Artificial Intelligence Networks Research Articles

"Heterogeneity and Criticality in Neural Networks: A Computational Model of the Griffiths Phase"

This article presents a computational exploration into the dynamics of neural networks, focusing on the manifestation of heterogeneity and critical behavior akin to the Griffiths phase observed in condensed matter physics. Drawing inspiration from the rich tapestry of neural activities within the human neocortex, we develop a simplified model to investigate how networks with diverse propensities for critical behavior can exhibit complex, adaptive functionalities. Utilizing an Erdős–Rényi random graph as the foundation, we introduce a proportion of nodes designated as "critical," possessing a higher likelihood of activation, to simulate the nuanced interplay between different regions of a theoretical brain network. Through iterative simulations, we examine the activation patterns over time, paying close attention to the influence of critical nodes on the overall network dynamics. The model integrates fundamental principles from network theory and neuroscience, offering insights into the potential mechanisms underlying the brain's remarkable ability to process information efficiently, adapt to new stimuli, and maintain robustness in the face of perturbations. Our findings highlight the importance of heterogeneity and criticality in enhancing the computational capabilities of neural networks, providing a conceptual bridge between theoretical physics and cognitive neuroscience. This work contributes to a deeper understanding of the brain's operational principles and opens avenues for further research into the applications of criticality and Griffiths phases in artificial intelligence and neural network design.

Bioenergy relations with agriculture, forestry and other land uses: Highlighting the specific contributions of artificial intelligence and co-citation networks

The concerns with the environment and sustainability have promoted options for energy sources that mitigate the footprint of human life. The use of biomass from agriculture, forestry and other land uses (AFOLU) has enormous potential for the production of bioenergy as a renewable source of energy. In this context, this research aims to analyse the interrelationships between bioenergy and agriculture, forestry and other land uses, highlighting the contributions of the digital transition for these dimensions. To achieve these objectives, a bibliometric analysis through co-citation links (and items related to cited authors, references and sources) was carried out for the dimensions associated with the bioenergy and the AFOLU and after a specific literature survey was performed for the contributions from the digital transition for these frameworks. With this study, top authors, references and sources were identified for the topics assessed and it was highlighted the importance of digital transitions for more efficient bioenergy use and production in the worldwide contexts.

Construction and validation of a joint diagnosis model based on random forest and artificial intelligence network for hepatitis B-related hepatocellular carcinoma.

Hepatitis B virus (HBV) is the dominant pathogenic factor of hepatocellular carcinoma (HCC) in Asia and Africa. Early identification and clinical diagnosis are crucial for HBV-related HCC. Random forest (RF) and artificial neural network (ANN) were an innovative and highly effective supervised machine learning (ML) algorithm for the early diagnosis and screening of HBV-related HCC. This study aims to identify significant biomarkers and develop a novel genetic model for the efficient diagnosis of HBV-related HCC. Gene Expression Omnibus (GEO) Series (GSE)19665, GSE55092, and GSE121248 were used to identify significant differentially expressed genes (DEGs). The enrichment analysis was performed on Metascape online tool. The RF algorithm and ANN were used to select the potential predictive gene panels and construct an HBV-related HCC diagnostic model. Subsequently, GSE17548, GSE104310, GSE44074, and GSE136247 were used to test the accuracy of the ANN model. Finally, the CIBERSORT algorithm was used to assess the abundance of immune infiltrates in all samples. First, 116 genes were identified as DEGs, and the DEGs were particularly enriched in cellular hormone metabolic process, monocarboxylic acid metabolic process, NABA extracellular matrix (ECM) AFFILIATED steroid metabolic process and metabolism of bile acid and bile salt. DNA topoisomerase II alpha (TOP2A), C-type lectin domain family 1 member B (CLEC1B), BUB1 mitotic checkpoint serine/threonine kinase B (BUB1B), ficolin 2 (FCN2), C-X-C motif chemokine ligand 14 (CXCL14), cyclase associated actin cytoskeleton regulatory protein 2 (CAP2), ficolin 3 (FCN3), kynurenine 3-monooxygenase (KMO) and cadherin related family member 2 (CDHR2) were available to develop an HBV-related HCC diagnostic model. After validation, the diagnostic model showed high sensitivity (88.5%, 90%, 88.5%, 76.5%) and specificity (100%, 81.8%, 89.5%, 72.2%), and the areas under the receiver operating characteristic (ROC) curves showed excellent efficiency (1, 0.927, 0.921, 0.833). Finally, the percentage of infiltrating immune cell types [B cells naïve, B cells memory, plasma cells, T cells CD8, T cells CD4 memory resting, T cells regulatory (Tregs), T cells gamma delta, natural killer (NK) cells resting, NK cells activated, Macrophages M0, Dendritic cells activated, Mast cells activated] for hepatitis B-related HCC were significantly different from that of non-cancerous liver tissue with HBV. A novel early diagnostic model of HBV-related HCC was established, and the model showed better efficiency in distinguishing HBV-related HCC from other non-cancerous with HBV individuals.

