Wearable IMU-Based Human Activity Recognition Algorithm for Clinical Balance Assessment Using 1D-CNN and GRU Ensemble Model

In this study, a wearable inertial measurement unit system was introduced to assess patients via the Berg balance scale (BBS), a clinical test for balance assessment. For this purpose, an automatic scoring algorithm was developed. The principal aim of this study is to improve the performance of the machine-learning-based method by introducing a deep-learning algorithm. A one-dimensional (1D) convolutional neural network (CNN) and a gated recurrent unit (GRU) that shows good performance in multivariate time-series data were used as model components to find the optimal ensemble model. Various structures were tested, and a stacking ensemble model with a simple meta-learner after two 1D-CNN heads and one GRU head showed the best performance. Additionally, model performance was enhanced by improving the dataset via preprocessing. The data were down sampled, an appropriate sampling rate was found, and the training and evaluation times of the model were improved. Using an augmentation process, the data imbalance problem was solved, and model accuracy was improved. The maximum accuracy of 14 BBS tasks using the model was 98.4%, which is superior to the results of previous studies.

Ensemble of Hybrid Neural Networks to Compensate for Epistemic Uncertainties: A Case Study in System Prognosis

In this contribution, a case study considering an unexpected corrosion-fatigue crack propagation issue in an aircraft fleet is used to discuss how to compensate for incomplete knowledge in time dependent responses integration and extrapolation. For the considered application, degradation resulting from mechanical fatigue is well understood and accounted in the damage models. However, the unexpected corrosion effects are not accounted in damage integration, yielding a large discrepancy between predicted and observed crack lengths. To address this epistemic uncertainty in the fleet damage accumulation model, hybrid neural networks cells are formulated; where physics-informed layers address well-understood aspects of the degradation, and data-driven layers are trained to act as correction terms. The considered case study encompasses highly imbalanced data sets with uncertainties acting asynchronously. To improve overall accuracy, ensemble learning techniques are adapted to merge the resulting hybrid neural network cells predictions. Lastly, a heuristic based on optimal ensemble weights is presented to help in the decision-making task of defining safe operation of the fleet. Results show that our proposed approach was capable of compensating for the epistemic uncertainties, and that the proposed heuristic can be used to rank aircraft damage severity, allowing to prioritize aircraft for inspection and/or route reassignment.

Ensembles for Viticulture Climate Classifications of the Willamette Valley Wine Region

Future climate projections provide an opportunity to evaluate cultivar climate classification and preferred styles of wine production for a wine grape growing region. However, ensemble selection must account for downscaled archive model skills and interdependence rather than be arbitrary and subjective. Relatedly, methods for generalizing climate model choice remain uncertain, particularly for identifying optimal ensemble subsets. In this study we consider the complete archive of the thirty-two Coupled Model Intercomparison Project Phase 5 (CMIP5) daily Localized Constructed Analogs (LOCA) downscaled historic datasets and their observational data that were used for downscaling and bias corrections. We apply four model averaging methods to determine optimal ensembles for the computation of six common climate classification indices for the Willamette Valley (WV) American Viticultural Area (AVA). Among the four methods evaluated, elastic-net regularization consistently performed best with identifying optimal ensemble subsets. Variation exists among the optimal ensembles computed for each of the six bioclimatic indices. However, a subset of approximately seven to ten climate models were consistently excluded across all six indices’ ensembles. While specific to the archive and wine region, optimal ensemble sizes were noticeably larger than ensemble sizes commonly employed in published studies. Results are reported such that they can be used by researchers to independently perform analyses involving any one of the six bioclimatic indices throughout the WV AVA while using historic and future LOCA CMIP5 climate projections. The data and methods employed herein are applicable for other wine regions.

On the Classical Capacity of General Quantum Gaussian Measurement

In this paper, we consider the classical capacity problem for Gaussian measurement channels. We establish Gaussianity of the average state of the optimal ensemble in the general case and discuss the Hypothesis of Gaussian Maximizers concerning the structure of the ensemble. Then, we consider the case of one mode in detail, including the dual problem of accessible information of a Gaussian ensemble. Our findings are relevant to practical situations in quantum communications where the receiver is Gaussian (say, a general-dyne detection) and concatenation of the Gaussian channel and the receiver can be considered as one Gaussian measurement channel. Our efforts in this and preceding papers are then aimed at establishing full Gaussianity of the optimal ensemble (usually taken as an assumption) in such schemes.

A New Optimal Ensemble Algorithm Based on SVDD Sampling for Imbalanced Data Classification

Nowadays, imbalanced data classification is a hot topic in data mining and recently, several valuable researches have been conducted to overcome certain difficulties in the field. Moreover, those approaches, which are based on ensemble classifiers, have achieved reasonable results. Despite the success of these works, there are still many unsolved issues such as disregarding the importance of samples in balancing, determination of proper number of classifiers and optimizing weights of base classifiers in voting stage of ensemble methods. This paper intends to find an admissible solution for these challenges. The solution suggested in this paper applies the support vector data descriptor (SVDD) for sampling both minority and majority classes. After determining the optimal number of base classifiers, the selected samples are utilized to adjust base classifiers. Finally, genetic algorithm optimization is used in order to find the optimum weights of each base classifier in the voting stage. The proposed method is compared with some existing algorithms. The results of experiments confirm its effectiveness.

Facial erythema detects diabetic neuropathy using the fusion of machine learning, random matrix theory and self organized criticality

Rubeosis faciei diabeticorum, caused by microangiopathy and characterized by a chronic facial erythema, is associated with diabetic neuropathy. In clinical practice, facial erythema of patients with diabetes is evaluated based on subjective observations of visible redness, which often goes unnoticed leading to microangiopathic complications. To address this major shortcoming, we designed a contactless, non-invasive diagnostic point-of-care-device (POCD) consisting of a digital camera and a screen. Our solution relies on (1) recording videos of subject’s face (2) applying Eulerian video magnification to videos to reveal important subtle color changes in subject’s skin that fall outside human visual limits (3) obtaining spatio-temporal tensor expression profile of these variations (4) studying empirical spectral density (ESD) function of the largest eigenvalues of the tensors using random matrix theory (5) quantifying ESD functions by modeling the tails and decay rates using power law in systems exhibiting self-organized-criticality and (6) designing an optimal ensemble of learners to classify subjects into those with diabetic neuropathy and those of a control group. By analyzing a short video, we obtained a sensitivity of 100% in detecting subjects diagnosed with diabetic neuropathy. Our POCD paves the way towards the development of an inexpensive home-based solution for early detection of diabetic neuropathy and its associated complications.