基于级联卷积神经网络的前列腺磁共振图像分类

针对深度学习训练成本高,以及基于磁共振图像的前列腺癌临床诊断需要大量医学常识且极为耗时的问题,本文提出了一种基于级联卷积神经网络（Convolutional Neural Network,CNN）和磁共振图像的前列腺癌（Prostate Cancer,PCa）自动分类诊断方法,该网络以Faster-RCNN作为前网络,对前列腺区域进行提取分割,用于排除前列腺附近组织器官的干扰;以基于ResNet改进的网络结构CNN40_bottleneck作为后网络,用于对前列腺区域病变进行分类.后网络由瓶颈结构串联组成,其中使用批量标准化（Batch Normalization,BN）、全局平均池化（Global Average Pooling,GAP）进行优化.实验结果证明,本文方法对前列腺癌诊断结果较好,而且缩减了训练时间和参数量,有效降低了训练成本.     

Multi-Sensor Vibration Signal Based Three-Stage Fault Prediction for Rotating Mechanical Equipment

In order to reduce maintenance costs and avoid safety accidents, it is of great significance to carry out fault prediction to reasonably arrange maintenance plans for rotating mechanical equipment. At present, the relevant research mainly focuses on fault diagnosis and remaining useful life (RUL) predictions, which cannot provide information on the specific health condition and fault types of rotating mechanical equipment in advance. In this paper, a novel three-stage fault prediction method is presented to realize the identification of the degradation period and the type of failure simultaneously. Firstly, based on the vibration signals from multiple sensors, a convolutional neural network (CNN) and long short-term memory (LSTM) network are combined to extract the spatiotemporal features of the degradation period and fault type by means of the cross-entropy loss function. Then, to predict the degradation trend and the type of failure, the attention-bidirectional (Bi)-LSTM network is used as the regression model to predict the future trend of features. Furthermore, the predicted features are given to the support vector classification (SVC) model to identify the specific degradation period and fault type, which can eventually realize a comprehensive fault prediction. Finally, the NSF I/UCR Center for Intelligent Maintenance Systems (IMS) dataset is used to verify the feasibility and efficiency of the proposed fault prediction method.     

高光谱和卷积神经网络的大白菜农残检测

针对大白菜农药残留传统化学检测手段存在前期处理过程繁琐、检测周期长等不足,提出了一种快速无损识别大白菜农药残留种类的方法.以1组无农药残留和4组含有均匀喷洒农药(毒死蜱、乐果、灭多威和氯氰菊酯)的大白菜样本为研究对象(药液浓度配比分别为0.10,1.00,0.20和2.00 mg·kg-1),经12小时自然吸收后,利用...     

一种基于卷积神经网络的恒星光谱快速分类法

恒星光谱数据的分类是天体光谱自动识别的最基本任务之一,光谱分类的研究能够为恒星的演化提供线索。随着科技的发展,天文数据也向大数据时代迈进,需要处理的恒星光谱数量越来越多,如何对其进行自动而精准地分类成为了天文学家要解决的难题之一。当前恒星光谱自动分类问题的解决方法相对较少,为此本文使用了一种基于卷积神经网络的方法对恒星光谱MK系统进行分类。该网络由数据输入层、四个卷积层、四个池化层、全连接层、输出层构成,与传统网络相比具有局部感知、参数共享等优点实验。在Python3.5的环境下编程,利用Tensorflow构建了一个简单高效的具有四个卷积层的卷积神经网络,并将Dropout作用于全连接层之后以防止过度拟合。Dropout的基本思想：当网络模型进行训练时,把一些神经网络节点按一定的比例丢弃,使其暂时不发挥作用。Dropout可以理解成是一种十分高效的神经网络模型平均方法,由于它不依赖于某些局部特征所以能够让网络模型更加鲁棒。实验中使用的一维恒星光谱图是取自LAMOST DR3数据库,首先进行预处理截取光谱3 600~7 300 Å的部分,均匀采样后使用min-max标准化法对其进行初始化。实验包括两部分：第一部分为依据恒星光谱MK系统对光谱进行分类,每一类的训练样本包含1 000条光谱数据,测试样本为400条光谱数据,首先通过训练样本对CNN网络进行训练,进行3 000次的迭代,用训练后的网络将测试样本进行分类以验证网络的准确性;第二部分为相邻两类的恒星光谱的分类,其中O型星数据集样本为250条光谱,其余类别恒星样本数据集均为4 000条光谱,将数据5等分,每次选取当中的一份当作测试集,其余部分当作训练集,采用5折交叉验证法求得模型准确率,用BP神经网络进行对比实验。选择对网络模型进行评估的指标包括精确率P、召回率R、F-score、准确率A。实验结果显示CNN在对六类恒星光谱进行分类时其准确率都在95%以上,在对相邻类别的恒星进行分类时,由于O型星样本量较少,所以得到的分类结果不太理想,对其余类别的恒星分类准确率都高于98%,以上结果都证明了CNN算法能够很好地解决恒星光谱的分类问题。     

具有时滞的细胞神经网络周期解与稳定性

本文研究了具有时滞的细胞神经网络周期解存在性和平凡解的稳定性问题 .利用 Lyapunov函数法并结合不等式分析技巧 ,我们首先证明了时滞细胞神经网络的解是有界的 ,然后建立了时滞细胞神经网络的周期解的存在准则 ,最后在时滞细胞神经网络有平衡点时 ,给出了神经网络系统的平衡点指数稳定的充分条件 .其结果推广了文 [7,8]的相应结果 .     

