Concerns about learning how to write are ubiquitous in elementary schools across the world, one reason why this is the case is that many students received insufficient writing instruction in elementary classrooms. The lack of specific instructional practice and adaptions have impeded students’ writing development. Given the changing nature of literacy and the importance of early writing, integrating technology and writing in elementary classrooms provided a potential solution for this problem. This paper examined 20 empirical studies published between 1990 and 2020 by conducting a meta-analysis to measure the impact of technology on the writing performances of elementary students. The results of this meta-analysis confirmed that technology has a medium effect on writing quality and a strong effect on writing quantity for elementary school students. Subsequently, the authors analyzed the effect sizes of moderating variables by including study features such as types of technology integration, writing genres, demographics, and methodological characteristics. The authors have found that the type of technology integration and writing genres are two important variables affecting the casual relationship of technology and writing performances for elementary students. This aspect has been overlooked by previous literature. The novel findings indicated how we can address writing issues and change classroom writing practices for the better across the world by increasing stakeholders’ awareness about the importance of elementary school writing, with the goal of developing visions for curriculum and instruction at the classroom, school, and policy levels. Recommendations for more research on elementary school writing with advanced technology were discussed. 

The Impact of Technology on Students’ Writing Performances in Elementary Classrooms: A Meta-Analysis

Heart diseases are the leading cause of deaths nowadays. Due to the high severity of the problem, it has attracted several researchers around the globe. Researchers have considered the heart diagnosis as a classification problem where meaningful patterns are detected using data mining techniques. This paper presents an evaluation of various supervised learning algorithms and feature selection techniques for heart disease prediction. The performance of six machine learning classifiers (Naive Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine, k-Nearest Neighbour) and five feature selection techniques (Chi-Square, Gain Ratio, Information Gain, One-R and RELIEF) have been investigated on the benchmark dataset obtained from UCI Machine Learning Repository, Cleveland. The experimental results show that machine learning classifiers can achieve prediction accuracy up to 82.81% for heart disease prediction. The feature selection techniques further improve the classification performance and achieve prediction accuracy up to 83.41%.

Heart Disease Diagnosis: Performance Evaluation of Supervised Machine Learning and Feature Selection Techniques

Parkinson's disease (PD) is a neurodegenerative disorder with slow progression whose symptoms can be identified at late stages. Early diagnosis and treatment of PD can help to relieve the symptoms and delay progression. However, this is very challenging due to the similarities between the symptoms of PD and other diseases. The current study proposes a generic framework for the diagnosis of PD using handwritten images and (or) speech signals. For the handwriting images, 8 pre-trained convolutional neural networks (CNN) via transfer learning tuned by Aquila Optimizer were trained on the NewHandPD dataset to diagnose PD. For the speech signals, features from the MDVR-KCL dataset are extracted numerically using 16 feature extraction algorithms and fed to 4 different machine learning algorithms tuned by Grid Search algorithm, and graphically using 5 different techniques and fed to the 8 pretrained CNN structures. The authors propose a new technique in extracting the features from the voice dataset based on the segmentation of variable speech-signal-segment-durations, i.e., the use of different durations in the segmentation phase. Using the proposed technique, 5 datasets with 281 numerical features are generated. Results from different experiments are collected and recorded. For the NewHandPD dataset, the best-reported metric is 99.75% using the VGG19 structure. For the MDVR-KCL dataset, the best-reported metrics are 99.94% using the KNN and SVM ML algorithms and the combined numerical features; and 100% using the combined the mel-specgram graphical features and VGG19 structure. These results are better than other state-of-the-art researches. 

/pdf/a-generic-optimization-and-learning-framework-for-parkinson-2qkze6h7.pdf

A generic optimization and learning framework for Parkinson disease via speech and handwritten records

: The population of older adults globally increased during the last couple of decades. Due to these demographic changes, the need for medical care has also significantly increased. Despite the age-related disabilities and chronic diseases, most older adults prefer independent living in their home environment. Technology-enhanced systems and eHealth applications seem to provide some p romising solutions for older adults’ well -being and independent living. However, the adoption and acceptance of these applications for older adults are unclear and further research is needed in this area. This study was carried out as a literature review, to meet the aim of identifying and discussing important factors in the Human-computer interaction of eHealth for older adults. The overall research question for this study was: What are the critical factors to consider for an improved human-computer interaction in technology-enhanced health care systems for older adults? Findings indicate some important factors to address: personal integrity, trust, technology acceptance, accessibility of ICT and eHealth literacy. If the presented factors are considered and addressed, it would be easier to achieve the desired aim of independent living. The authors recommend a human-computer interaction that is older adults centred, with the involvement of older adults users in the design process. Proper education and training on the use of eHealth services are also of great importance. Finally, the technology-enhanced system should also provide good social and technological support to the users.

/pdf/human-computer-interaction-for-older-adults-a-literature-2mdfwiwa.pdf

Human-Computer Interaction for Older Adults - a Literature Review on Technology Acceptance of eHealth Systems

The Internet of Medical Things (IoMT) plays an important role in strengthening sustainable healthcare systems. IoMT significantly influences our healthcare because it facilitates monitoring and checking patient medical information before transferring the data to a cloud network for future use. The IoMT is a big-data platform which is growing rapidly, so it is critical to maintain all data safely and securely. In this study, Blockchain-Assisted Cybersecurity (BCCS) for the IoMT in the healthcare industry is proposed. Blockchain is a decentralized digital ledger that allows end-to-end communication and provides interaction between untrustworthy persons. BCCS uses a conventional in-depth approach and blockchain to create a procedure for collecting medical information from the IoMT and integrated devices. The proposed system utilizes blockchain to record and extract the accumulated information in a secure and distributed manner within a closed environment suitable for healthcare professionals, such as nursing homes, hospitals, and the healthcare industry where data exchange is needed. The experimental outcomes show that the proposed system has a high security rate of 99.8% and the lowest latency rate of 4.3% compared to traditional approaches. In all, the reliability of the proposed system gives the highest rate of 99.4%.

