نشریه اکتشاف و پردازش هوشمند دانش
پیاپی 12 (بهار 1403)

These days, with the emergence of technologies such as artificial intelligence (AI), virtual reality (VR), augmented reality (AR) and data visualization (DV), we are witnessing unprecedented developments in the field of sports. These technologies help to improve sports performance analysis, collect data automatically, and create effective training environments to improve decision-making processes. Traditional methods of sports performance analysis were usually based on manual data collection, subjective observations, and the use of limited statistical models, but with recent advances in technology, this practice has become objective and up-to-date. For example, AI has revolutionized sports analytics by simplifying data collection, processing large datasets, and automating sports analytics. Virtual reality enables training in highly realistic environments and allows athletes to practice their skills in controlled settings, and augmented reality provides digital information in the real sports environment and facilitates the tactical planning process. Data visualization techniques visualize complex data and improve understanding of performance metrics. This article examines the potential of these emerging technologies to transform sports performance analysis, providing valuable resources to coaches and athletes. The purpose of this article is to increase athletes' performance, optimize training strategies and improve decision-making processes. It also identifies existing challenges and provides solutions for integrating these technologies into current sports analysis methods. Based on the findings, it can be concluded that faster data is turned into actionable insights, training and competition events can be adjusted more quickly to align with specific goals. In this context, different environments, including virtual worlds and mixed reality, can be used to provide educational strategies Also, quality information can lead to valuable insights, and valuable insights can help achieve goals. These goals can primarily be addressed through training and performance improvement, which requires a continuous cycle of measurement and data processing.

Today, maintaining and strengthening customer loyalty has become a strategic challenge for organizations. Customer loyalty is more important in service industries such as the insurance industry than in other industries. According to studies, the long-term relationship between the customer and the organization depends on the level of customer trust. If customers trust the organization, they will be more engaged in the organization's products and services. Therefore, the present study was conducted to investigate the effect of trust on customer loyalty through the mediator role of customer engagement. The statistical population of the study included customers of Iran Insurance branches in Mashhad city. 384 people participated in this study by Non-random sampling available. The data collection tool was a standard questionnaire. The content validity of the questionnaire was confirmed by experts, the structure validity of the questionnaire was confirmed by factor analysis and the reliability of the questionnaire variables using Cronbach's alpha coefficient. Data were analyzed using SPSS 24 and Smart PLS 2 softwares and structural equation modeling method. The findings indicated that Customer trust has a positive and significant effect on brand loyalty and customer engagement with brand. Customer engagement with brand has a positive and significant effect on brand loyalty. The mediating role of customer engagement with brand in the relationship between customer trust and brand loyalty was also confirmed.

Software mining repositories is the operation of extracting and analyzing valuable data from software repositories. Therefore, it is very important to use appropriate data-mining tools and methods to properly explore software repositories. The data obtained from software mining repositories is useful for software development, and software development is the ultimate goal of software mining repositories. In this research, the quantity and quality of researches in the use of data mining tools and methods have been analyzed and evaluated using the Google Scholar database. The results show that tools such as Eclipse, Weka, RapidMiner, GNUPlot, programs such as Perl and R are widely used by researchers for the purpose of mining software repositories, which improve the exploration of software repositories and the evolution of code and Version control and tracking bugs and correct code changes are very effective. The number of researches conducted with the desired tool is less than half of the number of researches conducted with other tools. which relatively shows the researchers' good acceptance of the tools investigated in this research. In order to extract data related to software mining repositories, criteria of time period and subject range have been used. Two categories of time period are considered separately, the first category is from 2007 to 2012, and the second category is from 2007 to 2024.

Machine learning is a subfield of artificial intelligence (AI). The goal of machine learning in general is to understand the structure of data and fit that data into models that people can understand and use. Today, every technology user has benefited from machine learning. Facial recognition technology allows social media platforms to help users tag and share photos of their friends. Optical Character Recognition (OCR) technology converts text images into animated type. Recommendation engines, using machine learning, suggest what movies or TV shows to watch next, based on user preferences. Self-driving cars that rely on machine learning to navigate may soon be available to consumers. Machine learning is a constantly developing field. For this reason, there are considerations to keep in mind when working with machine learning methods or analyzing the impact of machine learning processes. In this article, common machine learning methods of supervised and unsupervised learning and common algorithmic approaches in machine learning. including k-nearest neighbor algorithm, decision tree learning and deep learning. His findings showed. With the expansion of the scope and fields of study and the use of machine learning in different fields, depending on the changing needs and complexity of different problems, different types of machine learning algorithms have emerged, each of which has its own efficiency and applications. . So you can choose the algorithm that best suits your business needs. In some cases, experts use a combination of these algorithms because one algorithm alone may not be able to solve a particular problem.

In response to the fundamental need for accurate recognition of tense faces wearing masks, this paper presents an innovative approach that takes advantage of parallel two-stage deep learning methods combined with hybrid meta-heuristic algorithms. The challenges associated with mask-wearing detection are addressed through a comprehensive framework that leverages state-of-the-art technologies and diverse inputs. This method includes a parallel algorithmic strategy, which optimizes the detection of faces with and without masks for accuracy. A special algorithm is used when detecting unmasked faces, while detecting masked faces uses a separate algorithm. In addition, an integration of multiple data sources including masked face images and inputs from temperature sensors increases the recognition accuracy. The main focus of this research is on data clustering, where datasets are organized based on their volume, then classification is performed using a proposed convolutional neural network. Duplicate features are carefully removed from each cluster, and parallel post-processing is performed by differentiating algorithms. In this study, two hybrid algorithms are introduced, and with the increase in data volume, additional algorithms can be easily inserted to provide scalability and increase accuracy. This innovative approach demonstrates the ability to significantly improve the accuracy and efficiency of complex facial recognition systems and addresses an important need in the fields of security to public health and beyond. Also, with the advancement of technology and the progress of research in this field, the possibility of improving the accuracy of detecting contracted faces is still promising.

Obsessive-Compulsive Disorder (OCD) is a debilitating mental health condition that can significantly impair an individual's quality of life. While traditional exposure-based therapies have shown promise, there is a growing interest in the use of virtual reality (VR) to enhance the effectiveness of OCD treatment. This study aimed to investigate the impact of a VR-based intervention on OCD symptom severity, associated mental health outcomes, and underlying neural correlates.

Thirty individuals diagnosed with OCD were recruited for this study. Participants engaged in a series of VR-based exposure therapy sessions, during which their brain activity was continuously monitored using a 32-channel EEG system. The primary outcome measure was the Yale-Brown Obsessive-Compulsive Scale (Y-BOCS), and secondary measures included assessments of anxiety, depression, and quality of life. Data was analyzed using repeated-measures ANOVA and correlational analyses.

The VR-based intervention resulted in a significant reduction in OCD symptom severity, as measured by the Y-BOCS, from baseline to post-treatment, and these improvements were maintained at the 3-month follow-up. Participants also reported significant improvements in anxiety, depression, and quality of life. The EEG data analysis revealed increased alpha and beta power in the medial prefrontal cortex and anterior cingulate cortex, brain regions associated with cognitive control and emotional regulation, which were positively correlated with the degree of clinical improvement.

This study provides evidence for the efficacy of VR-based therapy in the treatment of OCD and suggests that this approach may lead to measurable changes in brain function that are linked to positive clinical outcomes. The involvement of bachelor's degree students in the research process highlights the value of interdisciplinary collaboration in advancing the field of mental health treatment.