Search

With the rapid development of information technology, the field of education is undergoing a profound change, in which intelligent hybrid learning and virtual reality technology are increasingly valued. This study proposes an intelligent hybrid learning method based on virtual reality for student performance improvement. This paper reveals the limitations of traditional learning methods in meeting the needs of modern education, and expounds the theoretical basis of intelligent hybrid learning and virtual reality technology. This paper collects and processes a large amount of learning data, based on which a new model of student learning performance prediction is established. The verification results of the model show that the model in this study has excellent performance in predicting students' learning performance. This paper gives some suggestions for future educational practice and research. In general, this study provides a new learning method for the field of education and has important reference value for education reform and teaching practice. [ABSTRACT FROM AUTHOR]

Teaching and learning in higher education have increasingly become digitalized and associated with innovative pedagogical methodologies over the past decades. Following the sudden onset of the pandemic in March 2020, several studies tended to focus on traditional students' experiences with emergency remote education while literature is scarce on non‐traditional students (or adult learners) pedagogical experiences in Distance Education contexts. Using a qualitative case study approach, this study explored how digital technologies mediated instructors' and adult learners' educational experiences during COVID‐19 and their first‐time experiences with blended learning. Between October 2021 and July 2022, semi‐structured interviews were conducted with 40 adult learners and 20 instructors in three selected public higher education institutions (HEIs) in Ghana. Data analysis followed Braun and Clarke's (2012) thematic analysis approach. The results showed that the transition to blended learning was supported by the adoption and integration of varied virtual online technologies. The themes highlight the positive and negative impacts of technology in mediating the educational experiences of instructors and adult learners in blended learning environments. The themes which reflected both instructors' and adult learners' experiences were enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Blended learning facilitated by technology could be the ‘new normal learning’ post‐pandemic for adult learners pursuing Distance Education in Ghana. The study recommends the implementation of agile strategies and policies by HEIs to ensure sustainable quality education in distance learning. Practitioner notes What is already known about this topic The COVID‐19 pandemic necessitated the adoption of innovative pedagogical approaches in higher education contexts. Technological transformations in information and communication technology (ICT) have enhanced remote teaching in higher education institutions globally. The educational experiences of educators and learners differ in blended learning contexts. What this paper adds Instructors and adult learners' positive experiences with navigating a variety of web‐based technologies during the educational process are negatively impacted by technological difficulties during online instruction. Participants' experiences of blended learning are mixed with a preference for face‐to‐face dimension of blended learning instead of the online dimension. The paper identifies four themes that characterize instructors and adult learners' experiences with technology‐enhanced learning including enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Implications for practice and/or policy The study provides evidence‐based information on the relevance of digitizing distance education for sustainable development and promotion of lifelong learning opportunities for distance education students. The research recommends that higher education institutions (HEIs) implement agile policies to facilitate a seamless shift to distance learning. HEIs may adopt open distance learning frameworks to streamline 21st century pedagogical and learning practices in distance‐blended learning environments for quality course instruction. The study highlights the potential distance learning modalities that HEIs can consider for Distance Education students to sustain effective quality teaching and learning. What is already known about this topic The COVID‐19 pandemic necessitated the adoption of innovative pedagogical approaches in higher education contexts. Technological transformations in information and communication technology (ICT) have enhanced remote teaching in higher education institutions globally. The educational experiences of educators and learners differ in blended learning contexts. What this paper adds Instructors and adult learners' positive experiences with navigating a variety of web‐based technologies during the educational process are negatively impacted by technological difficulties during online instruction. Participants' experiences of blended learning are mixed with a preference for face‐to‐face dimension of blended learning instead of the online dimension. The paper identifies four themes that characterize instructors and adult learners' experiences with technology‐enhanced learning including enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Implications for practice and/or policy The study provides evidence‐based information on the relevance of digitizing distance education for sustainable development and promotion of lifelong learning opportunities for distance education students. The research recommends that higher education institutions (HEIs) implement agile policies to facilitate a seamless shift to distance learning. HEIs may adopt open distance learning frameworks to streamline 21st century pedagogical and learning practices in distance‐blended learning environments for quality course instruction. The study highlights the potential distance learning modalities that HEIs can consider for Distance Education students to sustain effective quality teaching and learning. [ABSTRACT FROM AUTHOR]

This paper discusses key themes of the 15th biennial conference of the Association for Language Awareness (2020), with a focus on increasing digital engagement in language education. The COVID-19 pandemic occasioned an abrupt transition to emergency remote language teaching and learning (ERLTL) worldwide. The ALA 2020 conference was also affected by this transition; originally planned as a located conference in Geelong, Australia, it was eventually held online, a first in ALA's conference history. The current paper engages with contemporary debates of language teaching and learning in two ways. Firstly, it traces recent discussions by presenting key findings from five papers given at the conference, and secondly, via a scoping review of literature focusing on critical lessons from the pandemic regarding language teaching and learning. The review captures recent research from the Australasian region. Key debates identified in the literature include the needs of teachers and learners during the transition to online learning, and how student engagement was affected. The literatures highlight that both educators and students have been developing new practices in teaching and learning resulting from the shift to online and blended modes, which may continue to shape language education and new pedagogies in the future. The 15th Conference of the Association for Language Awareness (ALA) was hosted online in late 2020 from Melbourne, Australia after the global pandemic had disrupted travel. In this paper, we present five papers from the conference and a literature review. The conference theme addressed how language teaching and learning are changing because of digital practices. The papers included focus on two main themes. The first theme relates to current beliefs and perceptions of educators about languages and language teaching. A second theme considers how the development of language awareness can be supported in the classroom, and with digital tools. The scoping review of literature contributes to these debates by examining findings from recent studies investigating the effects of the pandemic on language teaching and learning. This research snapshot focuses on the Australasian region where the conference was remotely hosted and where the authors of the current paper live and work. The Australasian region is also considered as one of the regions where the strictest lockdowns in the world were imposed, with far-reaching effects on teaching, learning, and research. We conclude with implications of the changes for language teaching and learning after the pandemic, and for the development of critical language awareness. [ABSTRACT FROM AUTHOR]

Generating data from small group interviews with 41 boys aged 10–11 years from two London schools in 2022, this paper contributes to the field of gender by introducing a new form of non‐hegemonic and positive masculinity, which I am calling 'blended' masculinity, and which was the most common formation in each school. Although its features differed a little in each setting, this blended formulation broadly consisted of orthodox qualities of masculinity (e.g. athleticism, assertiveness, confidence, independence), combined with feminine‐associated traits (e.g. kindness, caring, sociability, emotional literacy). I argue that this blended form is different from previous conceptualisations of hybrid masculinity in the gender literature and is more akin to recent conceptions of hybrid femininity. There were no dominant forms of masculinity with hierarchical connotations of superiority, and no hegemony that legitimated unequal relations, with obvious subordination of other masculinities or femininities. Boys and girls generally got on well with each other and there was also no evidence of homophobia or misogyny. The paper also explores notions of peer‐group popularity, which was based on a series of resources, and delineates the characteristics of a fictional, 'ideal', schoolboy, whose features and attributes were connected to the different versions of masculinity on show. [ABSTRACT FROM AUTHOR]

