Design Of Learning Systems Research Articles

RETRACTED ARTICLE: Towards secure deep learning architecture for smart farming-based applications

The immense growth of the cloud infrastructure leads to the deployment of several machine learning as a service (MLaaS) in which the training and the development of machine learning models are ultimately performed in the cloud providers’ environment. However, this could also cause potential security threats and privacy risk as the deep learning algorithms need to access generated data collection, which lacks security in nature. This paper predominately focuses on developing a secure deep learning system design with the threat analysis involved within the smart farming technologies as they are acquiring more attention towards the global food supply needs with their intensifying demands. Smart farming is known to be a combination of data-driven technology and agricultural applications that helps in yielding quality food products with the enhancing crop yield. Nowadays, many use cases had been developed by executing smart farming paradigm and promote high impacts on the agricultural lands.

Procurement As Policy: Administrative Process for Machine Learning

At every level of government, officials contract for technical systems that employ machine learning-systems that perform tasks without using explicit instructions, relying on patterns and inference instead. These systems frequently displace discretion previously exercised by policymakers or individual front-end government employees with an opaque logic that bears no resemblance to the reasoning processes of agency personnel. However, because agencies acquire these systems through government procurement processes, they and the public have little input into-or even knowledge about-their design or how well that design aligns with public goals and values. This Article explains the ways that the decisions about goals, values, risk, and certainty, along with the elimination of case-by-case discretion, inherent in machine-learning system design create policies-not just once when they are designed, but over time as they adapt and change. When the adoption of these systems is governed by procurement, the policies they embed receive little or no agency or outside expertise beyond that provided by the vendor. Design decisions are left to private third-party developers. There is no public participation, no reasoned deliberation, and no factual record, which abdicates Government responsibility for policymaking. This Article then argues for a move from a procurement mindset to policymaking mindset. When policy decisions are made through system design, processes suitable for substantive administrative determinations should be used: processes that foster deliberation reflecting both technocratic demands for reason and rationality informed by expertise, and democratic demands for public participation and accountability. Specifically, the Article proposes administrative law as the framework to guide the adoption of machine learning governance, describing specific ways that the policy choices embedded in machine learning system design fail the prohibition against arbitrary and capricious agency actions absent a reasoned decision-making process that both enlists the expertise necessary for reasoned deliberation about, and justification for, such choices, and makes visible the choices being made. Finally, this Article sketches models for machine-learning adoption processes that satisfy the prohibition against arbitrary and capricious agency actions. It explores processes by which agencies might garner technical expertise and overcome problems of system opacity, satisfying administrative law's technocratic demand for reasoned expert deliberation. It further proposes both institutional and engineering design solutions to the challenge of policymaking opacity, offering process paradigms to ensure the political visibility required for public input and oversight. In doing so, it also proposes the importance of using contestable design-design that exposes value-laden features and parameters and provides for iterative human involvement in system evolution and deployment. Together, these institutional and design approaches further both administrative law's technocratic and democratic mandates.

Application of Context-Aware and Collaborative Mobile Learning System Design Model in Interactive E-Book Reader Using Design Thinking Methods

800x600 Normal 0 false false false EN-US X-NONE X-NONE MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:Table Normal; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin:0in; mso-para-margin-bottom:.0001pt; mso-pagination:widow-orphan; font-size:10.0pt; font-family:Times New Roman,serif;} E-books as a learning medium have been widely used and utilized to support learning processes. The presence of e-books as digital books can be accepted by users because of the interactive content and display. However, the current format of e-book has not provided a mechanism/platform that accommodates contemporary learning styles on a two-way networked learning basis. E-books are more static in the sense that it has minimal interaction context. E-books have not been able to integrate learners with their learning environment in an interaction construct to support a learning activity. To address this problem, this study recommends a new approach called context-aware and collaborative mobile learning system design model. The method used in implementing the design model is design thinking . Usability testing using the guerrilla usability testing method is carried out to determine the quality of the e-books produced. The results obtained at the stages of empathize and define produced list and learning problems experienced by students when using e-books. The ideate and prototype stages produced e-book prototypes developed based on context-aware and collaborative mobile learning system design model. In the test stage, usability testing of 30 students showed good results. It is said to be good because there are no assignments with a score of one in the rubric usability testing table. So it can be concluded that the design model applied to the prototype e-book is feasible and can be understood by users . 800x600 Normal 0 false false false EN-US X-NONE X-NONE MicrosoftInternetExplorer4

