基于多源数据分析的区域划分形态识别与优化技术研究

传统的城市区域功能识别通常采用移动轨迹分析、POI兴趣点追踪技术来实现,手段单一且准确率较低。针对此问题,文中提出了一种基于多源数据融合分析的城市区域功能识别算法。该算法利用人群活动多源数据与自然语言文字处理的对应关系,使用Word2vec训练网络对人群活动数据进行训练。对于传统K-means聚类算法所存在的不足,从多个方面对其进行改进,改进后算法的聚类效果更优,同时还具有一定的隐私性,可以有效保证数据安全。实验测试结果表明,所提算法能够识别出的区域种类在对比算法中最多,且训练网络的准确率高达90.5%,能够实现城市区域功能的准确识别。     

基于独立分量分析的文本特征提取算法

文本特征提取的正确高效直接影响聚类结果准确率,针对文本特征提取中文本数据的高维、高噪声问题,提出采用独立分量分析作为文本特征词的提取技术.采用TF-IDF方法形成文本特征的数字描述矩阵一向量空间模型,使用独立分量分析算法实现对矩阵的关键特征词提取,使用非负矩阵分解及其扩展算法对矩阵进行聚类分析,实现聚类.     

基于调用习惯的恶意代码自动化同源判定方法

恶意代码同源判定对作者溯源、攻击事件责任判定、攻击场景还原等研究工作具有重要作用。目前恶意代码同源判定方法往往依赖人工分析,效率低下,为此,提出一种基于调用习惯的恶意代码自动化同源判定方法。该方法基于7类调用行为,使用数据挖掘算法构建作者编程习惯模型,基于频繁项离群检测算法计算同源度,利用K均值聚类算法选择同源判定阈值,进而实现恶意代码同源判定。实验结果表明,该方法具有99％以上的准确率和可接受的召回率。     

基于负荷分解与聚类融合的短期用电负荷预测研究

传统负荷预测算法通常仅以单一的数据源为基础进行计算,因此在面对动态随机特性较强的场景时难以准确预测。针对这一问题,提出了一种负荷分解后再聚类融合的短期用电负荷预测算法。该算法根据负荷行为按时间顺序分类及分解客户负载,并进行负荷数据的聚类融合,再基于贝叶斯时空高斯过程模型描述不同用电区域间的相关性。同时利用深度学习负荷数据中存在的时空相关性来表征电力消费行为特征,从而实现短期用电负荷的精准预测。在对公开数据集进行的预测实验结果表明,与现有方法相比,所提算法的误差较低,且预测性能显著提高。     

一种基于实例语义图的屏幕反窃照识别算法

目前防窃照技术手段主要依靠图像采集设备实时采集视频流,对拍照行为进行识别检测,但受复杂环境影响,现有识别方法存在精确度低、实时性差等问题。针对上述问题,提出了一种基于实例语义图的屏幕反窃照识别算法。该算法首先通过图像分割模型U²-Net提取原图像的显著视觉目标后生成实例语义图,然后通过微调单阶段的目标检测模型YOLO-v5实现对语义图中感兴趣对象的目标检测,最后通过设计的基于Inception-ResNet的拍照识别二分类模型实现对屏幕窃照行为的识别。实验结果表明,该算法在实际场景下的平均识别准确率达到95%以上。     

多优化机制下深度神经网络的音频场景识别

随着并行计算能力的不断攀升和音频数据量的日益扩增,音频场景识别成为场景理解领域重要的研究内容之一。针对音频场景识别建模难度大和识别准确率不高的问题,本文提出了融合多优化机制的并行卷积循环神经网络算法模型。首先,将音频信号经预处理后转化为一定尺寸的梅尔声谱图,之后输入到网络模型中进行充分的空间特征和时间特征学习,最后进行识别。为了验证模型的有效性,在DCASE2019音频场景数据集上进行识别性能测试,结果显示,该算法模型对音频场景的识别准确率能够达到88.84%,优于传统网络模型,说明该算法模型对音频场景识别问题的有效性。      

