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.
The new 4-[(7-chloro-2,1,3-benzoxadiazole)azo]-4,5-diphenyl imidazole (L) have been synthesized and characterized by micro elemental and thermal analyses as well as 1H.NMR, FT-IR, and UV-Vis spectroscopic techniques. (L) acts as a ligand coordinating with some metal ionsV(IV), Fe(III), Co(II), Ni(II), Cu(II), and Zn(II). Structures of the new compounds were characterized by elemental and thermal analyses as well as FT-IR and UV-Vis Spectra. The magnetic properties and electrical conductivities of metal complexes were also determined. Study of the nature of the complexes formed in ethanol following the mole ratio method.. The work also include a theoretical treatment of the formed complexes in the gas phase, this was done using the (hyperch
... Show More
(3)
Transforming the common normal distribution through the generated Kummer Beta model to the Kummer Beta Generalized Normal Distribution (KBGND) had been achieved. Then, estimating the distribution parameters and hazard function using the MLE method, and improving these estimations by employing the genetic algorithm. Simulation is used by assuming a number of models and different sample sizes. The main finding was that the common maximum likelihood (MLE) method is the best in estimating the parameters of the Kummer Beta Generalized Normal Distribution (KBGND) compared to the common maximum likelihood according to Mean Squares Error (MSE) and Mean squares Error Integral (IMSE) criteria in estimating the hazard function. While the pr
... Show More
This paper includes a comparison between denoising techniques by using statistical approach, principal component analysis with local pixel grouping (PCA-LPG), this procedure is iterated second time to further improve the denoising performance, and other enhancement filters were used. Like adaptive Wiener low pass-filter to a grayscale image that has been degraded by constant power additive noise, based on statistics estimated from a local neighborhood of each pixel. Performs Median filter of the input noisy image, each output pixel contains the Median value in the M-by-N neighborhood around the corresponding pixel in the input image, Gaussian low pass-filter and Order-statistic filter also be used. Experimental results shows LPG-PCA method
... Show MoreFour mixed ligand complexes were prepared from 1,10-phenanthroline (Phen), 5-chlorosalicylic acid (CSA), and anthranilic acid (Anthra) dissolved in aqueous ethanol at a ratio of (1:1:1:1) M: Phen:CSA: Anthra, M(II)= Cu, Zn, Cd, and Hg. The prepared compounds were analyzed by flame atomic absorption, FT—IR, UV-Vis, and spectroscopic methods, as well as conductivity measurements and magnetic properties. After analyzing the prepared compounds using the acquired data, the complexes formed by mixing ligands were concluded to adopt an octahedral geometry. That study has been conducted to test the inhibitory effectiveness of the complexes (1,10-Phenanthroline (Phen), 5-Chlorosalicylic acid (CSA), Na[Cu(Phen)(CSA)(Anthra), Na[Zn(Phen)(CSA)(Anthr
... Show MoreWe studied the relationship between DNA sequencing of interleukin-10 (IL-10) gene promoter for -1082 (A/G) and -592 (A/C) positions with the concentration of IL-10 in blood serum of Iraqi children with type 1 diabetes mellitus (T1D). Fifty blood serum samples collected from children with age ranged between 7-12 years. Thirty-five blood samples collected from patient children with T1D, and compared with 15 healthy children age matched as control sample. The results revealed decreasing in anti-inflammatory IL-10 concentration in T1D patient’s blood serum (0.068 Pg/ml) as compared with the control sample (0.111 Pg/ml). No significant differences were found in interleukin concentration between the studied samples when they analyzed with the M
... Show MoreThroughout this paper R represents a commutative ring with identity and all R-modules M are unitary left R-modules. In this work we introduce the notion of S-maximal submodules as a generalization of the class of maximal submodules, where a proper submodule N of an R-module M is called S-maximal, if whenever W is a semi essential submodule of M with N ? W ? M, implies that W = M. Various properties of an S-maximal submodule are considered, and we investigate some relationships between S-maximal submodules and some others related concepts such as almost maximal submodules and semimaximal submodules. Also, we study the behavior of S-maximal submodules in the class of multiplication modules. Farther more we give S-Jacobson radical of ri
... Show More
(3)
Throughout this paper R represents a commutative ring with identity and all R-modules M are unitary left R-modules. In this work we introduce the notion of S-maximal submodules as a generalization of the class of maximal submodules, where a proper submodule N of an R-module M is called S-maximal, if whenever W is a semi essential submodule of M with N ⊊ W ⊆ M, implies that W = M. Various properties of an S-maximal submodule are considered, and we investigate some relationships between S-maximal submodules and some others related concepts such as almost maximal submodules and semimaximal submodules. Also, we study the behavior of S-maximal submodules in the class of multiplication modules. Farther more we give S-Jacobson radical of rings
... Show More
|
Building Information Modeling (BIM) is becoming a great known established collaboration process in Architecture, Engineering, and Construction (AEC) industry. In various cases in many countries, potential benefits and competitive advantages have been reported. However, despite the potentials and benefits of BIM technologies, it is not applied in the construction sector in Iraq just like many other countries of the world. The purpose of this research is to understand the uses and benefits of BIM for construction projects in Iraq. This purpose has been done by establishing a fr |
The present work includes the preparation and characterization of{Co(II) , Ni(II), Pd(II), Fe(III) , Ru(III),Rh(III), Os(III) , Ir(III) , Pt(IV) and VO(IV)}complexes of a new ligand 4-[(1-phenyl-2,3-dimethyl-3-pyrozoline-5-one)azo]-N,N-dimethylanline (PAD). The product (PAD) was isolated,studies and characterized by phsical measurements,i.e., (FT-IR), (UV) Spectroscopy and elemental analysis(C.H.N). The prepared complexes were identified and their structural geometric were suggested in solid state by using flame atomic absorption, elemental analysis(C.H.N), (FT-IR) and (UV-Vis) Spectroscopy, as well as magnetic susceptibility and conductivity measurements . The study of the nature of the complexes formed in( ethanolic solution) following t
... Show More
The research aims to measure the impact of the quality of the audit on the Earnings Quality, for a sample of private joint stock companies listed on the Iraq Stock Exchange, as the research sample included (14) private and listed joint stock companies in issuing their financial statements for the period from (2010-2018), as well as companies The audit offices in charge of auditing these companies, which number (18) companies or an audit office, and the research relied on two main models for measurement, as the first model reflects the assumed relationship between independent variables represented in the characteristics of external audit quality and measuring the extent of its impact on the dependent variable represented in the Ea
... Show More