輸入特徵向量 的英文怎麼說
中文拼音 [shūrùtèzhǐxiàngliáng]
輸入特徵向量
英文
input feature value- 輸 : Ⅰ動詞1 (運輸; 運送) transport; convey 2 [書面語] (捐獻) contribute money; donate 3 (失敗) l...
- 入 : Ⅰ動詞1 (進來或進去) enter 2 (參加) join; be admitted into; become a member of 3 (合乎) conf...
- 特 : Ⅰ形容詞(特殊; 超出一般) particular; special; exceptional; unusual Ⅱ副詞1 (特別) especially; v...
- 徵 : 名詞[音樂] (古代五音之一 相當于簡譜的「5」) a note of the ancient chinese five tone scale corre...
- 量 : 量動1. (度量) measure 2. (估量) estimate; size up
- 輸入 : 1 (從外部送到內部) import 2 [電學] input; entry; entering; in fan; fan in; 輸入變壓器 input tra...
- 特徵 : characteristic; feature; properties; aspect; trait
-
The process of feature extraction is to transform the eradiate noise signal to different feature space and extract the feature vectors that reflect the category of the input sample. the extracted features are the input modes to the classifier
特徵提取的過程是把輸入的船舶輻射噪聲信號變換到不同的特徵空間,提取出反映樣本的類別特性的特徵向量,並把其作為分類器的輸入模式。Firstly the patterns of the multifingered hands are detailed, eight patterns are defined. the classical bayes method is used in the classification of pre - grasp of multiple fingers based on three patterns which are grasping, holding and pinching. based on the eight pre - grasp patterns, bp neural network is applied in the classification of the pre - grasp of multifingered hands and gets a good effect. the method solves the shortcoming input sample relying on the propobility density and simplified the un - insititution characters extraction. in this paper, support vector machine ( svm ) and binary - tree with clustering is applied in the classification. this method can solve the slow speed and effect with fewness sample in the classification, achieving a good effect. in this papper, we extract the characters of the regulation object with geometry characters and extact the unregulation object with the image analysis
此法解決了輸入樣本依賴物體的概率密度的特點,簡化了分類特徵提取的不直觀性。本文還採用了支持向量機( svm )和聚類二叉樹相結合的方法對機器人手預抓取八類模式進行分類,解決了預抓取模式分類訓練速度過慢以及在分類中樣本數量偏少而影響分類效果的問題,得到了較高的正確率。本文對預抓取幾何形狀規則的物體採用直接提取其幾何特徵,對于預抓取幾何形狀不規則的物體採用圖像分析的方法進行特徵提取。The equations of the mean value functions and the covariance functions are established for dynamical systems whose inputs are fuzzy stochastic processes. an existence and uniqueness theorem of ito fuzzy stochastic differential equations is proved, some explicit representations of solutions and the equations of statistical characteristics are deduced for linear fuzzy stochastic differential equations, and numerical methods to nonlinear fuzzy stochastic differential equations are proposed, the conditions for stability and observability of fuzzy linear systems are derived. the kalman filter algorithms of linear fuzzy stochastic systems are brought forward
主要成果包括:提出了模糊隨機變量協方差和反向協方差的概念;研究了二階模糊隨機變量的均方收斂性,並在此基礎上得到了均方模糊隨機分析、平穩模糊隨機過程及其譜分解的若干定理;根據均方模糊隨機分析理論,得到了輸入為模糊隨機過程的線性系統的輸出輸入統計特徵關系方程;證明了ito型模糊隨機微分方程解的存在唯一性,並給出了ito型線性模糊隨機微分方程解的表達式,統計特徵方程以及非線性模糊隨機微分方程的數值解法;得到了模糊線性系統的穩定性和可觀性條件、線性模糊隨機系統統計特徵方程和線性模糊隨機系統的kalman濾波演算法;研究了當觀測值是模糊數據時,線性回歸模型的建立。This method can reflect local signal feature and well perform in the experiments. we also present an integrated electromyographic signal ( emg ) pattern recognition scheme. the application of an artificial neural network ( ann ) technique together with a feature extraction technique, for the classification of emg signals is described
利用高階譜技術提取肌電信號的特徵信息,然後利用奇異值或者其它方法對二維特徵矩陣進行優化,將優化之後的一維特徵向量輸入神經網路分類器進行模式識別,這種方法能夠初步識別不同模式的上肢運動。A method of face detection based on support vector machine ( svm ) is put forward. the features are extracted by applying the discrete cosine transform ( dct ) to the preprocessing image. the dct coefficients are inputted to the svm and the svm are trained using the cropped face samples and the " bootstrapping non - face " samples