The preference for paper-based learning (traditional) or audio-visual learning (electronic) brought about hybrid learning whose preference among students is much greater due to the interaction with digital and audio-visual media. The general objective is to analyze and describe the experiences of university students on paper-based learning called traditional and audio-visual learning called e-learning, for which a quantitative descriptive and correlational methodology was used with a measurement instrument through an anonymous and voluntary survey with 1240 participants. The results have acceptable statistics and are demonstrated with the confirmatory factor analysis, showing the preference for hybrid learning. Conclusion, students request that universities implement this methodology (hybrid) to work properly and have a quality education in the future. [ABSTRACT FROM AUTHOR]

Police education and training, in common with education at all levels, was seriously affected by the onset of lockdown during the COVID-19 pandemic. Police organisations in England and Wales sought to cope by moving training and education programmes online, almost overnight. This paper presents findings from interviews conducted with Learning and Development leaders in 17 police forces in England and Wales to gauge the capacity of organizations to provide blended learning (BL) in the pre COVID period and plans for the future. Findings indicated that although there are challenges, the appetite and capacity to adopt BL methods in forces range on a spectrum. The paper and makes recommendations to support the rollout and use of BL in police education generally and proposes a theory of change to assist the introduction of BL in police organisations. [ABSTRACT FROM AUTHOR]

In this paper, we present the analysis of the students' achievements in learning calculus in a dynamic software environment during the Covid19 crisis. Two groups of students, the experimental and the control one, were monitored. Blended learning was applied to the students in the experimental group, with the help of Microsoft Teams and dynamic software GeoGebra, in autumn 2020. All students in the control group learned in the classroom without using GeoGebra in 2019. The comparison between these two groups of first-year students, regarding their calculus test results, is described in this paper. It is interesting that the results of the experimental group were significantly better than the results of students in the control group, despite the fact that the students from the experimental group learned during the Covid19 crisis. [ABSTRACT FROM AUTHOR]

Purpose: Higher education institutions (HEIs) seek innovative approaches to attract students. Since the COVID-19 pandemic, many HEIs have considered diversification through digitalization. From the initial urgency to implement technology at the start of the pandemic to a gradual acceptance over time, HEIs witnessed a shift in perceptions. This paper aims to explore the evolution of the use of technology in HEI classrooms from pre- to post-Covid-19 as seen through the eyes of students and faculty members. Design/methodology/approach: Seven surveys were conducted from March 2020 to January 2023 with faculty members and students at one business HEI in Switzerland. This longitudinal study analyzed the perceptions of faculty and students regarding technology in the ever-changing HEI environments. These results have been used to make practical recommendations for future HEI classroom settings. Findings: The findings reveal that the social aspect must be considered when implementing technology into HEIs. Faculty members and students need appropriate training and adequate resources to engage with the technology in and outside the classroom. The results suggest that one result of the pandemic was a greater acceptance of blended learning practices in traditional business education. Originality/value: The pandemic has left long-lasting effects on teaching and learning. While many HEIs revert to traditional ways, the authors suggest the need to embrace technology that encourages engagement and authentic teaching and learning. HEIs must listen to their faculty members and students, to create more innovative learning environments. [ABSTRACT FROM AUTHOR]

Creativity, driving environmentally sustainable fashion design through innovation, has become increasingly more important. From an educational perspective, enhancing students' creative design thinking processes, presents several challenges, especially in blended learning. This article addresses this concern and reports on the implementation of a blended learning teaching framework, applied to support students' positive emotions and creativity during an environmentally sustainable fashion design project that required innovative design solutions. The qualitative inquiry adopted a case study research design, involving undergraduate fashion design students at a tertiary institution in South Africa. Two key findings have emerged from the research. Firstly, the significant level of creativity required by the undertaken design project requires re-thinking of support for creative and innovative thinking. Secondly, a clearer understanding of the anxiousness caused when participants are faced with innovative design practices is needed to find suitable solutions. Based on the findings, this paper concludes with improvements presented in an amended framework. [ABSTRACT FROM AUTHOR]

Renewable microgrids enhance security, reliability, and power quality in power systems by integrating solar and wind sources, reducing greenhouse gas emissions. This paper proposes a machine learning approach, leveraging Gaussian Process (GP) and Krill Herd Algorithm (KHA), for energy management in renewable microgrids with a reconfigurable structure based on remote switching of tie and sectionalizing. The method utilizes Gaussian Process (GP) for modeling hybrid electric vehicle (HEV) charging demand. To counteract HEV charging effects, two scenarios are explored: coordinated and intelligent charging. A novel optimization method inspired by the Krill Herd Algorithm (KHA) is introduced for the complex problem, along with a self-adaptive modification to tailor solutions to specific situations. Simulation on an IEEE microgrid demonstrates efficiency in both scenarios. The predictive model yields a remarkably low Mean Absolute Percentage Error (MAPE) of 1.02381 for total HEV charging demand. Results also reveal a reduction in microgrid operation cost in the intelligent charging scenario compared to coordinated charging. [ABSTRACT FROM AUTHOR]

This paper presents a novel variant of the teaching–learning-based optimization algorithm, termed BLTLBO, which draws inspiration from the blended learning model, specifically designed to tackle high-dimensional multimodal complex optimization problems. Firstly, the perturbation conditions in the "teaching" and "learning" stages of the original TLBO algorithm are interpreted geometrically, based on which the search capability of the TLBO is enhanced by adjusting the range of values of random numbers. Second, a strategic restructuring has been ingeniously implemented, dividing the algorithm into three distinct phases: pre-course self-study, classroom blended learning, and post-course consolidation; this structural reorganization and the random crossover strategy in the self-learning phase effectively enhance the global optimization capability of TLBO. To evaluate its performance, the BLTLBO algorithm was tested alongside seven distinguished variants of the TLBO algorithm on thirteen multimodal functions from the CEC2014 suite. Furthermore, two excellent high-dimensional optimization algorithms were added to the comparison algorithm and tested in high-dimensional mode on five scalable multimodal functions from the CEC2008 suite. The empirical results illustrate the BLTLBO algorithm's superior efficacy in handling high-dimensional multimodal challenges. Finally, a high-dimensional portfolio optimization problem was successfully addressed using the BLTLBO algorithm, thereby validating the practicality and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Introduction: The increasing ageing of the population with growth in NCD burden in India has put unprecedented pressure on India's health care systems. Shortage of skilled human resources in health, particularly of specialists equipped to treat NCDs, is one of the major challenges faced in India. Keeping in view the shortage of healthcare professionals and the guidelines in NEP 2020, there is an urgent need for more health professionals who have received training in the diagnosis, prevention, and treatment of NCDs. This paper conducts a scoping review and aims to collate the existing evidence on the use of digital education of health professionals within NCD topics. Methods: We searched four databases (Web of Science, PubMed, EBSCO Education Research Complete, and PsycINFO) using a three-element search string with terms related to digital education, health professions, and terms related to NCD. The inclusion criteria covered the studies to be empirical and NCD-related with the target population as health professionals rather than patients. Data was extracted from 28 included studies that reported on empirical research into digital education related to non-communicable diseases in health professionals in India. Data were analysed thematically. Results: The target groups were mostly in-service health professionals, but a considerable number of studies also included pre-service students of medicine (n = 6) and nursing (n = 6). The majority of the studies included imparted online learning as self-study, while some imparted blended learning and online learning with the instructor. While a majority of the studies included were experimental or observational, randomized control trials and evaluations were also part of our study. Discussion: Digital HPE related to NCDs has proven to be beneficial for learners, and simultaneously, offers an effective way to bypass geographical barriers. Despite these positive attributes, digital HPE faces many challenges for its successful implementation in the Indian context. Owing to the multi-lingual and diverse health professional ecosystem in India, there is a need for strong evidence and guidelines based on prior research in the Indian context. [ABSTRACT FROM AUTHOR]

