Artificial Model Research Articles

Harmonic Interference Prediction of Power Amplifiers by Artificial Neural Network Behavioral Model

Harmonic Interference Prediction of Power Amplifiers by Artificial Neural Network Behavioral Model

Financial Revolution through Agent-based Artificial Simulation Computational Models for Predicting Market Behavior

The fundamental theory of the Efficient market hypothesis (EMH), which states that market participants are rational, has received a lot of criticism. The complexity of behavior in the capital market is still a black box, especially when psychological biases influence aggressively on decision-making amid uncertainty. Experimental research on finance and capital markets in the form of AI using machine learning seeks to predict the results of more complex interactions. This multidisciplinary approach offers efforts to explain social phenomena from the micro level to macro descriptions which are built artificially through the computational world. The processing modeling approach is preferred because it includes the complexes that emerge from the behavior and interactions of individuals in the real world. Agent Based Model (ABM) is an AI approach in the form of computational simulation that performs a bottom-up approach by combining irrational–rational agent interactions through networks in microenvironments. Using the ABM approach through Netlogo computing, this study proves that AI can be used to analyze investor behavior in the capital market. Keywords: Agent Based Model, artificial intelligence, investor behavior

Automated line scan profilometer based on the surface recognition method

Existing high-precision measurement devices face numerous challenges when dealing with complex surfaces, including high manual involvement, low measurement efficiency, and high costs. It is even more difficult to obtain complete surface data, particularly when confronted with unknown surfaces. This paper combines a fringe projection sensor with a high-precision line-structured light sensor to construct a line scan profiler. It proposes a surface recognition measurement method to overcome these challenges. This method fully leverages the fringe projection sensor's wide-field advantage to identify the object's surface shape and pose quickly. Subsequently, through the point cloud extraction and path planning algorithms proposed in this paper, efficient and complete line scan measurement paths are automatically generated, thus achieving the automation of the measurement process. Experimental measurements of aspherical lenses, freeform reflective mirrors, and artificial knee joint models validate the advantages of this method over existing methods in terms of measurement efficiency, automation capability, and applicability.

Modelling bridge deterioration using long short-term memory neural networks: a deep learning-based approach

PurposeBridge deterioration is a critical risk to public safety, which mandates regular inspection and maintenance to ensure sustainable transport services. Many models have been developed to aid in understanding deterioration patterns and in planning maintenance actions and fund allocation. This study aims at developing a deep-learning model to predict the deterioration of concrete bridge decks.Design/methodology/approachThree long short-term memory (LSTM) models are formulated to predict the condition rating of bridge decks, namely vanilla LSTM (vLSTM), stacked LSTM (sLSTM), and convolutional neural networks combined with LSTM (CNN-LSTM). The models are developed by utilising the National Bridge Inventory (NBI) datasets spanning from 2001 to 2019 to predict the deck condition ratings in 2021.FindingsResults reveal that all three models have accuracies of 90% and above, with mean squared errors (MSE) between 0.81 and 0.103. Moreover, CNN-LSTM has the best performance, achieving an accuracy of 93%, coefficient of correlation of 0.91, R2 value of 0.83, and MSE of 0.081.Research limitations/implicationsThe study used the NBI bridge inventory databases to develop the bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.Originality/valueThis study provides a detailed and extensive data cleansing process to address the shortcomings in the NBI database. This research presents a framework for implementing artificial intelligence-based models to enhance maintenance planning and a guideline for utilising the NBI or other bridge inventory databases to develop accurate bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.

The Influence of Disparities on Prostate Cancer at Diagnosis in the Charlotte Metropolitan Area.

