Search

The aim of this work was to develop three artificial intelligence-based methods to model the ternary adsorption of heavy metal ions {Pb2+, Hg2+, Cd2+, Cu2+, Zn2+, Ni2+, Cr4+} on different adsorbates {activated carbon, chitosan, Danish peat, Heilongjiang peat, carbon sunflower head, and carbon sunflower stem). Results show that support vector regression (SVR) performed slightly better, more accurate, stable, and more rapid than least-square support vector regression (LS-SVR) and artificial neural networks (ANN). The SVR model is highly recommended for estimating the ternary adsorption kinetics of a multicomponent system.

Blood testing is widely regarded as a fundamental diagnostic procedure in healthcare, with blood cell counting being particularly vital for diagnosing conditions and evaluating overall health. Traditional methods employing hemocytometers and diverse laboratory instruments are typically employed to conduct blood counts manually. Using a microscope, manually counting, and examining blood cells takes time and effort. Thus, developing autonomous blood cells detecting and counting cells in this system becomes necessary to help doctors diagnose patients quickly and accurately. The proposed method integrates the YOLOv5 object detection framework with Enhanced Graywolf Optimization (EGWO) and an Attention Mechanism to improve the accuracy and efficiency of RBC detection. The YOLOv5 architecture is optimized for the task through the EGWO algorithm, which fine-tunes the model parameters, while the Attention Mechanism focuses on extracting critical features from blood cell images. The model is trained and validated using the BCCD dataset, employing an 80/20 split for training and validation. Data augmentation techniques, such as random rotations, flips, and color adjustments, are applied to enhance model generalization. Experimental results demonstrate that our method achieves a high accuracy of 99.89 %, outperforming existing models like Faster R-CNN, CNN, and DCNN regarding accuracy, training time, and inference speed. The proposed method's moderate complexity and fast inference time make it suitable for real-time applications in clinical settings. This research provides a robust and efficient solution for automated RBC detection and counting, with potential implications for improving diagnostic processes in hematological analyses. Overall, in practical applications, it is helpful for counting red blood cells from smeared pictures in less than a second.

Health performance and well-being are crucial elements of Saudi Arabia's Vision 2030, aiming to improve the overall quality of life and promote a prosperous community. Within this context, this study intended to examine the impact of recent innovations, logistical measures, Information and Communication Technology (ICT) diffusion, environmental quality improvements, economic growth, and green (renewable) energy exploitation on health performance and well-being, in Saudi Arabia from 1990 to 2022, by implementing machine learning models (random forest and gradient boosting) and regression algorithms (ridge and lasso). Overall, the findings of machine learning models indicate a strong impact of digital connectivity on health spending by internet users, with scores of 0.673 and 0.86. Further, economic growth also influences health costs but to a lesser extent, with scores of 0.145 and 0.082. Mobile user penetration and CO2 emissions have moderate to low importance, suggesting nuanced interactions with health expenditure. Patent applications and logistics performance show minimal impact, indicating a limited direct influence on health costs within this study. Similarly, the share of renewable energy is negligible, reflecting its minimal impact on the analyzed data. Finally, regression analyses using ridge and lasso models confirmed similar trends, further validating these findings. Limitations and several policy implications are also debated.=

Abstract Restoring ecological dynamics is a key objective of conservation translocations. Exemplarily, reconnecting the reintroduced alpine populations with native Pyrenean populations through re‐establishing locally extinct populations in between, in the Causses and the Pre‐Alps, is a major goal for the long‐term conservation of Bearded Vultures in Europe. Understanding Bearded Vultures' post‐release movements and foraging behavior is critical to understanding the settlement of newly restored populations and to supporting conservation measures. The telemetric monitoring of 43 translocated and wild‐born juveniles allowed us to investigate whether differences exist in post‐release movements and foraging behavior during the first year of life between reintroduced and native populations. Medium‐ and long‐distance exploration movements start during the spring following fledging for both translocated and wild‐born individuals. However, birds translocated in the most distant release site (Causses) exhibited greater exploration distances with no clear directional movement pattern, had smaller home ranges, and had a stronger preference for supplementary feeding stations than those from other populations. Although some birds translocated in the Pre‐Alps displayed similar behaviors, the pattern is not as strong as in the Causses, likely because of the proximity to the breeding populations reintroduced in the Alps or differences in the number and management of supplementary feeding stations. Preference for supplementary feeding stations (SFS) mostly occurred in the Pre‐Alps and the native populations, but was lower in the Causses. Seasonal variations in SFS preference were consistent among populations, with a peak in the first spring following fledging. Beyond documenting post‐release movements in Bearded Vultures, we suggest better accounting for the demographic consequences of behaviors to track conservation translocation effectiveness, at both local and regional scales.

