با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
A prediction of leaf mechanical properties with data mining
پیش بینی خواص مکانیکی برگ با داده کاوی-2019 The mechanical properties of the leaf are typically determined by mechanical testing approaches to study the
leaf lifespan, plant anti-herbivore defences and ecological functions by considering habitat influences, environmental
resources variation and species diversity. While the leaf morphology features were commonly used
for plant recognition and plant disease detection with the aid of an automated inspection system. However, the
influence of morphology features on leaf mechanical properties is vague. In this research, we investigated the
effect of various morphological features on mechanical properties of leaf, followed by proposed a novel leaf
mechanical properties prediction model using data mining techniques. A 600×22 feature vector was collected
and examined using Pearson correlation analysis and Welch’s test to select the relevant features. The prediction
on four mechanical properties indicators was performed with LinearRegression, KStar, DecisionTable and M5P
algorithms in the Waikato Environment for Knowledge Analysis (WEKA). The experimental results show that
numeric prediction for Tearing Force (FT) and Tearing Strength (ST) (RRSE ≈ 25%) were about two folds better
as compared to Work-to-tear (WT) and Specific Work-to-tear (SWT) (RRSE≈50%) in four algorithms tested. The
best results achieved was the FT indicator prediction with M5P algorithms (RRSE=23.12%). FT indicator
prediction model adopted from M5P algorithms output was constructed. Keywords: Data mining | Leaf geometry | Leaf morphology | Regression |
مقاله انگلیسی |