Science Journal of University of Zakho

HYBRID TECHNIQUE FOR SOFTWARE DEFECT PREDICTION USING MACHINE LEARNING TECHNIQUES

2025-06-11T02:05:36+03:00

Human errors during software development lead to many defects, which emphasizes the importance of early detection and minimization. However, existing approaches often fall short in delivering accurate, scalable, and generalizable predictions due to challenges such as class imbalance, feature extraction limitations, and computational inefficiencies. This study proposes a hybrid method using a Convolutional Neural Network (CNNs) + Long Short-Term Memory (LSTM) for feature extraction, addressing class imbalance with Adaptive Synthetic Sampling (ADASYN) and subsequent training using Extreme Gradient Boosting (XGboost), to predict software defects. The proposed approach was evaluated on five publicly available datasets (CM1, MC1, KC1, PC1, and PC4) and compared with state-of-the-art (SOTA) models. Experimental results demonstrated that the hybrid model significantly outperforms traditional XGBoost-based models in terms of recall, F1-score, and area under the receiver operating characteristic curve (AUC), addressing the shortcomings of existing methods. Results demonstrate the effectiveness of the proposed method, with notable performance metrics achieved across all datasets. For example, on the MC1 dataset, the model attained an accuracy of 0.9980, a precision of 0.9971, a recall of 0.9988, an F1-score of 0.9980, and an AUC-ROC of 0.9999. On the KC1 dataset, it achieved an accuracy of 0.9344, a precision of 0.9265, a recall of 0.9375, an F1-score of 0.9320, and an AUC-ROC of 0.9839. The model achieves better performance than traditional machine learning methods and separate deep learning models, especially in the areas of recall and AUC-ROC. This research presents a robust solution through hybrid approaches that address class imbalance and maintain high predictive accuracy for software development process tasks, offering insights into the trade-offs between machine learning and deep learning methods.

DIETARY TURMERIC (Curcuma longa) ENHANCES GROWTH, ANTIOXIDANT DEFENSE, AND IMMUNITY IN Cirrhinus mrigala

2025-07-25T18:49:28+03:00

Aquaculture is pivotal in addressing global food security, yet intensive practices compromise fish health and productivity. This study investigated the efficacy of dietary turmeric (Curcuma longa) supplementation as a natural alternative in Cirrhinus mrigala, a species critical to South Asian aquaculture. A 60-day feeding trial evaluated four diets: control (0% turmeric), 0.5%, 1.0%, and 1.5% turmeric inclusion. Results demonstrated that 1.0% turmeric significantly enhanced growth performance, with a 28% increase in final body weight (19.6 ± 1.4 g vs. 15.7 ± 1.1 g in control; p< 0.01) and improved feed conversion ratio (1.4 ± 0.2 vs. 1.7 ± 0.2; p= 0.004). Antioxidant enzyme activities (SOD, CAT, GPx) increased by 34–53%, while lipid peroxidation (MDA) decreased by 29% (p = 0.001), indicating robust oxidative stress mitigation. Immunological assays revealed a 65% rise in lysozyme activity and 70% higher phagocytic capacity (p< 0.01), underscoring turmeric’s immunostimulatory potential. The hepatosomatic index decreased by (1.3 ± 0.2% vs. 1.4 ± 0.2%; p = 0.038), suggesting increased metabolic efficiency. These findings highlight 1.0% turmeric as the optimal dosage, offering a sustainable strategy to augment aquaculture productivity while reducing reliance on antibiotics

IMPACT OF VARYING AMOUNTS OF PEANUT (Arachis hypogaea) MEAL ON RAINBOW TROUT (Oncorhynchus mykiss) DIETS INSTEAD OF SOYBEAN MEAL ON THE ELEMENTAL COMPOSITION AND BIOMAGNIFICATION FACTORS IN FILLETS

