Fusion of Data Augmentation for Improved Dysarthria Severity Classification

Dysarthria is a neurological speech disorder that affects the speech intelligibility of the speaker. Speech assistive aids are developed to support their communication needs. Successful speech assistive aids are developed using automatic speech recognition systems trained using their own speech data. The effectiveness and usefulness of speech recognition systems depend on the amount of speech data used for training. However, collecting a large amount of dysarthric speech data is difficult. Data augmentation involves applying transformation techniques to increase the quantity of available speech data. Adding noise data is also one of the approaches to make such transformations and create a new volume of data. However, care should be taken while using noise data for the transformation of the dysarthric speech data since dysarthria on its own is disordered data, and adding even more distortion reduces its quality of it. However, by performing a proper analysis of the noisy data, noise can also be used as a source to create new samples of dysarthric speech data. This paper concentrates on identifying noise characteristics and finding the suitability of using noise as a source for data augmentation in dysarthric speech. With the noise-augmented dysarthric speech data, dysarthric speech recognition systems were trained to evaluate the quality of the augmented data. It was noted that for dysarthric speakers, especially with the severe category, the low-frequency noise selection approach has resulted in a lower WER than the without augmentation by 12.29%.

Knee osteoarthritis (KOA) is a prevalent degenerative joint disease requiring accurate severity assessment for effective management. Manual grading of KOA severity from X-ray images using the Kellgren-Lawrence (KL) system is subjective and time-consuming. Deep learning, particularly transfer learning with Convolutional Neural Networks (CNNs), offers a promising automated alternative. This study evaluates the performance of six widely used pre-trained CNN architectures (VGG16, VGG19, InceptionV3, DenseNet121, MobileNetV2, and ResNet101) applied by transfer learning to classify the severity of KOA into five KL grades (0-4) using the publicly available "Knee Osteoarthritis Dataset with Severity Grading". Models were trained using standard preprocessing and data augmentation. Performance was evaluated based on test accuracy and computational efficiency. Results indicate that VGG16 achieved the highest test accuracy (68.90%), closely followed by VGG19 (67.63%), while other architectures performed in the mid-60s percentage range. A distinct trade-off between accuracy and efficiency was observed, with larger VGG models being most accurate but slowest, and MobileNetV2 offering the fastest training with slightly lower accuracy. While demonstrating the feasibility of transfer learning for 5-class KOA grading, the performance suggests that achieving higher accuracy requires further optimization, potentially through deeper fine-tuning, class balancing strategies, or hybrid approaches. This work establishes a comparative baseline for applying widely used pre-trained models to the challenging task of knee osteoarthritis severity classification.

Chronic obstructive pulmonary disease (COPD) is a major public health concern across the world. Since it is an incurable disease, early detection, and accurate diagnosis are very crucial for preventing the progression of the disease. Lung sounds provide reliable and accurate prognoses for identifying respiratory diseases. Recently, Altan et al. recorded 12-channel real-time lung sound dataset, namely RespiratoryDatabase@TR, for five different severity levels of COPD at Antakya State Hospital Turkey, and proposed deep learning frameworks for two-class COPD classification and five-class classification using a deep belief network (DBN) classifier and extreme learning machine (ELM) classifier respectively. A classification accuracy of 95.84% and 94.31% were achieved for two-class and five-class, respectively. In this paper, we have proposed a melspectrogram snippet representation learning framework for both two-class and five-class COPD classification. The proposed framework consists of the following stages: data augmentation and pre-processing, melspectrogram snippet representation generation from lung sound, and fine-tuning of a pre-trained YAMNet. Experimental analysis on the RespiratoryDatabase@TR dataset demonstrates that the proposed framework achieves accuracies of 99.25% and 96.14% for binary and multi-class COPD severity classification, respectively, which are superior to the only existing methods proposed by Altan et al. for severity analysis of COPD using lung sounds.

Diabetic retinopathy (DR) is a complication of diabetes which is due to the impairment of blood vessels of photosensitive cells in the eyes. This complication results in loss of eyesight if not diagnosed in the early stages. There are five stages of diabetic retinopathy: No DR, mild, moderate, severe, and proliferative. DR detection by traditional methods consumes a lot of time. An automatic and precise model would require an adequate amount of data for training which is not available. Publicly available dataset is highly imbalanced for other classes apart from No DR, especially proliferative and severe classes. In this paper, a model is created in two stages. The first stage involves the generation of synthetic data points using Deep Convolutional Generative Adversarial Network (DCGAN). The synthetic data are for highly imbalanced classes namely severe and proliferative. The second phase involves the augmented data classification using a CNN architecture.