基于软件定义的网络准入控制体系

网络准入控制主要通过安全认证与控制实现端点的安全接入,各类准入控制技术不断涌现和发展以解决局域网边界安全问题,然而随着网络复杂性和部署管理便捷性要求的提升,固定的准入控制手段已不能适应种类繁多的安全场景需求。综述准入控制框架及技术发展,提出一种基于软件定义思想的准入控制体系,阐述其模型、架构、主要技术及应用场景,通过资源编排、资产管理与态势统一呈现等设计适应不同用户环境的安全准入和资产管理需求。     

基于口令识别的无线控制系统的设计

文章将口令识别与无线通信、机器人控制相结合,实现了基于口令识别的智能车无线控制系统。该系统包含接收和识别口令的主机,发送指令和接收指令的通信模块以及带有特定功能的智能车。主机识别口令后,以无线传送方式将指令发送给智能车,智能车按指令实现相应功能。主机和智能车都基于嵌入式系统。主机硬件电路由三星S3C6410处理器和外围电路组成,口令识别部分采用连续隐马尔科夫模型算法。实验表明,该系统有良好的稳定性和实用性。     

基于MobileNet的电缆局部放电模式识别方法

针对传统方法判别电缆局部放电类型非常耗时,且准确率较低等问题,提出了一种基于MobileNet的电缆局部放电模式识别方法。对电缆高频局部放电带电检测仪器采集到的各类PRPD图谱进行预处理与数据增强,形成图谱库;将预先训练好的MobileNetV1模型中的权值迁移到局部放电的新任务中,对模型进行网络结构和权值的微调;对迁移后的新模型进行训练,将训练得到的识别率最高的模型作为测试模型,并对测试集中的PRPD图谱进行测试。实验结果表明,该算法的识别准确率可达96.4%,并有效提升了训练的收敛速率。将该算法应用于基于安卓设备的智能局部放电巡检仪,在实际场景下,能够实现局部放电缺陷类型的快速识别,且识别准确率达到95%以上。     

基于显著性特征的选择性目标跟踪算法

针对长期目标跟踪算法中目标部分遮挡甚至消失情况下的目标有效跟踪问题,提出了一种融合了目标显著性特征的选择性跟踪算法.首先,为了有效抑制背景信息的干扰,综合HOG特征以及颜色统计特征的特点提出了前景概率图来实现增强目标显著性抑制背景干扰的效果.其次,为了减少跟踪漂移和解决重度照明和遮挡等挑战性场景中的跟踪失败问题,引入了具有筛选条件的选择性跟踪和检测框架,用以控制检测器的激活以及最终结果的选择.OTB2013数据集上的实验结果证明,本文算法可以取得91.1%的总体准确率以及67%的总体成功率,结果优于大部分跟踪算法.     

Design and verification of on-chip debug circuit based on JTAG

An on-chip debug circuit based on Joint Test Action Group (JTAG) interface for L-digital signal processor (L- DSP) is proposed, which has debug functions such as storage resource access, central processing unit (CPU) pipeline control, hardware breakpoint/ observation point, and parameter statistics. Compared with traditional debug mode, the proposed debug circuit completes direct transmission of data between peripherals and memory by adding data test-direct memory access (DT-DMA) module, which improves debug efficiency greatly. The proposed circuit was designed in a 0-18 μm complementary metal-oxide-semiconductor ( CMOS) process with an area of 167 234.76 μm² and a power consumption of 8.89 mW. And the proposed debug circuit and L-DSP were verified under a field programmable gate array (FPGA). Experimental results show that the proposed circuit has complete     

Real-time hand tracking based on YOLOv4 model and Kalman filter

Aiming at the shortcomings of current gesture tracking methods in accuracy and speed, based on deep learning You Only Look Once version 4 (YOLOv4) model, a new YOLOv4 model combined with Kalman filter rea-time hand tracking method was proposed. The new algorithm can address some problems existing in hand tracking technology such as detection speed, accuracy and stability. The convolutional neural network (CNN) model YOLOv4 is used to detect the target of current frame tracking and Kalman filter is applied to predict the next position and bounding box size of the target according to its current position. The detected target is tracked by comparing the estimated result with the detected target in the next frame and, finally, the real-time hand movement track is displayed. The experimental results validate the proposed algorithm with the overall success rate of 99.43%     

