二维SIMD结构的低功耗调度

针对二维SIMD结构,提出一种可以动态关闭空转部件且结合编译器、指令集和体系结构支持的低功耗调度算法,其中包括编译器优化二维SIMD指令,功耗指令发出部件开关信号,系统接收信号并执行。采用对不同功能单元分别调度的方式和部件局部化的方法。在模拟器上的实验结果表明该方法可以节省整个系统约15％的能量消耗。     

不等保护码在CBTC系统中的应用

针对轨道交通车地通信中信息对误码敏感程度不同的现象,提出利用不等保护码作为信道编码方案,为基于通信的列车控制（CBTC）系统重要信息提供更好的误码保护。采用分离最小理想的方法给出R—S码空间的构造方法,提出一种适用于具有2个保护能力等级的R—S码的译码算法——二次译码算法。仿真显示,不等保护码可以使高保护等级信息位的信噪比降低0．5dB以上。     

Identify Congested Links Based on Enlarged State Space

When paths share a common congested link, they will all suffer from a performance degradation. Boolean tomography exploits these performance-level correlations between different paths to identify the congested links. It is clear that the congestion of a path will be distinctly intensive when it traverses multiple congested links. We adopt an enlarged state space model to mirror different congestion levels and employ a system of integer equations, instead of Boolean equations, to describe relationships between the path states and the link states. We recast the problem of identifying congested links into a constraint optimization problem, including Boolean tomography as a special case. For a logical tree, we propose an up-to-bottom algorithm and prove that it always achieves a solution to the problem. Compared with existing algorithms, the simulation results show that our proposed algorithm achieves a higher detection rate while keeping a low false positive rate.     

自由飞行空间机器人的遥操作分数阶PID控制

作为空间操控的重要手段, 空间遥操作将趋向于更精细和更灵活. 然而传统的空间遥操作控制方法难以兼 顾操作的精细性和灵活性. 针对这一问题, 本文阐述了一种面向自由飞行空间机器人的遥操作分数阶PID控制方法. 首先根据自由飞行空间机器人的动力学模型, 设计了空间遥操作分数阶PID控制系统. 其次, 针对空间遥操作时滞 系统和系统的鲁棒性和抗干扰性要求, 基于系统的参数稳定域, 对分数阶PID控制器的参数进行整定. 最后, 数值仿 真和地面遥操作实验验证了分数阶PID控制器的跟踪性能、抗干扰性、鲁棒性和抗时延抖动性能. 因此, 本文设计的 分数阶PID控制器不仅适合于空间遥操作复杂时滞系统, 而且可以满足未来空间遥操作任务的发展需求.     

基于近红外与高光谱技术的小麦种子多指标检测方法

采集47份小麦样本的高光谱图像,提取感兴趣区内的平均光谱,结合反映小麦品质的水分、蛋白质和湿面筋三个指标基础数据,通过OPUS软件搜寻最佳的光谱预处理和波段组合,分别建立了三个指标的偏最小二乘法(PLS)定量分析模型.同时与采用近红外(.NIR)光谱技术建立的三个指标的近红外模型进行比较,发现高光谱模型的各性能指标均明显优于近红外模型.结果表明:当被测样品为颗粒状且内部化学成分分布不均匀时,近红外模型的准确性和稳定性会受其测量条件的限制,而高光谱采样面积大,获取信息更全面,展现出强大的分析检测潜质,为小麦品质评价提供了新方法.     

一种多源感知数据流上的连续真值发现技术

真值发现作为整合由不同数据源提供的冲突信息的一种手段,在传统数据库领域已经得到了广泛的研究.然而现有的很多真值发现方法不适用于数据流应用,主要原因是它们都包含迭代的过程.本文针对一种特殊的数据流—感知数据流上的连续真值发现问题进行了研究.结合感知数据本身及其应用特点,提出一种变频评估数据源可信度的策略,减少迭代过程的执行,提高每一时刻多源感知数据流真值发现的效率.本文首先定义并研究了当感知数据流真值发现的相对误差和累积误差较小时,相邻时刻数据源的可信度变化需要满足的条件,进而给出了一种概率模型,以预测数据源的可信度满足该条件的概率.之后,通过整合上述结论,实现在预测的累积误差以一定概率不超过给定阈值的前提下,最大化数据源可信度的评估周期以提高效率,并将该问题转化为了一个最优化问题.在此基础上,提出了一种变频评估数据源可信度的算法—CTF-Stream (Continuous Truth Finding over Sensor Data Streams),CTF-Stream 结合历史数据动态地确定数据源可信度的评估时刻,在保证真值发现结果达到用户给定精度的同时提高了效率.最后,本文通过在真实的感知数据集合上进行实验,进一步验证了算法在处理感知数据流的真值发现问题时的效率和准确率.     

深度学习应用技术研究

本文针对深度学习应用技术进行了研究性综述。详细阐述了RBM（Restricted Boltzmann Machine）逐层预训练后再用BP（back-propagation）微调的深度学习贪婪层训练方法,对比分析了BP算法中三种梯度下降的方式,建议在线学习系统,采用随机梯度下降,静态离线学习系统采用随机小批量梯度下降;归纳总结了深度学习深层结构特征,并推荐了目前最受欢迎的5层深度网络结构设计方法。分析了前馈神经网络非线性激活函数的必要性及常用的激活函数优点,并推荐ReLU （rectified linear units）激活函数。最后简要概括了深度CNNs(Convolutional Neural Networks), 深度RNNs(recurrent neural networks), LSTM(long short-termmemory networks)等新型深度网络的特点及应用场景,并归纳总结了当前深度学习可能的发展方向。     

Appearance Harmonization for Single Image Shadow Removal

Shadow removal is a challenging problem and previous approaches often produce de‐shadowed regions that are visually inconsistent with the rest of the image. We propose an automatic shadow region harmonization approach that makes the appearance of a de‐shadowed region (produced using any previous technique) compatible with the rest of the image. We use a shadow‐guided patch‐based image synthesis approach that reconstructs the shadow region using patches sampled from non‐shadowed regions. This result is then refined based on the reconstruction confidence to handle unique textures. Qualitative comparisons over a wide range of images, and a quantitative evaluation on a benchmark dataset show that our technique significantly improves upon the state‐of‐the‐art.     

Adaptive sparse coding on PCA dictionary for image denoising

Sparse coding is a popular technique in image denoising. However, owing to the ill-posedness of denoising problems, it is difficult to obtain an accurate estimation of the true code. To improve denoising performance, we collect the sparse coding errors of a dataset on a principal component analysis dictionary, make an assumption on the probability of errors and derive an energy optimization model for image denoising, called adaptive sparse coding on a principal component analysis dictionary (ASC-PCA). The new method considers two aspects. First, with a PCA dictionary-related observation of the probability distributions of sparse coding errors on different dimensions, the regularization parameter balancing the fidelity term and the nonlocal constraint can be adaptively determined, which is critical for obtaining satisfying results. Furthermore, an intuitive interpretation of the constructed model is discussed. Second, to solve the new model effectively, a filter-based iterative shrinkage algorithm containing the filter-based back-projection and shrinkage stages is proposed. The filter in the back-projection stage plays an important role in solving the model. As demonstrated by extensive experiments, the proposed method performs optimally in terms of both quantitative and visual measurements.