Affective computing is an emerging area of education research and has the potential to enhance educational outcomes. Despite the growing number of literature studies, there are still deficiencies and gaps in the domain of affective computing in education. In this study, we systematically review affective computing in the education domain. Methods: We queried four well-known research databases, namely the Web of Science Core Collection, IEEE Xplore, ACM Digital Library, and PubMed, using specific keywords for papers published between January 2010 and July 2023. Various relevant data items are extracted and classified based on a set of 15 extensive research questions. Following the PRISMA 2020 guidelines, a total of 175 studies were selected and reviewed in this work from among 3102 articles screened. The data show an increasing trend in publications within this domain. The most common research purpose involves designing emotion recognition/expression systems. Conventional textual questionnaires remain the most popular channels for affective measurement. Classrooms are identified as the primary research environments; the largest research sample group is university students. Learning domains are mainly associated with science, technology, engineering, and mathematics (STEM) courses. The bibliometric analysis reveals that most publications are affiliated with the USA. The studies are primarily published in journals, with the majority appearing in the Frontiers in Psychology journal. Research gaps, challenges, and potential directions for future research are explored. This review synthesizes current knowledge regarding the application of affective computing in the education sector. This knowledge is useful for future directions to help educational researchers, policymakers, and practitioners deploy affective computing technology to broaden educational practices.

Model-based Systems Engineering (MBSE) advocates the use of models in every stage of development, leading to large number of models that need coordination, collaboration, and discipline management. Model Management (MoM) is a possible approach to manage inter-related collections of models among which Model Federation (MF) provides unique capabilities, like independence of development in individual modelling domains. There is currently a lack of studies about commonalities, variabilities, and gaps in MF approaches. In this paper, we propose a survey and a critical discussion of carefully selected papers about MF. From 59 contributions collected by experts in MoM, we selected, and classified, 23 papers. We extract the main trends we observed, according to our Classification. We then critically review the Classification, and discuss important gaps found in our corpus. The survey results and artefacts are all available online.

Uncertainty is an inherent property of any complex system, especially those that incorporate physical parts or operate in real environments. In this paper, we focus on the Digital Twins of adaptive systems, which are particularly complex to design, verify, and optimize. One of the problems of having two systems (the physical one and its digital replica) is that their behavior may not always be consistent. In addition, both twins are normally subject to different types of uncertainties, which complicates their comparison. In this paper we propose the explicit representation and treatment of the uncertainty of both twins, and show how this enables a more accurate comparison of their behaviors. Furthermore, this allows us to reduce the overall system uncertainty and improve its behavior by properly averaging the individual uncertainties of the two twins. An exemplary incubator system is used to illustrate and validate our proposal.

Biopotential data measurement plays an important role in monitoring the body’s physiological functions. It is affected by noise from various sources for different signals adversely affecting our ability to interpret them. Traditional methods of data detrending are either computationally inefficient, power-intensive, or have high latency. The Maximum-Mean-Minimum (MaMeMi) filter reported for ECG de-noising is a computationally efficient algorithm. The MaMeMi filter response depends on two filter coefficients. In real-time, it is difficult to gauge the characteristics of the detected signal beforehand. In this paper, we propose an Adaptive MaMeMi filter, the AMaMeMi filter, which adaptively computes the filter coefficients according to the properties of the input. We have used hardware-software co-design techniques for optimized implementation of the AMaMeMi filter. The proposed hardware accelerator architecture for the AMaMeMi filter can be used in both adaptive and manual modes of operation. The hardware accelerator is tested for various biopotential signal detrending and the single hardware is capable of eliminating baseline wander from all considered measurements with less computational costs and low latency. We implemented the AMaMeMi filter on Xilinx Zynq-7000 System-on-Chip (part number XCZ7020-CLG484-1) and statistically verified the results. The hardware accelerator implementation results provide a good correlation with MATLAB simulation results. The hardware accelerator implementation provides an average correlation of 0.9999, normalized root-mean-square error of 0.0038 and maximum SNR gain of 19 dB. The low computational complexity of the proposed architecture implies low power consumption. It consumes 12mW at 100MHz clock and 0.7mW at 500Hz clock.

In the automotive industry, new systems are being developed to enhance vehicle safety and driver convenience. These systems are increasingly complex to build and maintain. To develop these systems Renault makes intensive use of simulation and must deal with thousands of models. This huge number of models must be well managed. To manage these models, Renault has developed the SysML-based Model Identity Card (MIC), used with a Model-Based Simulation (MBSi) approach. However, despite this first solution, managing simulation models remains a difficult task. In this paper, we describe the current simulation model management approaches used at Renault, and their shortcomings and challenges in the modelling and simulation of complex automotive systems. We use Advanced Driver Assistance System (ADAS) and its Automatic Emergency Breaking (AEB) sub-system as examples to illustrate the utilization of the MIC and demonstrate current practices. From these examples, we derive main challenges faced by the virtual simulation team and propose research directions to solve them, based on state of the art methodologies for simulation models' validation and verification management.

Measuring electroencephalography (EEG) signals has a variety of important applications. Most processing systems utilize statistical machine learning algorithms. To increase accuracy of such systems, more data is measured in the form of increased channel-count, called High-Definition EEG (HD-EEG). EEG processing is hampered by noise from different instruments. While traditional detrending algorithms are highly resource intensive, the problem is compounded for HD-EEG detrending. The generic-compounding architecture is not scalable. In such an architecture, one instance of the hardware accelerator is utilized for each channel. This is unsuitable for wearable devices which have limited computational and energy resources. In this article, we propose a time-sliced architecture to optimize resource and power utilization for a multi-channelled system. This is accomplished using time-division multiplexers and demultiplexers to share resources between different channels. The Adaptive-Maximum-Mean-Minimum (AMaMeMi) filter is a computationally efficient algorithm, reported earlier for detrending EEGs. We apply guidelines of the proposed architecture, on the AMaMeMi filter, to design an efficient HD-EEG detrending hardware accelerator. The proposed accelerator is implemented for various channel-counts. We use the Xilinx field-programmable gate array with part number XC7VX980T-1FFG1930 for implementation. We verify the correctness of the proposed architecture by comparing its output with that of the generic-compounding architecture. For a 1024-channelled system, the proposed time-sliced architecture provides 99% reduction in look-up table utilization, 70% in flip-flop utilization, 95% in area utilization, and 70% in estimated power utilization.