In the context of typhlo music therapy, personalized interventions can significantly enhance the therapeutic experience for visually impaired children. Leveraging a data-driven approach, we incorporate action-rule discovery to provide insights into the factors of music that may benefit individual children. The system utilizes a comprehensive dataset developed in collaboration with an experienced music therapist, special educator, and clinical psychologist, encompassing meta-decision attributes, decision attributes, and musical features such as tempo, rhythm, and pitch. By extracting and analyzing these features, our methodology identifies key factors that influence therapeutic outcomes. Some themes discovered through action-rule discovery include the effect of harmonic richness and loudness on expression and communication. The main findings demonstrate the system’s ability to offer personalized, impactful, and actionable insights, leading to improved therapeutic experiences for children undergoing typhlo music therapy. Our conclusions highlight the system’s potential to transform music therapy by providing therapists with precise and effective tools to support their patients’ developmental progress. This work shows the significance of integrating advanced data analysis techniques in therapeutic settings, paving the way for future enhancements in personalized music therapy interventions.

Purpose: The extraction of actionable insights is critical for intelligent systems and recommendation engines. However, traditional methods for action rule discovery face challenges in scalability and efficiency when applied to large datasets. This study introduces a correlation-based vertical partitioning method to improve the consistency and interpretability of action rules while addressing the limitations of random partitioning and unstructured approaches. Methods: The proposed method clusters flexible attributes using correlations, enabling structured partitions for parallel rule generation via hierarchical clustering. Comparative experiments evaluated its precision, runtime, lightness, and coverage against random and baseline partitioning approaches. Results: The correlation-based method outperformed random partitioning and significantly improved runtime efficiency over the baseline. It generates interpretable rules in a single iteration, avoiding variability and repeated runs, though challenges in rule combination efficiency suggest areas for improvement. Conclusion: The correlation-based vertical partitioning method strikes a balance between computational efficiency and rule quality, making it a promising solution for large-scale action rule discovery. Future work could enhance scalability further by improving the rule combination process and exploring hybrid or adaptive partitioning strategies to extend the method’s applicability across diverse domains.

Introduction:While both induced abortion and natural pregnancy loss have been associated with subsequent mental health problems, population-based studies directly comparing these two pregnancy outcomes are rare. We sought to compare mental health morbidity after an induced abortion or natural loss. Methods:Continuously eligible Medicaid beneficiaries age 16 in 1999 were assigned to two cohorts based upon the first pregnancy outcome: abortion (n = 1,331) or natural loss (n = 605). Outcomes were mental health outpatient visits, inpatient hospital admissions and hospital days of stay per patient per year. Average exposure periods before and after the first pregnancy outcome for each cohort were used to adjust the mental health service rates. Results:Prior to the first pregnancy outcome, all three utilization rates were significantly higher for the natural loss cohort compared to the abortion cohort. For the abortion cohort, the per-patient per-year increase from the pre- to post-pregnancy periods was significant for all three rates: 2.04 times for outpatient visits (p < 0.0001), 3.04 times for inpatient admissions (p = 0.0003), and 3.01 times for hospital days of stay (p = 0.0112). None of the pre-to-post rate increases were significant for the natural loss cohort. Conclusion:Higher pre-pregnancy use rates for women who experience a natural pregnancy loss indicate that increased mental health services use following abortion cannot be solely attributed to pre-existing mental illness. Only the abortion cohort, but not the natural loss cohort, experienced significant increases in mental health services use following the first pregnancy outcome.

Action Rules are rule based systems that extract actionable patterns which are hidden in big volumes of data. Users need recommendations on actions they can undertake to increase their profit or accomplish their goals, this recommendations are provided by Actionable patterns. In the technological world of big data, massive amounts of data are collected by organizations, including in major domains like financial, medical, social media and Internet of Things(IoT). To analyze and store such a massive amount of data, distributed computing frameworks like Hadoop and Spark are introduced to store the big data in a distributed fashion which manage and analyze them in parallel. The traditional Action Rules extraction models, which analyze the data in a nondistributed fashion, do not perform well when dealing larger datasets. Serious complications of discovering Action Rules with such distributed environments are - data distribution among computing nodes and calculation of major parameters including : support, confidence, utility, and coverage, that represent the whole data. Information granules form basic entities in the world of Granular Computing(GrC), which represents meaningful smaller units derived from a larger complex information system. In this research, we focus on the data distribution phase of the distributed Actionable Pattern Mining problem. To handle the data distribution task by splitting the big data in both horizontal and vertical fashions - we propose partition threshold rho. In this work, we concentrate on using information granules to implement a vertical data splitting strategy with Meta Actions. Hence our results discover valuable Actionable Knowledge with application in Business and Education domains.