Development of Learning Tools by Applying The MASTER Plan Technique Based on A Scientific Approach to Improve Student Learning Outcomes on Number Pattern Material

This research is motivated by the lack of optimal learning outcomes of students due to the lack of learning devices that are considered being able to train students’ abilities in solving problems. The purpose of this study is to develop mathematics learning tools that meet the validity, practicality, and effectiveness requirements to improve the learning outcomes of grade VIII students of SMP / MTs on material number patterns. The development model used is the ADDIE model for designing learning systems. The instruments used were syllabus validation instruments, RPP, LKPD, practicality instruments and effectiveness instruments. The technique used is the technique of collecting observation data, interviews, questionnaire documentation and tests. Mathematics learning to use the MASTER Plan technique based on a scientific approach is already valid with the results of syllabus validation 84.25%, RPP 90.30%, LKPD 86.50%. This learning device fulfills the practical requirements for large group trials with an average of 93.52% results and an average student questionnaire response rate of 95.66%. The use of effective learning tools to improve student learning outcomes for KKM achievement is 83.33%.

When the Clock Strikes: Exploring the Mindset Effects of Temporal Cues in Gamified Online Learning Systems

Gamification has been widely employed in online learning systems to enhance users’ gratification and to retain them from dropping out. Compared with core learning modules, gamification modules provide more hedonic value, which increases user engagement in the short term but these modules may also cause distraction and impede learning performance. Thus, time management and self-control are crucial for users of online learning systems. Our study proposes that users tend to treat on-the-hour time points (i.e., the strike of the traditional clock) as temporal cues, which substantially influence their interactions with the core learning versus gamification modules, as well as both the instrumental and experiential outcomes of these interactions. Through a set of three multi-method studies that focus on the sharp clock-striking time points, we find that i) users are more (versus less) likely to begin using core learning modules (versus gamification modules) after clock-striking time points; ii) beginning the use of core learning modules at clock-striking time points has a positive relationship with learning persistence and learning performance; iii) beginning the use of gamification modules at clock-striking time points results in a lower level of perceived enjoyment than beginning at random time points. Further, the results of studies 2 and 3 indicate that clock-striking time points can activate users’ implemental mindset, which supports them in building a longer learning persistence and achieving better learning performance. Our findings add to the design of online learning systems by understanding the mindset effects of temporal cues in user-system interactions of gamified learning systems, based on which notification and reminder systems can be implemented to further facilitate the effectiveness of online learning.

Trends in Expert System Development: A Practicum Content Analysis in Vocational Education for Over Grow Pandemic Learning Problems

The impact of the COVID-19 has emerged as a varied issue, ranging from the economy, society's social order, and edu­cation, especially when social and physical distancing have been introduced in various areas of community activities as one of the prevention. It has also affected the tertiary edu­cation institution where learning activities should be con­ducted from and at home, forcing the higher education communities to shift learning from conventional learning to online learning. Needless to say, learning that does not re­quire practicum is easier compared to learning that needs it. Consequently, it is a new task for lecturers to ensure the meaningful practicum learning implementation is con­ducted as it should be. Therefore, the creation of expert systems for practicum learning in vocational education is urgently required in online learning. The aim of this litera­ture review was to examine the development of an expert system used at practicum learning in tertiary institutions and how the design of learning systems could be integrated into vocational education in facing the COVID-19 pandemic. The method used was the literature study, through research stages starting from the finding and selection of articles and journals with relevant topics, and then analysing the data. The findings of this study was to identify the development of an expert program in an attempt to promote practicum learning using e-learning in the midst of the COVID-19 pan­demic outbreak.

