發(fā)布時間：2018-05-20 19:13

  本文選題：前饋神經(jīng)網(wǎng)絡 + 極限學習機�。� 參考：《蘭州大學》2014年碩士論文

【摘要】：極限學習機(Extreme Learning Machine, ELM)是由黃廣斌提出的一種新型單層前饋神經(jīng)網(wǎng)絡。與傳統(tǒng)前饋神經(jīng)網(wǎng)絡相比,極限學習機結(jié)構(gòu)簡單,學習速度快且具有全局搜索能力和良好的泛化性能。但是在實際的應用過程中,極限學習機的隱含層的節(jié)點數(shù)的設(shè)置會對實際問題有所影響。過多的隱含層節(jié)點會產(chǎn)生過擬合,并且隱含層節(jié)點中不免會有對實際問題作用很小或者無用的節(jié)點。針對這一問題,一種基于極限學習機的最優(yōu)裁剪極限學習機(Optimally Pruned Extreme Learning Machine, OP-ELM)被提出,通過對極限學習機中隱含層節(jié)點進行裁剪,提高了極限學習機的魯棒性和泛化性。 認知無線電(Cognitive Radio, CR)是目前解決無線頻譜資源日益緊缺問題的關(guān)鍵技術(shù)。頻譜分配的不合理是造成頻譜資源緊缺的重要原因,認知無線電通過感知主用戶(Primary User, PU)的頻譜占用情況,使次用戶(Second User,SU)充分利用主用戶的頻譜空洞,智能的對頻譜資源動態(tài)分配,實現(xiàn)可靠的通信服務并提高頻譜的利用率。頻譜預測是認知無線電中的關(guān)鍵技術(shù),傳統(tǒng)的預測方法有很多,如馬爾科夫鏈方法、回歸分析方法和神經(jīng)網(wǎng)絡方法等。傳統(tǒng)的預測方法預測所需的時間較長,不能滿足頻譜預測的實時性的要求。極限學習機的引入,不僅滿足了頻譜預測實時性的要求,且優(yōu)化裁剪極限學習機的魯棒性和泛化性優(yōu)于傳統(tǒng)的極限學習機,更適應于認知無線電頻譜預測問題。 本文主要工作如下。 (1)系統(tǒng)并深入地研究了極限學習機的原理和特點。介紹了極限學習機和幾種改進的極限學習機的數(shù)學模型和訓練算法,從理論上闡述了極限學習機的快速特性。通過仿真實驗比較分析比較了極限學習機與傳統(tǒng)前饋神經(jīng)網(wǎng)絡的預測性能。 (2)針對隱含層節(jié)點數(shù)目過多,會影響網(wǎng)絡性能的問題,對經(jīng)典的極限學習機進行隱含層節(jié)點的調(diào)整,構(gòu)造最優(yōu)裁剪極限學習機。并通過基準實驗對其性能進行了分析。 (3)將極限學習機用于認知無線電的頻譜預測問題。針對現(xiàn)有預測方法在預測精度和預測速度上存在的不足,利用極限學習機的簡單、快速及全局最優(yōu)等特點,對認知無線電系統(tǒng)中主用戶的頻譜狀態(tài)持續(xù)時間進行預測。比較了極限學習機及其幾種改進模型與傳統(tǒng)的前饋神經(jīng)網(wǎng)絡,反饋神經(jīng)網(wǎng)絡在頻譜預測問題上的性能,實驗表明,與傳統(tǒng)前饋神經(jīng)網(wǎng)絡和反饋神經(jīng)網(wǎng)絡相比,極限學習機,特別是最優(yōu)裁剪極限學習機,無論是在預測精度上還是在預測速度上都獲得了較好的性能,更適用于無線頻譜預測問題。
[Abstract]:Extreme Learning Machine, ELM) is a new single-layer feedforward neural network proposed by Huang Guangbin. Compared with the traditional feedforward neural network, the LLM has the advantages of simple structure, fast learning speed, global searching ability and good generalization performance. However, in the practical application, the number of nodes in the hidden layer of the LLM will affect the practical problems. Too many hidden layer nodes will be over-fitted, and there will inevitably be nodes with little or no effect on practical problems. In order to solve this problem, an optimal Pruned Extreme Learning Machine, OP-ELM based on LLM is proposed. The robustness and generalization of LLM are improved by cutting the hidden layer nodes in LLM. Cognitive Radio Cognitive Radio (CRC) is the key technology to solve the problem of increasing shortage of wireless spectrum resources. The unreasonable spectrum allocation is an important reason for the shortage of spectrum resources. By sensing the spectrum occupation of primary user (PU), cognitive radio makes the secondary user make full use of the main user's spectrum hole. Intelligent dynamic allocation of spectrum resources to achieve reliable communication services and improve the spectrum efficiency. Spectrum prediction is a key technology in cognitive radio. There are many traditional prediction methods, such as Markov chain method, regression analysis method and neural network method. The traditional prediction method takes a long time and can not meet the real-time requirement of spectrum prediction. The introduction of LLM not only meets the requirement of real-time spectrum prediction, but also optimizes the robustness and generalization of LLMs, which is more suitable for cognitive radio spectrum prediction. The main work of this paper is as follows. The principle and characteristics of LLM are studied systematically and deeply. This paper introduces the mathematical models and training algorithms of the ultimate learning machine and several improved learning machines, and expounds the fast characteristics of the ultimate learning machine theoretically. The prediction performance of LLM and traditional feedforward neural network is compared by simulation experiments. 2) aiming at the problem that too many hidden layer nodes will affect the performance of the network, the classical ultimate learning machine is adjusted to construct the optimal clipping ultimate learning machine. Its performance is analyzed by benchmark experiment. In this paper, the extreme learning machine is applied to the spectrum prediction of cognitive radio. Aiming at the shortcomings of existing prediction methods in prediction accuracy and prediction speed, the duration of spectrum state of primary users in cognitive radio systems is predicted by using the characteristics of simple, fast and global optimization of extreme learning machines (LLMs). This paper compares the performance of LLM and its improved models with those of traditional feedforward neural networks and feed-back neural networks in spectrum prediction. The experimental results show that compared with traditional feedforward neural networks and feed-back neural networks, the performance of LLMs is better than that of traditional feedforward neural networks and feed-back neural networks. Especially, the optimal clipping extreme learning machine has better performance in both prediction accuracy and prediction speed, so it is more suitable for wireless spectrum prediction.
【學位授予單位】：蘭州大學
【學位級別】：碩士
【學位授予年份】：2014
【分類號】：TN925

【參考文獻】

相關(guān)期刊論文 前4條

1 李明國,郁文賢;神經(jīng)網(wǎng)絡的函數(shù)逼近理論[J];國防科技大學學報;1998年04期

2 楊晶晶;;在線極限學習機及其在圖像識別中的應用[J];電子產(chǎn)品世界;2012年04期

3 陸慧娟;安春霖;馬小平;鄭恩輝;楊小兵;;基于輸出不一致測度的極限學習機集成的基因表達數(shù)據(jù)分類[J];計算機學報;2013年02期

4 高光勇;蔣國平;;采用優(yōu)化極限學習機的多變量混沌時間序列預測[J];物理學報;2012年04期

，

本文編號：1915892