Electrical Discharge Machining (EDM) is a non-traditional cutting technique for metals removing which is relied upon the basic fact that negligible tool force is produced during the machining process. Also, electrical discharge machining is used in manufacturing very hard materials that are electrically conductive. Regarding the electrical discharge machining procedure, the most significant factor of the cutting parameter is the surface roughness (Ra). Conventional try and error method is time consuming as well as high cost. The purpose of the present research is to develop a mathematical model using response graph modeling (RGM). The impact of various parameters such as (current, pulsation on time and pulsation off time) are studied on

This study aims to model the flank wear prediction equation in metal cutting, depending on the workpiece material properties and almost cutting conditions. A new method of energy transferred solution between the cutting tool and workpiece was introduced through the flow stress of chip formation by using the Johnson-Cook model. To investigate this model, an orthogonal cutting test coupled with finite element analysis was carried out to solve this model and finding a wear coefficient of cutting 6061-T6 aluminum and the given carbide tool.

LandSat Satellite ETM+ image have been analyzed to detect the different depths of regions inside the Tigris river in order to detect the regions that need to remove sedimentation in Baghdad in Iraq Country. The scene consisted of six bands (without the thermal band), It was captured in March ٢٠٠١. The variance in depth is determined by applying the rationing technique on the bands ٣ and ٥. GIS ٩. ١ program is used to apply the rationing technique and determined the results.

Offline handwritten signature is a type of behavioral biometric-based on an image. Its problem is the accuracy of the verification because once an individual signs, he/she seldom signs the same signature. This is referred to as intra-user variability. This research aims to improve the recognition accuracy of the offline signature. The proposed method is presented by using both signature length normalization and histogram orientation gradient (HOG) for the reason of accuracy improving. In terms of verification, a deep-learning technique using a convolution neural network (CNN) is exploited for building the reference model for a future prediction. Experiments are conducted by utilizing 4,000 genuine as well as 2,000 skilled forged signatu