對預處理后的圖像進行離散餘弦變換提取特徵,取dct系數作為支持向量機的輸入,將經過裁剪的「人臉」樣本與「自舉」方法得到的「非人臉」樣本一起用來訓練支持向量機。3 ) k - mean clustering algorithm is used classification. the category is two, according to the object and the experience knowledge
3 )應用無監督分類演算法中k均值( k - means )聚類演算法對輸入特徵向量進行分類。The method using wavelet packet analysis is proposed to extract fault information from vibration signal obtained from testing jig of tilting train. the vector comprised of the energy of signal in all spectrum bands is input to a feed forward neural network
利用小波包分析,將擺式車體試驗臺上採集到的振動加速度信號分解在相互獨立的頻帶之p內,各頻帶內的能量值形成一個向量,將其作為神經網路的輸入特徵向量, 。The input and output state vectors are defined, which are a 6 1 column vector including motion types, the magnitude and spatial orientation, respectively. the state matrices ( sms ) can be deduced by vectors operation, that is, the output state vectors multiplied by the input state vectors
其中,前者按照輸入輸出端的不同運動類型、速度矢量的大小及方向特徵,以6維矢量形式表示;而後者作為輸入、輸出特徵矢量之間的紐帶,描述了基本變換單元的功能與特徵。The most obvious feature of the first leading term of eof applied to the climatic vertically integrated water vapor flux over asian - australian monsoon region shows a planetary - scale southwesterly moisture transport, starting from south hemisphere, passing over asian monsoon region and flowing into north pacific, which indicates the interaction between the northern and southern hemisphere as well as between mid and low latitudes in the northern hemisphere
( 3 )亞澳季風區氣候平均狀態下4 - 9月份的水汽通量的eof矢量展開的第一特徵向量最顯著的特徵是存在一條行星尺度的強西南風水汽輸送帶,它源於南半球低緯地區,經過亞洲季風區,進入北太平洋地區,集中反映了南北半球和中低緯各支水汽輸送氣流的相互作用。In nntcs, we use artificial neural networks ( ann ) as the classifier. the recorded term frequencies form the original feature vector, matching with neurons in the input layer of ann one by one
系統使用神經網路作為分類器,特徵詞的詞頻組成原始特徵向量,和神經網路輸入層的神經元一一對應。A method of face classification and recognition based on dct and svm is proposed. the features are extracted by dct and a small set of dct coefficients are inputted to svm. the experiments show that the performance is satisfactory
提出了一種基於dct和支持向量機的人臉分類和識別方法,首先對人臉圖像作二維離散餘弦變換,取離散餘弦變換系數作為特徵輸入支持向量機,然後用支持向量機進行性別分類及人臉識別。To solve this inconsistency effectively, we don ’ t confine to one single fusion method or wavelet coefficients fusion rule, but combine them together and improve them. we consider several eigenvectors of the input images synthetically, and use the discrete biorthogonal wavelet transform at the lowest decomposition level to fulfill the new cwt - ihs multisensor remote sensing image fusion algorithm based on color compensation rule
為了有效地解決這一矛盾,本文不局限於單一的圖像融合方法和小波系數融合規則,而是將各種方法和規則結合起來並加以改進,綜合考慮輸入圖像的多個特徵向量,用最低層的離散雙正交小波變換實現了一種新的基於顏色補償的cwt - ihs多源衛星遙感圖像融合演算法。First classifier chooses two classes whose matching distance between it and paper currency is bigger than others from all class. then in the second stage, we extract some new feature and improve the classifier to generate the last result. in the stage of defect detection for paper currency, we advances a homogeneity based algorithm for the detection of scratch and cracks appearing on paper currency, in which the homogeneity feature of the sensed paper currency image is first constructed to locate the pixels that probably been polluted, the image registration algorithm is subsequently used to overlay the sensed and reference paper currency image