The paper concerns the problem of action-rule extraction when datasets are large. Such rules can be used to construct a knowledge base in a recommendation system. One of the popular approaches to construct action rules in such cases is to partition the dataset horizontally (personalization) and vertically. Different clustering strategies can be used for this purpose. Action rules extracted from vertical clusters can be combined and used as knowledge discovered from the horizontal clusters of the initial dataset. The number of extracted rules strongly depends on the methods used to complete that task. In this study, we chose a software package called SCARI recently developed by Sikora and his colleagues. It follows a rule-based strategy for action-rule extraction that requires prior extraction of classification rules and generates a relatively small number of rules in comparison to object-based strategies, which discover action rules directly from datasets. Correlation between attributes was used to cluster them. We used an agglomerative strategy to cluster attributes of a dataset and present the results by using a dendrogram. Each level of the dendrogram shows a vertical partition schema for the initial dataset. From all partitions, for each level, action rules are extracted and then concatenated. Their precision, the lightness, and the number of rules are presented and compared. Lightness shows how many action rules can be applied on average for each tuple in a dataset.

Education sector ,Business field,Medical domain and SocialMedia,huge amounts of data in a single day . Mining this data can provide a lot of meaningful insights on how to improve user experience in social media, users engage in these domains collect and cherish the data as they hope to find patterns and trends and the golden nuggets that help them to accomplish their goal. For example: How to improve student learning; how to increase business profit ability; how to improve user experience in social media; and how to heal patients and assists hospital administrators. Action Rule Miningmines actionable patterns which are hidden in various datasets. Action Rules provide actionable suggestions on how to change the state of an object from an existing state to a desired state for the benefit of the user. There are two major frameworks in the literature of Action Rule mining namely Rule-Based method where the extraction of Action Rules is dependent on the pre-processing step of classification rule discovery and Object-Based method where it extracts the Action Rules directly from the database without the use of classification rules.Hybrid Action rule mining approach combines both these frame works and generates complete set of Action Rules. The hybrid approach shows significant improvement in terms computational performance over the Rule-Based and Object-Based approach. In this work we propose a novel Modified Hybrid Action rule method with Partition Threshold Rho, which further improves the computational performance with large datasets.

Objective:To determine whether exposure to a first pregnancy outcome of induced abortion, compared to a live birth, is associated with an increased risk and likelihood of mental health morbidity.Materials and methods:Participants were continuously eligible Medicaid beneficiaries age 16 in 1999, and assigned to either of two cohorts based upon the first pregnancy outcome, abortion (n = 1331) or birth (n = 3517), and followed through to 2015. Outcomes were mental health outpatient visits, inpatient hospital admissions, and hospital days of stay. Exposure periods before and after the first pregnancy outcome, a total of 17 years, were determined for each cohort.Findings:Women with first pregnancy abortions, compared to women with births, had higher risk and likelihood of experiencing all three mental health outcome events in the transition from pre- to post-pregnancy outcome periods: outpatient visits (RR 2.10, CL 2.08-2.12 and OR 3.36, CL 3.29-3.42); hospital inpatient admissions (RR 2.75, CL 2.38-3.18 and OR 5.67, CL 4.39-7.32); hospital inpatient days of stay (RR 7.38, CL 6.83-7.97 and OR 19.64, CL 17.70-21.78). On average, abortion cohort women experienced shorter exposure time before (6.43 versus 7.80 years), and longer exposure time after (10.57 versus 9.20 years) the first pregnancy outcome than birth cohort women. Utilization rates before the first pregnancy outcome, for all three utilization events, were higher for the birth cohort than for the abortion cohort.Conclusion:A first pregnancy abortion, compared to a birth, is associated with significantly higher subsequent mental health services utilization following the first pregnancy outcome. The risk attributable to abortion is notably higher for inpatient than outpatient mental health services. Higher mental health utilization before the first pregnancy outcome for birth cohort women challenges the explanation that pre-existing mental health history explains mental health problems following abortion, rather than the abortion itself.

Art authentication is the process of identifying the artist who created a piece of artwork and is manifested through events of provenance, such as art gallery exhibitions and financial transactions. Art authentication has visual influence via the uniqueness of the artist’s style in contrast to the style of another artist. The significance of this contrast is proportional to the number of artists involved and the degree of uniqueness of an artist’s collection. This visual uniqueness of style can be captured in a mathematical model produced by a machine learning (ML) algorithm on painting images. Art authentication is not always possible as provenance can be obscured or lost through anonymity, forgery, gifting, or theft of artwork. This paper presents an image-only art authentication attribute marker of contemporary art paintings for a very large number of artists. The experiments in this paper demonstrate that it is possible to use ML-generated models to authenticate contemporary art from 2368 to 100 artists with an accuracy of 48.97% to 91.23%, respectively. This is the largest effort for image-only art authentication to date, with respect to the number of artists involved and the accuracy of authentication.

