Modern predictive maintenance techniques have been significantly improved with the development of Industrial Internet of Things solutions which have enabled easier collection and analysis of various data. Artificial intelligence-based algorithms in combination with modular interconnected architecture of sensors, devices and servers, have resulted in the development of intelligent maintenance systems which outperform most traditional machine maintenance approaches. In this paper, a novel acoustic-based IoT system for condition detection of rotating machines is proposed. The IoT device designed for this purpose is mobile and inexpensive and the algorithm developed for condition detection consists of a combination of discrete wavelet transform and neural networks, while a genetic algorithm is used to tune the necessary hyperparameters. The performance of this system has been tested in a real industrial setting, on different rotating machines, in an environment with strong acoustic pollution. The results show high accuracy of the algorithm, with an average F1 score of around 0.99 with tuned hyperparameters.

Linear regression is a very simple machine learning model that is supposed to find linear relations between input and output data. Its use is limited since real-world random variables are almost never linearly correlated, but when there is limited amount of data for training, using other larger and more sophisticated models might be impossible. Even though simple linear relations are hard to come by in nature, more complex mathematical dependencies can often be linearized i.e. approximated using linear models. Additionally, by preprocessing the input data using nonlinear mathematical operations linear regression can artificially account for nonlinear relations. This methodology was tested on real data representing measurements in thermal power plant while the goal was predicting the specific energy of the coal that was being burnt in the plant. Estimating coals caloric value is of tremendous value since using this information power plant can be configured to run more efficiently.

The standing long jump (SLJ) is a test used to evaluate lower limb strength and function. In addition to jump distance, evaluating stability during the jump is also important. This study investigates stability classification in SLJ by analysing the rotational movements of the lower limbs. Inertial sensors were used to collect kinematic data from 10 healthy subjects. Segment and joint angles were derived based on angular velocities in the sagittal plane. Functional principal component analysis (fPCA) was performed on two datasets: joint angles (MfPCAjoint) and segment angles (MfPCAsegment). The resulting fPCA scores were used as inputs for support vector machine classifiers. The classification accuracy was 86% for MfPCAjoint and 85% for MfPCAsegment, with MfPCAjoint also showing more consistent performance metrics. These results suggest that fPCA scores can effectively describe stability, although a larger dataset is necessary for further validation.

The efficacy of any moving target tracking technique depends on the understanding the background, or clutter, and the parameters that describe the detection properties of the objects. The nature of these quantities is statistical and not only are they unknown as a rule in practice, but they are also variable over both time and space. The study proposes a method for estimating the time‐varying probability of detection of each tracked object individually, and the density of false alarms in the immediate vicinity of the current position of an object. The method is based on the generalised maximum likelihood approach, assuming tracking of a solitary target. The applicability and constraints of the proposed solution are illustrated by simulations.

Several recently signed environmental agreements and protocols emphasize the global need to reduce GHG emissions, with a focus on limiting coal consumption due to high NOx and CO2 emissions. However, many countries, including those in the Western Balkans, rely heavily on coal for electricity generation. The outdated thermal power plant infrastructure in these regions poses a major challenge when it comes to meeting modern environmental standards while maintaining efficiency. This study is part of the more comprehensive research which aims to develop an expert system that utilizes existing measurements to estimate key parameters crucial for both energy production and pollution reduction. The focus is on Serbian thermal power plants, particularly plant Nikola Tesla unit B1. One of the critical parameters for optimizing thermal power plant control loops is the heating value of coal, which is challenging to measure in real time due to the coal?s varying chemical compositions and caloric values. This paper examines 74 different parameters measured in 59 instances to estimate the hating value of coal at unit B1. Through detailed analysis and feature selection methods, including linear regression, this research aims to identify the most informative parameters for estimating the heating value of coal, which will improve the control system that enables more efficient and environmentally friendly power generation in coal fired thermal power plants.