Reef fish identification through image records using artificial intelligence and convolutional neural network system

Coral reef environments show great diversity and abundance of species that represent important biological resources for obtaining food and medicines, in addition to acting as bioindicators of the quality of reef environments, serving as a parameter to diagnose environmental impacts and, simultaneously, to evaluate the availability and use of fishing stocks and biological resources in such environments. Monitoring such ecosystems arises from the urgent need to better understand the natural geographic and environmental variability of these systems, as well as their main drivers of change, to inform and promote more effective management of such environments. With the growing need to monitor communities of reef organisms, particularly fish, the creation of a digital analysis method would make a great contribution to the studies of reef fish. To fill this knowledge gap, our work evaluates the possibility of using an artificial intelligence mechanism using convolutional neural networks (CNN) to identify and count reef fish in image records, to optimize digital analysis of videos and/or photos in reef environments for fish ecology studies. The accuracy of the CNN identification method was effective, although it still has challenges to improve, such as: the need for a preliminary survey of reef fish species existing in the target area to be monitored, with the capture of good resolution images in different positions space for each species; production of an image bank with a large number of diverse images for each species (minimum of 200 images per species) and; To detect fish in videos, fast computers with a dedicated GPU card are needed, especially if the videos are high or ultra-resolution and have a large number of fps.

Size-dependent nonlinear vibrations of functionally graded origami-enabled auxetic metamaterial plate: Application of artificial intelligence networks for solving the engineering problem

Auxetic metamaterials are a kind of advanced materials that have distinct mechanical and physical characteristics that are not seen in traditional materials. This study presents a new concept for a microplate composed of graphene origami (GOri)-enabled auxetic metamaterials (GOEAMs) with functionally graded (FG) properties. The research also examines the nonlinear free vibration behavior of the microplate, which is reinforced by the GOEAMs. The microplate is composed of many layers of GOEAMs, with the GOri content varying in a layer-wise manner across the thickness. This variation in content allows for the graded modification of the auxetic property and other material characteristics. These modifications may be accurately determined using micromechanical models helped by genetic programming (GP). The modified couple stress theory (MCST) is used to accurately represent the microstructure of the current plate, given its size. This theory incorporates a single-length scale parameter. This study uses the first-order shear deformation theory and includes von Kármán type nonlinearity to establish the nonlinear kinematic equations. These equations are then solved numerically using the generalized differential quadrature (GDQ) method and pseudo-arc-length continuation approach. This article utilizes mathematical modeling to collect data on the nonlinear frequency and deflection of the FG microplate made of GOEAMs. The data is then preprocessed by normalizing the input features and splitting the dataset into training and validation sets. Subsequently, an artificial intelligence network (AIN) architecture is constructed, consisting of an input layer, hidden layers, and an output layer. Once the AIN has been utilized to test, train, and validate the findings, this approach may be used in future studies on the nonlinear frequency and deflection of FG microplates built of GOEAMs, with reduced computational cost. Ultimately, the findings suggest that the nonlinear free vibration characteristics of the microplate may be successfully adjusted by manipulating the GOri parameter and distribution.

