NTU Journal of Engineering and Technology

The majority of the energy utilized in systems is transformed into heat energy, making the world's constantly rising rate of energy consumption one of the most significant challenges of our day. Heat pipe heat exchangers, or HPHEs, are used in many different fields, such as air conditioning, electronics, aerospace, and aircraft. With the inclusion of HPHE, this article seeks to physically modify the HVAC system of the all rooms in order to enhance its dehumidification capabilities, which are used to remove contaminated air. The overall goal of the study was to increase people's comprehension of heat pipes through the collection and organization of readily available data in a range of formats across the material spectrum, its presentation in an orderly fashion ranging from rudimentary to sophisticated understanding of heat pipes, and the provision of further information regarding the quality of considerations made in the design and construction of heat pipes as well as the examination of the effects of altering heat pipe parameters on performance. This paper covers the research that has been done on heat pipes in terms of design and analysis HPHE succeeded in reducing the energy consumed by the precooling and reheating processes of the HVAC system, enhancing its dehumidification capability.

A retinal detachment is a serious condition resulting in the retina detaching from its support layers, which are just beneath it. If untreated, this can cause blindness. To detect the classes of retinal detachment in various images, this paper introduces a novel method employing deep learning techniques involving the YOLOv8 algorithm. Notably, this marks the first use of the YOLOv8 model for retinal detachment detection. Retinal detachment can be identified with high precision using images obtained from Optical Coherence Tomography (OCT). The proposed work assesses the performance of these models using metrics such as mAP50, recall, and precision by training five YOLOv8 models: YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. Among these, the YOLOv8s model had the best performance with a mAP50 of 0.985, a recall of 0.97, and a precision of 0.968. The other models had the following mAP scores: YOLOv8n (0.949), YOLOv8m (0.906), YOLOv8l (0.889), and YOLOv8x (0.907). This demonstrates that the proposed system works effectively in detecting retinal detachment, resulting in highly accurate results mined from complex medical data sets and imaging, thereby making it an important tool in medicine.

Significant progress has been made in using artificial intelligence, especially deep learning, to help doctors evaluate the bone age of children in medical images. Traditional methods like the Leather Tanner-Whitehouse and Greulich-Pyle approaches have some issues with consistency and accuracy. But with AI, there's been a big shift. This review looks at how AI has changed bone age evaluation over time, making it easier and more reliable. It covers different AI systems used, from older semi-automated ones like HANDX to newer ones like BoneXpert. The review explains how these systems work, their pros and cons, and how well they perform. It's a helpful guide for scientists, doctors, and anyone interested in this field, covering both old and new AI-driven methods for evaluating bone age.

Many industrial applications recently are utilizing from the pool boiling to treat heat, including power plants, cooling and refrigeration applications, and electronics cooling applications like data centers. The high efficiency of pool boiling is becoming very important to improve and develop systems performance and to lessen the fuel and energy loss or consumption. This literature review gathers the existing knowledge as possible on the pool boiling enhancement techniques. Paying attention on the challenges and development associated with these techniques. The examination involves studying basic principles of pool boiling focusing on factors like heat transfer rate and the technical specifications for surface and fluids. Then, it goes deeper reviewing the methods of enhancement, including surface treatment methods, surface modification and liquid physical properties. The goal of this review is to propose as a valuable resource for researchers, engineers, and students seeking a comprehensive understanding of the current state of pool boiling enhancement techniques. By strengthen diverse research findings and identifying gaps in knowledge, this review contributes to the ongoing pursuit of more efficient and sustainable heat transfer solutions for diverse industrial applications.The abstract needs to summarize the content of the paper.

Classifying medical datasets using machine learning algorithms could help physicians to provide accurate diagnosing and suitable treatment. For instance, stroke is one of the serious diseases that attacks many patients annually, and analyzing it is symptoms in advance could save patients’ lives. The warning signs of the stroke can be investigated to be used as attributes or predictors for machine learning models. This study evaluates the performance of four machine learning models to classify stroke datasets. Specifically, Decision Tree, Naïve Bayes, K- Nearest Neighbor (KNN) and Linear discriminant Analyses (LDA) models were trained on 11 attributes collected from 5110 patients to predict stroke risk. The findings showed that KNN outperformed the three other models with an achieved accuracy of 90%, while lowest accuracy was attained by LDA. Moreover, KNN model exhibited an acceptable prediction speed relative to the rest of models. The study also considered balancing the employed data prior validating the models to provide accurate classification. Cross-validation technique was used to avoid over-fitting and under-fitting during training phases.

This study examines the design and analysis of a training aircraft wing. The methodology includes aerodynamic and stress analyses. Microsoft Excel is utilized for scaling. Aerodynamic forces, load distribution, and air foil comparison computations were performed by Xflr 5. Inventor was used for stress analysis, which yielded wing deflections, Von Mises stresses, and safety factors. AutoCAD was employed to draw wing parts. The proper design for the cross-sectional shape of the inner wing components was determined. The goal is to find the lightest cross-section, the placements and numbers of wing ribs, and calculate the wing's dimensions. The findings revealed that wing tip deflection did not exceed 0.02. The von Mises calculations also show that the chosen material meets the requisite safety factor. For I and U sections, the deflection, von Mises stresses, and safety factor were 46.52mm and 43.27mm, 219.3 MPa and 152.7MPa, and 1.25 and 1.8, respectively.

Human activity recognition has attracted researchers’ attention in the last two decades. Anterior Cruciate Ligament (ACL) exercises are example of these activities that have to be performed correctly to ensure efficient knee joint recovery. Hence, Machine and Deep Learning algorithms have been employed to classify ACL exercises and evaluate its correctness. This study investigates the accuracy of five machine learning algorithms, SVM, Decision Tree, Random Forest, Gradient boosting and KNN, with CNN in terms of their ability to classify ACL exercises. The data of seven ACL exercises, performed by four subjects, were collected using Accelerometer and gyroscope sensors, then these data were used to train the algorithms. Results showed that both CNN and Random Forest models performed well and achieved higher accuracy among the other algorithms with real accelerometer and gyroscope data. However, Random Forest model outperformed other models when relying on real accelerometer data only or with synthesized data. Moreover, it is also found that gyroscope data are essential for such systems to train the algorithms efficiently and excluding such data leads to downgrade the classification performance.

This thorough analysis provides a detailed overview of developments, obstacles, and future prospects in this important field of structural engineering by synthesizing current works on shear wall design for seismic protection in multi-story residential structures. Shear walls are discussed in terms of location, organization, and creative design strategies. Shear walls are essential for resisting lateral stresses and guaranteeing stability during seismic occurrences. Shear walls arranged in a central core are shown to be helpful in minimizing top-story displacement during seismic activity. Studies on materials show improved strength, ductility, and stiffness, such as corrugated steel plates. The article includes experiments that investigate the behavior of shear walls under different loading scenarios, including information on aspects ratio effects, overturning resistance, and the connection between panel height and drift/shear strength. The impact of anchoring solutions on wall movement is closely examined. Furthermore, research using computer tools such as STAAD.Pro and ETABS provide quantifiable data on the behavior of buildings, highlighting the beneficial effect of shear walls in minimizing displacement.