Science Journal of University of Zakho

Deep Learned Feature Technique for Human Action Recognition in the Military using Neural Network Classifier

2025-05-18T20:13:55+03:00

Assessing military trainee in an obstacle crossing competition requires an instructor to go along with participants or be strategically placed. These assessments sometimes suffer from fatigue or biasedness on the part of instructors. There is the need to have a system that can easily recognize various human actions involved in obstacle crossing and also give a fair assessment of the whole process. In this paper, VGG16 model features with neural network classifier is used to recognize human actions in a military obstacle-crossing competition video sequence involving multiple participants performing different activities. The dataset used was captured locally during military trainees’ obstacle-crossing exercises at a military training institution to achieve the objective. Images were segmented into background and foreground using a Grabcut-based segmentation algorithm. On the foreground masked images, features were extracted and used for classification with neural network. This method used the VGG16 model to automatically extract deep learned features at the max-pooling layer and the input presented to neural network classifier for classification into the various classes of human actions achieving 90% recognition accuracy which is at training time of 104.91secs. The accuracy obtained showed 3.6% performance improvement when compared to selected state-of-the-art model. The model also achieved 90.1% precision value and recall of 90.2%. Although many studies have focused on human recognition action recognition in several application areas, this study introduced a novel model for real time recognition of fifteen different classes of complex actions involving multiple participants during obstacle crossing competition in a military environment leveraging on the strength of deep learning and neural network classifier. This study will be of immense unbiased benefit to the military in the assessment of a trainee’s performance during training exercises or competitions.

COMPARATIVE ANALYSIS OF GROWTH PERFORMANCE AND PROXIMATE BODY COMPOSITION IN Hypophthalmichthys molitrix AND Labeo rohita FED DIET WITH RICE PROTEIN MEAL

2025-03-28T03:05:18+03:00

The present study evaluated the role of rice protein meal (RPM) as a cost-effective and widely available plant-based protein source in the diets of H. molitrix (Silver Carp) and L. rohita (Rohu). 360 fingerlings were randomly assigned to 18 aquaria (20 fingerlings/aquaria) after a 1-week of acclimation period. There were three-dietary groups, T0: control, T1:RPM5%, and T2:RPM10%, each with triplicates. The trial lasted for 60 days. Results showed that treatment T2 exhibited significantly higher (weight, Protein efficiency ratio, Specific growth rate) performance. T2 showed higher weight gain (3.53 ± 0.05^a) compared to T0 and T1 in Rohu (P < 0.0001), and silver carp had significantly higher weight gain in T1 (2.42 ± 0.08^b) and T2 (2.61 ± 0.09^a) treatments compared to the T0 group (2.31±0.06^c). In Rohu, PER and SGR were also observed to be higher (P < 0.001) in treatment groups, particularly in T2, than control group, and also observed comparable outcomes in silver carp. Proximate body composition analysis revealed that T2 had significantly (P < 0.05) higher moisture, crude protein, and ash content. Notably, Rohu in the T0 group exhibited higher crude fat levels; similarly, silver carp in T2 showed similar results. T2 was most effective in promoting sustainable growth and improving nutrient utilization in both species

DNA BARCODING OF Adansonia digitata USING MULTI-LOCI GENE REGIONS (ITS, rbcL, rpoC1 and psbA-trnH)

2025-04-06T11:45:48+03:00

Adansonia digitata, also known as Baobab, is a tree species endemic to Africa. It belongs to the family Malvaceae. The species holds immense economic, cultural, and scientific value worldwide. As a result, it has been introduced to other parts of the world such as India, Sri Lanka, and Australia. Despite its immense value, information on its DNA barcodes for effective identification and conservation efforts of the species is inadequate in the literature. This study aimed to molecularly characterize A. digitata found in Nigerian flora using DNA barcodes from ITS, rbcL, rpoC1, and psbA-trnH primers. DNA was isolated from young leaves, and Sanger sequencing reactions were subsequently performed. Sequences obtained from each primer were subjected to Basic Local Alignment Search Tool (BLAST) analyses conducted on the National Center for Biotechnology Information (NCBI) website. A high percentage similarity range of 98-100% was recorded. Phylogeny was inferred using the Maximum likelihood method with a bootstrap test of 1000 replications. Results revealed a successful species-level identification of A. digitata by rbcL, ITS, and PsbA-trnH primers, as the consensus clustered with identical species with 39%, 88%, and 57% bootstrap support values, respectively. The DNA barcode of A. digitata obtained from the rpoC1 primer submitted to the NCBI nucleotide database with accession number OR251003.1 is the first to be submitted to the database. The accession numbers for the rbcL, ITS, and PsbA-trnH primers are OQ694034, OP709538, and OR135362 respectively. This study provides DNA barcodes for the identification of A. digitata relevant for research, economic, and conservation endeavours.