Customer churn, a major concern for most of the companies, leads to higher customer acquisition cost, lower volume of service consumption and reduced product purchase. Thus, it is critical for companies to take effective strategies to reduce customer outflow. In this paper, we aim to discover high quality action rules and provide valid and trustworthy recommendations to improve customer churn rate. We propose a Semantic-aided Customer Attrition Management System (SaCAMS), in which we use reducts for feature engineering, apply hierarchical clustering to build the semantic similarity relationship among clients, run action rule mining to discover the actionable patterns, and extract meta-actions to get the final recommendations. The experimental results show that SaCAMS can discover high quality action rules. Moreover, based on the improved action rules, SaCAMS can extract effective meta-actions to generate recommendations. Last but not least, SaCAMS utilizes meta-node to provide decision-makers with valid and trustworthy strategies, which are quantified by effectiveness scores.

The popularity of machine learning algorithms produced numerous applications in computer vision in the past 10 years. One application is art authentication, which assures that a piece of art is created by an artist. The models produced by machine learning algorithms provide an objective measure to authenticate an artist to their artwork collection. This article discusses an experiment using the residual neural network machine learning algorithm. This experiment demonstrates how a computer can distinguish between 34 and 958 artists with various degrees of confidence.

Action rule mining is an important technology that can be applied to build recommender systems for reducing customer churn. Confidence, support, and coverage are used to measure the quality of action rules. In practice, action rules with higher confidence and support are more useful to users. However, there is little research work focused on improving the quality of the discovered action rules. To improve the quality of action rules extracted from a given client, this article proposes a guided (by threshold) agglomerative clustering algorithm by utilizing the knowledge extracted from semantically similar clients. The idea is to pick up only such clients that are doing better in business than the given client and are semantically similar with the given client. By doing that, the given client can follow business recommendations from the better-performing clients. The algorithm is guided by the threshold value checking how large the improvement of action rules discovered so far in their confidence is. If the improvement is lower than this threshold, the algorithm stops.

Introduction Multiple abortions are consistently associated with adverse health consequences. Prior abortion is a known risk factor for another abortion. Objective To determine the persistence of the association of a first-pregnancy abortion with the likelihood of subsequent pregnancy outcomes. Methods Data was extracted for a study population of 5453 continuously eligible Medicaid beneficiaries in states which funded and reported elective abortions 1999–2015. Women age 16 in 1999 were organized into three cohorts based upon the first pregnancy outcome: abortion, birth, natural loss. Results Women in the abortion cohort are more likely than those in the birth cohort to experience another abortion rather than a birth or natural loss, and less likely to experience a live birth rather than an abortion or natural loss, for every subsequent pregnancy. The tendency toward abortion (OR 2.99, CL 2.02-4.43) and away from birth (OR 0.49, CL 0.39-0.63) peaks at the sixth pregnancy, but persists throughout the reproductive period ages 16–32. The pattern is reversed, but similarly consistent, for women in the birth cohort. They remain likelier to have another birth rather than an abortion or natural loss in subsequent pregnancies. Compared to the birth cohort, the abortion cohort had 1.35 times as many pregnancies: 4.31 times the abortions, 1.53 times the natural losses, but only 0.52 times the births. They were 4.3 and 5.0 times as likely to have 2-plus and 3-plus abortions, but only 0.47 times and 0.31 times as likely to have 2-plus and 3-plus births. Of the abortion cohort, 37.1% had no births. By contrast, 73.6% of the birth cohort had no abortions. Conclusion The first-pregnancy abortion maintains a strong and persistent association with the likelihood of another abortion in subsequent pregnancies, enabling a cascade of adverse events associated with multiple abortions.

The catalogue raisonné compiled by art scholars holds information about an artist’s work such as a painting’s image, medium, provenance, and title. The catalogue raisonné as a tangible asset suffers from the challenges of art authentication and impermanence. As the catalogue raisonné is born digital, the impermanence challenge abates, but the authentication challenge persists. With the popularity of artificial intelligence and its deep learning architectures of computer vision, we propose to address the authentication challenge by creating a new artefact for the digital catalogue raisonné: a digital classification model. This digital classification model will help art scholars with new artwork claims via a tool that authenticates a proposed artwork with an artist. We create this tool by training a machine learning model with 90 artists having at least 150 artworks and achieve an accuracy of 87.31%. We use the ResNet Convolutional Neural Network to improve accuracy and number of artist classes over state-of-the-art artist classification experiments using the WikiArt database. We address inconsistencies in the way scholars approach artist classification by providing a consistent method to recreate our dataset and providing a consistent method to calculate performance metrics based on imbalanced data.

