Digital audio signal reconstruction of a lost or corrupt segment using deep learning algorithms has been explored intensively in recent years. Nevertheless, prior traditional methods with linear interpolation, phase coding and tone insertion techniques are still in vogue. However, we found no research work on reconstructing audio signals with the fusion of dithering, steganography, and machine learning regressors. Therefore, this paper proposes the combination of steganography, halftoning (dithering), and state-of-the-art shallow and deep learning methods. The results (including comparing the SPAIN, Autoregressive, deep learning-based, graph-based, and other methods) are evaluated with three different metrics. The observations from the results show that the proposed solution is effective and can enhance the reconstruction of audio signals performed by the side information (e.g., Latent representation) steganography provides. Moreover, this paper proposes a novel framework for reconstruction from heavily compressed embedded audio data using halftoning (i.e., dithering) and machine learning, which we termed the HCR (halftone-based compression and reconstruction). This work may trigger interest in optimising this approach and/or transferring it to different domains (i.e., image reconstruction). Compared to existing methods, we show improvement in the inpainting performance in terms of signal-to-noise ratio (SNR), the objective difference grade (ODG) and Hansen’s audio quality metric. In particular, our proposed framework outperformed the learning-based methods (D2WGAN and SG) and the traditional statistical algorithms (e.g., SPAIN, TDC, WCP).

Background

Chronic obstructive pulmonary disease (COPD) is a severe condition affecting millions worldwide, leading to numerous annual deaths. The absence of significant symptoms in its early stages promotes high underdiagnosis rates for the affected people. Besides pulmonary function failure, another harmful problem of COPD is the systematical effects, e.g., heart failure or voice distortion. However, the systematic effects of COPD might provide valuable information for early detection. In other words, symptoms caused by systematic effects could be helpful to detect the condition in its early stages.

Objective

The proposed study aims to explore whether the voice features extracted from the vowel “a” utterance carry any information that can be predictive of COPD by employing Machine Learning (ML) on a newly collected voice dataset.

Methods

Forty-eight participants were recruited from the pool of research clinic visitors at Blekinge Institute of Technology (BTH) in Sweden between January 2022 and May 2023. A dataset consisting of 1246 recordings from 48 participants was gathered. The collection of voice recordings containing the vowel “a” utterance commenced following an information and consent meeting with each participant using the VoiceDiagnostic application. The collected voice data was subjected to silence segment removal, feature extraction of baseline acoustic features, and Mel Frequency Cepstrum Coefficients (MFCC). Sociodemographic data was also collected from the participants. Three ML models were investigated for the binary classification of COPD and healthy controls: Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB). A nested k-fold cross-validation approach was employed. Additionally, the hyperparameters were optimized using grid-search on each ML model. For best performance assessment, accuracy, F1-score, precision, and recall metrics were computed. Afterward, we further examined the best classifier by utilizing the Area Under the Curve (AUC), Average Precision (AP), and SHapley Additive exPlanations (SHAP) feature-importance measures.

Results

The classifiers RF, SVM, and CB achieved a maximum accuracy of 77 %, 69 %, and 78 % on the test set and 93 %, 78 % and 97 % on the validation set, respectively. The CB classifier outperformed RF and SVM. After further investigation of the best-performing classifier, CB demonstrated the highest performance, producing an AUC of 82 % and AP of 76 %. In addition to age and gender, the mean values of baseline acoustic and MFCC features demonstrate high importance and deterministic characteristics for classification performance in both test and validation sets, though in varied order.

Conclusion

This study concludes that the utterance of vowel “a” recordings contain information that can be captured by the CatBoost classifier with high accuracy for the classification of COPD. Additionally, baseline acoustic and MFCC features, in conjunction with age and gender information, can be employed for classification purposes and benefit healthcare for decision support in COPD diagnosis.

This study developed a procedure for rapidly reconstructing a crack profile for calculating the parameters of fracture mechanics such as stress intensity factor with energy release rate (J) and displacement opening crack tip using data from the eddy current sensor. The inverse problem focused on adopting genetic algorithms to solve the direct problem iteratively. The use of the differential probe allows a rapid and precise resolution of the direct problem. The incident field produced by the two coils is determined using the 3D finite element results and the variation of impedance in each coil due to the crack. For the inverse problem, the crack’s surface is considered regular shape in terms of dimensions, and the sensor’s impedance expresses the objective function in terms of the width and length of the crack. The evaluation of the shape function and mesh matrix is made dependent on the iterative process, which makes the reversal procedure computationally lightweight when using genetic algorithms. © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2024.

