http://hdl.handle.net/10366/145972 Wed, 10 Jun 2026 17:23:04 GMT 2026-06-10T17:23:04Z http://hdl.handle.net/10366/146116 Wed, 05 May 2021 00:00:00 GMT http://hdl.handle.net/10366/146116 2021-05-05T00:00:00Z http://hdl.handle.net/10366/146115 Machine learning has widely spread in the areas of pattern recognition, prediction or forecasting, cognitive game theory and in bioinformatics. In recent days, machine learning is being introduced into manufacturing and material industries for the development of new materials and simulating the manufacturing of the required products. In the recent paper, machine learning algorithm is developed by using Python programming for the determination of grain size distribution in the microstructure of stir zone seam of Friction Stir Welded magnesium AZ31B alloy plate The grain size parameters such as an equivalent diameter, perimeter, area, orientation etc. were determined. The results showed that the developed algorithm is able to determine various grain size parameters accurately. Thu, 10 Dec 2020 00:00:00 GMT http://hdl.handle.net/10366/146115 2020-12-10T00:00:00Z http://hdl.handle.net/10366/146114 Currently the climate computer offers many benefits and solves problems related to the regulation, monitoring and controls. Greenhouse growers remain vigilant and attentive, facing this technological development. They ensure competitiveness and optimize their investments / production cost which continues to grow. The application of artificial intelligence in the industry known for considerable growth, which is not the case in the field of agricultural greenhouses, where enforcement remains timid. It is from this fact, we undertake research work in this area and conduct a simulation based on meteorological data through MATLAB Simulink to finally analyze the thermal behavior greenhouse microclimate energy. In this paper we present comparison of modeling and simulation management of the greenhouse microclimate by fuzzy logic between a wetland (Dar El Beida Algeria) and the other arid (Biskra Algeria).; Actualmente la computadora climática ofrece muchos beneficios y resuelve problemas relacionados con la regulación, monitoreo y controles. Los productores de invernadero permanecen vigilantes y atentos frente a este desarrollo tecnológico. Aseguran la competitividad y optimizan sus inversiones / coste de producción que sigue creciendo. La aplicación de la inteligencia artificial en la industria destaca por un crecimiento considerable, que no es el caso en el campo de los invernaderos agrícolas, donde la aplicación sigue siendo tímida. Es a partir de este hecho, que emprendemos un trabajo de investigación en esta área y realizamos una simulación basada en datos meteorológicos a través de MATLAB Simulink para finalmente analizar el comportamiento térmico de la energía del microclima de efecto invernadero. En este trabajo presentamos una comparación de la gestión de modelado y simulación del microclima de invernadero por lógica difusa entre un humedal (Dar El Beida Argelia) y otro árido (Biskra Argelia). Thu, 25 Feb 2021 00:00:00 GMT http://hdl.handle.net/10366/146114 2021-02-25T00:00:00Z http://hdl.handle.net/10366/146112 Students at Saudi universities face difficulty registering for the right course since Student performance there is no support offered to students that uniquely consider each situation. Machine learning techniques could be applied to fill this gap by predicting grades of new courses for each student based on their historical data. This paper experiments with nine different prediction algorithms to predict course grades for public university students. The data-set includes grades for 215 students and 180 various courses. The models utilize grades obtained in semesters between the 2015 and 2018 academic years and evaluated on grades obtained in the 2019 academic year. Our result shows that the K-nearest neighbor with ZScore model outperforms the remaining models with respect to the Percentage of Tick Accuracy (PTA), which is the difference between two consecutive letter grades for the predicted letter grade and the observed letter grade. Our work achieved an 84% accuracy score in PTA2, where the difference between the predicted letter grade and the actual letter grade is less than or equal to two consecutive letter grades. Thu, 11 Feb 2021 00:00:00 GMT http://hdl.handle.net/10366/146112 2021-02-11T00:00:00Z http://hdl.handle.net/10366/146113 The increase in the volume and velocity of credit card transactions causes class imbalance and concept deviation problems in data sets where credit card fraud is detected. These problems make it very difficult for traditional approaches to produce robust detection models. In this study, a different perspective has been developed for this problem and a novel approach named Fraud Detection with Image Conversion (FDIC) is proposed. FDIC handles credit card transactions as time series and transforms them into images. These images, which comprise temporal correlations and bilateral relationships of features, are classified by a convolutional neural