Odor Classification Research Articles

Test on Noxious Gases in Urban Sewage Pipe Based on Odor Classification

Urban sewage pipes are filled with flammable, explosive, toxic and other noxious gases, which have brought hidden troubles during system maintenance and operation. To ease these threats to the urban sewage pipeline network, we should perform spot inspection and take some measures against safety risks that may occur on them. But of those, the test of noxious gases is the most challenging. Based on the odor classification method, we take an urban sewage pipe network in Chongqing as a study case for sample collection and spot inspection. The purpose of this paper is to classify and test the methane CH4 and hydrogen sulfide H2S by different methods. Data available from individual supervision spots are compared and analyzed in parallel, in order to explore how to measure these noxious gases and what’s the distribution and concentration change laws of them in urban sewage pipes, hoping to provide the clues to the early warning and safety operation of urban sewage pipeline network.

A 1-V 2.6-mW Environmental Compensated Fully Integrated Nose-on-a-Chip

Miniature gas detection system is desirable for many applications. In this brief, we propose a fully integrated nose-on-a-chip for mobile phones and wearable devices. The chip has 36 on-chip sensors, a 36-channel adaptive interface with an integrated programmable amplifier, a four-channel frequency readout interface, one on-chip temperature sensor, a successive approximation analog-to-digital converter, a scalable learning kernel cluster, and a reduced instruction set computing core with low-voltage static random-access memory. This chip is fabricated using the TSMC 180-nm CMOS process and consumes 2.6 mW at 1 V. on-chip temperature and humidity sensors are included in this system for acquiring environmental information. An environmental compensation algorithm based on common principal components analysis is also implemented for high-accuracy odor classification. This fully integrated nose-on-a-chip provides promising results for odor detection and classification for use in mobile and wearable device applications.

Development of an Electronic Nose for Olfactory System Modelling using Artificial Neural Network

Electronic nose (e-nose) devices have received considerable attention in the field of sensor technology because of their many potential uses such as in identification of toxic wastes, monitoring air quality, examining odors in infected wounds and in inspection of food. Notwithstanding the vast amount of literature on the usage of e-noses for specific purposes, the technology originally and ultimately aims to mimic the capability of mammals to discriminate odors from all sorts of objects. This study demonstrates the theoretical and practical feasibility of designing an e-nose towards general odor classification. A multi-sensor array hardware unit was carefully constructed for data collection and odor detection. Important hardware design considerations such as sensor calibration, aeration, circuit protection, and voltage/current requirements were satisfied. A highly fine-tuned artificial neural network (ANN) was integrated to the hardware to interpret and relate the data to a target odor class from a set of 10 primary odors identified in a previous study. Various network architecture considerations, such as neuron count, number of layers and activation function, as well as various data treatment methods, such as normalization, and data partitioning, were investigated. The results showed that careful hardware integration with an ANN having sufficiently deep internal structure can yield accurate classification to at least half of the ten primary odor classes, namely fragrant (96%), fruity (98%), chemical (99%), peppermint (98%), and popcorn (90%). The results demonstrate the feasibility of making e-noses for general odor classification, which could lead to further broadening of e-nose applications.

Early-blind Individuals Show Impaired Performance in Wine Odor Categorization

Blind individuals display superior sensory abilities in other modalities, yet results remain contradictory regarding their performance on olfactory tasks. Using complex ecological olfactory tasks, we evaluated the impact of blindness on olfactory performance. We tested 12 early-blind individuals (M = 49, SD = 13.09) and 12 sighted controls (M = 49, SD = 14.31) who were all blindfolded. Based solely on the wine odors, participants evaluated 24 pairs of wine and determined if both samples belonged to the same category (red wine, white wine, or rosé wine) or not (odor categorization), and if so, whether they were identical or not (odor differentiation). Then, they had to classify 15 different wines (5 red, 5 white and 5 rosé) into red, white, and rosé wines (odor classification). Blind individuals (d′: M = 1.3, SD = 1.2) presented lower scores compared to sighted controls (M = 2.2 SD = 0.8; p < .05) in the odor categorization task, but no group difference was observed for the other tasks. For all participants, red wine odors were the easiest to classify (1.8 ± 1.0), followed by white wine odors (0.5 ± 0.6) and finally rosé wine odors (blind and sighted; F[2; 44] = 11.9, p < .001). In summary, early-blind individuals had a harder time to categorize wine odors. This could be explained by a different construction of internal reference categories for wine in early-blind individuals. Finally, this research is in line with the notion of the absence of higher olfactory sensitivity in blind individuals.

