The research and development of hardware neuron technologies are accelerating at a very fast pace to provide for increased efficiency in performing artificial intelligence and autonomy functions beyond that possible with emulation on digital computers. Moreover, dedicated hardware for these biologically inspired functions creates capabilities not possible currently—especially regarding the integration of quantum information processing and advanced non-linear dynamical phenomenon necessary for bridging the gap between artificial and biological intelligence. A synthetic artificial neuron network functional in a regime where quantum information processes are co-integrated with spiking computation provides significant improvement in the capabilities of neuromorphic systems in performing artificial intelligence and autonomy tasks. This provides the ability to execute with the qubit coherence states and entanglement as well as in tandem to perform functions such as read-out and basic arithmetic with conventional spike-encoding. Ultimately, this enables the generation and computational processing of information packets with advanced capabilities and an increased level of security in their routing. We now use the dynamical pulse sequences generated by a memristive spiking neuron to drive synthetic neurons with built-in superconductor-ionic memories built in a lateral layout with integrated niobium metal electrodes as well as a gate terminal and an atomic layer deposited ionic barrier. The memories operate at very low voltage and with direct, and hysteretic Josephson tunneling and provide enhanced coherent properties enabling qubit behavior. We operated now specifically in the burst mode to drive the built-in reconfigurable qubit states and direct the resulting quantum trajectory. We analyze the new system with a Hamiltonian that considers an integrated rotational dependence, dependent on the unique co-integrated bursting mode spiking—and where the total above threshold spike-count is adjustable with variation of the level of coupling between the neurons. We then examined the impact of key parameters with a longer-term non-Markovian quantum memory and finally explored a process and algorithm for the generation of information packets with a coupled and entangled set of these artificial neuron-qubits that provides for a quantum process to define the level of regularity or awareness of the information packets. These results, therefore, enable quantum neural networks where qubit/quantum memory states and the associated quantum trajectories are now available for conducting advanced computational algorithms in conjunction with the information processing capabilities of general spiking neurons.

Background: This study presents a systematic bibliometric mapping and analysis on the acceptance of technology in the field of artificial intelligence (AI), machine learning (ML) and neuronal networks (NN), evaluating the evolution and research trends within this interdisciplinary field. Methods: Using data from the Web of Science (WoS) and Scopus databases, we identify important authors, institutions, and geographic distributions, highlighting key research areas and emerging themes. The analysis was performed using VOSviewer (v.1.6.20) and RStudio (v.4.1.3) with the Bibliometrix package. Results: Our analysis reveals a steady increase in scientific output between 1999 and 2023, with a notable acceleration in recent years, indicating a growing interest in how AI technologies are accepted in various domains. The research illuminates the central role of technology and AI acceptance models, as demonstrated by thematic and keyword analyses. The study reveals a pronounced focus on the technological facets of AI acceptance, alongside discernible gaps in research linking energy, climate mitigation, and sustainability. Differences in findings underline the characteristics of the WoS and Scopus databases. Conclusions: The findings argue for a diversified research agenda to overcome these identified gaps, fostering a more comprehensive understanding of technology acceptance in the age of AI. This research charts a course for future explorations within this critical interdisciplinary field.

Purpose This study aims to improve mechanical strength and build time of Fused Filament Fabrication (FFF)-printed high-impact polystyrene (HIPS), considering five key controllable FFF process parameters including layer thickness, printing speed, number of contours, raster angle and infill density and their effects on mechanical performance of the HIPS. Design/methodology/approach This study develops a novel multistage material optimisation framework with a mixing experimental and theoretical analysis procedures for FFF of thermoplastic polymers. Artificial neuron network (ANN) is adopted for pattern recognition before the genetic algorithm (GA) and multi-criteria decision-making algorithm are applied for optimisation. Findings Optimised FFF-printing HIPS with rational balance between mechanical properties (tensile strength, flexural strength and impact strength) and build time were achieved. The infill density as the main contributor to the tensile strength and flexural strength, the raster angle as the main contributor to the impact strength while the layer thickness has the highest impact on the build time. ANN-GA method succeeds at achieving a reasonable balance of mechanical strength and build time. Originality/value User-friendly and innovative methodology are devised for developing highly accurate ANN-GA-TOPSIS models for multi-objective optimisation. Optimum settings for three-dimensional-printing HIPS with rational balance between mechanical properties (tensile strength, flexural strength and impact strength) and build time are achieved. The outcome of this research can be useful to achieve high-performance FFF-printed HIPS parts for automotive industries and medical fields with significantly reduced build time.

