Progress on the development of a wearable ultrasonic bladder monitoring device is reported. The device is intended to help in the diagnosis of urinary incontinence of both young and elderly patients. We present all the components of the device - the textile band, electronics, as well as the early results of reconstruction algorithms.

This research aimed to develop a high accuracy machine learning algorithm that can diagnose cardiovascular diseases from the stream of data from multiple body surface potential mapping devices equipped with 102 textile electrodes. The algorithm is based on the 1D convolutional neural network, trained on the comparable real-life data gathered from the FLUKE ECG simulator connected to the resistance-based human phantom. The developed neural network achieved an accuracy of 99.91% on the test data. Additionally, an additional algorithm was developed that can use the neural network to analyse the data streamed from the medical device and notice the medical staff about dangerous heart rhythms detected by the system.

Effective transition from raw industrial data to knowledge-based executive actions without human action requires developing new analytical tools, what also means new challenges for expert and intelligent systems. Studies must be conducted especially on developing effective analytical solutions for intelligent modules of Computerized Maintenance Management Systems, that take advantage of data analysis and decision support tools to predict and prevent the potential failure of machines or its elements. This is why the idea of a new classifier for condition assessment and Remaining Useful Life (RUL) prediction as an expert system tool for real-time monitoring of the manufacturing process was presented. Based on monitoring and current system check data, a new method enabling both early prediction of the machine tool’s remaining useful life and its current condition classification was devised. Its failure and normal properties were distinguished as well. To this end, it was proposed that the remaining useful life prediction should be made via the combined use of the Support Vector Machine (SVM) as a classification tool and AutoRegressive and Integrated Moving Average (ARIMA) based identification. This would provide process engineers and machine operators with an expert system that is easy to implement and use at the operational level, thus allowing them confidently perform technological processes, according to the acceptable failure probability.

This paper discusses the problem of timeconstrained job-shop scheduling with technological machine breakdown prediction.The first section gives short characteristics of the field of research, and describes the effects of machine failure on job completion times.Secondly, the discussed problem is represented by means of mathematical equations and solved with original algorithms for machine failure prediction and implementation of redundant service times, and finally, the proposed solutions are verified by means of simulation.In the computational experiment stage a typical production case with taking into account 3 machines failure was considered.The last part of this paper draws conclusions from the study and presents directions of future research work.

Scheduling production jobs in the real production system requires considering a number of factors which may prove to exert a negative effect on the production processes. Hence the need for the identification and compensation of potential disruptions as early as at the production planning stage. The aim of this paper is to employ the survival and the hazard function to anticipate potential disruptions of the schedule so that they could be absorbed to produce a robust job schedule.