Search

This article evaluates the violent deaths during and after the COVID-19 pandemic using automated machine learning and neural network analysis. For this purpose, data recorded by the National Police about the homicides during March 2020 and June 2023 were used. From these data, the profiles of violent deaths during the pandemic (March 2020 and December 2021) and in the post-pandemic (i.e., January 2022 and June 2023) were calculated. Then a comparative analysis was carried out between these two periods using a two-layer neural network to classify and predict future violent deaths with a precision rate of 100%. [ABSTRACT FROM AUTHOR]

The photoelectric factor (PEF) is an important well-logging tool to distinguish between different types of reservoir rocks because PEF measurement is sensitive to elements with high atomic numbers. Furthermore, the ratio of rock minerals could be determined by combining PEF log with other well logs. However, PEF logs could be missing in some cases such as in old well logs and wells drilled with barite-based mud. Therefore, developing models for estimating missing PEF logs is essential in those circumstances. In this work, we developed various machine learning models to predict PEF values using the following well logs as inputs: bulk density (RHOB), neutron porosity (NPHI), gamma ray (GR), compressional and shear velocity. The predictions of PEF values using adaptive-network-fuzzy inference system (ANFIS) and artificial neural network (ANN) models have errors of about 16% and 14% average absolute percentage error (AAPE) in the testing dataset, respectively. Thus, a different approach was proposed that is based on the concept of automated machine learning. It works by automatically searching for the optimal model type and optimizes its hyperparameters for the dataset under investigation. This approach selected a Gaussian process regression (GPR) model for the accurate estimation of PEF values. The developed GPR model decreases the AAPE of the predicted PEF values in the testing dataset to about 10% AAPE. This error could be further decreased to about 2% by modeling the potential noise in the measurements using the GPR model. [ABSTRACT FROM AUTHOR]

This research study applies the J48 algorithm (Weka platform) to determine the most influential independent variables in the quality process of the following fruits: blackberry, orange, passion fruit, lemon, strawberry, lulo, mango, feijoa, and peach. This analysis is based on a database of 211 records, a dependent variable (quality), and a set of 10 independent variables: raw material type, °Brix, pH, acidity, color, smell, flavor, maturity, washed pH, and washed color. The results show with an accuracy of 93% that the most influential variables are: taste, color, and smell. However, if these variables are suppressed, it is revealed that the variables pH, °Brix, and product can predict the dependent quality variable with an accuracy greater than 93%. It is concluded that there are three organoleptic properties (taste, color, and smell) that are associated with fruit product quality. [ABSTRACT FROM AUTHOR]

We propose an automatic ternary classification model for Bipolar Disorder (BD) states. As input information, the model uses speech signals from patients’ audio-visual recordings of structured interviews. The model classifies the patient's clinical state as Mania, Hypo-Mania, or Remission. We capture Mel-Frequency Cepstral Coefficients (MFCCs) and Geneva Minimalistic Acoustic Parameter Set (GeMAPS) as audio features. We compute linguistic and sentiment features for each subject's transcript. We present a stacked ensemble classifier to classify all fused features after feature selection. A set of three homogeneous Convolutional Neural Networks (CNNs) and a Multi Layer Perceptron (MLP) construct the first-level and second-level of the stacked ensemble classifier respectively. Moreover, we use the Neural Architecture Search (NAS) reinforcement learning strategy to optimize the networks and their hyperparameters. We show that our stacked ensemble framework outperforms existing models on the BD Turkish corpus with a $ 59.3\%$ 59. 3 % Unweighted Average Unit (UAR) on the test set. To the best of our knowledge, this is the highest UAR achieved on this dataset. [ABSTRACT FROM AUTHOR]