A novel role for scavenger receptor B1 as a contributor to the capture of specific volatile odorants in the nasal cavity.

Class B scavenger receptors, scavenger receptor B1 (SR-B1) and cluster of differentiation 36 (CD36), are broadly expressed cell-surface proteins and are believed to serve as multifaceted players in lipid and lipoprotein metabolism in mammals. Because of its ability to recognise distinct odour-active volatile compounds and its presence in murine olfactory epithelium, CD36 has recently emerged as a participant in the detection of odorants within the nasal cavity. However, there have been no attempts to assess whether SR-B1 has such a role. In this study, we performed a cell-free in-vitro assay utilising a peptide mimic of the receptor, and demonstrated that SR-B1 could recognise aliphatic aldehydes (e.g., tetradecanal), a distinct class of volatile odorants, as potential ligands. By reverse transcription-polymerase chain reaction and western immunoblot analyses, we detected the expression of SR-B1 mRNA and protein, respectively, in mouse olfactory tissue. Finally, we immunohistochemically mapped the distribution of SR-B1 in the surface layer of olfactory epithelium in vivo, which is the first line of odorant detection. These findings uncover a novel role for SR-B1 as a contributor to the capture of specific odorants in the nasal cavity of mammals.

Functional odor classification through a medicinal chemistry approach.

Crucial for any hypothesis about odor coding is the classification and prediction of sensory qualities in chemical compounds. The relationship between perceptual quality and molecular structure has occupied olfactory scientists throughout the 20th century, but details of the mechanism remain elusive. Odor molecules are typically organic compounds of low molecular weight that may be aliphatic or aromatic, may be saturated or unsaturated, and may have diverse functional polar groups. However, many molecules conforming to these characteristics are odorless. One approach recently used to solve this problem was to apply machine learning strategies to a large set of odors and human classifiers in an attempt to find common and unique chemical features that would predict a chemical's odor. We use an alternative method that relies more on the biological responses of olfactory sensory neurons and then applies the principles of medicinal chemistry, a technique widely used in drug discovery. We demonstrate the effectiveness of this strategy through a classification for esters, an important odorant for the creation of flavor in wine. Our findings indicate that computational approaches that do not account for biological responses will be plagued by both false positives and false negatives and fail to provide meaningful mechanistic data. However, the two approaches used in tandem could resolve many of the paradoxes in odor perception.

Electronic Nose-Based Odor Classification using Genetic Algorithms and Fuzzy Support Vector Machines

Electronic nose devices consisting of a matrix of sensors to sense the smell of various target gases have received considerable attention during the past two decades. This paper presents an efficient classification algorithm for a self-designed electronic nose, which integrates both genetic algorithms (GAs) and fuzzy support vector machines (FSVMs) to detect the target odor. GAs are applied to select the informative features and the optimal model parameters of FSVMs. FSVMs are adopted as fitness evaluation criterion and the sequent odor classifier, which can reduce the outlier effects and provide a robust and accurate classification. This proposed algorithm has been compared with some commonly used learning algorithms, such as support vector machine, the k-nearest neighbors and other combination algorithms. This study is based on experimental data collected from the response of the UTS NOS.E, which is the electronic nose system developed by the University of Technology Sydney NOS.E team. In comparison with other approaches, the experiment results show that the proposed odor classification algorithm can significantly improve the classification accuracy by selecting high-quality features and reach to 92.05% classification accuracy.

