Learning Capacity Research Articles

Point cloud geometry compression with sparse cascaded residuals and sparse attention

AbstractEffective compression of point clouds is essential for implementing virtual and mixed reality applications, which require encoding millions or even tens of millions of points. This paper offers a new geometric compression for point clouds based on sparse cascaded residuals and sparse attention. A sparse cascaded residual module is posited to connect multiple residual modules through shortcuts, thereby augmenting the network's learning capacity and compression efficacy. The authors developed a sparse attention module to acquire global features by computing interdependencies among points, enhancing compression performance to a greater extent. Trade‐off parameters are employed to optimize the rate and distortion. The authors’ method outperforms the state‐of‐the‐art open‐source method regarding rate‐distortion on the ShapeNet, ModelNet, and Microsoft Voxelized Upper Bodies datasets, with average bjøntegaard‐delta (BD)‐rate gains of −14.44% and −15.38%.

A Prospective Study of Machine Learning-Assisted Radiation Therapy Planning for Patients Receiving 54 Gy to the Brain

PurposeThe capacity for machine learning (ML) to facilitate radiotherapy (RT) planning for primary brain tumors has not been described. We evaluated ML-assisted RT planning with regards to clinical acceptability, dosimetric outcomes and planning efficiency for adults and children with primary brain tumours. Methods and MaterialsIn this prospective study, children and adults receiving 54 Gy fractionated radiotherapy for a primary brain tumor were enrolled. For each patient, one ML-assisted RT plan was created and compared with one or two plans created using standard (“manual”) planning procedures. Plans were evaluated by the treating oncologist, who was blinded to the method of plan creation. The primary endpoint was the proportion of ML plans that were clinically acceptable for treatment. Secondary endpoints included the frequency with which ML plans were selected as preferable for treatment, and dosimetric differences between ML and manual plans. ResultsA total of 116 manual plans and 61 ML plans were evaluated across 61 patients. Ninety-four percent of ML plans and 93% of manual plans were judged to be clinically acceptable (p = 1.0). Overall, the quality of ML plans were similar to manual plans. ML plans comprised 34.5% of all plans evaluated, and were selected for treatment in 36.1% of cases (p = 0.82). Similar tumor target coverage was achieved between both planning methods. Normal brain (brain minus PTV) received an average of 1 Gy less mean dose with ML plans (as compared to manual plans, p < 0.001). ML plans required an average of 45.8 minutes less time to create, as compared with manual plans (p < 0.001). ConclusionML-assisted automated planning creates high-quality plans for patients with brain tumours, including children. Plans created with ML assistance delivered slightly less dose to normal brain tissues, and can be designed in less time.

Deriving relations at multiple levels of complexity following minimal instruction: A demonstration.

Recommendations for achieving generalized instructional outcomes often overlook the capacity for generative learning for most verbally competent humans. Four children (ages 5-8) participated in this project. In Study 1, we provided decontextualized discrete trial teaching to establish arbitrary relations between colors, pictures of characters, and researcher motor actions. All participants engaged in derivative responding, providing evidence of relational framing. Subsequently, we demonstrated that, with no additional instruction, these derivatives contributed to effective action within a socially valid context (i.e., Candyland gameplay). Study 2 extended the demonstration by teaching frames of opposition. Following teaching, all participants engaged in novel and contextually appropriate responding that entailed the derivation of both coordination and opposition between untrained stimuli. This outcome demonstrates how teaching simple relations can result in learning that manifests at higher levels of complexity (i.e., relational networking), providing some evidence that there can be socially valid benefits to decontextualized discrete trial instruction.

Unveiling the dynamics of self-regulated learning in project-based learning environments

Project-based learning (PBL) has been found to exert a positive influence on learners' academic achievements, while also fostering their intrinsic motivation and playing a crucial role in nurturing sustainable learning capacities. Understanding individual differences in self-regulated learning (SRL) within project-based foreign language learning can guide language teachers in delivering personalized instruction. This study utilized a blended learning management system to collect and analyze data on SRL from 95 learners enrolled in a project-based College English course. Through microanalysis, latent profile analysis (LPA), and epistemic network analysis (ENA), the study identified distinct learner profiles and traced their developmental trajectories in project-based language learning. The findings revealed that PBL facilitates the occurrence of SRL behaviors and strengthens connections across different regulation phases. Notably, learners with diverse profiles displayed variations in their SRL epistemic network structures and developmental trajectories. These results highlight the dynamic nature of SRL within the PBL context, underscoring the significance of considering individual differences and supporting learners’ evolving self-regulatory behaviors and strategies throughout their engagement in PBL activities. To enhance SRL in PBL, educators are encouraged to provide scaffolding support, promote help-seeking behaviors, and implement interventions targeting metacognitive processes and reflective practices.

