As a result of the urgent need to immediately identify individuals through the Internet, especially given the Coronavirus (COVID-19) pandemic at present, the recognition of online handwritten signatures has quickly evolved to become an urgent and necessary matter. However, signature identification remains challenging in the pattern recognition field due to intra-class variability and inter-class similarity. Intra-class variability is a characteristic of human behavioural activities, particularly in handwriting where no two handwritten signatures of any person can exactly coincide. The inter-class similarity is also a characteristic of human movement-based activities such as handwritten signatures particularly when the number of writers is large. In this research, an optimized transfer-learning-based architecture is proposed as a highly accurate identification technique for online-signatures using ResNet18 as a feature extraction deeplearning module. The X-Y time-series signals of the signatures were initially converted into images and used in retraining the ResNet18 model to achieve relatively high accuracy. The retrained ResNet18 model was then used to extract features that possess high discriminative distances among different classes of handwritten signatures. The model's deep layers were searched to determine the best layer that provided the most discriminative features when using a 1-nearest neighbour learning algorithm based on the cosine distance. By using an ensemble of five models trained on rotated versions of the original signatures and using only three training samples from each writer, the classification accuracy achieved 100% when applied on the genuine signatures of public datasets such as SVC 2004 TASK1 and TASK2, and a new proprietary dataset composed of 120 genuine users. When the abovementioned technique was tested on the aggregated version of the aforementioned datasets, the resultant accuracy was still above 99%. Moreover, the robustness of the technique was proven by testing the generated models trained with one dataset with the other two datasets resulting in accuracy above 99% for all combinations.

Driving behavior classification is an essential real-world requirement in different contexts. In traffic safety, avoiding traffic accidents by taking corrective actions against aggressive behaviors is necessary to protect drivers. Similarly, in the automotive insurance industry, distinguishing between driving behaviors is essential to adopt usage-based insurance (UBI) policies. Also, in the ridesharing industry, monitoring and evaluating driving behaviors is critical for risk assessment and service improvement. This research presents a deep learning-based solution for driving behavior classification using an optimized Stacked-LSTM model based on the signals of smartphone embedded sensors generating two different classification models: threeclass and binary. Three-class classification distinguishes between normal, drowsy, and aggressive behaviors to support advanced driver-assistance systems (ADAS). Binary classification differentiates between aggressive and non-aggressive behaviors to support commercial applications, such as ridesharing services and automotive insurance services based on UBI. Our time-series classification models have been evaluated on the public UAH-DriveSet dataset. Using the proper number and type of features, the optimum factor of upsampling for the raw signals, and the optimum time-series window size, our proposed Stacked-LSTM model made a breakthrough in the F1-score when applied to the aforementioned dataset. The achieved scores are 99.49% and 99.34% for the Three-class and binary classification models, respectively. Comparisons with state-of-the-art models, our three-class classification model surpassed the highest published F1-score of 91% by 8.49% when applied to the aforementioned dataset.

No abstract

No abstract

Due to the spread of educational management information systems (EMIS), it become necessary to add intelligent layers to improve the educational process. One of the important tasks when the student moves from one stage to the other within the educational system of a university is the determination of the appropriate department if the transition is from the first level of a faculty to a certain department or the determination of the specialization track within a certain department in higher levels. These transition moments are crucial because they affect the degree of success of the student in the selected specialization and the quality of the educational process as a whole. In this research, different machine learning (ML) techniques have been tested to predict students' marks based on their marks in the preceded courses to guide them in the selection of the most suitable specialization or track. A variety of ML prediction models have been studied, experimented and evaluated on a propriety dataset, which resulted in the selection of a neural network (NN) architecture that gives an average root mean squared error of 6.26 and a mean absolute error of 5.74 based on a scale of 0 to 100. The accuracy is comparable to the state-of-the-art work and a practical example has been given that proves the ability of the proposed system to recommend certain tracks and/or specializations based on the marks of the already studied courses. Moreover, indirect prediction using cascaded networks has been proven to generate acceptable results that can facilitate building a hierarchy of networks using a shortterm dataset to draw a weighted course road map that helps students to select the best path and help institutions to perform early measures to deal with weaknesses and anomalies.