scholarly journals Efficient and Explainable Deep Neural Networks for Airway Symptom Detection in Support of Wearable Health Technology

2021 ◽  
Author(s):  
René Groh ◽  
Zhengdong Lei ◽  
Lisa Martignetti ◽  
Nicole YK Li-Jessen ◽  
Andreas M Kist
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Signal Acquisition ◽  
Acoustic Data ◽  
Wearable Systems ◽  
Unseen Data ◽  
Airway Symptoms ◽  
Speech Information ◽  
Term Monitoring

Mobile health wearables are often embedded with small processors for signal acquisition and analysis. These embedded wearable systems are, however, limited with low available memory and computational power. Advances in machine learning, especially deep neural networks (DNNs), have been adopted for efficient and intelligent applications to overcome constrained computational environments. In this study, evolutionary optimized DNNs were analyzed to classify three common airway-related symptoms, namely coughs, throat clears and dry swallows. As opposed to typical microphone-acoustic signals, mechano-acoustic data signals, which did not contain identifiable speech information for better privacy protection, were acquired from laboratory-generated and publicly available datasets. The optimized DNNs had a low footprint of less than 150 kB and predicted airway symptoms of interests with 83.7% accuracy on unseen data. By performing explainable AI techniques, namely occlusion experiments and class activation maps, mel-frequency bands up to 8,000 Hz were found as the most important feature for the classification. We further found that DNN decisions were consistently relying on these specific features, fostering trust and transparency of proposed DNNs. Our proposed efficient and explainable DNN is expected to support edge computing on mechano-acoustic sensing wearables for remote, long-term monitoring of airway symptoms.

scholarly journals Detection of activity and position of speakers by using deep neural networks and acoustic data augmentation

2019 ◽  
Vol 134 ◽  
pp. 53-65 ◽  
Author(s):  
Paolo Vecchiotti ◽  
Giovanni Pepe ◽  
Emanuele Principi ◽  
Stefano Squartini
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Acoustic Data

scholarly journals Systematic identification of external influences in multi-year microseismic recordings using convolutional neural networks

2019 ◽  
Vol 7 (1) ◽  
pp. 171-190 ◽  
Author(s):  
Matthias Meyer ◽  
Samuel Weber ◽  
Jan Beutel ◽  
Lothar Thiele
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Error Rate ◽  
Process Analysis ◽  
External Influences ◽  
Microseismic Data ◽  
Long Term Monitoring ◽  
Systematic Identification ◽  
Term Monitoring

Abstract. Passive monitoring of ground motion can be used for geophysical process analysis and natural hazard assessment. Detecting events in microseismic signals can provide responsive insights into active geophysical processes. However, in the raw signals, microseismic events are superimposed by external influences, for example, anthropogenic or natural noise sources that distort analysis results. In order to be able to perform event-based geophysical analysis with such microseismic data records, it is imperative that negative influence factors can be systematically and efficiently identified, quantified and taken into account. Current identification methods (manual and automatic) are subject to variable quality, inconsistencies or human errors. Moreover, manual methods suffer from their inability to scale to increasing data volumes, an important property when dealing with very large data volumes as in the case of long-term monitoring. In this work, we present a systematic strategy to identify a multitude of external influence sources, characterize and quantify their impact and develop methods for automated identification in microseismic signals. We apply the strategy developed to a real-world, multi-sensor, multi-year microseismic monitoring experiment performed at the Matterhorn Hörnligrat (Switzerland). We develop and present an approach based on convolutional neural networks for microseismic data to detect external influences originating in mountaineers, a major unwanted influence, with an error rate of less than 1 %, 3 times lower than comparable algorithms. Moreover, we present an ensemble classifier for the same task, obtaining an error rate of 0.79 % and an F1 score of 0.9383 by jointly using time-lapse image and microseismic data on an annotated subset of the monitoring data. Applying these classifiers to the whole experimental dataset reveals that approximately one-fourth of events detected by an event detector without such a preprocessing step are not due to seismic activity but due to anthropogenic influences and that time periods with mountaineer activity have a 9 times higher event rate. Due to these findings, we argue that a systematic identification of external influences using a semi-automated approach and machine learning techniques as presented in this paper is a prerequisite for the qualitative and quantitative analysis of long-term monitoring experiments.

scholarly journals Forms of explanation and understanding for neuroscience and artificial intelligence

2021 ◽  
Author(s):  
Jessica A. F. Thompson
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Scientific Explanation ◽  
Scientific Progress ◽  
Neural Systems ◽  
Relational Reasoning ◽  
Integrated Science ◽  
Philosophical Questions

