CPI systems used to spray crops in the Karbala Desert face two main problems: the cost of generating electricity with generators and the difficulty of delivering electricity from the grid to remote areas. Second, the fixed solar panels feeding some of these systems cannot produce enough electricity because they cannot track the sun’s rays. To solve these issues, appropriate actuators must be combined with these panels to form solar trackers. Due to their advantages over others, pneumatic actuators are proposed to enable the panels to constantly track the sun’s rays. This leads to the production of as much energy as possible during daylight hours. This study aims to design a single-axis pneumatic solar tracker using MATLAB/Simulink to produce sufficient electrical power to operate the entire irrigation system. An economic feasibility study was conduct for the developed system. Mathematical calculations were performed on the irrigation system to obtain the initial values necessary to complete the design procedure. The design results showed that using the pneumatic tracker enabled the PV panels to efficiently run the entire irrigation system during the day. Moving the panels on one axis increased the average panel’s efficiency by 48% compared to fixed panels. The feasibility study results indicate that building a CPI system using a solar tracker is expected to have 29.41% lower energy costs than a similar system with fixed panels.
Effective thermal management is critical for ensuring the safety, performance, and longevity of EV batteries. This study presents a comprehensive assessment of advanced BTMSs using CFD simulations, experimental validation, and statistical modeling. Three advanced heat transfer mechanisms microchannel cooling, heat pipes, and jet impingement cooling— were evaluated alongside novel materials, including graphene-enhanced TIMs and hybrid PCMs incorporating carbon nanotubes (CNTs). Jet impingement cooling provided the lowest peak temperature (33.8 °C) and the greatest heat dissipation efficiency (94.5%) among the tested systems. Microchannel cooling maintained 34.5 °C with superior temperature uniformity while graphene CNT hybrid PCMs reached thermal conductivities of up to 15.8 W/m·K, reducing the maximum temperature to 32.4 °C under high-power loads. Regression analysis confirmed that thermal conductivity and flow rate were key predictors of cooling performance (R² > 0.85). Although these technologies are promising, integration remains constrained by high material costs and long-term reliability concerns, such as mechanical degradation and fatigue. This work offers a novel contribution by comparatively analyzing heat transfer mechanisms and material innovations across multiple validation platforms. This study provides data-driven insights to guide cost-effective and scalable thermal solutions for next-generation EV platforms.
Alzheimer’s disease (AD) is a complicated neurodegenerative disease marked by the slow worsening of memory and cognitive functions. Early detection is a key to effective disease management, but the creation of reliable machine learning models is not an easy task because medical data are limited, and there are strict privacy requirements, such as GDPR and HIPAA, that inhibit the creation of central databases. In this paper, a new privacy-saving model that combines personalized federated learning (PFL) with generative adversarial networks (GANs) is proposed to diagnose Alzheimer’s disease. Under the proposed method, the synthesis of data using GAN is conducted on the client to expand small datasets and counteract the performance loss due to non-identically distributed (non-IID) data across institutions. Massive testing was performed on the OASIS MRI dataset and compared with known federated learning baselines, such as FedAvg, FedSGD, and FedPer. The perFedGAN framework was proposed, and in IID settings, the proposed method achieved an accuracy of 96.41%. In non-IID difficult settings, the proposed method had an accuracy of 92.5%, which is a significant improvement over traditional federated averaging methodologies and also better robustness and personalization among dissimilar clients. This finding demonstrates the importance of using a combination of generative modeling and personalized federated learning to enable the precise, scalable, and privacy-preserving early detection of AD.
The development of robust machine learning models for medical diagnostics is constrained by the scarcity of large, annotated imaging datasets, a challenge rooted in high acquisition costs and stringent privacy regulations. To address this, generative approaches for data synthesis have emerged as an essential tool, and this study explores the use of diffusion models to generate medical images. This study introduces a novel Diffusion Autoencoder Model (DAM) integrated with a semantic encoder framework to generate interpretable and decodable image representations. Our DAM learns disentangled latent features via its encoder, which then conditions a diffusion probabilistic model acting as the decoder, enabling the synthesis of highly informative medical images. The model’s performance is assessed by using quantitative metrics demonstrating superior results compared to state-of-the-art generative models. In addition to its generative precision, the proposed model has significant potential for image classification. Notably, the semantic encoder learned by the model generates representations that lead to a significant increase in classification accuracy: for PneumoniaMNIST, the binary classification accuracy improved from 0.854 to 0.95; for RetinaMNIST, the multiclass accuracy increased from 0.528 to 0.94. These findings underscore the potential of DAMs to tackle data scarcity issues, enhance classification performance, and ultimately improve diagnostic methodologies.
Bridges are constructed to facilitate the crossing of pedestrians, vehicles, or trains and are essential components of land transportation infrastructure, which is crucial for ensuring the smooth flow of traffic. As part of the reconstruction project for the south side of the Muja Muju Bridge on Jalan Kusumanegara, the Yogyakarta City Government rebuilt this section of the bridge, which had become unfit for traffic use. The area features two bridges, serving as transportation routes: the Muja Muju Bridge on the north side and the newly reconstructed bridge on the south side. The demolition of the south side of the Muja Muju Bridge, as the initial stage of the project, will impact the construction of the bridge on the north side. Excavation for the foundation on the south side must consider various safety considerations, one of which is determining the depth of the foundation on the north side. In this study, the foundation depth is assessed through the geoelectrical measurement method, specifically the dipole–dipole technique. The interpretation of the results indicates that the foundation lies at a depth of 9 to 10 m from the soil surface.