Застосування технології глибинного навчання для побудови інтелектуальних автономних машин

One of the most common tasks that arise in building intelligent machine vision systems for intellectually autonomous machines is the problems of classification and regression. Classification problems are used for the reflexive action of autonomous machines. Prediction tasks can be used to build machine vision systems to provide intelligent autonomous machines with environmental knowledge, which in turn is important for planned predictable movements. Defining a class of task instances is an important procedure for the effective design of deep learning systems. In this context, the possibility of using a multilayered neural network as a regressor to construct elementary functional mappings is explored for further prediction. The study outlines the peculiarities of functioning and configuration of a specialized robotics system, considered in this paper as an intelligent autonomous machine or physical agent, generates a set of data points for elementary functions, analytical modeling and modeling of training systems. Input graph was constructed, neural network architecture was defined, gradient descent algorithm was implemented, and output schedules were finally constructed: learning process, results prediction and comparative graph of predicted results superimposed on the input graph. As a result of the study, an assessment of the machine's intellectual ability to predict was made.

Enhancing Instructor Credibility and Immediacy in the Design of Distance Learning Systems and Virtual Classroom Environments

What are the optimal techniques for applying the latest generation of telepresence, video conferencing, and communication technologies in distance education and virtual classroom designs? If human beings use more than voice to communicate, what implications does the ability to more effectively replicate eye-to-eye contact have in collaborative distance education? This research study explored the effects of perceived faculty credibility and immediacy during virtual classroom presentations. This quantitative experiment created four independent treatments that varied the video resolution and varied the ability of the instructor to maintain virtual eye-contact with students during each presentation. Participants were assigned into one of the four treatment groups, each listening to the same instructor narration and viewing the same instructor present the same subject matter, only the resolution and camera angle differed. A series of 2x2 Analysis of Variances were conducted on independent groups where an instructor was simultaneously recorded from two high-definition (1920x1080) cameras, one at eye-level and one located 15-degrees above eye-level, during the delivery of a 20-minute instructional module. These two camera angles were also replicated in a lower resolution (320x240). A total of 108 undergraduate and graduate participants completed the video and audio multimedia presentations and completed credibility and immediacy survey instruments. The results suggest that the position of the instructor's camera is more important than the resolution of the recorded video.

Understanding adversarial attacks on deep learning based medical image analysis systems

Deep neural networks (DNNs) have become popular for medical image analysis tasks like cancer diagnosis and lesion detection. However, a recent study demonstrates that medical deep learning systems can be compromised by carefully-engineered adversarial examples/attacks with small imperceptible perturbations. This raises safety concerns about the deployment of these systems in clinical settings. In this paper, we provide a deeper understanding of adversarial examples in the context of medical images. We find that medical DNN models can be more vulnerable to adversarial attacks compared to models for natural images, according to two different viewpoints. Surprisingly, we also find that medical adversarial attacks can be easily detected, i.e., simple detectors can achieve over 98% detection AUC against state-of-the-art attacks, due to fundamental feature differences compared to normal examples. We believe these findings may be a useful basis to approach the design of more explainable and secure medical deep learning systems.

Engineering problems in machine learning systems

Fatal accidents are a major issue hindering the wide acceptance of safety-critical systems that employ machine learning and deep learning models, such as automated driving vehicles. In order to use machine learning in a safety-critical system, it is necessary to demonstrate the safety and security of the system through engineering processes. However, thus far, no such widely accepted engineering concepts or frameworks have been established for these systems. The key to using a machine learning model in a deductively engineered system is decomposing the data-driven training of machine learning models into requirement, design, and verification, particularly for machine learning models used in safety-critical systems. Simultaneously, open problems and relevant technical fields are not organized in a manner that enables researchers to select a theme and work on it. In this study, we identify, classify, and explore the open problems in engineering (safety-critical) machine learning systems—that is, in terms of requirement, design, and verification of machine learning models and systems—as well as discuss related works and research directions, using automated driving vehicles as an example. Our results show that machine learning models are characterized by a lack of requirements specification, lack of design specification, lack of interpretability, and lack of robustness. We also perform a gap analysis on a conventional system quality standard SQuaRE with the characteristics of machine learning models to study quality models for machine learning systems. We find that a lack of requirements specification and lack of robustness have the greatest impact on conventional quality models.

