Artificial Neural Networks - Science topic

Early and accurate plant diseases detection is very important for increased agricultural production and guaranteed food safety. In addition to that, traditional methods of disease diagnosis (typical to large scale farming operations), such as manual inspection, are not very efficient, usually labour intensive and less accurate. A systematic review...

The quality of education is associated with the condition of the infrastructure in which the educational process occurs, necessitating the continuous maintenance of these facilities. Limited and often insufficient maintenance funds pose a challenge in this context. Current cost estimates are inaccurate, and data on school and maintenance costs are...

Even before the age of artificial intelligence, automated scoring received considerable attention in educational measurement. However, its application to constructed response (CR) items in international large-scale assessments (ILSAs) has remained a challenge, primarily due to the difficulty of handling multilingual responses spanning many language...

In the field of reacting flows, numerical simulations often face an accuracy-cost trade-off, and continuous predictions for multi-scale stiff reacting flows can be prohibitively expensive, especially for large-scale cases. Although neural network models have been explored as surrogates for numerical solvers, the high cost of training models with mu...

Large spatial stainless steel structures can be susceptible to accidental events such as fires, given their high occupancy, wide range of combustible materials and diverse usage. Consequently, a comprehensive investigation into the temperature field in large spatial stainless steel structures in the event of a fire has been conducted, encompassing...

The radon-deficit technique has proven to be a valuable tool for environmental site characterization, particularly in detecting subsurface organic contamination. This work highlights its successful application in two contaminated sites, validated by consulting firms and supported by independent data collection campaigns. In the first case study, th...

Arabic letter writing is known as khat art. Khat is classified into many categories and can be identified into three types: Khat Naskhi, Khat Qufi, and Khat Farisi, per the rules established in the art of Khat. Arabic letters, the subjects of khat art, evolved following the region where it first appeared. As a result, the Qufi style, for instance,...

Purpose This study examines existing automatic screening methods for developmental language disorder (DLD), a neurodevelopmental language deficit without known biomedical etiologies, focusing on languages, data sets, extracted features, performance metrics, and classification methods. Additionally, it summarizes the strengths and weaknesses of curr...

Introduction: Glioblastoma (GBM), the most aggressive primary brain tumor, poses a significant challenge in predicting patient survival due to its heterogeneity and resistance to treatment. Accurate survival prediction is essential for optimizing treatment strategies and improving clinical outcomes. Methods: This study utilized metadata from 135 G...

This review highlights the application of artificial intelligence (AI), particularly deep learning and machine learning (ML), in managing antimicrobial resistance (AMR). Key findings demonstrate that AI models, such as Naïve Bayes, Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and Artificial Neural Networks (ANN), have sig...

This study introduces a novel approach for predicting the mechanical properties of 3D-printed polylactic acid wood composites using gene expression programming (GEP) and artificial neural networks (ANN) modeling methods. Addressing the challenge of determining optimal process parameters in fused deposition modeling of natural fiber composites, expe...

Infrared (IR) photodetectors based on narrow‐bandgap 2D materials and heterojunctions have shown great promise in constructing IR sensing systems, including optical communication, security monitoring, thermal imaging, and astronomy exploration. In recent years, significant progress has been made in developing performance enhancement strategies for...

The fluid flow analysis past a Riga plate is significantly considered in engineering and physics, particularly used for examining the boundary layer nanofluid flow. The Riga surface is normally used for estimation and regulating the properties of turbulent and laminar flow. Determining the behavior of fluid flow across a Riga plate is important in...

Intrusion detection systems (IDS) have become a fundamental layer in cybersecurity infrastructure, particularly with the rising complexity and volume of cyber threats. Efficient feature selection is crucial for enhancing the performance and scalability of machine learning (ML) and deep learning (DL) models used in IDS. Feature selection aims to red...

