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...

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.

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.

Software projects are failing for several decades due to multiple reasons. In this regard a lot of research has been done to investigate the reasons behind the failure. However, most of this research was executed in developed countries while under-developed and developing countries got little attention. The main objective of this study is to assess the impact of critical factors on the success of software projects for under-developed countries (like Pakistan), because enterprise environmental factors along with staff working habits, their experience and expertise level also have an impact on the success of a project. To accomplish this, a survey was conducted through the Pakistan Software Export Board (PSEB), and logistic regression enquiry was executed to measure the relationship between various factors affecting software. The results reflect that improper planning along with wrong cost and time estimation are positively and significantly associated with software failure. Based on the finding of the survey, a model is proposed for intelligent decision support system (IDSs). The proposed model keeps track of the previous knowledge and behavior in a well-structured manner that might be helpful for project managers in the estimation and decision-making process of upcoming software projects. This research adds new knowledge from an under-developed country which will open new dimensions for the IT industry and project manager working under similar circumstances.

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.

For many years, improving air quality has been great attention of the whole world. It has been recognized that air pollution as a hypothetically hazardous type of environmental pollution and polluted air directly affects the human health. In Asian countries, it has converged less attention of ever growing most alarming and hazardous issue of air pollution. This paper presents a case study of Lahore city of Pakistan for the prediction of Air Quality Index (AQI) using hybrid approach of Neuro Fuzzy (NF) inference system. The ambient air data of Lahore was taken from the Environmental Protection | department (EPD) working under government of the Punjab. For results evaluation, data was recorded at different station in the period from April 2007 to May 2015. The fuzzy rules have been generated according to the Pakistan Environmental Protection Agency (PAK-EPA) standard of AQI. The NF Inference Model took the air pollutants such as Particulate Matter (PM2.5), Ozone (O3), Carbon Monoxide (CO), Sulphur Dioxide (SO2) and Nitrogen Dioxide (NO2) as inputs and predicted the air quality index as good, moderate, or unhealthy air. The results showed that NF based AQI prediction model classifies the AQI proficiently, robustly, and accurately as compared to conventional method.