Explore the vast range of titles available.

Cardiovascular diseases (CVDs) pose a significant threat to human health and place considerable strain on healthcare systems. Therefore, it is crucial to maximize the acquisition of cardiovascular information (CVI) through non-invasive methods to enhance early screening, diagnosis, and evaluation of CVDs. Numerous studies have demonstrated that obtaining more CVI by simultaneously acquiring multi-site signals and applying pressure stimulation at specific sites, such as blood pressure measurement, is an effective approach. Based on this evidence, we proposed a novel signal acquisition-and-analysis system to gather comprehensive CVI through a combination of a non-pressure and six pressure-stimulation sub-processes. This system involves the novelty of applying slowly gradual decrease, personalized maximum-pulse amplitude, and blocking blood-flow pressure to six cuffs placed on both arms, wrists, and ankles in a predetermined time sequence. During each sub-process, the system has newly integrated the multi-site simultaneous collection of 27-channel non-invasive signals, including electrocardiogram, heart sound, lung sound, photoplethysmographic-and-pressure pulse. To ensure measurement accuracy, three types of verification-and-calibration instruments were employed. Our results demonstrate that the system can achieve simultaneous acquisition of 27-channel signals during each sub-process, yielding both novel and traditional cardiovascular parameters with high accuracy and good stability. Furthermore, the results suggest that the system can facilitate in-depth research into the relationships between collected signals and CVDs, provide rich raw data for cardiovascular health assessment and disease prediction models based on machine learning algorithms, and offer a new non-invasive method for early diagnosis, evaluation, and prediction of CVDs.

Providing a comfortable sound for users is an important factor for high-value products. Therefore, many studies have investigated pleasant sound levels for developing and manufacturing new products. Notably, sounds containing 1/f fluctuations provide a relaxing effect in humans. There are many studies on the influence of sound signals, including 1/f fluctuations; however, the verification of fluctuations, including sound signals, has not been performed. In this study on fluctuation, the discrete Fourier transform was used to directly calculate the time of the sound signal. We evaluated the duration of music and the 1/f fluctuation via the discrete Fourier transform using the time history of the music data. Furthermore, we investigated the relaxation effect of music containing a 1/f fluctuation. We determined a person’s comfort according to the difference in the calculated fluctuation coefficient by subjectively evaluating the comfort felt by people when listening to music with two different fluctuation coefficients, and we examined the improvement in the fluctuation coefficient and human comfort.

Recently, the development of online quality monitoring system based on the arc sound signal has become one of the main interests due its ability to provide the non-contact measurement. Notwithstanding, numerous unrelated-to-defect sources which influence the sound generation are one of the aspects that increase the difficulties of applying this method to detect the defect during welding process. This work aims to reveal the hidden information that associates with the existence of irregularities and porosity on the weld bead from the acquired arc sound by applying the discrete wavelet transform. To achieve the aim, the arc sound signal was captured during the metal inert gas (MIG) welding process of three API 5L X70 steel specimens. Prior to the signal acquisition process, the frequency range was set from 20 Hz to 10 000 Hz which is in audible range. In the next stage, a discrete wavelet transform was applied to the acquired sound in order to reveal the hidden information associated with the occurrence of discontinuity and porosity. According to the results, it was clear that the acquired arc sound was not giving an obvious indication of the presence of defect as well as its location due to the high noise level. More interesting findings have been obtained when the discrete wavelet transform (DWT) analysis was applied. The analysis results indicate that the level 8 of the approximate and detail wavelet coefficient have given a significant sign associated with the presence of irregularities and porosity respectively. Moreover, despite giving the information on the surfaces pores, the detail wavelet coefficient was found to give a clear indication of the sub-surface porosity formation during welding process. Hence, it could be concluded that the hidden information with respect to the occurrence of discontinuity and porosity on the weld bead could be obtained by applying the discrete wavelet transform.

Lung auscultation has long been used as a valuable medical tool to assess respiratory health and has gotten a lot of attention in recent years, notably following the coronavirus epidemic. Lung auscultation is used to assess a patient’s respiratory role. Modern technological progress has guided the growth of computer-based respiratory speech investigation, a valuable tool for detecting lung abnormalities and diseases. Several recent studies have reviewed this important area, but none are specific to lung sound-based analysis with deep-learning architectures from one side and the provided information was not sufficient for a good understanding of these techniques. This paper gives a complete review of prior deep-learning-based architecture lung sound analysis. Deep-learning-based respiratory sound analysis articles are found in different databases including the Plos, ACM Digital Libraries, Elsevier, PubMed, MDPI, Springer, and IEEE. More than 160 publications were extracted and submitted for assessment. This paper discusses different trends in pathology/lung sound, the common features for classifying lung sounds, several considered datasets, classification methods, signal processing techniques, and some statistical information based on previous study findings. Finally, the assessment concludes with a discussion of potential future improvements and recommendations.

