Development Of Learning System Research Articles

Explainability as fig leaf? An exploration of experts’ ethical expectations towards machine learning in psychiatry

The increasing implementation of programs supported by machine learning in medical contexts will affect psychiatry. It is crucial to accompany this development with careful ethical considerations informed by empirical research involving experts from the field, to identify existing problems, and to address them with fine-grained ethical reflection. We conducted semi-structured qualitative interviews with 15 experts from Germany and Switzerland with training in medicine and neuroscience on the assistive use of machine learning in psychiatry. We used reflexive thematic analysis to identify key ethical expectations and attitudes towards machine learning systems. Experts’ ethical expectations towards machine learning in psychiatry partially challenge orthodoxies from the field. We relate these challenges to three themes, namely (1) ethical challenges of machine learning research, (2) the role of explainability in research and clinical application, and (3) the relation of patients, physicians, and machine learning system. Participants were divided regarding the value of explainability, as promoted by recent guidelines for ethical artificial intelligence, and highlighted that explainability may be used as an ethical fig leaf to cover shortfalls in data acquisition. Experts recommended increased attention to machine learning methodology, and the education of physicians as first steps towards a potential use of machine learning systems in psychiatry. Our findings stress the need for domain-specific ethical research, scrutinizing the use of machine learning in different medical specialties. Critical ethical research should further examine the value of explainability for an ethical development of machine learning systems and strive towards an appropriate framework to communicate ML-based medical predictions.

Fear modulates parental orienting during childhood and adolescence

Adults quickly orient toward sources of danger and deploy fight-or-flight tactics to manage threatening situations. In contrast, infants who cannot implement the safety strategies available to adults and depend heavily on caregivers for survival are more likely to turn toward familiar adults, such as their parents, to help them navigate threatening circumstances. However, work has yet to investigate how readily children and adolescents orient toward their parents in threatening or fearful contexts. The current work addressed this question using a visual search paradigm that included arrays of parents’ and strangers’ faces as target and distractor stimuli, preceded by a fear or neutral emotional priming procedure. Linear mixed-effects models showed that children and adolescents (N = 88, age range = 4–17 years; 42M/46F) were faster to search for the face of their parent than of a stranger. However, fear priming attenuated this effect of the parent on search times, such that children and adolescents were significantly slower to orient toward their parent in an array of strangers' faces if they were first primed with fear as opposed to a neutral video. This work indicates that fear priming may phasically interfere with parental orienting during childhood and adolescence, possibly because fear reallocates attention away from parents and toward (potentially threatening) unfamiliar people in the environment to facilitate the development of independent threat learning and coping systems.

Guest Editorial Special Section on Learning With Multimodal Data for Biomedical Informatics

In this Special Section of the IEEE Transactions on Circuits and Systems for Video Technology, it is our honor to present emerging advanced machine learning and data analytics algorithms aiming at catalyzing synergies among image/video processing, text/speech understanding, and multimodal learning in biomedical informatics. Our goals are to 1) introduce novel data-driven models to accelerate knowledge discovery in biomedicine through the seamless integration of medical data collected from imaging systems, laboratory and wearable devices, as well as other related medical devices; 2) promote the development of new multi-modal learning systems to enhance the healthcare quality and patient safety; and 3) promote new applications in biomedical informatics that can leverage or benefits from the integration of multi-modal data and machine learning.

Designing a Regional Teacher Professional Development Enterprise

Teacher professional learning is foundational to high quality P-12 education. While many researchers have identified the importance and criteria of high-quality professional learning, little research explains how this professional learning can be implemented in a regional system. This ten-month case study offers one planning approach to engage important stakeholders, including principals, other education leaders, professional development providers and especially teachers, in a process to design a regional professional learning collaborative. This approach employed features of high-quality professional development throughout the planning activities. Drawing on principles from design thinking, findings identify the importance of the empathize, define, ideate, and prototype phases in designing innovative systems for professional learning. Emphasis is placed on the importance of shared authority with teachers, optimism inherent to design thinking, and relationship and community building throughout these phases. Implications for the development of educator professional learning systems are discussed and a coda sharing the current efforts of the collaborative is presented.

Clones in deep learning code: what, where, and why?