Penerapan Model Pembelajaran PBL dalam Mata Pelajaran Informatika Kelas X 5 untuk Meningkatkan Kreativitas Siswa di SMA Negeri 8 Maros

In an era of cultural acceleration and rapid advancements in science and technology, this research evaluates the application of the Problem-Based Learning (PBL) model in Informatics at SMA Negeri 8 Maros, focusing on enhancing student creativity. Employing a quantitative method within the Classroom Action Research framework, this study involves cycles of planning, action, observation, and reflection. Data collected through creativity tests, surveys, and class observations reveal that PBL significantly boosts student creativity. These findings are crucial, considering the critical role of education in preparing future generations for digital era challenges. This study highlights how education, especially in Informatics covering programming, artificial intelligence, and computer networking, can adapt to changing times. By integrating technology and innovative approaches into the learning process, students can enhance creativity and other essential skills needed in the digital age. This research offers valuable insights for educators and policymakers in preparing students for a bright, sustainable future.

Effect of Remote and Virtual Technology on Home Dialysis.

In the United States, regulatory changes dictate telehealth activities. Telehealth was available to patients on home dialysis as early as 2019, allowing patients to opt for telehealth with home as the originating site and without geographic restriction. In 2020, coronavirus disease 2019 was an unexpected accelerant for telehealth use in the United States. Within nephrology, remote patient monitoring has most often been applied to the care of patients on home dialysis modalities. The effect that remote and virtual technologies have on home dialysis patients, telehealth and health care disparities, and health care providers' workflow changes are discussed here. Moreover, the future use of remote and virtual technologies to include artificial intelligence and artificial neural network model to optimize and personalize treatments will be highlighted. Despite these advances in technology challenges continue to exist, leaving room for future innovation to improve patient health outcome and equity. Prospective studies are needed to further understand the effect of using virtual technologies and remote monitoring on home dialysis outcomes, cost, and patient engagement.

Technical and ethical considerations in telesurgery.

Telesurgery, a cutting-edge field at the intersection of medicine and technology, holds immense promise for enhancing surgical capabilities, extending medical care, and improving patient outcomes. In this scenario, this article explores the landscape of technical and ethical considerations that highlight the advancement and adoption of telesurgery. Network considerations are crucial for ensuring seamless and low-latency communication between remote surgeons and robotic systems, while technical challenges encompass system reliability, latency reduction, and the integration of emerging technologies like artificial intelligence and 5G networks. Therefore, this article also explores the critical role of network infrastructure, highlighting the necessity for low-latency, high-bandwidth, secure and private connections to ensure patient safety and surgical precision. Moreover, ethical considerations in telesurgery include patient consent, data security, and the potential for remote surgical interventions to distance surgeons from their patients. Legal and regulatory frameworks require refinement to accommodate the unique aspects of telesurgery, including liability, licensure, and reimbursement. Our article presents a comprehensive analysis of the current state of telesurgery technology and its potential while critically examining the challenges that must be navigated for its widespread adoption.

Systemic Modeling and Prediction of Port Container Throughput Using Hybrid Link Analysis in Complex Networks

This paper introduces a hybrid framework for port container throughput forecasting, which is essential in global trade and transportation systems. It uses a multidisciplinary method that combines artificial intelligence, link prediction, and complex networks. To better grasp the interconnection and dynamics of port operations, time series data are first transformed using complex network theory into a network structure. The framework applies 13 similarity metrics, encompassing various aspects of network structural similarity, to form a feature set representing the complex port operation network. The most effective features are selected using the maximum relevance minimum redundancy (mRMR) method, adhering to systems theory’s efficiency principles. These features are processed through SVM, DNN, and LSTM models for link prediction, which is crucial for forecasting in port logistics. Finally, the methodology concludes with regression analysis to obtain container throughput forecasts, which is a key metric in port systems management. Case studies of Shanghai Port and Shenzhen Port validate the framework’s effectiveness, demonstrating a significant improvement in forecasting accuracy over the baseline models. This study contributes to systems analysis by showcasing a hybrid, AI-enhanced approach for managing and forecasting critical aspects of maritime trade systems.