Prototyping of Smart School Emergency Tents (SADAR) modular-based for post disaster recovery in education

Disasters in Indonesia caused damage to school facilities and their conversion into refugee camps, so that teaching and learning activities were disrupted. Meanwhile, students still need learning activities such as trauma healing and post-disaster learning continuity. Emergency tents that are not yet effective and efficient do not fulfill the eligibility criteria for teaching and learning activities regarding safety, comfort and conduciveness. They have not utilized alternative energy to support learning activities. A hampered learning system can reduce learning capacity and delay the delivery of material to students. This research aims to create innovations related to post-disaster recovery in the education sector so that learning activities are not disrupted due to disasters. The research method applied is R&D (Research and Development) with a 4D model (Define, Design, Develop and Disseminate). The result of this research is a Smart Emergency School Tent (SADAR) Prototype Model with an effective and efficient installation design. This modular tent uses polycrystalline type solar panels as its power source and a knock-down multifunctional portable table that can be used as a table and bed. The emergency school tent design innovation is made flexible, structured, and can function as trauma healing for students.

TRANSLANGUAGING: STUDENTS AS MEANING MAKING CONTRIBUTORS

Contrary to Communicative Language Teaching ideology, translanguaging exploits the collective linguistic output that potentially adds to the language learning capacity of learners. It has emerged as an empowering tool for bi/multilingual learners of a language. The following research questions will be asked: 1) How can translanguaging enrich students’ writing skills in the Target Language (TL)? 2) What are the drawbacks that may be encountered? 3) How does translanguaging go beyond the conventional approach to classroom learning? The study will focus on the mixed method approach employing a semi structured questionnaire and interviews. Anderson’s (2017 as cited in Turnbull, 2019) translanguaging continuum will be used as a reference point for this research. The results will be collated to examine the difference in responses and to see which strategy produces more favourable outcomes. This study will help to legitimize the use of translanguaging in the classroom as a means of maximizing students' potential of meaning-making activity.&#x0D;

A joint autoencoder and classifier deep neural network for AD and MCI classification

AbstractIn this article, we present a new approach to distinguish progressive mild cognitively impaired (pMCI) subjects, who eventually develop Alzheimer's disease (AD) from stable MCI (sMCI) subjects whose situation does not deteriorate into AD. The proposed approach combines the discriminating capabilities of classifiers and representation learning capacities of autoencoders into a unified architecture, and is hence termed as joint autoencoder and classifier deep neural network (JACDNN). JACDNN employs a single classifier and multiple autoencoders that are trained together to perform pattern classification. The classifier in JACDNN is trained using standard approaches to distinguish between subject from different classes using the binary cross entropy loss. The autoencoders in JACDNN, regularizes individual layers in the network used for classification to learn representations useful for reconstructing a given input. The performance of JACDNN has been evaluated on several machine learning problems pertaining to dementia, namely AD versus cognitively normal (CN) subjects, AD versus sMCI, CN versus pMCI, and pMCI versus sMCI. These problems are targeted using two datasets. The first dataset consist of gray matter (GM) features of subjects and the second dataset consist of combination of GM and white matter (WM) features. It is observed that better classification results are obtained when the classifier is built on GM and WM as compared with GM features alone. Performance comparison of JACDNN with other existing approaches has been conducted for these problems. The results clearly indicate that JACDNN performs better than other existing approaches for these problems.

Advancing Ultrasonic Defect Detection in High-Speed Wheels via UT-YOLO.