Prostate cancer (PCa) is the most diagnosed noncutaneous malignancy and second leading-cause of cancer death in men, yet screening is decreasing. As PCa screening has become controversial, socioeconomic disparities in PCa diagnosis and outcomes widen. This study was designed to determine the current disparities influencing PCa diagnosis in Charlotte, NC. The Levine Cancer Institute database was queried for patients with PCa, living in metropolitan Charlotte. Socioeconomic status (SES) was determined by the Area Deprivation Index (ADI); higher ADI indicated lower SES. Patients were compared by their National Comprehensive Cancer Network risk stratification. Artificial intelligence predictive models were trained and heatmaps were created, demonstrating the geographic and socioeconomic disparities in late-stage PCa. Of the 802 patients assessed, 202 (25.2%) with high-risk PCa at diagnosis were compared with 198 (24.7%) with low-risk PCa. High-risk PCa patients were older (69.8±9.0 vs. 64.0±7.9 years; p<0.001) with lower SES (ADI block: 98.4±20.9 vs. 92.1±19.8; p=0.004) and more commonly African-American (White: 66.2% vs. 78.3%, African-American: 31.3% vs. 20.7%; p=0.009). On regression, ADI block was an independent predictor (odds ratio [OR]=1.013, 95% confidence interval [CI] 1.002-1.024; p=0.024) of high-risk PCa at diagnosis, whereas race was not (OR=1.312, 95% CI 0.782-2.201; p=0.848). A separate regression demonstrated higher ADI (OR=1.016, 95% CI 1.004-1.027; p=0.006) and older age (OR=1.083, 95% CI 1.054-1.114; p<0.001) were independent predictors for high-risk PCa. Findings, depicted in heatmaps, demonstrated the geographic locations where men with PCa were predicted to have high-risk disease based on their age and SES. Socioeconomic status was more closely associated with high-risk PCa at diagnosis than race. Although, of any variable, age was most predictive. The heatmaps identified areas that would benefit from increased awareness, education, and screening to facilitate an earlier PCa diagnosis.

Artificial urinary bladder model.

Technological advancements in the medical field are often slow and expensive, sometimes due to complexities associated with pre-clinical testing of medical devices and implants. There is therefore a growing need for new test beds that can mimic more closely the in vivo environment of physiological systems. In the present study, a novel bladder model was designed and fabricated with the aim of providing a pre-clinical testing platform for urological stents and catheters. The model is collapsible, has a Young's modulus that is comparable to a biological bladder, and can be actuated on-demand to enable voiding. Moreover, the developed fabrication technique provides versatility to adjust the model's shape, size, and thickness, through a rapid and relatively inexpensive process. When compared to a biological bladder, there is a significant difference in compliance; however, the model exhibits cystometry profiles during priming and voiding that are qualitatively comparable to a biological bladder. The developed bladder model has therefore potential for future usage in urological device testing; however, improvements are required to more closely replicate the architecture and relevant flow metrics of a physiological bladder.

An artificial intelligence-based nerve recognition model is useful as surgical support technology and as an educational tool in laparoscopic and robot-assisted rectal cancer surgery

BackgroundArtificial intelligence (AI) has the potential to enhance surgical practice by predicting anatomical structures within the surgical field, thereby supporting surgeons' experiences and cognitive skills. Preserving and utilising nerves as critical guiding structures is paramount in rectal cancer surgery. Hence, we developed a deep learning model based on U-Net to automatically segment nerves.MethodsThe model performance was evaluated using 60 randomly selected frames, and the Dice and Intersection over Union (IoU) scores were quantitatively assessed by comparing them with ground truth data. Additionally, a questionnaire was administered to five colorectal surgeons to gauge the extent of underdetection, overdetection, and the practical utility of the model in rectal cancer surgery. Furthermore, we conducted an educational assessment of non-colorectal surgeons, trainees, physicians, and medical students. We evaluated their ability to recognise nerves in mesorectal dissection scenes, scored them on a 12-point scale, and examined the score changes before and after exposure to the AI analysis videos.ResultsThe mean Dice and IoU scores for the 60 test frames were 0.442 (range 0.0465–0.639) and 0.292 (range 0.0238–0.469), respectively. The colorectal surgeons revealed an under-detection score of 0.80 (± 0.47), an over-detection score of 0.58 (± 0.41), and a usefulness evaluation score of 3.38 (± 0.43). The nerve recognition scores of non-colorectal surgeons, rotating residents, and medical students significantly improved by simply watching the AI nerve recognition videos for 1 min. Notably, medical students showed a more substantial increase in nerve recognition scores when exposed to AI nerve analysis videos than when exposed to traditional lectures on nerves.ConclusionsIn laparoscopic and robot-assisted rectal cancer surgeries, the AI-based nerve recognition model achieved satisfactory recognition levels for expert surgeons and demonstrated effectiveness in educating junior surgeons and medical students on nerve recognition.