Oral diseases are the most prevalent chronic childhood diseases, presenting as a major public health issue affecting children of all ages in the developing and developed countries. Early detection and control of these diseases is very crucial for a child's oral health and general wellbeing. The aim of this systematic review is to assess the performance of artificial intelligence models designed for application in pediatric dentistry. A systematic search of the literature was conducted using different electronic databases, primarily (PubMed, Scopus, Web of Science, Embase, Cochrane) and secondarily (Google Scholar and the Saudi Digital Library) for studies published from 1 January 2000, until 20 July 2022, related to the research topic. The quality of the twenty articles that satisfied the eligibility criteria were critically analyzed based on the QUADAS-2 guidelines. Artificial intelligence models have been utilized for the detection of plaque on primary teeth, prediction of children's oral health status (OHS) and treatment needs (TN); detection, classification and prediction of dental caries; detection and categorization of fissure sealants; determination of the chronological age; determination of the impact of oral health on adolescent's quality of life; automated detection and charting of teeth; and automated detection and classification of mesiodens and supernumerary teeth in primary or mixed dentition. Artificial intelligence has been widely applied in pediatric dentistry in order to help less-experienced clinicians in making more accurate diagnoses. These models are very efficient in identifying and categorizing children into various risk groups at the individual and community levels. They also aid in developing preventive strategies, including designing oral hygiene practices and adopting healthy eating habits for individuals. [ABSTRACT FROM AUTHOR]

The importance of Corrective Feedback (CF) to language learners has been a controversial topic for a long time. While some studies recognised CF's importance for accurate language use, others considered it deterrent to the meaningful acquisition of a second language. Recently, modern types of corrective feedback that utilise the vast advance in IT and Artificial Intelligence (AI) have emerged. This advancement has opened new investigation areas. Up to now, researchers have acknowledged the role of Automated Written Evaluation (AWE) in enhancing students’ writing and motivating them. Other studies have focused on students’ and teachers’ perceptions of such tools. However, the particular variance between this type of CF and the traditional one is still an area to explore. Accordingly, the present study aimed to compare CF provided by teachers to that offered by a well-known writing assistant Grammarly. The descriptive design was used to analyse the CF instances provided by five college professors to the Grammarly suggestions on a corpus of 115 texts, 23700 words, written by college students. The descriptive statistics method was adopted to summarise the findings. The study's main results indicated no significant difference in the number of errors detected by the two techniques. However, human raters outperformed Grammarly in detecting grammatical errors and were more accurate in identifying structure-related mistakes. On the other hand, Grammarly was found more effective in detecting errors related to spelling and punctuation. These findings imply using focused CF to exploit both methods. Teachers can implement their regular CF approach to develop structural aspects of language. Further, they can encourage students to adopt sophisticated writing assistants to develop their writing mechanics. To account for the potential limitations of the current study, further research that employs a larger sample size and is conducted on longitudinal and experimental bases is required.

Objective: To analyze the effectiveness of short training sessions on instructor-led and computer-based resuscitation maneuvers for future lifeguards. Methods: To measure effects of training methods on performance of a hands-only CPR test, each participant completed testing H (1) before training (T1); (2) immediately after completion of six short training sessions (T2); (3) 3 weeks after T2 (T3). The training involved performing 4 rounds of 30 seconds of chest compressions with 30 seconds of recovery between rounds. Participants were randomized to groups (G1 or G2) to receive feedback at the end of each round from an instructor or from a manikin with a feedback system, respectively. Results: Twenty-seven participants (26% female) were included. After training, performance of chest compressions in both training groups improved significantly in terms of overall quality (P < 0.01) and of adequacy of compression depth (P < 0.01). There were no significant differences in any of the three tests between G1 and G2. Conclusions: Short training sessions with instructor or automated feedback effectively improves quality of chest compressions and prolong skills retention in the short term. [ABSTRACT FROM AUTHOR]

