Communities in DSpace
Select a community to browse its collections.
Now showing 1 - 2 of 2
Recent Submissions
Item
A HYBRID DEEP LEARNING MODEL FOR FORECASTING PM2.5 AIR POLLUTANT CONCENTRATIONS
(An-Najah National University, 2024-12-18) Massad, Asma
Air quality forecasting is a crucial research field that aids scientists and policymakers in making informed decisions to combat air pollution. Among various pollutants, PM2.5 -particulate matter with a diameter smaller than 2.5 micrometers- poses significant health risks, as it can reach the lower respiratory tract and enter the bloodstream. Accurately forecasting PM2.5 levels is thus essential. Although machine learning-based spatiotemporal forecasting models have advanced, the pursuit for more accurate forecasts continues. The use of hybrid deep learning models for PM2.5 forecasting represents a promising and active area of research, as these models aim to capture complex spatiotemporal dependencies more effectively.
We developed a Dynamic Graph Attention Network (DyGAT) to model spatial dependencies effectively. DyGAT leverages engineered edge features, including distance, wind speed, and wind direction, while using attention mechanisms to capture the dynamic nature of these dependencies. DyGAT was then combined with Informer, a Transformer for efficient time-series forecasting, to capture spatial and temporal patterns comprehensively, improving prediction accuracy. Our model was evaluated on a benchmark dataset from Beijing, with 420,768 records over four years. DyGAT-Informer outperformed a version without the DyGAT component and other baseline models. It achieved 50.43 for MAE, 79.9 for RMSE and 28.88% for SMAPE, compared to 51.44 for MAE, 80.83 for RMSE and 30.25% for SMAPE in the next best model.
Additionally, we conducted a case study using a dataset from Nablus, Palestine, consisting of 2692 records per station over a two months period. We incorporated geospatial features about nearby pollution sources into the dataset. Due to the insufficient number of records in the Nablus dataset for training the Informer, it was replaced with a sequence-to-sequence Long Short-Term Memory (LSTM) model. DyGAT-LSTM, trained with additional geospatial features about nearby pollution sources, achieved a 2.08% reduction in MAE, 1.17% in RMSE, and 1.96% in SMAPE. This confirms the benefit of incorporating such data. Finally, despite the short distances between stations, DyGAT successfully captured spatial dependencies, where DyGAT-LSTM achieved a reduction of 3.13% in MAE, 1.48% in RMSE, and 3.67% in SMAPE when compared to the LSTM-only model.
Item
EXPLORING EFL STUDENTS’ PERSPECTIVES ON THE ROLE OF CHATGPT-ASSISTED AUTONOMOUS LEARNING IN ENHANCING SELF-DIRECTED LEARNING IN PALESTINIAN HIGHER EDUCATION
(An-Najah National University, 2024-12-16) Al-Atrash, Aya
This study aimed to investigate the perspectives of EFL students on the role of ChatGPT-assisted autonomous learning in enhancing self-directed learning at two Palestinian universities which are An-Najah National University and Al-Quds Open University. To achieve this aim, the researcher employed a mixed-approach research design to analyze and explain the collected data. The data were collected through the study tools which are interviews and a questionnaire from a sample of EFL students according to demographic variables such as gender, academic level, and university. An analytical descriptive approach was used by using the questionnaire as a tool for the study and was analyzed using SPSS V.23. The sample of the study consisted of (348) students chosen by stratified random method. The quantitative analysis revealed generally positive perspectives of ChatGPT’s effectiveness in fostering self-directed learning. The findings of the questionnaire showed a high response to the total degree of the main question. Moreover, there were no statistically significant differences attributed to the variables of academic level and university while there were statistically significant differences due to gender in favor of males. The qualitative data further emphasized the potential of ChatGPT to function as a supplementary tool, providing learners with ways to steer academic learning more efficiently. The study also emphasized the need for teacher guidance to ensure balanced use. Overall, ChatGPT is seen as a valuable benefit in the educational process even though its success depends on thoughtful integration with conventional teaching methods. The study ultimately recommended the necessity of raising the awareness level of perspective on the impact of ChatGPT-assisted autonomous learning in enhancing self-directed learning and profound studies about this domain.
Item
EXPLORING EIGHT – NINTH GRADE MATHEMATICS TEACHERS' PERSPECTIVES, AND PRACTICES: A COMPREHENSIVE STUDY ON CREATIVITY IN PALESTINIAN CLASSROOMS
(جامعة النجاح الوطنية, 2024-12-30) Sultan Amin Issa Kowkas
The concept of creativity is multifaceted and constantly evolving as it is interpreted differently across various disciplines and cultures, resulting in a diverse array of viewpoints, from the notion of divine inspiration embraced by early philosophers to the modern ideas of originality and problem-solving abilities. Through this dissertation, the researcher delve into a thorough investigation of creativity within the realm of mathematics education, specifically examining the perspectives and methods of Palestinian math teachers in eighth and ninth grade classrooms. In the context of mathematics, creativity manifests in a distinct manner of that in Art and Literature, blending newness with practicality and displaying agility, adaptability, and ingenuity in thought. There is an inevitable conclusion that mathematical creativity entails a fusion of originality and significance. This comprised of three essential qualities: fluency, flexibility, and originality. It is worth noting that mathematical intelligence and creativity have a complementary relationship, with each strengthening the other.
