LPNet: A DNN based latency prediction technique for application mapping in Network-on-Chip design

Analytical models used for latency estimation of Network-on-Chip (NoC) are not producing reliable accuracy. This makes these analytical models difficult to use in optimization of design space exploration. In this paper, we propose a learning based model using deep neural network (DNN) for latency predictions. Input features for DNN model are collected from analytical model as well as from Booksim simulator. Then this DNN model has been adopted in mapping optimization loop for predicting the best mapping of given application and NoC parameters combination. Our simulations show that using the proposed DNN model, prediction error is less than 12% for both synthetic and application specific traffic. More than 108 times speedup could be achieved using DPSO with DNN model compared to DPSO using Booksim simulator.     

满速率全分集的准正交空时分组码及性能分析

正交分组编码(OSTBC)因其获得全分集和简单的译码算法在无线通信中得到了广泛的应用。但对于复信号的星座图,速率为1的正交设计仅存在两根发射天线中。为能在任意阵列天线应用发射分集的理论,一种可行的方法就是放宽码字间的正交性,利用准正交设计(QOSTBC)来实现满速率,译码时仍采用最大似然译码算法(ML)。但这种准正交设计不能达到全分集,为此,本文对一些符号的星座图利用旋转来实现满速率全分集的方法作了一些初步的讨论,并通过计算机仿真说明理论分析的正确性。     

一种IPv6环境下DDoS实时检测方法

DDoS攻击是当今网络包括下一代网络IPv6中最严重的威胁之一,提出一种基于流量自相似的IPv6的实时检测方法。分别采用改进的WinPcap实现流数据的实时捕获和监测,和将Whittle ML方法首次应用于DDoS攻击检测。针对Hurst估值方法的选择和引入DDoS攻击流的网络进行对比仿真实验,结果表明:Hurst估值相对误差,Whittle ML方法比小波变换减少0.07%;检测到攻击的误差只有0.042%,准确性达99.6%;增强了DDoS攻击检测的成功率和敏感度。     

A Framework of Deep Learning and Selection-Based Breast Cancer Detection from Histopathology Images

Breast cancer (BC) is a most spreading and deadly cancerous malady which is mostly diagnosed in middle-aged women worldwide and effecting beyond a half-million people every year. The BC positive newly diagnosed cases in 2018 reached 2.1 million around the world with a death rate of 11.6% of total cases. Early diagnosis and detection of breast cancer disease with proper treatment may reduce the number of deaths. The gold standard for BC detection is biopsy analysis which needs an expert for correct diagnosis. Manual diagnosis of BC is a complex and challenging task. This work proposed a deep learning-based (DL) solution for the early detection of this deadly disease from histopathology images. To evaluate the robustness of the proposed method a large publically available breast histopathology image database containing a total of 277524 histopathology images is utilized. The proposed automatic diagnosis of BC detection and classification mainly involves three steps. Initially, a DL model is proposed for feature extraction. Secondly, the extracted feature vector (FV) is passed to the proposed novel feature selection (FS) framework for the best FS. Finally, for the classification of BC into invasive ductal carcinoma (IDC) and normal class different machine learning (ML) algorithms are used. Experimental outcomes of the proposed methodology achieved the highest accuracy of 92.7% which shows that the proposed technique can successfully be implemented for BC detection to aid the pathologists in the early and accurate diagnosis of BC.     

Symbol Detection Based on Back Tracking Search Algorithm in MIMO-NOMA Systems

One of the most important methods used to cope with multipath fading effects, which cause the symbol to be received incorrectly in wireless communication systems, is the use of multiple transceiver antenna structures. By combining the multi-input multi-output (MIMO) antenna structure with non-orthogonal multiple access (NOMA), which is a new multiplexing method, the fading effects of the channels are not only reduced but also high data rate transmission is ensured. However, when the maximum likelihood (ML) algorithm that has high performance on coherent detection, is used as a symbol detector in MIMO NOMA systems, the computational complexity of the system increases due to higher-order constellations and antenna sizes. As a result, the implementation of this algorithm will be impractical. In this study, the backtracking search algorithm (BSA) is proposed to reduce the computational complexity of the symbol detection and have a good bit error performance for MIMO-NOMA systems. To emphasize the efficiency of the proposed algorithm, simulations have been made for the system with various antenna sizes. As can be seen from the obtained results, a considerable reduction in complexity has occurred using BSA compared to the ML algorithm, also the bit error performance of the system is increased compared to other algorithms.     

基于最大似然估计的空间谱测向技术

介绍了基于最大似然估计（简称ML）的空间谱测向,ML是一种高分辨算法,常用于空间测向和谱估计等方面。文中首先介绍了ML测向原理,由于ML是一个非线性、多维的极值问题,需要全局极值的多维搜索,其计算量非常的巨大,因此采用了AP算法进行ML算法的优化,最后通过均匀圆阵对非相干信号和相干信号进行了ML测向的计算机仿真,仿真结果表明：一个阵列对空间多个信号的分辨能力除了与信噪比有关外,还与入射信号是否相干以及两相干信号的相位差有关,ML算法可以直接对相干的入射信号进行测向,但是信号的相干性会影响ML算法测向的角度分辨率,在两信号相关的情况下,两信号间的相位差越大则测向精度越高。     

无源毫米波成像最大似然频域校正超分辨算法

在无源毫米波成像中, 因为天线孔径大小的限制而导致获取的图像分辨率低, 所以必须采取有效的后处理措施增强分辨率. 本文提出了一种针对无源毫米波成像应用的最大似然频域校正超分辨算法. 该算法首先使用Wiener滤波复原算法恢复图像通带内的频谱分量, 然后运用Richardson-Lucy算法实现频谱外推, 最后通过一种频域校正算法, 用Wiener滤波器恢复的频谱代替通带内的频谱, 保证图像的低频分量不被破坏. 实验结果表明, 该算法改善了收敛速度, 增强了图像的分辨率, 同时能够有效地减轻恢复图像中的振铃波纹, 有利于无源毫米波成像超分辨的实现.     

一种新的监督聚类学习方法及其在故障诊断中的应用

本文提出了一种新的监督聚类学习方法。系统根据样本特征矢量空间的整体分布和局部分布情况对样本进行监督聚类,克服了传统神经网络只是利用样本局部分布信息调节权值造成的局部最小,计算量大等问题,并实现了包括对未知模式的识别。仿真结果表明该方法是可行和有效的。     

基于泊松-高斯混合噪声的最大似然改进算法

传统的图像复原算法仅针对高斯噪声进行处理,没有考虑高斯及泊松混合噪声污染。为此,引入泊松-高斯混合分布的成像模型,对基于混合模型的最大似然算法进行有效近似,在此基础上提出基于泊松-高斯混合噪声的最大似然改进算法,避免对噪声敏感性和PSF初始估计的依赖。实验结果表明,与原有算法相比,改进算法复原效果明显,且稳健性较好。