Fully Automated Artificial Intelligence-Based Frailty Model Predicts Heart Failure and Death After Transcatheter Aortic Valve Replacement

Fully Automated Artificial Intelligence-Based Frailty Model Predicts Heart Failure and Death After Transcatheter Aortic Valve Replacement

Skin cancer classification based on an optimized convolutional neural network and multicriteria decision-making

Skin cancer is a type of cancer disease in which abnormal alterations in skin characteristics can be detected. It can be treated if it is detected early. Many artificial intelligence-based models have been developed for skin cancer detection and classification. Considering the development of numerous models according to various scenarios and selecting the optimum model was rarely considered in previous works. This study aimed to develop various models for skin cancer classification and select the optimum model. Convolutional neural networks (CNNs) in the form of AlexNet, Inception V3, MobileNet V2, and ResNet 50 were used for feature extraction. Feature reduction was carried out using two algorithms of the grey wolf optimizer (GWO) in addition to using the original features. Skin cancer images were classified into four classes based on six machine learning (ML) classifiers. As a result, 51 models were developed with different combinations of CNN algorithms, without GWO algorithms, with two GWO algorithms, and with six ML classifiers. To select the optimum model with the best results, the multicriteria decision-making approach was utilized to rank the alternatives by perimeter similarity (RAPS). Model training and testing were conducted using the International Skin Imaging Collaboration (ISIC) 2017 dataset. Based on nine evaluation metrics and according to the RAPS method, the AlexNet algorithm with a classical GWO yielded the optimum model, achieving a classification accuracy of 94.5%. This work presents the first study on benchmarking skin cancer classification with many models. Feature reduction not only reduces the time spent on training but also improves classification accuracy. The RAPS method has proven its robustness in the problem of selecting the best model for skin cancer classification.

Hydrogen Bonding-Driven Self-Coacervation of Nonionic Homopolymers for Stimuli-Triggered Therapeutic Release.

Inspired by the unique functionalities of biomolecular membraneless organelles (MLOs) formed via liquid-liquid phase separation (LLPS) of intrinsically disordered proteins (IDPs) and nucleic acids, a great deal of effort has been devoted to devising phase-separated artificial subcellular dynamic compartments. These endeavors aim to unravel the molecular mechanism underlying the formation and intracellular delivery of susceptible macromolecular therapeutics. We report herein pyroglutamic acid (PGA)-based well-defined homopolymers featuring stimuli-tunable reversible self-coacervation ability. The polymer exhibits an upper critical solution temperature (UCST) transition in aqueous solutions and has the propensity to undergo cooling-induced LLPS, producing micrometer-sized liquid droplets. This phase separation phenomenon could be modulated by various factors, including polymer concentration, chain length, solution pH, and types and concentrations of different additives. These micrometer droplets are thermally reversible and encapsulate a wide variety of cargoes, including small hydrophobic fluorescent molecules, hydrophilic anticancer drugs, and fluorophore-labeled macromolecular proteins (bovine serum albumin and lysozyme). The payloads were released by exploiting the thermo/pH-mediated disassembly behavior of the coacervates, preserving the bioactivity of the sensitive therapeutics. This environmentally responsive, simple yet versatile artificial MLO model system will provide insights into the biomolecular nonionic condensates and pave the way for the de novo design of dynamic biomolecule depots.

The promise and challenges of Artificial Intelligence-Large Language Models (AI-LLMs) in obstetric and gynecology

HIGHLIGHTS 1. The article highlights how Artificial Intelligence with Large Language Models (AI-LLMs) greatly improves diagnosis and treatment personalization in obstetrics &amp; gynecology, and also enhances medical education through interactive simulations and up-to-date learning materials.2. The article also discusses the ethical issues linked to AI, emphasizing the need for cooperation among different stakeholders to use AI responsibly in medicine, focusing on protecting data privacy and minimizing reliance on technology. ABSTRACT The introduction of Artificial Intelligence through Large Language Models (AI-LLM) into medicine holds great promise for improving patient care and medical education, especially in obstetrics and gynecology. AI-LLM can significantly improve diagnostic accuracy and treatment efficiency by utilizing large medical databases, which is especially useful for dealing with rare diseases that are difficult to document or understand by human practitioners alone. In addition, AI-LLM can provide informed patient care recommendations by analyzing large amounts of data and providing insights based on unique patient profiles, with the added benefit of being accessible 24/7 via the internet. This constant availability ensures that patients receive prompt information and assistance as needed. In the field of education, AI-LLMs enhance the learning experience by incorporating interactive simulations into the curriculum, improving medical students' and professionals' practical knowledge. They also ensure that educational materials are always up-to-date reflecting the most recent research and worldwide medical standards. This access latest information from global resources helps to bridge the educational gap, making advanced knowledge more accessible to learners regardless of their geographic location. However, the introduction of AI-LLMs is not without challenges. Ethical issues, such as data privacy and the risk of overreliance on technology, must be addressed. Effective management of these concerns necessitates collaboration among medical professionals, technological experts, academics, hospital committees, and representatives of patients. This multidisciplinary teamwork is vital for upholding ethical norms and preserving patient dignity and respect. AI-LLMs can considerably improve both patient care and medical education in obstetrics and gynecology provided they are appropriately balanced with innovation and ethics.