In the context of defect detection in high-speed railway train wheels, particularly in ultrasonic-testing B-scan images characterized by their small size and complexity, the need for a robust solution is paramount. The proposed algorithm, UT-YOLO, was meticulously designed to address the specific challenges presented by these images. UT-YOLO enhances its learning capacity, accuracy in detecting small targets, and overall processing speed by adopting optimized convolutional layers, a special layer design, and an attention mechanism. This algorithm exhibits superior performance on high-speed railway wheel UT datasets, indicating its potential. Crucially, UT-YOLO meets real-time processing requirements, positioning it as a practical solution for the dynamic and high-speed environment of railway inspections. In experimental evaluations, UT-YOLO exhibited good performance in best recall, mAP@0.5 and mAP@0.5:0.95 increased by 37%, 36%, and 43%, respectively; and its speed also met the needs of real-time performance. Moreover, an ultrasonic defect detection data set based on real wheels was created, and this research has been applied in actual scenarios and has helped to greatly improve manual detection efficiency.

Revolutionizing Regulatory Reporting through AI/ML: Approaches for Enhanced Compliance and Efficiency

In the intricate regulatory landscape of today, financial institutions encounter formidable hurdles in meeting reporting mandates while upholding operational efficacy. This study delves into the transformative capacity of Artificial Intelligence (AI) and Machine Learning (ML) technologies in refining regulatory reporting procedures. Through harnessing AI/ML, entities can streamline data aggregation, analysis, and submission, thus fostering enhanced compliance and operational efficiency. Key strategies for integrating AI/ML into regulatory reporting frameworks are discussed, encompassing data standardization, predictive analytics, anomaly detection, and automation. Furthermore, the paper explores the advantages, obstacles, and optimal approaches associated with deploying AI/ML solutions in regulatory reporting. Drawing on real-world illustrations and case studies, this study offers insights into how AI/ML technologies can redefine regulatory reporting practices, empowering financial institutions to adeptly navigate regulatory intricacies while optimizing resource allocation and decision-making processes.

Revolutionizing Regulatory Reporting through AI/ML: Approaches for Enhanced Compliance and Efficiency

ISSN: 3006-4023 (Online), Vol. 2, Issue 1Journal of Artificial Intelligence General Science (JAIGS)journal homepage: https://ojs.boulibrary.com/index.php/JAIGSRevolutionizing Regulatory Reporting through AI/ML: Approaches forEnhanced Compliance and EfficiencyHarish Padmanaban Ph.D.Site Reliability Engineering lead and Independent Researcher.AbstractIn the intricate regulatory landscape of today, financial institutions encounter formidable hurdles in meeting reportingmandates while upholding operational efficacy. This study delves into the transformative capacity of ArtificialIntelligence (AI) and Machine Learning (ML) technologies in refining regulatory reporting procedures. Throughharnessing AI/ML, entities can streamline data aggregation, analysis, and submission, thus fostering enhancedcompliance and operational efficiency. Key strategies for integrating AI/ML into regulatory reporting frameworksare discussed, encompassing data standardization, predictive analytics, anomaly detection, and automation.Furthermore, the paper explores the advantages, obstacles, and optimal approaches associated with deploying AI/MLsolutions in regulatory reporting. Drawing on real-world illustrations and case studies, this study offers insights intohow AI/ML technologies can redefine regulatory reporting practices, empowering financial institutions to adeptlynavigate regulatory intricacies while optimizing resource allocation and decision-making processes.

Trustworthy multi-view clustering via alternating generative adversarial representation learning and fusion

Multi-view clustering (MVC) has attached extensive attention as it provides an effective approach to deal with the unlabeled data in real-world applications. To enjoy the strong feature extraction capacity of deep learning, traditional shallow MVC methods are further extended to deep version. Though achieve superiorities in many fields, most existing deep MVC models are still limited by their lacking assurance of the trustworthiness and robustness. This drawback also leads to the possible poor clustering performance. To tackle this drawback, we propose an alternating generative adversarial learning strategy based network, termed as Alternating Generative Adversarial Representation Learning (AGARL) network for multi-view clustering, aiming to drive different views to fall into the same semantic space for the further alignment and information fusion. Various from the traditional generative adversarial learning strategy, the proposed alternating adversarial representation learning strategy successes in further aligning the distributions of the view-specific representations and exploring the cross-view consistency credited by its setting each view as the reference alternately. Then a consensus representative latent representation can be learned through an attention-like sub-network for all views. Finally, a self-supervised clustering module is employed in the proposed network to guide the learning of cluster assignment. In addition, comprehensive experiments on numerous benchmark MVC datasets have been performed to demonstrate the effectiveness of the proposed network compared to other state-of-the-art methods.

