Objective Acoustic analysis of voice has the potential to expedite detection and diagnosis of voice disorders. Applying an image‐based, neural‐network approach to analyzing the acoustic signal may be an effective means for detecting and differentially diagnosing voice disorders. The purpose of this study is to provide a proof‐of‐concept that embedded data within human phonation can be accurately and efficiently decoded with deep learning neural network analysis to differentiate between normal and disordered voices. Methods Acoustic recordings from 10 vocally‐healthy speakers, as well as 70 patients with one of seven voice disorders (n = 10 per diagnosis), were acquired from a clinical database. Acoustic signals were converted into spectrograms and used to train a convolutional neural network developed with the Keras library. The network architecture was trained separately for each of the seven diagnostic categories. Binary classification tasks (ie, to classify normal vs. disordered) were performed for each of the seven diagnostic categories. All models were validated using the 10‐fold cross‐validation technique. Results Binary classification averaged accuracies ranged from 58% to 90%. Models were most accurate in their classification of adductor spasmodic dysphonia, unilateral vocal fold paralysis, vocal fold polyp, polypoid corditis, and recurrent respiratory papillomatosis. Despite a small sample size, these findings are consistent with previously published data utilizing deep neural networks for classification of voice disorders. Conclusion Promising preliminary results support further study of deep neural networks for clinical detection and diagnosis of human voice disorders. Current models should be optimized with a larger sample size. Levels of Evidence Level III

Advancing front packing algorithms have proven to be very efficient in 2D for obtaining high density sets of particles, especially disks. However, the extension of these algorithms to 3D is not a trivial task. In the present paper, an advancing front algorithm for obtaining highly dense sphere packings is presented. It is simpler than other advancing front packing methods in 3D and can also be used with other types of particles. Comparison with respect to other packing methods have been carried out and a significant improvement in the volume fraction (VF) has been observed. Moreover, the quality of packings was evaluated with indicators other than VF. As additional advantage, the number of generated particles with the algorithm is linear with respect to time.

SUMMARYThe generation of a set of particles with high initial volume fraction is a major problem in the context of discrete element simulations. Advancing front algorithms provide an effective means to generate dense packings when spherical particles are assumed. The objective of this paper is to extend an advancing front algorithm to a wider class of particles with generic size and shape. In order to get a dense packing, each new particle is placed in contact with other two (or three in 3D) particles of the advancing front. The contact problem is solved analytically using wrapping intersection technique. The results presented herein will be useful in the application of these algorithms to a wide variety of practical problems. Examples of geometric models for applications to biomechanics and cutting tools are presented.

No abstract