Digitization of Macro-Logistics Systems in Ukraine

This article delves into the multifaceted realm of digitizing macrologistical systems, scrutinizing their nature, influencing factors, and emerging trends. It intricately explores how the integration of digital technologies empowers transport enterprises to deliver superior logistics services while concurrently curtailing costs. A comparative analysis meticulously dissects various facets of the macrologistical system, elucidating the interplay and correlation of its elements within the realms of commodity-money and contractual relationships. The study accentuates the pivotal role of the macro-logistics system in supply chain management.In scrutinizing Ukraine’s Logistics Performance Index scores vis-à-vis EU countries, the authors attribute the disparity to the enduring conflict. A notable European logistics market trend is identified: a surge in digitization investments by individual companies and the establishment of cohesive online platforms. The paper advocates for the integration of automation in transport logistics, particularly in the backdrop of a wartime economy.European standards for a contemporary transport management system are analyzed, culminating in the selection of the CargoClix logistics platform. The article expounds on the platform’s merits in adeptly digitizing the operations of transport and logistics enterprises, offering real-time tracking crucial for prompt responses amid wartime exigencies.The article concludes by substantiating findings with pertinent diagrams and tables. In essence, the digitization of macrologistical systems entails a holistic amalgamation of digital technologies, data analytics, and decision-making solutions for information management in logistics and supply chain operations. This transformative journey, leveraging technologies such as the Internet of Things, unmanned technologies, identification technologies, blockchain, big data, robotic systems, artificial intelligence, and neural networks, aspires to amplify efficiency, visibility, and coordination throughout the supply chain. This paradigm shift is pivotal for evaluating the efficacy of transport and logistics companies, determining their competitive stance in today’s market. Future research trajectories encompass formulating strategies for national companies operating in the domestic logistics market, identifying and implementing key competitive advantages, and devising measures and tools to ensure efficiency during wartime.

A novel artificial intelligence network to assess the prognosis of gastrointestinal cancer to immunotherapy based on genetic mutation features.

Immune checkpoint inhibitors (ICIs) have revolutionized gastrointestinal cancer treatment, yet the absence of reliable biomarkers hampers precise patient response prediction. We developed and validated a genomic mutation signature (GMS) employing a novel artificial intelligence network to forecast the prognosis of gastrointestinal cancer patients undergoing ICIs therapy. Subsequently, we explored the underlying immune landscapes across different subtypes using multiomics data. Finally, UMI-77 was pinpointed through the analysis of drug sensitization data from the Genomics of Drug Sensitivity in Cancer (GDSC) database. The sensitivity of UMI-77 to the AGS and MKN45 cell lines was evaluated using the cell counting kit-8 (CCK8) assay and the plate clone formation assay. Using the artificial intelligence network, we developed the GMS that independently predicts the prognosis of gastrointestinal cancer patients. The GMS demonstrated consistent performance across three public cohorts and exhibited high sensitivity and specificity for 6, 12, and 24-month overall survival (OS) in receiver operating characteristic (ROC) curve analysis. It outperformed conventional clinical and molecular features. Low-risk samples showed a higher presence of cytolytic immune cells and enhanced immunogenic potential compared to high-risk samples. Additionally, we identified the small molecule compound UMI-77. The half-maximal inhibitory concentration (IC50) of UMI-77 was inversely related to the GMS. Notably, the AGS cell line, classified as high-risk, displayed greater sensitivity to UMI-77, whereas the MKN45 cell line, classified as low-risk, showed less sensitivity. The GMS developed here can reliably predict survival benefit for gastrointestinal cancer patients on ICIs therapy.

