Bio-Inspired Strategies for Improving the Selectivity and Sensitivity of Artificial Noses: A Review

Hurot, Charlotte; Scaramozzino, Natale; Buhot, Arnaud; Hou, Yanxia

doi:10.3390/s20061803

Cited by 35 publications

(24 citation statements)

References 207 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Optimally, it captures every performed shot, corresponding to a high sensitivity. Since there is a conflict between sensitivity and selectivity [ 32 , 33 ], a suitable trigger algorithm has to be found.…”

Section: Methodsmentioning

confidence: 99%

Classification of Tennis Shots with a Neural Network Approach

Ganser

Hollaus

Stabinger³

2021

Sensors

View full text Add to dashboard Cite

Data analysis plays an increasingly valuable role in sports. The better the data that is analysed, the more concise training methods that can be chosen. Several solutions already exist for this purpose in the tennis industry; however, none of them combine data generation with a wristband and classification with a deep convolutional neural network (CNN). In this article, we demonstrate the development of a reliable shot detection trigger and a deep neural network that classifies tennis shots into three and five shot types. We generate a dataset for the training of neural networks with the help of a sensor wristband, which recorded 11 signals, including an inertial measurement unit (IMU). The final dataset included 5682 labelled shots of 16 players of age 13–70 years, predominantly at an amateur level. Two state-of-the-art architectures for time series classification (TSC) are compared, namely a fully convolutional network (FCN) and a residual network (ResNet). Recent advances in the field of machine learning, like the Mish activation function and the Ranger optimizer, are utilized. Training with the rather inhomogeneous dataset led to an F1 score of 96% in classification of the main shots and 94% for the expansion. Consequently, the study yielded a solid base for more complex tennis analysis tools, such as the indication of success rates per shot type.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification of Tennis Shots with a Neural Network Approach

Ganser

Hollaus

Stabinger³

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…2 [1,29,30,31] High accuracy High accuracy due to natural binding of OR with specific ligand. 2 [1,29] High resolution Substances can be detected in very high resolutions at a level of nanomoles (or lower).…”

Section: Fulfillment Rating Referencesmentioning

confidence: 99%

Market Perspectives and Future Fields of Application of Odor Detection Biosensors—A Systematic Analysis

Full

Delbrück

Sauer

et al. 2020

The 1st International Electronic Conference on Biosensors

View full text Add to dashboard Cite

The technological advantages that biosensors have over conventional technical sensors for odor detection have not yet been comprehensively analyzed. However, this is necessary for assessing their suitability for specific fields of application as well as their improvement and development goals. In this paper specific market potentials of biosensors for odor detection are identified by applying a tailored methodology that enables the derivation and systematic comparison of both the performance profiles of biosensors as well as the requirement profiles for various application fields. Therefore, the fulfillment of defined requirements is evaluated for biosensors by means of 16 selected technical criteria in order to determine a specific performance profile. Further, a selection of application fields for odor detection sensors is derived to compare the importance of the criteria for each of the fields, leading to market-specific requirement profiles. The analysis reveals that the requirement criteria considered to be the most important ones across all application fields are high specificity, high selectivity, high repeat accuracy, high resolution, high accuracy, and high sensitivity. All these criteria, except for the repeat accuracy, can potentially be better met by biosensors than by technical sensors, according to the results obtained. Therefore, biosensor technology in general has a high application potential for all the areas of application under consideration. Health and safety applications especially are considered to have high potential for biosensors due to their correspondence between requirement and performance profiles.

show abstract

“…Classical methods of chemical analysis, such as gas and liquid chromatography, mass spectrometry, nuclear magnetic resonance, and spectrophotometry, are highly reliable, although they are expensive, time-consuming, and unsuitable for on-site monitoring. Over the last two decades, one can observe a rapid expansion in the development of artificial organoleptic systems [ 1 ], so called electronic noses (e-noses). Various sensing methods based on thermal, optical, gravimetric, and electrochemical techniques have been developed since the introduction of the e-nose concept.…”

Section: Introductionmentioning

confidence: 99%

Odor Detection Using an E-Nose With a Reduced Sensor Array

Borowik

Adamowicz

Tarakowski

et al. 2020

Sensors

View full text Add to dashboard Cite

Recent advances in the field of electronic noses (e-noses) have led to new developments in both sensors and feature extraction as well as data processing techniques, providing an increased amount of information. Therefore, feature selection has become essential in the development of e-nose applications. Sophisticated computation techniques can be applied for solving the old problem of sensor number optimization and feature selections. In this way, one can find an optimal application-specific sensor array and reduce the potential cost associated with designing new e-nose devices. In this paper, we examine a procedure to extract and select modeling features for optimal e-nose performance. The usefulness of this approach is demonstrated in detail. We calculated the model’s performance using cross-validation with the standard leave-one-group-out and group shuffle validation methods. Our analysis of wine spoilage data from the sensor array shows when a transient sensor response is considered, both from gas adsorption and desorption phases, it is possible to obtain a reasonable level of odor detection even with data coming from a single sensor. This requires adequate extraction of modeling features and then selection of features used in the final model.

show abstract

Bio-Inspired Strategies for Improving the Selectivity and Sensitivity of Artificial Noses: A Review

Cited by 35 publications

References 207 publications

Classification of Tennis Shots with a Neural Network Approach

Classification of Tennis Shots with a Neural Network Approach

Market Perspectives and Future Fields of Application of Odor Detection Biosensors—A Systematic Analysis

Odor Detection Using an E-Nose With a Reduced Sensor Array

Contact Info

Product

Resources

About