The popularity of machine learning algorithms produced numerous applications in the past ten years. One application is that of art authentication which assures that a piece of art is created by an artist. A certificate of authenticity created from proper art authentication significantly increases the value of a piece of art which impacts all parties in an art transaction. The models produced by machine learning algorithms provide an objective measure to authenticate an artist to their artwork collection. In the past ten years numerous machine learning algorithms have been used to address art authentication on a variety of datasets. Our work extends art authentication with residual neural networks and the Rijksmuseum data set. Our results show contributions is four key areas: A performance increase of 21% over the baseline for 958 artists; A new baseline for 1,199 artists; A standard methods for recreating the Rijksmuseum data set; and A standard method for measuring results from imbalanced data for the Rijksmuseum data set.

This paper considers decision systems (see [6]) with decision attributes which are hierarchical. Atomic queries are built only from values of decision attributes. Queries are constructed from atomic queries the same way as we construct terms in logic using functors {+, *, -.}. Negation symbol "-." is only used on the atomic level. Queries are approximated by terms built from values of classification attributes. We only consider rule-based classifiers as the approximation tool for queries. When a user query fails, then the cooperative module of the query answering system (QAS) constructs its smallest generalization which does not fail and which is approximated by rules of the highest confidence discovered by the classifier. Two interpretations of queries are proposed: user-based and system-based. They are used to introduce the precision and recall of QAS. The implementation of QAS follows system-based interpretation. Automatic indexing of music by instruments and their types is an example of the application area for the proposed approach.

This research proposes a novel strategy for constructing a knowledge-based recommender system (RS) based on both structured data and unstructured text data. We present its application to improve the services of heavy equipment repair companies to better adjust to their customers’ needs. The ultimate outcome of this work is a visualized web-based interactive recommendation dashboard that shows options that are predicted to improve the customer loyalty metric, known as Net Promoter Score (NPS). We also present a number of techniques aiming to improve the performance of action rule mining by allowing to have convenient periodic updates of the system’s knowledge base. We describe the preprocessing-based and distributed-processing-based method and present the results of testing them for performance within the RS framework. The proposed modifications for the actionable knowledge miner were implemented and compared with the original method in terms of the mining results/times and generated recommendations. Preprocessing-based methods decreased mining by 10–20×, while distributed mining implementation decreased mining timesby 300–400×, with negligible knowledge loss. The article concludes with the future directions for the scalability of the NPS recommender system and remaining challenges in its big data processing.

Background Tinnitus, known as “ringing in the ears”, is a widespread and frequently disabling hearing disorder. No pharmacological treatment exists, but clinical management techniques, such as tinnitus retraining therapy (TRT), prove effective in helping patients. Although effective, TRT is not widely offered, due to scarcity of expertise and complexity because of a high level of personalization. Within this study, a data-driven clinical decision support tool is proposed to guide clinicians in the delivery of TRT. Methods This research proposes the formulation of data analytics models, based on supervised machine learning (ML) techniques, such as classification models and decision rules for diagnosis, and action rules for treatment to support the delivery of TRT. A knowledge-based framework for clinical decision support system (CDSS) is proposed as a UI-based Java application with embedded WEKA predictive models and Java Expert System Shell (JESS) rule engine with a pattern-matching algorithm for inference (Rete). The knowledge base is evaluated by the accuracy, coverage, and explainability of diagnostics predictions and treatment recommendations. Results The ML methods were applied to a clinical dataset of tinnitus patients from the Tinnitus and Hyperacusis Center at Emory University School of Medicine, which describes 555 patients and 3,000 visits. The validated ML classification models for diagnosis and rules: association and actionable treatment patterns were embedded into the knowledge base of CDSS. The CDSS prototype was tested for accuracy and explainability of the decision support, with preliminary testing resulting in an average of 80% accuracy, satisfactory coverage, and explainability. Conclusions The outcome is a validated prototype CDS system that is expected to facilitate the TRT practice.

In recent years, healthcare spending has risen and become a burden on many governments.There are multiple reasons for this increase such as overtesting, long medical treatment path, ignoring doctors' orders, ineffective use of technologies, medical errors, many hospital readmissions, unnecessary emergency room (ER) visits, and medical treatment acquired side effects and infections.The first part of this editorial presents Healthcare Cost and Utilization Project (HCUP) datasets and their hierarchical partition used to build hierarchically structured personalized recommendation systems in healthcare domain.The second part outlines a simple strategy for reducing the number of readmissions using the concept of action rules to provide recommendations.First, we extract from HCUP datasets all possible procedure paths (course of treatments) for a given initial medical procedure.Then, we cluster patients according to the similarities in their diagnoses in order to increase the predictability of the course of treatment following this initial procedure.Finally, we present a novel algorithm that provides recommendations (actionable knowledge) to the physicians to put patients on a treatment path that would result in optimal reduction of the number of readmissions for these patients.There is not much research done on decreasing the number of readmissions to hospitals after initial procedure and almost none based on action rules.