Search

In recent times, the field of education has experienced significant technological advancements, especially in area of Artificial Intelligence (AI). A particularly groundbreaking development is the emergence of humanoid AI robots, which holds immense promise for enhancing children’s learning experiences during early childhood. Unlike other forms of AI, humanoid AI robots bear a closer resemblance to humans, making them more approachable and engaging for young children. This paper explores a practical framework for incorporating humanoid AI robots into early childhood education. This framework includes several key components: first, introducing AI concepts in a child-friendly manner; second, fostering a relationship between children and AI; third, designing developmentally appropriate activities facilitated by AI; and finally, addressing the challenges associated with integrating AI into early childhood classrooms. The aim is to utilize the potential of AI in a way that enriches the educational environment for young learners. [ABSTRACT FROM AUTHOR]

This paper aims to explore the application of artificial intelligence in the petroleum industry, with a specific focus on oil well production forecasting. The study utilizes the Zananor field as a case study, systematically organizing raw data, categorizing different well instances and production stages in detail, and normalizing the data. An individual long short-term memory (LSTM) neural network model is constructed with monthly oil production data as input to predict the monthly oil production of the experimental oilfield. Furthermore, a multivariate LSTM neural network model is introduced, incorporating different production data as input sets to enhance the accuracy of monthly oil production predictions. A comparative analysis is conducted with particle swarm optimization optimized recurrent neural network results. Finally, gray relational analysis and principal component analysis methods are compared in feature selection. Experimental results demonstrate that the LSTM model is more suitable for the study area, and the multivariate model outperforms the univariate model in terms of prediction accuracy, especially for monthly oil production. Additionally, gray relational analysis exhibits higher accuracy and greater applicability in feature selection compared to principal component analysis. These research findings provide valuable guidance for production forecasting and operational optimization in the petroleum industry. [ABSTRACT FROM AUTHOR]

The Optimal Multivariate Mixture Problem (OMMP) consists of finding an optimal mixture which, starting from a set of elements (items) described by a set of variables (features), is as close as possible to an ideal solution. This problem has numerous applications spanning various fields, including food science, agriculture, chemistry, materials science, medicine, and pharmaceuticals. The OMMP is a class of optimization problems that can be addressed using traditional Operations Research (OR) approaches. However, it can also be effectively tackled using meta-heuristic techniques within Artificial Intelligence (AI). This paper aims to present an Artificial Intelligence perspective. It proposes a Genetic Algorithm (GA) for Optimal Multivariate Mixture (GA-OMM), a novel improved version of a GA whose modified genetic operators prove to improve the exploration efficiency. Here, the algorithm is described in its general framework, and a test case 8-items 5-features is conducted to evaluate efficiency by exploring various combinations of hyperparameters. Test cases are also set up for the previous version, as well as a linear programming (LP) approach. The data experiments indicate that the proposed GA is efficient, converges towards the global optimum, consistently outperforms its predecessor, and delivers highly competitive results. In particular, GA-OMM shows an average fitness of GA-OMMP/LP and standard deviation with an order of magnitude ranging between 10-8\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$10^{-8}$$\end{document} to 10-4\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$10^{-4}$$\end{document}. Moreover, it consistently outperforms its predecessor, which exhibits similar values around 10-3\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$10^{-3}$$\end{document} [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) is a paradigm that enables the integration of cyber-physical systems in critical infrastructures, such as power grids, water distribution networks, and transportation systems. IIoT devices, such as sensors, actuators, and controllers, can provide various benefits, such as performance optimization, efficiency improvement, and remote management. However, these devices also pose new security risks and challenges, as they can be targeted by malicious actors to disrupt the normal operation of the infrastructures they are connected to or to cause physical damage or harm. Therefore, it is essential to develop effective and intelligent solutions to detect and prevent attacks on IIoT devices and to ensure the security and resilience of critical infrastructures. In this paper, we present a comprehensive analysis of the types and impacts of attacks on IIoT devices based on a literature review and a data analysis of real-world incidents. We classify the attacks into four categories: denial-of-service, data manipulation, device hijacking, and physical tampering. We also discuss the potential consequences of these attacks on the safety, reliability, and availability of critical infrastructures. We then propose an expert system that can detect and prevent attacks on IIoT devices using artificial intelligence techniques, such as rule-based reasoning, anomaly detection, and reinforcement learning. We describe the architecture and implementation of our system, which consists of three main components: a data collector, a data analyzer, and a data actuator. We also present a table that summarizes the main features and capabilities of our system compared to existing solutions. We evaluate the performance and effectiveness of our system on a testbed consisting of programmable logic controllers (PLCs) and IIoT protocols, such as Modbus and MQTT. We simulate various attacks on IIoT devices and measure the accuracy, latency, and overhead of our system. Our results show that our system can successfully detect and mitigate different types of attacks on IIoT devices with high accuracy and low latency and overhead. We also demonstrate that our system can enhance the security and resilience of critical infrastructures by preventing or minimizing the impacts of attacks on IIoT devices. [ABSTRACT FROM AUTHOR]

Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also highlights the need for principled assessments and practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers and personnel. Despite advancements, challenges such as data biases and the scarcity of “big data” in many biomedical domains persist. We conclude with a discussion on principled innovation and collaborative efforts to further the mission of seamless integration of multimodal ML models into biomedical practice. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach known as the cross estimation network (CEN) for fitting the datasets obtained from psychological or educational tests and estimating the parameters of item response theory (IRT) models. The CEN is comprised of two subnetworks: the person network (PN) and the item network (IN). The PN processes the response pattern of individual respondent and generates an estimate of the underlying ability, while the IN takes in the response pattern of individual item and outputs the estimates of the item parameters. Four simulation studies and an empirical study were comprehensively and rigorously conducted to investigate the performance of CEN on parameter estimation of the two-parameter logistic model under various testing scenarios. Results showed that CEN effectively fit the training data and produced accurate estimates of both person and item parameters. The trained PN and IN adhered to AI principles and acted as intelligent agents, delivering commendable evaluations for even unseen patterns of new respondents and items. [ABSTRACT FROM AUTHOR]

Nowadays, phishing attacks have grown rapidly, and there is an urgent need to introduce a suitable detection method that has the ability to detect different types of phishing attacks. This paper investigates the capability to use bio-inspired meta-heuristic algorithms to improve the performance of the detection engine for phishing attacks by reducing the number of features. This improvement was practiced by investigating the effectiveness of five meta-heuristic algorithms: Particle Swarm Optimization (PSO), Firefly Optimization Algorithm (FFA), Multi-Verse Optimizer (MVO), Moth-Flame Optimization algorithm (MFO), and BAT optimization algorithm, to select the relevant features that could be affected directly by different types of phishing attacks. The suggested detection model was tested and evaluated using four benchmark phishing attack datasets, and the Apache Spark-based decision tree algorithm was selected as a detection engine. The conducted experiments have demonstrated that the Spark-based MVO algorithm achieved the highest detection rate for detecting different types of phishing attacks within four phishing attack datasets. Moreover, the suggested detection model was able to reduce effectively the feature space, which could enhance the computational efficiency. [ABSTRACT FROM AUTHOR]