Preprocessing is one of the main components in a conventional document categorization (DC) framework. This paper aims to highlight the effect of preprocessing tasks on the efficiency of the Arabic DC system. In this study, three classification techniques are used, namely, naive Bayes (NB), k-nearest neighbor (KNN), and support vector machine (SVM). Experimental analysis on Arabic datasets reveals that preprocessing techniques have a significant impact on the classification accuracy, especially with complicated morphological structure of the Arabic language. Choosing appropriate combinations of preprocessing tasks provides significant improvement on the accuracy of document categorization depending on the feature size and classification techniques. Findings of this study show that the SVM technique has outperformed the KNN and NB techniques. The SVM technique achieved 96.74% micro-F1 value by using the combination of normalization and stemming as preprocessing tasks.

Recurrent neural network (RNN) has achieved remarkable success in sequence labeling tasks with memory requirement. RNN can remember previous information of a sequence and can thus be used to solve natural language processing (NLP) tasks. Named entity recognition (NER) is a common task of NLP and can be considered a classification problem. We propose a bidirectional long short-term memory (LSTM) model for this entity recognition task of the Arabic text. The LSTM network can process sequences and relate to each part of it, which makes it useful for the NER task. Moreover, we use pre-trained word embedding to train the inputs that are fed into the LSTM network. The proposed model is evaluated on a popular dataset called “ANERcorp.” Experimental results show that the model with word embedding achieves a high F-score measure of approximately 88.01%.

Classification is an important task of machine intelligence in the field of information. The artificial neural network (ANN) is widely used for classification. However, the traditional ANN shows slow training speed, and it is hard to meet the real-time requirement for large-scale applications. In this paper, an improved brain-inspired emotional learning (BEL) algorithm is proposed for fast classification. The BEL algorithm was put forward to mimic the high speed of the emotional learning mechanism in mammalian brain, which has the superior features of fast learning and low computational complexity. To improve the accuracy of BEL in classification, the genetic algorithm (GA) is adopted for optimally tuning the weights and biases of amygdala and orbitofrontal cortex in the BEL neural network. The combinational algorithm named as GA-BEL has been tested on eight University of California at Irvine (UCI) datasets and two well-known databases (Japanese Female Facial Expression, Cohn–Kanade). The comparisons of experiments indicate that the proposed GA-BEL is more accurate than the original BEL algorithm, and it is much faster than the traditional algorithm.

Sequence labeling models with recurrent neural network variants, such as long short-term memory (LSTM) and gated recurrent unit (GRU), show promising performance on several natural language processing (NLP) problems, including named-entity recognition (NER). Most existing models utilize word embeddings for capturing similarities between words. However, they lag when handling previously unobserved or infrequent words. Moreover, the attention mechanism has been used to improve sequence labeling tasks. In this paper, we propose an efficient multi-attention layer system for the Arabic named-entity recognition (ANER) task. In addition to word-level embeddings, we adopt character-level embeddings and combine them via an embedding-level attention mechanism. The output is fed into an encoder unit with bidirectional-LSTM, followed by another self-attention layer that is used to boost the system performance. Our model achieves approximately matched F1 score of 91% on the “ANERCorpus.” The overall experimental results demonstrate that our method is superior to other systems. Our approach using multi-layer attention mechanism yields a new state-of-the-art result for the ANER.

In traditional optical multiple-image encryption schemes, different images typically have almost the same encryption or decryption process. Provided that an attacker manages to correctly decrypt some image, the conventional attacks upon other images are much easier to be made. In this paper, a binary-tree encryption strategy for multiple images is proposed to resist the attacks in this case. The encryption schemes produced by this strategy can not only increase the security of multiple-image encryption, but also realize an authority management with high security among the users sharing a cipher image. For a simulation test, we devise a basic binary-tree encryption scheme, whose encryption nodes are based on an asymmetric double random phase encoding in the gyrator domain. The favorable simulation results about the tested scheme can testify to the feasibility of the strategy.

Optical cryptosystems combined with compressed sensing can achieve compression and encryption simultaneously. But they usually use the same measurement matrix to sample all blocks of an image, which makes it easy to estimate the measurement matrix in the chosen plaintext attack. In this paper, we propose a robust scheme adopting multiple measurement matrices to overcome this shortcoming. The matrices can be efficiently derived by applying random row exchanging to a basic one, which is also encoded into the fractional Fourier transform (FrFT) domain to improve the visual effect of wrongly decrypted images. Chaos-based pixel scrambling is added into our double FrFT cryptosystem to guarantee its nonlinearity. Simulation results have shown the security and effectiveness of our scheme.