This paper will analyze two literatures on intelligent agents in education based on its background, motivation, problem, solution, result, and comments. The selected articles include “An Intelligent Learning Agent using Learner’s Information in Mobile Environment” and “Intelligent Agent Based Architectures for E-Learning System: Survey”.
An Intelligent Learning Agent using Learner’s Information in Mobile Environment
Background and motivation
The authors analyzed user information using various learning curves. As a result, the researchers proposed that an effective intelligent agent must correlate variables that stimulate the student’s information and activity pattern. Thus, the authors analyzed the intelligent learning agent of learners using the mobile environment.
Problem
The authors agreed with previous literatures on the influence of mobile phones and laptops in education. As a result, mobile technology has been developed to improve the problem solving skill of students and e-learners. However, the authors argued that mobile learning environment does not cover areas of specific demand. As a result, the student’s desire for quality learning through intelligent agent is affected. Thus, the researcher revealed that additional focus on the learner’s internet activity will stimulate and influence his or her learning curve. Previous surveys revealed that intelligent agents exclude various learning variables that stimulate the student’s desire for Internet activities. As a result, students are not motivated to learn. This problem stimulated the researcher’s drive to improve the intelligent agent in education. As a result, user-friendly information was created in the mobile environment to collect specific data on the learner’s Internet activity (Kim 140).
Solution
The study used an intelligent agent machine to design user preference in complex internet activity. As a result, the intelligent agent is embedded in the mobile environment. However, the intelligent agent can be developed in a different field to assist users in all disciplines. To understand and collect user information, the author proposed a two-system design. The intelligent agent embedded in the mobile environment includes the learning, context awareness, and system-mapping module. The context awareness module embedded in the mobile environment collects user information such as GPS location, learner database, learner log activity, and profile. These variables are transferred to the context awareness terminal. The recommendation module collects information such as logging information, and time constraint using the Bayesian network signal. Consequently, the system-mapping module analyzes the recommendation inference to improve learning. As a result, the mapping module develops the user content and list using the proposed system.
The study was conducted in the mobile environment to evaluate the user’s internet activity. As a result, the intelligent mobile agent was designed with the virtual programing scheme. The requirements for the mobile environment include mobile operating system (OS), system language, screen resolution, system database, and mobile device. Thus, the research used the android 2.3.5, Java/Android SDK, 1280×800, SQLite, and Galaxy Note device. Twenty students were selected at random to complete the study requirements. The recommendations of the sample population were based on the research study. Consequently, the learning content of the sample population was analyzed to determine the average test result. Thus, the student’s context awareness was generated using available time and logging information. Thus, the author compared the results with the learner’s basic status. The result A and B revealed the student’s learning contents in two situations. Situation A, the user’s basic information was used to assess the learning activity. Situation B, the user’s logging data, and time influenced the learning contents. The results for situation A, and B revealed that the learning contents scored 74 and 78 percent respectively. The result shows an outcome of 78 precise recommendations from 100 populations. Thus, user demand associated with basic information, Internet activity, and time influences the intelligent agent embedded in the mobile environment.
Comments
The study results revealed that further studies will improve its limitations. Consequently, the sample population must be extended to different geographical locations. As a result, inputs such as career field, subject verification, available resources, and previous literatures. By implication, the results may be different if the study analyzed previous literatures. Consequently, the filter method must accommodate complex user preferences. However, the lack of information on the study from previous studies suggests that the results were predetermined. By implication, the author’s analysis did not conform to previous surveys in the mobile environment. Thus, further studies must correlate quality literatures on the subject topic to improve validity.
Intelligent Agent Based Architectures for E-Learning System: Survey
Background and motivation
Previous literatures described intelligent agent in education as a system that stimulates, facilitates, and collaborates the user’s learning curves. By implication, the learning environment requires a scheme that influences quality education. E learning is an aspect of education that requires an internet platform. Unlike, the conventional classroom, the e-learning environments uses the intelligent agent to assist users. As a result, the authors provided an in depth analysis of e-learning architecture. Thus, the researchers correlated previous literatures on the topic to suggest the benefits of intelligent agent architecture in education (Arif and Hussain 23).
Problem
E-learning is a complex learning platform that requires specific inputs. E-learners encounter challenges that limit the benefits of the learning platform. However, research designers have engineered different systems of learning to accommodate diversity in education. As a result, educational attainment using an eLearning platform expands yearly. However, the system architecture of e-learning platforms must combine different intelligent agents to facilitate learning. Thus, the researchers provided the analysis of four e-learning based architectures. The intelligent agent architectures for E learning include domain ontology, serviced based architecture, multi-agent, and collaborative architecture. Thus, the author’s analysis will improve e-learning platforms from quality education.