Recently, there has been a substantial surge in interest surrounding diffusion models, which are considered a prominent class of generative models. This surge is primarily attributed to their potential applications in a variety of deep learning problems. The primary objective of this study is to assess the effectiveness of diffusion models as a data augmentation technique in the context of medical image analysis. Furthermore, it aims to conduct a comparative analysis of the performance exhibited by deep learning classifiers trained on two distinct datasets. One dataset is augmented using the diffusion model, while the other dataset undergoes traditional data augmentation techniques. Utilizing the IDRiD dataset for the purpose of diabetic retinopathy diagnosis, the results demonstrate the efficiency of the diffusion model as a data augmentation technique for medical images compared to traditional data augmentation techniques. The integration of diffusion model augmented data yields superior performance for both classifiers. Namely, the fine-tuned ResNet-50 reached an accuracy of 53.40%, and the proposed CNN-based approach reached an accuracy of 44.66%, surpassing the performance of classifiers trained using traditional data augmentation techniques. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Brain tumor segmentation, among various tasks in medical image analysis, has garnered significant attention in the research community. Despite continuous efforts by researchers, accurate brain tumor segmentation remains a key challenge. This challenge arises due to various factors, including location uncertainty, morphological uncertainty, low contrast imaging, annotation bias, and data imbalance. Magnetic resonance imaging (MRI) plays a vital role in providing detailed images of the brain, enabling the extraction of crucial information about the tumor’s shape, size, and location. In literature, deep learning algorithms have shown their efficiency in dealing with semantic segmentation, particularly the U-Net architecture. The latter has demonstrated impressive performance in Medical image segmentation. In this paper, a U-Net-based architecture for brain tumor segmentation is proposed. To further enhance the segmentation performance of our model, a novel ensemble learning method, EnsUNet, is introduced by integrating four pre-trained networks namely MobileNet, DeepLabV3+, ResNet, and DenseNet as the encoder within the U-Net architecture. The conducted experimental evaluation demonstrates promising results, achieving an Intersection over Union (IoU) score of 0.86, a Dice Coefficient (DC) of 0.92, and an accuracy of approximately 0.99. These findings underscore the effectiveness of our proposed EnsUNet for accurately segmenting brain tumors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

In this paper, we investigate the possibility of leveraging the predictive power of machine learning to generate animated lightning bolts in the image space efficiently. To this end, we selected state-of-the-art machine learning architectures based on Generative Adversarial Network (GAN) and trained them on the commonly available videos. We demonstrate that visually convincing animations are achievable even when employing a limited dataset. The visual realism of the generated sequences of lightning bolts is assessed by conducting a user study on the participants.

During the last decade, we have witnessed a rapiddevelopment of extended reality (XR) technologies such asaugmented reality (AR) and virtual reality (VR). Further, therehave been tremendous advancements in artificial intelligence(AI) and machine learning (ML). These two trends will havea significant impact on future digital societies. The vision ofan immersive, ubiquitous, and intelligent virtual space opensup new opportunities for creating an enhanced digital world inwhich the users are at the center of the development process,so-calledintelligent realities(IRs).The “Human-Centered Intelligent Realities” (HINTS) profileproject will develop concepts, principles, methods, algorithms,and tools for human-centered IRs, thus leading the wayfor future immersive, user-aware, and intelligent interactivedigital environments. The HINTS project is centered aroundan ecosystem combining XR and communication paradigms toform novel intelligent digital systems.HINTS will provide users with new ways to understand,collaborate with, and control digital systems. These novelways will be based on visual and data-driven platforms whichenable tangible, immersive cognitive interactions within realand virtual realities. Thus, exploiting digital systems in a moreefficient, effective, engaging, and resource-aware condition.Moreover, the systems will be equipped with cognitive featuresbased on AI and ML, which allow users to engage with digitalrealities and data in novel forms. This paper describes theHINTS profile project and its initial results. ©2023, Copyright held by the authors   

This article presents an interactive method for 3D cloud animation at the landscape scale by employing machine learning. To this end, we utilize deep convolutional generative adversarial network (DCGAN) on GPU for training on home-captured cloud videos and producing coherent animation frames. We limit the size of input images provided to DCGAN, thereby reducing the training time and yet producing detailed 3D animation frames. This is made possible through our preprocessing of the source videos, wherein several corrections are applied to the extracted frames to provide an adequate input training data set to DCGAN. A significant advantage of the presented cloud animation is that it does not require any underlying physics simulation. We present detailed results of our approach and verify its effectiveness using human perceptual evaluation. Our results indicate that the proposed method is capable of convincingly realistic 3D cloud animation, as perceived by the participants, without introducing too much computational overhead.

The use of digital documents is knowing a widespread in different daily administrative and economic transactions. Simultaneously, the forgery of many documents becomes a crime that costs billions to states and companies. Several researchers tried to develop techniques that automatically detect forged documents using machine learning and image processing. With the immense success of deep learning applications, we employ, in this work, a convolutional neural network architecture that uses a gathered dataset of forged and authentic administrative documents. The results obtained on our dataset of 493 documents reached 73.95% accuracy and 97.3% recall, surpassing the efficiency of the machine learning base methods. © 2022 IEEE.

Large amount of data are generated from in-situ monitoring of additive manufacturing (AM) processes which is later used in prediction modelling for defect classification to speed up quality inspection of products. A high volume of this process data is defect-free (majority class) and a lower volume of this data has defects (minority class) which result in the class-imbalance issue. Using imbalanced datasets, classifiers often provide sub-optimal classification results i.e. better performance on the majority class than the minority class. However, it is important for process engineers that models classify defects more accurately than the class with no defects since this is crucial for quality inspection. Hence, we address the class-imbalance issue in manufacturing process data to support in-situ quality control of additive manufactured components.  For this, we propose cluster-based adaptive data augmentation (CADA) for oversampling to address the class-imbalance problem. Quantitative experiments are conducted to evaluate the performance of the proposed method and to compare with other selected oversampling methods using AM datasets from an aerospace industry and a publicly available casting manufacturing dataset. The results show that CADA outperformed random oversampling and the SMOTE method and is similar to random data augmentation and cluster-based oversampling. Furthermore, the results of the statistical significance test show that there is a significant difference between the studied methods.  As such, the CADA method can be considered as an alternative method for oversampling to improve the performance of models on the minority class.