Item
3-AMINOIMIDAZO[1,2-a] PYRIDINE DERIVATIVES: SYNTHESIS AND ANTIMICROBIAL ACTIVITIES
(An-Najah National University, 2024-12-18) Dragmeh, Osama
Background: Worldwide, antimicrobial resistance continues to be a major public health issue. Novel antibacterials with improved activity characteristics are therefore in high demand. Antibacterial is one of the many pharmacological actions of imidazo[1,2-a]pyridines. These bioactive substances are the main ingredients of several widely marketed therapeutic medications, such as Alpidem and Zolpidem.
Objectives: Creation of novel 3-amino-6-floroimidazo[1,2-a]pyridine derivatives and evaluation of their effectiveness against five bacterial strains.
Methodology: The one-pot Groebke-Blackburn-Bienayme-Three Component Reaction (GBB-3CR) was used in the compound synthesis. Several spectroscopic methods, including infrared (IR), proton nuclear magnetic resonance (1H NMR), and carbon-13 nuclear magnetic resonance (13C NMR), were used to confirm the structure. The assessment of purity also makes use of the High-Performance Liquid Chromatography (HPLC) technology. To evaluate the compounds' effectiveness against S. aureus, S. epidermidis, K. pneumonia, P. aeruginosa, and E. coli, biological experiments were conducted on the produced compounds.
Results: The seven synthetic compounds (85-91) were produced with a purity of 88-100%. These compounds (85-91) have been verified for their structural formula using 1H NMR, 13C NMR, and IR spectroscopy. These techniques indicate the GBB-3CR normal product. Biologically, compound 91 exhibited the best inhibitory behavior among the others; the lowest MIC value (15.625 µg/ml) was recorded for compound 91 against E. coli. Moreover, compound 91 works better than Gentamicin against K. pneumoniae. The same observation was reported for compounds 85 and 89 against S. epidermis. It is worth pointing out that compound 89 in this study kills E. coli and S. epidermis at lower concentrations (62.5 µg/mL) than Gentamicin antibiotics 125 µg/mL and 250 µg/mL, respectively. The same observation was noticed for compound 85 against S. epidermis with an MBC value of 62.5 µg/mL. Compounds 91, 89, and 85 have good antibacterial effects due to the substitution on C-2 of 3-amino-6-floroimidazo[1,2-a]pyridine scaffolds, which are 1-methylimidazole, p-trifluoromethylphenyl, and 3,5-dimethoxy-4-hydroxyphenyl, respectively.
Conclusions: A straightforward, cost-effective, one-step process was used to create new, promising bioactive chemicals. Additional research on these derivatives might provide more potent compounds that show promise as innovative antibacterial treatment options.
Item
ENHANCING THE EFFICACY OF A GROUND SOURCE HORIZONTAL HEAT PUMP BY CARBON NANOTUBES SUSPENDED IN WATER
(An-Najah National University, 2025-01-09) Khoswan, Ibrahim
This study explores enhancements in ground source horizontal heat pumps ((GSHHP)) by improving the heat transfer medium through nano-fluids. Researchers have used various types of carbon nanotubes (CNTs) in water. Both functionalized single-walled, Multiwalled carbon nano tubes ((MWCNT)s) with Tween 80 as a surfactant provided optimal suspension, while multi-walled CNTs achieved a 126% increase in thermal conductivity after sonication. Effects of various parameters, like concentration, shape factor, temperature, viscosity, aspect ratio, and added surfactant were studied. The result for (MWCNT) at the thermal conductivity increased with the concentration of (MWCNT) using Tween 80 using 10-60-minute sonication for each sample, no extra suspension would happen beyond that time, and the suspension concentration became saturated. The Thermal conductivity of (SWCNT)-water suspension was less for the same concentration (10% wt.) to reach k(SWCNT)nf= 0.77 W/m.K with a 28% improvement compared to water thermal conductivity kw = 0.6 W/m.K. Those results were better compared to the literature. The results revealed that smaller concentrations of (SWCNT) will be needed, which lowers both capital and running costs. making the system eco-friendlier. The concentration of CNTs influenced the specific heat capacity of the water-based nano-fluid. Higher CNT concentrations led to enhanced thermal conductivity but had mixed effects on specific heat capacity, diverging from typical predictions in the literature((SWCNT)s), ((MWCNT)s) impacted the specific heat differently. (MWCNT)s showed a more noticeable effect on increasing thermal conductivity, though the specific heat enhancement was less pronounced for (SWCNT)s at similar concentrations. Sonication time and the use of a surfactant (Tween 80) affected CNT dispersion in water. A simulation study further verified the experimental findings in both thermal conductivity and specific heat. New models of our experimental data were developed in this dissertation to predict specific heat thermal conductivity enhancement as a function of CNT concentration and nano-fluid properties. These models offered a more accurate estimation of specific heat changes compared to earlier theoretical models which were inaccurate. Also, the simulation of ((GSHHP)) described a qualitative model to rationalize the effects of (CNTs) on nano-fluid conductivity.