ROLE OF ALGAE AND SEAWEED EXTRACT AS BIO-FERTILIZER IN IMPROVING GROWTH, YIELD, AND YIELD COMPONENTS OF ROSELLE (Hibiscus sabdariffa L.)

2025-05-09T13:53:48+03:00

Universal climate change causes to think about applying bio-fertilizers as an alternative way of using synthetic fertilizers, since more uses of artificial fertilizers are contaminating the soil, water, and air, and also it is the major contributor to raise greenhouse gas (GHG) emissions and lastly, harming the earth. During this current study, green algae and seaweed were used as a bio-fertilizer to provide soil nutrients resulting in higher roselle (Hibiscus sabdariffa L.) crop productivity. Different levels of algae (0.0, 0.5 and 1.0 t ha^-1) and also seaweed (0.0 and 0.5 t ha^-1), were applied to the soil. Seeds of roselle were sowed in the summer season of 2024. Results presented that applying 0.5 t ha^-1 of algae was superior on other levels and also on seaweed for most of the growth and yield parameters of roselle plant, such as stem diameter, number of branches per plant, number of fruits per plant, and calyx dry weight (23.3mm, 9.7, 84.3, and 20.0 g plant^-1), respectively. While, the longest fruit length was recorded for algae at the level of 1.0 t ha^-1 by (31.5mm). Generally, green algae were better than seaweed for all productivity characteristics. This makes us pay more attention to protect the environment and sustainable agriculture through applying algae

A NOVEL VITBILSTM DEEP LEARNING FRAMEWORK FOR BRAIN HEMORRHAGE PREDICTION USING CT BRAIN IMAGES

2025-04-02T16:27:52+03:00

Bleeding in the surrounding tissues of the human brain is called a brain hemorrhage. This problem can lead to stroke and even death. It requires fast intervention and accurate treatment to save a patient’s life. Current state-of-the-art methodologies to detect this issue benefit from the development in the artificial intelligence field, especially its sub-filed “deep learning”. This study introduces a new deep learning-based framework to detect brain hemorrhage inside CT brain images. The proposed model is a novel hybrid model of vision transformer models and the bidirectional long short-term memory and is denoted as “ViTBiLSTM”. The study utilizes two datasets, which are different in size and challenging. The first dataset consists of 6772 CT images, while the second one contains 2500 CT images. The study also compares the original vision transformer model with the proposed one. Besides that, the study utilizes different optimizers and compares the current research with the related work. Results show that the proposed ViTBiLSTM achieves its best performance when using the RMSProp optimizer with an accuracy of 100% and 96.94% on both datasets. Comparison with the current state of the art shows that the proposed methodology’s performance exceeds the best study by 3.7% in accuracy.

ADVANCEMENTS IN TRANSFER LEARNING: A COMPREHENSIVE REVIEW OF NOVEL APPROACHES FOR MRI BRAIN IMAGE DIAGNOSIS

2025-03-24T22:54:14+03:00

Magnetic Resonance Imaging (MRI) has rapidly advanced and established itself as an indispensable tool in both the detection and diagnosis of several diseases, most notably brain tumors. The interpretation of MRI scans still largely relies on expert radiologists, which can be time-consuming and potentially subject to variability. Transfer learning (henceforth, TL) approaches show potential for improving diagnostic precision in medical imaging analysis. In this literature review, the potential of MRI scans in classifying and detecting various medical conditions, such as glioma and Alzheimer’s, is discussed alongside current algorithmic limitations. Current research indicates potential challenges in adapting existing supervised deep learning algorithms that process MRI images to more efficient approaches. The findings suggest a notable increase in the quality of detecting sub-pathologies, even with a scarcity of well-annotated images. This can potentially reduce the training cycle duration. When transfer learning is applied to diagnostic approaches, it may act as supplemental support for decision-making processes for tumorous growth detection, potentially reducing the time period for treatment and increasing effectiveness according to preliminary research. This review examines the expansion in transfer learning in MRI for the assessment and treatment of brain disorders through recent algorithms from the current literature.