Oral diseases are the most prevalent chronic childhood diseases, presenting as a major public health issue affecting children of all ages in the developing and developed countries. Early detection and control of these diseases is very crucial for a child’s oral health and general wellbeing. The aim of this systematic review is to assess the performance of artificial intelligence models designed for application in pediatric dentistry. A systematic search of the literature was conducted using different electronic databases, primarily (PubMed, Scopus, Web of Science, Embase, Cochrane) and secondarily (Google Scholar and the Saudi Digital Library) for studies published from 1 January 2000, until 20 July 2022, related to the research topic. The quality of the twenty articles that satisfied the eligibility criteria were critically analyzed based on the QUADAS-2 guidelines. Artificial intelligence models have been utilized for the detection of plaque on primary teeth, prediction of children’s oral health status (OHS) and treatment needs (TN); detection, classification and prediction of dental caries; detection and categorization of fissure sealants; determination of the chronological age; determination of the impact of oral health on adolescent’s quality of life; automated detection and charting of teeth; and automated detection and classification of mesiodens and supernumerary teeth in primary or mixed dentition. Artificial intelligence has been widely applied in pediatric dentistry in order to help less-experienced clinicians in making more accurate diagnoses. These models are very efficient in identifying and categorizing children into various risk groups at the individual and community levels. They also aid in developing preventive strategies, including designing oral hygiene practices and adopting healthy eating habits for individuals.

Machine-age technologies, including automation, robotics, and artificial intelligence, are profoundly expanding the variety of service interfaces and therefore the possible ways that customers and firms can interact across customer journeys. This expansion challenges service firms' capabilities to deliver coherent streams of interactions for effective customer engagement. This article develops a conceptual framework of firm capabilities that enable firms to operate with "one voice" to deliver seamless, harmonious, and reliable interactions across diverse interfaces in a customer journey. The proposed framework integrates three themes: (1) service interaction space to capture the interrelationship among devices, interfaces, interactions, and journeys; (2) learning and coordination as core capabilities for generating and using intelligence, respectively, to enhance customer engagement in subsequent interactions; and (3) one-voice strategy to configure learning and coordination capabilities in combinations that meet conditions of fitness and equifinality for effective customer engagement. We provide several research questions and priorities to guide research and practice. [ABSTRACT FROM AUTHOR]

Treatment planning plays an important role in the process of radiotherapy (RT). The quality of the treatment plan directly and significantly affects patient treatment outcomes. In the past decades, technological advances in computer and software have promoted the development of RT treatment planning systems with sophisticated dose calculation and optimization algorithms. Treatment planners now have greater flexibility in designing highly complex RT treatment plans in order to mitigate the damage to healthy tissues better while maximizing radiation dose to tumor targets. Nevertheless, treatment planning is still largely a time-inefficient and labor-intensive process in current clinical practice. Artificial intelligence, including machine learning (ML) and deep learning (DL), has been recently used to automate RT treatment planning and has gained enormous attention in the RT community due to its great promises in improving treatment planning quality and efficiency. In this article, we reviewed the historical advancement, strengths, and weaknesses of various DL-based automated RT treatment planning techniques. We have also discussed the challenges, issues, and potential research directions of DL-based automated RT treatment planning techniques.

The mixture of factor analyzers (MFA) model has emerged as a useful tool to perform dimensionality reduction and model-based clustering for heterogeneous data. In seeking the most appropriate number of factors (q) of a MFA model with the number of components (g) fixed a priori, a two-stage procedure is commonly implemented by firstly carrying out parameter estimation over a set of prespecified numbers of factors, and then selecting the best q according to certain penalized likelihood criteria. When the dimensionality of data grows higher, such a procedure can be computationally prohibitive. To overcome this obstacle, we develop an automated learning scheme, called the automated MFA (AMFA) algorithm, to effectively merge parameter estimation and selection of q into a one-stage algorithm. The proposed AMFA procedure that allows for much lower computational cost is also extended to accommodate missing values. Moreover, we explicitly derive the score vector and the empirical information matrix for calculating standard errors associated with the estimated parameters. The potential and applicability of the proposed method are demonstrated through a number of real datasets with genuine and synthetic missing values. [ABSTRACT FROM AUTHOR]