In this paper, we (a) share perspectives from stakeholders who learn and teach in an EdD program located in the United States that utilizes telepresence for distance learning (TDL) in a synchronous, hybrid environment, (b) frame our learning as a community of practice, and (c) report affordances and challenges of this model. TDL students asserted that the telepresence option gave them choice in selecting their doctoral program and increased their social presence and ability to be perceived as real people, and all students recognized the importance of a cohesive community to offer support through technological challenges. Faculty were largely unfamiliar with utilizing telepresence in the classroom initially and acknowledged that revised pedagogies and instructional methods were essential to supporting all students in this model. TDL affords opportunities to increase equity and access in doctoral education; however, technological and logistical challenges must be remediated to ensure a successful learning environment. [ABSTRACT FROM AUTHOR]

Personalized learning leverages technology and data analytics to provide customized and adaptive education based on individual student needs. This paper examines how machine learning techniques can predict student performance in order to enable personalized interventions and support. A systematic literature review of 16 most cited studies on forecasting student outcomes using machine learning is presented. Key findings show that online activity patterns, assessment grades, and affective factors strongly predict achievement. Regression, neural networks, and tree-based models demonstrate promising results. However, further research is needed on blended learning contexts, socialemotional skills, and model interpretability. Guidelines are provided for collection of quality data, algorithm selection, and ethical use of analytics. The paper establishes machine learning as an essential driver of personalized learning at scale. [ABSTRACT FROM AUTHOR]

Because defects in software modules (e.g., classes) might lead to product failure and financial loss, software defect prediction enables us to better understand and control software quality. Software development is a dynamic evolutionary process that may result in data distributions (e.g., defect characteristics) varying from version to version. In this case, effective cross‐version defect prediction (CVDP) is not easy to achieve. In this paper, we aim to investigate whether the defect prediction method of the threshold‐based active learning (TAL) can tackle the problem of the different data distribution between successive versions. Our TAL method includes two stages. At the active learning stage, a committee of investigated metrics is constructed to vote on the unlabeled modules of the current version. We pick up the unlabeled module with the median of voting scores to domain experts. The domain experts test and label the selected unlabeled module. Then, we merge the selected labeled module and the remaining modules with pseudo‐labels from the current version into the labeled modules of the prior version to form enhanced training data. Based on the training data, we derive the metric thresholds used for the next iteration. At the defect prediction stage, the iterations stop when a predefined threshold is reached. Finally, we use the cutoff threshold of voting scores, that is, 50%, to predict the defect‐prone of the remaining unlabeled modules. We evaluate the TAL method on 31 versions of 10 projects with three prevalent performance indicators. The results show that TAL outperforms the baseline methods, including three variations methods, two common supervised methods, and the state‐of‐the‐art method Hybrid Active Learning and Kernel PCA (HALKP). The results indicate that TAL can effectively address the different data distribution between successive versions. Furthermore, to keep the cost of extensive testing low in practice, selecting 5% of candidate modules from the current version is sufficient for TAL to achieve a good performance of defect prediction. [ABSTRACT FROM AUTHOR]

Existing POI recommendation methods often fail to capture the fine-grained preferences of users and face the challenge of modeling multiple relationships. Moreover, knowledge graph-based recommendation methods are limited in storing dynamic user trajectories, making them unsuitable for POI recommendation scenarios. In this paper, we propose a Multi-View Heterogeneous Knowledge learning model that utilizes techniques for heterogeneous knowledge representation learning and multi-view context modeling. Our model comprehensively models user preferences and the relationships between users and POIs by utilizing information from users' visiting sequences and POI attributes knowledge graph. Specifically, we design a heterogeneous knowledge embedding method to learn the representation of users and POIs using POI attribute knowledge and users' visiting sequences. Additionally, we constructed a user trajectory similarity graph and a POI attribute similarity graph to explore potential relations between users and between POIs. The former measures the similarity of user behaviors based on user visit sequences, and the latter quantifies the similarity between different POIs through a novel feature mapping method. Finally, we propose a multi-view hybrid learning method that combines unsupervised and supervised learning paradigms to model complex relationships, improving the overall recommendation performance. Extensive experiments on real-world datasets validate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

This paper proposes four principles for managers and higher education educators who are designing units and programmes so as to be dual mode ready. 'Dual mode' design and delivery enables students to equitably complete their studies fully online, while also offering on-campus experiences where possible. The four principles are: (1) All learning outcomes can be met irrespective of participation mode; (2) Teaching-learning activities are equitable across participation modes; (3) All students have equivalent opportunity to demonstrate achievement of learning outcomes; and (4) 'Online ready' design. Being dual mode ready will likely remain important as on-campus delivery may not be possible for all students. Further, universities may need to pivot rapidly to fully online delivery for a range of reasons, including pandemic-related circumstances. The four principles provide guidance on how best to ensure equity and fairness for students and teachers in a dual mode context. [ABSTRACT FROM AUTHOR]

During the COVID pandemic many centres adopted e-learning as a tool to adhere to social distancing recommendations while continuing to provide ongoing postgraduate medical education. We aimed to complete this scoping review in order to map experience and perceptions amongst surgeons and surgical trainees to remote learning during the COVID pandemic. Using Arksey and O'Malley's five step model for conducting a scoping review, a systematic search strategy was undertaken across three online databases SCOPUS, MEDLINE and Web of Science. Only original articles in English in the field of postgraduate education in surgery were included. 44 studies were selected for review. Of these 44, 21 were studies of perception of a newly developed e-learning tool/platform. 17 were surveys of surgeon's attitudes towards e-learning during the COVID pandemic. The remaining 6 studies were studies of knowledge or skills acquired through new e-learning, which included a survey of experience. The United States was the most common country of origin with General Surgery the most represented surgical speciality. Response rates across all three study subgroups were on average >60%. Surgeon's experience of e-learning was reported in only positive terms in 86% (n = 38/44) of studies. This paper is informative in that it focuses specifically on surgeons' perceptions of a e-learning tools used in addition to skills or knowledge gained. Positive e-learning experience reported in these studies may lead to more blended learning curriculums being developed, deployed and evaluated going forward. • Scoping review of surgeons' perceptions towards e-learning during COVID. • Maps out the wide range of e-learning tools that were used during the pandemic. • Provides subgrouping framework of pandemic era e-learning studies. [ABSTRACT FROM AUTHOR]