2025-08-07T21:25:16+03:00

In this study, the effects of using different ratios of peanut meal (PNM) instead of soybean meal in rainbow trout (Oncorhynchus mykiss) diet on elemental composition and biomagnification factor (BMF) were evaluated for 12 weeks. Three experimental diets containing 50% (PNM₅₀), 75% (PNM₇₅), and 100% (PNM₁₀₀) peanut meal were prepared. In the study, two control groups were fed a commercial feed (CF) and a diet containing 0% PNM (C), respectively. The CF had the greatest Ca/P ratio and the highest Se, Ca, and P levels, and these values were also significantly different from the other experimental diets. The PNM₇₅ diet had significantly higher Mn and Cu values (p<0.05). Fe, Mg, and Na levels increased with the increasing level of PNM ratios. The PNM100 group had the highest values of these elements. At the end of the study, the CF group had high BMF of K, Mg, Mn, and Cu elements. Compared with the C group, rainbow trout fillets in the CF group had high BMFs of Ca, Fe, Na, and Se. The BMF of the P element was high in PNM75 group. In summary, the element values of rainbow trout fillets did not have an adverse effect when using PNM instead of soybean meal in their diets

MULTI-CLASSIFICATION OF EYE DISEASES USING A CNN-HARALICK HYBRID FRAMEWORK

2025-06-12T00:07:10+03:00

The detection and classification of eye diseases, including Diabetic Retinopathy, Cataract, and Normal conditions, are critical in medical imaging for early diagnosis and treatment. This study proposes a hybrid CNN-Haralick model, leveraging the lightweight MobileNetV2 CNN architecture for spatial feature extraction and Haralick texture features extraction for texture analysis to enhance the accuracy of eye disease classification. A dual-branch architecture is employed, which fuses features from both the Convolutional Neural Network and the Haralick-based texture analysis at an early stage. The model is evaluated on a dataset consisting of images from multiple sources. Experimental results show that the hybrid CNN-Haralick model achieves an overall accuracy of 98% on the validation set, outperforming traditional CNN models. The model demonstrates exceptional performance, with a macro average F1-score of 98% for the three classes, and AUC-ROC scores of 100% for each category. The confusion matrix and classification report further validate the model's capability to accurately classify eye diseases, providing reliable decision support for clinicians. Additionally, the model's effectiveness is discussed in comparison with existing works, highlighting its superior performance in terms of both accuracy and computational efficiency.

EFFECT OF DIFFERENT LIGHT TYPES AND EXPOSURE DURATIONS ON STOMATAL CHARACTERISTICS IN TWO CULTIVARS OF CARNATION (Dianthus caryophyllus L.)

2025-08-08T13:44:28+03:00

A study was conducted to examine the effects of different light types, colors, and exposure durations on the morphological and stomatal characteristics of two carnation (Dianthus caryophyllus) cultivars, Ormea and Moonlight, cultivated under controlled greenhouse conditions, during the period of (2024 - 2025) at the College of Agricultural Engineering Sciences, University of Duhok, to understanding how Light quality and photoperiod play a crucial role in regulating stomatal density, size, and function, which are vital for key physiological processes such as transpiration and photosynthesis. The results indicate that specific light treatments significantly influence both morphological traits and stomatal parameters. The highest leaf number, leaf length, and leaf area per plant, were measured under 14-hour incandescent lighting (42.872 leaves/plant, 13.050 cm, and 25.801 cm²), respectively, followed by 14h LED-mix (39.37leaves/plant, 12.020 cm and 24.218cm²), respectively. Similarly, the longest leaf observed on the Ormea cultivar (12.336 cm) when exposed to 14 hours of incandescent light significantly outperformed other treatments. While the results of the interaction between cultivar and light on stomatal density and number showed that the Moonlight cultivar could achieve higher stomatal densities and stomatal numbers when exposed to 14 hours of incandescent. On the other hand, the Ormea and Moonlight cultivars showed the highest significant increase in stomatal densities (96.482 and 95.587) in the lower epidermis when exposed to 14 hours of incandescent lights. In the Ormea cultivar, growing under incandescent light for 14h caused a notable increase in both stomatal length and width (24.978 and 13.389 µm), followed by stomatal length and width (24.533 and 13.067 µm), respectively, under LED-mix for 14h

