Mental fatigue is a major public health issue worldwide that is common among both healthy and sick people. In the literature, various modern technologies, together with artificial intelligence techniques, have been proposed. Most techniques consider complex biosignals, such as electroencephalogram, electro-oculogram or classification of basic heart rate variability parameters. Additionally, most studies focus on a particular area, such as driving, surgery, etc. In this paper, a novel approach is presented that combines electrocardiogram (ECG) signal feature extraction, principal component analysis (PCA), and classification using machine learning algorithms. With the aim of daily mental fatigue recognition, an experiment was designed wherein ECG signals were recorded twice a day: in the morning, i.e., a state without fatigue, and in the evening, i.e., a fatigued state. PCA analysis results show that ECG signal parameters, such as Q and R wave amplitude values, as well as QT and T intervals, presented with the largest differences between states compared to other ECG signal parameters. Furthermore, the random forest classifier achieved more than 94.5% accuracy. This work demonstrates the feasibility of ECG signal feature extraction for automatic mental fatigue detection.

Healthy lifestyle is one of the most important factors in the prevention of premature deaths, chronic diseases, productivity loss, obesity, and other economic and social aspects. The workplace plays an important role in promoting the physical activity and wellbeing of employees. Previous studies are mostly focused on individual interviews, various questionnaires that are a conceptual information about individual health state and might change according to question formulation, specialist competence, and other aspects. In this paper the work ability was mostly related to the employee’s physiological state, which consists of three separate systems: cardiovascular, muscular, and neural. Each state consists of several exercises or tests that need to be performed one after another. The proposed data transformation uses fuzzy logic and different membership functions with three or five thresholds, according to the analyzed physiological feature. The transformed datasets are then classified into three stages that correspond to good, moderate, and poor health condition using machine learning techniques. A three-part Random Forest method was applied, where each part corresponds to a separate system. The obtained testing accuracies were 93%, 87%, and 73% for cardiovascular, muscular, and neural human body systems, respectively. The results indicate that the proposed work ability evaluation process may become a good tool for the prevention of possible accidents at work, chronic fatigue, or other health problems.

The concept of a hyper coupled map lattice (CML) is presented in this paper. The complexity of the lattice is increased not by adding another spatial dimension of the lattice but by replacing scalar nodal variables by multidimensional square matrices of iterative variables. The proposed scheme exploits the nonlinear effects of the spatiotemporal divergence induced by nilpotent nodal matrices to generate separate secret images at different discrete moments of time during the evolution of the CML. The time variable plays the primary role in the decoding stage of the scheme. The carrying capacity of the proposed scheme is different dichotomous digital images, where is the dimension of the nilpotent nodal matrices. Computational experiments are used to demonstrate the efficacy of the proposed scheme.