Application of Neuromorphic Olfactory Approach for High-Accuracy Classification of Malts.

Current developments in artificial olfactory systems, also known as electronic nose (e-nose) systems, have benefited from advanced machine learning techniques that have significantly improved the conditioning and processing of multivariate feature-rich sensor data. These advancements are complemented by the application of bioinspired algorithms and architectures based on findings from neurophysiological studies focusing on the biological olfactory pathway. The application of spiking neural networks (SNNs), and concepts from neuromorphic engineering in general, are one of the key factors that has led to the design and development of efficient bioinspired e-nose systems. However, only a limited number of studies have focused on deploying these models on a natively event-driven hardware platform that exploits the benefits of neuromorphic implementation, such as ultra-low-power consumption and real-time processing, for simplified integration in a portable e-nose system. In this paper, we extend our previously reported neuromorphic encoding and classification approach to a real-world dataset that consists of sensor responses from a commercial e-nose system when exposed to eight different types of malts. We show that the proposed SNN-based classifier was able to deliver 97% accurate classification results at a maximum latency of 0.4 ms per inference with a power consumption of less than 1 mW when deployed on neuromorphic hardware. One of the key advantages of the proposed neuromorphic architecture is that the entire functionality, including pre-processing, event encoding, and classification, can be mapped on the neuromorphic system-on-a-chip (NSoC) to develop power-efficient and highly-accurate real-time e-nose systems.

Application of a Brain-Inspired Spiking Neural Network Architecture to Odor Data Classification.

Existing methods in neuromorphic olfaction mainly focus on implementing the data transformation based on the neurobiological architecture of the olfactory pathway. While the transformation is pivotal for the sparse spike-based representation of odor data, classification techniques based on the bio-computations of the higher brain areas, which process the spiking data for identification of odor, remain largely unexplored. This paper argues that brain-inspired spiking neural networks constitute a promising approach for the next generation of machine intelligence for odor data processing. Inspired by principles of brain information processing, here we propose the first spiking neural network method and associated deep machine learning system for classification of odor data. The paper demonstrates that the proposed approach has several advantages when compared to the current state-of-the-art methods. Based on results obtained using a benchmark dataset, the model achieved a high classification accuracy for a large number of odors and has the capacity for incremental learning on new data. The paper explores different spike encoding algorithms and finds that the most suitable for the task is the step-wise encoding function. Further directions in the brain-inspired study of odor machine classification include investigation of more biologically plausible algorithms for mapping, learning, and interpretation of odor data along with the realization of these algorithms on some highly parallel and low power consuming neuromorphic hardware devices for real-world applications.

A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data.

In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking neural network (SNN)-based classifier, implemented in a chip-emulation-based development environment, that can be seamlessly deployed on a neuromorphic system-on-a-chip (NSoC). Under three different scenarios of increasing complexity, the SNN was determined to be able to classify real-valued sensor data with greater than 90% accuracy and with a maximum latency of 3 s on the software-based platform. Highlights of this work included the design and implementation of a novel encoder for artificial olfactory systems, implementation of unsupervised spike-timing-dependent plasticity (STDP) for learning, and a foundational study on early classification capability using the SNN-based classifier.

Real-Time Classification of Multivariate Olfaction Data Using Spiking Neural Networks.

Recent studies in bioinspired artificial olfaction, especially those detailing the application of spike-based neuromorphic methods, have led to promising developments towards overcoming the limitations of traditional approaches, such as complexity in handling multivariate data, computational and power requirements, poor accuracy, and substantial delay for processing and classification of odors. Rank-order-based olfactory systems provide an interesting approach for detection of target gases by encoding multi-variate data generated by artificial olfactory systems into temporal signatures. However, the utilization of traditional pattern-matching methods and unpredictable shuffling of spikes in the rank-order impedes the performance of the system. In this paper, we present an SNN-based solution for the classification of rank-order spiking patterns to provide continuous recognition results in real-time. The SNN classifier is deployed on a neuromorphic hardware system that enables massively parallel and low-power processing on incoming rank-order patterns. Offline learning is used to store the reference rank-order patterns, and an inbuilt nearest neighbor classification logic is applied by the neurons to provide recognition results. The proposed system was evaluated using two different datasets including rank-order spiking data from previously established olfactory systems. The continuous classification that was achieved required a maximum of 12.82% of the total pattern frame to provide 96.5% accuracy in identifying corresponding target gases. Recognition results were obtained at a nominal processing latency of 16ms for each incoming spike. In addition to the clear advantages in terms of real-time operation and robustness to inconsistent rank-orders, the SNN classifier can also detect anomalies in rank-order patterns arising due to drift in sensing arrays.

Noninvasive Diagnosis of Irritable Bowel Syndrome via Bowel Sound Features: Proof of Concept.

