TDACNN: Target-domain-free Domain Adaptation Convolutional Neural Network for Drift Compensation in Gas Sensors
This addresses the unpredictable sensor drift problem in gas sensors, which is critical for real-world applications where target domain data is unavailable, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackles sensor drift in gas recognition by proposing TDACNN, a target-domain-free domain adaptation method that uses a multibranch CNN to extract domain-invariant features without needing target domain data, achieving superior performance on two drift datasets compared to state-of-the-art methods.
Sensor drift is a long-existing unpredictable problem that deteriorates the performance of gaseous substance recognition, calling for an antidrift domain adaptation algorithm. However, the prerequisite for traditional methods to achieve fine results is to have data from both nondrift distributions (source domain) and drift distributions (target domain) for domain alignment, which is usually unrealistic and unachievable in real-life scenarios. To compensate for this, in this paper, deep learning based on a target-domain-free domain adaptation convolutional neural network (TDACNN) is proposed. The main concept is that CNNs extract not only the domain-specific features of samples but also the domain-invariant features underlying both the source and target domains. Making full use of these various levels of embedding features can lead to comprehensive utilization of different levels of characteristics, thus achieving drift compensation by the extracted intermediate features between two domains. In the TDACNN, a flexible multibranch backbone with a multiclassifier structure is proposed under the guidance of bionics, which utilizes multiple embedding features comprehensively without involving target domain data during training. A classifier ensemble method based on maximum mean discrepancy (MMD) is proposed to evaluate all the classifiers jointly based on the credibility of the pseudolabel. To optimize network training, an additive angular margin softmax loss with parameter dynamic adjustment is utilized. Experiments on two drift datasets under different settings demonstrate the superiority of TDACNN compared with several state-of-the-art methods.