Deep Learning applications are becoming increasingly popular worldwide. Developers of deep learning systems like in every other context of software development strive to write more efficient code in terms of performance, complexity, and maintenance. The continuous evolution of deep learning systems imposing tighter development timelines and their increasing complexity may result in bad design decisions by the developers. Besides, due to the use of common frameworks and repetitive implementation of similar tasks, deep learning developers are likely to use the copy-paste practice leading to clones in deep learning code. Code clone is considered to be a bad software development practice since developers can inadvertently fail to properly propagate changes to all clones fragments during a maintenance activity. However, to the best of our knowledge, no study has investigated code cloning practices in deep learning development. The majority of research on deep learning systems mostly focusing on improving the dependability of the models. Given the negative impacts of clones on software quality reported in the studies on traditional systems and the inherent complexity of maintaining deep learning systems (e.g., bug fixing), it is very important to understand the characteristics and potential impacts of code clones on deep learning systems. This paper examines the frequency, distribution, and impacts of code clones and the code cloning practices in deep learning systems. To accomplish this, we use the NiCad clone detection tool to detect clones from 59 Python, 14 C#, and 6 Java based deep learning systems and an equal number of traditional software systems. We then analyze the comparative frequency and distribution of code clones in deep learning systems and the traditional ones. Further, we study the distribution of the detected code clones by applying a location based taxonomy. In addition, we study the correlation between bugs and code clones to assess the impacts of clones on the quality of the studied systems. Finally, we introduce a code clone taxonomy related to deep learning programs based on 6 DL software systems (from 59 DL systems) and identify the deep learning system development phases in which cloning has the highest risk of faults. Our results show that code cloning is a frequent practice in deep learning systems and that deep learning developers often clone code from files contain in distant repositories in the system. In addition, we found that code cloning occurs more frequently during DL model construction, model training, and data pre-processing. And that hyperparameters setting is the phase of deep learning model construction during which cloning is the riskiest, since it often leads to faults.

Automated Aerial Docking System Using Onboard Vision-Based Deep Learning

This paper proposes an automated aerial docking system for unmanned aerial vehicles. The proposed automated aerial docking system consists of the following two subsystems: 1) docking mechanical system and 2) vision-based deep learning detection/tracking system. A fundamental challenge during the midair docking phase is integration between the leader and follower vehicles with a robust target detection/tracking strategy. This paper presents not only the design of a probe-and-drogue-type aerial docking system, but it also presents the development of an onboard machine learning system for aerial target detection and tracking, which is limited from 0.1 to 3.5 m. The aerial docking system is designed based on a bistable mechanism to increase the robustness of integration and separation between two vehicles. The prototype of the proposed docking mechanism is built by a 3D printer. To employ effective drogue detection in the air, a deep convolutional neural network-based single-stage detector algorithm, YOLOv4-tiny, is applied. Furthermore, to track the moving drogue in the air simultaneously, a point cloud-based tracking algorithm with an RGB-D camera system is developed. The developed deep learning-based detection/tracking system is implemented to be operated in the Arm architecture-based onboard machine learning computer. For performance validation of the proposed automated aerial docking system, a ground test using two robot arms and an indoor flight test using quadcopter drone and an unmanned ground vehicle were conducted.

Teacher Training Effectiveness in Self-Regulation in Virtual Environments.

Higher education in the 21st century faces the challenge of changing the way in which knowledge is conveyed and how teachers and students interact in the teaching-learning process. The current pandemic caused by SARS-CoV-2 has hastened the need to face up to this challenge and has furthered the need to approach the issue from the perspective of digitalisation. To achieve this, it is necessary to design training programmes geared towards teaching staff and which address both the use of technology and instructional design aimed at promoting the development of self-regulated learning (SRL) and automatic feedback systems. In this study, work was carried out with 23 teachers (8 inexperienced and 15 experienced teachers) in a training programme conducted through Moodle. The aims were: (1) to test whether there were any significant differences between the behaviour patterns of new teachers compared to experienced teachers, (2) to determine whether clusters of behaviour patterns corresponded to the type of teacher and (3) to ascertain whether the level of teacher satisfaction with the training activity in digital teaching will depend on the type of teacher. A quantitative as well as a qualitative design was applied. Differences were found in the behaviour patterns in the training activities for the development of rubrics and use of learning analytics systems in virtual learning environments. It was also found that the type of teacher did not correspond exactly to the behaviour cluster in the learning platform. In addition, no significant differences were found in the level of satisfaction between the two kinds of teacher. The main contribution this study makes is to provide a detailed description of the training stage as well as the materials required for its repetition. Further analytical studies are required on teacher perception of training programmes in digital teaching in order to provide personalised training proposals that lead to an effective use of teaching in digital environments.