Introduction: Every area of our lives has been devastated by the worldwide Coronavirus disease 2019 (COVID-19) epidemic. However, the development of artificial intelligence has made it possible to build advanced applications that can fulfill this level of clinical accuracy. This study aimed to create a deep learning model that can detect COVID-19 from a chest image dataset of confirmed patients treated at the provincial hospital in Aceh. Methods: Eight hundred confirmed COVID-19 patients' chest X-ray photos were gathered locally from Dr. Zainoel Abidin General Hospital, Banda Aceh. Performance was evaluated in several ways. First, the dataset was used for training and testing. Second, the data was used to train and test the model. VGG16 is a robust network adapted to an enhanced dataset constructed from a confirmed COVID-19 chest X-ray pool. To artificially produce a huge number of chest X-ray pictures, this study used data augmentation techniques such as random rotation at an angle between 10 and 10°, random noise, and horizontal flips. Results: The experimental results were encouraging: the proposed models classified chest X-ray pictures as normal or COVID-19 with an accuracy of 97.20% for Resnet50, 98.10% for InceptionV3, and 98.30% for VGG16. The results showed the outstanding performance of straightforward COVID-19 diagnosis with the classification of COVID-19 severity, such as mild, severe, and very severe. Conclusion: These made it possible to automate the X-ray image interpretation process accurately and could also be applied when materials and reverse transcription polymerase chain reaction (RT-PCR) tests are scarce.

A Machine Learning with Ordinal Ranking Approach for Dysarthria Severity Classification in Parkinson’s Disease

Speaker independent dysarthria severity classification using synthesis-based augmentation

The lungs are critical components of the respiratory system because they allow for the exchange of oxygen and carbon dioxide within our bodies. However, a variety of conditions can affect the lungs, resulting in serious health consequences. Lung disease treatment aims to control its severity, which is usually irrevocable. The fundamental objective of this endeavor is to build a consistent and automated approach for establishing the intensity of lung illness. This paper describes MixNet-LD, a unique automated approach aimed at identifying and categorizing the severity of lung illnesses using an upgraded pre-trained MixNet model. One of the first steps in developing the MixNet-LD system was to build a pre-processing strategy that uses Grad-Cam to decrease noise, highlight irregularities, and eventually improve the classification performance of lung illnesses. Data augmentation strategies were used to rectify the dataset’s unbalanced distribution of classes and prevent overfitting. Furthermore, dense blocks were used to improve classification outcomes across the four severity categories of lung disorders. In practice, the MixNet-LD model achieves cutting-edge performance while maintaining model size and manageable complexity. The proposed approach was tested using a variety of datasets gathered from credible internet sources as well as a novel private dataset known as Pak-Lungs. A pre-trained model was used on the dataset to obtain important characteristics from lung disease images. The pictures were then categorized into categories such as normal, COVID-19, pneumonia, tuberculosis, and lung cancer using a linear layer of the SVM classifier with a linear activation function. The MixNet-LD system underwent testing in four distinct tests and achieved a remarkable accuracy of 98.5% on the difficult lung disease dataset. The acquired findings and comparisons demonstrate the MixNet-LD system’s improved performance and learning capabilities. These findings show that the proposed approach may effectively increase the accuracy of classification models in medicinal image investigations. This research helps to develop new strategies for effective medical image processing in clinical settings.

Traffic safety is a critical issue in urban transportation systems, with crash severity predictions playing a key role in mitigating road traffic injuries and fatalities. This study addresses the research question: how can transforming tabular crash data into image-based representations using deep learning techniques improve the prediction of crash severity, while effectively managing class imbalances? For analysis, 63,745 barrier crashes that occurred in Texas from 2017–2022 were examined. Using a sample database of barrier crash incidents, we introduce a novel approach that leverages Convolutional Neural Networks (CNNs) to convert traditional tabular crash data into image representations by employing the DeepInsight technique, which maps feature similarity into structured two-dimensional grids, enhancing the accuracy and effectiveness of prediction models. Generative Adversarial Networks (GANs) were used for data augmentation, addressing issues of class imbalances with innovative sampling techniques including under-sampling, over-sampling, and balanced sampling. Key findings indicate that balanced datasets significantly improve predictive performance, enhancing generalizability across diverse crash scenarios. Moreover, under- and over-sampling strategies offer a refined trade-off among precision, recall, and F1-score, while the over-sampling method distinctly excels in practical model performance by reducing misclassification rates and improving overall accuracy. Comparative evaluation against an XGBoost baseline on identical balanced data highlights the ability of the image-based deep learning framework to capture complex crash patterns. These findings suggest that integrating feature-similarity–based tabular-to-image transformation with deep learning and balanced data sampling can significantly improve crash severity classification.

