Image processing applications are currently spreading rapidly in industrial agriculture. The process of sorting agricultural fruits according to their color comes first among many studies conducted in industrial agriculture. Therefore, it is necessary to conduct a study by developing an agricultural crop separator with a low economic cost, however automatically works to increase the effectiveness and efficiency in sorting agricultural crops. In this study, colored pepper fruits were sorted using a Pixy2 camera on the basis of algorithm image analysis, and by using a TCS3200 color sensor on the basis of analyzing the outer surface of the pepper fruits, thus This separation process is done by specifying the pepper according to the color of its outer surface, afterward selecting the fruit is achieved, then the crop is sorted by color. An electromechanical system was developed for this process with three different belt conveyor speeds (0.8, 2 and 3 m /s). The image processing algorithms and external surface color analysis that were developed within the scope of the study were tested on this system in real practical time. Moreover, choosing the appropriate speed for the conveyor belt, depending on the time sufficient to process the images or analyze the colors of the outer surface of the pepper fruits. The highest successav erage of 93.33% was recorded along with the lowest error average of 6.66%, at the first speed using the Pixy2 camera, whereas the sorting process using the TCS3200 color sensor recorded the highest success average of 83.33% along with the lowest error average of 16.66%, at the first speed. It is evident from the above-mentioned values, that the method of sorting the pepper with the Pixy2 camera is more successful than the second method of using the TCS3200 color sensor, nevertheless, the second method can also be used in the process of sorting the pepper fruits.
Deep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod
... Show More
(11)
(4)
Abstract: Two different shapes of offset optical fiber was studied based on coreless fiber for refractive index (RI)/concentration (con.) measurement, and compare them. These shapes are U and S-shapes, both shapes structures were formed by one segment of coreless fiber (CF) was joined between two single mode (SMF) lead in /lead out with the same displacement (12.268µm) at both sides, the results shows the high sensitive was achieved in a novel S-shape equal 98.768nm/RIU, to our knowledge, no one has ever mentioned or experienced it, it’s the best shape rather than the U-shape which equal 85.628nm/RIU. In this research, it was proved that the offset form has a significant effect on the sensitivity of the sensor. Addi
... Show More
(1)
(6)
(5)
Two unsupervised classifiers for optimum multithreshold are presented; fast Otsu and k-means. The unparametric methods produce an efficient procedure to separate the regions (classes) by select optimum levels, either on the gray levels of image histogram (as Otsu classifier), or on the gray levels of image intensities(as k-mean classifier), which are represent threshold values of the classes. In order to compare between the experimental results of these classifiers, the computation time is recorded and the needed iterations for k-means classifier to converge with optimum classes centers. The variation in the recorded computation time for k-means classifier is discussed.
The problem of Multicollinearity is one of the most common problems, which deal to a large extent with the internal correlation between explanatory variables. This problem is especially Appear in economics and applied research, The problem of Multicollinearity has a negative effect on the regression model, such as oversized variance degree and estimation of parameters that are unstable when we use the Least Square Method ( OLS), Therefore, other methods were used to estimate the parameters of the negative binomial model, including the estimated Ridge Regression Method and the Liu type estimator, The negative binomial regression model is a nonline
... Show More
Background: The demand for better esthetic during orthodontic treatment has increased nowadays, so orthodontists starting using esthetic arch wires, brackets and ligatures.Tooth colored brackets were introduced in different types of materials. Sapphire ceramic brackets are one type of esthetic brackets and their color stability remains the main concern for the clinicians and patients at the same time. The present study design to evaluate the effect of three different staining materials (pepsi, black tea and cigarette smoke) on the stainability of sapphire ceramic brackets bonded with three types of light cure orthodontic adhesives which include: Resilience, Enlight and Transbond. Materials and Methods: The sample consisted of three hundre
... Show More