Improving stream data processing efficiency in an intelligent educational system

Emerging real-time applications such as those classified under ultra-reliable low latency (uRLLC) generate bursty traffic and have strict quality of service (QoS) requirements. The passive optical network (PON) is a popular access network technology, which is envisioned to handle such applications at the access segment of the network. However, the existing standards cannot handle strict QoS constraints for such applications. The available solutions rely on instantaneous heuristic decisions and maintain QoS constraints (mostly bandwidth) in an average sense. Existing proposals in generic networks with optimal strategies are computationally complex and are, therefore, not suitable for uRLLC applications. This paper presents a novel computationally efficient, far-sighted bandwidth allocation policy design for facilitating bursty uRLLC traffic in a PON framework while satisfying strict QoS (age of information/delay and bandwidth) requirements. To this purpose, first we design a delay-tracking mechanism, which allows us to model the resource allocation problem from a control-theoretic viewpoint as a model predictive control (MPC) problem. MPC helps in making far-sighted decisions regarding resource allocations and captures the time-varying dynamics of the network. We provide computationally efficient polynomial time solutions and show their implementation in the PON framework. Compared to existing approaches, MPC can improve delay violations by 15% and 45% at loads of 0.8 and 0.9, respectively, for delay-constrained applications of 1 ms and 4 ms. Our approach is also robust to varying traffic arrivals.

Computer-based educational systems are becoming increasingly important in all levels and types of education. Intelligent Educational Systems (IESs) are computer-based educational systems encompassing Artificial Intelligence schemes to increase the effectiveness of the learning process. In this paper, we survey patents regarding IESs. As IESs we consider either Intelligent Tutoring Systems (ITSs) or Adaptive Educational Hypermedia Systems (AEHSs) incorporating intelligent techniques. We first present indicative functions implemented in the three basic components of an IES: the domain knowledge, the user (or student) modeling unit and the pedagogical module. Afterwards, we focus on representative patents concerning IESs and present the corresponding work. At the end, we outline current and future developments regarding IESs. Keywords: Intelligent tutoring systems, adaptive educational hypermedia systems, intelligent educational systems, artificial intelligence in education, intelligent E-learning systems, intelligent computer-based training systems, artificial intelligence in Elearning

In this paper two observations are the starting points for a proposal as to how learning, rather than computing considerations, can be made the main focus in the development of Intelligent Educational Systems (IESs). These observations are: a) the predominant use of computers in education is for the running of general tool software; and b) the symbolic approach to Artificial Intelligence is being questioned from a situated cognition perspective.Learning interactions are seen as consisting of a Task Level, and a higher‐level Discussion Level comprising planning and evaluation of, and reflection about, Task Level activity. It is proposed that IESs should be developed by adding a module to support Discussion Level interaction with the learner. The Mayday project is described, in which expert human teachers are being studied as they support Discussion Level with a learner working at computer‐based lexical activities. It is argued that such studies of human learning is a necessary step towards the development of the proposed IESs.

Towards a Design of an Intelligent Educational System

Intelligent training systems have been developed using techniques advanced within the AI in education community. Each new system developed, however, exhibits its own inherent idiosyncrasies and does not address the problems of high development costs. This paper describes two generic approaches adopted within the Mobit project for building Intelligent Training Systems. The first being our approach to acquiring domain specific knowledge which initially requires a decomposition of the training objective into primitive generic tasks. The second being our approach to training based on domain independent learning styles and training strategies.

The Graph Model of Combinatory Logic (Engeler, 1981) is also a mathematical model for "how does the brain think". It attempts to explain how complex scripts of behavior and conceptual content can reside in, combine, and interact on large neural networks (Engeler 2019). This has an impact on building intelligent systems that interact with humans. Intelligent systems should employ the same kind of concepts humans do; otherwise, their actions remain incomprehensible and erratic to human users, concepts can be represented in the Graph Model by using the "Lambda-Theorem" found be Barendregt in 1977.Both the Graph Model and the mathematical model for the human brain have been published as part of Theoretical Computer Science and remain thus out of the reach of normal AI engineers. Nevertheless, they suggest solutions for today's problems with Intelligent Systems, such as autonomous vehicles mastering the traffic in Palermo, or robots caring for people and working together with them. Intelligent Systems need to adhere to concepts quite similar to humans that follow certain rules in their behavior.The paper explains what a “Concept” is in AI, how to state requirements for AI, and how to test them. Intelligent Systems using concepts behave similar to humans, following rules but are still able to break the rules when need arises, and can be certified for safety and security; solving certain difficulties for Learning Machines that can learn and unlearn.ReferencesH. P. Barendregt, "The Type-Free Lambda-Calculus," in Handbook of Math. Logic, vol. 90, J. Barwise, Ed., Amsterdam, North Holland, 1977, pp. 1091 -1132.E. Engeler, "Algebras and Combinators," Algebra Universalis, vol. 13, pp. 389-392, 1981. E. Engeler, "Neural algebra on "How does the brain think?"," Theoretical Computer Science, vol. 777, pp. 296-307, 2019. T. M. Fehlmann, Autonomous Real-time Testing – Testing Artificial Intelligence and Other Complex Systems, Berlin, Germany: Logos Press, 2020. H. Curry and R. Feys, Combinatory Logic, Vol. I, Amsterdam: North-Holland, 1958. K. Bimbó, Combinatory Logic - Pure, Applied and Typed, Boca Raton, FL: CRC Press, 2012.