Neuroimplants are likely major technological breakthroughs of the next decade with the potential for unprecedented social impact. In addition to attractive and miracle-looking possibilities, the major obstacle for the industry is complicated, unpredictable, and unfavorable side effects due to tissue damage, biocompatibility limitations, and foreign body response at the brain-implant interface. Luckily, one major barrier preventing the connection of the neuroimplant to brain cells-the glial scar-has been studied previously for its role in brain trauma. This review highlights pharmacological and tissue engineering avenues that could be readily transferred from the brain trauma area to fast-growing neuroimplant engineering. The opportunities for chondroitinase ABC treatment, stem cells, and hydrogels for the prevention of glial scarring are emphasized. Alternatively, the glial scar may also be viewed not as an obstacle but as a possible regeneration-permissive component of the optimally working brain-neuroimplant interface. Feasible steps in that direction are discussed, including applications for chondroitin sulfate-binding peptides. Finally, the crucial role of new microscopy and data processing techniques for peri-implant glial scar monitoring is highlighted. To that end, we stress the importance of artificial intelligence, including artificial neuronal networks, for the analysis of cell morphology at the brain-neuroimplant interface.

The blood-brain barrier (BBB) is a stringent barrier that restricts the successful brain delivery of polar neurotherapeutics molecules. One such molecule is Zonisamide (ZNS), a hydrophilic centrally acting anti-epileptic drug. This study aims to overcome the poor ZNS BBB permeability using the nose-to-brain (NTB) carbon-based biocompatible nanodiamonds (ND) delivery system to deliver ZNS directly to the brain, bypassing the BBB, thereby enhancing its efficacy and reducing systemic side effects associated with oral ZNS currently available formulation in clinical practice. Intranasal (IN) ND-ZNS formulations were optimised using an Artificial neuronal network (ANN) and assessed for particle size (PS), zeta potential, loading efficiency (%LE), morphology, and in vitro release. The optimum radiolabelled ND-ZNS complex F1 biodistribution in different organs and its pharmacokinetics were compared to oral and IN-free ZNS in mice. Temporal lobe epilepsy (TLE) model in rats was used to compare the anti-epileptic activity of IN ND-ZNS F1 to IN free ZNS by assessing brain activity, epileptic biomarkers such as (brain neuronal specific enolase (NSE), neurofilament light polypeptide (NEFL), and matrix metallopeptidase-9 (MMP-9)), hippocampal histopathology and the modulatory effect on epigenetic miR-199/SIRT-1 and PVT-1/BDNF pathways. Optimized ND-ZNS complex F1 consists of a ZNS:ND ratio of 1:2 and sonicated for 5 min exhibited the least PS (193.7 ± 19.3 nm), adequate %LE (87.1 ± 9.2%) similar to ANN predictions, with a biphasic in vitro release profile of ZNS, beneficial for both acute and chronic epilepsy treatment. The IN delivery of ND-ZNS complex F1 showed preferential higher in vivo brain uptake with minimal systemic exposure linked with higher brain/blood ratio and significant (p ≤ 0.05) overall enhanced pharmacokinetics expressed by Cmax and AUC (0-120min) when compared to oral and IN free ZNS. Moreover, the TLE model confirmed the improved anti-epileptic activity of F1 compared to IN-free ZNS regarding brain activity and hippocampal histopathology, significant suppression of serum NSE, NEFL, MMP-9 levels, miR-199/SIRT-1 pathway, and normalization of PVT-1/BDNF pathway. Therefore, ND used in this study could be a novel, promising carrier to target ZNS directly to the brain via the IN route for effective epilepsy management with less drug dosing and the least systemic side effects.

Metal-organic frameworks (MOFs) have been extensively studied for hydrogen storage due to their unique properties. This paper aims to develop several regression-based machine learning models to predict the hydrogen storage capacity of MOFs, including artificial neuron network (ANN), support vector regression (SVR), random forest (RF), extreme learning machine (ELM), kernel extreme learning machine (KELM), and generalized regression neural network (GRNN). An improved population-based metaheuristic optimization algorithm, the artificial lemming algorithm (ALA), is employed to select the hyperparameters of these machine learning models, enhancing their performance. All developed models are trained and tested using experimental data from multiple studies. The performance of the models is evaluated using various statistical metrics, complemented by regression plots, error analysis, and Taylor graphs to further identify the most effective predictive model. The results show that the ALA-RF model obtains the best performance in predicting hydrogen storage, with optimal values of coefficient of determination (R2), root mean square error (RMSE), Willmott's index (WI), and weighted average percentage error (WAPE) in both training and testing phases (0.9845 and 0.9840, 0.2719 and 0.2828, 0.9961 and 0.9959, and 0.0667 and 0.0714, respectively). Additionally, pressure is identified as the most significant feature for predicting hydrogen storage in MOFs. These findings provide an intelligent solution for the selection of MOFs and optimization of operational conditions in hydrogen storage processes.

