training data set 中文意思是什麼
training data set
解釋
定型數據集-
Point training data can be converted to a fuzzy set, therefore the new method can predict both point events and area - events
因此，該方法可以對面事件、點事件和線事件進行評價和預測。 -
We use control chart to characterize states of security environment and data mining to construct intrusion detection strategies. the latter includes pattern mining, pattern consolidation arid pattern comparing. in succession to it, we construct attribute set and training set for classification of net data
其次討論了自適應空間的構成，使用控制圖來構建條件空間，用數據挖掘技術來構建策略空間，重點討論了怎樣把數據挖掘技術應用到策略空間的構造中，包括模式的挖掘、合併、比較以及在此基礎上構建分類器所需要的屬性集與學習集。 -
In the paper, theories and functions of the whole system are introduced, the typical theories and algorithms of relay protection employed in the system are lucubrated, the configuration of relay protections is researched, the demonstration constitution schemes are determined, the psd remote program upgrading method based on 80c196kc is provided, the relay protection software is designed based modular structure and in which the technologies of pts data transmission and the lcd multilevel menus which contain chinese characters and graphs are adopted, a configuration software design method is provided for adapting the need of training of different structure of substations, and a set of teaching, experimental and training software which has good teaching effects and has innovation to some extent is designed
本文介紹了整個系統的結構、原理和功能，深入地研究了本系統所用的典型微機保護原理與演算法；研究了保護的配置；確定了變電站綜合自動化系統的示範構成方案；提出了基於80c196kc的psd微機保護遠程程序升級方法；設計了裝置保護軟體，軟體模塊化設計、流程清晰，並採用了pts數據傳送和lcd圖形和多級漢字菜單設計等技術；適應對不同結構的變電站培訓的需要，提出了一種組態軟體設計方法；設計了教學性好、啟迪性強、可靈活組態的教學實驗培訓軟體，有一定的創新性。 -
Thus the scale of the training data set is reduced greatly and the training speed of svm is improved enormously. because the decision boundary of svm is only determined by support vectors, the classification accuracy is almost preserved when other samples are omitted
在svm學習之前，首先剔除訓練樣本集中距離判決邊界遠的樣本，選取靠近判決邊界的樣本構成有效訓練樣本集，然後用svm對有效樣本集進行學習，這樣大大降低了訓練樣本集的規模，提高了svm的學習速度。 -
First of all, to normalize the load data to [ - 1, + 1 ], and then set up the model of load forecast. then training and simulating this model with the neural network toolbox of matlab software, then get all parameters of module after trained
首先將負荷數據歸一化，建立負荷預測模型，然後使用matlab軟體中的神經網路工具箱對該模型進行模擬訓練，計算出訓練后的模型各個參數。 -
In our work here, a model of data mining was developed, which got its foundation from artificial neural networks. hi fact, this kind of model might be called an infant protocol for dss ( decision support system ), which accepts final users " raw data, integrates various sources of data, cleanses them from garbages, then normalizes them into an intermediatary data file. from this temporary data file, the dss model can now make a conclusion, which is a fuzzy set. to do this, we introduce a kind of ann models called bp network, which classifies the records from the normalized data file. in the model. we put our main emphasis on bp network and its training algorithm. ann has been a branch of ai, and it has some kind of intelligence of human beings, as to memorization and reasoning
我們實現的模型是一個有機的數據處理和決策綜合系統，首先，模型接受用戶在通常的mis系統中積累產生的各種數據，對這些原始的， 「粗糙」的數據，我們第一步的工作是對他們進行預處理，這個過程其實相當的復雜棘手，最典型的，它首先要集成來自不同數據源的數據，其次，它要能夠對這種數據進行清洗，除去我們不感興趣的臟數據，最後，它還要對數據進行重新的解釋，處理數據的規范化，一致化等問題。在進行了必要的數據預處理之後，我們就可以對這種合適的數據進行決策分類了。 -
It is observed experimentally and algorithmically that when training data are noisy and overlapping, many support vectors have lagrange multipliers on the upper bound. if it were known beforehand which examples are bound support vectors, these examples could be removed from the training set and their values are fixed at the upper bound. due to the reduced free variable counts, this method is promising to improve training time
實驗和演算法推導顯示在強噪聲和類間重疊數據下訓練svm得到的支持向量很多處于邊界位置，如果我們能夠預先知道哪些樣本是邊界支持向量，這些邊界支持向量的值就可以被固定在邊界處，從而不參加訓練過程，這樣，訓練過程中要優化的變量就可以減少，運行時間也可以縮短。 -
At the same time, this paper puts forward a validity function for judging clustering in order to lead us to use it in k - nearest neighbor classification ; then introduces " generalization capability of a case " to k - nearest neighbour. according to the proposed approach, the cases with better generalization capability are maintained as the representative cases while those redundant cases found in their coverage are removed. we can find a new less but almost complete training data set, consequently reduce complexity of seeking near neighbour
針對k值的學習，本文初步使用了遺傳演算法選擇較優的k值，同時總結了一種聚類有效性函數，數值實驗證實了其有效性，旨在指導應用於k -近鄰分類中；然後還將「擴張能力」的概念引入k -近鄰演算法，根據訓練集例子不同的覆蓋能力，刪除冗餘樣本，得到數量較小同時代表類別情況又比較完全的新的訓練集，從而降低查找近鄰復雜性。 -
Training data set
培訓數據集 -
Unlike the ordinary weights of evidence using point training sets, the new method involves training data as a fuzzy set
通過適當的變換也可以把點訓練層轉換為模糊集合。 -
If methods use a training data set with correct classifications for learning specific predictive patterns, they are called “ supervised ”. if we just use the data itself to and internal structure, the method is called “ unsupervised ”
如果用來建立模型的訓練集合中的每個樣本已經有了明確的類別屬性，那麼在這樣的數據集上建立模型的過程就是有指導學習。 -
But in many cases, the traditional algorithms are hard to apply, or the application effects are not good. these cases include noisy data, redundant information, incomplete data, and sparse data in database. neural networks can acquire knowledge by training set
本文針對現有數據挖掘方法在很多情況下難以推廣應用，例如對于有噪聲的數據、有冗餘的信息、數據不完整、數據稀疏等情況下，這些傳統演算法的使用效果往往不佳。 -
The emphasis of the research are the method of how to set up power system data model 、 the automatic coding method of net connection and the automatic getting method of the locking logic for avoiding wrong operation in normal operation training
研究的重點是電網數據模型的建立方法、網路連接關系的自動編號以及正常操作培訓的防誤操作閉鎖邏輯的自動生成方法。
分享友人