This study aims to analyse teachers' understanding of realistic mathematics education (RME) through a blended workshop on designing an RME-based learning trajectory. Data was collected via online pre-test and post-test, involving mathematics teachers of junior high schools in Banda Aceh, Indonesia. The tests were accompanied by interviews, chats on WhatsApp groups, and video recording. A descriptive analysis of the various sources of data indicated that the teachers made varying shifts in understanding the principles of RME. The teachers slightly altered their understanding of the intertwinement and level principles. However, their comprehension of the reality principle remained the same; they considered real problems as daily life problems only, even though some teachers had already written the meaning of real problems as problems that students can imagine. They also have already possessed a satisfactory understanding of the activity principle before the workshop. Moreover, nearly half of the teachers showed a good understanding of RME-based learning trajectories. The findings reported that teachers benefited from the blended workshop and obtained knowledge of the RME-based learning trajectory after participation. Finally, the implications for further research were discussed in this paper. [ABSTRACT FROM AUTHOR]

Autonomous driving navigation relies on diverse approaches, each with advantages and limitations depending on various factors. For HD maps, modular systems excel, while end-to-end methods dominate mapless scenarios. However, few leverage the strengths of both. This paper innovates by proposing a hybrid architecture that seamlessly integrates modular perception and control modules with data-driven path planning. This innovative design leverages the strengths of both approaches, enabling a clear understanding and debugging of individual components while simultaneously harnessing the learning power of end-to-end approaches. Our proposed architecture achieved first and second place in the 2023 CARLA Autonomous Driving Challenge's SENSORS and MAP tracks, respectively. These results demonstrate the architecture's effectiveness in both map-based and mapless navigation. We achieved a driving score of 41.56 and the highest route completion of 86.03 in the MAP track of the CARLA Challenge leaderboard 1, and driving scores of 35.36 and 1.23 in the CARLA Challenge SENSOR track with route completions of 85.01 and 9.55 , for, respectively, leaderboard 1 and 2. The results of leaderboard 2 raised the hybrid architecture to the first position, winning the edition of the 2023 CARLA Autonomous Driving Competition. [ABSTRACT FROM AUTHOR]

Teaching-learning processes can incorporate information and communication technologies (ICT) for transmission, mediation, interaction, and assessment in several fields of knowledge. This paper established the current trends in using ICT for social science in higher education, including online, blended, and ICT-supported learning. The review allowed us to quantify studies related to social science education, identify research trends, and identify ICT tools. The systematic review showed that: there is a lag in the incorporation of ICT tools in social sciences; most of the research identified were perception studies; few works introduce new digital tools; and few research studied the impact of ICT on student performance. This review establishes the advantages and disadvantages of online learning and some recommendations to incorporate ICT in social science teaching-learning processes. [ABSTRACT FROM AUTHOR]

Museum artifacts are the main way for visitors to experience and learn about cultural heritage. Augmented reality (AR) allows for high interactivity and is increasingly applied in museums to improve tourists' experience and learning. It also supports the extension of museum experience to outside of the physical museum space, contributing to the visiting trajectory and takeaway experience. In this paper, we present our design of two tangible AR interfaces for cultural artifacts: Postcard AR and CubeMuseum AR, followed by three user studies that evaluate and optimize the design. In Study 1, we conducted a within-subjects study (N = 24) that compares the two AR interfaces with a baseline condition (Leaflet). Our results demonstrate the positive effects of tangible AR interfaces on users' motivation and engagement in learning cultural heritage. In Study 2, we further explored how to optimize CubeMuseum AR by adopting a user-centered design approach. Through the analysis of expert interviews (N = 7) and an online survey (N = 207), the results specify a series of requirements and design guidelines for tangible AR interfaces to be used as a learning tool and a hybrid gift. Based on the findings, the design of the CubeMuseum AR was optimized and evaluated in Study 3. A between-subjects user study was conducted (N = 32) to compare the optimized design with the initial design. The results verified the positive effects of gamified tangible AR interfaces on users' motivation, engagement, and performance in learning cultural heritage. We present our design and evaluation results, and discuss the implications of designing tangible AR interfaces for cultural heritage learning and museum gifting. [ABSTRACT FROM AUTHOR]

The article discusses the use of model predictive control (MPC) for drone flight control in unknown dynamic environments. MPC is a practical method for drone flight control due to its robustness against modeling errors and uncertainties. However, it can degrade in performance when faced with unknown environmental dynamics. The paper introduces a parameterized MPC approach called hyMPC that adapts to uncertain environmental conditions. It uses a novel policy search framework to train a high-level Gaussian policy and neural network policies to provide real-time decision variables. The effectiveness of hyMPC is validated through numerical simulations, achieving a 100% success rate in drone flight tests. The text discusses a framework for maneuvering drones through swinging gates using reinforcement learning (RL) and model predictive control (MPC). The framework utilizes episode-based policy search methods to acquire parameterized motor primitives and skills for controlling the drone. The RL-driven MPC framework incorporates a multi-layer perceptron to predict the gate's future state and a hybrid MPC cost function for trajectory optimization. The policy parameters are updated using a reward function that evaluates the quality of sampled trajectories. The proposed framework is validated through numerical simulations. This document presents a novel framework for navigating drones through swinging gates with unknown dynamics. The framework combines real-time Model Predictive Control (MPC) and offline Reinforcement Learning (RL) techniques. The approach involves training a neural network to predict gate motions and using an MLP to guide trajectory planning. The framework divides the traversal task into gate-following and gate-traversing [Extracted from the article]

Purpose: This paper aims to present commentary on adult safeguarding designated officers' (nominated senior staff members in the Health Service Executive and its funded services) in Ireland readiness for online learning and their perception of the blended approach used in their training and considers the implications of this for practice. Design/methodology/approach: In total, 233 designated officers were surveyed. A self-administered online survey comprising of two instruments was used. The questionnaire combines two previously validated tools measuring readiness for online learning and perceptions of blended learning. Minor modifications were made to account for local circumstance and language. Demographic questions relevant to the survey population were added. The response rate was 49%. Findings: Designated officers regarded specified competencies for online learning as important to very important with highest importance placed in time management. Designated officers expressed they were confident to very confident in their ability to accomplish all competencies in online learning. The highest confidence was in the technical competencies. Designated officers are demonstrating high readiness for online learning. Designated officers reported positively on online contributions and on blended learning workload. The scores indicate positive perceptions of the blended learning experience. Responses to an open-ended question were largely positive with some suggestions for improvement made. Practical implications: Findings have helped inform planning and development of the Health Service Executive's adult safeguarding training for designated officers with changes made since this survey was undertaken. Originality/value: To the best of the author's knowledge, this is the first time a survey was undertaken of designated officers in Ireland with a view to improving safeguarding training. Recommendations for adaptions to the blended designated officer programme were proposed and subsequently accepted and implemented. [ABSTRACT FROM AUTHOR]