Metal Oxides Semiconductor Sensors for Odor Classification

&lt;span&gt;The performance of gas sensor will differ and vary due to the surrounding environment changing, the way of implementation, and the position of the sensors to the source. To reach a good result on gas sensors implementation, a performance test on sensors is needed. The results of the tests are useful for characterizing the properties of the particular material or device. This paper discusses the performances of metal oxides semiconductor (MOS) sensors. The sensors are tested to determine the sensors' time response, sensors' peak duration, sensors' sensitivity, and sensors' stability of the sensor when applied to the various sources at different range. Three sources were used in experimental test, namely: ethanol, methanol, and acetone. The gas sensors characteristics are analyzed in open sampling method in order to see the sensors' sensitivity to the uncertainty disturbances, such as wind. The result shows that metal oxides semiconductor sensor was responsive to the 3 sources not only in static but also dynamic conditions. The expected outcome of this study is to predict the MOS sensors' performance when they are applied in robotic implementation. This performance was considered as the training datasets of the sensor for odor classification in this research. From the experiments, It was got, in dynamic experiment, the senrors has average of precision of 93.8-97%, the accuracy 93.3-96.7%, and the recall 93.3-96.7%. This values indicates that the sensors were selective to the odor they sensed.&lt;/span&gt;

Classification of Mixed Odors Using A Layered Neural Network

Odor classification has been forcused due to one of five senses of human being. If we could establish the odor classification technology, we would expect various new technology since human being requires five sences to acheive higher quality information processing and sophistcated decision making. For example, we could expect the odor classification and odor synthesis, which enable us to achieve odor communication technology. Furthermore, the odor classification would be applicable to keep the society safe by detecting the dangerous odors and to make our life more satisfactory by using additional odor information. In this paper we develop an electronic nose using a neural network. The neural network is a multi-layered neural network based on the gradient method. After classifying the various odors, we consider the classification in case that mixed odors are measured. To improve the classification accuracy we adopt a genetic algorithm to find a reduction factor to separate two mixed odors.

Sensory Characterization of Odors in Used Disposable Absorbent Incontinence Products.

PURPOSE:The objectives of this study were to characterize the odors of used incontinence products by descriptive analysis and to define attributes to be used in the analysis. A further objective was to investigate to what extent the odor profiles of used incontinence products differed from each other and, if possible, to group these profiles into classes.SUBJECTS AND SETTING:Used incontinence products were collected from 14 residents with urinary incontinence living in geriatric nursing homes in the Gothenburg area, Sweden.METHODS:Pieces were cut from the wet area of used incontinence products. They were placed in glass bottles and kept frozen until odor analysis was completed. A trained panel consisting of 8 judges experienced in this area of investigation defined terminology for odor attributes. The intensities of these attributes in the used products were determined by descriptive odor analysis. Data were analyzed both by analysis of variance (ANOVA) followed by the Tukey post hoc test and by principal component analysis and cluster analysis.RESULTS:An odor wheel, with 10 descriptive attributes, was developed. The total odor intensity, and the intensities of the attributes, varied considerably between different, used incontinence products. The typical odors varied from “sweetish” to “urinal,” “ammonia,” and “smoked.” Cluster analysis showed that the used products, based on the quantitative odor data, could be divided into 5 odor classes with different profiles.CONCLUSIONS:The used products varied considerably in odor character and intensity. Findings suggest that odors in used absorptive products are caused by different types of compounds that may vary in concentration.

Body odor classification by selecting optimal peaks of chemical compounds in GC–MS spectra using filtering approaches

Present study deals with the operation of filter based approaches for selection of an optimal subset of peaks of chemical compounds in gas chromatography (GC)-mass spectrometry (MS) spectra with the objective to robust classification modeling of human body odor. Particularly, we have employed four filter based approaches including CFS, Linear-correlation, Rank-correlation, and Relief, in the selection of significant peaks and compared their performance. Selected subsets have been validated for qualitative and quantitative classification of human body odor samples in principal component (PC) space. Filter schemes were validated by analyzing sixteen decisive odor data sets obtained through characterization of body odor samples by GC–MS in four different experiments. Every feature filtering method results in an optimal subset of peaks for each data set. Efficiency of a particular subset of peaks has been evaluated by using them in PC analysis, and thereafter on the basis of visual discrimination as well inter-class separation (b) and intra-class (a) separation in PC space. Few methods result in a common subset of peaks for some data sets, though the maximum value of b and a minimum value of a has been obtained for discrimination amongst body odor samples by using selected subsets of peaks compare to all peaks in spectra. Best human body odor class discrimination outcomes have been achieved by using peaks of chemical compounds selected by Relief and CFS filters.