HYPOTHETICAL LEARNING TRAJECTORY BASED ON ETHNOMATHEMATICS

Ethnomathematics is the study of the relationship between mathematics and culture. The culture in question is related to the habits of human behavior in their environment. It is intended that through ethnomathematics, students can better understand mathematical concepts and their culture so as to create meaningful learning. It is important for teachers to develop a mathematics learning model that is meaningful to students from the aspects of content and process. One of the efforts that can be made is to design an ethnomathematics-based Hypothetical Learning Trajectory (HLT) in mathematics learning. The method used in writing this article is literature review. Based on supporting theories, it can be concluded that HLT is a learning design that includes student learning activities based on initial understanding abilities and student characteristics to achieve higher understanding abilities. HLT consists of three components, namely learning objectives, learning activities and learning process hypothesis. HLT in material form is in the form of context and content related to culture-based environment. Developing ethnomathematics-based HLT means using cultural values contextually by considering learning obstacles, material linkages, learning stages that are in accordance with students' thinking abilities, methods used by students and the carrying capacity of learning.

Comparative Analysis of Deep Learning Models for Olive Detection on the Branch

The future of deep learning integration in agriculture holds great potential for advancing sustainable agricultural practices, precision agriculture and improved decision-making. With the rapid development of image processing and artificial intelligence technologies in recent years, deep learning has begun to play a major role in identifying agricultural pests and optimizing agricultural product marketing. However, there are challenges related to data quality, model scalability, and geographical limitations for widespread adoption of deep learning in agriculture. This study on Olive was conducted to improve the quality of the data set and to ensure more reliable training of object detection models. According to the result of the training process of YOLOv7 used in the study, it was concluded that it was characterized by decreasing loss values and showed an increase in the model's ability to detect objects correctly. It was observed that the other model, YOLOv8l, had a more effective learning capacity and a tendency to learn faster. The performance of both models was evaluated with various metrics, and it was determined that YOLOv8l had higher Precision, Recall, and mAP values. It was emphasized that YOLOv8l showed high performance even in low epoch numbers and can be preferred especially in cases where time and computational resources were limited. It was determined that YOLOv7 made detections in a wide confidence range, but had difficulty in detections with low confidence scores. It was observed that YOLOv8l made more stable and reliable detections with higher confidence scores. The metric data of the "YOLOv8l" model was found to be higher compared to other models. The F1 score of the YOLOv5l model was 92.337%, precision 96.568%, recall %88,462,mAP@0.5:0.65 value gave the highest score with 94.608%. This research on deep learning-based object detection models indicated that YOLOv8l showed superior performance compared to YOLOv7 and was a more reliable option for agricultural applications.

How does rapid internationalization explain emerging-market multinationals' innovation? The moderating role of organizational capacity

PurposeThe purpose of this study is to investigate the impact of rapid internationalization by emerging-market multinational enterprises (EMNEs) on their innovation performance. It also seeks to identify any potential moderating factors that could influence this relationship.Design/methodology/approachBy analyzing data from listed Chinese MNEs from 2012 to 2022, this study applies a negative binomial regression model to test the research hypotheses.FindingsThis study uncovers an inverted U-shaped relationship between the internationalization speed of EMNEs and their innovation performance. It also suggests that strong absorptive, learning and managerial capacities could play positive moderating roles in the effect of internationalization speed on EMNEs’ innovation performance.Originality/valueThis study highlights rapid global expansion, promoting new knowledge acquisition for EMNEs. However, due to time-compression dilemmas with limited EMNE firm-specific advantages, overly accelerated internationalization hinders learning effectiveness. Additionally, this study reveals the critical importance of three firm-specific capacities in EMNEs – absorptive, learning and managerial capacities – in efficiently assimilating newly acquired knowledge from foreign markets and enhancing their innovation performance through rapid internationalization.