Organic dyes are pollutants that threaten aquatic life and human health. These dyes are used in various industries; therefore, recent research focuses on the problem of their removal from wastewater. The aim of this study is to examine the clay/gum arabic nanocomposite (CG/NC) as an adsorbent to adsorb methylene blue (MB) and crystal violet (CV) dyes from synthetic wastewater. The CG/NC was characterized using Fourier transform infrared spectroscopy (FTIR), X-ray diffraction (XRD), scanning electron microscopy (SEM), and Brunaure–Emmett–Teller (BET). The effect of parameters that may influence the efficiency of removing MB and CV dyes was studied (dosage of CG/NC, contact time, pH values, initial concentration, and temperature), and the optimal conditions for removal were determined. Furthermore, an artificial neural network (ANN) model was adopted in this study. The results indicated that the adsorption behavior adhered to the Langmuir model and conformed to pseudo-second-order kinetics. The results also indicated that the removal efficiency reached 99%, and qmax reached 66.7 mg/g and 52.9 mg/g for MB and CV, respectively. Results also proved that CG/NC can be reused up to four times with high efficiency. The ANN models proved effective in predicting the process of the removal, with low mean squared errors (MSE = 1.824 and 1.001) and high correlation coefficients (R2 = 0.945 and 0.952) for the MB and CV dyes, respectively.

Investigating green hydrogen production operated by redundant energy on a solar PV mini-grid through matlab simulation and artificial neural network

Multi-scenario adaptive electronic nose for the detection of environmental odor pollutants.

Forecasting is a process of predicting future events based on past event data. One of the time series models that can be used for forecasting is the Autoregressive Integrated Moving Average (ARIMA). The advantages of ARIMA are in the accuracy and flexibility of its forecasting in representing several different types of time series, but the main limitation is the linear form of the model which causes ARIMA to be unable to capture non-linear patterns in the data. An alternative model for time series modeling is Artificial Neuron Network (ANN). ANN can overcome the weaknesses of ARIMA, but cannot handle linear and nonlinear patterns of the data simultaneously. As an effort to improve forecasting accuracy, Hybrid ARIMA-ANN is carried out by taking advantage of the supremacy of ARIMA and ANN. This study aims to obtain the best model for forecasting the export value of Bengkulu Province, a model generated by the time series data of export values issued by Pulau Baai Harbour from January 2014 to June 2022. The result shows that the best model for predicting the export value of Bengkulu Province is the ARIMA-ANN hybrid model with MAAPE of 0.5289 and MASE of 0.7664.

Abstract PEP07 is a potent and selective brain penetrating oral Chk1 inhibitor. Chk1 is involved in the DNA damage response and cell cycle regulation and helps maintain the integrity of the genome during cell division, especially in response to DNA damage or replication stress. PEP07 showed strong activity in repressing cancer cell growth in vitro and in vivo in different solid cancer models. Over 100 cell lines showed IC50<0.5μM toward PEP07 in vitro, and PEP07 achieved over 90% tumor growth inhibition (TGI) in multiple in vivo models either by monotherapy or combined with standard of care (SoC) treatments. With the property of blood-brain barrier (BBB) penetration, PEP07 was able to inhibit brain cancer in orthotopic models when combined with SoC treatments. In addition, in vitro cell proliferation and transcriptome data were used to train artificial neuron network (ANN) models to identify cancer cells that are sensitive to PEP07. Patient-derived tumor cells (PDCs) were used to validate the prediction of sensitive cells by ANN models. PEP07 is currently being evaluated in clinical studies for both hematologic and solid cancers. PEP07-102 (NCT05983523), a Phase 1, open-label, multi-center PK/PD and dose-escalation study employs an accelerated titration design combined with a traditional 3+3 approach assessing PEP07 as monotherapy in patients with advanced or metastatic solid tumors. Citation Format: Chieh-Fang Cheng, Hui-Ling Chen, Feng_Yu Lee, Cheng-Hao Liu, Chien-Feng Li, Hong-Ren Wang. Preclinical and clinical studies of PEP07, a novel brain penetrating Chk1 inhibitor, on solid tumor treatments [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 5638.

