The complexity and variety of language included in policy and academic documents make the automatic classification of research papers based on the United Nations Sustainable Development Goals (SDGs) somewhat difficult. Using both pre-trained and contextual word embeddings to increase semantic understanding, this study presents a complete deep learning pipeline combining Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Network (CNN) architectures which aims primarily to improve the comprehensibility and accuracy of SDG text classification, thereby enabling more effective policy monitoring and research evaluation. Successful document representation via Global Vector (GloVe), Bidirectional Encoder Representations from Tra

This study employs evolutionary optimization and Artificial Intelligence algorithms to determine an individual’s age using a single-faced image as the basis for the identification process. Additionally, we used the WIKI dataset, widely considered the most comprehensive collection of facial images to date, including descriptions of age and gender attributes. However, estimating age from facial images is a recent topic of study, even though much research has been undertaken on establishing chronological age from facial photographs. Retrained artificial neural networks are used for classification after applying reprocessing and optimization techniques to achieve this goal. It is possible that the difficulty of determining age could be reduce

A new and hybrid deep learning-based approach for diagnosing faults in electric vehicle (EV) drive motors is proposed in this article. This article presents a new and hybrid deep learning-based method of diagnosing faults in the drive motors of electric vehicles (EV). In contrast to standard CNNLSTM approaches that depend on SoftMax classification, the introduced framework combines a Random Forest (RF) classifier to enhance the generalization, interpretability, and robustness of fault prediction. Furthermore meant for use on edge computing equipment with IoT integration, the design allows for real-time monitoring in resource-limited settings. The introduced algorithm utilizes a Random Forest (RF) classifier for accurate fault classification

Breast cancer is highlighted in recent research as one of the most prevalent types of cancer. Timely identification is essential for enhancing patient results and decreasing fatality rates. Utilizing computer-assisted detection and diagnosis early on may greatly improve the chances of recovery by accurately predicting outcomes and developing suitable treatment plans. Grading breast cancer properly, especially evaluating nuclear atypia, is difficult owing to faults and inconsistencies in slide preparation and the intricate nature of tissue patterns. This work explores the capability of deep learning to extract characteristics from histopathology photos of breast cancer. The research introduces a new method called SMOTE-based Convolut

Genome sequencing has significantly improved the understanding of HIV and AIDS through accurate data on viral transmission, evolution and anti-therapeutic processes. Deep learning algorithms, like the Fined-Tuned Gradient Descent Fused Multi-Kernal Convolutional Neural Network (FGD-MCNN), can predict strain behaviour and evaluate complex patterns. Using genotypic-phenotypic data obtained from the Stanford University HIV Drug Resistance Database, the FGD-MCNN created three files covering various antiretroviral medications for HIV predictions and drug resistance. These files include PIs, NRTIs and NNRTIs. FGD-MCNNs classify genetic sequences as vulnerable or resistant to antiretroviral drugs by analyzing chromosomal information and id

The rapid development of Internet of Things (IoT) devices and their increasing numbers have caused a tremendous increase in network traffic and a wider range of cyber-attacks. This growing trend has complicated the detection process for traditional intrusion detection systems and heightened the challenges faced by these devices, such as imbalanced and large training data. This study presents a cohesive methodology of a series of intelligent techniques to prepare clean and balanced data for training the first (core) layer of a robust hierarchical intrusion detection system. The methodology was built by cleaning and compressing the data using an Autoencoder and preparing a strong latent space for balancing using a hybrid method that combines

This research describes a new model inspired by Mobilenetv2 that was trained on a very diverse dataset. The goal is to enable fire detection in open areas to replace physical sensor-based fire detectors and reduce false alarms of fires, to achieve the lowest losses in open areas via deep learning. A diverse fire dataset was created that combines images and videos from several sources. In addition, another self-made data set was taken from the farms of the holy shrine of Al-Hussainiya in the city of Karbala. After that, the model was trained with the collected dataset. The test accuracy of the fire dataset that was trained with the new model reached 98.87%.

Metasurface polarizers are essential optical components in modern integrated optics and play a vital role in many optical applications including Quantum Key Distribution systems in quantum cryptography. However, inverse design of metasurface polarizers with high efficiency depends on the proper prediction of structural dimensions based on required optical response. Deep learning neural networks can efficiently help in the inverse design process, minimizing both time and simulation resources requirements, while better results can be achieved compared to traditional optimization methods. Hereby, utilizing the COMSOL Multiphysics Surrogate model and deep neural networks to design a metasurface grating structure with high extinction rat