A HYBRID APPROACH FOR MALARIA CLASSIFICATION USING CNN-BASED FEATURE EXTRACTION AND TRADITIONAL MACHINE LEARNING CLASSIFIERS

2025-04-23T17:51:48+03:00

Malaria is a major global health threat, and timely and correct diagnosis is essential for effective treatment. Traditional diagnostic methods, such as the microscopic examination of blood smears, are time-consuming and require expert personnel. The study presents a mix of machine learning methods for automatic diagnosis of malaria by using the feature extraction capability of Convolutional Neural Networks (CNNs) along with the efficient classification performance of traditional machine learning classifiers. For our study, we utilize VGG16 CNN with a weight pre-trained on ImageNet to extract the features from non-infected and infected blood cell images from malaria. Five classical machine learning algorithms, such as Random Forest, Logistic Regression, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), & Gradient Boosting, are used to classify the extracted features. Each classifier's performance is calculated based on accuracy, F1 score, precision, and recall metrics. The results of our experiments showed that the hybrid model has high accuracy in classification, where the Logistic Regression classifier could achieve above 93% accuracy. This hybrid method is a powerful diagnostic for malaria disease, accomplishing a more satisfactory compromise between the efficacy of the deep learning architectures such as CNNs, and the computational capabilities of more conventional classifiers. It holds promise for deployment into resource-limited settings where fast, automated threading diagnostic systems are much needed

ON NIL-SYMMETRIC RINGS AND MODULES SKEWED BY RING ENDOMORPHISM

2025-05-29T22:26:28+03:00

The symmetric property plays an important role in non-commutative ring theory and module theory. In this paper, we study the symmetric property with one element of the ring and two nilpotent elements of skewed by ring endomorphism on rings, introducing the concept of a right - -symmetric ring and extend the concept of right - -symmetric rings to modules by introducing another concept called the right - -symmetric module which is a generalization of -symmetric modules. According to this, we examine the characterization of a right - -symmetric ring and a right - -symmetric module and their related properties including ring and explore their connections to other classes of rings and modules. Furthermore, we investigate the concept of - -symmetric on some ring extensions and localizations like Dorroh extension, Jordan extension and module localizations like

PROTECTIVE ROLES OF Lactuca serriola AND Glycyrrhiza glabra ON ETHYLENE GLYCOL INDUCED UROLITHIASIS IN MALE ALBINO RATS (Rattus norvegicus)

2025-03-28T02:59:24+03:00

This study aimed to evaluate the protective effects of Lactuca serriola (L. serriola) and Glycyrrhiza glabra (G. glabra) against ethylene glycol (EG)-induced urolithiasis in male albino rats. Twenty-eight rats were divided into four groups: control, EG-treated, and two groups co-administered with L. serriola or G. glabra alongside EG. Body weight, food and water intake, kidney and liver function, serum electrolytes, and lipid profiles were assessed. Histological examination and urine crystal analysis were also performed. Co-administration of L. serriola and G. glabra protected against EG-induced increases in serum creatinine, urea, and glutamic oxaloacetic transaminase (GOT) levels. Lactuca serriola also prevented triglyceride (TG) elevation, while G. glabra effectively maintained food intake. Both herbs significantly reduced the kidney weight increase, crystal formation, and tissue damage. Histological analysis showed reduced calcium oxalate (CaOx) crystal deposition and tissue injury with herb supplementation. In conclusion, L. serriola and G. glabra demonstrated protective roles against urolithiasis and may serve as potential natural anti-urolithiasis agents

CARDIOVASCULAR BIOMARKERS, TYG INDEX AND TG/HDL-C RATIO IN SUBCLINICAL HYPOTHYROIDISM PATIENTS

2025-05-13T10:11:08+03:00

Subclinical hypothyroidism (SCH) is characterized by exhibiting a normal value of free thyroxine (T4) and excessive blood thyroid-stimulating hormone (TSH) concentration. SCH may be regarded as a prevalent concern of the emergence of overt hypothyroidism and cardiovascular disease (CVD). Disturbance in irisin, visfatin, NADPH oxidase, triglyceride/high-density lipoprotein-cholesterol (TG/HDL-c) ratio, and triglyceride glucose (TyG) index are associated with an increased cardiometabolic risk. The present study aimed to investigate serum levels of visfatin, irisin, NADPH oxidase (gp91^phox), TyG index, TG/HDL-c ratio, and anti-TPO in patients with SCH in comparison to apparently healthy individuals. A study of the case-control method was carried out at Vin Specialist Laboratory, Kurdistan Region, Iraq, involving 146 subjects, including 73 newly diagnosed subclinical hypothyroid patients and 73 healthy controls. Biochemical tests such as glucose, TSH, FT4, FT3, Anti-Thyroid Peroxidase (anti-TPO), TG, and HDL-C were analyzed using Cobas6000 (Roche), whereas, enzyme-linked immunosorbent assay was conducted to estimate the value of serum visfatin, NADPH oxidase (gp91^phox) and irisin. There was significantly a higher mean serum level of NADPH oxidase in 73 patients with SCH compared to that of 73 healthy individuals (8.73±2.89 ng/mL, 6.41±1.23 ng/mL, P=0.004). Mean serum levels of visfatin (41.29±8.16 ng/ml) and NADPH oxidase (8.73±2.89 ng/ml) were elevated in subclinical hypothyroid patients in comparison with healthy individuals with significant differences (p<0.001 and p=0.001), whereas, the mean serum level of irisin (15.78±2.64 ng/ml) was reduced in the SCH patients compared to healthy individuals (p=<0.001). The study found that, in contrast to healthy control individuals, patients with subclinical hypothyroidism had lower levels of serum irisin and higher mean values of TG/HDL-C, visfatin, TyG index, and NADPH oxidase