HUBUNGAN TINGKAT KECEMASAN KOMUNIKASI DENGAN KEAKTIFAN MAHASISWA KEDOKTERAN DALAM DISKUSI PROBLEM BASED LEARNING

ABSTRACT
 
 Background: Problem-Based Learning (PBL) is a strategic learning system design which aimed at enhancing and optimizing the collaborative learning, contextual and self- directed. Factors that influence PBL’s success are a good scenario, responsible facilitator and students who can be able to active in PBL. Factors such us lack of preparation, communication skills and anxiety can affect the activeness. This study aims to determine the relationship between anxiety level of communication with activeness on PBL. 
 Methods: The design of study was cross sectional quantitative. The sample in this study were 240 respondents. with a total sampling technique. Anxiety level of communication’s data obtained through anxiety scale communication and activeness on PBL get by instrument of activeness. The analysis test using chi- square. 
 Result: There is a significant relationship between anxiety level of communication with activeness on PBL with p = 0,000 (p<0,05). 
 Conclusions: There was a relationship between anxiety level of communication with activeness on PBL medical student of Lampung University.
 

From Design to Management of Digital Epistemic Games

The development of pedagogies that can provide alternatives to traditional approaches is becoming increasingly important as a means of enhancing the attractiveness of training courses, appealing to new types of learners and designing learning systems that help to develop multidisciplinary skills. In this context, the JEN.lab project aims to offer innovative perspectives for learning based on the design of digital epistemic games (JENs in French). The research effort presented in this paper is part of the JEN.lab project. We aim to study problems related to the modelling and design of digital epistemic games. We propose a co-design process and an assistant tool supporting this process to guide teachers in designing digital epistemic games called ADDEGames (Assistance Design tool for Digital Epistemic Games). Our approach is based on: (i) the learners and the situation that emerges when they play the game, rather than the device used to play; and (ii) the teachers who want to manage a game-based learning situation. The iterative and participative development process and acceptance test using an agile approach are presented.

Automatic waste detection by deep learning and disposal system design

As Dubai aims to become a greener city by the year 2021, efforts are currently being made by the government to devise a more efficient and innovative approach to tackling solid-waste-management issues in the city. With a much higher rate of recycling of trash, there arises a need to find a better approach to classifying this trash with increased efficiency. Machine learning techniques can be employed to classify trash into different recycling categories so that it is easier to recycle waste. In this paper, an automatic waste-classification system is proposed using a deep learning algorithm to classify waste as metal, paper, plastic and non-recyclable waste. The classification was performed through this computer vision approach by using the AlexNet convolutional neural network architecture in real time so that the waste can be dropped into the appropriate chambers as soon as it is thrown into dustbins. The data set used to train the system consisted of images collected from the Internet, as well as hand-collected images. The model used was tested for classification of different types of trash and was found to show a high accuracy, as discussed in the result section.

DEVELOPING ICT-BASED CALCULUS LEARNING MEDIA

The purpose of this study is to produce information and communication technology/ICT-based calculus learning media that meets the valid, practical, and effective criteria. This type of research is development research. The development model used is the ADDIE model. According to Pribadi (2009: 125) one of the learning system design models with basic stages of learning system design that is simple and easy to learn is the ADDIE model. ADDIE stands for Analysis, Design, Development, Implementation, and Evaluation. The ADDIE model was developed by Reiser and Mollenda (Branch. 2009: 17-18). Validity data was obtained from validation results by material experts, media experts, and user lecturers. While practicality data is obtained from lecturers' decisions, student responses and the implementation of the learning process (lectures). For effectiveness analysis, it is done by determining the percentage of students who reach the minimum high category for the motivation questionnaire and determining the percentage of completeness of students' scores on classical learning achievement tests. Modules will be categorized as valid and practical if each review minimally is considered to the "good" category, whereas it is effective if students who achieve classical completeness of at least 80% for achievement tests and a minimum questionnaire assessment of the "good" category.

