1393 research outputs found
Sort by
A Self-Regulated Learning Approach to Educational Recommender Design
Get PDFRecommender systems, or recommenders, are information filtering systems prevalent today in many fields. One type of recommender found in the field of education, the educational recommender, is a key component of adaptive learning solutions as these systems avoid “one-size-fits-all” approaches by tailoring the learning process to the needs of individual learners. To function, these systems utilize learning analytics in a student-facing manner.
While existing research has shown promise and explores a variety of types of educational recommenders, there is currently a lack of research that ties educational theory to the design and implementation of these systems. The theory considered here, self-regulated learning, is underexplored in educational recommender research. Self-regulated learning advocates a cyclical feedback loop that focuses on putting students in control of their learning with consideration for activities such as goal setting, selection of learning strategies, and monitoring of one’s performance.
The goal of this research is to explore how best to build a self-regulated learning guided educational recommender and discover its influence on academic success. This research applies a design science methodology in the creation of a novel educational recommender framework with a theoretical base in self-regulated learning. Guided by existing research, it advocates for a hybrid recommender approach consisting of knowledge-based and collaborative filtering, made possible by supporting ontologies that represent the learner, learning objects, and learner actions. This research also incorporates existing Information Systems (IS) theory in the evaluation, drawing further connections between these systems and the field of IS. The self-regulated learning-based recommender framework is evaluated in a higher education environment via a web-based demonstration in several case study instances using mixed-method analysis to determine this approach’s fit and perceived impact on academic success. Results indicate that the self-regulated learning-based approach demonstrated a technology fit that was positively related to student academic performance while student comments illuminated many advantages to this approach, such as its ability to focus and support various studying efforts. In addition to
contributing to the field of IS research by delivering an innovative framework and demonstration, this research also results in self-regulated learning-based educational recommender design principles that serve to guide both future researchers and practitioners in IS
and education
Formative Validity of A Novel Authentication Artifact for Augmented and Virtual Realities
No full textAugmented and virtual realities (AR/VR) have matured significantly in the past decade. As these devices have matured, security has become an important consideration. Despite the ability to completely re-create interfaces in the AR/VR space, the most common tool for authentication remains the traditional password. Passwords have many known weaknesses, and have been blamed for many high profile cyberattacks, leaving much to be desired. This study, following the design science approach and utilizing a cognitive walkthrough, explores the formative validity of a novel authentication artifact designed for AR/VR space. We report on our results, and identify that the proposed artifact exhibits good usability and security properties based on the feedback of technological and cybersecurity specific experts
Native American Rural Community Digital Divide: Student Insights
No full textThe digital divide continues to be an issue for many Native American individuals in rural tribal areas. This research used a qualitative grounded theory method from the data collection of semi-structured interviews with Native American university students. The open coding of the transcribed responses was used to analyze the text data from individual Native American experiences. The data analysis codes included cost, location, access, digital literacy, and technology knowledge as continuing issues. The coding also shows limited technical support or training availability in the communities. The absence of technology use increases the need to understand factors that remain digital divide barriers for Native American communities. The digital divide - individual experiences model (DD-IEM) is based on three main categories: community, education, and home environments. Six propositions produced the DD-IEM that encompasses digital environments within the three settings that are unique to each individual
Access Control for IoT: A Survey of Existing Research, Dynamic Policies and Future Directions
Get PDFInternet of Things (IoT) provides a wide range of services in domestic and industrial environments. Access control plays a crucial role in granting access rights to users and devices when an IoT device is connected to a network. However, many challenges exist in designing and implementing an ideal access control solution for the IoT due to the characteristics of the IoT including but not limited to the variety of the IoT devices, the resource constraints on the IoT devices, and the heterogeneous nature of the IoT. This paper conducts a comprehensive survey on access control in the IoT, including access control requirements, authorization architecture, access control models, access control policies, access control research challenges, and future directions. It identifies and summarizes key access control requirements in the IoT. The paper further evaluates the existing access control models to fulfill the access control requirements. Access control decisions are governed by access control policies. The existing approaches on dynamic policies’ specification are reviewed. The challenges faced by the existing solutions for policies’ specification are highlighted. Finally, the paper presents the research challenges and future directions of access control in the IoT. Due to the variety of IoT applications, there is no one-size-fits-all solution for access control in the IoT. Despite the challenges encountered in designing and implementing the access control in the IoT, it is desired to have an access control solution to meet all the identified requirements to secure the IoT
Prospects of Deep Learning and Edge Intelligence in Agriculture: A Review