Cardiac disorders are critical and must be diagnosed in the early stage using routine auscultation examination with high precision. Cardiac auscultation is a technique to analyze and listen to heart sound using electronic stethoscope, an electronic stethoscope is a device which provides the digital recording of the heart sound called phonocardiogram (PCG). This PCG signal carries useful information about the functionality and status of the heart and hence several signal processing and machine learning technique can be applied to study and diagnose heart disorders. Based on PCG signal, the heart sound signal can be classified to two main categories i.e., normal and abnormal categories. We have created database of 5 categories of heart sound signal (PCG signals) from various sources which contains one normal and 4 are abnormal categories. This study proposes an improved, automatic classification algorithm for cardiac disorder by heart sound signal. We extract features from phonocardiogram signal and then process those features using machine learning techniques for classification. In features extraction, we have used Mel Frequency Cepstral Coefficient (MFCCs) and Discrete Wavelets Transform (DWT) features from the heart sound signal, and for learning and classification we have used support vector machine (SVM), deep neural network (DNN) and centroid displacement based k nearest neighbor. To improve the results and classification accuracy, we have combined MFCCs and DWT features for training and classification using SVM and DWT. From our experiments it has been clear that results can be greatly improved when Mel Frequency Cepstral Coefficient and Discrete Wavelets Transform features are fused together and used for classification via support vector machine, deep neural network and k-neareast neighbor(KNN). The methodology discussed in this paper can be used to diagnose heart disorders in patients up to 97% accuracy. The code and dataset can be accessed at “https://github.com/yaseen21khan/Classification-of-Heart-Sound-Signal-Using-Multiple-Features-/blob/master/README.md”.

The analysis of heart sound signals is critical in the early diagnosis of cardiovascular disease. However, the complexity and diversity of these signals pose significant challenges for accurate recognition. In this paper, we propose a novel heart sound dual-branch feature extraction network (HSDFE-Net) to address these challenges. The model first extracts both conventional audio features and bi-spectrum features from preprocessed heart sound signals, enabling comprehensive characterization of their linear spectral and nonlinear properties. Unlike conventional single-branch networks, HSDFE-Net employs a dual-branch architecture where one branch processes bi-spectrum features to capture nonlinear relationships, while the other processes conventional audio features. By fusing these complementary feature sets, the network achieves a more thorough understanding of signal characteristics. Furthermore, a squeeze-and-excitation module is integrated into the conventional audio branch to adaptively emphasize key feature channels, which enhances overall model performance. Experimental results on three public datasets demonstrate that HSDFE-Net achieves accuracies of 99.00%, 99.53%, and 83.33%, validating its effectiveness and robustness in heart sound analysis and providing a promising solution for heart sound recognition.

Chatter is a self-excited vibration between the workpiece and tool with negative effects. In this work, a chatter detection method is proposed based on synchrosqueezing transform (SST) of sound signals. Firstly, the SST is used to analyze the sound signals recorded with the microphone and a time-frequency representation is obtained. Then, filtering is conducted to remove the disturbance of tooth passing frequency and its harmonics in time-frequency domain. Next, singular value decomposition (SVD) method is employed to condense the TF matrix and the first-order singular value is calculated as the chatter indicator. Finally, chatter threshold is set based on 3 σ criterion for the detection of chatter occurrence. The proposed method is validated with cutting tests, and the results show that the method has great potential to be used for the online chatter detection of high-speed milling process.

Piping systems play a crucial role in modern society and industry, serving as a fluid transport system with a high level of integrity. Yet, they also encounter significant problems, including leakages. Several researchers have developed methods for detecting leak positions in pipes. The current detection method uses pressure differences and ultrasonic waves, which are relatively expensive, and the instruments, equipment, and sensors used are very expensive. In this study, a leak detection system for straight pipes using sound signals was developed. For this purpose, a test setup was created using a straight PVC pipe with a length of 1.55 m as the test object, a loudspeaker to provide sound excitation into the pipe, a sound microphone to capture reflected sound from inside the pipe, and a sound card to convert analog data to digital. The loudspeaker provides sound excitation in the form of impulses into the pipe, and the microphone captures the reflected sound inside the pipe. The sound signal is then processed using signal processing software with a wavelet transform to extract the position of the leak. The leak position can be detected very well, which is indicated by a higher peak value of the wavelet coefficient. From the test, the results obtained were that the greater the damage given, the greater the value of the wavelet coefficient produced, with an error in position detection of less than 5%. It has been confirmed that the proposed method works very well in detecting the position of leaks in pipes, promising low-cost damage detection.

Acoustic cameras (ACs) have become very popular in the last decade as an increasing number of applications in environmental acoustics are observed, which are mainly used to display the points of greatest noise emission of one or more sound sources. The results obtained are not yet certifiable because the beamforming algorithms or hardware behave differently under different measurement conditions, but at present, not enough studies have been dedicated to clarify the issues. The present study aims to provide a methodology to extract analytical features from sound maps obtained with ACs, which are generally only visual information. Based on the inputs obtained through a specific measurement campaign carried out with an AC and a known sound source in free field conditions, the present work elaborated a methodology for gathering the coordinates of the maximum emission point on screen, its distance from the real position of the source and the uncertainty associated with this position. The results obtained with the proposed method can be compared, thus acting as a basis for future comparison studies among calculations made with different beamforming algorithms or data gathered with different ACs in all real case scenarios. The method can be applicable to any other sector interested in gathering data from intensity maps not related to sound.

In response to the difficulties faced in detecting bolt connection damage in steel truss structures, this paper proposes a bolt loosening identification method based on sound signal analysis, a Genetic Algorithm-Optimized Support Vector Machine (GA-SVM), and Recursive Feature Elimination (RFE). By preprocessing and feature extraction of sound signals, short-term energy, short-term zero crossing rate, and wavelet packet frequency band energy features were extracted. SVM-RFE was used for sensitive feature selection, and genetic algorithm was combined to optimize SVM parameters, ultimately obtaining the optimal recognition model. The effectiveness of this method was verified through bolt loosening tests on steel truss structures. The results showed that the method can achieve a recognition accuracy of 99.5% with a small training dataset, and has strong practicality and feasibility, providing technical support for safety monitoring of engineering structures.