Towards a robust and trustworthy machine learning system development: An engineering perspective

While Machine Learning (ML) technologies are widely adopted in many mission critical fields to support intelligent decision-making, concerns remain about system resilience against ML-specific security attacks and privacy breaches as well as the trust that users have in these systems. In this article, we present our recent systematic and comprehensive survey on the state-of-the-art ML robustness and trustworthiness from a security engineering perspective, focusing on the problems in system threat analysis, design and evaluation faced in developing practical machine learning applications, in terms of robustness and user trust. Accordingly, we organize the presentation of this survey intended to facilitate the convey of the body of knowledge from this angle. We then describe a metamodel we created that represents the body of knowledge in a standard and visualized way. We further illustrate how to leverage the metamodel to guide a systematic threat analysis and security design process which extends and scales up the classic process. Finally, we propose the future research directions motivated by our findings. Our work differs itself from the existing surveys by (i) exploring the fundamental principles and best practices to support robust and trustworthy ML system development, and (ii) studying the interplay of robustness and user trust in the context of ML systems. We expect this survey provides a big picture for machine learning security practitioners.

Development of computer-based learning system for learning behavior analytics

<p>This paper aims to analyze the learning behavior of Thai learners by using a computer-based learning system for English writing. Three main objectives were set: the development of a computer-based learning system, automatic behavior data collection, and learning behavior analytics. Firstly, the system is developed under a multidisciplinary idea that is designed to integrate two concepts between the self-regulated learning model and components of natural language processing. The integration design encourages self-learning in the digital learning environment and supports appropriate English writing by the provided component selection. Second, the system automatically collects the writing behavior of a group of Thai learners. The data collected are necessary input for the process of learning analytics. Third, the writing behaviors data were analyzed to find the learning behavioral patterns of the learners. For learning analytics, behavior sequential analysis was used to analyze the learning logs from the system. The 31 undergraduate students are participated to record writing behaviors via the system. The learning patterns in relation to grammatical skills were compared between three groups: basic, intermediate, and advanced levels. The learning behavior patterns of the three groups are different that use for reflecting learners and improving the learning materials or curriculum.</p>

Application GIS and remote sensing for soil organic carbon mapping in a farm-scale in the hilly area of central Vietnam

Soil Organic Carbon (SOC) influences many soil properties including nutrient and water holding capacity, nutrient cycling and stability, improved water infiltration and aeration. It also is an essential parameter in the assessment of soil quality, especially for agricultural production. However, SOC mapping is a complicated process that is costly and time-consuming due to the physical challenges of the natural conditions that is being surveyed. The best model for SOC mapping is still in debate among many researchers. Recently, the development of machine learning and Geographical Information Systems (GIS) has provided the potential for more accurate spatial prediction of SOC content. This research was conducted in a relatively small-scale capacity in the Central Vietnam region. The aim of this study is to compare the accuracy of Inverse Distance Weighting (IDW), Ordinary Kriging (OK), and Random Forest (RF) methods for SOC interpolation, with a dataset of 47 soil samples for an area of 145 hectares. Three environmental variables including elevation, slope, and the Normalized Difference Vegetation Index (NDVI) were used for the RF model. In the RF model, the values of the number of variables randomly sampled as candidates at each split, (mtry), and the number of bootstrap replicates, (ntree), were determined in terms of 1 and 1,000 respectively The results at our research site showed that using IDW is the most accurate method for SOC mapping, followed by the methods of RF and OK respectively. Concerning SOC mapping based-on auxiliary variables, in areas where there is human activity, the selection of auxiliary variables should be carefully considered because the variation in the SOC may not only be due to environmental variables but also by farming technologies.

