Metrisor: A novel diagnostic method for metritis detection in cattle based on machine learning and sensors.

The Metrisor device has been developed using gas sensors for rapid, highly accurate and effective diagnosis of metritis. 513 cattle uteri were collected from abattoirs and swabs were taken for microbiological testing. The Metrisor device was used to measure intrauterine gases. The results showed a bacterial growth rate of 75.75 % in uteri with clinical metritis. In uteri positive for clinical metritis, the most commonly isolated and identified bacteria were Trueperella pyogenes, Fusobacterium necrophorum and Escherichia coli. Measurements taken with Metrisor to determine the presence of metritis in the uterus yielded the most successful results in evaluations of relevant machine learning algorithms. The ICO (Iterative Classifier Optimizer) algorithm achieved 71.22 % accuracy, 64.40 % precision and 71.20 % recall. Experiments were conducted to examine bacterial growth in the uterus and the random forest algorithm produced the most successful results with accuracy, precision and recall values of 78.16 %, 75.30 % and 78.20 % respectively. ICO also showed high performance in experiments to determine bacterial growth in metritis-positive uteri, with accuracy, precision and recall values of 78.97 %, 77.20 % and 79.00 %, respectively. In conclusion, the Metrisor device demonstrated high accuracy in detecting metritis and bacterial growth in uteri and could identify bacteria such as E. coli, S. aureus, coagulase-negative staphylococci, T. pyogenes, Bacillus spp., Clostridium spp. and F. necrophorum with rates up to 80 %. It provides a reliable, rapid and effective means of detecting metritis in animals in the field without the need for laboratory facilities.

Time-frequency analysis of phonocardiogram signals using wavelet transform: a comparative study.

Analysis of phonocardiogram (PCG) signals provides a non-invasive means to determine the abnormalities caused by cardiovascular system pathology. In general, time-frequency representation (TFR) methods are used to study the PCG signal because it is one of the non-stationary bio-signals. The continuous wavelet transform (CWT) is especially suitable for the analysis of non-stationary signals and to obtain the TFR, due to its high resolution, both in time and in frequency and has recently become a favourite tool. It decomposes a signal in terms of elementary contributions called wavelets, which are shifted and dilated copies of a fixed mother wavelet function, and yields a joint TFR. Although the basic characteristics of the wavelets are similar, each type of the wavelets produces a different TFR. In this study, eight real types of the most known wavelets are examined on typical PCG signals indicating heart abnormalities in order to determine the best wavelet to obtain a reliable TFR. For this purpose, the wavelet energy and frequency spectrum estimations based on the CWT and the spectra of the chosen wavelets were compared with the energy distribution and the autoregressive frequency spectra in order to determine the most suitable wavelet. The results show that Morlet wavelet is the most reliable wavelet for the time-frequency analysis of PCG signals.