A user-centered, learning asthma smartphone application for patients and providers.

ProblemSmartphone applications are an increasingly useful part of patients' self‐management of chronic health conditions. Asthma is a common chronic health condition for which good self‐management by patients is very helpful in maintaining stability. User‐centered design and intelligent systems that learn are steps forward in building applications that are more effective in providing quality care that is scalable and tailored to each patient.MethodsA literature and application store search to review historic and current asthma smart phone applications. User‐centered design is a methodology that involves all stakeholders of a proposed system from the beginning of the design phase to the end of installation. One aspect of this user‐centered approach involved conducting focus groups with patients and health care providers to determine what features they desire for use in applications and create a model to build smart infrastructure for a learning health care system. A simple prototype for an asthma smartphone application is designed and built with basic functionality.OutcomesOnly one publication in the literature review of asthma smartphone applications describes both user‐centered design and intelligent learning systems. The authors have presented a set of user‐desired attributes for a smart health care application and a possible data flow diagram of information for a learning system. A prototype simple user‐centered designed asthma smartphone application that better assists patients in their care illustrates the value of the proposed architecture.DiscussionOur user‐centered approach helped design and implement a learning prototype smart phone application to help patients better manage their asthma and provide information to clinical care providers. While popular in other industries, user‐centered design has had slow adoption in the health care area. However, the popularity of this approach is increasing and will hopefully result in mobile application that better meets the needs of both patients and their care providers.

Interface Xperience

Digital technology has proven to enhance learning outcomes across educational sectors and contexts, yet critical challenges remain, notably: minimising the decay of digital interventions over time; and, achieving widespread learning outcomes in diverse, multicultural and complex settings (Aguayo, 2016; Dunn & Marinetti, 2008; Hennessy et al., 2019). One ambitious solution to these challenges may lie in a theoretical concept coming from biology called ‘autopoiesis’. Autopoiesis, literally meaning self-making, defines living organisms as self-organising units capable of adapting to unpredictable changes in their environments while maintaining internal coherence over time (Maturana & Varela, 1980). The Santiago school of cognition (Luisi, 2016), founded on the concept of autopoiesis, considers this adaptive capacity of living organisms towards their environment as an ‘intelligent’ and ‘cognitive’ process. But most importantly, it establishes that human experience and cognition are unique to every individual and context (Thompson, 2007). This has profound epistemological consequences when designing digital technology in education, as the dominant ‘one solution fits all’ paradigm becomes invalid; on the contrary, digital technology and their associated educational processes on learners ought to provide as many (intelligent) solutions as individuals and contexts there are (Aguayo, 2018, 2019). Hence, from the perspective of the Santiago school, the notion of ‘user experience design’ (UX design) is inadequate.
 
 Based on the above, Aguayo (2018) proposes that digital technology can be embedded with autopoietic properties found in living systems during the design of the ‘user interface’ (UI design), potentially creating ‘intelligent’ technology-enhanced learning tools, platforms, affordances, experiences and/or systems that can, in theory, self-adapt to changing conditions and socio-culturally different learners over time. This means that during the process of creating digital technology tools and affordances – or ‘systems’, the focus should be on developing adaptable and flexible interfaces that can actively facilitate the learning process and learning experience on users – a process termed here as ‘interface experience design’ or IX design. Such an epistemological view of technology-enhanced learning design becomes important given that learners bring into the learning process complex and unpredictable socio-cultural and emotional backpacks that determine their own learning experience in unique ways. Ultimately, the aim behind the notion of IX design is to promote a more efficient and adaptable type of design, development and use of technology-enhanced learning systems over time. In this session, the underlying theoretical and conceptual arguments from the Santiago school of cognition for reconsidering UI/UX design in technology-enhanced learning will be introduced and explored in relation to promoting adaptable and long-lasting meaningful learning processes on diverse audiences.

