Abstract:This paper proposes a novel memetic algorithm (MA) for the blind equalization of digital multiuser channels with Direct-Sequence / Code-Division Multiple-Access (DS/CDMA) sharing scheme. Equalization involves two different tasks, the estimation of: (1) channel response and (2) transmitted data. The corresponding channel model is first analyzed and then the MA is developed for this specific communication system. Convergence, population diversity and near-far resistance have been analyzed. Numerical experiments include comparative results with traditional multiuser detectors as well as with other nature-inspired approaches. Proposed receiver is proved to allow higher transmission rates over existing channels, while supporting stronger interferences as well as fading and time-variant effects. Required computation requisites are kept moderate in most cases. Proposed MA saves approximately 80% of computation time with respect to a standard genetic algorithm and about 15% with respect to a similar two-stage memetic algorithm, while keeping a statistically significant higher performance. Besides, complexity increases only by a factor of 5, when the number of active users doubles, instead of 32x found for the optimum maximum likelihood algorithm. The proposed method also exhibits high near-far resistance and achieves accurate channel response estimates, becoming an interesting and viable alternative to so far proposed methods.
Abstract:Cough is a protective reflex conveying information on the state of the respiratory system. Cough assessment has been limited so far to subjective measurement tools or uncomfortable (i.e., non-wearable) cough monitors. This limits the potential of real-time cough monitoring to improve respiratory care. Objective: This paper presents a machine hearing system for audio-based robust cough segmentation that can be easily deployed in mobile scenarios. Methods: Cough detection is performed in two steps. First, a short-term spectral feature set is separately computed in five predefined frequency bands: [0, 0.5), [0.5, 1), [1, 1.5), [1.5, 2), and [2, 5.5125] kHz. Feature selection and combination are then applied to make the short-term feature set robust enough in different noisy scenarios. Second, high-level data representation is achieved by computing the mean and standard deviation of short-term descriptors in 300 ms long-term frames. Finally, cough detection is carried out using a support vector machine trained with data from different noisy scenarios. The system is evaluated using a patient signal database which emulates three real-life scenarios in terms of noise content. Results: The system achieves 92.71% sensitivity, 88.58% specificity, and 90.69% Area Under Receiver Operating Characteristic (ROC) curve (AUC), outperforming state-of-the-art methods. Conclusion: Our research outcome paves the way to create a device for cough monitoring in real-life situations. Significance: Our proposal is aligned with a more comfortable and less disruptive patient monitoring, with benefits for patients (allows self-monitoring of cough symptoms), practitioners (e.g., assessment of treatments or better clinical understanding of cough patterns), and national health systems (by reducing hospitalizations).
Abstract:This work proposes a modified version of an emerging nature-inspired technique, named Flower Pollination Algorithm (FPA), for equalizing digital multiuser channels. This equalization involves two different tasks: 1) estimation of the channel impulse response, and 2) estimation of the users' transmitted symbols. The new algorithm is developed and applied in a Direct-Sequence / Code-Division Multiple-Access (DS/CDMA) multiuser communications system. Important issues such as robustness, convergence speed and population diversity control have been in deep investigated. A method based on the entropy of the flowers' fitness is proposed for in-service monitoring and adjusting population diversity. Numerical simulations analyze the performance, showing comparisons with well-known conventional multiuser detectors such as Matched Filter (MF), Minimum Mean Square Error Estimator (MMSEE) or several Bayesian schemes, as well as with other nature-inspired strategies. Numerical analysis shows that the proposed algorithm enables transmission at higher symbol rates under stronger fading and interference conditions, constituting an attractive alternative to previous algorithms, both conventional and nature-inspired, whose performance is frequently sensible to near-far effects and multiple-access interference problems. These results have been validated by running hypothesis tests to confirm statistical significance.
Abstract:First-pass perfusion cardiac magnetic resonance (FPP-CMR) is becoming an essential non-invasive imaging method for detecting deficits of myocardial blood flow, allowing the assessment of coronary heart disease. Nevertheless, acquisitions suffer from relatively low spatial resolution and limited heart coverage. Compressed sensing (CS) methods have been proposed to accelerate FPP-CMR and achieve higher spatial resolution. However, the long reconstruction times have limited the widespread clinical use of CS in FPP-CMR. Deep learning techniques based on supervised learning have emerged as alternatives for speeding up reconstructions. However, these approaches require fully sampled data for training, which is not possible to obtain, particularly high-resolution FPP-CMR images. Here, we propose a physics-informed self-supervised deep learning FPP-CMR reconstruction approach for accelerating FPP-CMR scans and hence facilitate high spatial resolution imaging. The proposed method provides high-quality FPP-CMR images from 10x undersampled data without using fully sampled reference data.