Development of remote learning system in higher educational institutions of the Russian Federation: from local practice to integration into the digital university model

Development of remote learning system in higher educational institutions of the Russian Federation: from local practice to integration into the digital university model

Adaptation of the procedure for designing local learning systems to the requirements of system engineering

The article clarifies the requirements of system engineering for the procedure of designing local learning systems. On the basis of comparative analysis of these requirements with the procedure of designing the learning process generally accepted in pedagogy, the essence of the inconsistencies of individual pedagogical design procedures with the requirements of system engineering is revealed. The causes of the identified inconsistencies and approaches to their elimination are analyzed. The difference in the approaches of system engineering (pragmatic approach) and pedagogy (research approach) to the definition of design goals is considered as the main cause of the identified inconsistencies. The prospects of developing a practical (pragmatic) variant of pedagogical design are substantiated and a variant of the V–model of the system engineering method is presented, which is focused on the development of local learning systems.

Adaptive learning model for prin ted circuit boards (pcb) module designing in an intelligent learning system

The prospects for the adaptation usage in an intelligent learning system for designing modules based on printed circuit boards (PCB) are considered. Models of primary adaptation, training scenario, trained designer, adaptation of training materials, subject area, testing and practical tasks are created. The use of models in an adaptive learning system allows you to build a learning process aimed at consistent and unconditional learning of educational material for different levels of students. The practical significance of the work lies in the program for the implementation of the proposed models of adaptive control of the learning process according to the individual characteristics of the student in the development of an intelligent adaptive learning system. The results of the study have found practical application at the stages of the project development cycle at the Vietnamese shipyard X52 to increase the level of engineer competence in the design of modules based on PCB. Keywords adaptation, adaptive learning, intelligent learning system, module design, printed circuit board (PCB)

Development of remote learning system in higher educational institutions of the Russian Federation: from local practice to integration into the digital university model

The experience of remote learning during the pandemic COVID-19 significantly accelerated the process of digitalisation of the higher education in Russia and intensified preparations for the transition to a model of the Digital University. However, even those educational institutions that successfully applied remote technologies in the educational process faced the problem of effectively managing the entire remote learning system. The aim of the study is to identify the management potential of remote learning at universities in Russia from the point of view of the methodology of active management systems. Models of the remote learning system in institutions of higher education relevant for different stages of development have been created; recommendations are made to integrate the proposed models into the Digital University model. Research results contribute to the development of the theory and practice of active management systems in terms of modelling remote learning in institutions of higher education.

INSTINCT AS A QURANIC CONCEPT & ITS ROLE IN ISLAMIC PEDAGOGY: A GENERAL OVERVIEW

Islamic pedagogy is an approach refers to the influence of Islamic values on the theory and practice of learning and how it is reshaping the relation between learners and Islamic knowledge. Muslim scholars had their contribution in finding and improving an Islamic pedagogy through Maqasid al-Shari’ah and practicing of learning. However, their great effort is not highlighted academically to show the possible application of Islamic pedagogy in the modern schools and how to encounter the challenges of secular philosophical trends and the implications of current educational systems. The researchers followed a descriptive method to analyse and criticise the data collected by induction from the writings of Ibn “Ashur about Maqasid al-Shari’ah and the works of Abdessalam Yassine on Islamic pedagogy. The researchers found that Ibn “Ashur set instinct as a foundation for Maqasid which, through it, many fractions of Islamic law could be regulated, while Yassine utilized his long experience of being a teacher and educational inspector to observe the role of the Quranic instinct in Islamic pedagogy and the development of learning system.

Development Content Learning System (CLS) Material Corrosion Based on Project Base Learning (PjBL) with Shortened Flipped Classrooms in SMA MA

This study goals is to produce an e-learning to help students understand chemistry lesson eventough they can’t study in class or study in a normal condition. This research is focused development of content learning system e-learning on corossion topic based on project-based learning model using flipped classroom. This study is a research and development (R&D) method to produce a particular product, and test the effectiveness of the product. The data collection techniques used is questionnaire of product evaluation. The e-learning product validation conducted by postgraduates students of educational chemistry from Universitas Negeri Padang. The validation analysis was carried out using V aiken index. The validation of 3 aspects of content validity shows is Guide and information, this components show the average result of V about 0.833, it means this component is valid. The average result of V for material content is 0.838 and for evaluation is 0.84.For the construct validity for guide and information, which the V average result is 0.796. For the program performance the v result is 0.83 and in the design principles shows 0.777 of v result. This result conclude that the e-learning product is valid, and can be use for learning process in Senior High School.