The hippocampus influences assimilation and accommodation of schemata that are not hippocampus-dependent.

Learning is facilitated when information can be incorporated into an already learned set of rules or 'mental schema'. The location of a new restaurant, for example, is learned more easily if the neighbourhood's general layout is already known. This type of information is processed by the hippocampus and stored as a schema in the cortex, but it is not known whether the hippocampus can also map new stimuli to cortical schemata that are hippocampus-independent, such as odour classification. Using a hippocampus-independent odour-rule task we found that animals without a functional hippocampus learnt which odours did not fit the rule faster than sham animals, which persistently applied the rule to all odours. Conversely, when non-fitting odours were linked to a new rule sham animals were faster to link these odours to the new rule. The hippocampus, thus, regulates the association of stimuli with existing schemata even when the schemata are hippocampus-independent. © 2016 Wiley Periodicals, Inc.

Variant Ionotropic Receptors in the Malaria Vector Mosquito Anopheles gambiae Tuned to Amines and Carboxylic Acids

The principal Afrotropical human malaria vector mosquito, Anopheles gambiae, remains a significant threat to global health. A critical component in the transmission of malaria is the ability of An. gambiae females to detect and respond to human-derived chemical kairomones in their search for blood meal hosts. The basis for host odor responses resides in olfactory receptor neurons (ORNs) that express chemoreceptors encoded by large gene families, including the odorant receptors (ORs) and the variant ionotropic receptors (IRs). While ORs have been the focus of extensive investigation, functional IR complexes and the chemical compounds that activate them have not been identified in An. gambiae. Here we report the transcriptional profiles and functional characterization of three An. gambiae IR (AgIr) complexes that specifically respond to amines or carboxylic acids - two classes of semiochemicals that have been implicated in mediating host-seeking by adult females but are not known to activate An. gambiae ORs (AgOrs). Our results suggest that AgIrs play critical roles in the detection and behavioral responses to important classes of host odors that are underrepresented in the AgOr chemical space.

Odor classification of neural networks

We consider odor classification using a neural network. By establishing the odor classification technology, we would expect various new technology since human being requires five senses to achieve higher quality information processing and sophisticated decision making. In this paper we develop an electronic nose using a neural network. The neural network is a multi-layered neural network based on the gradient method. After classifying the various odors, the classification is considered in case that mixed odors are measured. To improve the classification accuracy we adopt a genetic algorithm to find a reduction factor to separate two mixed odors.

Virtual organization with fusion knowledge in odor classification

E-nose systems are becoming increasingly important instruments across all industries, especially the fields of food and beverages and biomedicine. Given the inaccurate, unsafe and unreliable dependency on the human nose to detect smells that are highly risky and hazardous to human health, e-nose systems offer a tremendous advantage. E-noses are convenient, highly efficient and can be used in real life to detect various types of odors. This paper presents a virtual organization of agents that integrates different classification techniques and neural networks to perform information fusion from parameters retrieved by the E-nose. The integral brain in e-noses is the data processing system, which classifies odors that have been detected by the detection part of its system. The system mimics how a human brain classifies odors.

Electronic Nose Testing Procedure for the Definition of Minimum Performance Requirements for Environmental Odor Monitoring.

Despite initial enthusiasm towards electronic noses and their possible application in different fields, and quite a lot of promising results, several criticalities emerge from most published research studies, and, as a matter of fact, the diffusion of electronic noses in real-life applications is still very limited. In general, a first step towards large-scale-diffusion of an analysis method, is standardization. The aim of this paper is describing the experimental procedure adopted in order to evaluate electronic nose performances, with the final purpose of establishing minimum performance requirements, which is considered to be a first crucial step towards standardization of the specific case of electronic nose application for environmental odor monitoring at receptors. Based on the experimental results of the performance testing of a commercialized electronic nose type with respect to three criteria (i.e., response invariability to variable atmospheric conditions, instrumental detection limit, and odor classification accuracy), it was possible to hypothesize a logic that could be adopted for the definition of minimum performance requirements, according to the idea that these are technologically achievable.