PurposeThe development of adaptable and intelligent educational systems is widely considered one of the great challenges in scientific research. Among key elements for building advanced training systems, an important role is played by methodologies chosen for knowledge representation. In this scenario, the introduction of ontology formalism can improve the quality of formative process, allowing the introduction of new and effective services. Ontology can lead to important improvements in the definition of courses knowledge domain, in the generation of adapted learning path and in the assessment phase. The purpose of this paper is to provide an initial discussion of the role of ontology in the context of e‐learning. It seeks to discuss the improvements related to the introduction of ontology formalism in the e‐learning field and to show a novel algorithm for ontology building through the use of Bayesian networks. Finally, it aims to illustrate its application in the assessment process and some experimental results.Design/methodology/approachA novel method for learning ontology for e‐learning is illustrated, using an approach based on Bayesian networks. Thanks to their characteristics, these networks can be used to model and evaluate the conditional dependencies among the nodes of ontology on the basis of the data obtained from student tests. An experimental evaluation of the proposed method was performed using real student data.FindingsThe proposed method was integrated in a tool for the assessment of students during a learning process. This tool is based on the use of ontology and Bayesian network. In particular through the matching between ontology and Bayesian network, it was found that our tool allows an effective tutoring and a better adaptation of learning process to demands of students. The assessment based on Bayesian approach allows a deeper analysis of student's knowledge.Research limitations/implicationsThe proposed approach needs more experimentation with other domains and with more complex ontology.Originality/valueThis paper provides an initial discussion of the role of ontology in the context of e‐learning. The improvements related to the introduction of ontology formalism in the e‐learning field are discussed and a novel algorithm for ontology building through the use of Bayesian Networks is showed. Finally, its application in the assessment process and some experimental results are illustrated.

With the popularization of computers and various mobile intelligent terminals, intelligent teaching systems based on learners are becoming more and more popular among learners. The above phenomenon has greatly affected and changed the current teaching quality diagnosis methods and models. However, the author found through investigation that the current intelligent teaching quality diagnosis still has different degrees of deficiencies in the design and implementation. In response to the above problems, this paper proposes a teaching quality intelligent diagnosis model based on the combination of wireless sensor networks and fuzzy comprehensive evaluation algorithms. First of all, this article is based on the wireless sensor network to link various levels of intelligent teaching systems, and constructs the information transmission structure of the teaching intelligent diagnosis system. Secondly, this article uses fuzzy comprehensive evaluation and convolutional neural network algorithms to evaluate and excavate intelligent teaching information. Finally, the model successfully passed the simulation test and simulation application, which can provide intelligent diagnosis of teaching quality for modern intelligent teaching system.

With the rapid development of e-commerce over Internet, web services have attracted much attention in recent years. Nowadays, enterprises are able to outsource their internal business processes as services and make them accessible via the Web. Then they can dynamically combine individual services to provide new value-added services. With the increasing number of web services having equivalent functionality, the binding procedure is driven by some non-functional, Quality of Service (QoS) criteria, such as the money cost, response time, reputation, reliability or a trade-off between them. Thus, an important problem is, given QoS constraints, how to aggregate and leverage individual service’s QoS information to derive the optimal QoS of the composite service. In this paper, we propose a novel QoS model for performing flexible service selection. The key idea of the model is to relax users’ QoS constraints and try to find the most possible services satisfying users’ QoS requirements. Based on the proposed QoS framework, we develop various algorithms for making service selection on individual and composite services. We also introduce a top-k ranking strategy to reflect a user’s personalized requirements. Experimental evaluation shows the proposed QoS model is efficient and practical.

The ongoing COVID-19 pandemic has accelerated the adoption of e-learning, remote learning, and hybrid models in education. These models have become essential in meeting the demands of smart cities and addressing the limitations of traditional distance learning. However, to truly achieve academic success, education must be adaptive and tailored to the individual needs of students. This study presents a novel concept for intelligent educational systems that integrate Explainable Artificial Intelligence (XAI) and Internet of Behavior (IoB) technologies. The integration of these technologies aims to revolutionize intelligent educational systems by providing a more personalized and effective learning experience. By collecting and analyzing student behavior data, the system can provide real-time feedback and adjust to meet the needs of each individual student. The results of this study demonstrate the significant impact of IoB technology on student performance. The integration of IoB led to a substantial increase in student response from 40% to 79%. These findings highlight the potential for IoB to enhance learner assistance and improve system modifications to better meet the expectations of students for increased performance. The proposed concept of integrating XAI and IoB technologies in intelligent educational systems can pave the way for a more personalized and effective learning experience in the future.

