Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Ryman, Shaun K.; Bruce, Neil D. B.; Freund, Michael S.

doi:10.1016/j.snb.2016.03.059

Cited by 7 publications

(12 citation statements)

References 70 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the cleaning quality of the active surface of the sensor and the background in the measuring environment can also affect the signal quality. To improve the signal‐to‐noise ratio and obtain more real and effective data, it is necessary to filter the original signal (Pérez et al, 2016; Ryman, Bruce, & Freund, 2016). After filtering, the signal will become relatively smooth and stable, as shown in Figure 6. Mean filtering methodThe mean filtering method is based on the principle of obtaining the mean value of the same characteristic feature measured multiple times instead of the current measurement value.…”

Section: Gas Sensing Technologymentioning

confidence: 99%

Gas sensing technology for meat quality assessment: A review

Wang

Chen

2022

J Food Process Engineering

View full text Add to dashboard Cite

Meat is rich in many nutritional elements and is one of the most basic foods for human beings. The demand for meat is increasing year by year, but at the same time, meat is highly susceptible to spoilage during storage and transportation, and consumption of such meat can be hazardous to human health. Gas sensing technology provides a nondestructive, less time‐consuming, and convenient detection method compared with traditional meat quality testing techniques. In this review, we briefly describe the working principle, the common sensors, signal processing, and pattern recognition for gas sensing technology. Then, we discuss the most relevant contributions of gas sensing technology to meat freshness evaluations and authenticity assessments using different data processing methods in recent years. Finally, the problems, prospects, and likely future development of gas sensing technology are highlighted. Practical applications This article analyzes each key technology of gas sensing, points out some existing defects and future trends, reviews the practical applications of gas sensing technology in meat quality inspection in recent years, and puts forward feasible technology enhancement suggestions.

show abstract

Section: Gas Sensing Technologymentioning

confidence: 99%

Gas sensing technology for meat quality assessment: A review

Wang

Chen

2022

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…[35]. Recently, a novel Artificial Neural Networks (ANN)-based pattern recognition system was developed based on optical sensing results, which chemically learns about any changes in the surrounding environment [36]. Most machine olfaction sensing technologies (e.g electronic noses) are employed in environment monitoring, industrial manufacturing, disease diagnostic and so on.…”

Section: ) Olfactionmentioning

confidence: 99%

A DASH-Based Adaptive Multiple Sensorial Content Delivery Solution for Improved User Quality of Experience

Zou

Muntean

2019

IEEE Access

View full text Add to dashboard Cite

Increasing number of researchers are focusing on the emerging communication technologies which enrich user perceived quality of experience by involving vision, auditory, tactile, olfaction, gustatory, and other senses. However, there are multiple challenges related to using multiple sensorial media (i.e., mulsemedia), including synchronization with the traditional multimedia content and delivery over diverse network environments. This paper proposes MulseDASH, a novel multiple sensorial media content delivery solutions based on the Dynamic Adaptive Streaming over HTTP standard (DASH). MulseDASH is described and evaluated in a real test-bed in terms of the effectiveness of its adaptive streaming and synchronization mechanisms. The extensive testing involving both network emulation and subjective assessment experiments shows how MulseDASH performs an excellent real-time streaming adjustment to match network conditions and improves user quality of experience.

show abstract

“…Sparse filtering proved to be an excellent algorithm for unsupervised learning: it is extremely simple to tune since it has only a single hyper-parameter to select; it scales very well with the dimension of the input; it is easy to implement; and, more importantly, it was shown to achieve stateof-the-art performance on image recognition and phone classification (Ngiam et al, 2011;Goodfellow et al, 2013;Romaszko, 2013). Thanks to its success and to the simplicity of implementing and integrating the algorithm in already existing machine learning systems, sparse filtering was adopted in many realworld applications (see, for instance, the works of Dong et al, 2014;Raja et al, 2015;Lei et al, 2015;Ryman et al, 2016).…”

Section: Sparse Filtering and Related Workmentioning

confidence: 99%

Towards understanding sparse filtering: A theoretical perspective

Zennaro

Chen

2018

Neural Networks

View full text Add to dashboard Cite

In this paper we present a theoretical analysis to understand sparse filtering, a recent and effective algorithm for unsupervised learning. The aim of this research is not to show whether or how well sparse filtering works, but to understand why and when sparse filtering does work. We provide a thorough theoretical analysis of sparse filtering and its properties, and further offer an experimental validation of the main outcomes of our theoretical analysis. We show that sparse filtering works by explicitly maximizing the entropy of the learned representations through the maximization of the proxy of sparsity, and by implicitly preserving mutual information between original and learned representations through the constraint of preserving a structure of the data. Specifically, we show that the sparse filtering algorithm implemented using an absolute-value non-linearity determines the preservation of a data structure defined by relations of neighborhoodness under the cosine distance. Furthermore, we empirically validate our theoretical results with artificial and real data sets, and we apply our theoretical understanding to explain the success of sparse filtering on real-world problems. Our work provides a strong theoretical basis for understanding sparse filtering: it highlights assumptions and conditions for success behind this feature distribution learning algorithm, and provides insights for developing new feature distribution learning algorithms.

show abstract

Temporal responses of chemically diverse sensor arrays for machine olfaction using artificial intelligence

Cited by 7 publications

References 70 publications

Gas sensing technology for meat quality assessment: A review

Gas sensing technology for meat quality assessment: A review

A DASH-Based Adaptive Multiple Sensorial Content Delivery Solution for Improved User Quality of Experience

Towards understanding sparse filtering: A theoretical perspective

Contact Info

Product

Resources

About