The main issue that TIG welding experiences is limited weld penetration which eventually restricts its productivity. In order to overcome this difficulty and incomparable advantages of TIG welding, a method known as activating flux tungsten inert gas (A-TIG) welding was introduced, and is currently the focus of extensive research. When compared to...

This study employs physics-informed neural ordinary differential equations to perform time series forecasting for dynamic system monitoring. In this approach, predictions of the system’s dynamic response over time are generated by integrating physical laws with observed data, enhancing forecasting accuracy. The dataset consists of vibration data fr...

Multiclass classification with small datasets often presents a significant challenge for conventional machine learning (ML) algorithms, predicting with an accuracy affected by this context of data scarcity. To remedy this, this papers presents a novel ML model based on a differentiable deterministic finite-state machine (DFSM) that improves the pre...

This research explores the application of artificial intelligence, particularly artificial neural networks, in the diagnosis and prediction of cardiovascular diseases. It highlights how AI technologies enhance diagnostic accuracy, support early detection, and enable personalized treatment strategies in modern cardiology.

This research utilizes machine learning (ML), and especially deep learning (DL), techniques for efficient feature extraction of intrusion attacks. We use DL to provide better learning and utilize machine learning multilayer perceptron (MLP) as an intrusion detection (IDS) and intrusion prevention (IPS) system (IDPS) method. We deploy DL and MLP tog...

Energy efficiency is a critical determinant in the design and operation of Wireless Sensor Networks (WSNs), as sensor nodes are typically powered by constrained battery resources. Asynchronous duty cycle mechanisms have emerged as a viable strategy to optimize energy consumption while preserving network functionality. This research presents a compa...

Friction Stir Welding (FSW) arose as a game changing joining technology for high-strength materials, predominantly in aerospace, automotive, and marine applications. However, ensuring weld quality and process optimization remains a critical challenge owing to the complex interplay of parameters and the occurrence of defects. Latest advancements in...

In recent years, the scarcity of high-quality and sufficient water resources has become a significant challenge for sustainable development. Understanding water cycle processes and runoff data is crucial in this context. This study focuses on the Ajichai sub-basin within the Urmia Lake Basin, aiming to model daily rainfall-runoff using intelligent...

This research examines the key performance indicators (KPIs) that impact physical jump performance among elite female volleyball players. It tests three main hypotheses: (1) that using the STR score for training load quantification provides a better explanation and prediction of jump performance than traditional methods; (2) that high-intensity exe...

The synergistic development of nanophotonics and machine learning has inspired tremendous innovations in both fields in the past decade. In diverse photonics research, deep-learning methods using artificial neural networks become the key game changer that greatly facilitates rapid nanophotonics design and the versatile processing of optical informa...

In industrial production, obtaining sufficient bearing fault signals is often extremely difficult, leading to a significant degradation in the performance of traditional deep learning-based fault diagnosis models. Many recent studies have shown that data augmentation using generative adversarial networks (GAN) can effectively alleviate this problem...

El presente estudio propone el diseño de una herramienta predictiva basada en redes neuronales artificiales para estimar la producción anual de caña de azúcar. La producción de caña de azúcar está sujeta a múltiples variables que dificultan su predicción precisa mediante métodos tradicionales. Se recopilaron datos históricos de producción de caña d...

Spike transformers cannot be pretrained due to objective factors such as lack of datasets and memory constraints, which results in a significant performance gap compared to pretrained artificial neural networks (ANNs), thereby hindering their practical applicability. To address this issue, we propose a hybrid attention spike transformer that utilis...

Diffusion in biological systems is inherently complex due to heterogeneous interactions, which lead to anomalous diffusion where single-particle trajectories transition between distinct diffusive states. Detecting these transitions is crucial for understanding the underlying mechanisms, as they offer valuable insights into changes in microscopic in...

Recently, there has been an increase in the usage of novel devices in distribution networks for fault locating and detection, such as fault indicators (FI). They provide additional data sets that can help with faulted section location (FSL). This paper proposes an artificial neural network (ANN) method that uses the FI statuses to determine the FSL...