The purpose of this position paper is to describe a historical timeline of science education. Using historical documents and current science education research, the authors create an evolutionary description of science education changes over time and how these shifts could influence how Artificial Intelligence (AI) is used in science education. The focus is on how societal and educational catalyst events, spanning from the Industrial Revolution to the Next Generation Science Standards (NGSS) and the COVID-19 pandemic, influenced science education. Next, the authors suggest that teachers should meaningfully implement the use of AI in ways that focus on student-centered learning and restore the progress made by the K-12 Framework and NGSS. These include generating ideas about problems that students can solve in an interest area, analyzing large sets of real-world data, generating grade appropriate science readings to develop background knowledge, and using AI to grade unique student work to replace multiple-choice response exams. AI and science education may best be described by a Chat GPT response: "It's important to note that while AI can enhance science education, it should not replace human teachers. Instead, it should be used as a tool to augment and support their expertise, fostering a blended learning environment that combines the benefits of technology with human guidance and mentorship." [ABSTRACT FROM AUTHOR]

Psychomotor skill performance is central to effective clinical practice across health professions. These complex skills are challenging to teach, particularly in the novice learner. As many health professions programs have increased blended course offerings, educators must establish best practices for teaching psychomotor skills in this evolving learning environment. The purpose of this paper is to describe the innovative application of an evidence-based framework to teaching psychomotor skills to novice learners in a blended learning environment. Using a modified 9-step framework, two novice clinical skills courses in a Doctor of Physical Therapy Program were redesigned to teach psychomotor skills in a blended format, using online and in-person class sessions. Online coursework consisted of synchronous and asynchronous learning activities that preceded an immersive lab experience. Formative and summative assessments occurred during lab immersion. The learning framework provided a central evidence-based pillar for novel course design, guiding development of learning activities for teaching psychomotor skills to novice learners in a blended learning environment. Initial student outcomes appear favorable when compared with previous traditional course structures and satisfaction was high. These preliminary findings align with prior research using similar frameworks for learning complex skills and provide an archetype curricular model for a blended learning environment. [ABSTRACT FROM AUTHOR]

In this paper, we propose a method for predicting epileptic seizures using a pre-trained model utilizing supervised contrastive learning and a hybrid model combining residual networks (ResNet) and long short-term memory (LSTM). The proposed training approach encompasses three key phases: pre-processing, pre-training as a pretext task, and training as a downstream task. In the pre-processing phase, the data is transformed into a spectrogram image using short time Fourier transform (STFT), which extracts both time and frequency information. This step compensates for the inherent complexity and irregularity of electroencephalography (EEG) data, which often hampers effective data analysis. During the pre-training phase, augmented data is generated from the original dataset using techniques such as band-stop filtering and temporal cutout. Subsequently, a ResNet model is pre-trained alongside a supervised contrastive loss model, learning the representation of the spectrogram image. In the training phase, a hybrid model is constructed by combining ResNet, initialized with weight values from the pre-trained model, and LSTM. This hybrid model extracts image features and time information to enhance prediction accuracy. The proposed method's effectiveness is validated using datasets from CHB-MIT and Seoul National University Hospital (SNUH). The method's generalization ability is confirmed through Leave-one-out cross-validation. From the experimental results measuring accuracy, sensitivity, and false positive rate (FPR), CHB-MIT was 91.90%, 89.64%, 0.058 and SNUH was 83.37%, 79.89%, and 0.131. The experimental results demonstrate that the proposed method outperforms the conventional methods. [ABSTRACT FROM AUTHOR]

Globally, the number of online courses offered as electronic versions of conventional learning courses has increased annually over the past decade. A critical variable for measuring the success or failure of these courses is student satisfaction. This paper presents a study which aims to investigate the students’ satisfaction with the quality of an online course supporting training in Object-Oriented Programming performed in blended learning mode. The developed questionnaire allows students to assess the course content and design, course organization, communication and support, and evaluation. Based on the summarized result, recommendations for improving the course quality to meet students’ expectations and needs have been done. [ABSTRACT FROM AUTHOR]

In the context of a full-scale war, participants in the educational process are implementing innovative strategies for adapting to new realities, based on the development and application of models of blended learning. The purpose of the academic paper is to study the features of the blended learning methodology in crisis situations with the identification of advantages and risks. The research was conducted using general scientific methods of cognition: analysis, synthesis, comparison, abstraction, specification, generalization, and formalization. In the course of the research, the existing models of the mixed type of educational process and the means of their practical implementation in educational institutions were analyzed. The problems of blended learning in the crisis period of military conflict are actualized, its features are presented. The risks accompanying the process of implementing the blended learning methodology are identified, and variations of measures to prevent them are proposed. It has been proven that the quality of the blended learning process depends on the teacher’s digital competencies in the online process. It has been established that the trend under study enriches the students’ learning experience and stimulates their motivation to study. The level of efficiency of blended learning is analyzed in comparison with distance and traditional learning. It has been determined that blended learning is much more effective than traditional and distance learning subject to careful planning of the educational process and a reasonable selection of tools. The essence of the methodology of blended learning as an innovative technology of the educational process and its effective anti-crisis format is proven. The practical significance of the research results lies in the possibility of their productive use in the process of optimizing the system of education in war conditions by improving existing and developing new methods and algorithms of blended learning. [ABSTRACT FROM AUTHOR]

Wind farm (WF) is gradually required to provide inertial support during frequency events nowadays. Existing WF inertial control methods have exhibited limitations in parameter estimation and optimal control parameter tuning under variable operating conditions. Moreover, traditional model-based methods suffer from computational efficiency problems due to their reliance on repeated iterations or derivative computations in optimization process. Thus, this paper proposes an inertial control method for large-scale WF based on hierarchical distributed hybrid deep-reinforcement learning (HDH-DRL). Firstly, the control objectives for the inertial control are defined, and are decomposed on the basis of wind turbines (WTs) division. Next, this paper presents a HDH-DRL based inertial control framework consisting of two levels. The upper-level control is achieved by the hybrid multi-agent DRL (HMA-DRL) algorithm with hybrid action exploration mechanism and multi-agent coordination. The consensus based lower-level control aims to achieve the consensus convergence of the control through the locally distributed interaction among WTs. Finally, the inertial control processes of the model are exhibited; the influences of DRL algorithms on the control are discussed; the computational speed and solution accuracy of the proposed method are compared with the model-based methods; the multi-scenario applicability and performance in local communication failures of the model are analyzed. The results demonstrate that the proposed method significantly improves the active power response and frequency stability, achieving rapid consensus convergence with a power deviation below 0.3%, surpassing traditional control methods by at least 0.2%; also, it demonstrates superior performance across various scenarios, including transient and steady-state conditions, with frequency enhancements up to 0.30% and exceptional stability under different wind conditions and communication disruptions. • Introduces HDH-DRL for improved WF inertial control and frequency stability. • Develops a bi-level HDH-DRL framework for faster, accurate control actions. • Utilizes HMA-DRL with a novel exploration mechanism for complex WF operations. • Achieves better accuracy and quicker computation than model-based methods. • Ensures control robustness across varied wind conditions and communication breaks. [ABSTRACT FROM AUTHOR]

