Deep Learning-based Mental Health Monitoring Scheme for College Students Using Convolutional Neural Network

Artificial intelligence (AI) in healthcare has recently been promising using deep neural networks. It is indeed even been in clinical trials more and more, with positive outcomes. Deep learning is the process of using algorithms to train a neural network model using huge quantities of data to learn how to execute a given task and then make an accurate classification or prediction. Apart from physical health monitoring, such deep learning models can be used for the mental health evaluation of individuals. This study thus designs a deep learning-based mental health monitoring scheme (DL-MHMS) for college students. This model uses the most efficient convolutional neural network (CNN) to classify the mental health status as positive, negative, and normal using the EEG signals collected from college students. The simulation analysis achieves the highest classification accuracy and F1 scores of 97.54% and 98.35%, less sleeping disorder rate of 21.19%, low depression level of 18.11%, reduced suicide attention level of 28.14%, increasing personality development ratio of 97.52%, enhance self-esteem ratio of 98.42%, compared to existing models.

SealWasteSafe: materials technology, monitoring techniques, and quality assurance for safe sealing structures in underground repositories

Within the project SealWasteSafe, we advance construction materials and monitoring concepts of sealing structures applied for underground disposal of nuclear or toxic waste. As these engineered barriers have high demands concerning integrity, an innovative alkali-activated material (AAM) is improved and tested on various laboratory scales. This AAM has low reaction kinetics related to a preferential slow release of the heat of reaction in comparison to alternative salt concretes based on Portland cement or magnesium oxychloride cements. Hence, crack formation due to thermally induced strain is reduced. After successful laboratory scale analysis (Sturm et al., 2021), the AAM is characterised on a larger scale by manufacturing test specimens (100–300 L). Conventional salt concrete (DBE, 2004) and the newly developed AAM are compared using two specimen geometries, i.e. cylindrical and cuboid. A comprehensive multisensor monitoring scheme is developed to compare the setting process of AAM and salt concrete for these manufactured specimens. The analysed parameters include temperature and humidity of the material, acoustic emissions, and strain variations. Passive sensor systems based on radiofrequency identification technology (RFID) embedded in the concrete, enable wireless access to temperature and humidity measurements and are compared to conventional cabled systems. Additionally, fibre-optic sensors (FOS) are embedded to record strain, but also have potential to record temperature and moisture conditions. Part of this project aims at demonstrating the high reliability of sensors and also their resistance to highly alkaline environments and to water intrusion along cables or at sensor locations. Further technical improvements were implemented so that first results clearly show the scalability of the setting process from previous small-scale AAM experiments and particularly the high potential of the newly developed approaches. Furthermore, ultrasonic methods are used for quality assurance to detect obstacles, potential cracks and delamination. On the one hand, both active and passive ultrasonic measurements complement the results obtained from the multisensor monitoring scheme for the produced specimens. On the other hand, the unique large aperture ultrasonic system (LAUS) provides great depth penetration (up to nearly 10 m) and can thus be applied at in situ sealing structures built as a test site in Morsleben by the Federal Company for Radioactive Waste Disposal (Bundesgesellschaft für Endlagerung, BGE) as shown by Effner et al. (2021). An optimised field lay-out identified from forward modelling studies and advanced imaging techniques applied to the measured data will further improve the obtained results. To characterise the inside of the test engineered barrier and achieve a proof-of-concept, an ultrasonic borehole probe is developed to enable phased arrays that can further improve the detection of potential cracks. Modelling results and first analysis of semispherical specimens confirmed the reliability of the directional response caused by the phased arrays of the newly constructed ultrasonic borehole probe. Overall, the project SealWasteSafe improves the construction material, multisensor monitoring concepts and ultrasonics for quality assurance. This will help to develop safe sealing structures for nuclear waste disposal. The outcomes are particularly valuable for salt as a host rock but partly also transferrable to alternative conditions.

Bootstrap beta control chart for monitoring proportion data

PurposeAs an alternative to the standard p and np charts along with their various modifications, beta control charts are used in the literature for monitoring proportion data. These charts in general use average of proportions to set up the control limits assuming in-control parameters known. The purpose of the paper is to propose a control chart for detecting shift(s) in the percentiles of a beta distributed process monitoring scheme when in-control parameters are unknown. Such situations arise when specific percentile of proportion of conforming or non-conforming units is the quality parameter of interest.Design/methodology/approachParametric bootstrap method is used to develop the control chart for monitoring percentiles of a beta distributed process when in-control parameters are unknown. Extensive Monte Carlo simulations are conducted for various combinations of percentiles, false-alarm rates and sample sizes to evaluate the in-control performance of the proposed bootstrap control charts in terms of average run lengths (ARL). The out-of-control behavior and performance of the proposed bootstrap percentile chart is thoroughly investigated for several choices of shifts in the parameters of beta distribution. The proposed chart is finally applied to two skewed data sets for illustration.FindingsThe simulated values of in-control ARL are found to be closer to the theoretical results implying that the proposed chart for percentiles performs well with both positively and negatively skewed data. Also, the out-of-control ARL values for the percentiles decrease sharply with both downward and upward small, medium and large shifts in the parameters. The phenomenon indicates that the chart is effective in detecting shifts in the parameters. However, the speed of detection of shifts varies depending on the type of shift, the parameters and the percentile being considered. The proposed chart is found to be effective in comparison to the Shewhart-type chart and bootstrap-based unit gamma chart.Originality/valueIt is worthwhile to mention that the beta control charts proposed in the literature use average of proportion to set up the control limits. However, in practice, specific percentile of proportion of conforming or non-conforming items should be more useful as the quality parameter of interest than average. To the best of our knowledge, no research addresses beta control chart for percentiles of proportion in the literature. Moreover, the proposed control chart assumes in-control parameters to be unknown, and hence captures additional variability introduced into the monitoring scheme through parameter estimation. In this sense, the proposed chart is original and unique.