Arabic text classification is a challenging task because of the complex morphology of the language, the existence of different writing forms and a multitude of dialects, which can result in sparser common text representations. While transformer models such as AraBERT have obtained superior results on many Arabic NLP tasks, their high computational requirements make them difficult to deploy in environments with limited hardware resources. In some cases this can also make the model less practical for researchers working with basic computer systems. This study focuses on a more practical issue: how much accuracy a simple classifier may lose when the amount of required computation is reduced. We use a combined TF-IDF representation based on both words and characters, then reduce the number of features using Chi-Square selection. The selected features are finally used with a linear SVM to create a model that is faster and more efficient, while still keeping good predictive performance. However, the method do not always provide the same level of accuracy as more complex models, especially with difficult text. The proposed lightweight method is tested against several other approaches, including word-based TF-IDF, character-based TF-IDF, Naive Bayes, Logistic Regression, BiLSTM, and AraBERT. All methods are tested using the same data distribution to make the comparison fair. The dataset used is the arbml/arabic_100k_reviews corpus, which originally contains 99,999 balanced reviews from three sentiment categories. After cleaning the data and removing very short reviews, the dataset was reduced to 99,759 samples. The training, validation, and testing sets includes 69,831, 9,976, and 19,952 reviews, respectively. This setup allows the different models to be compared under similar conditions and with the same evaluation process. After applying Chi-Square feature selection, the hybrid feature set was reduced from 250,000 to 50,000 dimensions, which represents an 80% reduction. That proposed method achieved 67.90% accuracy and a Macro-F1 score of 67.75%. Its training time was around 41 seconds, while the complete test set was processed in about 0.03 seconds. Among all the evaluated models, AraBERT achieved the best overall performance, reaching 74.08% accuracy and 74.25% Macro-F1. However, its computational requirements were much higher, with nearly 1,760 seconds needed for training and about 47 seconds for inference on the same test set. Depending on the processing stage, this makes AraBERT approximately 40 to 1,500 times slower than the proposed lightweight approach. The proposed method is therefore not presented as a replacement for AraBERT in terms of accuracy, since its accuracy is lower. Instead, its main advantage is the considerable and measurable reduction in computational cost. This trade-off can be useful in situations where GPU availability, memory capacity, or response time are limited.
Steganography can be defined as the art and science of hiding information in the data that could be read by computer. This science cannot recognize stego-cover and the original one whether by eye or by computer when seeing the statistical samples. This paper presents a new method to hide text in text characters. The systematic method uses the structure of invisible character to hide and extract secret texts. The creation of secret message comprises four main stages such using the letter from the original message, selecting the suitable cover text, dividing the cover text into blocks, hiding the secret text using the invisible character and comparing the cover-text and stego-object. This study uses an invisible character (white space
... Show More
(5)
(1)
Hiding technique for dynamic encryption text using encoding table and symmetric encryption method (AES algorithm) is presented in this paper. The encoding table is generated dynamically from MSB of the cover image points that used as the first phase of encryption. The Harris corner point algorithm is applied on cover image to generate the corner points which are used to generate dynamic AES key to second phase of text encryption. The embedded process in the LSB for the image pixels except the Harris corner points for more robust. Experimental results have demonstrated that the proposed scheme have embedding quality, error-free text recovery, and high value in PSNR.
(12)
(4)
In this paper we investigate the automatic recognition of emotion in text. We propose a new method for emotion recognition based on the PPM (PPM is short for Prediction by Partial Matching) character-based text compression scheme in order to recognize Ekman’s six basic emotions (Anger, Disgust, Fear, Happiness, Sadness, Surprise). Experimental results with three datasets show that the new method is very effective when compared with traditional word-based text classification methods. We have also found that our method works best if the sizes of text in all classes used for training are similar, and that performance significantly improves with increased data.
(6)
(5)
This study aims to improve the quality of satellites signals in addition to increase accuracy level delivered from handheld GPS data by building up a program to read and decode data of handheld GPS. Where, the NMEA protocol file, which stands for the National Marine Electronics Association, was generated from handheld GPS receivers in real time using in-house design program. The NMEA protocol file provides ability to choose points positions with best status level of satellites such as number of visible satellite, satellite geometry, and GPS mode, which are defined as accuracy factors. In addition to fix signal quality, least squares technique was adopted in this study to minimize the residuals of GPS observations and enh
... Show MorePopulation growth and economic and industrial development coupled have significantly accelerated the rate of Land Use and Land Cover (LULC) changes, particularly in developing countries, so finding optimum ways to observe these change has become a pressing issue. Quantification evaluation of these changes is crucial to comprehend and oversee land management conversion, therefore, it is necessary to evaluate the accuracy of various algorithms for LULC classification to determine the most effective classifier for Earth observation applications. The performance of Maximum Likelihood (ML), Support Vector Machines (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN) was examined in this study, based on Sentinel 2A satellite images. T
... Show More
(1)
(2)
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 achieve
... Show More
(7)
(4)
The Character is one of the elements of Storytelling, as it is the center of the plot, making it the basis on which the talk is about. The talk is the portrayal of the character while they’re acting; the novelist presents the character by interacting with the events, and the extent of the negative and positive appearing impact on the character. It should be noted that everyone has two personalities or more, each one appearing in a different position or situation. For instance, a man can be a father, a lover, an employee, a son or anyone else .. in another position, he might be a master, and in another a looser begging for the mercy of his humiliator, and sometimes he can show weakness to the one he loves, or show strength to his enemie
... Show More
Early detection of brain tumors is critical for enhancing treatment options and extending patient survival. Magnetic resonance imaging (MRI) scanning gives more detailed information, such as greater contrast and clarity than any other scanning method. Manually dividing brain tumors from many MRI images collected in clinical practice for cancer diagnosis is a tough and time-consuming task. Tumors and MRI scans of the brain can be discovered using algorithms and machine learning technologies, making the process easier for doctors because MRI images can appear healthy when the person may have a tumor or be malignant. Recently, deep learning techniques based on deep convolutional neural networks have been used to analyze med
... Show More
(12)
Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19. These datasets were introduced to the combination network that contained deep lea
... Show More
(8)
(10)