Benefits of Adaptive Learning Transfer From Typing-Based Learning to Speech-Based Learning.

Memorising vocabulary is an important aspect of formal foreign-language learning. Advances in cognitive psychology have led to the development of adaptive learning systems that make vocabulary learning more efficient. One way these computer-based systems optimize learning is by measuring learning performance in real time to create optimal repetition schedules for individual learners. While such adaptive learning systems have been successfully applied to word learning using keyboard-based input, they have thus far seen little application in word learning where spoken instead of typed input is used. Here we present a framework for speech-based word learning using an adaptive model that was developed for and tested with typing-based word learning. We show that typing- and speech-based learning result in similar behavioral patterns that can be used to reliably estimate individual memory processes. We extend earlier findings demonstrating that a response-time based adaptive learning approach outperforms an accuracy-based, Leitner flashcard approach in learning efficiency (demonstrated by higher average accuracy and lower response times after a learning session). In short, we show that adaptive learning benefits transfer from typing-based learning, to speech based learning. Our work provides a basis for the development of language learning applications that use real-time pronunciation assessment software to score the accuracy of the learner’s pronunciations. We discuss the implications for our approach for the development of educationally relevant, adaptive speech-based learning applications.

Investigating Online Learning Satisfaction in Jordan Schools during the COVID-19 Outbreak: The Student Perspective

In the past two years, the flare-up of the COVID-19 pandemic in Jordan has turned traditional education into online teaching, which impacted the education quality. This studyuses an integrated model of UTAUT model, ISS model, and quality of interaction to study the online learning satisfaction in Jordan from the students' point of view during the COVID-19 outbreak. For such purpose, a questionnaire survey was distributed among students from five different Jordanian schools to gather the data, and the SmartPLS tool was used to analyze this data. The results showed that all the employed factors in the proposed model significantly influenced the students' satisfaction with online learning throughout the COVID-19 pandemic proliferation. Thus, these research results will be a significant reference for educational institutes, decision-makers, developers, and researchers on the significant factors that influence students' satisfaction with online learning, which in turn can improve the development of online learning systems.

Development and Application of an Augmented Reality Oyster Learning System for Primary Marine Education

Marine knowledge is such an important part of education that it has been integrated into various subjects and courses across educational levels. Previous research has indicated the importance of AR assisted students’ learning during the learning process. This study proposed the AR Oyster Learning System (AROLS) that integrates mobile AR with a marine education teaching strategy for teachers in primary schools. To evaluate the effectiveness of the proposed approach, an experiment was conducted in a primary school natural science course regarding oysters. The participants consisted of 22 fourth-grade students. The experimental group comprised 11 students who learned with the AROLS learning approach and the control group comprised 11 students who learned with the conventional multimedia learning approach. The results indicate that (1) students were interested in the AR learning approach, (2) students’ learning achievement and motivation were improved by the AR learning approach, (3) students acquired the target knowledge through the oyster course, and (4) students learned the importance of sustainability when taking online courses at home during the pandemic.

Polynomial Approximations for Several Neural Network Activation Functions

Active deployment of machine learning systems sets a task of their protection against different types of attacks that threaten confidentiality, integrity and accessibility of both processed data and trained models. One of the promising ways for such protection is the development of privacy-preserving machine learning systems, that use homomorphic encryption schemes to protect data and models. However, such schemes can only process polynomial functions, which means that we need to construct polynomial approximations for nonlinear functions used in neural models. The goal of this paper is the construction of precise approximations of several widely used neural network activation functions while limiting the degree of approximation polynomials as well as the evaluation of the impact of the approximation precision on the resulting value of the whole neural network. In contrast to the previous publications, in the current paper we study and compare different ways for polynomial approximation construction, introduce precision metrics, present exact formulas for approximation polynomials as well as exact values of corresponding precisions. We compare our results with the previously published ones. Finally, for a simple convolutional network we experimentally evaluate the impact of the approximation precision on the bias of the output neuron values of the network from the original ones. Our results show that the best approximation for ReLU could be obtained with the numeric method, and for the sigmoid and hyperbolic tangent – with Chebyshev polynomials. At the same time, the best approximation among the three functions could be obtained for ReLU. The results could be used for the construction of polynomial approximations of activation functions in privacy-preserving machine learning systems.