ABSTRACT Accurate electric load forecasting is essential for efficient energy management, cost reduction, and grid stability. Traditional forecasting models, such as the Autoregressive Integrated Moving Average (ARIMA) and Artificial Neural Networks (ANNs), have limitations when used independently. ARIMA effectively captures linear trends, while AN...

In this study, two feedforward artificial neural networks (ANNs) were trained on experimental data to predict the melt-blowing (MB) fiber diameter of hot-melt adhesive and polypropylene fibers based on process operating conditions and nozzle geometry. These ANNs enabled a sensitivity analysis to investigate the effects of input parameters on the fi...

Context. The problem of identification and determination of personalized comprehensive indicators of presence each of the impact factors in the processes of personal subjectivization of the researched supported object’s perception by the relevant subjects interacting with it and making influence on its support, is being considered in this research....

The aim of the research was to develop and evaluate the usefulness of artificial neural network models for predicting the key operating parameters of centrifugal settlers. Various settler structures were analyzed, taking into account such elements as internal partitions and also inlet and outlet nozzles. Neural network modeling was continued until...

We utilize the machine learning to extrapolate to the infinite model space the no-core shell model (NCSM) results for the energies and rms radii of the 6He ground state and 6Li lowest states. The extrapolated energies and rms radii converge as the NCSM results from larger model spaces are included in the training dataset for ensemble of artificial...

The application of shower heat exchangers (SHEs) allows for a reduction in the amount of energy necessary to heat domestic hot water (DHW). As a result, not only the costs of heating DHW but also the emission of harmful products of fuel combustion is reduced. However, the identification of key areas determining the resulting carbon dioxide emission...

Considering the increasing dependence on artificial intelligence in various fields, including accountability and scrutiny in a wide range, the need to develop internal audit work in economic units has shown by resorting to artificial intelligence applications, and accordingly, this study aims to know the impact of adoption of artificial neurologica...

Concrete production heavily relies on natural aggregates, leading to environmental concerns due to resource depletion and extraction impacts. This study explores the feasibility of using demolished concrete aggregate (DA) as a sustainable alternative. Despite being a major global waste product, DA’s effects on concrete properties remain underexplor...

Practitioners and academics alike have applied the Black–Scholes model when pricing options practically since its introduction in 1973. The COVID-19 pandemic and the oil futures price crash of April 2020 caused major markets to briefly switch to the less widely known Bachelier model to price derivatives, as the model allows for negative strikes on...

Single-molecule localization microscopy methods such as dSTORM require specific buffer conditions to enable blinking and detection of individual emitters, making them incompatible with live cell imaging and expansion microscopy. An alternative approach to achieve super-resolution without blinking is to observe the fluctuations of the emitter intens...

Spiking neural networks (SNN) hold the promise of being a more biologically plausible, low-energy alternative to conventional artificial neural networks. Their time-variant nature makes them particularly suitable for processing time-resolved, sparse binary data. In this paper, we investigate the potential of leveraging SNNs for the detection of pho...

Spectrum distribution and channel detection have long been seen as an impending addition to intelligent radios for wireless communications systems with permit-free groups. Standard approaches have been put forth to handle periodic scanning as a signal characterization technique for applications where carrier frequencies and transmission speeds are...

Tracking control of multibody systems is a challenging task requiring detailed modeling and control expertise. Especially in the case of closed‐loop mechanisms, inverse kinematics as part of the controller may become a game stopper due to the extensive calculations required for solving nonlinear equations and inverting complicated functions. The pr...

The hot deformation behavior of Ferrium® C64 (Fe–16Co–7.5Ni–0.1C) alloy was investigated through isothermal uniaxial hot compression tests over a temperature range of 1123–1423 K and strain rates from 0.01 to 10 s⁻¹. Based on the experimental results, three predictive models were developed: Arrhenius-type constitutive model (ACM), strain-compensate...