INTRODUCTION: Irritable bowel syndrome (IBS) is a common and debilitating disorder estimated to affect approximately 11% of the world's population. Typically, IBS is a diagnosis of exclusion after patients undergo a costly and invasive colonoscopy to exclude organic disease. Clinician's and researchers have identified a need for a new cost-effective, accurate, and noninvasive diagnostic test for IBS. METHODS: Using a diagnostic case-control study, we explored the use of bowel sounds to characterize IBS with a view to diagnostic use. We recruited participants with an existing clinical diagnosis of IBS or healthy (asymptomatic) digestive systems. We recorded bowel sounds for 2 hours after fasting and then for 40 minutes after a standard meal. RESULTS: We here report our results including our accuracy in characterizing IBS-related bowel sounds and differentiation between participants with IBS and healthy participants. Leave-one-out cross-validation of our model developed using the first 31 IBS and 37 healthy participants gave 90% sensitivity and 92% specificity for IBS diagnosis. Independent testing using the next 15 IBS and 15 healthy participants demonstrated 87% sensitivity and 87% specificity for IBS diagnosis. CONCLUSIONS: These preliminary results provide proof of concept for the use of bowel sound analysis to identify IBS. A prospective study is needed to confirm these findings. TRANSLATIONAL IMPACT: Our belt and model offer hope of a new approach for IBS diagnosis in primary practice. Combined with screening tests for organic disease, it would offer greater confidence to patients and could reduce the burden of unnecessary colonoscopies for health care systems and patients.

Advances in Acoustic Signal Processing Techniques for Enhanced Bowel Sound Analysis.

With the invention of the electronic stethoscope and other similar recording and data logging devices, acoustic signal processing concepts and methods can now be applied to bowel sounds. In this paper, the literature pertaining to acoustic signal processing for bowel sound analysis is reviewed and discussed. The paper outlines some of the fundamental approaches and machine learning principles that may be used in bowel sound analysis. The advances in signal processing techniques that have allowed useful information to be obtained from bowel sounds from a historical perspective are provided. The document specifically address the progress in bowel sound analysis, such as improved noise reduction, segmentation, signal enhancement, feature extraction, localization of sounds, and machine learning techniques. We have found that advanced acoustic signal processing incorporating novel machine learning methods and artificial intelligence can lead to better interpretation of acoustic information emanating from the bowel.

Bowel Sounds Identification and Migrating Motor Complex Detection with Low-Cost Piezoelectric Acoustic Sensing Device.

Interpretation of bowel sounds (BS) provides a convenient and non-invasive technique to aid in the diagnosis of gastrointestinal (GI) conditions. However, the approach's potential is limited by variation between BS and their irregular occurrence. A short, manual auscultation is sufficient to aid in diagnosis of only a few conditions. A longer recording has the potential to unlock additional understanding of GI physiology and clinical utility. In this paper, a low-cost and straightforward piezoelectric acoustic sensing device was designed and used for long BS recordings. The migrating motor complex (MMC) cycle was detected using this device and the sound index as the biomarker for MMC phases. This cycle of recurring motility is typically measured using expensive and invasive equipment. We also used our recordings to develop an improved categorization system for BS. Five different types of BS were extracted: the single burst, multiple bursts, continuous random sound, harmonic sound, and their combination. Their acoustic characteristics and distribution are described. The quantities of different BS during two-hour recordings varied considerably from person to person, while the proportions of different types were consistent. The sensing devices provide a useful tool for MMC detection and study of GI physiology and function.

A mathematical model of bowel sound generation.

Humans have been interested in bowel sounds and wondered about their origins for millennia. To better understand the phenomenon, a mathematical model of bowel sound generation was developed based on a spring-mass-damping system. This is similar to vocal folds models for speech. The bowel sound model has four parameters that link to bowel activities: the individual wave component, pressure index, component quantity, and component interval time. All types of bowel sound documented previously can be modelled by combining different values for these parameters. Further, a 2500 ms bowel sound incorporating all the common types was simulated to present the model's accuracy.

An Investigation into Spike-Based Neuromorphic Approaches for Artificial Olfactory Systems.

The implementation of neuromorphic methods has delivered promising results for vision and auditory sensors. These methods focus on mimicking the neuro-biological architecture to generate and process spike-based information with minimal power consumption. With increasing interest in developing low-power and robust chemical sensors, the application of neuromorphic engineering concepts for electronic noses has provided an impetus for research focusing on improving these instruments. While conventional e-noses apply computationally expensive and power-consuming data-processing strategies, neuromorphic olfactory sensors implement the biological olfaction principles found in humans and insects to simplify the handling of multivariate sensory data by generating and processing spike-based information. Over the last decade, research on neuromorphic olfaction has established the capability of these sensors to tackle problems that plague the current e-nose implementations such as drift, response time, portability, power consumption and size. This article brings together the key contributions in neuromorphic olfaction and identifies future research directions to develop near-real-time olfactory sensors that can be implemented for a range of applications such as biosecurity and environmental monitoring. Furthermore, we aim to expose the computational parallels between neuromorphic olfaction and gustation for future research focusing on the correlation of these senses.

A Review of Current Neuromorphic Approaches for Vision, Auditory, and Olfactory Sensors.

Conventional vision, auditory, and olfactory sensors generate large volumes of redundant data and as a result tend to consume excessive power. To address these shortcomings, neuromorphic sensors have been developed. These sensors mimic the neuro-biological architecture of sensory organs using aVLSI (analog Very Large Scale Integration) and generate asynchronous spiking output that represents sensing information in ways that are similar to neural signals. This allows for much lower power consumption due to an ability to extract useful sensory information from sparse captured data. The foundation for research in neuromorphic sensors was laid more than two decades ago, but recent developments in understanding of biological sensing and advanced electronics, have stimulated research on sophisticated neuromorphic sensors that provide numerous advantages over conventional sensors. In this paper, we review the current state-of-the-art in neuromorphic implementation of vision, auditory, and olfactory sensors and identify key contributions across these fields. Bringing together these key contributions we suggest a future research direction for further development of the neuromorphic sensing field.