نفذت الدراسة في منطقة الشيخ بدر التابعة لمحافظة طرطوس للموسم الزراعي 2023 ، لدراسة تأثير إضافة مستويات مختلفة من الفحم الحيوي و روث الأبقار على بعض الخصائص الإنتاجية لمحصول فول الصويا وبعض الخصائص الفيزيائية للتربةتم تصميم التجربة على أساس القطاعات العشوائية الكاملة بتسعة معاملات بواقع ثلاث مكررات لكل معاملة شاهد دون إضافة ، (15 طن/هكتار-30 طن/هكتار) من روث الأبقار ، (2% - 4 % من التربة وزناً) فحم حيوي، (15 طن/هكتار روث أبقار مع %2 من التربة وزناً فحم حيوي ) (15 طن/هكتار روث أبقار مع 4 % من التربة وزناً فحم حيوي)،(30 طن/هكتار من روث الأبقار مع 2% من التربة وزناً فحم حيوي) (30 طن/هكتار من روث الأبقار مع 4% من التربة وزناً فحم حيوي ). وشملت الدراسة العديد من صفات المحصول الإنتاجية مثل ( عدد القرون على النبات و عدد البذور في القرن ، وزن المئة بذرة ) ، و العديد من خصائص التربة الفيزيائية مثل (المسامية ،التوزع الحجمي للمسامات و الكثافة الظاهرية ).حيث أظهرت النتائج : تفوق معاملة الفحم الحيوي 4% من التربة وزناً و روث الأبقار 30 طن/هكتار في زيادة عدد القرون على النبات ، وزيادة عدد البذور في القرن،وزيادة وزن المئة بذرة ؛ كما وقد أسهمت المعاملة بالفحم الحيوي 4% من التربة وزناً و روث الأبقار 30 طن/هكتار في خفض الكثافة الظاهرية و رفع المسامية الكلية و الهوائية وخفض المسامية الشعرية.

Adversarial attacks involve manipulating data to trick Artificial Intelligence (AI) models, making false predictions or classifications or even disrupting the normal functions of the smart grid. This can be done by providing the wrong information to the models, hence producing wrong predictions and therefore leading to instabilities, power imbalances and overall operational failure. Thus, employing an AI model is vital for controlling energy usage, identifying and even predicting equipment failures, and accurately determining power availability. Thus, their input dependency does not enable them to withstand cyber-attacks, which compromises the stability of the grid. These attacks affect energy control, cause losses and intrude into the critical infrastructure part of the smart grid, hence the call for enhanced smart grid protection. This study first generates a novel adversarial attack dataset on smart grids with three attacks: adversarial perturbation, backdoor injection, DOS attacks, and one benign class. Next, it provides a fine-tuned Deep Neural Network (DNN) model to significantly improve resistance against adversarial attacks on smart grids. Results from the various Machine Learning (ML) and DNN algorithms showed accuracy varying between 29.10% to 73.9%, with DNN recording the highest levels of accuracy. This shows how the approach can be utilised in the prediction of such attacks and how the grid can be protected and secured.

The increasing occurrence of Hypertension highlights the need for advanced predictive tools in healthcare. This research proposes a novel approach that combines machine and deep learning for new feature generation and hypertension prediction. We explore machine learning-based models: Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), XGBoost (XGB), and Gradient Boosting (GB) for new Feature Prediction (FP) and integrated these predictions with the original dataset for training deep Long short-term memory (LSTM) model. To evaluate the efficiency of the proposed approach, we compare all models, predicting new features, with those in the existing study. The results demonstrate that the GB-based FP + LSTM are standout performers. The GB-based FP + LSTM combination demonstrates the highest accuracy at 98.48%. On the contrary, the LR-based FP + LSTM combination exhibits a lower accuracy of 89.39%. The remaining combinations, including RF-based FP + LSTM, XGB-based FP + LSTM, and DT-based FP + LSTM, showcase accuracies ranging from 95.45% to 97.97%. In practical terms, the high F1-score of 98.48% is achieved by the combination of GB-based FP + LSTM, which implies a reliable tool for clinicians to aid in early hypertension detection. These findings hold deep practical implications, offering healthcare practitioners and policymakers a pathway to deploy accurate and timely hypertension identification tools.