THE SYNTHESIS, CHARACTERIZATION, DFT-OPTIMIZATION, BIOLOGICAL ASSAYS, AND HEAVY METAL STUDIES OF A NEW TETRA DENTATE DERIVATIVE LIGAND AND ITS COMPLEXES

2025-06-11T09:59:43+03:00

A new tetra dentate derivative ligand [(E)-N-((E)-(2-(((Z)-1-hydroxybutylidene) amino) phenyl) (isopropylimino) methyl) butyrohydrazonic acid] [N₃O] type has been prepared from the condensation process of equimolar 2-aminobenzohydrazide, isopropyl amine and followed by another addition of butyric acid. Spectroscopic techniques as FT-IR, UV-visible, Mass spectrum, ¹H,¹³C-NMR, T.L.C., Melting point, Conductivity measurements, Magnetic moment, DFT-optimization studies and other methods have been used to characterize the ligand and its new complexes with the general formula [L(M₂)Cl₃.H₂O] (where M= Ni^II, Co^II, Cu^II, Mn^II, Cd^II, and Zn^II). Studying biological activity for the ligand and its complexes against two gram-positive and two gram-negative bacteria . The formed compounds were evaluated for antibacterial activity against two gram-positive and two gram-negative bacteria which are Staphylococcus aureus, Staphylococcus epidermidis, Escherichia coli, and Pseudomonas aeruginosa. The developed ligand and its metal complexes performed well versus both kinds of bacteria Scheme 1

PHYTOREMEDIATION POTENTIAL OF Catalpa bignonioides IN CRUDE OIL-CONTAMINATED SOILS: EVIDENCE FROM DUHOK, KURDISTAN REGION

2025-05-29T20:39:46+03:00

Phytoremediation is a promising method for cleaning crude oil-contaminated soils. This study aimed to evaluate the potential of Catalpa bignonioides seedlings for remediating soil polluted with 1% and 2% (w/w) crude oil. One- and two-year-old seedlings were grown for eight months under contaminated conditions. Plant growth parameters, crude oil degradation percentage, total petroleum hydrocarbons (TPH), soil pH, electrical conductivity (EC), organic matter (OM), and nitrogen (N), phosphorus (P), and potassium (K) levels in both soil and plant shoots were measured. The seedlings successfully grew in contaminated soil, with no plant mortality observed, despite some leaf yellowing and necrosis. Chlorophyll a remained unaffected, while chlorophyll b significantly decreased. Plant height, shoot and root biomass were significantly reduced at 2% oil concentration. Soil pH slightly decreased, while EC and OM increased with contamination. TPH analysis showed complete removal of 10 hydrocarbon fractions (C3–C8, C10–C14), with degradation rates ranging from 70.37% to 84.02%. Crude oil significantly affected soil N and P levels but not K; in plant tissues, only N was significantly altered. Two-year-old seedlings exhibited greater growth and higher N and K content than younger plants. These findings confirm the species’ potential for phytoremediation of crude oil-contaminated soils

ADOMIAN DECOMPOSITION METHOD AND VARIATIONAL ITERATION METHOD FOR SOLVING SASA-SATSUMA EQUATION

2025-05-18T00:03:19+03:00

The Sasa-Satsuma equation is an integrable higher-order nonlinear Schrodinger equation. In this paper, two schemes are proposed to study numerical solutions of the Sasa-Satsuma nonlinear Schrödinger equation with initial conditions using the Adomian decomposition method and the variational iteration method. Both approaches produce quickly convergent series for each scheme with particularly important features. The present results have been displayed graphically and, in a table, to demonstrate the effectiveness and applicability of those techniques. The results obtained by the Adomian decomposition method are compared with the exact solution as well as the results obtained by variational iteration method. A comparison between the two approaches reveals that the Adomian decomposition approach is closer and more efficient than the variational iteration approach

