Dual graph attention network for robust fault diagnosis in photovoltaic inverters.

This paper presents a novel deep learning framework based on a Dual Graph Attention Network (DualGAT) to enhance the accuracy and robustness of fault diagnosis in photovoltaic (PV) inverters operating under diverse environmental and operational conditions. Given the critical role of PV inverters in ensuring stable energy conversion, early and reliable detection of open-circuit faults is essential to prevent performance degradation and equipment failure. To address this, a detailed simulation model of a grid-connected PV inverter was developed in MATLAB/Simulink, incorporating variations in irradiance and temperature to generate realistic fault scenarios.

Multisite study using a customised NLP model to predict disposition in the emergency department: protocol paper.

Introduction: To address timely care in emergency departments, artificial neural networks (ANNs) with natural language processing will be applied to triage notes to predict patient disposition. This study will develop a predictive model that predicts disposition and type of admission.

Methods And Analysis: This will include data preprocessing and quality enhancement, masked language modelling, ANN-based fusion network for prediction.

Deep representation learning using layer-wise VICReg losses.

This paper presents a layer-wise training procedure of neural networks by minimizing a Variance-Invariance-Covariance Regularization (VICReg) loss at each layer. The procedure is beneficial when annotated data are scarce but enough unlabeled data are present. Being able to update the parameters locally at each layer also handles problems such as vanishing gradient and initialization sensitivity in backpropagation.

Corrigendum to "Environmental impact assessment of tobacco farming in northern Bangladesh" [Heliyon Volume 9, Issue 3, March 2023, Article e14505].

[This corrects the article DOI: 10.1016/j.heliyon.

An effective statistical moment-based feature extraction technique to identify the phosphoglycerylation sites from protein sequences.

A kind of covalent modification known as post-translational modification (PTM) happens following the biosynthesis process, which is important in cell biology research. A reversible PTM called Lysine phosphoglycerylation alters glycolytic enzyme activity and is linked to several disorders, including heart failure, arthritis, and nervous system deterioration. Identification of phosphoglycerylation has been improved using a variety of feature extraction approaches with machine learning technologies.

Recent Advances in Food Drying Modeling: Empirical to Multiscale Physics-Informed Neural Networks.

Food insecurity is a major global challenge. Food preservation, particularly through drying, presents a promising solution to enhance food security and minimize waste. Fruits and vegetables contain 80%-90% water, and much of this is removed during drying.

Deep learning for early detection of chronic kidney disease stages in diabetes patients: A TabNet approach.

Chronic kidney disease (CKD) poses a significant risk for diabetes patients, often leading to severe complications. Early and accurate CKD stage detection is crucial for timely intervention. However, it remains challenging due to its asymptomatic progression, the oversight of routine CKD tests during diabetes checkups, and limited access to nephrologists.

Navigating nutrients: A scoping review on real-time food nutrition classification and recommendation systems.

In an era where fast-paced lifestyles often conflict with the pursuit of healthy eating, the demand for innovative solutions to aid nutritional decision-making has never been more pressing. Real-time food nutrition classification and recommendation systems offer an effective solution to this growing issue. By harnessing state-of-the-art technologies such as sensor-based data collection and machine learning algorithms, these systems can conduct a precise analysis of the nutritional composition of foods.

Biosynthesis and Characterization of ZnO Nanoparticles Using Peel Followed by Photocatalytic, Antibacterial, and Antioxidative Nanotherapeutic Attributes Assessment Supported by Computer Simulation.

Introduction: ZnO nanoparticles (NPs) have garnered significant attention due to their remarkable multifunctionality, particularly in biomedical and environmental applications.

Methods: The study synthesized ZnO NPs using Blanco peel extracts. The structural, morphological, and optical properties of ZnO NPs have been analyzed.

Lung Segmentation with Lightweight Convolutional Attention Residual U-Net.

Examining chest radiograph images (CXR) is an intricate and time-consuming process, sometimes requiring the identification of many anomalies at the same time. Lung segmentation is key to overcoming this challenge through different deep learning (DL) techniques. Many researchers are working to improve the performance and efficiency of lung segmentation models.

Designing Chip-Feed High-Gain Millimeter-Wave Resonant Cavity Antenna (RCA) Array and Optimization of Beam Steering Metasurface.

In this article, a chip-fed millimeter-wave high-gain antenna system with in-antenna power combining capability is presented. A low-profile resonant cavity antenna (RCA) array is fed by multiple spherical dielectric resonators (DRs), demonstrating its multi-feed capabilities. Each of the DRs is fed by two microstrip resonators on a planar circuit board.

Synthesis and characterization of spin coated ZnTe thin films for improving the efficiency of ZnTe/ZnS solar cell using SCAPS-1D.

Cadmium telluride (CdTe) absorber layer in solar cells (SCs) is environmentally dangerous for the toxic behavior of cadmium (Cd). Alternatively, zinc telluride (ZnTe) is deliberated as a promising PV material for its adoptable absorption coefficient, better conversion efficiency and low production cost of materials requirements. The main objective of this study is to synthesis and characterization analysis of ZnTe thin films to enhance the performance of ZnS/ZnTe solar cell.