在特徵提取中,我們對基於方向塊的特徵提取方法進行了分析,在此基礎上針對美元特點,對圖像方向塊的劃分方式做了研究,並提出了基於幾何距離的特徵提取方法;在分類器設計中,我們採用了lvq網路對紙幣進行學習與分類,並提出了一種具有兩層結構的分類演算法,第一層首先對輸入的特徵向量進行粗分類,選定與特徵向量匹配距離最大的兩類幣種,進入第二層分類器;在第二層分類器中,我們通過研究進入該模塊兩類幣種特徵塊的相關性,重新設計了特徵向量,同時對分類器進行改進,最終實現對紙幣的分類。But its weight adjustment is determined only by its learning rate and the difference between the input pattern and the winner neuron ' s weight. it seems that the som obviously ignores some ( implicit ) correlative relationships during the learning, which actually exist between the input
自組織特徵映射權值的調整僅考慮了學習率及輸入模式與鄰域內權值之間的關系,忽略了輸入模式分量與全體參與競爭的神經元權值向量間的某種相關關系。For better performance in the circumstance of different hand - drawn shape input, an adaptive hmm ( ahmm ) structure is presented which combines single - band integral algorithm and an adaptive compression ratio control technique into one closed loop feedback recognition system, the ahmm can adaptively compress feature vectors according to geometry feature of input graphics, also can it adaptively adjust the feature compression ratio by feedback, this recognition structure achieve good performance in recognition
為了使識別系統能夠更好的適應輸入圖形的變化,本文提出了一種ahmm識別結構,利用基於單邊積分的特徵壓縮演算法和自適應壓縮率調整技術構造了一種閉環反饋識別系統,既能夠根據圖形的幾何特徵自適應的壓縮特徵向量,又能夠通過閉環反饋調整特徵向量壓縮率,達到了很好的識別效果。While in the stage of document classifying, nntcs inputs feature vectors of the document to be classified, runs network with fixed weights, then compares the output with the predefined threshold to judge the class of the unlabelled document
而在文本分類的時候,輸入待分類文檔的特徵向量,運行固定權值的網路,得到的輸出值與閾值比較確定類別。Because wavelet transform has forceful ability to pick - up character and artificial neural network has a strong capability to classify information. in this paper, the wavelet network has been formed by the wavelet transform, which is multi - dimension wavelet, and the artificial neural network which is back - propagation network. taking the eigenvector as an input of the wavelet network, the wavelet network can fulfill diagnosis of faults
根據小波變鵬胞強的特徵提取能力和人工神經網路經訓練后具有較強的分類能力的特點,本文把多維小波與目前應用廣泛的bp ( backpid剛on )相結合釀成小波神經網路,並以表徵故障的特徵向量作為小波神經網路的輸入。The features related to the target maneuver are extracted from radar and infrared sensor. and as inputs are sent into the support vector machines firstly, and then, the target ’ s maneuver inputs are estimated secondly, so that, the accurate tracking is achieved finally
先從傳感器的量測輸出和跟蹤濾波器的狀態輸出中提取和目標機動有關的特徵,而後送入支持向量機,估計目標的機動輸入,實現對機動目標的精確跟蹤。First we construct a covariance matrix from sample images, then compute the eigenvalues and corresponding eigenvectors of the covariance matrix, construct a feature matrix with the eigenvectors. then every images in database can be projected into the feature matrix and gain a projection vector, so does the input image. then we can judge the resemblance between input image with each image in database by computing the distance between their projection vectors
我們首先根據採集的樣本圖像構造一個協方差矩陣,然後求取該矩陣的特徵值,以這些矩陣特徵值對應的特徵向量構造出一個特徵空間,然後將輸入圖像向該特徵空間映射,將獲取的映射系數與樣本庫中圖像的映射系數進行距離計算,根據計算出的距離判定輸入圖像與樣本圖像間的匹配程度。First we construct a covariance matrix from sample images, then compute the eigenvalues and corresponding eigenvectors of the covariance matrix, construct a feature matrix with the eigenvectors. then every image in database can be projected into the feature matrix and gain a projection vector, so does the input image. then we can judge the resemblance between input image with each image in database by computing the distance between their projection vectors
然後,根據採集的樣本圖像構造一個協方差矩陣,求取該矩陣的特徵值,以這些矩陣特徵值對應的特徵向量構造一個特徵空間,將輸入圖像向該特徵空間映射,計算獲取的映射系數與樣本庫中各類圖像的映射系數的歐基里德距離,根據計算出的距離判定輸入圖像與樣本圖像間的匹配程度。分享友人