Research of the potential impact of social engineering on digital transformation processes

Digital transformation reflects the process of transition of society and business to new technologies in order to improve operations and provide new opportunities. This process includes the introduction of artificial intelligence, the Internet of Things, cloud services, and many other technologies to improve business results. Such a transition promises us a number of advantages, including: flexibility and efficiency of digital processes due to total computerization; increasing the efficiency of production processes due to the Internet of Things, cloud computing and automation; improving interaction with customers based on artificial intelligence. This is far from a complete list of Digital Transformation technologies. But no matter how many technologies appear in the future, all of them, along with their advantages, create new challenges for cyber security, including those based on social engineering methods. Social engineering is manipulative and deceptive methods used to obtain confidential information, access systems, or gain control over people through the use of psychological and social mechanisms. The article examines known cases of cyberattacks using social engineering. It is shown that neither small nor large companies are immune from social engineering. The basic model of social engineering, which is based on the tendency of people to transfer all information and perform illogical actions, was studied. Social engineering technologies were analyzed: Pretexting, Phishing, Road apple, Shoulder surfing, Service for service. Potential threats from social engineering methods for systems: SCADA, Cloud Computing, Internet of Things, Drones, Big Data, Blockchain, Artificial Intelligence and Social Networks are assessed. The key means of countering social engineering in the era of digital transformation have been identified. Conclusions are made regarding the impact of social engineering in the future.

A review on monitoring activities through human activity recognition

field of human activity recognition (HAR) is advancing with the integration of cutting-edge technologies such as artificial intelligence and sensor networks. These developments enable accurate detection and interpretation of human behavior, driven by advances in AI and machine learning. A growing number of electronic devices and applications contribute to a comprehensive understanding of the three pillars of HAR – AI, various devices and methodologies and their applications. This review consolidates HAR research and highlights its processes, applications, and device comparisons. Key findings include the importance of non-invasive, real-time sensor-based approaches, particularly in healthcare for the detection of behavioral abnormalities in the elderly. The study highlights Adam as an outstanding optimizer in HAR applications, who predicts continued expansion and development in various industries. particularly in the healthcare sector.

ЦИФРОВІ РІШЕННЯ В УПРАВЛІННІ ЕЛЕКТРОННИМИ ВІДХОДАМИ

The article is devoted to the actual problem of substantiating directions for the use of innovative digital solutions in the management of waste electrical and electronic equipment. The structure of e-waste in developed countries in 2022, which includes IT and telecommunications devices, consumer devices and solar panels, power tools and medical devices, was analyzed and it was found that the largest share is household large-sized appliances (52.7%). Analysis of the dynamics of electronic waste generation per capita in industrialized countries in 2013–2022 showed that in 2022, each resident of Australia – 22.42 kg, Canada – 20.58 kg, Israel – 14.56 kg of electronic waste was generated, Japan – 20.55 kg, Korea – 16.80 kg, Great Britain – 24.63 kg, USA – 21.50 kg, EU – 28.54 kg. Considered the practice of waste management in industrially developed countries. For example, Japan (18–25%) is most actively involved in the processing of electronic waste. The EU has developed a strategy - an action plan for the closed cycle economy, in which the reduction of electrical and electronic waste is a key priority, and a number of proposals have been submitted to promote the repair of goods. The well-founded role of digitalization in the management of electronic waste, which consists in increasing the speed of waste processing and increasing its economic efficiency. The areas of use of innovative digital solutions in electronic waste management are defined, such as: robotics, artificial intelligence and neural networks, the Internet of Things, cloud solutions and data analytics. The advantages of digitization in waste management are disclosed, which includes: automation in waste disposal; improvement of the recycling process; ensuring waste minimization and saving natural resources; creating opportunities to identify problem areas and assess the efficiency of electronic waste disposal; helps to save money, energy and time for waste collection and disposal. The directions for handling electrical and electronic equipment waste have been defined, which consist in preventing the generation of waste, its collection, separation, processing, extraction of secondary raw materials through reuse, recycling and other forms of recovery, which will contribute to the realization of the goals of sustainable production and consumption and the improvement of environmental indicators.

ПРОБЛЕМЫ И ПОТЕНЦИАЛ ИСПОЛЬЗОВАНИЯ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В РАСТЕНИЕВОДСТВЕ НА РАЗНЫХ СТАДИЯХ ЖИЗНЕННОГО ЦИКЛА

Modern crop production faces challenges that require drastic approaches to ensure safety and production efficiency. This article discusses the current issues and potential of using artificial intelligence (AI) and neural networks in agriculture. The introduction of AI promises optimization of production processes, analysis of climate change data, effective problem management and advances in genetic breeding. The article analyzes the problems and areas of application of AI in the context of different stages of the life cycle of crop production.