CNN-aided multiple PU spectrum sensing in uncalibrated massive antennas SU system

This paper deploys the Convolutional Neural Network (CNN) to learn and set the statistical test in Spectrum Sensing (SS) task of multiple primary user (PU) sources in massive uncalibrated antennas of secondary users (SU) sharing the same spectrum resources. The proposed deep learning-based SS method (DL-SS) is based on the CNN architecture that has the capability of extracting features of the sample covariance matrices (SCMs) that are given as the network input, improving the overall performance and robustness. The proposed CNN-SS method is compared with nine recent multiple-antennas SS methods, namely the arithmetic–geometric detector (AGM), John’s detector (JD), sphericity detector (SD), generalized likelihood test (GLRT), locally most powerful invariant test (LMPIT), maximum–minimum eigenvalue detector (MME), covariance detector (CAV), Hadamard detector (HD) and volume detector (VD) methods; besides, the proposed method is also compared with five recent state-of-art CNN-based SS methodologies. Performance-complexity trade-off of the proposed and reference SS methods are corroborated via Monte Carlo Simulations (MCS). The proposed CNN-SS method under uncalibrated massive antennas reveals substantial benefits w.r.t. the reference methods and is competitive with others CNN-SS methodologies, both in terms of complexity and performance, achieving detection probability of $P_d=0.9$ $(@SNR=-20\mathrm{dB})$ under very low false alarm probability $P_f=0.1$. Under different figures of merit, the performance of the CNN-based SS detector has revealed to be indubitably superior regarding the state-of-art SS detectors. However, the proposed CNN-based SS detector presents relative computational complexity increases. Hence, to be effective, such a superior operational performance requires a very efficient processing structure in the SU base stations.     

Determination of quantum toric error correction code threshold using convolutional neural network decoders

Quantum error correction technology is an important solution to solve the noise interference generated during the operation of quantum computers.In order to find the best syndrome of the stabilizer code in quantum error correction,we need to find a fast and close to the optimal threshold decoder.In this work,we build a convolutional neural network(CNN)decoder to correct errors in the toric code based on the system research of machine learning.We analyze and optimize various conditions that affect CNN,and use the RestNet network architecture to reduce the running time.It is shortened by 30%-40%,and we finally design an optimized algorithm for CNN decoder.In this way,the threshold accuracy of the neural network decoder is made to reach 10.8%,which is closer to the optimal threshold of about 11%.The previous threshold of 8.9%-10.3%has been slightly improved,and there is no need to verify the basic noise.     

Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection

Multivariate time series anomaly detection is a widespread problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors in novel industry systems makes the anomaly detection process quite difficult for humans. Algorithms that automate the process of detecting anomalies are crucial in modern failure prevention systems. Therefore, many machine learning models have been designed to address this problem. Mostly, they are autoencoder-based architectures with some generative adversarial elements. This work shows a framework that incorporates neuroevolution methods to boost the anomaly detection scores of new and already known models. The presented approach adapts evolution strategies for evolving an ensemble model, in which every single model works on a subgroup of data sensors. The next goal of neuroevolution is to optimize the architecture and hyperparameters such as the window size, the number of layers, and the layer depths. The proposed framework shows that it is possible to boost most anomaly detection deep learning models in a reasonable time and a fully automated mode. We ran tests on the SWAT and WADI datasets. To the best of our knowledge, this is the first approach in which an ensemble deep learning anomaly detection model is built in a fully automatic way using a neuroevolution strategy.     

Understanding Dilated Mathematical Relationship between Image Features and the Convolutional Neural Network’s Learnt Parameters

Deep learning, in general, was built on input data transformation and presentation, model training with parameter tuning, and recognition of new observations using the trained model. However, this came with a high computation cost due to the extensive input database and the length of time required in training. Despite the model learning its parameters from the transformed input data, no direct research has been conducted to investigate the mathematical relationship between the transformed information (i.e., features, excitation) and the model’s learnt parameters (i.e., weights). This research aims to explore a mathematical relationship between the input excitations and the weights of a trained convolutional neural network. The objective is to investigate three aspects of this assumed feature-weight relationship: (1) the mathematical relationship between the training input images’ features and the model’s learnt parameters, (2) the mathematical relationship between the images’ features of a separate test dataset and a trained model’s learnt parameters, and (3) the mathematical relationship between the difference of training and testing images’ features and the model’s learnt parameters with a separate test dataset. The paper empirically demonstrated the existence of this mathematical relationship between the test image features and the model’s learnt weights by the ANOVA analysis.