Live and mediated user engagements: A comparative dataset from two Bengali audio-story based youtube channels.

The dataset contains user engagement and language-related information from two audio story-producing channels on YouTube. It offers a comparative view of live and mediated engagements, which includes information pertinent to the user's interaction of audio-story based YouTube contents. The speciality of this dataset is the inclusion of textual data of live comments on YouTube videos.

A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images.

Brain tumors present a significant global health challenge, and their early detection and accurate classification are crucial for effective treatment strategies. This study presents a novel approach combining a lightweight parallel depthwise separable convolutional neural network (PDSCNN) and a hybrid ridge regression extreme learning machine (RRELM) for accurately classifying four types of brain tumors (glioma, meningioma, no tumor, and pituitary) based on MRI images. The proposed approach enhances the visibility and clarity of tumor features in MRI images by employing contrast-limited adaptive histogram equalization (CLAHE).

Design and numerical analysis of a modified core hexa-deca photonic crystal fiber for highly negative dispersion and birefringence control in optical communication bands.

The paper presents a thorough investigation into the design of a Modified Core Hexa-Deca Photonic Crystal Fiber (MHD-PCF) with adjustable features to regulate dispersion and birefringence. At the target wavelength of 1550 nm, the suggested MHD-PCF exhibits extraordinary optical properties, including an ultra-high negative dispersion coefficient of - 7755 ps/(nm km) and significant birefringence of 1.905 × 10.

Ensembling methods for protein-ligand binding affinity prediction.

Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features.

CSXAI: a lightweight 2D CNN-SVM model for detection and classification of various crop diseases with explainable AI visualization.

Plant diseases significantly impact crop productivity and quality, posing a serious threat to global agriculture. The process of identifying and categorizing these diseases is often time-consuming and prone to errors. This research addresses this issue by employing a convolutional neural network and support vector machine (CNN-SVM) hybrid model to classify diseases in four economically important crops: strawberries, peaches, cherries, and soybeans.

ECG waveform generation from radar signals: A deep learning perspective.

Cardiovascular diagnostics relies heavily on the ECG (ECG), which reveals significant information about heart rhythm and function. Despite their significance, traditional ECG measures employing electrodes have limitations. As a result of extended electrode attachments, patients may experience skin irritation or pain, and motion artifacts may interfere with signal accuracy.

Biomechanical analysis of little penguins' underwater locomotion from the free-ranging dive data.

Penguins are proficient swimmers, and their survival depends on their ability to catch prey. The diving behaviour of these fascinating birds should then minimize the associated energy cost. For the first time, the energy cost of penguin dives is computed from the free-ranging dive data, on the basis of an existing biomechanical model.

RHMCD-20 dataset: Identify rapid human mental health depression during quarantine life using machine learning.

The RHMCD-20 dataset offers a thorough investigation of the dynamics of mental health in Bangladesh while under quarantine. The structured survey that was distributed to different demographic groups yielded a dataset that included a wide range of variables, such as age, gender, occupation, and stress levels. Predictive modelling, understanding the effects of quarantine on the workplace and society, and intergenerational insights are all greatly enhanced by this dataset.

An in-depth analysis and review of management strategies for E-waste in the south Asian region: A way forward towards waste to energy conversion and sustainability.

The soaring rise of electronic and electrical waste (E-waste) leads to significant challenges to the South Asian region, urging for incorporating comprehensive assessment and management strategies. The research dives into the intricacies of E-waste and examines how regulatory barriers, public ignorance, and the limited lifespan of electronic devices all contribute to the significant production of E-waste. This study emphasizes the vital need for ongoing and appropriate management practices by bringing attention to the short lifespan of electronic devices and the resulting generation of E-waste.

A smart medicine reminder kit with mobile phone calls and some health monitoring features for senior citizens.

The demand for an effective system that combines cutting-edge technologies with medical research to improve healthcare systems has increased with the development of medical technology. The most fundamental form of disease prevention is taking the right medication when needed. With the right care, many fatal diseases can be cured or prevented.

Numerical simulation and performance optimization of a lead-free inorganic perovskite solar cell using SCAPS-1D.

The perovskite solar cells, founded on lead halides, have garnered significant attention from the photovoltaic industry owing to their superior efficiency, ease of production, lightweight characteristics, and affordability. However, due to the hazardous nature of lead-based compounds, these solar cells are currently unsuitable for commercial production. In this context, a lead-free perovskite, cesium-bismuth iodide (CsBiI) is considered as a potential alternative to the lead halide-based cell due to their non-toxicity and stability, but this perovskite cannot be matched with random hole transport layer (HTL) and electron transport layer (ETL) materials compared to lead halide-based perovskite because of their crystal structure and band gap.

Advancements in adsorption based carbon dioxide capture technologies- A comprehensive review.

The significant increase in energy consumption has facilitated a rapid increase in offensive greenhouse gas (GHG) and CO emissions. The consequences of such emissions are one of the most pivotal concerns of environmental scientists. To protect the environment, they are conducting the necessary research to protect the environment from the greenhouse effect.