NUMERICAL SOLUTION OF CUBIC-QUINTIC NONLINEAR SCHRÖDINGER EQUATION

2025-06-22T00:45:25+03:00

This paper is devoted to investigating and comparing the variational iteration method (VIM) and the residual power series method (RPSM) for solving the cubic-quintic nonlinear Schrödinger equation (CQNLSE) initially developed to elucidate the propagation of pulses in optical fibers. Next, we use the initial conditions to get the numerical solutions of the CQNLSE. We compared the known exact solutions with the approximate results obtained using both the VIM and RPSM. The exact solution and the results from RPSM are evaluated against those from VIM. The findings demonstrated that VIM outperformed RPSM in terms of accuracy, efficiency, and ease of implementation for solving the CQNLSE. In addition, the current results are shown graphically and in the table

ENHANCING GROWTH PERFORMANCE, ANTIOXIDANT DEFENSE, AND IMMUNE RESPONSE IN STRIPED CATFISH (Pangasius hypophthalmus) THROUGH DIETARY SUPPLEMENTATION WITH Aloe vera: A SUSTAINABLE AQUACULTURE APPROACH

2025-07-31T13:04:29+03:00

A 60-day feeding trial was conducted to investigate the effects of dietary Aloe vera leaf powder supplementation on growth performance, hematological parameters, antioxidant status, and immune responses in Pangasius hypophthalmus. A total of 300 juvenile striped catfish with an initial weight of 14.2±0.13 g was randomly allocated to five dietary treatments containing 0% (control), 0.5%, 1%, 2%, and 4% Aloe vera leaf powder, with three replicates per group. Results reveal significant dose-dependent enhancements in growth parameters, with the 2% Aloe vera group exhibiting the highest final weight 72.21±1.54 g, weight gain 371.1±4.5%, and specific growth rate (3.21 ± 0.03%/day), alongside the lowest feed conversion ratio (1.54 ± 0.01) (p<0.05). Hematological analysis revealed enhanced red blood cell count (2.32±0.06 ×10⁶/μL), hemoglobin levels (9.0±0.3 g/dL), and white blood cell count (66.5±2.1 ×10³/μL) in the 2% group. Antioxidant enzyme activities (Superoxide dismutase (SOD), Catalase (CAT), and Glutathione peroxidase (GPx)) increased by 52.1%, 36.2%, and 27.8%, respectively, while malondialdehyde levels decreased by 31.8% related to the (control; p<0.05). Immune parameters were also significantly elevated, including lysozyme activity (14.3±0.5 U/mL) and phagocytic index (33.87±1.3%). These findings indicate that 2% Aloe vera supplementation optimally enhances growth, physiological resilience, and disease resistance in P. hypophthalmus, offering a sustainable alternative to synthetic additives in aquaculture

GREEN-SYNTHESIZED ZINC OXIDE NANOPARTICLES FROM VERJUICE (Vitis vinifera) EXHIBIT HEPATOPROTECTIVE AND ANTIOXIDANT EFFECTS AGAINST CARBON TETRACHLORIDE -INDUCED TOXICITY IN MALE RATS

2025-07-20T19:24:37+03:00

Drug-induced liver injury, particularly that caused by carbon tetrachloride (CCl₄), poses significant clinical challenges due to oxidative stress and limited therapeutic options. This study investigated the hepatoprotective and antioxidant potential of green-synthesized zinc oxide nanoparticles (ZnO-NPs) using verjuice extract from unripe grapes in a CCl₄–induced rat model. The ZnO-NPs were characterized using UV-visible spectroscopy, X-ray diffraction, fourier transform infrared (FTIR) scanning electron microscopy, and energy-dispersive X-ray spectroscopy (EDX) analyses. Twenty male Wistar rats were assigned to four groups: control, CCl₄ toxicity (1 mL/kg twice weekly for 4 weeks), co-treatment (CCl₄ + ZnO-NPs 50 mg/kg daily for 4 weeks), and ZnO-NP post-treatment (CCl₄ for 4 weeks followed by ZnO-NPs 50 mg/kg daily for 4 weeks). ZnO-NPs significantly restored superoxide dismutase (SOD) activity and decreased malondialdehyde (MDA) levels to near control values, while normalizing alanine aminotransferase (ALT), aspartate aminotransferase (AST), and alkaline phosphatase (ALP) activities. Histopathological evaluation confirmed near-complete recovery of hepatic and renal architectures. These results demonstrate that verjuice-synthesized ZnO-NPs exert potent antioxidant and regenerative effects through the preservation of endogenous defenses and promotion of tissue repair, and the green synthesis approach offers an eco-friendly, biocompatible nanotherapeutic strategy with promising applications for drug-induced liver injury