A Long‐Range Touch Interface for Interaction with Smart TVs

A powerful interaction mechanism is one of the key elements for the success of smart TVs, which demand far more complex interactions than traditional TVs. This paper proposes a novel interface based on the famous touch interaction model but utilizes long‐range bare hand tracking to emulate touch actions. To satisfy the essential requirements of high accuracy and immediate response, the proposed hand tracking algorithm adopts a fast color‐based tracker but with modifications to avoid the problems inherent to those algorithms. By using online modeling and motion information, the sensitivity to the environment can be greatly decreased. Furthermore, several ideas to solve the problems often encountered by users interacting with smart TVs are proposed, resulting in a very robust hand tracking algorithm that works superbly, even for users with sleeveless clothing. In addition, the proposed algorithm runs at a very high speed of 82.73 Hz. The proposed interface is confirmed to comfortably support most touch operations, such as clicks, swipes, and drags, at a distance of three meters, which makes the proposed interface a good candidate for interaction with smart TVs.     

基于自适应小生境混合遗传算法的说话人识别

为了解决传统高斯混合模型(Gaussian Mixture Model,GMM)对初值敏感,在实际训练中极易得到局部最优参数的问题,本文提出了一种GMM参数优化的新方法.将小生境技术与最大似然估计融入到遗传训练过程,形成了一种新的混合算法,缓解了遗传算法产生的"早熟"现象,提高了算法的局部搜索能力.采用自适应策略来控制交叉和变异算子,同时在适应度评价中融入了其他用户的区分性信息,提高了模型的分类精度,增强了GMM的泛化能力.实验表明,与传统和改进的两种方法相比,本文的方法都可以得到更优的模型参数,使得系统的识别率进一步提高.     

基于双模板Siamese网络的鲁棒视觉跟踪算法

近年来,Siamese网络由于其良好的跟踪精度和较快的跟踪速度,在视觉跟踪领域引起极大关注,但大多数Siamese网络并未考虑模型更新,从而引起跟踪错误。针对这一不足,该文提出一种基于双模板Siamese网络的视觉跟踪算法。首先,保留响应图中响应值稳定的初始帧作为基准模板R,同时使用改进的APCEs模型更新策略确定动态模板T。然后,通过对候选目标区域与2个模板匹配度结果的综合分析,对结果响应图进行融合,以得到更加准确的跟踪结果。在OTB2013和OTB2015数据集上的实验结果表明,与当前5种主流跟踪算法相比,该文算法的跟踪精度和成功率具有明显优势,不仅在尺度变化、平面内旋转、平面外旋转、遮挡、光照变化情况下具有较好的跟踪效果,而且达到了46 帧/s的跟踪速度。     

修正的当前统计模型及自适应跟踪算法

针对当前统计模型及其自适应算法对弱机动目标跟踪精度较低以及强机动发生时刻跟踪误差增大的缺陷,提出了一种修正的当前统计模型及自适应跟踪算法。一方面,利用指数函数对当前统计模型中加速度极值进行实时修正,从而提高了算法对弱机动目标的跟踪精度;另一方面,利用滤波残差调整预测协方差,同时对滤波结果发生较大偏差的上一时刻的滤波结果进行修正,从而提高了对强机动目标的适应能力。仿真结果表明,所提算法对弱机动目标和强机动目标都具有良好的跟踪性能。     

Data-driven hybrid remaining useful life estimation approach for spacecraft lithium-ion battery

