OBJECTIVES: This study aimed to segment the breath cycles from pulmonary acoustic signals using the newly developed adaptive neuro-fuzzy inference system (ANFIS) based on breath phase detection and to subsequently evaluate the performance of the system.
METHODS: The normalised averaged power spectral density for each segment was fuzzified, and a set of fuzzy rules was formulated. The ANFIS was developed to detect the breath phases and subsequently perform breath cycle segmentation. To evaluate the performance of the proposed method, the root mean square error (RMSE) and correlation coefficient values were calculated and analysed, and the proposed method was then validated using data collected at KIMS Hospital and the RALE standard dataset.
RESULTS: The analysis of the correlation coefficient of the neuro-fuzzy model, which was performed to evaluate its performance, revealed a correlation strength of r = 0.9925, and the RMSE for the neuro-fuzzy model was found to equal 0.0069.
CONCLUSION: The proposed neuro-fuzzy model performs better than the fuzzy inference system (FIS) in detecting the breath phases and segmenting the breath cycles and requires less rules than FIS.
METHODS: Twenty-five young and healthy university students performed a triceps push-down exercise at 45% one repetition maximum (1RM) with and without CS until task failure, and the rate of fatigue (ROF), endurance time (ET) and number of repetitions (NR) for both exercises were analyzed. In addition, the first and last six repetitions of each exercise were considered non-fatiguing (NF) and fatiguing (Fa), respectively, and the root mean square (RMS), mean power frequency (MPF) and median frequency (MDF) for each exercise repetition were evaluated.
RESULTS: The lateral and long head showed significant differences (P<0.05) in the ROF between the two exercises, and all the heads showed significant (P<0.05) differences in the RMS between the two exercises under NF conditions. Only the long head showed a significant difference (P<0.05) in the MPF and MDF between the two exercises. CS increases the ET (24.74%) and NR (27%) of the exercise. The three heads showed significant differences (P<0.05) in the RMS, MPF and MDF under all exercise conditions.
CONCLUSION: A lower ROF was obtained with CS. In addition, the RMS was found to be better approximator of CS, whereas MPF and MDF were more resistant to the effect of CS. The results showed that the three heads worked independently under all conditions, and the non-synergist and synergist head pairs showed similar behavior under Fa conditions. The findings from this study provide additional insights regarding the functioning of each TB head.
AIMS: To develop a model to detect the respiratory phases present in the pulmonary acoustic signals and to evaluate the performance of the model in detecting the respiratory phases.
METHODS: Normalised averaged power spectral density for each frame and change in normalised averaged power spectral density between the adjacent frames were fuzzified and fuzzy rules were formulated. The fuzzy inference system (FIS) was developed with both Mamdani and Sugeno methods. To evaluate the performance of both Mamdani and Sugeno methods, correlation coefficient and root mean square error (RMSE) were calculated.
RESULTS: In the correlation coefficient analysis in evaluating the fuzzy model using Mamdani and Sugeno method, the strength of the correlation was found to be r = 0.9892 and r = 0.9964, respectively. The RMSE for Mamdani and Sugeno methods are RMSE = 0.0853 and RMSE = 0.0817, respectively.
CONCLUSION: The correlation coefficient and the RMSE of the proposed fuzzy models in detecting the respiratory phases reveals that Sugeno method performs better compared with the Mamdani method.
METHODS: Twenty male participants performed repetitive submaximal (60% MVIC) grip muscle contractions to induce muscle fatigue and the results were analyzed during the pre- and post-fatigue MVIC. MMG signals were recorded on the extensor digitorum (ED), extensor carpi radialis longus (ECRL), flexor digitorum superficialis (FDS) and flexor carpi radialis (FCR) muscles. The cross-correlation coefficient was used to quantify the cross-talk values in forearm muscle pairs (MP1, MP2, MP3, MP4, MP5 and MP6). In addition, the MMG RMS and MMG MPF were calculated to determine force production and muscle fatigue level, respectively.
RESULTS: The fatigue effect significantly increased the cross-talk values in forearm muscle pairs except for MP2 and MP6. While the MMG RMS and MMG MPF significantly decreased (p<0.05) based on the examination of the mean differences from pre- and post-fatigue MVIC.
CONCLUSION: The presented results can be used as a reference for further investigation of cross-talk on the fatigue assessment of extensor and flexor muscles' mechanic.