network architecture as fraudulent or legitimate. When the obtained results are compared with the related studies, FDIC has the best F1-score and recall values, which are 85.49% and 80.35%, respectively. Since the images created during the FDIC process are difficult to interpret, a new explainable artificial intelligence approach is also presented. In this way, feature relationships that have a dominant effect on fraud detection are revealed. Thu, 11 Feb 2021 00:00:00 GMT http://hdl.handle.net/10366/146113 2021-02-11T00:00:00Z http://hdl.handle.net/10366/146111 Time series forecasting methods are used by an evolving field of data analytics for the prediction of market trends, sales, and demands. Turkey is the major producer of hazelnut in the world. If Turkey wants to continue its domination of hazelnut and protect the price-setting role, time series forecasting methods could be key factors accordingly. There are a few studies that focused on time series forecasting of hazelnut export quantities of Turkey, and this study uses a recently developed algorithm and implements a power transformation to increase the forecast accuracy. The presented research aims to forecast Turkey's hazelnut export quantities for the coming 36-months starting from June 2020. The forecasting process was conducted with the help of Facebook's Prophet algorithm. To improve the forecast accuracy, a Box-Cox power transformation was also implemented to process. To find out the stationarity and periodicity of the data set, the Augmented Dickey-Fuller test and autocorrelation function was applied to the time-series data. The Prophet algorithm, with Box-Cox transformation, projected the hazelnut export quantity could be over five hundred thousand tons from 07/2020 to 06/2023. The export quantities were in an increment trend, and the slope of the trend has increased since June 2008 by 0.66 % per month. The Prophet algorithm also revealed the seasonality of the data set, and the export amounts indicate monthly oscillations. The monthly export volumes start to increase and reach their peak value in October because August is the time for the harvest of hazelnuts in Turkey. Tue, 02 Feb 2021 00:00:00 GMT http://hdl.handle.net/10366/146111 2021-02-02T00:00:00Z http://hdl.handle.net/10366/146110 Saudi Arabia is interested in providing health care and ambulatory for all citizens, residents and tourists of the pilgrims and pilgrims, and it is cooperating with the Saudi Red Crescent Authority (SRCA) to provide emergency health care especially for the pilgrims, Ammar - an independent body dealing with this. The efforts of SRCA can be highly noticed during on the Hajj season and public events such as the national day celebrations. The main issue lies in the fact that despite their efforts, the Ambulance Response Time (ART) remains higher than the global standard. Moreover, the reasons behind the high ART are circumstantial and thus hard to maneuver or manipulate. Therefore, to benefit from the Red Crescent's efforts and the first aid courses they offer, a system where credible first aiders can be summoned to provide proper and faster first aid to the injured is suggested. This study aims to develop an application to request the help of the nearest first aider by the injured or bystanders close to the injured. Also, to develop an interface that shows the route to get to the victim. The result has shown a positive indication of the importance of a system where credible first aiders can be summoned to provide proper and faster first aid to the injured. This study contributes to increase bystanders' awareness because they have the ability to connect with the nearest registered first aider. Tue, 26 Jan 2021 00:00:00 GMT http://hdl.handle.net/10366/146110 2021-01-26T00:00:00Z http://hdl.handle.net/10366/146109 In this research application of wavelet based multiscale image analysis methods for texture analysis has been highlighted. These methods are based on multiresolution properties of the two-dimensional wavelet transform, which is used to extract the features needed to discriminate and differentiate various textures more accurately then existing methods, we also took into account the texture model, the noise distribution, and the inter-dependence of the texture features which further help in discriminating factor. Multiresolution approach is nothing but a modified wavelet transform called the tree-structured wavelet transform or wavelet packets for texture analysis and classification. This approach is motivated by the observation that a large class of natural textures can be modeled as quasi-periodic signals whose dominant frequencies are located in the middle frequency channels. With the transform, we are able to zoom into any desired frequency channels for further decomposition and thus we could extract more texture features as compared to other methods. Thu, 10 Dec 2020 00:00:00 GMT http://hdl.handle.net/10366/146109 2020-12-10T00:00:00Z http://hdl.handle.net/10366/146108 Wed, 05 May 2021 00:00:00 GMT http://hdl.handle.net/10366/146108 2021-05-05T00:00:00Z