Results 21 to 30 of about 1,827 (107)
probability neural network based on particle swarm optimization algorithm [PDF]
标签分布学习是近几年发展起来的解决多标签分类问题的方法。该方法基于这样的假设:属于不同标签的实例可能会存在部分的共同特征,因此在学习过程中,每个实例都可以对不同的标签做出贡献,这极大地降低了学习的难度。条件概率神经网络作为解决这个模型的算法,在进行分类时具有独特的优势,然而如何对其进行有效的训练,从而找到最优参数却是一个困难的问题。 本文对条件概率神经网络的优化进行了研究,在考虑标签分布的性质和条件概率神经网络的结构特点之后,从三个方面改进了条件概率神经网络,并将改进的条件概率神经网络应用于年龄估计问题,
徐骏捷
core
为了对锂离子电池剩余电量(SOC)进行准确测量,以2 200 mA?h的聚合物锂电池为研究对象,利用Hyperion平衡充放电设备采集6个不同放电电流下(0.7,1.1,1.7,2.2,2.7和3.3A)的放电电压和放电倍率;采取误差反向传播(BP)和径向基函数(RBF) 2个原理不同的神经网络算法进行SOC预测;把采集的样本数据分为训练组和测试组,采用不同的神经网络算法对训练组进行训练后,选择合适的参数构建神经网络,并用测试组数据进行测试;最终比较2种算法的预测效果和误差。研究结果表明 ...
余杰 +6 more
core
A model for short-term load forecasting in power system based on multi-AI methods [PDF]
将自组织(SOM)和反向传播(bP)两种神经网络结合起来,并使用模糊理论,建立了一种基于集成智能方法的日负荷预测智能模型,该模型首先利用SOM网络的竞争学习能力将历史数据分成若干类别从而找出与预测日同类型的预测类别.然后,把温度、日类型等不确定性扰动因素分离出去,利用bP算法的非线性函数逼近功能,完成电力负荷的基本分量部分的预测工作.在处理温度、天气情况、日类型等不确定因素对负荷的影响时,采用模糊逻辑理论对负荷基本分量进行修正.提出了一种基于进化树的自组织神经网络算法(SOETA ...
张群洪
core
Malicious DNS traffic detection based neural networks [PDF]
To solve the problems of low detection accuracy and speed caused by low efficiency in extracting traffic features using machine learning to detect malicious DNS traffic, a malicious DNS traffic detection method FDS-DL was proposed, which combines ...
CHEN Wenzhi +3 more
core +1 more source
Prediction of Grain Porosity Based on GWO-BP Neural Network and Grain Compression Experiment [PDF]
Porosity is a key parameter that affects the heat and moisture transfer within a grain pile. In order to investigate the distribution law of porosity in bulk grain piles in grain silos, grain compression experiment was carried out to obtain the porosity ...
CHEN Jia-hao +6 more
core +1 more source
High-roubustness keystroke recognition method based on acoustic spatial gradient [PDF]
For the fluctuation of CFCC caused by environmental noise is the main reason for the low accuracy of keystroke detection,the spatial characteristics of adjacent between CFCC were studied,and the spatial gradient structure of CFCC based on points was ...
Kangkang HAN, Ying LIU, Zhihong QIAN
core +1 more source
Study on Qianling Lake Restoration with Artificial Wetland [PDF]
黔灵湖水质变坏的根源可以追溯到黔灵湖的上游小关湖,影响水质的根源是养猪废水,其中,主要污染物质为氮、磷、无机质、有机质和微生物等。在小关水库的下游建造人工湿地,种植的植物首先应选择一些去污力强,又宜于本土生长,根系发达,茎叶繁茂,具有耐污能力和抗寒能力、抗病虫能力强的植物,同时还应具有一定的观赏性。用人工湿地技术可以除去上游养猪废水和生活污水中的氮、磷、无机物质和有机物质等,将废水中的氮和磷转化为生物体组织中的氮和磷,从而减少了微生物的大量繁殖形成的“水华“导致黔灵湖水质变坏。同时 ...
严重玲 +5 more
core
The Research on FPA Infrared Thermal Imaging Technology [PDF]
红外热成像技术由于其具有作用距离远,可全天候工作,能穿透云雾,能识别伪装等特点,受到各国的广泛关注,并且得到了迅速的发展。目前,红外探测器已由第一代发展到了第三代,而非制冷型红外探测器因其具有价格低、体积小、操作方便等诸多优点,成为当今世界高技术领域发展的热点之一。我国的红外焦平面技术研究起步比较晚,与先进国家的水平还有一定差距。因此在我国研究红外技术显得紧迫且有意义。 本文首先研究了UL03081型红外探测器的工作原理和设计要求,设计了探测器的直流偏置电路,温控电路,时序驱动电路及A/D转换电路 ...
王家慧
core
The Application of ZigBee Technology and Neural Network Algorithms in Street Light Control Systems [PDF]
This paper introduces a street lamp control system based on zigbee technology and neural network algorithm. Street lamp control system consists of microcontrollers, sensors, displays, buttons, ZigBee, street lights.
core +1 more source
基于多元统计和神经网络算法的竞技体育胜负预测模型 [PDF]
This paper uses NBA 2014 - 2015 regular season as one of the examples of competitive sports and tries to find a general model for the prediction of other competitive sports.
core +1 more source

