Automatic Diagnosis of Snoring Sounds with the Developed Artificial Intelligence-based Hybrid Model

Abstract

Sleep patterns and sleep continuity have a great impact on people's quality of life. The sound of snoring both reduces the sleep quality of the snorer and disturbs other people in the environment. Interpretation of sleep signals by experts and diagnosis of the disease is a difficult and costly process. Therefore, in the study, an artificial intelligence-based hybrid model was developed for the classification of snoring sounds. In the proposed method, first of all, audio signals were converted into images using the Mel-spectrogram method. The feature maps of the obtained images were obtained using Alexnet and Resnet101 architectures. After combining the feature maps that are different in each architecture, dimension reduction was made using the NCA dimension reduction method. The feature map optimized using the NCA method was classified in the Bilayered Neural Network. In addition, spectrogram images were classified with 8 different CNN models to compare the performance of the proposed model. Later, in order to test the performance of the proposed model, feature maps were obtained using the MFCC method and the obtained feature maps were classified in different classifiers. The accuracy value obtained in the proposed model is 99.5%

An Optimized Data and Model Centric Approach for Multi-Class Automated Urine Sediment Classification

“…The proposed method exhibits clear advantages compared to state-of-the-art, as illustrated in Table 5. It can be seen that the proposed method's accuracy is a little lower [3]; however, it exceeds [4], [5], [45], [18] and [44]. It is worth noting that the methodologies proposed in [3] can successfully handle only 7 out of the 12 categories in the given recognition challenge.…”

“…Motivation: Inspired by the diverse model architectures used by [5] , [18], and [22], our hybrid approach integrates modelcentric techniques to refine the architecture and parameters. This ensures that the deep learning model is well-suited to capture intricate patterns in urine sediment images, fostering improved recognition of classes and overall model performance.…”

“…Motivation: Recognizing the challenges posed by class imbalance, evident in models like [5] our hybrid approach is strategically designed to tackle these issues head-on. Through a combination of data-centric technique and modelcentric adjustments, we strive to balance class representation, ensuring that the model is equally proficient in distinguishing both prevalent and less frequent components in urine sediment samples.…”

“…These parameters hold paramount importance in the assessment of various acute or chronic medical conditions [1], [2], [3], [4]. Moreover, the identification and measurement of protein or sugar in urine serve as crucial indicators in diagnosing several kidneyrelated ailments, particularly kidney failure [5]. Regrettably, conventional microscopic examination-based methods for urine sediment analysis suffer from inefficiency and subjectivity, rendering them error-prone and time-consuming [6], [7].…”

“…Object segmentation is crucial for identifying and distinguishing individual cell types and sediments [12], [13]. The effectiveness of these methods depends on precise target segmentation and the efficient selection and combination of relevant features, as emphasized in previous studies [3], [5]. Deep learning models, particularly convolutional neural networks (CNNs) [14], [15], [16], [17], have emerged as pivotal tools in image recognition.…”