AUIQ Technical Engineering Science

Radiation loss due to fiber curving or bending is a major challenge in advanced technical applications like fiber-optic
sensing or biomedical applications. This study focuses on the basic features that characterize a single-mode fiber (SMF)
and its critical parameters in view of the recent improvements made. The planned design of SMF is, however, intended
to resolve these problems by proposing minimizing bend loss by adopting a five-layer fiber structure designed to keep
the optical field within the fiber core. The proposed SMF design exhibit ultra-low bending sensitivity, with estimated
bending loss of 2 × 10−3 dB/turn for bending radius of 5 mm. The fiber is designed to op

Artificial intelligence, Machine learning, SMOTE, Thalassemia

Over the past three decades, knee implant design has significantly advanced to address the challenges of replacing
damaged knee joint bone with durable and efficient prosthetics. The aim of this review explore key developments in
materials and manufacturing processes, focusing on biocompatible options such as zirconium, titanium alloys, UHMWP,
and smart materials, as well as coatings designed for metal-sensitive patients. The study examines the mechanical forces
acting on implants during daily activities, highlighting wear and infection risks, and evaluates the role of innovative
manufacturing techniques in improving implant precision, cost-efficiency, and durability. Simulation methods, including
Finite Element Analysis (FEA), are discussed for assessing implant behavior under static and dynamic loading conditions,
ensuring stress distribution and wear reduction. By synthesizing advancements in material science, coating technologies,
and simulation techniques, this review provides valuable insights into optimizing knee arthroplasty outcomes and
identifying future opportunities for innovation.

The fast and unprecedented urban growth process may violate cities’ responsibilities by causing an urban heat island
(UHI) and increasing the public’s risk of heat-related illnesses due to vegetative area reduction and urban area inclination.
The Bangkok Metropolitan Area (BMA)’s variations in Land Use Land Cover (LULC), Land Surface Temperature (LST),
UHI, and several geospatial indicators, as well as the daytime and nighttime LST, are the main subjects of the study.
Between 2015 and 2021, the highest Daytime LST (DLST) rose consistently from 36.77°C to 38.14°C, then slightly
decreased to 37.22°C in 2023. There is a general increase in the maximum Surface Urban Heat Island (SUHI) intensity
from 1.112 (2015) to 1.162 (2021), and then a minor decrease to 1.157 (2023). With the highest values circling 11.0
and the lowest around 7.32, UTFVI levels stayed reasonable between 2015 and 2018. Nonetheless, there has been a
discernible increase in high-heat zones since 2019, with peak UTFVI values continuously exceeding 11.0 and rising to
12.19 by 2023. SAVI readings over the observed time vary from a low of roughly −0.088 to a high of 0.398. Consistent
urban expansion is suggested by the significant increase in the maximum NDBI values over the nine years, especially
from 2015 (0.057) to 2021 (0.081). To lower the risks and offer practical answers, the city planners and officials
implement sustainable urban development and urban resilience by adopting sustainable urban design techniques, such
as incorporating green infrastructure, preserving vegetation-rich regions, and putting heat-mitigation techniques like
rooftop gardens, urban parks, and permeable surfaces into practice, is crucial to overcoming these obstacles.

The distal weight-bearing implant was selected from a pool of approximately 17 implant systems that utilize the
osseointegration mechanism currently available globally. It stands out due to its modernity, rarity, and creative concept,
offering amputees with “above-knee amputation” a range of options that ensure their satisfaction and fulfill their
requirements. However, this implant requires additional refinement and adaptation to achieve the highest level of
perfection. This research implemented various modifications to the mechanical design of the implant, which were
subsequently evaluated using the finite element analysis software “ANSYS.” Modifications included substituting the
threads along the femoral stem with a groove (internal cut threads) or external thread, while the groove depth was
adjusted to enhance stability, while the thread profile was modified to improve mechanical engagement with the bone,
resulting in four distinct designs. The mechanical forces acting on the implant at the midstance phase within the femur
were simulated and compared to those of the traditional implant under standardized conditions. The results showed that
the new modifications exhibited superior resistance to “total deformation,” a safer value for “Von-mises” stresses, and
a significantly higher (based on observed mechanical performance trends) “safety factor” compared to the traditional
design. These findings highlight the potential of the modified implant design to offer improved mechanical performance
and patient satisfaction.

As global climate variability intensifies, the need for accurate and reliable weather forecasting becomes increasingly
important. This study aimed to classify daily weather conditions in Kabul, Afghanistan, by comparing two decision-treebased machine learning (ML) models that includes Decision Tree Classifier (DTC) and Extra Trees Classifier (ETC). A
complete year dataset consisting of 366 daily meteorological observations collected from a central weather station in
the region for 2024 was used. Results revealed that the DTC model consistently outperformed the ETC model, obtained
an overall accuracy of 99% in both the training and testing phases, compared to the ETC model’s accuracy of 96%
(training) and 89% (testing). Specifically, the DTC model showed almost perfect weighted-average precision (0.99),
recall (0.99), and F1-scores (0.99) for both phases training and testing respectively, whereas ETC demonstrated lower
metrics in testing phase with weighted-average precision of 0.90, recall of 0.89, and F1-score of 0.88. Furthermore,
sensitivity analysis demonstrated that precipitation probability is 40%, cloud cover is 31%, snow is 18%, temperature
fleeks like max is 8%, and solar radiation is 3% as the most impactful variables in weather classification. Scientifically,
this study contributes to enhancing the effectiveness of localized weather prediction, providing critical support for urban
planning, agriculture, and disaster management decisions in regions with similar climatic conditions.