One of the main causes of death from cardiovascular diseases is Myocardial Infarction (MI), which is brought on by coronary artery problems. Myocardial infarction is a pathological condition resulting from an anatomical issue with the Left Ventricle (LV). MI is a potentially fatal cardiac disease for which prompt medical attention can lower the fatality risk. This paper proposes a Deep Learning (DL) based approach to robustly detect binary and multiclass myocardial infarction (MI) in two environments, i.e., with and without data balancing. We employed a Myocardial infarction dataset that contains 1700 MI patients’ medical records. The data preprocessing step is performed, during which data balancing and normalization are carried out. In many real-world medical datasets, class imbalance is a serious problem since it often causes the proposed algorithms to predict the majority class. We apply a class imbalance handling technique to solve the imbalance issue and create a balanced and trustworthy prediction approach. To ensure the generalizability and performance comparison, we employ various deep learning algorithms such as Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Deep Neural Network (DNN), Long Short-Term Memory (LSTM) without data balancing first, and then after that, with data balancing to enhance model performance. Experiments reveal that the DNN model outperformed others by applying the class imbalance handling technique compared to the method without balancing data. The DNN model attained a maximum test accuracy of 99.39% and a test loss of 0.0252 for the binary class and achieved a maximum test accuracy of 99.74% and a test loss of 0.0115 for multiclass categorization.

Dyslexia is a form of specialized learning disability that can lead to academic dissatisfaction. Detection is essential yet difficult, especially for languages like Arabic and Spanish that have straightforward orthographies. As seen by the abundance of work given in a wide range of scientific journals, the detection of dyslexia continues to be a key pursuit for the research efforts in a variety of domains. It appears that machine learning and other statistical approaches are quite useful for these tasks, such as those used in the classification of medical datasets. In this paper, we combined principle machine learning models for dyslexia detection. However, a lot of work remains to be done by hand in order to properly categorize the enormous dataset employed during training. Recent research have shown that machine learning models are effective, proving their ability to lessen the workload associated with feature engineering. However, applying the machine learning model directly to the classification task yields no statistically significant gain in performance. For better machine learning prediction, we introduce an optimal ensemble learning model based on a genetic algorithms. Dyslexia feature extraction is first, followed by a hybridization of algorithms for machine learning in step tow of the model. After that, we use an adaptive genetic algorithm for select the most optimal weight to combine different machine learning models. We conducted trials on the Dyslexia dataset to show that our proposed technique significantly increases accuracy.

The objective of this study is the development of innovative nanocurcumin-based formulations designed for the treatment and prevention of oxidative stress and diabetes. Nanocurcumin was obtained through a micronization process and subsequently encapsulated within biopolymers derived from corn starch and fenugreek mucilage, achieving encapsulation rates of 75% and 85%, respectively. Subsequently, the encapsulated nanocurcumin was utilized in the formulation of sugar-free syrups based on Stevia rebaudiana Bertoni. The stability of the resulting formulations was assessed by monitoring particle size distribution and zeta potential over a 25-day period. Dynamic light scattering (DLS) revealed a particle size of 119.9 nm for the fenugreek mucilage-based syrup (CURF) and 117 nm for the corn starch-based syrup (CURA), with polydispersity indices PDIs of 0.509 and 0.495, respectively. The dissolution rates of the encapsulated nanocurcumin were significantly enhanced, showing a 67% improvement in CURA and a 70% enhancement in CURF compared with crude curcumin (12.82%). Both formulations demonstrated excellent antioxidant activity, as evidenced by polyphenol quantification using the 2.2-diphenyl 1-pycrilhydrazyl (DPPH) assay. In the evaluation of antidiabetic activity conducted on Wistar rats, a substantial reduction in fasting blood sugar levels from 392 to 187 mg/mL was observed. The antioxidant properties of CURF in reducing oxidative stress were clearly demonstrated by a macroscopic observation of the rats’ livers, including their color and appearance.