Treatment planning plays an important role in the process of radiotherapy (RT). The quality of the treatment plan directly and significantly affects patient treatment outcomes. In the past decades, technological advances in computer and software have promoted the development of RT treatment planning systems with sophisticated dose calculation and optimization algorithms. Treatment planners now have greater flexibility in designing highly complex RT treatment plans in order to mitigate the damage to healthy tissues better while maximizing radiation dose to tumor targets. Nevertheless, treatment planning is still largely a time-inefficient and labor-intensive process in current clinical practice. Artificial intelligence, including machine learning (ML) and deep learning (DL), has been recently used to automate RT treatment planning and has gained enormous attention in the RT community due to its great promises in improving treatment planning quality and efficiency. In this article, we reviewed the historical advancement, strengths, and weaknesses of various DL-based automated RT treatment planning techniques. We have also discussed the challenges, issues, and potential research directions of DL-based automated RT treatment planning techniques. [ABSTRACT FROM AUTHOR]

This article describes problems of designing automated teaching system for “Computational complexity of algorithms” course. This system should provide students with means to familiarize themselves with complex mathematical apparatus and improve their mathematical thinking in the respective area. The article introduces the technique of algorithms symbol scroll table that allows estimating lower and upper bounds of computational complexity. Further, we introduce a set of theorems that facilitate the analysis in cases when the integer rounding of algorithm parameters is involved and when analyzing the complexity of a sum. At the end, the article introduces a normal system of symbol transformations that allows one both to perform any symbol transformations and simplifies the automated validation of such transformations. The article is published in the authors’ wording.

In this paper, we describe the concept of generative design approach applied to the automated evolutionary learning of mathematical models in a computationally efficient way. To formalize the problems of models’ design and co-design, the generalized formulation of the modeling workflow is proposed. A parallelized evolutionary learning approach for the identification of model structure is described for the equation-based model and composite machine learning models. Moreover, the involvement of the performance models in the design process is analyzed. A set of experiments with various models and computational resources is conducted to verify different aspects of the proposed approach.

Copyright of Dirasat Tarbawiya is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The issue of energy in a wireless sensor network is one of the most important challenges for these networks. This issue is also being considered today in the new IoT topic. This paper studies the ability of the learning automata model to solve the problem in the sensor networks. Because they have capabilities such as low computational load, ability to use in distributed environments, and inaccurate information, require the least feedback from the environment, etc. One of the solutions to energy optimization is to provide routing protocols. In the routing area, a routing protocol based on learning automata has been proposed in which the network lifetime criterion is considered. The simulation results and the comparison of the proposed protocol with other protocols indicate that this protocol has better performance in the energy conversation and network lifetime. [ABSTRACT FROM AUTHOR]

Incorporating gamification into training−learning at universities is hampered by a shortage of quality, adapted educational video games. Large companies are leading in the creation of educational video games for their internal training or to enhance their public image and universities can benefit from collaborating. The aim of this research is to evaluate, both objectively and subjectively, the potential of the simulation game BugaMAP (developed by the MAPFRE Foundation) for university teaching about insurance. To this end, we have assessed both the game itself and the experience of using the game as perceived by 142 economics students from various degree plans and courses at the University of Seville during the 2017−2018 academic year. As a methodology, a checklist of gamification components is used for the objective evaluation, and an opinion questionnaire on the game experience is used for the subjective evaluation. Among the results several findings stand out. One is the high satisfaction of the students with the knowledge acquired using fun and social interaction. Another is that the role of the university professors and the company monitors turns out to be very active and necessary during the game-learning sessions. Finally, in addition to the benefits to the university of occasionally available quality games to accelerate student skills training, the company−university collaboration serves as a trial and refinement of innovative tools for game-based learning.