Analysis of the user experience (On site vs. Virtual Reality) through biological markers and cognitive tests in museums: the case of Museo Cristo de la Sangre (Murcia, Spain)

Digital technologies have changed almost every aspect of our lives, including the way we access heritage. Following the pandemic caused by COVID-19 and the technological evolution of recent years, museums and institutions, among others, have changed the way they display their collections, taking a greater interest in new technologies, platforms and digital software. This technological boom finds its greatest transformation with the implementation of Virtual Reality (VR) and Metaverse in the museum sector. This article shows the concrete influence of VR/Metaverse in a museum room previously digitised through different techniques. Subsequently, the impact over user experience in the VR scenario versus on-site visit has been measured. In parallel, to measure the enzyme alpha-amylase in saliva, a cognitive test and usability test (SUS) were carried out to determine the learning capacity and degree of satisfaction obtained with experience alongside the room of the Museo de la Sangre in Murcia (Spain).

A Procedural Constructive Learning Mechanism with Deep Reinforcement Learning for Cognitive Agents

Recent advancements in AI and deep learning have created a growing demand for artificial agents capable of performing tasks within increasingly complex environments. To address the challenges associated with continuous learning constraints and knowledge capacity in this context, cognitive architectures inspired by human cognition have gained significance. This study contributes to existing research by introducing a cognitive-attentional system employing a constructive neural network-based learning approach for continuous acquisition of procedural knowledge. We replace an incremental tabular Reinforcement Learning algorithm with a constructive neural network deep reinforcement learning mechanism for continuous sensorimotor knowledge acquisition, thereby enhancing the overall learning capacity. The primary emphasis of this modification centers on optimizing memory utilization and reducing training time. Our study presents a learning strategy that amalgamates deep reinforcement learning with procedural learning, mirroring the incremental learning process observed in human sensorimotor development. This approach is embedded within the CONAIM cognitive-attentional architecture, leveraging the cognitive tools of CST. The proposed learning mechanism allows the model to dynamically create and modify elements in its procedural memory, facilitating the reuse of previously acquired functions and procedures. Additionally, it equips the model with the capability to combine learned elements to effectively adapt to complex scenarios. A constructive neural network was employed, initiating with an initial hidden layer comprising one neuron. However, it possesses the capacity to adapt its internal architecture in response to its performance in procedural and sensorimotor learning tasks, inserting new hidden layers or neurons. Experimentation conducted through simulations involving a humanoid robot demonstrates the successful resolution of tasks that were previously unsolved through incremental knowledge acquisition. Throughout the training phase, the constructive agent achieved a minimum of 40% greater rewards and executed 8% more actions when compared to other agents. In the subsequent testing phase, the constructive agent exhibited a 15% increase in the number of actions performed in contrast to its counterparts.

Digital, Self-Regulated Vocabulary Learning and Device Control In Out-Of-Class, Higher Education Settings

Self-regulation of learning behaviour is particularly important when it comes to vocabulary learning for academic purposes in a second language because it often needs to be done on a regular and consistent basis and mostly in out-of-class, self-directed settings to be successful. Self-regulation is also vital when this learning takes place using digital activities on smartphones because these are now ubiquitous devices and deeply embedded in both daily life and higher education settings. Features such as notifications from social media applications can end up distracting students from their academic tasks unless they have the capacity to manage and control their behaviour. This naturalistic, mixed methods study conducted with students on an academic English foundation course in a higher education context aimed to measure their capacity for self-regulated vocabulary learning through technology before and after 10 weeks of intentional digital vocabulary learning in out-of-class settings and to see if there was any difference between learning on a laptop and a smartphone. The purpose of this study was to find out if device control was a relevant dimension of self-regulation, which is an under-researched area. The study collected quantitative data through a recently developed self-report survey tool, and differences in scores were measured using Wilcoxon signed-rank tests. Qualitative data was also collected from students through paired-depth interviews, and this was analysed using typological analysis. The results revealed that the students’ self-reported capacity for self-regulated vocabulary learning through laptops was significantly higher than their capacity for self-regulated vocabulary learning through smartphones. In addition, commitment regulation when using a smartphone decreased significantly over the 10-week period primarily due to distractions from social media notifications. At the same time, students were aware of when to use each device for different types of learning activities and under different temporal and spatial conditions. Overall, this study showed that device control should be considered an additional dimension of a model of digital, self-regulated vocabulary learning and should also be incorporated into future research in the field of e-learning. In addition, students in higher education need to be given more guidance about the benefits and drawbacks of different devices and how to develop their capacity and strategies for greater device self-regulation.