Since the late 1999, extensive groundwater extraction within the Sahara aquifer system has been investigated. In this study we analyze the overexploitation of the thermal groundwater stored in the Continental Intercalary aquifer in the Algerian province of Ghardaia. The Saharan aquifer system is recognized by a large number of over 8800 boreholes and springs, on which 3500 operate the Continental Intercalary series and 5300 operate the Terminal complex. This work describes the groundwater order problem of overexploitation and the flows that exploit this hydrothermal system to be identified and analyzed. We have negative impacts on groundwater in that region due to the practice of certain activities which directly affect the quantity causing the water level of the aquifer to be lowered. Using theoretical context, water quality status can be assessed and recommendations suggested. Results show that we have 387.86 million m3 /yr of flow today which is determined 30 m drawdowns. Measures need to be taken until the effects of the appeal become irreversible and the legal system instruments need practical applicability to prevent this context from extending to other areas.

The use of agricultural chemicals has adversely affected soil health and the environment. Organic farming practices, particularly vermicompost (VC), are gaining attention for their potential to improve soil fertility and crop productivity. This study investigated VC rate applications on lettuce growth, yield, soil fertility, nutrient dynamics, enzyme activity, biological parameters, and biochemical aspects under greenhouse conditions in Samsun, Turkey during 2022–2023. Experimentally, VC was applied at rates of V1: 1%, V2: 2%, and V3: 4% w/w, with a control group without VC application, V0: 0% w/w. Batavia lettuce, which is sensitive to environmental conditions and nutrient deficiency, was subjected to these treatments in a randomized complete block design, replicated thrice. Results showed consistent improvements in plant dry weight across all VC treatments, with the 2% application rate (V2) yielding the highest increase in lettuce yield (56.43%). Soil pH varied across treatments, with V1 being slightly alkaline and V3 showing high electrical conductivity and increased nitrogen content. Phosphorus content increased in all treatments, while potassium varied, with V3 having the highest values. Soil enzyme activities increased with VC concentrations, with V3 showing the highest urease activity. Pearson correlations confirmed positive associations with growth parameters and soil enzymatic activity. These findings highlight vermicompost as a sustainable solution for lettuce production and soil improvement.

The agricultural sector faces the dual challenge of enhancing crop productivity and mitigating environmental impacts. Optimizing nutrient management is vital for sustainable agriculture, particularly in sloping terrains like the Himalayan region, where damaged soils require restoration. This study explores the synergistic effects of urea, poultry manure, and zeolite on wheat growth and yield in degraded mountainous soils. A total of twelve treatments were implemented in a randomized complete block design, replicated three times. The treatments included a control (T1); urea nitrogen at 120 kg N ha−1 (UN120) (T2); poultry manure (PM) at 120 kg N ha−1 (T3); zeolite-1 (Z1) at 5 t ha−1 (T4); zeolite-2 (Z2) at 5 t ha−1 (T5); UN120 + Z1 (T6); PM + Z1 (T7); UN120 + Z2 (T8); PM + Z2 (T9); ½ UN + ½ PM + Z1 (T10); ½ UN + ½ PM + Z2 (T11); and ½ UN + ½ PM + ½ Z1 + ½ Z2 (T12). The UN120 treatment demonstrated significant improvements in wheat growth, with notable increases in shoot length (79.7%), shoot fresh weight (50.8%), root length (50.6%), chlorophyll content (53.6%), and leaf area (72.5%) compared to the control. Wheat yield and its components experienced significant improvements when treated with urea nitrogen (UN) and zeolites. Among these treatments, UN120 exhibited the highest efficacy. Nutrient content analysis revealed substantial increases in shoot nitrogen (70.6%), phosphorus (33.3%), and potassium (15.6%) with UN120 treatment compared to the control. The concoction of UN and PM with zeolites further enhanced nutrient levels. Integrating mineral nitrogen sources with organic amendments and zeolites proved effective in enhancing wheat productivity in degraded mountainous soils. Despite positive results, further research is essential for widespread recommendations.