EVALUATION OF NATURAL RADIOACTIVITY LEVELS AND CORRESPONDING DOSE RATES IN SOIL SAMPLES COLLECTED FROM DUHOK PROVINCE, KURDISTAN REGION-IRAQ

2025-05-29T23:31:55+03:00

ABSTRACT:

One of the significant concerns in daily human life is exposure to elevated levels of natural background radiation, both outdoors and indoors. This radiation primarily originates from primordial radioisotopes such as Uranium, Thorium, and Potassium, which emit harmful gamma rays. This study examines the activity concentrations of natural radioisotopes Ra-226, Th-232, and K-40 in soil samples collected from various locations in the Duhok Governorate, northern Iraq. To the best of our knowledge, comprehensive studies on these three radioisotopes in this region are limited, highlighting the novelty of this work. Gamma-ray spectrometry using a high-purity NaI(Tl) detector was employed to measure activity concentrations. Several radiological parameters were assessed, including the radium equivalent activity (Ra_eq), indoor and outdoor absorbed dose rates (D_in, D_out), internal and external hazard indices (H_in, H_ex), and annual effective dose rates (AE_in, AE_out). Results showed average concentrations of 30 Bq/kg for Ra-226, 56 Bq/kg for Th-232, and 145 Bq/kg for K-40. While Ra-226 and K-40 levels were within global safety limits, Th-232 exceeded recommended values, raising potential health concerns

POLLEN MICROMORPHOLOGY OF FOUR Onobrychis SPECIES (Fabaceae) FROM THE KURDISTAN REGION OF IRAQ

2025-07-27T09:45:30+03:00

Polleniferous materials of four Onobrychis species were used in this study. Two different microscopes and one-way ANOVA analysis were applied. The pollen grains were tricolpate, isopolar, and consistently radially symmetrical. The value of the polar axis/equatorial diameter ranged from prolate to perprolate, which were categorized as tiny or medium in size. Exine sculpture patterns varied significantly when scanning electron microscopy was used: Onobrychis megataphora, O. crista-galli, and O. caput-galli have reticulate patterns; O. galegifolia has micro-reticulate perforates. The pollen morphology of O. caput-galli was noticeably perprolate due to its maximum polar axis/equatorial diameter value (2.02 µm). The O. crista-galli had the lowest polar axis/equatorial diameter value (1.37 µm), showing its prolate pollen morphology. A one-way ANOVA analysis revealed significant differences (P < 0.05) in the morphological features of polar length and equatorial diameter. The O. megataphros was primarily circular to ovoid-triangular in form, and O. caput-galli had a triangular outline. The two remaining species had circular shapes in polar view. In equatorial view, two species had elliptic-elongated shapes, while others had rectangular-obtuse outlines. Thus, these micromorphological dissimilarities indicate variations among taxa, and they can be used as taxonomic characters to identify and delimit Onobrychis species

IMPACT OF VITAMIN D STATUS, IRON PROFILES, AND TRACE ELEMENTS IMBALANCES ON CARDIOMETABOLIC RISK FACTORS IN WOMEN WITH SUBCLINICAL HYPOTHYROIDISM

2025-06-19T12:27:58+03:00

The main aim of this study was to elucidate the impact of vitamin D, iron profile, and trace elements imbalances on cardiometabolic risk factors in newly diagnosed women with subclinical hypothyroid. Fifty newly diagnosed subclinical hypothyroid (SCHT) females, aged 18-50 years, and 40 healthy females matched in age with patients were enrolled in the present study. Thyroid-stimulating hormone (TSH), Free thyroxin (FT4), Free triiodothyronine (FT3), vitamin D, and serum ferritin were measured using an electrochemiluminescence assay. Lipid profile, serum iron (Fe), and unsaturated iron binding capacity (UIBC) were analyzed by a photometric measuring unit. Serum zinc (Zn), magnesium (Mg), and copper (Cu) were quantified using a colorimetric method. The current study indicated a significant increase in cardiometabolic risk factors such as fasting blood sugar (FBS), lipid profile, Triglyceride-glucose index (TyGi), and Atherogenic index of plasma (AIP) in SCHT, in contrast to the healthy group. Furthermore, a strong association was noted between elevated TSH and lipid profile, fasting blood sugar, AIP, and TyGi. Additionally, a substantial association was indicated between reduced vitamin D, ferritin, magnesium levels, and elevated copper levels with cardiometabolic risk factors. The current study concluded that low vitamin D, ferritin, magnesium levels, and elevated copper levels are linked with cardiometabolic risk factors in females diagnosed with subclinical hypothyroidism. Reduced vitamin D, magnesium levels, disrupted iron metabolism, and elevated serum copper were linked to heightened atherogenic risk and metabolic abnormalities

