Robots have become an essential part of modern industries in welding departments to increase the accuracy and rate of production. The intelligent detection of welding line edges to start the weld in a proper position is very important. This work introduces a new approach using image processing to detect welding lines by tracking the edges of plates according to the required speed by three degrees of a freedom robotic arm. The two different algorithms achieved in the developed approach are the edge detection and top-hat transformation. An adaptive neuro-fuzzy inference system ANFIS was used to choose the best forward and inverse kinematics of the robot. MIG welding at the end-effector was applied as a tool in this system, and the wel

Brachytherapy treatment is primarily used for the certain handling kinds of cancerous tumors. Using radionuclides for the study of tumors has been studied for a very long time, but the introduction of mathematical models or radiobiological models has made treatment planning easy. Using mathematical models helps to compute the survival probabilities of irradiated tissues and cancer cells. With the expansion of using HDR-High dose rate Brachytherapy and LDR-low dose rate Brachytherapy for the treatment of cancer, it requires fractionated does treatment plan to irradiate the tumor. In this paper, authors have discussed dose calculation algorithms that are used in Brachytherapy treatment planning. Precise and less time-consuming calculations

This research aims to solve the problem of selection using clustering algorithm, in this research optimal portfolio is formation using the single index model, and the real data are consisting from the stocks Iraqi Stock Exchange in the period 1/1/2007 to 31/12/2019. because the data series have missing values ,we used the two-stage missing value compensation method, the knowledge gap was inability the portfolio models to reduce The estimation error , inaccuracy of the cut-off rate and the Treynor ratio combine stocks into the portfolio that caused to decline in their performance, all these problems required employing clustering technic to data mining and regrouping it within clusters with similar characteristics to outperform the portfolio

Earth cover of the city of Baghdad was studied exclusively within its administrative border during the period 1986-2019 using satellite scenes every five years, as Landsat TM5 and OLI8 satellite images were used. The land has been classified into ten subclasses according to the characteristics of the land cover and was classified using the Maximum Likelihood classifier. A study of the changing urban reality of the city of Baghdad during that period and the change of vegetation due to environmental factors, human influences and some human phenomena that affected the accuracy of the classification for some areas east of the city of Baghdad is presented. The year 2019 has been highlighted because of its privacy in changing the land cover of th

      The problem of text recognition and its applicability as part of images captured in the wild has gained a significant attention from the computer vision community in recent years. In contrast to the recognition of printed documents, scene text recognition is a difficult problem. Contrary to recognition of printed documents, recognizing a scene text is a challenging problem. Many researches focus on the problem of recognizing text extracted from natural scene images. Significant attempts have been made to address this problem in recent past. However, many of these attempts work on utilizing availability of strong context, which naturally limits the dictionary. This paper presents a review of recent papers related to scene text

Breast cancer is the second deadliest disease infected women worldwide. For this
reason the early detection is one of the most essential stop to overcomeit dependingon
automatic devices like artificial intelligent. Medical applications of machine learning
algorithmsare mostly based on their ability to handle classification problems,
including classifications of illnesses or to estimate prognosis. Before machine
learningis applied for diagnosis, it must be trained first. The research methodology
which isdetermines differentofmachine learning algorithms,such as Random tree,
ID3, CART, SMO, C4.5 and Naive Bayesto finds the best training algorithm result.
The contribution of this research is test the data set with mis

The gaps and cracks in an image result from different reasons and affect the images. There are various methods concerning gaps replenishment along with serious efforts and proposed methodologies to eliminate cracks in diverse tendencies. In the current research work a color image white crack in-painting system has been introduced. The proposed inpainting system involved on two algorithms. They are Linear Gaps Filling (LGF) and the Circular Gaps Filling (CGF). The quality of output image depends on several effects such as: pixels tone, the number of pixels in the cracked area and neighborhood of cracked area and the resolution the image. The quality of the output images of two methods (linear method: average Peak Signal to Noise Ratio (PS

Image classification can be defined as one of the most important tasks in the area of machine learning. Recently, deep neural networks, especially deep convolution networks, have participated greatly in end-to-end learning which reduce need for human designed features in the image recognition like Convolution Neural Network. It is offers the computation models which are made up of several processing layers for learning data representations with several abstraction levels. In this work, a pre-trained deep CNN is utilized according to some parameters like filter size, no of convolution, pooling, fully connected and type of activation function which includes 300 images for training and predict 100 image gender using probability measures. Re

       Human detection represents a main problem of interest when using video based monitoring. In this paper, artificial neural networks, namely multilayer perceptron (MLP) and radial basis function (RBF) are used to detect humans among different objects in a sequence of frames (images) using classification approach. The classification used is based on the shape of the object instead of depending on the contents of the frame. Initially, background subtraction is depended to extract objects of interest from the frame, then statistical and geometric information are obtained from vertical and horizontal projections of the objects that are detected to stand for the shape of the object. Next to this step, two ty

 Active worms have posed a major security threat to the Internet, and many research efforts have focused on them. This paper is interested in internet worm that spreads via TCP, which accounts for the majority of internet traffic. It presents an approach that use a hybrid solution between two detection algorithms: behavior base detection and signature base detection to have the features of each of them. The aim of this study is to have a good solution of detecting worm and stealthy worm with the feature of the speed. This proposal was designed in distributed collaborative scheme based on the small-world network model to effectively improve the system performance.