This study investigates the mechanical properties of hybrid composites reinforced with jute, kenaf, and glass fibers, incorporating Aluminum Oxide (Al2O3) as a nanoparticle filler. The effects of three key parameters—fiber orientation, fiber sequence, and weight percentage of Al2O3 on—the tensile and impact strength of the composites were examined....

Artificial neural networks trained in the field of artificial intelligence (AI) have emerged as key tools to model brain processes, sparking the idea of aligning network representations with brain dynamics to enhance performance on AI tasks. While this concept has gained support in the visual domain, we investigate here the feasibility of creating...

An Artificial Neural Network (ANN) inference involves matrix vector multiplications that require a very large number of multiply and accumulate operations, resulting in high energy cost and large device footprint. Stochastic computing (SC) offers a less resource-intensive ANN implementation and can be realized through stochastic-magnetic tunnel jun...

Aircraft weight is a key input in flight trajectory prediction and environmental impact assessment tools. However, the lack of openly available data regarding the actual aircraft weight throughout the flight requires the development of mass estimation approaches to be incorporated into these tools. This study uses large-scale open aviation data mad...

Objective This study is experimental in nature and assesses the effectiveness of the Cross-Attention Vision Transformer (CrossViT) in the early detection of Oral Squamous Cell Carcinoma (OSCC) and proposes a hybrid model that combines CrossViT features with manually extracted features to improve the accuracy and robustness of OSCC diagnosis. Metho...

El presente artículo analiza los determinantes socioeconómicos y demo-gráficos de la inclusión financiera en México. Empleando microdatos de la Encuesta Nacional de Inclusión Financiera (ENIF) 2021 se construye un índice de inclusión financiera, considerando los siguientes productos: tarjeta de crédito, cuenta de ahorro, fondo de inversión, crédito...

The world population continues to increase with a large proportion of this increase happening in Africa just as predicated by Food and Agriculture Organization of the United Nation. To meet the demand of feeding this increasing population, innovative farming practices are being developed to increase the yield of the major stable food supply. This r...

Memristors are considered as key components of brain-like hardware to meet the demand for energy-efficient computing in the era of big data. The realization of synaptic and neuronal functions based on memristors is a prerequisite for building artificial neural networks. In this study, we fabricated artificial synaptic devices based on Zr-doped BaTi...

Natural systems often exhibit chaotic behavior in their space-time evolution. Systems transiting between chaos and order manifest a potential to compute, as shown with cellular automata and artificial neural networks. We demonstrate that swarms optimisation algorithms also exhibit transitions from chaos, analogous to motion of gas molecules, when p...

A method for the optimal design of special transformers is proposed; it is based on machine learning models, which, in turn, are informed by a sequence of magnetic field analyses. The optimal design of a leakage reactance transformer is considered as the case study. The results show that surrogate models amenable to artificial neural networks (ANNs...

The increasing demand in modern society for natural sources of bioactive compounds with potential applications in preventive medicine has driven the development of innovative approaches to optimize extraction processes. While Response Surface Methodology (RSM) has been extensively utilized for prediction and optimization in extraction studies, Arti...

Deep learning has revolutionized medical image analysis, offering the possibility of automated, efficient, and highly accurate diagnostic solutions. This article explores recent developments in deep learning techniques applied to medical imaging, including Convolutional Neural Networks (CNNs) for classification and segmentation, Recurrent Neural Ne...

The increased consumption of natural resources, such as water, has become a global concern. Consequently, determining information that can minimize water consumption, such as evapotranspiration, is increasingly necessary. This research evaluates the capacity of Genetic Algorithms (GAs) in training and fine-tuning the parameters of Artificial Neural...

Grouting with water–cement mixtures is the most widely used and cost‐effective method for managing excess water inflow during tunnel construction. Due to uncertain geological and hydrological conditions, current grouting design relies heavily on the experience of onsite engineers. Recent advances in machine learning offer a promising alternative to...

