19 May 2021 in IEEE Sensors Journal
Electronic noses (E-noses) have been successfully applied in various fields. However, as a result of the inherent variability of chemical sensors, a signal processing algorithm well trained with the data from the existing domain often cannot be directly applied to the domain of interest. This severely limits the large-scale use of E-noses. In this paper, an unsupervised discriminative domain reconstruction based extreme learning machine (DDR-ELM) is proposed to compensate for such drifts/shifts and address the domain adaptation problem. Specifically, the method learns a domain-invariant space to minimize the distribution difference between different domains by discriminatively handling the different domain data using an extreme learning machine (ELM) framework. This method retains as many of the useful spatial characteristics of the source domain as possible and reduces the divergence between domains without any labeled target domain data. It avoids the cost and labor of obtaining access to the labels of data from the domain of interest. In addition, both the domain reconstruction and classification processes utilize the ELM, which is solved by pseudoinverse operations without error back-propagation iterations, consequently keeping computational complexity low. Experiments on different sensor datasets demonstrate that the proposed method is superior to several state-of-the-art drift/shift compensation methods not only in classification accuracy but also maintaining higher efficiency.
30 August 2021 in IEEE Transactions on Instrumentation and Measurement
The gas sensor drift problem arises from the bias of data, which is known as a significant problem in the artificial olfactory community. Traditionally, hardware calibration methods are laborious and ineffective due to frequent recalibration actions involving different gases, and some calibration transfer and baseline calibration methods are not effective enough. In this work, a local manifold embedding cross-domain subspace learning (LME-CDSL) model is proposed based on domain distribution alignment. It is a unified subspace learning model combined with manifold learning and domain adaptation, which tends to explore a latent transform matrix that not only enforces the drifted target domain data to learn the manifold of nondrifted source domain data but also adopts the domain adaptation method to align the domain data distribution. In general, the LME-CDSL model has three features: 1) the unsupervised and adaptation distribution subspace projection can be easily computed through eigenvector decomposition; 2) the local linear manifold learns to achieve the compact representations of high-dimensional data and is capable of preserving the local features of nondrifted samples; and 3) the domain adaptation part utilizes the maximum mean discrepancy (MMD) and variance maximization to make the sample distributions of different domains more similar and preserve the intrinsic properties. For long-term and short-term drift compensation on a single E-nose system, the local manifold embedding cross-domain subspace learning (LME-CDSL) model obtains the average recognition accuracy of 70.95% and 74.09%, respectively, while 71.71% and 73.96%, respectively for multiple identical E-nose systems with both long-term and interplate drift, which are higher than several comparative methods and proves the its effectiveness and superiority on anti-drift and gas recognition.
7 April 2025 in IEEE Robotics and Automation Letters
Ultrasound (US)-guided needle insertion is widely employed in percutaneous interventions. However, providing feedback on the needle tip position via US imaging presents challenges due to noise, artifacts, and the thin imaging plane of US, which degrades needle features and leads to intermittent tip visibility. In this letter, a Mamba-based US needle tracker MambaXCTrack utilizing structured state space models cross-correlation (SSMX-Corr) and implicit motion prompt is proposed, which is the first application of Mamba in US needle tracking. The SSMX-Corr enhances cross-correlation by long-range modeling and global searching of distant semantic features between template and search maps, benefiting the tracking under noise and artifacts by implicitly learning potential distant semantic cues. By combining with cross-map interleaved scan (CIS), local pixel-wise interaction with positional inductive bias can also be introduced to SSMX-Corr. The implicit low-level motion descriptor is proposed as a non-visual prompt to enhance tracking robustness, addressing the intermittent tip visibility problem. Extensive experiments on a dataset with motorized needle insertion in both phantom and tissue samples demonstrate that the proposed tracker outperforms other state-of-the-art trackers while ablation studies further highlight the effectiveness of each proposed tracking module.
18 June 2025 in IEEE Transactions on Instrumentation and Measurement
Permanent magnet tracking using the external sensor array is crucial for the accurate localization of wireless capsule endoscope robots. Traditional tracking algorithms, based on the magnetic dipole model and Levenberg-Marquardt (LM) algorithm, face challenges related to computational delays and the need for initial position estimation. More recently proposed neural network-based approaches often require extensive hardware calibration and real-world data collection, which are time-consuming and labor-intensive. To address these challenges, we propose MobilePosenet, a lightweight neural network architecture that leverages depthwise separable convolutions to minimize computational cost and a channel attention mechanism to enhance localization accuracy. Besides, the inputs to the network integrate the sensors’ coordinate information and random noise, compensating for the discrepancies between the theoretical model and the actual magnetic fields and thus allowing MobilePosenet to be trained entirely on theoretical data. Experimental evaluations conducted in a 90 × 90 × 80 mm workspace demonstrate that MobilePosenet exhibits excellent 5-DOF localization accuracy (1.54 ± 1.03 mm and 2.24 ± 1.84°) and less inference time (0.9 ms) against state-of-the-art methods trained on real-world data. Since network training relies solely on theoretical data, MobilePosenet can eliminate the hardware calibration and real-world data collection process, improving the generalizability of this permanent magnet localization method and the potential for rapid adoption in different clinical settings.
23 February 2024 in Journal of Medical Robotics Research