SIMULATION DESIGN OF HYBRID RENEWABLE ENERGY SYSTEMS AT THE COLLEGE OF SCIENCE IN THE UNIVERSITY OF ZAKHO, IRAQ

2025-05-15T18:27:30+03:00

Utilising renewable energy sources (RESs) instead of conventional power generation methods is crucial for mitigating climate change and global warming. As in other cities of the Kurdistan Region and Iraq, the national electricity outage crisis persists in Zakho, and power production via various sources remains necessary. In this study, the optimisation program 'Hybrid Optimisation Model for Electric Renewables' HOMER Pro has been utilised to simulate two solar energy systems: grid-connected and off-grid. The systems are modelled for installation on the roof of the College of Science building at Zakho University, Iraq, which operates for 6 hours daily, from 9:00 a.m. to 3:00 p.m., Sunday to Thursday, while electricity consumption is extremely low during the summer weekends. Our findings confirm that the on-grid system is the more favourable option, with a cost of energy (COE) of $0.0194/kWh and a net present cost (NPC) of $295,544. On the other hand, the stand-alone design has a COE of $0.159/kWh and an NPC of $699,14. Moreover, the on-grid model derives 96% of its energy from renewable sources; whereas, the grid-independent design achieves 91.2%

IRRIGATION WATER QUALITY ASSESSMENT USING CROSS IN DUHOK GOVERNORATE, KURDISTAN REGION OF IRAQ

2025-06-16T19:31:44+03:00

This study was conducted in the Duhok Governorate, Kurdistan Region of Iraq. A total of eleven natural water samples were collected from different water sources, including Rivers, lakes, wells, and drainage canals. All samples were analyzed in triplicate to ensure accuracy and reproducibility. Electrical Conductivity (EC), pH, Bicarbonate (HCO₃⁻), major Cations: Calcium (Ca²⁺), magnesium (Mg²⁺), Sodium (Na⁺), and Potassium (K⁺) were determined.

Sodium (Na) levels ranged from 0.075 to 34.883 mmol_c L⁻¹, with Kashi exhibiting the highest concentration, while the lowest one was registered in the Khabur River 0.075 mmol_cL⁻¹). Potassium (K) concentration was generally low across all samples, with a mean of 3.253 mmol/L. Khabur River had the lowest across all samples (0.055 mmol_c L⁻¹). The highest was in Hishkarow (0.63 mmol_cL⁻¹). Calcium levels vary widely from 1.05 to 5.4 mmol_c L⁻¹, with Bedol River showing the highest Ca concentration. Magnesium levels were higher than Ca in some samples. Qasara well 2 had the highest magnesium (Mg) concentration (6.00 mmol_c L⁻¹), while the lowest was determined in Bedol River (0.6 mmol_c L⁻¹). The adjusted Ca concentrations ranged from 0.907 to 3.548 mmolc L⁻¹, with the highest value in Duhok Dam. Highest Kashi EC (4.290 dS. m⁻¹) indicates very high salinity, which may affect water usability for irrigation, in contrast to the lowest in Bedol River (0.406 dS. m⁻¹), which suggests good water quality with low dissolved salts. Sodium Adsorption Ratio (SAR) was the highest for Kashi (17.082), indicating a high risk of soil dispersion if used for irrigation; however, the lowest was (0.056) for Khabur River, suggesting no salinity hazard. CROSS values ranged from 0.091 to 18.368, and CROSS (using adj. Ca) ranged from 0.103 (Khabure River) to 24.341 in (Kashi).