The accurate prediction of body mass (BM) in cattle is crucial for herd monitoring, assessing biological efficiency, and optimizing nutritional management. This study evaluated BM prediction models using morphological data from 465 lactating Holstein cows, including the dorsal length (DL), thoracic width (TW), abdominal width (AW), rump width (RW),...

Viral diseases pose a significant threat to public health, highlighting the importance of understanding protein–protein interactions between hosts and viruses for therapeutic development. However, this process is often expensive and time-consuming, especially given the rapid evolution of viruses. Machine learning algorithms and artificial intellige...

As one of the four basic electronic components, memristors have been widely applied in artificial neural networks in recent years. However, most of the existing researches focus on the application of memristors in artificial neural networks with three or more neurons, and the artificial neural networks with two neurons are rarely reported. Therefor...

Introduction The rapid advancement of AI, particularly artificial neural networks, has led to revolutionary breakthroughs and applications, such as text-generating tools and chatbots. However, this potent technology also introduces potential misuse and societal implications, including privacy violations, misinformation, and challenges to integrity...

This paper proposes a novel control structure for permanent magnet synchronous motors (PMSMs), integrating a fuzzy logic-enhanced PI controller (FPI) with maximum torque per ampere (MTPA) and field weakening (FW) strategies. The primary objective is to address the nonlinear behavior of PMSMs, particularly the complex relationship between reference...

Accurate solar radiation prediction is essential for optimizing renewable energy systems and supporting grid stability. This study investigates the use of principal component analysis (PCA) for dimensionality reduction in solar radiation prediction models, followed by an evaluation of the models’ performance across varying feature sets. A series of...

This paper addresses the design and implementation of a measurement system for the steel industry, enabling precise positioning of steel castings before cutting. The focus is on measurement tools and methods, particularly the design of a new measurement chain for distance measurement. It highlights the importance of understanding environmental cond...

The application of machine learning has revolutionized drug discovery process, enabling more accurate prediction of physicochemical properties. In this study, we utilized machine learning models including Artificial Neural Networks (ANN), XGBoost, and AdaBoost to predict properties of selected anti-biofilm drugs. Both 2D and 3D structural analyses...

Entangled two-photon absorption (eTPA) has been recognized as a potentially powerful tool for the implementation of ultra-sensitive spectroscopy. Unfortunately, there exists a general agreement in the quantum optics community that experimental eTPA signals, particularly those obtained from molecular solutions, are extremely weak. Consequently, obta...

The need for sustainable alternatives in refrigeration has grown as Europe enforces mandates on avoiding high global warming potential (GWP) refrigerants. CO₂-based refrigerants have emerged as a promising choice in response, distinguished by its low GWP and reduced flammability, compared to formulated hydrofluoroolefins, thus offering a safer and...

Time series forecasting is crucial for guiding capital investment, production enhancement, and optimization in the oil and gas industry. However, conventional data-driven approaches for the production prediction fail to meet the industry's criteria. This paper develops a hybrid model combining bidirectional long short-term memory (Bi-LSTM) or bidir...

Objective To refine the lycopene extraction from tomato powder with ionic liquid-microwave assistance, seeking a more efficient and cost-effective process that optimizes resource usage, lowers extraction costs, and boosts the economic value of lycopene. Methods The study investigated the effects of various factors on the extraction yield of lycope...

A novel integration of machine learning (ML) and eXplainable artificial intelligence (XAI) based prediction is proposed to investigate the variability of nanowire (NW) gate-all-around (GAA) ferroelectric-field effect transistors (Fe-FETs). XAI methods such as local interpretable model-agnostic explanations (LIME) and shapley additive explanations (...

Manufactured Insights (AI) and Machine Learning (ML) are increasingly becoming apparatus usage, mainly in neural network models. This extension offers a Verilog-based Manufactured Neural Network (ANN) designed for handwritten letter set recognition on an FPGA. The ANN is a 5-layer fully connected technology-based architecture, making use of ReLU an...