Amperometric Gas Sensors: From Classical Industrial Health and Safety to Environmental Awareness and Public Health

KWJ Engineering and SPEC Sensors LLC have been working to develop and commercialize a new class of amperometric gas sensor, the screen-printed electrochemical sensor (SPEC) for the past several years. These new, tiny, ultralow power sensors and device built around them are making in-roads in a diverse set of endeavors. Much of this potential has been driven by the explosion of interest and activity in sensor technologies driven by our increasingly connected world (Internet of Things). Amperometric gas sensors were once found mainly in industrial hygiene applications, e.g., four gas monitors, confined space entry monitoring and leak detection. Conventional sensors are fairly large, although not requiring particularly high power (on the order of tens of milliwatts). However, they are not compatible with modern needs. The advent of tiny form factors with the SPEC sensor has opened up new possibilities in applications requiring portability, wearability (e.g., watches or other personal monitoring devices) and self-powered or long-term unattended battery operation by virtue of the very small size and ultralow power (microwatt) requirements.This paper will review several recent efforts in next-generation gas sensor development and applications at KWJ Engineering. Major scientific directions include portable and wearable environmental monitoring of inhalation hazards for personal and public health protection and detection and classification of odors.

Improving odorant chemical class prediction with multi-layer perceptrons using temporal odorant spike responses from drosophila melanogaster olfactory receptor neurons.

In this work, we examine the possibility of improving the prediction performance of an olfactory biosensor through the use of temporal spiking data. We present an Artificial Neural Network (ANN), in the form of an optimal hybrid Multi-Layer Perceptron (MLP) system for the classification of chemical odorants from olfactory receptor neuron spike responses of the Drosophila melanogaster fruit fly (DmOrs). The data used in this study contains the responses to 34 odorants from 6 individual DmOrs, of which we exploit the temporal spiking responses of a 500ms odorant stimulus window. We report, for the first time, the difference between the classification performance of the temporal spiking data to an equivalent spontaneous scalar dataset that we have reported previously. We demonstrate that a higher prediction (%) was obtained when using the temporal data, in which a greater number of validation odorants are identified to their correct chemical class. This work presents a novel technique to improve the classification performance of an olfactory biosensor, whilst maintaining a limited sensory array of 6 DmOr receptors.

Classification of odorants across layers in locust olfactory pathway.

Olfactory processing takes place across multiple layers of neurons from the transduction of odorants in the periphery, to odor quality processing, learning, and decision making in higher olfactory structures. In insects, projection neurons (PNs) in the antennal lobe send odor information to the Kenyon cells (KCs) of the mushroom bodies and lateral horn neurons (LHNs). To examine the odor information content in different structures of the insect brain, antennal lobe, mushroom bodies and lateral horn, we designed a model of the olfactory network based on electrophysiological recordings made in vivo in the locust. We found that populations of all types (PNs, LHNs, and KCs) had lower odor classification error rates than individual cells of any given type. This improvement was quantitatively different from that observed using uniform populations of identical neurons compared with spatially structured population of neurons tuned to different odor features. This result, therefore, reflects an emergent network property. Odor classification improved with increasing stimulus duration: for similar odorants, KC and LHN ensembles reached optimal discrimination within the first 300-500 ms of the odor response. Performance improvement with time was much greater for a population of cells than for individual neurons. We conclude that, for PNs, LHNs, and KCs, ensemble responses are always much more informative than single-cell responses, despite the accumulation of noise along with odor information.

Causal Inference and Explaining Away in a Spiking Network.

While the brain uses spiking neurons for communication, theoretical research on brain computations has mostly focused on non-spiking networks. The nature of spike-based algorithms that achieve complex computations, such as object probabilistic inference, is largely unknown. Here we demonstrate that a family of high-dimensional quadratic optimization problems with non-negativity constraints can be solved exactly and efficiently by a network of spiking neurons. The network naturally imposes the non-negativity of causal contributions that is fundamental to causal inference, and uses simple operations, such as linear synapses with realistic time constants, and neural spike generation and reset non-linearities. The network infers the set of most likely causes from an observation using explaining away, which is dynamically implemented by spike-based, tuned inhibition. The algorithm performs remarkably well even when the network intrinsically generates variable spike trains, the timing of spikes is scrambled by external sources of noise, or the network is mistuned. This type of network might underlie tasks such as odor identification and classification.