Scientific research is increasingly relying on complex workflows that span multiple computing paradigms, including high-performance computing (HPC), high-throughput computing (HTC), and machine learning/artificial intelligence (ML/AI). Traditional monolithic computing infrastructures often struggle to accommodate these diverse and evolving demands. The Reconfigurable Advanced Platform for Transdisciplinary Open Research (RAPTOR) addresses this challenge by providing a dynamically reconfigurable computing environment that integrates with federated resources. RAPTOR's architecture enables dynamic provisioning between an HPC cluster and the Chameleon Cloud platform based on workload requirements, supporting bare-metal customization for specialized applications. This paper focuses on RAPTOR's reconfigurability features and demonstrates their effectiveness through quantitative performance evaluations across four scientific domains: computational proteomics, climate modeling, weather research, and hurricane risk assessment. Our results demonstrate that RAPTOR's reconfigurable design significantly enhances research productivity by providing an appropriate computing environment for diverse computational needs.

Stealth assessment is a methodology that utilizes machine learning (ML) for processing unobtrusively collected data from serious games to produce inferences regarding learners' mastery level. Although stealth assessment can produce valid and reliable assessments, its robustness over a wide a range of conditions has not been examined yet. The main reason is its complex, laborious, and time-consuming practical application. Therefore, its exposure to different conditions has been limited, as well as its wider uptake from the serious game community. Nevertheless, a framework for developing a generic tool has been proposed to lift its barriers. In this article, a generic stealth assessment (SA) software tool was developed based on this framework to examine the robustness of the stealth assessment methodology under various conditions. In specific, the conditions relate to processing data sets of different distribution types and sizes (960 data sets containing a total of 72.336.000 data points are used for this reason), utilizing two different ML algorithms (Gaussian Naïve Bayes Network and C4.5), and using statistical models relating to two different competency constructs. Results show that stealth assessment is a robust methodology, whilst the generic SA tool is a highly accurate tool capable of handling efficiently a wide range of conditions.

Stealth assessment could radically extend the scope and impact of learning analytics. Stealth assessment refers to the unobtrusive assessment of learners by exploiting emerging data from their digital traces in electronic learning environments through machine learning technologies. So far, stealth assessment has been studied extensively in serious games, but has not been widely applied, as it is a laborious and complex methodology for which no support tools are available. This study proposes a generic tool for the arrangement of stealth assessment to remove its current limitations and pave the road for its wider adoption. It describes the conceptual design of such a tool including its requirements regarding users, functions, and workflow. A prototype was implemented as a basic console application covering the tool's core requirements, including a Gaussian Naïve Bayes Network utility. Generated input files were used for testing and validating the approach. In a controlled test condition the stealth assessment classification accuracy was found to be inherently stable and high (typically above 92%). It is argued that the proposed approach could radically increase the applicability of stealth assessment in serious games and inform current learning analytics approaches with unobtrusive, more detailed and genuine assessments of learning.

This paper represents our newly developed software for emotion recognition from facial expressions. Besides allowing emotion recognition from image files and recorded video files, it uses webcam data to provide real-time, continuous, and unobtrusive facial emotional expressions. It uses FURIA algorithm for unordered fuzzy rule induction to offer timely and appropriate feedback based on learners’ facial expressions. The main objective of this study was first to validate the use of webcam data for a real-time and accurate analysis of facial expressions in e-learning environments. Second, transform these facial expressions to detected emotional states using the FURIA algorithm. We measured the performance of the software with ten participants, provided them with the same computer-based tasks, requested them a hundred times to mimic specific facial expressions, and recorded all sessions on video. We used the recorded video files to feed our newly developed software. We then used two experts’ opinions to annotate and rate participants’ recorded behaviours and to validate the software’s results. The software provides accurate and reliable results with the overall accuracy of 83.2%, which is comparable to the recognition by humans. This study will help to increase the quality of e-learning.

This article describes the validation study of our software that uses combined webcam and microphone data for real-time, continuous, unobtrusive emotion recognition as part of our FILTWAM framework. FILTWAM aims at deploying a real-time multimodal emotion recognition method for providing more adequate feedback to the learners through an online communication skills training. Herein, timely feedback is needed that reflects on the intended emotions they show and which is also useful to increase learners’ awareness of their own behavior. At least, a reliable and valid software interpretation of performed face and voice emotions is needed to warrant such adequate feedback. This validation study therefore calibrates our software. The study uses a multimodal fusion method. Twelve test persons performed computer-based tasks in which they were asked to mimic specific facial and vocal emotions. All test persons’ behavior was recorded on video and two raters independently scored the showed emotions, which were contrasted with the software recognition outcomes. A hybrid method for multimodal fusion of our multimodal software shows accuracy between 96.1% and 98.6% for the best-chosen WEKA classifiers over predicted emotions. The software fulfils its requirements of real-time data interpretation and reliable results.

Distributed intelligent software agents (DISA) are software agents that help out users and act on their behalf. Such agents might be robots or virtual software systems. They are able to intelligent if they interact with their environment in an approach that would generally be observed as intelligent if that communication were carried out by a human being. As a result, gathering information from Web sources via distributed intelligent software agents in enterprise architecture can be implemented platform independent, reusable, and would be better modeled in n-tier or enterprise-tier architecture. The purpose of this paper is to develop a novel distributed intelligent software agent architecture capable of manually and automatically locating and extracting user specified data from the Web, and to dynamically populate semantic databases with the data for later access and retrieval. Implementation of this project not only enables the software to access the semantic information which has been created by a typical Web source, but also it is equipped producing a meta database for executing the queries in semantic database. On the other hand, agents of this system have been enabled for the creation of customized knowledge-based ontology files over enterprise model for future usage of users.

Web mining treats the World Wide Web as the ultimate data source. This area of research is more interesting than data mining involving extracting data from in- house corporate databases or data warehouses. Gathering information from Web sources via distributed intelligent software agents in enterprise architecture can be implemented securely, platform independent, reusable, and would be better modeled in n-tier or enterprise-tier architecture. The purpose of this paper is to develop a novel distributed software agent architecture capable of automatically locating and extracting user specified data from the web, and to dynamically populate semantic databases with the data for later access and retrieval. Implementation of this project not only enables the software to access the semantic information which has been created by a typical Web source, but also it is capable of producing a meta database for executing the queries in semantic database. On the other hand, it is too difficult for the current users to interact with distributed intelligent agents over n-tier architecture on the Internet and gather information for Web mining issues which have been produced by those agents.