Electrical power system (EPS) is one of the most critical sub-systems of the spacecraft. Lithium-ion battery is the vital component is the EPS. Remaining useful life (RUL) prediction is an effective mean to evaluate the battery reliability. Autoregressive model (AR) and particle filter (PF) are two traditional approaches in battery prognosis. However, the parameters in a trained AR model cannot be updated which will cause the under-fitting in the long term prediction and further decrease the RUL prediction accuracy. On the other hand, the measurement function in the PF algorithm cannot be obtained in the long term prediction process. To address these two challenges, a hybrid method of IND-AR model and PF algorithm are proposed in this work. Compared with basic AR model, a nonlinear degradation factor and an iterative parameter updating method are utilized to improve the long term prediction performance. The capacity prediction results are applied as the measurement function for the PF algorithm. The nonlinear degradation factor can make the linear AR model suitable for nonlinear degradation estimation. And once the capacity is predicted, the state-space model in the PF is activated to obtain an optimized result. Optimized capacity prediction result of each cycle is utilized to re-train the regression model and update the parameters. The predictor keeps working iteratively until the capacity hit the failure threshold to calculate the RUL value. The uncertainty involved in the RUL prediction result is presented by PF algorithm as well. Experiments are conducted based on commercial lithium-ion batteries and real-applied satellite lithium-ion batteries. The results have high accuracy in capacity fade prediction and RUL prediction of the proposed method. The real applied lithium-ion battery can meet the requirement of spacecraft. All the experiments results show great potential of the proposed framework.     

基于IMM-KF算法改进的欺骗式干扰检测算法

针对基于接收机基线长度的欺骗干扰检测方法在短基线和低定位精度下检测性能差的问题,提出了一种交互多模型卡尔曼滤波（Interactive Multi-model Kalman Filtering,IMM-KF）算法改进的欺骗式干扰检测算法。该方法通过IMM-KF算法对两个接收机天线的位置信息进行最优估计,提高基线解算精度,从而提升基于基线长度的欺骗干扰检测方法的检测性能。首先,详细分析了基于基线长度的欺骗干扰检测方法的数学原理;其次,建立欺骗检测算法模型,并对其性能进行仿真分析;然后,根据算法应用场景引入IMM-KF算法优化基线长度估计量;最后,针对不同的基线长度和定位精度进行仿真实验,对算法进行性能评估。仿真结果表明,该算法可以在接收机伪距测量精度为0.1 m、基线长度为0.5 m的情况下达到86%的检测成功率,而传统算法在此情况下检测成功率仅为10%。     

Ergodic Capacity and Symbol Error Rate Analysis of a Wireless System with α-μ Composite Fading Channel

Surgeons must intraoperatively view cross-section images under sterilization conditions. Keyboard and computer mouse are sources of contamination. A computer vision algorithm and a hand movement pattern analysis technique have been applied to solve the problem based on surgeon’s behaviors. This paper proposed a new method to control the radiological image viewer in an operating room. A pattern code of hand movement and a grid square guideline are used. Our proposed algorithm comprises three steps: hand tracking, pattern code area identification, and hand movement pattern recognition. First, the system is fed with a sequence of three-dimensional data. A 3D camera captures the whole target body. A skeleton tracking algorithm is used to detect the human body. The left-hand joint in the skeleton data set is tracked. Second, as this algorithm supports one hand movement, a grid square guideline is defined. Hand movements are interpreted from the hand path moving in the grid square area. Finally, the pattern code is defined as a feature vector. By using the feature vector and closest point classifier, the hand movements are recognized by the K-Nearest Neighbors algorithm. To test the performance of the proposed algorithm, data from twenty subjects were used. Seven commands were used to interface with the computer workstation to control the radiological image viewer. The accuracy rate was 95.72%. The repeatability was 1.88. The advantage of this method is that one hand can control the image viewer software from a distance of 1.5 m satisfactorily without contacting computer devices. Our method also does not need big data set to train the system.

     

基于优势遗传的模糊函数主脊切面智能搜索方法

提取和补充新的信号参数是解决复杂体制雷达辐射源信号分选难题的有效手段,模糊函数主脊切面特征是众多新特征参数中较为可行的特征之一。为更快速地搜索信号的模糊函数主脊切面,本文构建了一种优势遗传搜索的智能算法,并采用统计假设检验理论对数据进行分析和检验。实验结果表明,所提方法可使模糊函数主脊切面的平均搜索耗时降低为原方法的28.6%,且能以较高的概率成功搜索到精度更高的切面特征,证实了所提方法的有效性和可行性。