• Improving the quality of Federal Learning encrypted alignment data. • Use Gaussian mixture clustering to cluster samples and set a threshold to filter samples. • Use the encrypted sample attribute searching algorithm to fill in the missing value of the sample. • Design the combination model of variation auto-encoder Gaussian hybrid clustering and federated learning. Federated learning can achieve multi-party data-collaborative applications while safeguarding personal privacy. However, the process often leads to a decline in the quality of sample data due to a substantial amount of missing encrypted aligned data, and there is a lack of research on how to improve the model learning effect by increasing the number of samples of encrypted aligned data in federated learning. Therefore, this paper integrates the functional characteristics of deep learning models and proposes a Variational AutoEncoder Gaussian Mixture Model Clustering Vertical Federated Learning Model (VAEGMMC-VFL), which leverages the feature extraction capability of the autoencoder and the clustering and pattern discovery capabilities of Gaussian mixture clustering on diverse datasets to further explore a large number of potentially usable samples. Firstly, the Variational AutoEncoder is used to achieve dimensionality reduction and sample feature reconstruction of high-dimensional data samples. Subsequently, Gaussian mixture clustering is further employed to partition the dataset into multiple potential Gaussian-distributed clusters and filter the sample data using thresholding. Additionally, the paper introduces a labeled sample attribute value finding algorithm to fill in attribute values for encrypted unaligned samples that meet the requirements, allowing for the full recovery of encrypted unaligned data. In the experimental section, the paper selects four sets of datasets from different industries and compares the proposed method with three federated learning clustering methods in terms of clustering loss, reconstruction loss, and other metrics. Tests on precision, accuracy, recall, ROC curve, and F1-score indicate that the proposed method outperforms similar approaches. [ABSTRACT FROM AUTHOR]

Since deep Q-networks and AlphaGO by Google DeepMind were proposed, not only a reinforcement learning integrated with deep learning but also its applications have attracted much attention on. ChatGPT, which learns by Proximal Policy Optimization as one of reinforcement learning mechanisms, is an excellent example. With this background, we propose the special issue titled "Cutting Edge of Reinforcement Learning and its Hybrid Methods," which is the same of the special issue in 2017, to cover the latest progress and trends in reinforcement learning and its hybrid methods (combined with machine learning, neural networks, and evolutionary computation). We received 28 submissions, out of which 12 submissions were peer-reviewed and 16 submissions that were outside the scope of the special issue were excluded. After a thorough review process including comments and suggestions by reviewers, seven submissions were accepted. These included four theory and three application papers, indicating nearly equal contributions in theory and application aspects. The content of the first three papers is related to inverse reinforcement learning, while the fourth one is not directly related to reinforcement learning but it would be related to reinforcement learning in the future. All papers address issues surrounding cutting-edge technology in reinforcement learning. We would like to end by expressing that we hope and believe that this special issue can largely contribute to the development in the field of reinforcement learning while holding a wide international appeal. [ABSTRACT FROM AUTHOR]

Bayesian network (BN) structure learning is the basis of BN applications and plays a pivotal role in many machine learning tasks. Whereas remarkable progress in structure learning has been achieved in the past, making further improvements in the efficiency and accuracy of structure learning is a significant challenge. In this paper, we propose an efficient skeleton learning approach-based hybrid algorithm (ESLH), which consists of two phases. In the constraint-based phase, a dynamic threshold (DTH) strategy and a skeleton learning method based on triangle breaking (SLTB) are proposed to learn the skeleton of a BN structure efficiently. DTH designs a dynamic threshold to remove redundant edges in the initial skeleton with little time overhead. By the result of DTH, SLTB first finds, tests and breaks triangles in the initial skeleton to efficiently remove redundant edges and then removes the remaining redundant edges to discover the final skeleton. In the score-and-search phase, ESLH employs the hill-climbing algorithm to find the highest-scored structure. We propose a novel strategy to divide this phase into three steps, both utilizing the learned skeleton to constrain the search space and preventing the errors of the learned skeleton from reducing the quality of the final learned structure. Extensive experiments on benchmark BNs validate the effectiveness of DTH and SLTB and demonstrate that ESLH is more than five times faster than the state-of-the-art structure learning algorithms while maintaining the highest average accuracy. [ABSTRACT FROM AUTHOR]

Bayesian network (BN) structure learning is the basis of BN applications and plays a pivotal role in many machine learning tasks. Whereas remarkable progress in structure learning has been achieved in the past, making further improvements in the efficiency and accuracy of structure learning is a significant challenge. In this paper, we propose an efficient skeleton learning approach-based hybrid algorithm (ESLH), which consists of two phases. In the constraint-based phase, a dynamic threshold (DTH) strategy and a skeleton learning method based on triangle breaking (SLTB) are proposed to learn the skeleton of a BN structure efficiently. DTH designs a dynamic threshold to remove redundant edges in the initial skeleton with little time overhead. By the result of DTH, SLTB first finds, tests and breaks triangles in the initial skeleton to efficiently remove redundant edges and then removes the remaining redundant edges to discover the final skeleton. In the score-and-search phase, ESLH employs the hill-climbing algorithm to find the highest-scored structure. We propose a novel strategy to divide this phase into three steps, both utilizing the learned skeleton to constrain the search space and preventing the errors of the learned skeleton from reducing the quality of the final learned structure. Extensive experiments on benchmark BNs validate the effectiveness of DTH and SLTB and demonstrate that ESLH is more than five times faster than the state-of-the-art structure learning algorithms while maintaining the highest average accuracy. [ABSTRACT FROM AUTHOR]

To optimize the operation of his wind farm, the farm manager needs to make precise diagnostic decisions for scheduling efficiently the maintenance actions. To assist him in this task, this paper proposes an approach aimed at designing a hybrid diagnoser model for two main goals. The first one is to detect anomalies at an early stage, and the second one is to provide specific deductions or explanations about the potential cause of the problem. In this way, the developed system can help the maintenance manager understand why a particular decision needs to be made. To do this, an original approach coupling the artificial intelligence technique with a discrete event system is proposed to diagnose, identify, and explain a probable source of a problem. Thus, the proposed method uses a hybrid approach consisting of two model blocks. The first block consists of autoencoder models to extract feature representation to diagnose the health state of the system. The second one is a discrete event-based model to create and visualize rule-based anomaly alerts and triggers to provide plausible explanations to the operator to improve his task. Then, this work introduces a methodology to jointly train these two models and learn all parameters of the hybrid diagnoser. It is shown how the information extracted from the neural network model is used to automatically construct the event-based model to explain the occurrence of an anomaly. The proposed system achieved significant results in explaining and detecting early five types of anomalies in wind turbine systems with accuracy up to 80%. The results demonstrate that the approach can deliver performance gains of up to 20% compared to standard techniques such as Long short-term memory and Random cut forest. • Anomalies detection and explanation in wind turbine systems. • Hybrid learning of an autoencoder and event-based model. • Computation of a set of rules for identifying the root causes of anomalies. • Explainable predictive maintenance for improving decision-making processes. [ABSTRACT FROM AUTHOR]

