoor PM2.5 concentrations between (20,50] µg/m³ and (50,100] µg/m³, the median prediction error is 8.3 and 9.2 µg/m³, respectively. The low prediction error between the ground-truth and predicted values shows that the RNN can predict indoor PM2.5 concentrations with satisfactory performance.     

Sequential alignment attention model for scene text recognition

Scene text recognition has been a hot research topic in computer vision due to its various applications. The state-of-the-art solutions usually depend on the attention-based encoder-decoder framework that learns the mapping between input images and output sequences in a purely data-driven way. Unfortunately, there often exists severe misalignment between feature areas and text labels in real-world scenarios. To address this problem, this paper proposes a sequential alignment attention model to enhance the alignment between input images and output character sequences. In this model, an attention gated recurrent unit (AGRU) is first devised to distinguish the text and background regions, and further extract the localized features focusing on sequential text regions. Furthermore, CTC guided decoding strategy is integrated into the popular attention-based decoder, which not only helps to boost the convergence of the training but also enhances the well-aligned sequence recognition. Extensive experiments on various benchmarks, including the IIIT5k, SVT, and ICDAR datasets, show that our method substantially outperforms the state-of-the-art methods.     

Learning a Deep Predictive Coding Network for a Semi-Supervised 3D-Hand Pose Estimation

In this paper we present a CNN based approach for a real time 3D-hand pose estimation from the depth sequence. Prior discriminative approaches have achieved remarkable success but are facing two main challenges: Firstly, the methods are fully supervised hence require large numbers of annotated training data to extract the dynamic information from a hand representation. Secondly, unreliable hand detectors based on strong assumptions or a weak detector which often fail in several situations like complex environment and multiple hands. In contrast to these methods, this paper presents an approach that can be considered as semi-supervised by performing predictive coding of image sequences of hand poses in order to capture latent features underlying a given image without supervision. The hand is modelled using a novel latent tree dependency model (LDTM) which transforms internal joint location to an explicit representation. Then the modeled hand topology is integrated with the pose estimator using data dependent method to jointly learn latent variables of the posterior pose appearance and the pose configuration respectively. Finally, an unsupervised error term which is a part of the recurrent architecture ensures smooth estimations of the final pose. Experiments on three challenging public datasets, ICVL, MSRA, and NYU demonstrate the significant performance of the proposed method which is comparable or better than state-of-the-art approaches.      

依托泊苷联合卡铂用于复发性髓母细胞瘤患儿的疗效与安全性

目的:探讨依托泊苷联合卡铂用于复发性髓母细胞瘤患儿的疗效与安全性。方法:选取浙江大学医学院附属儿童医院在2011年1月至2014年6月收治的72例复发性髓母细胞瘤患儿（3～15岁），随机分为CE组和对照组，每组36例，CE组采用依托泊苷＋卡铂给药方式化疗；对照组采用经典伊立替康＋替莫唑胺＋长春新碱方案化疗。比较两组患儿临床疗效、卡诺夫斯基健康状况量表（KPS）评分、儿科生活质量测定量表4.0（PedsQLTM4.0）评分、总生存期（OS）、无事件生存（EFS），记录患儿治疗期间药物不良反应的发生情况。结果:治疗后CE组和对照组完全缓解率（CR）分别为41.67%（15/36）和27.78%（10/36），总缓解率（OR）分别为94.44%（34/36）和77.78%（28/36），差异有统计学意义（P<0.05）。两组患儿治疗前KPS评分及PedsQLTM4.0评分无统计学差异（P＞0.05），治疗后CE组和对照组的KPS评分分别为（80±8）和（75±10）分，PedsQLTM4.0评分分别为（89±11）和（84±11）分，差异均有统计学意义（均P<0.05）。截至末次随访时间，CE组有3例失访，对照组有2例失访。截至末次随访时间，CE组和对照组总生存率分别为78.8%（26/33）和55.9%（19/34），差异有统计学意义（P<0.05），无事件生存率分别为72.7%（24/33）和52.9%（18/34），差异无统计学意义（P＞0.05）。CE组化疗期间共出现10例3级以上不良反应，发生率为27.78%（10/36），对照组化疗期间共出现9例3级以上不良反应，发生率为25.00%（9/36），差异无统计学意义（P＞0.05）。结论:依托泊苷联合卡铂方案能够明显提高患儿临床缓解率，延长患儿总生存率，同时不增加化疗不良反应，但对无事件生存率的影响并不明显。     

二氧化氯和臭氧杀菌处理对菜心贮藏品质的影响

为提高菜心贮藏品质,研究二氧化氯(ClO2)、臭氧(O3)两种杀菌剂对菜心贮藏期间的呼吸强度、丙二醛含量、过氧化物酶活等品质指标变化规律的影响。研究发现,与对照组相比,在贮藏期内ClO2和O3对菜心呼吸的影响是先促进后抑制,二者均使菜心呼吸高峰提前到达,但贮藏中后期(6 d^9 d)杀菌组的呼吸强度低于对照组,ClO2对呼吸的抑制优于O3;ClO2和O3提高了菜心贮藏前期的硬度,贮藏后期ClO2组菜心硬度适中;ClO2降低了菜心a*值,有利于保持菜心的绿色;O3对菜心a*值略有提高,对菜心绿色影响不显著;ClO2和O3促使菜心中丙二醛的累积,但量小难以促衰老;ClO2能稳定维持偏低的过氧化物酶活性,抑制苯丙氨酸解氨酶活性,延缓其木质化和衰老,保持品质。综合分析得出,ClO2更适合杀菌处理菜心,货架期可达12 d,具有潜在的应用前景。     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

Input-to-state learning of recurrent neural networks with delay and disturbance

This article deals with the issue of input-to-state stabilization for recurrent neural networks with delay and external disturbance. The goal is to design a suitable weight-learning law to make the considered network input-to-state stable with a predefined -gain. Based on the solution of linear matrix inequalities, two schemes for the desired learning law are presented via using decay-rate-dependent and decay-rate-independent Lyapunov functionals, respectively. It is shown that, in the absence of external disturbance, the proposed learning law also guarantees the exponential stability of the network. To illustrate the applicability of the present weight-learning law, two numerical examples with simulations are given.