Search - TI - CodeBus

Search - TI - List

[AI-NN-PR] gesture-recognition DL : 0: 出并设计了基于计算机视觉的手势识别系统。采用双肤色模型和背景自适应模型进行手势分割，解决纷乱背景下实时手势分割问题。以傅里叶描述于表缸E手势轮廓，基于BP网络建立的手势识别分类器，具有较强的自学习能力，提高了识别率。-A hand gesture recogll主ti。n system which based on∞mputer vision is Prescn}ed in thi3 pape。A method of combinirlg double c010r-spatial model arld background—adaptive model is used for gesture segrllentation to solve the problem of dynaf试c gesture se鲫entati。n under intficate backgrourld Fourier descriptors of feature of gesture edge is extracted．Cla商fier of gesture recognition based on BP netw。rk hs higher self．1eaming abilit斗The recog一工lition rate is impmved
Date : 2025-12-25 Size : 294kb User : Decheng Yu
[AI-NN-PR] diantidiaodu DL : 0: 该程序是一个简单的电梯调度算法，可以有效的计算电梯的调度过程。-gai chen xu shi yi ge jian dan de dian ti diao du suan fa. ke yi you xiao jie jue dian ti de diao du guo cheng.
Date : 2025-12-25 Size : 4kb User : panfh
[AI-NN-PR] Multi-class-SVM-Image-Classification DL : 0: 基于神经网络的遥感图像分类取得了较好的效果,但存在固有的过学习、易陷入局部极小等缺点.支持向量机机器学习方法,根据结构风险最小化(SRM)原理,表现出很多优于其他传统方法的性能,本研究的基于多类支持向量机分类器的遥感图像分类取得了达95.4 的分类精度.但由于遥感图像分类类别多,所需训练样本较大,人工选择效率较低,为此提出以人工选择初始聚类质心、C均值模糊聚类算法自动标注训练样本的基于多类支持向量机的半监督式遥感图像分类方法,期望能在获得适用的分类精度的基础上有效提高分类效率-Neural net based remote sensing image classification has obtained good results. But neural net has inherent flaws such as overfitting and local minimums. Support vector machine (SVM), which is based on Structural Risk Min- imization(SRM), has shown much better performance than most other existing machine learning methods. Using mul- ti-class SVM classifier high class rate of 95.4 is obtained. But for the class number of remote sensing image is much great, manually obtaining of training samples is a much time-consuming work. So a multi-class SVM based semi-super- vised approach is presented. It is choosed that the initial clustering centroids manually first, then label the samples as the training ones automatically with fuzzy clustering algorithm. It is believed that this method will upgrade the classifi- cation efficiency greatly with practicable class rate
Date : 2025-12-25 Size : 25kb User : cissy
[AI-NN-PR] Scc24000C DL : 0: 用单片机SCM实现的TI CC2400/1100/2500无线收发发c代码，空旷距离300米有效，FSK/GFSK调制，2.4G频段 -SCM SCM TI CC2400/1100/2500 wireless transceiver hair c code, open distance of 300 meters, the FSK/GFSK modulation, the 2.4G band
Date : 2025-12-25 Size : 16kb User : 设施
[AI-NN-PR] GAzi-ji-he-wen-ti-yingyong DL : 0: matlab在子集和问题上的应用，与遗传算法的结合使用-matlab subset problem, with the combined use of the genetic algorithm
Date : 2025-12-25 Size : 6kb User : 李倩
[AI-NN-PR] eqep_freqcal DL : 0: TI公司 TMS320F28XX系列经典例程-TI' s series of classic routines TMS320F28XX
Date : 2025-12-25 Size : 13kb User : xiaoxiao
[AI-NN-PR] BPNN DL : 0: 前向型神经网络(BPNN) 1.首先使用随机函数对每一层间的连接权值矩阵和偏置向量进行随机初始化. 2.依次使用一个训练样本对网络进行训练，并按照上面的公式计算每个样本的Δti,t 1,...,T− 1 3.训练p个样本后(一次batch)，按照更新方程对W与b进行更新. 4.重复步骤2～3，直到误差小于设定的阈值或者达到设定的batch次数.-Forward neural network (BPNN) 1. First, using a random function of connection weight matrices and bias vectors between each layer of random initialization. 2 in order to use a training sample to train the network, and calculated according to the above formula Δti each sample, t 1, ..., T-1 3. training p samples after (a batch), according to the update equation of W and b are updated. 4. repeat steps 2-3 until the error is less than set threshold or reach the batch number of the set.
Date : 2025-12-25 Size : 4kb User : 王志坦
[AI-NN-PR] bei-bao-wen-ti DL : 0: 基于粒子群算法的多目标搜索算法。运用粒子群算法求解背包问题。-Using Particle Swarm Optimization to Solve Knapsack Problem
Date : 2025-12-25 Size : 3kb User : lcy
[AI-NN-PR] lv-xing-shang-wen-ti DL : 0: 基于遗传算法的TSP算法。本案例以14个城市为例，寻找出一条遍历14个城市的最短路径。-TSP Algorithm Based on Genetic Algorithm. In this case, 14 cities, for example, to find a traversal of the 14 cities in the shortest path.
Date : 2025-12-25 Size : 9kb User : lcy