Analysis of hyperspectral imagery (HSI) is a critical aspect remote sensing in precision agriculture, for which effective dimensionality reduction (DR) strategies the inherent complexity and uncertainty data are highly necessary. The fusion fuzzy logic with DR techniques offers potential promises to refine enough feature information from classification system, may potentially compromise information. However, graph-based deep learning, especially use graph attention networks (GATs), has...

The rapid development of computational methods and the increasing volume chemical biological data have contributed to an immense growth in research. This field study is known as "chemoinformatics," which a discipline that uses machine-learning techniques extract, process, extrapolate from structures. One significant lines research chemoinformatics blood–brain barrier (BBB) permeability, aims identify drug penetration into central nervous system (CNS). In this research, we attempt solve...

Recent advances in machine and deep learning algorithms enhanced computational capabilities have revolutionized healthcare medicine. Nowadays, research on assistive technology has benefited from such creating visual substitution for impairment. Several obstacles exist people with impairment reading printed text which is normally substituted a pattern-based display known as Braille. Over the past decade, more wearable embedded devices solutions were created to facilitate of texts. However,...

Segmenting brain tumors is a critical task in medical imaging that relies on advanced deep-learning methods. However, effectively handling complex tumor regions requires more comprehensive and strategies to overcome challenges such as computational complexity, the gradient vanishing problem, variations size visual impact. To these challenges, this research presents novel computationally efficient method termed lightweight Inception U-Net (LIU-Net) for accurate segmentation task. LIU-Net...

Ultrasound imaging is frequently employed to aid with fetal development. It benefits from being real-time, inexpensive, non-intrusive, and simple. Artificial intelligence becoming increasingly significant in medical can assist resolving many problems related the classification of organs. Processing ultrasound (US) images uses deep learning (DL) techniques. This paper aims assess development existing DL systems for use a real maternal-fetal healthcare setting. experimental process has two...

Computational approaches for synthesizing new chemical compounds have resulted in a major explosion of data the field drug discovery. The quantitative structure-activity relationship (QSAR) is widely used classification and regression method to represent between structure its activities. This research focuses on effect dimensionality-reduction techniques high-dimensional QSAR dataset. Because multi-dimensional nature QSAR, become an integral part modeling process. Principal component...

Colon cancer is one of the world's three most deadly and severe cancers. As with any cancer, key priority early detection. Deep learning (DL) applications have recently gained popularity in medical image analysis due to success they achieved detection screening cancerous tissues or organs. This paper aims explore potential deep techniques for colon classification. research will aid prediction order provide effective treatment timely manner. In this exploratory study, many optimizers were...

The blood–brain barrier plays a crucial role in regulating the passage of 98% compounds that enter central nervous system (CNS). Compounds with high permeability must be identified to enable synthesis brain medications for treatment various diseases, such as Parkinson’s, Alzheimer’s, and tumors. Throughout years, several models have been developed solve this problem achieved acceptable accuracy scores predicting penetrate barrier. However, “low” has challenging task. In study, we present...

In the rapidly evolving landscape of modern technology, convergence blockchain innovation and machine learning advancements presents unparalleled opportunities to enhance computer forensics. This study introduces SentinelFusion, an ensemble-based framework designed bolster secrecy, privacy, data integrity within systems. By integrating cutting-edge security properties with predictive capabilities learning, SentinelFusion aims improve detection prevention breaches tampering. Utilizing a...

Fruits and vegetables are among the most nutrient-dense cash crops worldwide. Diagnosing diseases in fruits is a key challenge maintaining agricultural products. Due to similarity disease colour, texture, shape, it difficult recognize manually. Also, this process time-consuming requires an expert person. We proposed novel deep learning optimization framework for apple cucumber leaf classification consider above challenges. In framework, hybrid contrast enhancement technique based on Bi-LSTM...

The recent advances in Machine Learning tools and algorithms have influenced fields including drug discovery. Nowadays, research conducted via trial- and-error experiments been replaced by computational approaches. This growth prompted an undeniable development synthesizing chemical data to support chemoinformatics research. One of the widely used model problems is Quantitative Structure-Activity Relationships (QSAR). Previous QSAR models were dealing with small datasets limited number...

Brain stress monitoring has emerged as a critical research area for understanding and managing neurological health issues. This burgeoning field aims to provide accurate information prediction about individuals' levels by analyzing behavioral data physiological signals. To address this emerging problem, study proposes an innovative approach that uses attention mechanism-based XLNet model (called BrainNet) continuous level prediction. The proposed analyzes streams of brain data, including...

Quantitative structure-activity relationship (QSAR) modeling is an established approach for drug discovery, but many QSAR datasets suffer from the curse of dimensionality, a challenge that usually addressed by using dimensionality reduction techniques such as principal component analysis (PCA). However, although linear feature extraction have low computational cost and can handle relationships between descriptors, they cannot complex structures found in data. Hybridization effective to...

The research in the field of e-commerce security and cyber frauds is continually arising. Many measures were taken to facilitate dealing with attacks protect system as a whole. However, most these work only after attack took place. In this research, we take new approach identifying some symptoms relating website, web-server or network that might be an alarming indicator at risk. correlation existence relatively high show study highly crucial for websites operators their preliminary...

The growing incidence of web 2.0 challenges the traditional offline retailers to create a new method shopping and usage consuming goods services through virtual space over electronic store. A contextual framework customer relationship emerges aggregation collaborative-shared opinion on personal preferences about in Web. While benefits building dynamic content into an e-commerce site are profound, personalized access perhaps even bigger. Today more than ever, it is widely assumed that getting...

The authentication process plays a crucial role in ensuring accurate and high-level security various applications, particularly the face of emerging technologies growing threat unauthorized access. Through comprehensive review previous studies on brain-computer interface (BCI)-based authentication, we have identified it as secure promising solution, harnessing unique characteristics brainwaves. main objective this research is to systematically categorized literature based modality, type, BCI...

In recent times, automated detection of diseases from pathological images leveraging Machine Learning (ML) models has become fairly common, where the ML learn detecting disease by identifying biomarkers images. However, such an approach requires to be trained on a vast amount data, and healthcare organizations often tend limit access due privacy concerns. Consequently, collecting data for traditional centralized training becomes challenging. These concerns can handled Federation (FL), which...

<title>Abstract</title> Parkinson’s disease (PD) is a neurodegenerative affecting millions of people around the world. Conventional PD detection algorithms are generally based on first and second-generation artificial neural network (ANN) models which consume high energy have complex architecture. Considering these limitations, time-varying synaptic efficacy function-based leaky-integrate fire neuron model, called SEFRON used for PD. explores advantages Spiking Neural Network (SNN) suitable...