Linear discriminant analysis (LDA) uses labeled samples for acquiring a discriminant projection direction, by which data of different categories are separated into distinct groups in a lower-dimensional subspace. In response to the issue that LDA lacks robustness to non-Gaussian data with rich local information, improvements on LDA explore the subspace manifold structure by building a fully connected similarity graph. However, these methods are vulnerable to the interference of noisy and redundant information. In this paper, we propose a new local LDA method, named adaptive and fuzzy locality discriminant analysis (AFLDA), which aims at extracting precise and compact features. Firstly, an adaptive and fuzzy k-means strategy is adopted, where the membership between data and corresponding subclass centers for each class is learned to establish a hybrid bipartite graph and capture local information. Secondly, we design a discrete and probability constraint imposed on the membership matrix to explore the intricate structure of multimodal data. Moreover, the subblock partition for each class makes data accommodate to multimodal subclasses. Thirdly, the maximum total scatter regularization term is introduced, which amply disperses the data to enhance the recognition of local structure and avoid trivial solutions. Finally, to eliminate the interference of noisy and redundant information, AFLDA learns an optimized subspace, where cluster centers and the membership matrix are updated alternately. Promising results in experiments illustrate the efficacy of the model. • We propose a subclass partition strategy to learn potential submanifold structures. • Subclass partition provides a concise representation of data for each class. • Fuzzy membership between instances and subclass centers for each class is learned. • A discrete tactic is adopted on memberships to obtain a pseudo-label for each sample. • The membership matrix can be updated adaptively and independently through each class. • The model could handle non-Gaussian data and identify potential subclusters. [ABSTRACT FROM AUTHOR]

Reliable multi-vehicle detection in unregulated traffic environments is a crucial computer vision task in the development of Intelligent Transportation Systems (ITS). Despite the promising potential of Deep Learning (DL) methods for vehicle detection, the presence of uncertainties such as varying vehicle shapes and sizes, intricate background clutter, and unpredictable vehicle flow contribute to the chaotic unregulated traffic. For real-time vehicle detection in an unregulated traffic environment this paper proposes the Hybrid Learning Multi-Vehicle Detection framework (HL-MVD) based on the C onvolutional M ulti-head A ttention T ransformer D etector (CMATDet). The primary objective of this study is to generate a dataset containing highly informative video frames using a Pool-based Active Learning Strategy (PALS). Additionally, transfer learning will be implemented to train CMATDet to achieve improved accuracy and reduced detection latency. The proposed approach restructures the baseline YOLOv5x and incorporates a Multi-head Attention transformer encoder to effectively extract global features and a Scale Specific Bidirectional Feature Pyramid Network (SS-BiFPN) to facilitate multi-scale feature representation. Simplified Optimal Transport Algorithm with top-q approximation technique (Sim-OTA) is utilized for label assignment approach. Heatmap analysis demonstrated the suitability of the newly generated dataset "AU-INV-P-PALS" for detecting specific Indian native vehicles. The performance of the proposed framework is evaluated on our custom-developed AU-INV-P-PALS vehicle dataset and the IITM-HeTra Dataset 1. In comparison with contemporary detection models, the proposed HL-MVD framework resulted with higher mAP scores (91.1% on mAP@0.5 and 78.3% on mAP@0.5:0.95) for AU-INV-P-PALS. The proposed model demonstrated lower inference latency (8.1 ms), higher precision score (82.7% for IoU = 0.5), and higher recall score (90.8% for IoU = 0.5) than recent deep learning-based detection models in the literature. The top-q approximation technique in the detection head results in a reduced false-positive rate compared to conventional models. Finally, the performance of the proposed framework is tested on CCTV traffic footage captured on city roads in Chennai, India. • Hybrid Learning framework for reliable vehicle detection in unregulated traffic. • Active Learning to generate compact and informative dataset (AU-INV-P-PALS). • CNN-Transformer based network (CMATDet) to improve detection capabilities. • Dynamic label assignment to reduce false positives during vehicle occlusion. • Validation on real-time CCTV traffic footages for reliability. [ABSTRACT FROM AUTHOR]

In recent years, deep learning algorithms have rapidly revolutionized artificial intelligence, particularly machine learning, enabling researchers and practitioners to extend previously hand-crafted feature extraction procedures. In particular, deep learning uses adaptive learning processes to learn more complex and informative patterns from datasets of varying sizes. With the increasing availability of multimodal data streams and recent advances in deep learning algorithms, multimodal deep learning is on the rise. This requires the development of complex models that can process and analyze multimodal information in a consistent manner. However, unstructured data can come in many different forms (also known as modalities). Extracting relevant features from this data remains an ambitious goal for deep learning researchers. According to the literature, most deep learning systems consist of a single architecture (i.e., standalone deep learning). When two or more deep learning architectures are combined over multiple sensory modalities, the result is called a multimodal hybrid deep learning model. Since this research direction has received much attention in the field of deep learning, the purpose of this survey is to provide a broader overview of the topic. In this paper, we provide a comprehensive review of recent advances in multimodal hybrid deep learning, including a thorough analysis of the most commonly developed hybrid architectures. In particular, one of the main challenges in multimodal hybrid analysis is the ability of these architectures to systematically integrate cross-modal features in hybrid designs. Therefore, we propose a generic framework for multimodal hybrid learning that focuses mainly on fusion methods. We also identify trends and challenges in multimodal hybrid learning and provide insights and directions for future research. Our findings show that multimodal hybrid learning can perform well in a variety of challenging computer vision applications and tasks. • We categorize these methods based on hybrid deep architectures. • We review recent advances in unimodal and multimodal hybrid deep learning. • We consider multimodal and hybrid fusion techniques. • We highlight several challenging application-driven hybrid architectures. • We discuss current trends and challenges in multimodal hybrid learning. [ABSTRACT FROM AUTHOR]

This paper proposes an innovative method for achieving optimal tracking control in nonlinear continuous-time systems with input constraints. The method combines reinforcement learning and hybrid metaheuristics to enhance the controller's performance. Specifically, a hybrid metaheuristic algorithm is employed to optimize the hyperparameters of a critic neural network, which serves as the system's controller. The proposed approach is evaluated through extensive simulation studies on a nonlinear system with input constraints. Results demonstrate its superiority over traditional control techniques in terms of accuracy, timeliness, and stability. Notably, the approach effectively eliminates overshoot and steady-state error while providing precise and prompt tracking and showcasing remarkable robustness against model uncertainties. By synergistically integrating reinforcement learning and hybrid metaheuristics, this approach represents a significant advancement in enhancing the control performance of complex nonlinear systems. The simulation studies confirm superiority of the proposed approach over existing techniques, offering a promising solution for achieving optimal tracking control in nonlinear systems with input constraints. This approach holds potential for a wide range of applications, including robotics, aerospace, and manufacturing, where precise and prompt tracking control is critical. [ABSTRACT FROM AUTHOR]

