Connectogram – A graph-based time dependent representation for sounds

Türker, İlker; AKSU, Serkan

doi:10.1016/j.apacoust.2022.108660

Cited by 7 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…GCNs, or graph convolutional networks, go beyond traditional graph embedding techniques like Deepwalk in that they focus on creating a low-dimensional network representation while excluding node features [ 12 , 13 ]. Graph representative learning techniques are proven to represent comparable or superior classification performance for various medical tasks, including the signal and image domains [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Lung Disease Detection Using U-Net Feature Extractor Cascaded by Graph Convolutional Network

Rashid,

Türker

2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

Computed tomography (CT) scans have recently emerged as a major technique for the fast diagnosis of lung diseases via image classification techniques. In this study, we propose a method for the diagnosis of COVID-19 disease with improved accuracy by utilizing graph convolutional networks (GCN) at various layer formations and kernel sizes to extract features from CT scan images. We apply a U-Net model to aid in segmentation and feature extraction. In contrast with previous research retrieving deep features from convolutional filters and pooling layers, which fail to fully consider the spatial connectivity of the nodes, we employ GCNs for classification and prediction to capture spatial connectivity patterns, which provides a significant association benefit. We handle the extracted deep features to form an adjacency matrix that contains a graph structure and pass it to a GCN along with the original image graph and the largest kernel graph. We combine these graphs to form one block of the graph input and then pass it through a GCN with an additional dropout layer to avoid overfitting. Our findings show that the suggested framework, called the feature-extracted graph convolutional network (FGCN), performs better in identifying lung diseases compared to recently proposed deep learning architectures that are not based on graph representations. The proposed model also outperforms a variety of transfer learning models commonly used for medical diagnosis tasks, highlighting the abstraction potential of the graph representation over traditional methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Lung Disease Detection Using U-Net Feature Extractor Cascaded by Graph Convolutional Network

Rashid,

Türker

2024

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, Convolutional Neural Network (CNN)s have been proposed due to their ability to learn local and high-level features on the image space [6,8]. Furthermore, most current approaches explore the use of pre-trained CNNs, by redefining the last layers to address the sound classification problem [5,10]. The downside is the inability to adequately capture the long time dependencies in an audio clip [11].…”

Section: Introductionmentioning

confidence: 99%

Transformers for Urban Sound Classification—A Comprehensive Performance Evaluation

Nogueira

Oliveira

Machado

et al. 2022

Sensors

View full text Add to dashboard Cite

Many relevant sound events occur in urban scenarios, and robust classification models are required to identify abnormal and relevant events correctly. These models need to identify such events within valuable time, being effective and prompt. It is also essential to determine for how much time these events prevail. This article presents an extensive analysis developed to identify the best-performing model to successfully classify a broad set of sound events occurring in urban scenarios. Analysis and modelling of Transformer models were performed using available public datasets with different sets of sound classes. The Transformer models’ performance was compared to the one achieved by the baseline model and end-to-end convolutional models. Furthermore, the benefits of using pre-training from image and sound domains and data augmentation techniques were identified. Additionally, complementary methods that have been used to improve the models’ performance and good practices to obtain robust sound classification models were investigated. After an extensive evaluation, it was found that the most promising results were obtained by employing a Transformer model using a novel Adam optimizer with weight decay and transfer learning from the audio domain by reusing the weights from AudioSet, which led to an accuracy score of 89.8% for the UrbanSound8K dataset, 95.8% for the ESC-50 dataset, and 99% for the ESC-10 dataset, respectively.

show abstract

“…In a Convolutional Neural Network (CNN), the data are propagated through the included layers via convolutions and other operations, e.g., pooling, flattening, and dropout, having the network the ability to learn both local-and high-level information on the image space (Giannakopoulos et al [7], Luz et al [8]). Sound classification based on Convolutional Neural Network (CNN)s has already been proposed, with most of the current approaches exploring the use of pretrained Convolutional Neural Network (CNN)s by redefining the last layers to tackle the sound classification problem (Mushtaq and Su [3], ˙Ilker Türker and Aksu [15]) and, recently, using attention models (Akbari et al [10], Kong et al [16]) and novel augmentation techniques (Mushtaq and Su [3], Salamon and Bello [17]).…”

Section: Introductionmentioning

confidence: 99%

Sound Classification and Processing of Urban Environments: A Systematic Literature Review

Nogueira

Oliveira

Machado

et al. 2022

Sensors

View full text Add to dashboard Cite

Audio recognition can be used in smart cities for security, surveillance, manufacturing, autonomous vehicles, and noise mitigation, just to name a few. However, urban sounds are everyday audio events that occur daily, presenting unstructured characteristics containing different genres of noise and sounds unrelated to the sound event under study, making it a challenging problem. Therefore, the main objective of this literature review is to summarize the most recent works on this subject to understand the current approaches and identify their limitations. Based on the reviewed articles, it can be realized that dl architectures, attention mechanisms, data augmentation techniques, and pretraining are the most crucial factors to consider while creating an efficient sound classification model. The best-found results were obtained by Mushtaq and Su, in 2020, using a DenseNet-161 with pretrained weights from ImageNet, and NA-1 and NA-2 as augmentation techniques, which were of 97.98%, 98.52%, and 99.22% for UrbanSound8K, ESC-50, and ESC-10 datasets, respectively. Nonetheless, the use of these models in real-world scenarios has not been properly addressed, so their effectiveness is still questionable in such situations.

show abstract

Connectogram – A graph-based time dependent representation for sounds

Cited by 7 publications

References 41 publications

Lung Disease Detection Using U-Net Feature Extractor Cascaded by Graph Convolutional Network

Lung Disease Detection Using U-Net Feature Extractor Cascaded by Graph Convolutional Network

Transformers for Urban Sound Classification—A Comprehensive Performance Evaluation

Sound Classification and Processing of Urban Environments: A Systematic Literature Review

Contact Info

Product

Resources

About