The integration of biosensor technologies, like electroencephalography (EEG), has extended the limits of adaptive, intelligent education systems, offering real-time, personalized learning knowledge. This study explores the use of EEG to track and assess students’ cognitive states, allowing for the improvement of an active, adaptive English learning system that tailors content according to every student’s participation and improvement. Students’ cognitive states serve as the foundation for personalized education responses that motivate and enhance their participation. EEG data are gathered during English language testing to assess the correlation between learners’ cognitive states and their performance. Noise reduction is one of the preprocessing stages that ensures clear and pertinent data for analysis. Power spectral density (PSD) for feature extraction approaches is used to identify key cognitive patterns. Based on real-time EEG data, the personalized education feedback system constantly modified the course material, enhancing motivation and learning results. This research proposed a novel Dynamic Osprey Optimized Intelligent Gradient Boosting Machines (DOO-IGBM) to assess and improve the efficiency of an adaptive intelligent education system. The findings suggest that EEG-based adaptive systems make it possible to significantly progress English learning by offering personalized education paths based on brain activity to other conventional algorithms with 98.5% accuracy, 97.7% precision, 98% recall, and 98.6% F1-score. These outcomes provide precious insights and data to support the future development of adaptive, intelligent education systems for language learning.

Vehicular communications is an important enabler for enhancing the safety on roads by supporting mutual awareness of vehicles as well as for improving the efficiency of transportation through smart traffic management by intelligent transport systems (ITSs). Governments around the world have set ambitious goals for road fatality reduction in the near future; e.g., the European Union targets a 50% reduction of road fatalities by 2020 as compared to the year 2010. Furthermore, traffic telematic systems aim to minimize the environmental impact of transportation and maximize the utilization of available road infrastructure by adaptive traffic management. To realize these challenging targets, autonomous wireless information exchange among vehicles-vehicle to vehicle (V2V)-and with roadside infrastructure-vehicle to infrastructure (V2I)-are central ingredients. In addition to traffic efficiency and safetyrelated issues, vehicular communications is increasingly recognized as an important revenue driver by car manufacturing companies since it enables wirelessly connected in-vehicle entertainment systems that support on-demand video streaming and online Internet access for passengers. Also, in the future, machine-type communication is expected to play a major role in vehicular environments, with more sensors that monitor the internal state of vehicles and autonomously exchange service and maintenance information with cloud servers of manufacturers. Depending on the considered use-case, distinct quality of service (QoS) requirements come into play [1]: infotainment applications for in-car users require high bandwidth and network capacity, active road safety relies on delay- and outage-critical data transmission, whereas information exchange for road traffic efficiency management typically comes without strict QoS requirements and exhibits graceful degradation of performance with increasing latency.

There has been much discussion among academics on how pupils may be taught online while yet maintaining a high degree of learning efficiency, in part because of the worldwide COVID-19 pandemic in the previous two years. Students may have trouble focusing due to a lack of teacher–student interaction, yet online learning has some advantages that are unavailable in traditional classrooms. The architecture of online courses for students is integrated into a system called the Adaptive and Intelligent Education System (AIES). In AIESs, reinforcement learning is often used in conjunction with the development of teaching strategies, and this reinforcement-learning-based system is known as RLATES. As a prerequisite to conducting research in this field, this paper undertakes the consolidation and analysis of existing research, design approaches, and model categories for adaptive and intelligent educational systems, with the hope of serving as a reference for scholars in the same field to help them gain access to the relevant information quickly and easily.

Volunteer computing systems exploiting large amounts of geographically dispersed resources on the Internet for solving complex scientific problems. However, scheduling scientific workflows in a fully decentralised way and low overhead is a challenging task in these environments. To counter this challenge, this paper presents a fully decentralised proximity-aware workflow-scheduling policy for these environments. The proposed scheduling consists of three phases. In the first phase, each workflow application is partitioned into sub-workflows in order to minimise data dependencies among them. The second phase of the workflow-scheduling algorithm finds some resources to execute each sub-workflow. These resources are selected based on Quality of Service (QoS) constraints of the workflow, load balancing and proximity of resources. Each workflow can have QoS constraints in terms of minimum CPU speed and minimum RAM or hard disk requirements. In the third phase, sub-workflows will be executed on each resource based on local scheduling algorithm to minimise the partial makespan. The proposed scheduling policy focuses on the reduction of communication overhead to improve the performance of I/O-intensive and data-intensive workflows. Simulation results show that the proposed workflow-scheduling policy improves the average response time of scientific workflows up to 53.6% under a moderate load.

In instructional design, decisions about which instructional methods to use are made well in advance of their implementation. While expert teachers select methods while instruction is underway and are well placed to adapt instruction to changing conditions, designers must try to predict ahead of time how instructional conditions will change. This is difficult to do because design procedures are non-deterministic and instructional theory is incomplete. In intelligent instructional systems, it is possible to shift certain aspects of decision-making back to the implementation phase of instruction. This enables systems to adapt to changing conditions and to present information in a variety of formats. The designer becomes less concerned with selecting methods and puts more effort into writing rules that allow systems to select methods once instruction has begun.