Working with the Community: Reflections from an Instructional Design Service-Learning Project

As part of an instructional design course, EDCI 572 (Learning Systems Design), we completed a service project developing a face-to-face training for volunteer coordinators for United Way of Greater Lafayette. United Way promotes activities to encourage civic engagement and make a positive change in the community. A network of community members and organizations facilitate a larger community impact in collaboration with United Way. One part of this partnership is the United Way training for volunteer coordinators of different nonprofit organizations. Under the supervision of Dr. Seçil Caskurlu, we applied instructional design models to design and develop face-to-face training modules in consultation with a subject matter expert. This face-to-face training covered four topics: skill-based volunteering, recruitment, retention, and recognition. Students gained several skills from this service project, including experience in developing and creating learning solutions that drive measurable impact to the organization and align to organization’s and learner’s needs; experience in developing face-to-face learning experiences; experience applying instructional design models; communication, teamwork, and problem-solving skills; and strong organizational and time management skills. Thus, this authentic learning experience helped us develop instructional design skills by building practical knowledge and hands-on experience. Additionally, we received funding from the Community Service/Service-Learning Student Grant Program, which was used to support a showcase event where we presented this service project and shared our experiences. This event had the objectives of increasing awareness of course-based service projects, potentially creating new partnerships within the community, and allowing students to practice public speaking skills. In this service project, not only were concepts and theories taught, but they were applied to a real-world context and went beyond the conventional hypothetical classroom scenarios. The challenge to work for a real client, that helps communities grow, added an extra motivation to do our best.

User-Centred Design in Content Management System Development: The Case of EMasters

Including users in design and development of an interactive product is crucial to achieve high level of usability. Content management systems have two categories of users, content creators and content consumers, and designers of these systems have to considers the needs of both user groups. In design of interactive learning systems, special attention has to be given to the process of learning, which means that functional, accessible and usable interface has to serve the purpose of knowledge acquisition. Designing for mobile learning brings additional challenges due to the small screens of mobile devices. The paper describes the process of utilization of user-centred design in development of a simple content management system for learning called EMasters. The aim of the EMasters is to enable teachers to easily create and organize courses which will be delivered to students to facilitate web-based and mobile learning. According to the user-centred design approach, teachers and students are involved in iterative process of design, implementation and evaluation of EMasters. Evaluation study used complementary methods and provided quantitative and qualitative feedback. The usability score reached good level and the guidelines for redesign of the system interface are drown. According to the obtained results, proposed framework is confirmed to be applicable in user-centred design of content management systems in general. In addition, the directions for adjustment of the framework for specific cases are provided.

The Development of Blended Learning Theories of Learning Course for Educational Technology Student in FIP UNY

Education is intended to develop students’ potential ability to respond the emergent local, national, and global phenomenon. However, today’s disruption era has forced educational institutions to better prepare the students in facing the global dynamics. Thus, Educational Technology Department in Faculty of Ilmu Pendidikan UNY (State University of Yogyakarta) attempts to facilitate the students with various abilities to accommodate the needs above. Therefore, this research is aimed to develop Blended Learning learning model which is implemented in Teori Belajar dan Pembelajaran (Learning and Instruction Theory) course. This research adopts procedure of Borg and Gall (1983), learning system design model of C. M. Reigeluth, and combined with E. L. Criswell & Luther model, by; a) conducting preliminary research, b) devising plans, c) developing prototype model, d) testing materials and model experts followed by revisions, e) running user tests, and f) carrying out field experiment. Research produces Blended Learning learning model in Teori Belajar dan Pembelajaran course for undergraduates of Educational TechnologyDepartmentinFacultyofIlmuPendidikanUNYemploying besmart version 2 e-learning owned by UNY. To conclude, Blended Learning has proven feasible to be executed successfully, both from materials and learning media point of view as well as its convenience when used by students.

Pengembangan Bahan Ajar Berbasis Addie Model

Instructional material are an important part in determining the quality of learning. The design of the development of instructional material needs to pay attention to the development model to ensure the quality of instructional material in supporting learning effectiveness, because the development of instuctional material is basically a linear process with the learning process. One of the designs for the development of instructional material that is often used is the ADDIE Model through 5 stages; Analysis, Design, Development, Implementation and Evaluation. The ADDIE model is a learning system design model that shows the basic stages of a learning system that is easy to do.