work

近似熵与样本熵的计算程序，还有快速计算样本熵与近似熵的程序(Approximate entropy and sample entropy calculation procedures, as well as the rapid calculation of sample entropy and approximate entropy program)

matlab couse band matlab couse band matlab

结合雷达跟踪的空中目标的实际情况，针对目标运动模型中的线性运动和非线性运动，分别设计了两种模型，并用马尔科夫状态转移矩阵实现IMM算法。最后对交互多模型卡尔曼滤波算法进行了Matlab仿真及结果分析。(Combined with radar tracking air targets, for linear and non-linear movement of target motion model, two models were designed and used a Markov state transition matrix IMM algorithm. Finally, the interacting multiple model Kalman filter algorithm Matlab simulation and results analysis.)

说明：  针对蚁群算法的matlab程序设计，希望对大家有所帮助(ant colony matlab)

说明：  局部均值分解算法，多个版本，含有例子，便于学习(Local mean decomposition algorithm, multiple versions, including examples, easy to learn)

雷达信号处理，巴克码信号波形仿真，主要是5位巴克码的仿真(Radar signal processing, Barker code waveform simulation)

说明：  瑞利信道瑞利信道瑞利信道瑞利信道瑞利信道瑞利信道瑞利信道(Rayleigh channel)

自己做设计用的参数提取程序，主要是LPCC和MFCC。(Designs its own program with the parameter extraction, mainly LPCC and MFCC.)

we present a practical link adaptation algorithm for MIMO-OFDM systems. The proposed solution is based on sounding the channel periodically and choosing the optimal mode that will maximize the throughput or energy efficiency (EE) while satisfying the application’s quality of service (QoS) requirements. In addition, we address practical problems such as the computational complexity of the algorithm and determination of sounding period by novel closed form solutions and iterative algorithms. Realistic link level simulations confirm that the proposed solution achieves significant improvement over existing link adaptation algorithms when the aim is to maximize the throughput, and provides orders of magnitude gain in energy efficiency compared to poorly chosen fixed modes when used for energy efficiency maximization purposes. The resulting algorithms are implemented on a real time MIMOOFDM testbed, and we report on the experimental results.

Q-learning (Watkins, 1989) is a simple way for agents to learn how to act optimally in controlled Markovian domains. It amounts to an incremental method for dynamic programming which imposes limited computational demands. It works by successively improving its evaluations of the quality of particular actions at particular states. This paper presents and proves in detail a convergence theorem for Q,-learning based on that outlined in Watkins (1989). We show that Q-learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action-values are represented discretely. We also sketch extensions to the cases of non-discounted, but absorbing, Markov environments, and where many Q values can be changed each iteration, rather than just one.