Search

BACKGROUND: Parkinson's disease (PD) is a long-term neurodegenerative disease of the central nervous system. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affects most patients is voice impairment. OBJECTIVE: Voice samples are non-invasive data that can be collected remotely for diagnosis and disease progression monitoring. In this study, we analyzed voice recording data from a smartphone as a possible medical self-diagnosis tool by using only one-second voice recording. The data from one of the largest mobile PD studies, the mPower study, was used. METHODS: A total of 29,798 ten-second voice recordings on smartphone from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by participants saying /aa/ for ten seconds into an iPhone microphone. A dataset comprising 385,143 short one-second audio samples was generated from the original ten-second voice recordings. The samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples. RESULTS: Classification accuracies of the proposed method with LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively. CONCLUSIONS: We achieve a respectable classification performance using a generalized approach on a dataset with a large number of samples. The result emphasizes that an analysis based on one-second clip recorded on a smartphone could be a promising non-invasive and remotely available PD biomarker. [ABSTRACT FROM AUTHOR]

A study of electromagnetic resonances of an isotropic chiral sphere is presented. The characteristic equation of a chiral sphere, which is complex and transcendental, is obtained by forming solutions of the electromagnetic field for a chiral sphere in terms of the spherical vector wave functions. The characteristic equation is solved by using a computer. Resonant frequencies and Q factors of the first few modes for relative permittivities of two and ten are reported and discussed. These modes are hybrid modes. They are classed as either hybrid electric (HE) modes or hybrid magnetic (HM) modes. Chirality is observed to have a significant effect on the resonances of a sphere. Index Terms--Chiral media, chiral sphere, Q factor, resonance.

The method of moments technique for analyzing electromagnetic scattering from an arbitrarily shaped three-dimensional homogeneous chiral body is presented based on the combined field integral equations. The body is assumed to be illuminated by a plane wave. The surface equivalence principle is used to replace the body by equivalent electric and magnetic surface currents. These currents radiating in unbounded free space produce the correct scattered field outside. The negatives of these currents produce the correct total internal field, when radiating in an unbounded chiral medium. By enforcing the continuity of the tangential components of the total electric and magnetic fields on the surface of the body, a set of coupled integral equations is obtained for the equivalent surface currents. The surface of the body is modeled using triangular patches. The triangular rooftop vector expansion functions are used for both equivalent surface currents. The coefficients of these expansion functions are obtained using the method of moments. The mixed potential formulation for a chiral medium is developed and used to obtain explicit expressions for the electric and magnetic fields produced by surface currents. Numerical results for bistatic radar cross sections are presented for three chiral scatterers--a sphere, a finite circular cylinder, and a cube. Index Terms--Chiral media, electromagnetic scattering, integral equations, method of moments.

Most mango farms classify the maturity stage manually by trained workers using external indicators such as size, shape, and skin color, which can lead to human error or inconsistencies. We developed four common machine learning (ML) classifiers, the k-mean, naïve Bayes, support vector machine, and feed-forward artificial neural network (FANN), all of which were aimed at classifying the ripeness stage of mangoes at harvest. The ML classifiers were trained on biochemical data and then tested on physical and electrical data.The performance of the ML models was compared using fourfold cross validation. The FANN classifier performed the best, with a mean accuracy of 89.6% for unripe, ripe, and overripe classes, when compared to the other classifiers. [ABSTRACT FROM AUTHOR]

Various numerical techniques have been developed for modeling electromagnetic field propagation in various novel complex media. The validity of these techniques is usually verified by comparison to the exact solutions of canonical problems. Recently, research has focused on chiral media, a subclass of materials known as bianisotropic materials, and numerical techniques have been developed in order to calculate the interaction of electromagnetic fields with chiral objects. One canonical problem for these techniques is plane-wave scattering from a chiral sphere. This paper presents a software package that displays and saves the calculated data for the scattering from a chiral, dielectric, or a perfectly conducting sphere using a friendly graphical user interface (GUI). [ABSTRACT FROM AUTHOR]