With the rapid spread of the coronavirus epidemic all over the world, educational and other institutions are heading towards digitization. In the era of digitization, identifying educational e-platform users using ear and iris based multimodal biometric systems constitutes an urgent and interesting research topic to preserve enterprise security, particularly with wearing a face mask as a precaution against the new coronavirus epidemic. This study proposes a multimodal system based on ear and iris biometrics at the feature fusion level to identify students in electronic examinations (E-exams) during the COVID-19 pandemic. The proposed system comprises four steps. The first step is image preprocessing, which includes enhancing, segmenting, and extracting the regions of interest. The second step is feature extraction, where the Haralick texture and shape methods are used to extract the features of ear images, whereas Tamura texture and color histogram methods are used to extract the features of iris images. The third step is feature fusion, where the extracted features of the ear and iris images are combined into one sequential fused vector. The fourth step is the matching, which is executed using the City Block Distance (CTB) for student identification. The findings of the study indicate that the system's recognition accuracy is 97%, with a 2% False Acceptance Rate (FAR), a 4% False Rejection Rate (FRR), a 94% Correct Recognition Rate (CRR), and a 96% Genuine Acceptance Rate (GAR). In addition, the proposed recognition system achieved higher accuracy than other related systems.

No abstract

This paper presents an intelligent system to assist librarians in classification and circulation of books and periodicals. The system is based on a database containing the categories of scientific departments in the Faculty of Specific Education. It is also contains knowledge base that includes most of the words related to these categories. The Distance Vector Classifier Engine is used for text pre-processing classification. K-Nearest Neighbor algorithm and Term Frequency-Inverses Document Frequency are used for classification books and periodicals. The proposed system has achieved accuracy reached to 94.3%.

The security and protection of educational institutions from fire is a major challenge at the present time. However, advanced technologies can be of a great help in this regard, especially embedded systems and mechatronics, which has become a hot research topic as regard meeting those challenges. Hence, this paper presents a novel and effective expert mechatronics system to manage fire crises in educational institutions. The system provides solution for the problem of predicting fires before they break and how to prevent and manage them, to save lives and property. The system begins with obtaining data by measuring symmetrical physical quantities from the surrounding environment (temperature, gas, smoke, flames, and fire) using sensors. After then, the controller processes the data received from these sensors. In addition, data received from sensors are sent to the expert system to manage them and provide required suggestions and recommendations to manage the existing crisis. In the unsafe condition, such as the spread of gas or smoke smell or fire, the actuators will be activated and the proposed system will release two types of warning signals: an audio signal using sound alarms, and a visual one using red and yellow lights. Moreover, the system sends an SMS to the System Manager and decision makers in the educational institution about the secured place with information and details on the fire and its location. The proposed system was tested by fabricating different fire crisis instances. The performance of proposed system was evaluated in terms of the confusion matrix including parameters such as Precision, Sensitivity, Specificity, F-measure, Error Rate and Accuracy The findings show that the proposed system is effective and usable.