/pdf/blockchain-assisted-cybersecurity-for-the-internet-of-19t6jry4.pdf

Blockchain-Assisted Cybersecurity for the Internet of Medical Things in the Healthcare Industry

This paper presents the ontological design and implementation of the differentiated learning environment in the domain model of an intelligent tutoring system for children with specific learning disabilities. It addresses the learners need for differentiated instruction in a preferential learning environment. The proposed model helps to identify the most affected learning domains and related multiple-criteria’s which effects the learners. The learning resources and problems diagnosis questionnaires are organized and used with various learning strategies to create various learning environments such as case-based learning environment, game-based learning environment, practice-based learning environment and visual-based learning environment. Different techniques can define a set of rules to decide the most preferred learning environment. Here, multiple criteria decision analysis approach map the information, learning resources and learning environments to create a differentiated learning environment for the learning disabled. The contribution of proposed model is to reduce the gap between learner and learning habits with special needs. Our model is implemented as domain model of an intelligent tutoring system to develop learner-centric learning environment. In the designed intelligent tutoring system (ITS), the differentiated learning environment domain model is further evaluated and validated by a set of fuzzy rules. The pilot test result shows that proposed model enables an ITS to improve the implementation of appropriate learning strategies with high accuracy and sensitivity for both learning and non-learning-disabled users.

https://link.springer.com/content/pdf/10.1007/s12528-021-09278-y.pdf

A differentiated learning environment in domain model for learning disabled learners

Purpose This article reviews the instructional strategies used by assistive technologies and maps their problem manifestation and effectiveness for children with learning disabilities. The objective of this article is to investigate the most common types of assistive tools used in learning to study their attributes, limited to the needs of learners with the condition of dyslexia, dysgraphia and dyscalculia. Review methods It studies currently available low, mid and high-level assistive learning technologies available to deal with problems faced by these learners. Assistive tools studied in this article range from simple hardware tools to multi-sensory software. A simple analytical framework by interlinking, Problem Manifestation, Underpinned Implication, Instructional Strategy and Cognitive Strength Developed (PISC) is formulated to examine the tools. Results Five assistive tools types (non-electronic products, low-tech products, mid-tech products, high-tech products apps and learning software) for each learning disability are identified, analysed and associated learning implication is studied under PISC framework. This helps to map the problems and learning style of learning disabled and analyses the underpinned implication along with the corresponding development of skills (cognitive, affective or psychomotor) by these assistive technologies. Conclusion Performance of identified assistive tool types using PISC framework is analysed. Findings are reported and discussed. Implications for Rehabilitation Available assistive tools are not learning disability specific. So, in order to differentiate the learning path of a Learning Disabled learner from that of a Non-Learning Disabled learner, study is conducted under four attributes of PISC framework: Problem Manifestation, Underpinned Implication, Instructional Strategy and Cognitive Strength. Available assistive tools in the field of remedial education are found to be problem centric and only able in dealing with single academic learning need of a learner with specific learning difficulty. The mapping of the available assistive technologies under PISC framework provides a detailed structure for the selection of most suited assistive tool as per learning requirement of a learner with learning disability. This study also conclude the non- availability of the High-tech assistive tools and Educational Software specifically designed for learners with learning disability.

Underpinning implications of instructional strategies on assistive technology for learning disability: a meta-synthesis review.

Blockchain for Unmanned Underwater Drones: Research Issues, Challenges, Trends and Future Directions

Extended Reality is the term that encloses Virtual Reality (VR), Augmented Reality (AR) and Mixed Reality (MR). Virtual Reality experience provide impressiveness and eliminates the physical world from view, In Augmented Reality virtual images overlays the physical world and Mixed Reality presents an altered reality, to engage users to interact with an environment, utilizing virtual objects. With the advent of the Extended Reality various tools and assistive technologies have already been developed to support the disabled learners. These applications increase learner's motivation, provide ease of interaction, develop their cognitive skills, improve short-term memory, and make overall learning interactive, also enhances learning experience of the learners. However, challenges of implementing XR are several, ranging from logistical, technical, high-costs and need for qualified staff and training in electronic competencies. As, XR in educating specially-abled is an unexplored domain. Therefore, this work presents an investigation on various XR applications in promoting education of learning-disabled and outlines their impact on learner. On the basis of the findings, a recommendation approach for use of XR in educational pursuits is presented for the concerned stakeholders, the designers, the developers, the manufacturers, the adopting educational institutions, the special educators and the learners.

An Investigative Study of Long-Term Implication of Extended Reality Applications in Educational Pursuits for Learning-Disabled Population: A Recommendation Approach

Monika Thapliyal

Papers

A differentiated learning environment in domain model for learning disabled learners

Underpinning implications of instructional strategies on assistive technology for learning disability: a meta-synthesis review.

Blockchain for Unmanned Underwater Drones: Research Issues, Challenges, Trends and Future Directions

An Investigative Study of Long-Term Implication of Extended Reality Applications in Educational Pursuits for Learning-Disabled Population: A Recommendation Approach