We describe the development of an algorithm for the automatic classification of heart sound phonocardiogram waveforms as normal, abnormal or uncertain. Our approach consists of three major components: 1) Heart sound segmentation, 2) Transformation of one-dimensional waveforms into two-dimensional timefrequency heat map representations using Mel-frequency cepstral coefficients and 3) Classification of MFCC heat maps using deep convolutional neural networks. We applied the above approach to produce submissions for the 2016 PhysioNet Computing in Cardiology Challenge. We present results from the challenge, as well as describe in detail the resulting neural network architecture produced and design decisions made. IntroductionThe goal of the 2016 PhysioNet Computing in Cardiology Challenge was to accurately classify normal and abnormal heart sounds from phonocardiogram (PCG) waveforms. A particular aim was to identify from a single short recording whether a subject should be referred on for expert diagnosis. Accurate and robust algorithms were required that could deal with heart sounds that exhibit very poor signal quality.The challenge training set consisted of 3,240 heart sound recordings, lasting from 5 seconds to just over 120 seconds. Recordings were collected from nine different locations on the body (including aortic area, pulmonic area, tricuspid area and mitral area, among others). Recordings from healthy subjects were labeled as normal. Recordings from subjects with a confirmed cardiac diagnosis were labeled as abnormal. Abnormal recordings were collected from patients who suffered from a variety of illnesses, including heart valve defects (mitral valve prolapse, mitral regurgitation, aortic stenosis, valvular surgery) and coronary artery disease. An in depth description of the challenge and the dataset is provided in [1], as well as a thorough review of the field of cardiac auscultation.We present an algorithm that computes heat maps of the time-frequency distribution of signal energy and uses a deep convolutional neural network to automatically classify normal versus abnormal heart sound recordings. Logistic regression hidden semi-Markov model-based heart sound segmentation is first performed on the PCG waveform. Spectrograms (energy maps) consisting of 6 cepstral coefficients that capture Mel-frequencies varying over time are derived for overlapping sliding windows of threesecond duration, beginning at the first heart sound, S 1 . A deep convolutional neural network consisting of two alternating convolution and max pooling layers is trained to perform automatic feature extraction. A final multilayer perceptron, consisting of two fully connected layers, distinguishes between normal and abnormal spectrograms. Heart sound recordings of variable length are dealt with by computing an ensemble of logit scores for all overlapping three-second segments contained within a recording and maximizing the average scores computed for all classes. ApproachOur approach consists of three major components: 1. Segme...
Hybrid manufacturing (HM) technologies combine additive and subtractive manufacturing (AM/SM) capabilities, leveraging AM's strengths in fabricating complex geometries and SM's precision and quality to produce finished parts. We present a systematic approach to automated computer-aided process planning (CAPP) for HM that can identify nontrivial, qualitatively distinct, and cost-optimal combinations of AM/SM modalities. A multimodal HM process plan is represented by a finite Boolean expression of AM and SM manufacturing primitives, such that the expression evaluates to an 'as-manufactured' artifact. We show that primitives that respect spatial constraints such as accessibility and collision avoidance may be constructed by solving inverse configuration space problems on the 'as-designed' artifact and manufacturing instruments. The primitives generate a finite Boolean algebra (FBA) that enumerates the entire search space for planning. The FBA's canonical intersection terms (i.e., 'atoms') provide the complete domain decomposition to reframe manufacturability analysis and process planning into purely symbolic reasoning, once a subcollection of atoms is found to be interchangeable with the design target. The approach subsumes unimodal (all-AM or all-SM) process planning as special cases. We demonstrate the practical potency of our framework and its computational efficiency when applied to process planning of complex 3D parts with dramatically different AM and SM instruments.
M a n u fa c tu ra b ility F e e d b a c k and M o d e l C o rrectio n fo r A d d itiv e M a n u fa c tu rin g Additive manufacturing, or 3D printing, is the process o f building three-dimensional solid shapes by accumulating material laid out in sectional layers. Additive manufactur ing has been recognized fo r enabling production o f complex custom parts that are difficult to manufacture otherwise. However, the dependence on build orientation and physical limitations o f printing processes invariably lead to geometric deviations between manufactured and designed shapes that are usually evaluated after manufacture. In this paper, we formalize the measurement o f such deviations in terms o f a printability map that simulates the printing process and partitions each printed layer into disjoint regions with distinct local measures o f size. We show that manufacturing capabilities, such as printing resolution, and material specific design recommendations, such as minimal fe a ture sizes, may be coupled in the printability map to evaluate expected deviations before manufacture. Furthermore, we demonstrate how partitions with size measures below required resolutions may be modified using properties o f the medial axis transform and use the corrected printability map to construct a representation o f the manufactured model. We conclude by discussing several applications o f the printability map fo r additive manufacturing. RelatedWork. Existing software to analyze and prepare models for 3D printing are often intended to accompany a specific printer [1-3] and typically enable some combination of model cleanup, build direction optimization, and tool path generation. Model cleanup refers to geometric processing of the 3D model,
Functionally graded materials (FGM) have recently attracted a lot of research attention in the wake of the recent prominence of additive manufacturing (AM) technologies. The continuously varying spatial composition profile of two or more materials affords FGM to possess properties of multiple different materials simultaneously. Emerging AM technologies enable manufacturing complex shapes with customized multifunctional material properties in an additive fashion. In this paper, we focus on providing an overview of research at the intersection of AM techniques and FGM objects. We specifically discuss FGM modeling representation schemes and outline a classification system to classify existing FGM representation methods. We also highlight the key aspects such as the part orientation, slicing, and path planning processes that are essential for fabricating FGM object through the use of multimaterial AM techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.