Artificial Intelligence Models for the Detection of Microsatellite Instability from Whole-Slide Imaging of Colorectal Cancer.

With the advent of whole-slide imaging (WSI), a technology that can digitally scan whole slides in high resolution, pathology is undergoing a digital revolution. Detecting microsatellite instability (MSI) in colorectal cancer is crucial for proper treatment, as it identifies patients responsible for immunotherapy. Even though universal testing for MSI is recommended, particularly in patients affected by colorectal cancer (CRC), many patients remain untested, and they reside mainly in low-income countries. A critical need exists for accessible, low-cost tools to perform MSI pre-screening. Here, the potential predictive role of the most relevant artificial intelligence-driven models in predicting microsatellite instability directly from histology alone is discussed, focusing on CRC. The role of deep learning (DL) models in identifying the MSI status is here analyzed in the most relevant studies reporting the development of algorithms trained to this end. The most important performance and the most relevant deficiencies are discussed for every AI method. The models proposed for algorithm sharing among multiple research and clinical centers, including federal learning (FL) and swarm learning (SL), are reported. According to all the studies reported here, AI models are valuable tools for predicting MSI status on WSI alone in CRC. The use of digitized H&E-stained sections and a trained algorithm allow the extraction of relevant molecular information, such as MSI status, in a short time and at a low cost. The possible advantages related to introducing DL methods in routine surgical pathology are underlined here, and the acceleration of the digital transformation of pathology departments and services is recommended.

Reinforced colour preference of parasitoid wasps in the presence of floral scent: a case study of a cross-modal effect

We examined the possibility of a cross-modal effect in naïve Cotesia vestalis, a parasitoid wasp of diamondback moth larvae, by using artificial flower models of four colours (blue, green, yellow, and red) in the absence or presence of floral scent collected from Brassica rapa inflorescences. In a four-choice test, regardless of the floral scent, non-starved female wasps visited green and yellow models significantly more often than blue and red ones, although no significant difference was observed between visits to the green and yellow models. They seldom visited blue and red models. When starved, the wasps became even more particular, visiting yellow significantly more frequently than green models, irrespective of the presence of the floral scent, indicating that they preferred to use yellow visual cues in their food search. Furthermore, a factorial analysis of variance revealed a significant effect of the interaction between model colour and floral scent on the wasps’ visits to flower models. The floral scent induced starved and non-starved wasps to visit yellow and green models about twice as often as without the scent. A cross-modal effect of olfactory perception on the use of chromatic information by wasps may allow them to search efficiently for food sources.

CT-based artificial intelligence prediction model for ocular motility score of thyroid eye disease.

Thyroid eye disease (TED) is the most common orbital disease in adults. Ocular motility restriction is the primary complaint of patients, while its evaluation is quite difficult. The present study aimed to introduce an artificial intelligence (AI) model based on orbital computed tomography (CT) images for ocular motility score. A total of 410 sets of CT images and clinical data were obtained from the hospital. To build a triple classification predictive model for ocular motility score, multiple deep learning models were employed to extract features of images and clinical data. Subgroup analyses based on pertinent clinical features were performed to test the efficacy of models. The ResNet-34 network outperformed Alex-Net and VGG16-Net in prediction of ocular motility score, with the optimal accuracy (ACC) of 0.907, 0.870, and 0.890, respectively. Subgroup analyses indicated no significant difference in ACC between active or inactive phase, functional visual field diplopia or peripheral visual field diplopia (p > 0.05). However, in the gender subgroup, the prediction model performed more accurately in female patients than males (p = 0.02). In conclusion, the AI model based on CT images and clinical data successfully realized automatic scoring of ocular motility in TED patients. This approach potentially enhanced the efficiency and accuracy of ocular motility evaluation, thus facilitating clinical application.

How the Kondo effect stabilises delta-phase plutonium

ABSTRACT My purpose in this paper is to find the underlying electronic cause of the observed thermodynamic stabilisation of δ-phase plutonium. I present a simple model demonstrating that the valence fluctuations found in δ-phase are essential for stabilising this phase. I make two explicit comparisons of the temperature dependencies of the available heat capacity data: one of α-phase Pu versus δ-phase Pu, and the other of α-Pu versus an artificial δ-phase model which includes only lattice vibrations and a free-electron term. These comparisons strongly suggest that delta phase is stabilised – both at high and low temperature – by the entropy of the valence fluctuations which are present in this phase.

Syringaresinol Attenuates α-Melanocyte-Stimulating Hormone-Induced Reactive Oxygen Species Generation and Melanogenesis.

