During COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face mask detection. This work introduces a face mask model that is able to recognize whether a person is wearing mask or not. The proposed model has two stages to detect and recognize the face mask; at the first stage, the Haar cascade detector is used to detect the face, while at the second stage, the proposed CNN model is used as a classification model that is built from scratch. The experiment was applied on masked faces (MAFA) dataset with images of 160x160 pixels size and RGB color. The model achieved lower computational complexity and number of layers, while being more reliable compared with other algorithms applied to recognize face masks. The findings reveal that the model's validation accuracy reaches 97.55% to 98.43% at different learning rates and different values of features vector in the dense layer, which represents a neural network layer that is connected deeply of the CNN proposed model training. Finally, the suggested model enhances recognition performance parameters such as precision, recall, and area under the curve (AUC).
Accurate emotion categorization is an important and challenging task in computer vision and image processing fields. Facial emotion recognition system implies three important stages: Prep-processing and face area allocation, feature extraction and classification. In this study a new system based on geometric features (distances and angles) set derived from the basic facial components such as eyes, eyebrows and mouth using analytical geometry calculations. For classification stage feed forward neural network classifier is used. For evaluation purpose the Standard database "JAFFE" have been used as test material; it holds face samples for seven basic emotions. The results of conducted tests indicate that the use of suggested distances, angles
... Show MoreNowadays, people's expression on the Internet is no longer limited to text, especially with the rise of the short video boom, leading to the emergence of a large number of modal data such as text, pictures, audio, and video. Compared to single mode data ,the multi-modal data always contains massive information. The mining process of multi-modal information can help computers to better understand human emotional characteristics. However, because the multi-modal data show obvious dynamic time series features, it is necessary to solve the dynamic correlation problem within a single mode and between different modes in the same application scene during the fusion process. To solve this problem, in this paper, a feature extraction framework of
... Show MoreAbstract
Machining residual stresses correlate very closely with the cutting parameters and the tool geometries. This research work aims to investigate the effect of cutting speed, feed rate and depth of cut on the surface residual stress of steel AISI 1045 after face milling operation. After each milling test, the residual stress on the surface of the workpiece was measured by using X-ray diffraction technique. Design of Experiment (DOE) software was employed using the response surface methodology (RSM) technique with a central composite rotatable design to build a mathematical model to determine the relationship between the input variables and the response. The results showed that both
... Show MoreConvolutional Neural Networks (CNN) have high performance in the fields of object recognition and classification. The strength of CNNs comes from the fact that they are able to extract information from raw-pixel content and learn features automatically. Feature extraction and classification algorithms can be either hand-crafted or Deep Learning (DL) based. DL detection approaches can be either two stages (region proposal approaches) detector or a single stage (non-region proposal approach) detector. Region proposal-based techniques include R-CNN, Fast RCNN, and Faster RCNN. Non-region proposal-based techniques include Single Shot Detector (SSD) and You Only Look Once (YOLO). We are going to compare the speed and accuracy of Faster RCNN,
... Show MoreIn this research work, a new type of concrete based on sulfur-melamine modification was introduced, and its various properties were studied. This new type of concrete was prepared based on the sulfur-melamine modification and various ingredients. The new sulfur-melamine modifier was fabricated, and its fabrication was confirmed by IR spectroscopy and TG analysis. The surface morphology resulted from this modifier was studied by SEM and EDS analysis. The components ratios in concrete, chemical and physical characteristics resulted from sulfur-melamine modifier, chemical and corrosion resistance of concrete, stability of concrete against water adsorption, stability of concrete against freezing, physical and mechanical properties and durabi
... Show MoreUnter dem Titel " Technische Methoden im Fremdsprachunterricht als eine neueste Methode im Fremdsprachlernen, die Spiele als Muster"
versteht man, dass die Forschung sich mit einer neuen Methoden im Fremdsprachunterricht beschäftigt. Von den neuen Methoden im Unterricht sind die Spiele. So man sieht in den letzten Jahren viele Artikel zum Thema Spiele im Fremdsprschunterricht. Davon gehen wir aus, dass die Spiele im Unterricht eine groβe Rolle spielt, denn diese Methode macht Lust, Spaβ im Lernenprozeβ. Die Spiele im Unterricht bezeichnen als ein Mittel, um Unterricht etwas Schönes , Nützliches und Lebendigs zu sein. Die Spiele sind vielfälltig und unterscheidet sich nach den Themen und Materialien. In dieser F
... Show MoreSoftware-defined networking (SDN) is an innovative network paradigm, offering substantial control of network operation through a network’s architecture. SDN is an ideal platform for implementing projects involving distributed applications, security solutions, and decentralized network administration in a multitenant data center environment due to its programmability. As its usage rapidly expands, network security threats are becoming more frequent, leading SDN security to be of significant concern. Machine-learning (ML) techniques for intrusion detection of DDoS attacks in SDN networks utilize standard datasets and fail to cover all classification aspects, resulting in under-coverage of attack diversity. This paper proposes a hybr
... Show MoreThis study aims to estimate the accuracy of digital elevation models (DEM) which are created with exploitation of open source Google Earth data and comparing with the widely available DEM datasets, Shuttle Radar Topography Mission (SRTM), version 3, and Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model (ASTER GDEM), version 2. The GPS technique is used in this study to produce digital elevation raster with a high level of accuracy, as reference raster, compared to the DEM datasets. Baghdad University, Al Jadriya campus, is selected as a study area. Besides, 151 reference points were created within the study area to evaluate the results based on the values of RMS.Furthermore, th
... Show MoreThe general health of palm trees, encompassing the roots, stems, and leaves, significantly impacts palm oil production, therefore, meticulous attention is needed to achieve optimal yield. One of the challenges encountered in sustaining productive crops is the prevalence of pests and diseases afflicting oil palm plants. These diseases can detrimentally influence growth and development, leading to decreased productivity. Oil palm productivity is closely related to the conditions of its leaves, which play a vital role in photosynthesis. This research employed a comprehensive dataset of 1,230 images, consisting of 410 showing leaves, another 410 depicting bagworm infestations, and an additional 410 displaying caterpillar infestations. Furthe
... Show More