Organic dyes are pollutants that threaten aquatic life and human health. These dyes are used in various industries; therefore, recent research focuses on the problem of their removal from wastewater. This aim of this study is to examine the clay/Gum Arabic nanocomposite (CG/NC) as an adsorbent to adsorb methylene blue (MB) and crystal violet (CV) dyes from synthetic wastewater. The CG/NC was characterized using Fourier Transform Infrared spectroscopy (FTIR), X-ray diffraction (XRD), Scanning Electron Microscopy (SEM), and Brunaure-Emmett-Teller (BET). The effect of parameters that may influence the efficiency of removing MB and CV dyes was studied: (dosage of CG/NC, contact time, pH values, initial concentration, and temperature), and the optimal conditions for removal were determined. Furthermore, an Artificial Neural Network (ANN) model was adopted in this study. The results designated that the adsorption behavior adhered to the Langmuir model and conformed to pseudo-second-order kinetics. The results also indicated that the removal efficiency reached 99%, and qmax reached 66.7 mg/g and 52.9 mg/g for MB and CV, respectively. Results also proved that CG/NC can be reused up to four times with high efficiency. The ANN models have proven effective in predicting the process of the removal, with the low Mean Square Error (MSE = 1.824 and 1.001) and high Correlation Coefficient (R2 = 0.945 and 0.952) for the MB and CV dyes, respectively.

Purpose The purpose of the study concludes detecting address resolution protocol (ARP) Spoofing attack in software-defined network (SDN) architecture meanwhile using different machine learning models to evaluate their effectiveness. Design/methodology/approach This research originates from building a SDN topology and researching into its changes under ARP Spoofing attack. Based on that, the authors propose four features which show obvious abnormalities in network under attack stage. The data collected from SDN controller is used to build a data set, which is then put into different machine learning models, which are: Artificial Neuron network (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), CNN-LSTM and Gated Recurrent Unit (GRU). Findings After applying this proposal in simulation and experimental environments, they achieve impressive performance metrics. In simulation environment, the GRU model stands out with the highest accuracy of 98.94%. In real environments, the CNN-LSTM model leads with a recall of 98.38% and an F1-Score of 98.57%, while the LSTM model has the highest precision (98.8%). The GRU model also performs strongly in real scenarios with a high accuracy of 97.65%. ANN, despite its reliability, struggles with lower recall and F1-Score across both environments. Originality/value This analysis emphasizes the importance of the proposed features when applied to different models and their high potential to conduct in practical environment.

Can large language models be trusted? Not likely. Artificial neuron networks offer a much better option.

Abstract We establish the necessary framework for inputting any kind of mesostructure into multi-scale models for granular materials. Keeping intact the general statistical homogenization scheme, we propose a strategy to compute the mechanical response of the mesostructures directly with discrete element simulations of a few grains or thanks to surrogate models relying on artificial neuron networks (ANN). By applying machine learning techniques at the mesoscale (instead of the Representative Elementary Volume scale), it is indeed possible to generate the necessary learning database from discrete element simulations at a relatively cheap computational cost. We apply the meso-DEM and meso-ANN strategies to the H-model (one particular micromechanical model), and we show that they can replicate the original analytical expression of the model on biaxial tests. This work paves the way for using more complex mesostructures to account for instance for gap-graded materials.

Artificial Intelligence (AI) has witnessed significant growth in the field of medicine, leveraging machine learning, artificial neuron networks, and large language models. These technologies are effective in disease diagnosis, education, and prevention, while raising ethical concerns and potential challenges. However, their utility in sexual medicine remains relatively unexplored. We aim to provide a comprehensive summary of the status of AI in the field of sexual medicine. A comprehensive search was conducted using MeSH keywords, including "artificial intelligence," "sexual medicine," "sexual health," and "machine learning." Two investigators screened articles for eligibility within the PubMed and MEDLINE databases, with conflicts resolved by a third reviewer. Articles in English language that reported on AI in sexual medicine and health were included. A total of 69 full-text articles were systematically analyzed based on predefined inclusion criteria. Data extraction included information on article characteristics, study design, assessment methods, and outcomes. The initial search yielded 905 articles relevant to AI in sexual medicine. Upon assessing the full texts of 121 articles for eligibility, 52 studies unrelated to AI in sexual health were excluded, resulting in 69 articles for systematic review. The analysis revealed AI's accuracy in preventing, diagnosing, and decision-making in sexually transmitted diseases. AI also demonstrated the ability to diagnose and offer precise treatment plans for male and female sexual dysfunction and infertility, accurately predict sex from bone and teeth imaging, and correctly predict and diagnose sexual orientation and relationship issues. AI emerged as a promising modality with significant implications for the future of sexual medicine. Further research is essential to unlock the potential of AI in sexual medicine. AI presents advantages such as accessibility, user-friendliness, confidentiality, and a preferred source of sexual health information. However, it still lags human healthcare providers in terms of compassion and clinical expertise.