The results highlighted variation in all parameters, influencing the suitability of these water sources for irrigation. The best water source for agriculture is the Khabur River, which has the lowest Na, EC, and SAR values, making it the best choice. The worst water source is Kashi, which has extremely high sodium, EC, and SAR values, making it unsuitable for irrigation. Municipal and Dam water, generally moderate in all parameters, making them safer for multiple uses. In contrast, well water varies but tends to have higher magnesium levels

DIAMETER INCREMENT ESTIMATIONS OF Pinus brutia Ten. FORESTS STAND OF DUHOK GOVERNORATE, KURDISTAN REGION, IRAQ

2025-06-18T22:48:21+03:00

Pinus brutia Ten., a native eastern Mediterranean conifer, is prominent in northern Iraq and has enormous importance in the stability of ecosystems, biodiversity, and landscape protection. This study was conducted on Calabrian pine populations sampled from three ecologically differentiated sites in Duhok Province, Kurdistan Region, Iraq. Fifteen trees were selected, five per site, four of which will be used in a model calibration and one will be used for validation. Partial stem analysis was conducted by extracting cross-sections at breast height diameter. Despite the small sample size, the dataset provided sufficient observations for reliable statistical modeling. A systematic model selection framework was employed, incorporating tests of model assumptions, goodness of fit metrics, residual diagnostics, the Salih index to enhance the precision of Ohtomo’s test, R² interpretation, the Furnival index, and the Bias percent test. Allometric regression models were developed using STATGRAPHICS Centurion 19 software, and both homogeneous and heterogeneous forms were assessed. A t-test confirmed the reliability of the calibration models. Site-specific equations were derived based on the best-fitting regression forms: a curvilinear model was selected for both Zawita (Di = 6.2 − 1.2119 × ln(D)) and Atrush (Di = 14.8 − 2.8561 × ln(D)), while a square root transformation yielded the best fit at Belkef (Di = 14.1 − 1.7501 × √D)

ENHANCING NONLINEAR EQUATION SOLUTIONS THROUGH THE COMBINATION OF VARIANT NEWTON’S AND HALLEY’S METHODS

2025-07-20T22:18:01+03:00

This work presents a new iterative method for solving single-variable nonlinear equations. The method achieves ninth-order convergence with just three derivative evaluations per step, offering both accuracy and lower computational cost. Unlike slower bracketing methods, it builds on faster open methods, though these may sometimes fail to converge. By blending ideas from Newton's and Halley's methods, the new approach provides strong performance, as shown by a detailed convergence analysis and MATLAB tests. Compared to existing techniques, it finds solutions in fewer steps and less time, making it especially effective for difficult nonlinear problems

A PRUNED VGG16 WITH HYBRID PREPROCESSING AND DATA BALANCING FOR ROBUST AND INTERPRETABLE LUNG CANCER CLASSIFICATION

2025-06-25T13:40:21+03:00

Lung cancer is the most common and deadliest type of cancer globally, creating a critical need for diagnostic tools that are not only accurate but also practical for clinical integration. This study introduces a robust, computationally efficient, and interpretable deep learning framework using Computed Tomography (CT) images to address limitations in existing models, such as high computational costs, poor data quality, and a lack of transparency. Our approach utilizes a VGG16 architecture, streamlined through structured pruning, which reduced the parameter count from 138.3M to 26.6M without compromising performance. We developed a hybrid pipeline with dual filtering and adaptive CLAHE to enhance image quality, while data diversity and imbalance were mitigated using hybrid augmentation and SMOTE. The model was trained with a rigorous strategy, including four-fold cross-validation and dual-phase fine-tuning with a dynamic learning rate, ensuring stable convergence. On a primary single-source dataset, the model achieved a test accuracy of 0.9910 and a Matthews Correlation Coefficient (MCC) of 0.9845. To validate real-world applicability, the framework was tested on a large multi-source dataset, demonstrating strong generalization with a balanced accuracy of 0.9693 and an MCC of 0.9427. Model interpretability was confirmed using Grad-CAM visualizations to highlight clinically relevant regions. This framework provides a highly accurate, computationally efficient, and generalizable solution with significant potential for clinical deployment as a reliable diagnostic aid