Unmanned Aerial Vehicles (UAVs) are widely available in the current market to be used either for recreation as a hobby or to serve specific industrial requirements, such as agriculture and construction. However, illegitimate and criminal usage of UAVs is also on the rise which introduces their effective identification and detection as a research challenge. This paper proposes a novel machine learning-based for efficient identification and detection of UAVs. Specifically, an improved UAV identification and detection approach is presented using an ensemble learning based on the hierarchical concept, along with pre-processing and feature extraction stages for the Radio Frequency (RF) data. Filtering is applied on the RF signals in the detection approach to improve the output. This approach consists of four classifiers and they are working in a hierarchical way. The sample will pass the first classifier to check the availability of the UAV, and then it will specify the type of the detected UAV using the second classifier. The last two classifiers will handle the sample that is related to Bebop and AR to specify their mode. Evaluation of the proposed approach with publicly available dataset demonstrates better efficiency compared to existing detection systems in the literature. It has the ability to investigate whether a UAV is flying within the area or not, and it can directly identify the type of UAV and then the flight mode of the detected UAV with accuracy around 99%.

Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student model) is trained by utilizing the information from a larger model (teacher model). In this paper, we present an outlook of knowledge distillation techniques applied to deep learning models. To compare the performances of different techniques, we propose a new metric called distillation metric which compares different knowledge distillation solutions based on models' sizes and accuracy scores. Based on the survey, some interesting conclusions are drawn and presented in this paper including the current challenges and possible research directions.

In this paper, we report our comprehensive Arabic offline Handwritten Text database (KHATT) after completion of the collection of 1000 handwritten forms written by 1000 writers from different countries. It is composed of an image database containing images of the written text at 200, 300, and 600 dpi resolutions, a manually verified ground truth database that contains meta-data describing the written text at the page, paragraph, and line levels. A formal verification procedure is implemented to align the handwritten text with its ground truth at the form, paragraph and line levels. Tools to extract paragraphs from pages and segment paragraphs into lines are developed. Preliminary experiments on Arabic handwritten text recognition are conducted using sample data from the database and the results are reported. The database will be made freely available to researchers world-wide for research in various handwritten-related problems such as text recognition, writer identification and verification, etc.

Recognition of cursive handwritten Arabic text is a difficult problem because of context-sensitive character shapes, the non-uniform spacing between words and within a word, diverse placements of dots, and diacritics, and very low inter-class variation among individual classes. In this paper, we review and investigate different deep learning architectures and modeling choices for Arabic handwriting recognition. Further, we address the problem that imbalanced data sets present to deep learning systems. In order to address this issue, we are presenting a novel adaptive data-augmentation algorithm to promote class diversity. This algorithm assigns a weight to each word in the database lexicon. This weight is calculated based on the average probability of each class in a word. Experimental results on the IFN/ENIT and AHDB databases have shown that our presented approach yields state-of-the-art results.