Trade fuels economic development in interwoven international wood markets, while economic shocks and structural changes jolt market response behavior. In this context, both accurate predictions and forecasts of trade flows and a deep understanding of their influencing factors are essential for policymakers and stakeholders to enhance economic planning and decision-making affecting trade policies. A popular method for analyzing bilateral trade flows is the deterministic Gravity model of trade due to its intuitive design and effectiveness. However, data-driven machine learning methods such as artificial neural networks (ANN) could enhance the accuracy of deterministic modeling approaches through their complex and potentially nonlinear nature. To the best of our knowledge, no study exists that uses an ANN approach to assess bilateral trade for different wood-based products was. Therefore, it remains unclear whether ANN is an appropriate method to predict and forecast trade flows in forest product markets or if Gravity models of trade might yield better results. This study compares the ability of Gravity models and feedforward neuronal networks (FFNN) to predict existing and forecast future bilateral trade flows of four main product categories in international wood product markets. Our findings highlight that it is essential to consider the purpose of the analysis alongside the specific product group under investigation. The FFNN approach outperforms Gravity models for predicting past and present trade flows, delivering more accurate predictions across all product categories. Looking at the accuracy of forecast, we see that the superiority of FFNNs is present but decreases as the forecast horizon increases. • Machine learning has the potential to increase accuracy in predicting wood market trade. • Feedforward neural networks accurately replicate global trade flows from 2003 to 2020. • Gravity models provide stable forecasts of trade flows up to 17 years into the future. • Feedforward neural networks can be used to fill gaps in trade data.

This research studies the properties of two coupled Hodgkin-Huxley neurons. The influence of coupling strength as well as individual parameters of the neurons (i.e., initial conditions and external current values) have been studied. A Pearson correlation coefficient is used to estimate the synchrony degree between the neurons. It was found that the two neurons can be synchronized fairly easily in different regimes based on the combination of parameters: for some cases, the neurons are synchronous in a self-oscillating regime, but for other combinations, a single-spike regime becomes prevalent. It was also discovered that the synchronization regime can be controlled both by the external current value of each neuron and the coupling strength value. The obtained results can be profitable for future research of complex networks of artificial neurons.

Artificial neurons with bio-inspired firing patterns have the potential to significantly improve the performance of neural network computing. The most significant component of an artificial neuron circuit is a large amount of energy consumption. Recent literature has proposed memristors as a promising option for synaptic implementation. In contrast, implementing memristive circuitry through neuron hardware presents significant challenges and is a relevant research topic. This paper describes an efficient circuit-level mixed CMOS memristor artificial neuron network with a memristor synapse model. From this perspective, the paper describes the design of artificial neurons in standard CMOS technology with low power utilization. The neuron circuit response is a modified version of the Morris-Lecar theoretical model. The suggested circuit employs memristor-based artificial neurons with Dual Transistor and Dual Memristor (DTDM) synapse circuit. The proposed neuron network produces a high spiking frequency and low power consumption. According to our research, a memristor-based Morris Lecar (ML) neuron with a DTDM synapse circuit consumes 12.55 pW of power, the spiking frequency is 22.72 kHz, and 2.13 fJ of energy per spike. The simulations were carried out using the Spectre tool with 45 nm CMOS technology.

This article presents a dynamic modeling and control strategy for a non-ideal buck DC–DC (direct current) converter using a PID neural controller. Unlike conventional approaches that rely on fixed-gain PID (Proportional Integral Derivative) controllers, the proposed method dynamically updates the controller’s gain constants to enhance robustness against parametric variations caused by tolerances, wear, or other practical discrepancies. To ensure the neural network’s weight convergence, a Lyapunov-based algorithm is employed, enabling optimal weight adjustments in conjunction with the PID control strategy. The study validates the ANN-based (Artificial Neuronal Network) PID controller under diverse dynamic conditions (input voltage variations, disturbances in voltage sensors, etc.) through numerical simulations, incorporating theoretical derivations and circuit dynamics modeling. The main contribution of this work lies in demonstrating the convergence of the system under the proposed control law, substantiated by Lyapunov stability analysis and comparative simulations against traditional methods in the literature.