Long-term monitoring and modeling of in-situ soil bioremediation studies have their inherent challenges. In this work, the removal of diesel fuel (DF) from DF-spiked soil was studied for 138 days in six microcosm experiments, with different initial Carbon-to-Nitrogen ratios (C/N) (120, 180), and moisture content (MC) between 8 and 15% (w/w). A hybr...

Metaheuristic optimization is a research area that allows automating the seismic design of structures while prioritizing the sustainable use of resources. Unfortunately, these AI techniques have limited applicability due to their long execution times. To address this limitation, this paper explores the use of artificial neural networks (ANNs) as su...

Lecture and Seminar at National University of Singapore, November, 2007. "Inverse and direct problems of optics: usage of artificial neural networks". Using the ANN we can calculate local and integral characteristics of object by means of incomplete set of data that characterize optical images (or signals) Possibilities of usage the only value of...

The aim of this study is to accurately predict the water quality at these points over a decade through the combined use of statistical tools and artificial intelligence. This study brings the innovative use of neural networks implemented with the GRNN package of the R statistical software to predict the water quality of nine points on the Paraíba d...

Deep learning’s widespread dependence on large datasets raises privacy concerns due to the potential presence of sensitive information. Differential privacy stands out as a crucial method for preserving privacy, garnering significant interest for its ability to offer robust and verifiable privacy safeguards during data training. However, classic di...

Environmental DNA (eDNA) metabarcoding has revolutionized biodiversity monitoring, offering non‐invasive tools to assess ecosystem health. The complexity of eDNA metabarcoding data poses major challenges for conventional ordination methods in understanding assemblage similarities and assessing biodiversity patterns. Here, we introduce ORDNA (ORDina...

Wildfires pose significant environmental threats in Australia, impacting ecosystems, human lives, and property. This review article provides a comprehensive analysis of various empirical and dynamic wildfire simulators alongside machine learning (ML) techniques employed for wildfire prediction in Australia. The study examines the effectiveness of t...

A temperatura do ar é um dos elementos climáticos cruciais no planejamento agrícola e ambiental. No entanto, a rede de monitoramento em países em desenvolvimento possui baixa densidade, requerendo o desenvolvimento de métodos para estimá-la em locais sem medição. Uma opção é utilizar dados de reanálise, como o ERA5, que possuem vieses e necessitam...

Models of dense prediction based on traditional Artificial Neural Networks (ANNs) require a lot of energy, especially for image restoration tasks. Currently, neural networks based on the SNN (Spiking Neural Network) framework are beginning to make their mark in the field of image restoration, especially as they typically use less than 10\% of the e...

Worldwide, this is an important issue of managing water resources with the need for effective distribution and sustainable use. The processes of mathematical modeling and computational techniques of water distribution which include Genetic Algorithms (GA), Linear Programming (LP), Artificial Neural Networks (ANN) and Fuzzy Logic, are considered. To...

Natural systems often exhibit chaotic behavior in their space-time evolution. Systems transiting between chaos and order manifest a potential to compute, as shown with cellular automata and artificial neural networks. We demonstrate that swarm optimization algorithms also exhibit transitions from chaos, analogous to a motion of gas molecules, when...

The growing threat posed by deepfake videos, capable of manipulating realities and disseminating misinformation, drives the urgent need for effective detection methods. This work investigates and compares different approaches for identifying deepfakes, focusing on the GenConViT model and its performance relative to other architectures present in th...

BALA-NET is a bio-inspired neuromorphic AI system designed for real-time adaptive learning and decision-making. Leveraging principles from neuroscience and next-generation AI, BALA-NET incorporates Dynamic Spike-Timing-Dependent Plasticity Plus (Dynamic STDP+), Hybrid Memory Mechanisms, and Cross-Layer Neural Communication to enhance efficiency, ad...