Purpose: The purpose of this paper is to propose a system for automated learning directed towards discovering and enhancement of the set of recurrent behaviours that can be found within a learning knowledge base and how they can be modelled to enable a more effective reasoning and tactical strategies for personalized adaptation and decision making. Design/Methodology/Approach: The paper introduces a methodology that makes use of information readily available within a learning process to explore and analyse the data to obtain inference knowledge capable of enhancing individual learning performance. The author valuated this approach through a user-centric design prototype and a model developed using Business Process Model Notations to corroborate the focus on improving performance of e-learning systems. Findings: The technological response to satisfying the increasing demand for richer and more precise depiction of e-learning applications capable of providing platforms for pattern exploration where users can browse for knowledge they might consider as interesting is by providing a personalized adaptive learning system for the users. Adoption of such technological developments will spark a great success for many learners and needed to provide continuous intelligent recommendation, guidance and feedbacks on learner's performance especially in achieving the overall learning objective. Research limitations/implications: To meet the overall needs of intended users, there is requirement for e-learning systems to embody technologies that support learners in achieving their learning goals and this process do not happen automatically. Such process should take into account the fact that there is an additional task of matching these persons (user profiling) with solutions that best fits their particular learning needs (personalization). Practical implications: The work in this paper considers the implication of the user centered design approach, and to this end, identify some of the common design problems with e-learning systems as means to revealing the implications for designers to stick to user-centric standards when developing automated learning systems in order to ensure learners satisfaction and reliability. Originality/value: The approach and prototype described in this paper provides an enhanced model for learning which is useful towards the development of e-learning systems that are more intelligent, predictive and robotically adaptive, which also aid in discovery of new learning patterns and enhancement of existing learning processes. [ABSTRACT FROM AUTHOR]

“Big data” in the form of unstructured text pose challenges and opportunities to social scientists committed to advancing research frontiers. Because machine-based and human-centric approaches to content analysis have different strengths for extracting information from unstructured text, the authors argue for a collaborative, hybrid approach that combines their comparative advantages. The notion of a progressive supervised-learning approach that combines data science techniques and human coders is developed and illustrated using the Social, Political and Economic Event Database (SPEED) project’s Societal Stability Protocol. SPEED’s rich event data on civil strife reveal that conventional machine-based approaches for generating event data miss a great deal of within-category variance, while conventional human-based efforts to categorize periods of civil war or political instability routinely misspecify periods of calm and unrest. To demonstrate the potential of hybrid data collection methods, SPEED data on event intensities and origins are used to trace the changing role of political, socioeconomic, and sociocultural factors in generating global civil strife in the post–World War II era. [ABSTRACT FROM AUTHOR]

In this paper, we introduce an automated reasoning system for learning object behaviors and interactions through the observation of event sequences. We use an existing system to learn the models of objects and further extend it to model more complex behaviors. Furthermore, we propose a spatio–temporal reasoning based learning method for reasoning about interactions among objects. Experience gained through learning is to be used for achieving goals by these objects. We take The Incredible Machine game (TIM) as the main testbed to analyze our system. Tutorials of the game are used to train the system. We analyze the results of our reasoning system on four different input types: a knowledge base of relations; spatial information; temporal information; and spatio–temporal information from the environment. Our analysis reveals that if a knowledge base about relations is provided, most of the interactions can be learned. We have also demonstrated that our learning method which incorporates both spatial and temporal information gives close results to that of the knowledge-based approach. This is promising as gathering spatio–temporal information does not require prior knowledge about relations. Our second analysis of the spatio–temporal reasoning method in the Electric Box computer game domain verifies the success of our approach. [ABSTRACT FROM PUBLISHER]

One of the most important prerequisites for a long-term development of all countries is a high level of education for society. Nowadays the impact of technology on society is very deep. It is not story only about a group of people who share a defined territory and a culture. Technology plays a large role in many aspects of day-to-day life and many processes become automated. With automated learning support system is possible to work more closely with an adult to provide effective learning solutions that meet their unique needs. The problem is the inefficient or incomplete utilization of presence and cognition technologies and the non-usage of knowledge management technologies for the useful development of adults in an online environment. The goal of the paper is get a new perspective on knowledge sharing process and understanding of the future of automated learning support system involving the use of new technological opportunities. The main study question is how the automated learning support system could improve the efficiency and quality of further knowledge flow and provide sustainable cooperation between educational institutions and entrepreneurs. The research idea is to describe the principles of automated learning support focusing on an online system and knowledge management technologies for adults. The result of the research is the analysis of the information system as an online learning support platform, improved quality of knowledge flow, and recommendations for future work in this field. [ABSTRACT FROM AUTHOR]