Ginseng has been utilized for centuries in both the medicinal and cosmetic realms. Recent studies have actively investigated the biological activity of ginseng berry and its constituents. (+)-Syringaresinol [(+)-SYR], an active component of ginseng berry, has been demonstrated to have beneficial effects on the skin, but its potential impact on skin pigmentation has not been fully explored. Here, the antioxidant and anti-pigmentary activity of (+)-SYR were evaluated in B16F10 murine melanoma cells and in an artificial human pigmented skin model, Melanoderm™. A real-time PCR, Western blotting, immunofluorescence staining, and histochemistry staining were conducted to confirm the effects of (+)-SYR on pigmentation. (+)-SYR reduced melanogenesis and dendrite elongation in α-melanocyte-stimulating hormone (α-MSH)-primed B16F10 cells with low cytotoxicity. (+)-SYR suppressed the expression of melanogenic genes, namely tyrosinase (TYR), tyrosinase-related protein 1 (TRP-1), and tyrosinase-related protein 2 (TRP-2). Notably, (+)-SYR attenuated α-MSH-induced cytosolic and mitochondrial reactive oxygen species (ROS) generation, which was attributable at least in part to the suppression of NADPH oxidase-4 (NOX 4) expression. Finally, the brightening activities of (+)-SYR were verified using Melanoderm™, underscoring the potential of ginseng berry and (+)-SYR as functional ingredients in skin-brightening cosmetics.

Artificial Neural Network-aided Mathematical Model for Predicting Soil Stress-strain Hysteresis Loop Evolution

This study presents a novel approach to forecasting the evolution of hysteresis stress-strain response of different types of soils under repeated loading-unloading cycles. The forecasting is made solely from the knowledge of soil properties and loading parameters. Our approach combines mathematical modeling, regression analysis, and Deep Neural Networks (DNNs) to overcome the limitations of traditional DNN training. As a novelty, we propose a hysteresis loop evolution equation and design a family of DNNs to determine the parameters of this equation. Knowing the nature of the phenomenon, we can impose certain solution types and narrow the range of values, enabling the use of a very simple and efficient DNN model. The experimental data used to develop and test the model was obtained through Torsional Shear (TS) tests on soil samples. The model demonstrated high accuracy, with an average R² value of 0.9788 for testing and 0.9944 for training.

A fused grey wolf and artificial bee colony model for imbalanced data classification problems

A fused grey wolf and artificial bee colony model for imbalanced data classification problems

Artificial neural network-assisted theoretical model to predict the viscoelastic–plastic tensile behavior of polyamide-6 multi-ply yarns

Artificial neural network-assisted theoretical model to predict the viscoelastic–plastic tensile behavior of polyamide-6 multi-ply yarns

ViT-PSO-SVM: Cervical Cancer Predication Based on Integrating Vision Transformer with Particle Swarm Optimization and Support Vector Machine.

Cervical cancer (CCa) is the fourth most prevalent and common cancer affecting women worldwide, with increasing incidence and mortality rates. Hence, early detection of CCa plays a crucial role in improving outcomes. Non-invasive imaging procedures with good diagnostic performance are desirable and have the potential to lessen the degree of intervention associated with the gold standard, biopsy. Recently, artificial intelligence-based diagnostic models such as Vision Transformers (ViT) have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). This paper studies the effect of applying a ViT to predict CCa using different image benchmark datasets. A newly developed approach (ViT-PSO-SVM) was presented for boosting the results of the ViT based on integrating the ViT with particle swarm optimization (PSO), and support vector machine (SVM). First, the proposed framework extracts features from the Vision Transformer. Then, PSO is used to reduce the complexity of extracted features and optimize feature representation. Finally, a softmax classification layer is replaced with an SVM classification model to precisely predict CCa. The models are evaluated using two benchmark cervical cell image datasets, namely SipakMed and Herlev, with different classification scenarios: two, three, and five classes. The proposed approach achieved 99.112% accuracy and 99.113% F1-score for SipakMed with two classes and achieved 97.778% accuracy and 97.805% F1-score for Herlev with two classes outperforming other Vision Transformers, CNN models, and pre-trained models. Finally, GradCAM is used as an explainable artificial intelligence (XAI) tool to visualize and understand the regions of a given image that are important for a model's prediction. The obtained experimental results demonstrate the feasibility and efficacy of the developed ViT-PSO-SVM approach and hold the promise of providing a robust, reliable, accurate, and non-invasive diagnostic tool that will lead to improved healthcare outcomes worldwide.