Condition monitoring and diagnosis of a bearing are very important for any rotating machine as it governs the safety while the machine is in operating condition. To construct a feature vector selection of suitable signal processing techniques is a challenge for vibration-based condition monitoring techniques. In the methodology proposed, Short Time Fourier Transform (STFT), Walsh Hadamard Transform (WHT) and Variable Mode Decomposition (VMD) are used to generate 2-D time-frequency spectrograms from the various fault conditions of bearing. When Deep learning techniques apply for fault diagnosis, a large amount of dataset is required for training of machine learning model. To overcome this issue single image Generative Adversarial Network (SinGAN) as a data augmentation technique, utilized for generating additional 2-D time-frequency spectrograms from various fault conditions of ball bearing. To detect fault severity, four deep learning algorithms, ResNet 34, ResNet50, VGG16, and MobileNetV2 are used as a classifier. Experiments are conducted on a rolling bearing dataset provided by the bearing data center of Case Western Reserve University (CWRU) for validating the utility of methodology proposed. Results show that the proposed methodology enables to detect fault severity level with high classification accuracy.

Diabetic retinopathy is a serious concern for people dealing with diabetes. Detecting diabetic retinopathy poses significant challenges, requiring skilled professionals, extensive manual image processing, and considerable time investment. Fortunately, the integration of deep learning and transfer learning offers invaluable assistance to medical practitioners. This study introduces an ensemble classification framework to detect and grade diabetic retinopathy into 5 classes leveraging the concepts of transfer learning and data fusion. It utilizes three benchmark datasets on diabetic retinopathy: APTOS 2019, IDRiD, and Messidor-2. Initially, these datasets are merged, resulting in a total of 5922 fundus images. Then this fused dataset undergoes pre-processing. Firstly, the images are cropped to remove unwanted regions. Then, Contrast Limited Adaptive Histogram Equalization is applied to improve image quality and fine details. To tackle class imbalance issues, Synthetic Minority Over Sampling technique is employed. Additionally, data augmentation techniques such as flipping, rotation, and zooming are used to increase dataset diversity. The dataset is split into training, validation, and testing sets at a ratio of 70:10:20. For classification, three pre-trained CNN models, EfficientNetB2, DenseNet121, and ResNet50, are fine-tuned. After these models are trained, an ensemble model is constructed by averaging the predictions of each model. Results show that the ensemble model achieved the highest test accuracy of 96.96% in grading diabetic retinopathy into 5 classes outperforming the individual pre-trained models. Furthermore, the ensemble model’s performance is compared with previously published approaches where this model demonstrated superior result.

For efficient patient care and management, the correct and prompt assessment of CoVID severity using X-Ray images is crucial. Existing approaches for classifying CoVID severity from X-ray images have shortcomings in precision, accuracy, recall, and latency; as a result, more reliable and effective ways must be developed. This study introduces "SynthXNet," a unique approach that uses adversarial learning and data augmentation to improve the performance of CoVID severity classification, in response to such demands. A substantial collection of X-Ray images is acquired, covering cases of CoVID patients with differing degrees of severity, spanning different age groups, genders, and ethnicities, to address the dearth of diverse and representative datasets & samples. The Generative Adversarial Network (GAN) architecture, which consists of a generator and discriminator network, is the central innovation of this work. To create artificial images that closely mimic actual X-Rays of CoVID patients, the GAN is trained on the X-Ray dataset that has been gathered. In an adversarial training procedure, the generator and discriminator teach each other to produce realistic images while the discriminator teaches each other to discern between actual and fake X-Rays. A deep learning model, specifically a Convolutional Neural Network (CNN), used for CoVID severity classification uses the synthetic X-Ray images produced by the GAN as extra training data. In comparison to recently proposed methods, the model’s precision increases by 8.5%, accuracy by 9.4%, and recall by 8.3% when the dataset is supplemented with these synthetic images. The suggested method also speeds up CoVID severity classification by 4.9%, making it more effective for real-time scenarios. In order to overcome the shortcomings of existing approaches, "SynthXNet" presents a potent solution to CoVID severity classification from X-Ray images by utilizing adversarial learning and data augmentation. Its potential to improve patient care and management in the context of CoVID severity evaluation is indicated by the results, which show significant increases in performance indicators.

Electromyography signals are electrical signals generated by muscle activity and are very useful for analyzing the health conditions of muscles and nerves. Data imbalance is a prevalent issue in EMG signal data, especially when addressing patients with varied health conditions and restricted data availability. A major difficulty for machine learning models is class imbalance in datasets, which frequently leads to biased predictions favoring the dominant class and neglecting the minority classes. The data augmentation method employs the Synthetic Minority Over Sampling Technique (SMOTE) and Random Over Sampling (ROS) to address data imbalances and enhance the performance of classification models for underrepresented classes. This study employs an oversampling technique to enhance the efficacy of the XG Boost model. SMOTE exhibits better efficacy relative to competing methods; the application of appropriate oversampling techniques allows models to integrate patterns from both majority and often neglected minority data.