EVALUATION OF OXIDATIVE STRESS, ANTIOXIDANT DEFENSES, AND BIOCHEMICAL DYSREGULATION IN OBESE VS. NON-OBESE ADULT MALES

2025-06-14T02:49:38+03:00

Obesity is a major public health concern linked to metabolic disturbances and increased oxidative stress. The objective of this research is to evaluate the effect of obesity on oxidative–antioxidant balance in adult males. Comparative cross-sectional study was done at Zakho General Hospital, Iraq, from October 2024 to January 2025, involving 90 males aged 18–44 years, distributed into obese body mass index (BMI) ≥30 and non-obese body mass index (BMI) <25 groups. Blood samples were collected and analyzed for biochemical, and oxidative stress parameters using Cobas auto-analyzers and spectrophotometric methods. Obese individuals exhibited significantly higher body mass index (BMI), waist circumference (WC), diastolic blood pressure (DBP), fasting blood glucose (FBG), fasting insulin (FI), lipid profile, Liver enzymes (aspartate aminotransferase (AST), alanine aminotransferase (ALT), alkaline phosphatase (ALP), and gamma-glutamyl transferase (GGT)), Kidney function parameters (urea, creatinine and uric acid), High-sensitivity C-reactive protein (hs-CRP) and homeostatic model assessment of insulin resistance (HOMA-IR) in comparison with controls. Concentrations of Zinc (Zn) and copper (Cu) were elevated, whereas magnesium (Mg) was decreased in the obese group. Antioxidant markers (glutathione S-transferase (GST), superoxide dismutase (SOD), and catalase) were significantly reduced in obese group. Strong negative correlations are observed between oxidative markers and most anthropometric and biochemical parameters. Obesity in adult males is associated with impaired antioxidant defense and alterations in trace elements, emphasizing the oxidative stress burden in obese individuals and the need for early preventive strategies

INTEGRATING CNN AND DICTIONARY MECHANISMS FOR EFFECTIVE LOOP CLOSURE DETECTION

2025-06-09T22:05:17+03:00

Loop closure detection (LCD) remains a critical challenge in visual Simultaneous Localization and Mapping (SLAM), particularly in environments with repetitive structures or sparse textures where traditional methods suffer from perceptual aliasing and computational inefficiency. This paper presents a robust and scalable LCD framework that integrates a lightweight Convolutional Neural Network (CNN) with a dictionary-based voting mechanism, optimized for accuracy and real-time performance in resource-constrained settings. The proposed CNN architecture, featuring a single convolutional layer with 32 filters, achieves 98% classification accuracy on the Greenhouse Scene Dataset-a structured agricultural environment. Complementing the CNN, a dynamic dictionary tracks class frequencies to detect loop closures via adaptive thresholding, eliminating the need for complex feature matching or geometric verification. Experimental results demonstrate real-time operation (0.076 seconds per 70 frames) and resilience to spatial distortions, maintaining 92% accuracy under pixel-level shifts. Compared to state-of-the-art methods, our approach reduces computational overhead and memory usage

STUDY OF SOME PHYSICAL PROPERTIES OF BRIQUETTES FROM DIFFERENT FOREST WOODY BIOMASS COLLECTIONS IN KURDISTAN REGION OF IRAQ

2025-05-12T19:26:33+03:00

By using forest waste, energy sustainability can be improved, and biomass briquettes offer a sustainable and eco-friendly substitute for fossil fuels. This study examines the physical characteristics of briquettes made from various woody biomass species, as a result of assessing factors including the amount of moisture, density, shatter resistance, tumble resistance, and resistance to water penetration. Also, to identify ideal production circumstances, in both tree species (Quercus infectoria and Pinus brutia). Factors were particle size (2 and 4 mm), moisture levels (6, 9, and 12%), and briquetting temperature (330 and 350 °C). According to the results, Quercus infectoria briquettes processed at 350 °C, with particle sizes of 2 mm and moisture levels of 6%, showed enhanced physical characteristics and combustion efficiency. Longer burning times were caused by higher compactness, and storage stability was improved by resistance to water penetration. These results offer insightful information for the biofuel sector, assisting producers in improving their methods of production to produce premium, environmentally friendly biomass briquettes. The study advances the larger objective of lowering reliance on energy sources that are not renewable and advancing sustainable energy solutions by enhancing the durability and efficiency of biomass fuels. The findings support more investigation into improving biomass briquetting procedures for increasing environmental and financial advantages