No full textAgriculture is one of the high labor occupations around the globe. To meet the population growth and its demand, with the increase in labor cost, there is a need to explore efficient autonomous systems which may replace the traditional methods. Computer vision, edge, and deep learning (DL) models have become a promising area of research. This new paradigm of deep edge intelligence is most appropriate for agriculture activities where real-time decision-making is very important. In this chapter, the authors conduct a systematic literature review on deep learning-aided edge intelligence (EI) applications in agriculture to gather the evidence for prospects of DL at edge in agriculture. They discuss how DL models have shown outstanding performance within limited time and computation resources, and also provide future research directions to enhance the viability and applicability of complex deep learning (DL) models deployed at edge devices in agricultural applications
Perception of Bias in ChatGPT: Analysis of Social Media Data
Get PDFIn this study, we aim to analyze the public perception of Twitter users with respect to the use of ChatGPT and the potential bias in its responses. Sentiment and emotion analysis were also analyzed. Analysis of 5,962 English tweets showed that Twitter users expressed concerns regarding six predominant types of biases, namely: political, ideological, data and algorithmic, gender, racial, cultural, and confirmation biases. Sentiment analysis showed that most of the users reflected a neutral sentiment, followed by negative and positive sentiment. Emotion analysis mainly reflected anger, disgust, and sadness with respect to bias concerns with ChatGPT use
Conversational Agents for Mental Health and Well-being: Discovering Design Recommendations Using Text Mining
Get PDFConversational agents are increasingly being used by the general population due to shortages in healthcare providers and specialists, and limited access to treatments. They are also used by people to deal with loneliness and lack of companionship. As these apps are increasingly replacing real humans, there is a need to explore their design features and limitations for better design of conversational apps. Using text mining and topic modeling, this study analyzed a total of 126,610 reviews about Replika, a popular and well-established conversational agent mobile app. Our results emphasized current practices for designing conversational apps while at the same time sheds the light on limitations associated with these apps. Such limitations are related to the need for better conversations and intelligent responses, the need for advanced AI chatbots, the need to avoid questionable and inappropriate content, the need for inclusive design, and the need to address some technical limitations
The Applications of Artificial Intelligence in Managing Project Processes and Targets: A Systematic Analysis
Get PDFArtificial intelligence (AI) has emerged as the defining technology of the 21st century and has far-reaching impacts on project management (PM). This study assesses the applications of AI in managing project processes and targets through a systematic analysis of publications from 2017 to 2021. The analysis has revealed interesting insights, trends, gaps, and issues. This study informs the researchers and practitioners of the status of AI applications in the management of project processes and targets. It helps stimulate research efforts that can lead to more advances in applying AI to augment PM practices
Studying the Relationship Between Timely and Effective Care, Preventive Care, and Patient Hospital Recommendation
No full textThe problem of managing timely and effective care within emergency departments (ED) and preventive care in hospital facilities are often associated with patients’ overall satisfaction. Hence, the objective of this study is to determine the relationship between independent variables such as average ED wait time, percentage of left without being seen (LWBS), ED stay time, hospital overall rating, percentage of sepsis care, and percentage of patients’ response to hospital recommendation as a dependent variable. Given the objective, the study performed a linear regression analysis. The results of the study determined that patients’ willingness to recommend a hospital was significantly related to the average time a patient spent in ED (p \u3c 0.01), sepsis care (p \u3c 0.026), left without being seen percentage in ED (p \u3c 0.001), and hospital overall rating (p \u3c 0.001). Our findings suggest that variables related to ED throughput, and preventive care have a significant relationship with patient’s willingness to recommend / not recommend the hospital
Hybrid Quantum Artificial Intelligence Electromagnetic Spectrum Analysis Framework for Transportation System Security
No full textThe traffic signal control (TSC) system is faced with both opportunities and challenges as a consequence of connected vehicle (CV) technology. Although implementing CV technology might considerably enhance safety and mobility performance, the connection between vehicles and transportation infrastructure may raise the dangers of cyberattacks. Studies on cybersecurity in TSC systems have been undertaken in recent years. However, a safe framework for air-gapped malware analysis is still lacking. Our study aims to close this research gap by presenting a thorough electromagnetic analysis approach to address the cybersecurity issue facing the TSC in the CV environment. In this technique, a hybrid deep learning architecture based on classical quantum transfer learning models is constructed to study electromagnetic (EM) spectra. We assess the effect of adversarial attacks on TSC systems using these hybrid models and distinguish attacks from normal operations of the controller. A neural network trained on a dataset to collect pertinent characteristics from a high-dimensional dataset of electromagnetic (EM) trace-based TSC attack vectors form the basis of hybrid models. The quantum layer then examines the outcome of the standard deep learning process. A number of quantum gates make up the quantum layer, which can enable a number of quantum mechanical activities, including superposition and entanglement. The most conceivable and feasible attack approach in transport signal controllers has been found to be data spoofing, and the potential of the proposed air-gapped electromagnetic Hybrid classical quantum monitoring framework in sensor fusion and interrupts is explored in light of these findings. A range of sensor fusion configurations and interruptions have been investigated to identify a fake data attack from a normal controller operation. With lower penetration rates of 1% to 10%, the prediction accuracy of a four-way controller ranges from 76% to 84% and is in the low 80% for a two-way controller. There are fewer false alarms when the penetration rate is higher since there is greater confidence in the prediction. Further testing of different timing scheme modifications in a four-way controller operation yielded a prediction accuracy of 88% when the time duration was raised by more than 60% in all circumstances