Much of the controversy evoked by the use of deep neural networks as models of biological neural systems amount to debates over what constitutes scientific progress in neuroscience. In order to discuss what constitutes scientific progress, one must have a goal in mind (progress towards what?). One such long term goal is to produce scientific explanations of intelligent capacities (e.g., object recognition, relational reasoning). I argue that the most pressing philosophical questions at the intersection of neuroscience and artificial intelligence are ultimately concerned with defining the phenomena to be explained and with what constitute valid explanations of such phenomena. I propose that a foundation in the philosophy of scientific explanation and understanding can scaffold future discussions about how an integrated science of intelligence might progress. Towards this vision, I review relevant theories of scientific explanation and discuss strategies for unifying the scientific goals of neuroscience and AI.

scholarly journals Forms of explanation and understanding for neuroscience and artificial intelligence

2021 ◽  
Author(s):  
Jessica Anne Farrell Thompson
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Scientific Explanation ◽  
Scientific Progress ◽  
Neural Systems ◽  
Relational Reasoning ◽  
Integrated Science ◽  
Philosophical Questions

Much of the controversy evoked by the use of deep neural networks (DNNs) as models of biological neural systems amount to debates over what constitutes scientific progress in neuroscience. In order to discuss what constitutes scientific progress, one must have a goal in mind (progress towards what?). One such long term goal is to produce scientific explanations of intelligent capacities (e.g. object recognition, relational reasoning). I argue that the most pressing philosophical questions at the intersection of neuroscience and artificial intelligence are ultimately concerned with defining the phenomena to be explained and with what constitute valid explanations of such phenomena. As such, I propose that a foundation in the philosophy of scientific explanation and understanding can scaffold future discussions about how an integrated science of intelligence might progress. Towards this vision, I review several of the most relevant theories of scientific explanation and begin to outline candidate forms of explanation for neural and cognitive phenomena.

scholarly journals Artificial intelligence in cardiology

2020 ◽  
pp. 8-11
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Automated Image Analysis ◽  
Specific Domain ◽  
Feature Discovery ◽  
Medical Disciplines ◽  
Second Wave

In the first wave of artificial intelligence (AI), rule-based expert systems were developed, with modest success, to help generalists who lacked expertise in a specific domain. The second wave of AI, originally called artificial neural networks but now described as machine learning, began to have an impact with multilayer networks in the 1980s. Deep learning, which enables automated feature discovery, has enjoyed spectacular success in several medical disciplines, including cardiology, from automated image analysis to the identification of the electrocardiographic signature of atrial fibrillation during sinus rhythm. Machine learning is now embedded within the NHS Long-Term Plan in England, but its widespread adoption may be limited by the “black-box” nature of deep neural networks.

scholarly journals CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks

2020 ◽  
Author(s):  
Gasper Begus
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Training Data ◽  
Human Speech ◽  
Acoustic Data ◽  
Unique Information ◽  
Latent Space ◽  
Lexical Learning ◽  
Lexical Items

How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling unsupervised lexical learning from raw acoustic inputs, ciwGAN (Categorical InfoWaveGAN) and fiwGAN (Featural InfoWaveGAN), that combine a Deep Convolutional GAN architecture for audio data (WaveGAN; Donahue et al. 2019) with an information theoretic extension of GAN – InfoGAN (Chen et al., 2016), and propose a new latent space structure that can model featural learning simultaneously with a higher level classification. In addition to the Generator and the Discriminator networks, the architectures introduce a network that learns to retrieve latent codes from generated audio outputs. Lexical learning is thus modeled as emergent from an architecture that forces a deep neural network to output data such that unique information is retrievable from its acoustic outputs. The networks trained on lexical items from TIMIT learn to encode unique information corresponding to lexical items in the form of categorical variables in their latent space. By manipulating these variables, the network outputs specific lexical items. The network occasionally outputs innovative lexical items that violate training data, but are linguistically interpretable and highly informative for cognitive modeling and neural network interpretability. Innovative outputs suggest that phonetic and phonological representations learned by the network can be productively recombined and directly paralleled to productivity in human speech: a fiwGAN network trained on suit and dark outputs innovative start, even though it never saw start or even a [st] sequence in the training data. We also argue that setting latent featural codes to values well beyond training range results in almost categorical generation of prototypical lexical items and reveals underlying values of each latent code. Probing deep neural networks trained on well understood dependencies in speech bear implications for latent space interpretability, understanding how deep neural networks learn meaningful representations, as well as a potential for unsupervised text-to-speech generation in the GAN framework.

Sign in / Sign up

Export Citation Format

Share Document