Related Experiment Video
Updated: Jul 11, 2026
09:15
DNA-based Fish Species Identification Protocol
Published on: April 28, 2010
29.4K
Real time detection and identification of fish quality using low-power multimodal artificial olfaction system
Sicheng Liu1, Guoquan Sun2, Xiang Ren1
1School of Microelectronics, Tianjin University, Tianjin, 300072, China.
Talanta
|July 30, 2024
Summary
This study developed room-temperature bimetallic oxide gas sensors and advanced AI algorithms for precise gas detection. The artificial olfactory system accurately assesses food freshness in real-time.
Area of Science:
- Materials Science
- Artificial Intelligence
- Sensor Technology
Background:
- Single gas quantification and mixed gas identification pose significant challenges in gas detection.
- Chemo-resistive gas sensors have limitations, driving research into sensor arrays.
- Optimization of sensing materials and pattern recognition algorithms are crucial for improved gas detection.
Purpose of the Study:
- To develop novel bimetallic oxide-based gas sensors for room-temperature operation.
- To enhance gas identification and quantification accuracy using advanced algorithms.
- To create a low-power artificial olfactory system for real-time food freshness assessment.
Main Methods:
- Fabrication of four bimetallic oxide gas sensors using techniques like surface oxygen defects, polymerizing conducting polymers, Nano-metal modification, and flexible substrate compositing.
- Application of feature engineering for noise reduction and dimension reduction of sensor array signals.
- Utilizing a Support Vector Machine (SVM) model for qualitative gas identification and a combined Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) network for quantitative concentration estimation.
Main Results:
- Qualitative gas identification achieved 98.86% accuracy using the SVM model.
- The deep learning-based CNN-LSTM model demonstrated superior performance in concentration recognition, achieving a lowest Root Mean Square Error (RMSE) of 2.3.
- An integrated low-power artificial olfactory system was successfully established for real-time food freshness judgment.
Conclusions:
- The developed bimetallic oxide gas sensors and advanced pattern recognition algorithms significantly improve gas detection capabilities.
- The CNN-LSTM model effectively addresses overfitting and enhances concentration recognition accuracy.
- The artificial olfactory system offers a promising solution for real-time, accurate food freshness monitoring.
Related Concept Videos
01:25Olfaction
The sense of smell is achieved through the activities of the olfactory system. It starts when an airborne odorant enters the nasal cavity and reaches olfactory epithelium (OE). The OE is protected by a thin layer of mucus, which also serves the purpose of dissolving more complex compounds into simpler chemical odorants. The size of the OE and the density of sensory neurons varies among species; in humans, the OE is only about 9-10 cm2.
The olfactory receptors are embedded in the cilia of the...
The olfactory receptors are embedded in the cilia of the...
02:32Osmoregulation in Fishes
When cells are placed in a hypotonic (low-salt) fluid, they can swell and burst. Meanwhile, cells in a hypertonic solution—with a higher salt concentration—can shrivel and die. How do fish cells avoid these gruesome fates in hypotonic freshwater or hypertonic seawater environments?