政务信息系统风险评估实施要点

文章介绍了政务信息系统风险评估实施的要点,包括风险评估的目的、范围及风险评估模型,风险评估项目的具体工作流程及相关方法、工具,以及为完成好风险评估项目所必备的相关项目管理要求。文章对于指导信息系统风险评估项目实施工作有很好的借鉴作用。     

松材线虫病害高光谱时序与敏感特征研究

采用高光谱仪ASD FieldSpec Pro FR,连续观测了健康和发病马尾松针叶的时序高光谱,分析了松材线虫病害光谱的时序特征、敏感时期和敏感特征。结果表明:与健康马尾松相比,病害马尾松时序光谱差异较大;病害首先造成红边区域内光谱反射率减低,然后再出现红边蓝移的2阶段光谱变化规律;感染松材线虫的马尾松9月初已经出现了病态植被典型的光谱特征;近红外平台内最大的一阶微分值、红边内一阶微分的总和(SDr)与蓝边内一阶微分的总和(SDb)的比值等是指示病害发生的显著性高光谱特征。     

Forest park landscape pattern system based on FPGA and GIS system

Perceptual scenes and scene swing surveys are the ideas for reminding local and wooded area park executives and scene placement. The maximum precise analysis of panorama visualization, forest park landscapes, planning of essential scenic spots, and visualization and safety of Geographic Information Systems (GIS) cost tools is primarily based on management and historical data. Visual impacts and cultural, historical past adjustments to are expecting visual and natural landscapes. By deciding on points from a panorama attitude, intervention calls for vital signs and symptoms of safety. Among them, studies are being carried out in many towns around the arena. Geographic Information System (GIS) depends simply on noticeable assessment and is remembered for the social legacy plan. The Gate Array (FPGA) and Geographic Information System (GIS) are analyzed based on the panorama in every place within the painting's framework. In these activities, landscape planning is proposed thru the development of scientific Piedmont. Turin is conducting a few research. From a global attitude, the version suggests that these packages reduce the capability use of the era.     

Simulation of dance performance analysis with microprocessor and machine vision interaction

Dance is the expression of artists' favourite art forms such as express emotions, their body language, and the combination of dance art and stage effects in dance performance. In almost all genres of the art form, the effectiveness of the dance performance is largely due to the quality of the individual dancer's and group dance performance. Performing arts, particularly dance, it is one of the most important of intangible cultural heritage. However, due to the preservation, documentation, analysis, and visualization understanding of dance mode, it is difficult because of technical difficulties relations. The Proposed Machine Learning Support Decision Vector Machine (SDVM) algorithm and Field Programmable Gate Array (FPGA) is a dance expert watching dance due to the recognition task, the task knowledge of professional forecasters, gestures, and facial expressions and face-to-face conditions led to better synchronization of timing. In the proposed Machine learning SDVM algorithm, the results show that positive and dancers in the audience increased negative emotions; acceleration rate and body movement also increased. SDVM is classified as dancer performance based on the artist's facial expressions, stage performance, emotions. The simulation results show good results compared to other methods.     

全景分割研究综述

在计算机视觉领域, 全景分割是一个新颖且重要的研究主题, 它是机器感知、自动驾驶等新兴前沿技术的基石, 具有十分重要的研究意义. 本文综述了基于深度学习的全景分割研究的最新进展, 首先总结了全景分割任务的基本处理流程, 然后对已发表的全景分割工作基于其网络结构特点进行分类, 并进行了全面的介绍与分析, 最后对全景分割任务目前面临的问题以及未来的发展趋势做出了分析, 并针对所面临的问题提出了一些切实可行的解决思路.     

Feasibility of the indirect determination of blast-induced rock movement based on three new hybrid intelligent models

Engineering with Computers - The indirect and accurate determination of blast-induced rock movement has important significance in the reduction of ore loss and dilution and in the protection of...     

注意力ConvLSTM模型在RUL预测中的应用

预测性维护的应用能够极大地降低企业运维成本,而设备剩余使用寿命(Remaining Useful Life,RUL)预测是预测性维护的关键技术之一.针对传统RUL预测算法难以提取时序数据的潜藏特征以及特征权重分配不合理的问题,本文提出一种基于注意力机制(Attention Mechanism)的卷积长短时记忆(Convolution Long-Short Term Memory,ConvLSTM)预测模型,该模型充分利用LSTM网络处理和预测长期时间序列的优势,并引入注意力机制对产生显著影响的特征因子提高权重,极大地优化了模型的时空特征提取能力.为验证模型预测效果,本文以NASA提供的CMAPSS数据集为对象进行实验,以均方根误差(Root Mean Squared Error,RMSE)和数据集自定义的Score为评价指标,将预测结果与其他RUL预测算法作比对,证明了该模型具有更佳的预测准确性.     

基于FPGA的羊绒近红外光谱神经网络辨识研究

为了满足神经网络实现的实时性要求,介绍了一种基于FPGA的神经网络可重构实现方法。首先在软件中利用改进的BP神经网络算法得到最优权值,然后在改进了激励函数逼近方法的基础上,用FPGA实现了羊绒近红外光谱模型的辨识。通过仿真实验得知,该方法有较好的辨识精度和速度,是一种有效的硬件羊绒近红外光谱建模方法,为羊绒、羊毛鉴别的嵌入式实现奠定了基础。     

Distributed patching for mobile wireless sensor networks

Mobile wireless sensor networks (MWSNs), the continuous movement of sensor nodes, may cause complete disconnection of the network or at best a part of it. The design of such networks should guarantee that all sensor nodes at all times have a path to the sink node(s). Prolonging the lifetimes of the MWSNs is a crucial design issue but should not be at the expense of other essential functions such as connectivity. In this paper, we propose an energy efficient distributed framework for connectivity maintenance of MWSNs. In the proposed framework, sensor nodes of the MWSNs schedule and control their radio frequency (RF) modules based on dynamic coordinated reconstruction mechanism, some senor nodes may lose their connectivity with the network due to mobility, depletion of energy and/or incurred faults. Two protocols are developed to patch up the disconnection of the MWSNs. The first protocol reestablishes the network connection consuming far less energy than state-of-the-art alternatives. However, it is capable of reestablishing the connection when no more than 20% of the MWSN backbone nodes lose connection concurrently. The second protocol extends this limit to operate when up to 35% of the MWSN backbone nodes lose connection simultaneously.     

Ultra-Stretchable Monofilament Flexible Sensor with Low Hysteresis and Linearity based on MWCNTs/Ecoflex Composite Materials

Wearable human–computer interaction equipment is a common technology, which can improve the comfort, convenience, and safety of the human body, and also can monitor human health. The flexible and wearable tensile sensor can be conveniently installed on clothes or directly connected to the body. This provides a convenient, timely, and portable solution for the detection of human motion. Therefore, wearable electronic equipment is gaining more attention. In this paper, a highly stretchable, flexible, and sensitive strain sensor which is based on multi-walled carbon nanotubes/Ecoflex nanocomposites is reported. A monofilament tensile sensor obtains good linearity (10.77%), low hysteresis (1.63%), good stability (6000 cycles under 100% strain), and ultra-high strain range (ε = 1300%). This ultra-stretchable sensor has potential applications in human motion monitoring, medical rehabilitation, health monitoring, human–computer interaction, and soft robots.