Late-life depression (LLD) is a highly prevalent mood disorder occurring in older adults and is frequently accompanied by cognitive impairment (CI). Studies have shown that LLD may increase the risk of Alzheimer's disease (AD). However, the heterogeneity of presentation of geriatric depression suggests that multiple biological mechanisms may underlie it. Current biological research on LLD progression incorporates machine learning that combines neuroimaging data with clinical observations. There are few studies on incident cognitive diagnostic outcomes in LLD based on structural MRI (sMRI). In this paper, we describe the development of a hybrid representation learning (HRL) framework for predicting cognitive diagnosis over 5 years based on T1-weighted sMRI data. Specifically, we first extract prediction-oriented MRI features via a deep neural network, and then integrate them with handcrafted MRI features via a Transformer encoder for cognitive diagnosis prediction. Two tasks are investigated in this work, including (1) identifying cognitively normal subjects with LLD and never-depressed older healthy subjects, and (2) identifying LLD subjects who developed CI (or even AD) and those who stayed cognitively normal over five years. We validate the proposed HRL on 294 subjects with T1-weighted MRIs from two clinically harmonized studies. Experimental results suggest that the HRL outperforms several classical machine learning and state-of-the-art deep learning methods in LLD identification and prediction tasks. • A Hybrid Representation Learning (HRL) framework is developed for longitudinal diagnostic discrimination in late life depression (LLD) using T1-weighted MRI. To the best of our knowledge, this is the first attempt of predicting cognitive diagnosis over 5 years and finding related potential MRI biomarkers. • The HRL integrates data-driven and handcrafted MRI features into a unified framework. A feature fusion module is designed to fuse two types of features more effectively for better prediction. • The feature maps extracted by HRL help to identify potential MRI biomarkers for the assessment of cognitive change in LLD subjects, thus helping to improve clinical diagnosis. [ABSTRACT FROM AUTHOR]

In integrated energy systems (IESs), reliable planning and operation are challenging owing to significant uncertainties in energy production, utilization, and trading. To this end, this paper proposes a multi-task joint forecasting method that enables joint source-load-price forecasting. First, three uncertain variables in an IES, namely, renewable energy, the multi-energy load, and the energy price, were investigated and the complex coupling relationships among them were validated. Second, to cope with the redundant noise resulting from various inputs, multi-channel feature extraction and a hybrid attention mechanism were combined to enable separate extraction and unified fusion of features. Additionally, considering the unique one-dimensional input in the prediction domain, a sequential convolution attention module (SCAM) with a hybrid channel and temporal attention mechanism was proposed to guide multi-channel feature fusion. Finally, facing the challenge of multi-layer coupling information learning, a multi-task learning (MTL) integrated shared layer was designed. Based on the coordinated with MTL, multi-column convolutional neural network, SCAM and long short-term memory network, joint forecasting of source-load-price was realized. The simulation results showed that the average mean absolute percentage error of the proposed model was as low as 4.10% in source-load-price long-term forecasting, while that of winter short-term forecasting could reach 3.14%. In addition, the here proposed model was found to be superior to others in terms of computational efficiency and result stability. • Combining energy and market layers for source-load-price joint forecasting. • Proposing a SCAM with hybrid channel and temporal attention modules. • Designing an MTL integrated sharing layer and achieving adaptive adjusting of the loss function. • The average MAPE of the proposed model is as low as 4.10% for the long-term source-load-price forecasting. [ABSTRACT FROM AUTHOR]

The Adaptive Neuro-Fuzzy Inference System (ANFIS) is a regression model that uses fuzzy logic and neural networks, making it suitable for modeling the uncertainty of regression problems. However, the non-robust loss function in ANFIS's hybrid learning algorithm can make it susceptible to the direct effects of noise and outliers. This paper introduces a new procedure that uses robust loss functions to enhance the hybrid learning performance against noise and outliers. In addition, a new robust loss function is devised that can completely ignore outliers. Furthermore, a set of robust loss functions with mathematical relations are suggested. The proposed approach is evaluated on real-world problems, including weather forecasting and stock market prediction. Results suggested that the proposed model can reduce the Mean Square Error (MSE) in regression. Moreover, the new procedure enables utilizing different loss functions based on the application. • Introduce a new version of the hybrid learning algorithm for Adaptive Neuro-Fuzzy Inference Systems. • Emphasis on the significance of using different loss functions for parameter optimization. • Improve hybrid learning robustness against noise and outliers. • Development of the "incurious loss" function, a novel robust loss function against outliers. • Results demonstrate the importance of selecting an appropriate loss function for parameter optimization. [ABSTRACT FROM AUTHOR]

Goals-based wealth management (GBWM), an investment philosophy, is aiming to attain the desired goal or goals specified by an investor, in a long-term investment. A good algorithm for GBWM is able to provide decision-making and enhance the confidence of consumers and investors, under a complex economic situation. However, the existing methods suffer poor adaptability, oversimplified settings, and limited solution space. In this paper, we extend existing models to more realistic scenarios and propose a new hybrid RL-based algorithm, MHPPO to optimize complex discrete and continuous decisions simultaneously. Our algorithm outperforms existing methods in both simple and complicated settings. The prototype of the algorithm will be implemented on the platform of RoyalFlush company. • A new hybrid reinforcement learning for GBWH with extensive practical features. • New separate neural networks embedding in hybrid policy achieve higher utility. • Student's- T distribution in policy sampling beats other distributions. [ABSTRACT FROM AUTHOR]

With the rapid development of the economy and technology, the rate of product replacement has accelerated, resulting in a large number of products being discarded. Disassembly is an important way to recycle waste products, which is also helpful to reduce manufacturing costs and environmental pollution. The combination of a single-row linear disassembly line and a U-shaped disassembly line presents distinctive advantages within various application scenarios. The Hybrid Disassembly Line Balancing Problem (HDLBP) that considers the requirement of multi-skilled workers is addressed in this paper. A mathematical model is established to maximize the recovery profit according to the characteristics of the proposed problem. To facilitate the search for optimal solution, a new strategy for agents in reinforcement learning to interact with complex and changeable environments in real-time is developed, and deep reinforcement learning is used to complete the distribution of multi-products and disassembly tasks. On this basis, we propose a Soft Actor–Critic (SAC) algorithm to effectively address this problem. Compared with the Deep Deterministic Policy Gradient (DDPG) algorithm, Advantage Actor–Critic (A2C) algorithm, and Proximal Policy Optimization (PPO) algorithm, the results show that the SAC can get the approximate optimal result on small-scale cases. The performance of SAC is also better than DDPG, PPO, and A2C in solving large-scale disassembly cases. [ABSTRACT FROM AUTHOR]

Probability distributions of structural responses have been widely used in many engineering applications and their accuracy could significantly affect the performance and credibility of these applications. To obtain accurate distributions, existing methods often need massive calculations of the original response function, especially for highly nonlinear problems. To alleviate the computational burden, this paper proposes a multi-region active learning Kriging method to construct response distributions of highly nonlinear problems. First, a low-precision CDF curve is built based on the one-iteration MPP search and MPP prediction. Multiple regions and response values are then identified to obtain the limit state surfaces for Kriging modeling. To determine the best training points, a multi-region learning strategy including rough and precise selections is developed based on the U learning function and a hybrid index of the reward-based probability and nonlinearity. A two-level stopping criterion is further provided to achieve fast convergence and high accuracy. Finally, the response distributions are constructed using the obtained Kriging model. The effectiveness of the proposed method is verified by four examples. [ABSTRACT FROM AUTHOR]