Accurate prediction of pan evaporation remains a significant challenge due to inconsistencies across different climatic
regions. This study aims to enhance pan evaporation estimation by developing a robust hybrid machine learning (ML)
model that integrates spectral clustering with advanced regression techniques, specifically the Histogram-based Gradient
Boosting Regressor (HGBR) and Extreme Gradient Boosting Regressor (XGBR), to improve prediction accuracy and
adaptability across diverse environments. The research developed a novel methodology by employing spectral clustering
for models’ performance enhancement, followed by rigorous hyperparameter tuning, sensitivity analysis to assess the
impact of individual features on each model. Finally, models underwent lack of fit test to confirm model adequacy and
usability. The findings of the study revealed that the HGBR model outperformed the XGBR, this is evidenced by its
consistent training and testing results (training R2 of 0.94 and RMSE of 1.34; testing R2 of 0.92 and RMSE of 1.45) both
training and testing observed close enough for judging on the robustness of the model compared to the XGBR (training
R
2 of 0.96 and RMSE of 1.11; testing R2 of 0.91 and RMSE of 1.48) which raises the issue of overfitting due to large
gap between the R2 values for training and testing. These results demonstrate the HGBR model’s superior robustness
and reliability for predicting pan evaporation. The research contributes significantly to local and global water resource
management strategies by providing a reliable predictive tool and sets a foundation for future studies to further refine
these models and explore their applicability in other geographical settings.

Land Surface Temperature (LST) has become a critical urban climate concern due to rapid urbanization and land
cover transformation in Saudi Arabian cities. This study aimed to analyze the spatial and temporal variability of LST
in three climatically distinct cities encompassing Riyadh (hot desert), Dhahran (hot humid), and Abha (cold desert)
over the summer months (May to September) from 2017 to 2021. LST was retrieved through the RSLab Landsat LST
web application. A total of 80 samples per year were compiled for each city using a structured sampling approach,
and results were aggregated using the RS-LST Aggregation Framework (RSLAF). The results revealed that Riyadh’s
LST reached a maximum of 53.0°C in 2021 and a minimum of 0.0°C in 2019, showed sharp thermal contrasts and a
widening diurnal temperature range. Dhahran exhibited the highest thermal stress, with maximum LST rising steadily
from 54.7°C in 2017 to 60.6°C in 2021, and minimum temperatures increased from 29.2°C to 44.7°C, indicated strong
heat retention. In contrast, Abha remained significantly cooler, with maximum LST peaking at 42.2°C in 2020 and
falling to 33.0°C in 2021, while minimum temperatures fluctuated between 7.0°C and 20.0°C. These findings signified
the need for reflective materials, urban greenery, and climate-adaptive design in urban planning. Scientifically, the study
demonstrated a reproducible LST retrieval and aggregation framework for urban climate analysis, while practically, it
provided data-driven insights to guide sustainable development and heat mitigation strategies in arid and semi-arid cities.

Dam displacement is a crucial indicator for assessing the safety of a concrete dam through structural health monitoring.
Since the displacement data exhibits a non-linear and complex relationship with influencing factors like waterhead,
time and temperature, machine learning models are deployed to accurately predict dam displacement. Furthermore, the
limited availability of monitored data in the majority of the dams renders the studies conducted with a large number of
observations valueless. In order to address the aforementioned issues, this study proposes a feature selection approach
to predict dam displacement by examining the ability of four ensemble machine learning models on different input
combinations. The results reveal that the extreme gradient boost performs the best with a coefficient of determination
(R2
) and RMSE value of 0.960 and 0.275 mm respectively. Random forests and decision tree models exhibited better
performance on using single predictor variables waterhead and age respectively. AdaBoost exhibited moderate performance but was unaffected by the negative influence of extra predictor variables. The comparison results indicated that
models developed with only ambient air temperature as input data are insufficient to predict dam deformation. The
outcomes of this study are resourceful in prioritizing models based on the data availability for accurate prediction of
dam displacement.

Given the growing complexity of urban transportation systems, precise traffic flow forecasting is essential for
reducing not only issues of congestion but also, for boosting road safety and enhancing mobility management. This
study integrates Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Long Short-Term Memory
(LSTM), and Recurrent Neural Networks (RNN) to present a hybrid deep learning framework for traffic prediction.
Of these, the CNN-LSTM model is a reliable option for real-time traffic forecasting since it successfully captures both
spatial and temporal dependencies, resulting in superior predictive performance. The dataset used to assess the framework includes 48,120 records from a traffic monitoring system that include hourly vehicle counts at several intersections.
With an average of 22.79 vehicles per hour, a variance of 430.57, and a standard deviation of 20.75, statistical analysis
shows that traffic fluctuates significantly. Based on experimental results, CNN-LSTM achieves a competitive Mean sqd˙
Error (MSE) of 0.0095, a precision of 0.73, and a recall of 0.74, outperforming LSTM and RNN in high-traffic situations. This study demonstrates the potential of hybrid models—in particular, CNN-LSTM—in striking a balance
between computational efficiency and predictive accuracy. Future research should incorporate GPS feeds and real-time
data from IoT sensors to improve model adaptability and offer a scalable and clever urban traffic management solution.