Solution
To improve the learning curves of e-learners using intelligent agents, the authors described four architectures in education.
The collaborative e-learning architecture operates in three domains.
The levels include infrastructure layer, student platform, and service oriented interface. By implication, the student interface provides different search input to improve information acquisition and transfer. Thus, multiple educational contents for specific fields are correlated to suit the user preference. Consequently, the service-oriented architecture controls the search protocol and resources. The collaborative agent based architecture controls the three levels of learning. Thus, the user can activate the search guide using specific keyword. As a result, the command input triggers the request and transfer agent. Thus, the multi-agent collaborates the learning, teaching and support nodes. The authors analyzed the implications of human emotions on intelligent agents in education. The collaborative architecture tested sis variables to determine issues in information absence.
Multi-agent architecture
The paper revealed that the multi – agent mechanism controls four variables. The variables include database layer, middle, interface and control layer. However, the interface controller dictates the service interplay. Thus, the multi-agent architecture must be interactive, educations, simple, social, and effective. Each layer adopts a collaborative approach to improve service delivery. The paper described the common agent framework for E learning using simple feature designs. Thus, the results revealed that multi-agent architectures improve the user’s understanding. The agents of data collection include content manager, converter manager, and personal manager. Each agent performs a specific task in a multi-based architecture (Lee 10). Thus, the user command is identified, analyzed, converted, and transmitted to the recommendation module.
The service-oriented architecture
The authors analyzed the service-based system using personalized and integrated mechanisms. Thus, the researchers described the connection between Internet services and intelligent agents. The query module receives and transmits service commands across multiple platforms to improve E learning. Each platform is associated with the referral system. The referral system includes service module, multi-agent, neighbor agent, and agent profile (Sung 79). Thus, the feedback mechanism improves E learning.
Domain Ontology
Domain ontology architecture provided user adaptive feature to collaborate on educational systems. The authors described three phases in domain architecture. The phase includes result oriented, development and design phase. As a result, the search protocol provides match algorithms to improve E learning.
Results
The authors analyzed 38 E learning charts using random selection. The variables for the analysis include year, technique, communication protocol, a teacher based assistance, and student oriented advantages, tool, layer, and comment. However, the result showed the benefit of various e-learning architectures using intelligent based platforms. Consequently, the researchers adopt the study rage to enable documentation. As a result, analysis was conducted between 2004 and 2010. The benefits of intelligent based architecture include group learning, collaboration, course development, safe resource sharing, individual performance, multi- system utility, accessibility, recovery scheme, adaptive interaction, interoperability, and security.
Comments
The article describes various e learning architectures in education. However, the analysis was not simplified for different users. Techniques such as data mining, and web clusters were not developed. The research analysis did not base its findings on existing literatures. Thus, the paper lacked critical evaluation requirements under educational reviews. The year of publication and research material used did not reflect substantial discipline. By implication, user knowledge and study benefits are limited to the proposed field. Thus, further studies must cover different disciplines. A comparative study of intelligent agent architecture must be conducted to improve its structural design (Oskouei, Varzeghani and Samadyar 2290). However, the lack of information on the study from previous studies suggests that the results were predetermined. By implication, the author’s analysis did not conform to previous surveys in education. Thus, further studies must correlate quality literatures on the subject topic to improve validity.
Works Cited
Arif, Muhammad and Hussain Mehdi. “Intelligent Agent Based Architectures for E-learning System: Survey.” International Journal of u- and e- Service, Science and Technology 8.6 (2015): 9-24. Print.
Basak, Swati and Mazumdar Bireshwar. “Multi-Agent Coalition Formation for Course Selection Strategies in E-learning.” International Journal of Mathematics Trends and Technology 6.1 (2014): 36-43. Print.
Kim, Jin-II. “An Intelligent Learning Agent using Learner’s Information in Mobile Environment.” International Journal of Multimedia and Ubiquitous Engineering 9.11 (2014): 143-152. Print.
Lee, Jun. “Development and Application of E-Learning Content for Advertising Education.” IJAST 47.9 (2014): 1-12. Print.
Oskouei Rozita, Varzeghani Hamidreza and Samadyar Zahra. “Intelligent Agents: A Comprehensive Survey.” International Journal of Electronics Communication and Computer Engineering 5.4 (2014): 2278-4209. Print.
Sung, Ji. “U-Learning Model Design Based on Ubiquitous Environment.” IJAST 13.6 (2014): 77-90. Print.