Deep CNN Sparse Coding for Real Time Inhaler Sounds Classification.

Effective management of chronic constrictive pulmonary conditions lies in proper and timely administration of medication. As a series of studies indicates, medication adherence can effectively be monitored by successfully identifying actions performed by patients during inhaler usage. This study focuses on the recognition of inhaler audio events during usage of pressurized metered dose inhalers (pMDI). Aiming at real-time performance, we investigate deep sparse coding techniques including convolutional filter pruning, scalar pruning and vector quantization, for different convolutional neural network (CNN) architectures. The recognition performance has been assessed on three healthy subjects following both within and across subjects modeling strategies. The selected CNN architecture classified drug actuation, inhalation and exhalation events, with 100%, 92.6% and 97.9% accuracy, respectively, when assessed in a leave-one-subject-out cross-validation setting. Moreover, sparse coding of the same architecture with an increasing compression rate from 1 to 7 resulted in only a small decrease in classification accuracy (from 95.7% to 94.5%), obtained by random (subject-agnostic) cross-validation. A more thorough assessment on a larger dataset, including recordings of subjects with multiple respiratory disease manifestations, is still required in order to better evaluate the method's generalization ability and robustness.

Spectral Processing for Denoising and Compression of 3D Meshes Using Dynamic Orthogonal Iterations.

Recently, spectral methods have been extensively used in the processing of 3D meshes. They usually take advantage of some unique properties that the eigenvalues and the eigenvectors of the decomposed Laplacian matrix have. However, despite their superior behavior and performance, they suffer from computational complexity, especially while the number of vertices of the model increases. In this work, we suggest the use of a fast and efficient spectral processing approach applied to dense static and dynamic 3D meshes, which can be ideally suited for real-time denoising and compression applications. To increase the computational efficiency of the method, we exploit potential spectral coherence between adjacent parts of a mesh and then we apply an orthogonal iteration approach for the tracking of the graph Laplacian eigenspaces. Additionally, we present a dynamic version that automatically identifies the optimal subspace size that satisfies a given reconstruction quality threshold. In this way, we overcome the problem of the perceptual distortions, due to the fixed number of subspace sizes that is used for all the separated parts individually. Extensive simulations carried out using different 3D models in different use cases (i.e., compression and denoising), showed that the proposed approach is very fast, especially in comparison with the SVD based spectral processing approaches, while at the same time the quality of the reconstructed models is of similar or even better reconstruction quality. The experimental analysis also showed that the proposed approach could also be used by other denoising methods as a preprocessing step, in order to optimize the reconstruction quality of their results and decrease their computational complexity since they need fewer iterations to converge.

Feature Preserving Mesh Denoising Based on Graph Spectral Processing.

The increasing interest for reliable generation of large scale scenes and objects has facilitated several real-time applications. Although the resolution of the new generation geometry scanners are constantly improving, the output models, are inevitably noisy, requiring sophisticated approaches that remove noise while preserving sharp features. Moreover, we no longer deal exclusively with individual shapes, but with entire scenes resulting in a sequence of 3D surfaces that are affected by noise with different characteristics due to variable environmental factors (e.g., lighting conditions, orientation of the scanning device). In this work, we introduce a novel coarse-to-fine graph spectral processing approach that exploits the fact that the sharp features reside in a low dimensional structure hidden in the noisy 3D dataset. In the coarse step, the mesh is processed in parts, using a model based Bayesian learning method that identifies the noise level in each part and the subspace where the features lie. In the feature-aware fine step, we iteratively smooth face normals and vertices, while preserving geometric features. Extensive evaluation studies carried out under a broad set of complex noise patterns verify the superiority of our approach as compared to the state-of-the-art schemes, in terms of reconstruction quality and computational complexity.

Energy Efficient Monitoring of Metered Dose Inhaler Usage.

Life-long chronic inflammatory diseases of the airways, such as asthma and Chronic Obstructive Pulmonary Disease, are very common worldwide, affecting people of all ages, race and gender. One of the most important aspects for the effective management of asthma is medication adherence which is defined as the extent to which patients follow their prescribed action plan and use their inhaler correctly. Wireless telemonitoring of the medication adherence can facilitate early diagnosis and management of these diseases through the use of an accurate and energy efficient mHealth system. Therefore, low complexity audio compression schemes need to be integrated with high accuracy classification approaches for the assessment of adherence of patients that use of pressurized Metered Dose Inhalers (pMDIs). To this end, we propose a novel solution that enables the energy efficient monitoring of metered dose inhaler usage, by exploiting the specific characteristics of the reconstructed audio features at the receiver. Simulation studies, carried out with a large dataset of indoor & outdoor measurements have led to high levels of accuracy (98 %) utilizing only 2 % of the recorded audio samples at the receiver, demonstrating the potential of this method for the development of novel energy efficient inhalers and medical devices in the area of respiratory medicine.

A survey on M2M systems for mHealth: a wireless communications perspective.

In the new era of connectivity, marked by the explosive number of wireless electronic devices and the need for smart and pervasive applications, Machine-to-Machine (M2M) communications are an emerging technology that enables the seamless device interconnection without the need of human interaction. The use of M2M technology can bring to life a wide range of mHealth applications, with considerable benefits for both patients and healthcare providers. Many technological challenges have to be met, however, to ensure the widespread adoption of mHealth solutions in the future. In this context, we aim to provide a comprehensive survey on M2M systems for mHealth applications from a wireless communication perspective. An end-to-end holistic approach is adopted, focusing on different communication aspects of the M2M architecture. Hence, we first provide a systematic review ofWireless Body Area Networks (WBANs), which constitute the enabling technology at the patient's side, and then discuss end-to-end solutions that involve the design and implementation of practical mHealth applications. We close the survey by identifying challenges and open research issues, thus paving the way for future research opportunities.