RETRACTION: Online Education of a Music Flipped Classroom Based on Artificial Intelligence and Wireless Network

RETRACTION: Online Education of a Music Flipped Classroom Based on Artificial Intelligence and Wireless Network

Photonic neural networks and optics-informed deep learning fundamentals

The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI) and deep neural networks (DNNs), is currently instigating the demand for a novel computing paradigm that can overcome the insurmountable barriers imposed by conventional electronic computing architectures. Photonic neural networks (PNNs) implemented on silicon integration platforms stand out as a promising candidate to endow neural network (NN) hardware, offering the potential for energy efficient and ultra-fast computations through the utilization of the unique primitives of photonics, i.e., energy efficiency, THz bandwidth, and low-latency. Thus far, several demonstrations have revealed the huge potential of PNNs in performing both linear and non-linear NN operations at unparalleled speed and energy consumption metrics. Transforming this potential into a tangible reality for deep learning (DL) applications requires, however, a deep understanding of the basic PNN principles, requirements, and challenges across all constituent architectural, technological, and training aspects. In this Tutorial, we, initially, review the principles of DNNs along with their fundamental building blocks, analyzing also the key mathematical operations needed for their computation in photonic hardware. Then, we investigate, through an intuitive mathematical analysis, the interdependence of bit precision and energy efficiency in analog photonic circuitry, discussing the opportunities and challenges of PNNs. Followingly, a performance overview of PNN architectures, weight technologies, and activation functions is presented, summarizing their impact in speed, scalability, and power consumption. Finally, we provide a holistic overview of the optics-informed NN training framework that incorporates the physical properties of photonic building blocks into the training process in order to improve the NN classification accuracy and effectively elevate neuromorphic photonic hardware into high-performance DL computational settings.

Fibres-threads of intelligence-enable a new generation of wearable systems.

Fabrics represent a unique platform for seamlessly integrating electronics into everyday experiences. The advancements in functionalizing fabrics at both the single fibre level and within constructed fabrics have fundamentally altered their utility. The revolution in materials, structures, and functionality at the fibre level enables intimate and imperceptible integration, rapidly transforming fibres and fabrics into next-generation wearable devices and systems. In this review, we explore recent scientific and technological breakthroughs in smart fibre-enabled fabrics. We examine common challenges and bottlenecks in fibre materials, physics, chemistry, fabrication strategies, and applications that shape the future of wearable electronics. We propose a closed-loop smart fibre-enabled fabric ecosystem encompassing proactive sensing, interactive communication, data storage and processing, real-time feedback, and energy storage and harvesting, intended to tackle significant challenges in wearable technology. Finally, we envision computing fabrics as sophisticated wearable platforms with system-level attributes for data management, machine learning, artificial intelligence, and closed-loop intelligent networks.

Task-Oriented and Semantic-Aware Heterogeneous Networks for Artificial Intelligence of Things: Performance Analysis and Optimization

Task-Oriented and Semantic-Aware Heterogeneous Networks for Artificial Intelligence of Things: Performance Analysis and Optimization

ЭКОНОМИЧЕСКИЕ ПЕРСПЕКТИВЫ ИСПОЛЬЗОВАНИЯ ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ОБРАЗОВАТЕЛЬНОМ ПРОЦЕССЕ СТУДЕНТАМИ ТЕХНИЧЕСКОГО ВУЗА

In this article the economic analysis of the prospects of using artificial intelligence for the age category of 17–23 year olds studying in a technical university is carried out. Intelligent networks created on the basis of artificial intelligence are increasingly entering our daily life, and most quickly find their application in the youth environment. The purpose of the study was to analyze the application of the most popular artificial intelligence networks among students of technical universities, as well as the possibility of introducing financial and economic tools to pay the developers of such systems.