Advanced Noise Reduction Algorithms Research Articles

AE-BEGAN based Synthetic Data Augmentation for Sample-Limited High-Dimensional Problems with Application to NIR Spectral Data

Synthetic data augmentation holds substantial research and application value in scenarios characterized by limited samples and high dimensions. It enhances the analytical ability and efficiency of spectral analysis models. This paper proposes Autoencoder-Combined Boundary Equilibrium Generative Adversarial Networks (AE-BEGAN) as a new method for augmenting synthetic data in scenarios with limited samples and high dimensions, with a specific emphasis on near-infrared (NIR) spectral data. The spectral data first undergoes preprocessing procedures that encompass advanced noise reduction algorithms and techniques for removing abnormal samples, guaranteeing elimination of unwanted disturbances and outliers. Then, the pre-processed data is utilized to train the AE-BEGAN model, which generates augmented synthetic samples. Finally, real NIR spectral data obtained from lubricant samples exhibiting different water contents were employed to validate and test the performance of the model. The experimental results demonstrate that the AE-BEGAN model outperforms other GANs in generating synthetic data of high quality and diversity, as quantified by two evaluation metrics, α-Precision and β-Recall with scores of approximately 0.86 and 0.28, respectively. The application case study confirms that the AE-BEGAN model exhibits the capability to generate derived NIR spectra and expand the number of spectra in scenarios with limited samples and high dimensions.

Wearable Sensors and Machine Learning for Hypovolemia Problems in Occupational, Military and Sports Medicine: Physiological Basis, Hardware and Algorithms.

Hypovolemia is a physiological state of reduced blood volume that can exist as either (1) absolute hypovolemia because of a lower circulating blood (plasma) volume for a given vascular space (dehydration, hemorrhage) or (2) relative hypovolemia resulting from an expanded vascular space (vasodilation) for a given circulating blood volume (e.g., heat stress, hypoxia, sepsis). This paper examines the physiology of hypovolemia and its association with health and performance problems common to occupational, military and sports medicine. We discuss the maturation of individual-specific compensatory reserve or decompensation measures for future wearable sensor systems to effectively manage these hypovolemia problems. The paper then presents areas of future work to allow such technologies to translate from lab settings to use as decision aids for managing hypovolemia. We envision a future that incorporates elements of the compensatory reserve measure with advances in sensing technology and multiple modalities of cardiovascular sensing, additional contextual measures, and advanced noise reduction algorithms into a fully wearable system, creating a robust and physiologically sound approach to manage physical work, fatigue, safety and health issues associated with hypovolemia for workers, warfighters and athletes in austere conditions.

Application of an advanced noise reduction algorithm for imaging of hands in rheumatic diseases: evaluation of image quality compared to standard-dose images.

X-ray is the fundamental imaging technique in both diagnosis and follow-up of rheumatic diseases. As patients often require sequential X-rays over many years, dose reduction is of great importance. New advanced noise reduction algorithms allow for a dose reduction of up to 50%. The aim of this study was to evaluate whether quality of low-dose images is non-inferior to standard-dose images and, therefore, application of this technique is possible in the context of imaging of rheumatic diseases. A total of 298 patients with known or suspected rheumatic disease were enrolled prospectively into this study, separated into three consecutive groups: 80%, 64% and 50% tube charge reduction. All patients received imaging of one hand (laterality randomly assigned) with low-dose technique and imaging of the contralateral hand with standard-dose protocol. Images were evaluated by two independent readers who scored (on a scale of 1-5) the visualization of bony cortex, trabeculae and joint spaces of fingers and wrist separately. Additionally, soft tissue and overall contrast were evaluated on the same scale. Overall image quality (expressed by mean sum score out of 40) of the 50% low-dose images was 31.52 (SD 1.94) vs. 31.66 (SD 1.82) for standard images (p = 0.068). Bony contours as well as trabeculae were equally well visualized in both image sets. Median scores for soft tissue visualization was slightly lower for low dose compared to standard images [4 (IQR 3.5-4) vs. 4 (IQR 3.88-4); p = 0.001]. Overall image quality of low-dose images was not inferior to standard-dose images. Therefore, the application of low-dose technology based on advanced noise estimation algorithms in the context of imaging of rheumatic diseases is possible.

Asymmetric Coding for Rate-Constrained Noise Reduction in Binaural Hearing Aids

Binaural hearing aids (HAs) can potentially perform advanced noise reduction algorithms, leading to an improvement over monaural/bilateral HAs. Due to the limited transmission capacities between the HAs and given knowledge of the complete joint noisy signal statistics, the optimal rate-constrained beamforming strategy is known from the literature. However, as these joint statistics are unknown in practice, sub-optimal strategies have been presented. In this paper, we present a unified framework to study the performance of these existing optimal and sub-optimal rate-constrained beamforming methods for binaural HAs. Moreover, we propose to use an asymmetric sequential coding scheme to estimate the joint statistics between the microphones in the two HAs. We show that under certain assumptions, this leads to sub-optimal performance in one HA but allows to obtain the truly optimal performance in the second HA. Based on the mean square error distortion measure, we evaluate the performance improvement between monaural beamforming (no communication) and the proposed scheme, as well as the optimal and the existing sub-optimal strategies in terms of the information bit-rate. The results show that the proposed method outperforms existing practical approaches in most scenarios, especially at middle rates and high rates, without having the prior knowledge of the joint statistics.

Innovative Technology in Hearing Instruments

Hearing instrument technology research is almost entirely focused on the projected needs of the consumer market in the developed world. However, two thirds of the world's population with hearing impairment live in developing countries and this proportion will increase in future, given present demographic trends. In developing regions, amplification and other hearing health needs may differ from those in industrialized nations, for cultural, health, or economic reasons. World Health Organization estimates indicate that at present only a small percentage of individuals in developing countries who are in need of amplification have access to hearing aid provision. New technologies, such as trainable hearing aids, advanced noise reduction algorithms, feedback reduction circuitry, nano coatings for hearing aid components, and innovative power options, may offer considerable potential benefits, both for individuals with hearing impairment in developing countries and for those who provide hearing health care services in these regions. This article considers the possible supporting role of innovative hearing instrument technologies in the provision of affordable hearing health care services in developing countries and highlights the need for research that considers the requirements of the majority of the world population in need of hearing instrument provision.