Improving student success and retention in first-year nursing through embedded tutor support

BackgroundNursing students from diverse or equity backgrounds are less likely to possess the required skills to ensure success in their studies. This research explores the impact of embedded support on student learning in a first-year foundational subject, Contexts of Nursing, in an undergraduate nursing degree.t. MethodsThe Embedded Tutor Program offers specialised tutoring support for first-year undergraduate students. Embedded tutors, with backgrounds as registered nurses and academics, provided online one-on-one feedback to students on draft assessment tasks. Outreach contact was provided to students at risk of failing. A Pearson's Chi-squared test was used to assess the impact of tutor support on grade distribution and a paired student t-test was used to assess the difference in cumulative marks for students from equity backgrounds. Statistical significance was set at p < 0.05. Feedback provided by students, tutors and staff in an online anonymous survey was thematically analysed. ResultsThere was a significant grade shift for the 267 students who met with an embedded tutor (p < 0.05). Students who were a member of an Australian Government identified equity group had a significant increase in their cumulative mark if they met with a tutor of 9–17 % (p < 0.05). This improvement in cumulative mark was maintained for students with cumulative equity factors. The overwhelming majority of students who were identified as at risk of failing and met with a tutor following outreach support received a passing grade. Students reported growing skills and confidence in academic literacy was a key benefit of the program. ConclusionA shared approach to delivering education has a positive effect on the experience of learning. The combined efforts of the subject convenor, embedded tutors, and extended student service roles within the University resulted in outcomes that were positive for student learning. Determining student capacity for learning extended beyond a student's consideration of grades or their progression in the program to include the development of self-efficacy.

Developing indicators for a new principal induction program in Taiwan using the fuzzy delphi method

ABSTRACT Quality induction initiatives can mitigate burnout, turnover, and shortage challenges in global education systems. Increasing the relevance of induction programs for new principals is imperative. However, systematic program evaluations lack comprehensive tools. This study aims to construct assessment indicators for the Taipei Induction Program for New Principals (IPNP) using mixed methods. Six capacity-building dimensions and 52 indicators were developed through qualitative interviews, expert consensus, and the Fuzzy Delphi Method. Survey results showed positive perceptions of program effectiveness, particularly regarding communication, learning, and execution capacities. However, dimensions related to professionalism and accountability require further refinement. This study’s contribution lies in providing a comprehensive assessment tool for program providers and enhancing novice principal induction programs. By addressing a critical gap in systematic evaluation, this research contributes to the enhancement of principal development programs. Future research could prioritize indicators and delve into real-life experiences, further refining the design and implementation of effective induction programs.

A comprehensive review on heart disease prognostication using different artificial intelligence algorithms

Prediction of heart diseases on time is significant in order to preserve life. Many conventional methods have taken efforts on earlier prediction but faced with challenges of higher prediction cost, extended time for computation and complexities with larger volume of data which reduced prediction accuracy. In order to overcome such pitfalls, AI (Artificial Intelligence) technology has been evolved in diagnosing heart diseases through deployment of several ML (Machine Learning) and DL (Deep Learning) algorithms. It improves detection by influencing with its capacity of learning from the massive data containing age, obesity, hypertension and other risk factors of patients and extract it accordingly to differentiate on the circumstances. Moreover, storage of larger data with AI greatly assists in analysing the occurrence of the disease from past historical data. Hence, this paper intends to provide a review on different AI based algorithms used in the heart disease prognostication and delivers its benefits through researching on various existing works. It performs comparative analysis and critical assessment as encompassing accuracies and maximum utilization of algorithms focussed by traditional studies in this area. The major findings of the paper emphasized on the evolution and continuous explorations of AI techniques for heart disease prediction and the future researchers aims in determining the dimensions that have attained high and low prediction accuracies on which appropriate research works can be performed. Finally, future research is included to offer new stimulus for further investigation of AI in cardiac disease diagnosis.