The university's computer laboratory is currently one of the most challenging aspects when imparting practical tasks with regards to the education technology (ET) enhancement. This study intends to observe the issues confronted by students while performing tasks in the laboratory in different educational modes. The online survey is conducted using quantitative and qualitative research instruments to evaluate the students' perspectives. This exploratory work has emphasized the practical issues such as an insufficient time constraint, and instruments, geographical needs, financial concerns, and unavailability of subject specialists to cater for relevant issues about a particular course. The sample size was (N= 161) drawn from a stratified sampling method for analysis of four strata. This research addresses these problems in the laboratory with an aim to improve the student's practical skills as well as their investigation-based learning. It is needed for practical based courses, through experimentation with the help of artificial intelligence (AI) paradigms. The design science methodology is adopted, it presents the conception of an Intelligent Virtual Laboratory (IVL) based on pedagogical agent-based cognitive architecture (PACA). This IVL provides the level of excellence of laboratory needs by enhancing the ET which students can efficiently perform practical tasks online at anywhere. The results showed that IVL has a significant model for enhancing the learning to students and recommendations for further research implementation.

Financial domains are suffering from organized fraudulent activities that are inflicting the world on a larger scale. Basel Anti-Money Laundering (AML) index enlists 146 countries, which are impacted by criminal acts like money laundering, and represents the country's risk level with a notable deteriorating trend over the last five years. Despite AML being a substantially focused area, only a fraction of such activities has been prevented. Because financial data related to this field is concealed, access is limited and protected by regulatory authorities. This paper aims to study a graph-based machine-learning model to identify fraudulent transactions using the financial domain's synthetic dataset (100K nodes, 5.3M edges). Graph-based machine learning with financial datasets resulted in promising 77-79% accuracy with a limited feature set. Even better results can be achieved by enriching the feature vector. This exploration further leads to pattern detection in the graph, which is a step toward AML detection.

This paper describes an intensive design leading to the implementation of an intelligent lab companion (ILC) agent for an intelligent virtual laboratory (IVL) platform. An IVL enables virtual labs (VL) to be used as online research laboratories, thereby facilitating and improving the analytical skills of students using agent technology. A multi-agent system enhances the capability of the learning system and solves students’ problems automatically. To ensure an exhaustive Agent Unified Modeling Language (AUML) design, identification of the agents’ types and responsibilities on well-organized AUML strategies is carried out. This work also traces the design challenge of IVL modeling and the ILC agent functionality of six basic agents: the practical coaching agent (PCA), practical dispatcher agent (PDA), practical interaction and coordination agent (PICA), practical expert agent (PEA), practical knowledge management agent (PKMA), and practical inspection agent (PIA). Furthermore, this modeling technique is compatible with ontology mapping based on an enabling technology using the Java Agent Development Framework (JADE), Cognitive Tutor Authoring Tools (CTAT), and Protégé platform integration. The potential Java Expert System Shell (Jess) programming implements the cognitive model algorithm criteria that are applied to measure progress through the CTAT for C++ programming concept task on IVL and successfully deployed on the TutorShop web server for evaluation. The results are estimated through the learning curve to assess the preceding knowledge, error rate, and performance profiler to engage cognitive Jess agent efficiency as well as practicable and active decisions to improve student learning.

The management and estimation of agile projects are challenging tasks for software companies due to their high failure rates. This paper emphasizes how to improve management and estimation challenges in the context of scrum, which is an agile process widely used for the development of small to medium size software projects. The scrum emphasis on code results in spending inadequate time on the estimation process. Mostly, the scrum master, along with the scrum team, estimates the upcoming software projects based on experience or historical data. Many issues can arise in a case where expert judgment is not available or historical data are not properly organized. In this paper, an Intelligent Recommender and Decision Support System (IRDSS) is proposed that can help the scrum master to better estimate an upcoming software project in terms of cost, time, and recommendations of human resources. Formal specification of IRDSS is also performed using the formalism known as Z language. Furthermore, an experiment on fifteen web projects was performed to validate the proposed approach and compared it with Delphi and Planning Poker estimation methods. The overall results indicate that the proposed system can produce better estimation than Planning Poker and Delphi methods by applying MMRE and PRED evaluation. This research opens new directions for the scrum community for the development of software projects within the allocated time and cost.