An estimate on the reliability of prediction in the applications of electronic nose is essential, which has not been paid enough attention. An algorithm framework called conformal prediction is introduced in this work for discriminating different kinds of ginsengs with a home-made electronic nose instrument. Nonconformity measure based on k-nearest neighbors (KNN) is implemented separately as underlying algorithm of conformal prediction. In offline mode, the conformal predictor achieves a classification rate of 84.44% based on 1NN and 80.63% based on 3NN, which is better than that of simple KNN. In addition, it provides an estimate of reliability for each prediction. In online mode, the validity of predictions is guaranteed, which means that the error rate of region predictions never exceeds the significance level set by a user. The potential of this framework for detecting borderline examples and outliers in the application of E-nose is also investigated. The result shows that conformal prediction is a promising framework for the application of electronic nose to make predictions with reliability and validity.

A method using electronic nose to discriminate 10 different species of dendrobium, which is a kind of precious herb with medicinal application, was developed with high efficiency and low cost. A framework named aggregated conformal prediction was applied to make predictions with accuracy and reliability for E-nose detection. This method achieved a classification accuracy close to 80% with an average improvement of 6.2% when compared with the results obtained by using traditional inductive conformal prediction. It also provided reliability assessment to show more comprehensive information for each prediction. Meanwhile, two main indicators of conformal predictor, validity and efficiency, were also compared and discussed in this work. The result shows that the approach integrating electronic nose with aggregated conformal prediction to classify the species of dendrobium with reliability and validity is promising.

Dibutyl phthalate (DBP) is a widely used plasticizer which has been found to be a reproductive and developmental toxicant and ubiquitously existing in the air. A highly sensitive method for DBP monitoring in the environment is urgently needed. A DBP sensor based on a homemade wireless-electrodeless quartz crystal microbalance with dissipation (QCM-D) coated with nano-structured nickel hydroxide is presented. With the noncontact configuration, the sensing system could work at a higher resonance frequency (the 3rd overtone) and the response of the system was even more stable compared with a conventional quartz crystal microbalance (QCM). The sensor achieved a sensitivity of 7.3 Hz/ppb to DBP in a concentration range of 0.4–40 ppb and an ultra-low detection limit of 0.4 ppb of DBP has also been achieved.

Graph neural networks (GNNs) have shown great promise for representation learning on complex graph-structured data, but existing models often fall short when applied to directed heterogeneous graphs. In this study, we proposed a novel embedding method, a bidirectional heterogeneous graph neural network with random teleport (BHGNN-RT) that leverages the bidirectional message-passing process and network heterogeneity, for directed heterogeneous graphs. Our method captures both incoming and outgoing message flows, integrates heterogeneous edge types through relation-specific transformations, and introduces a teleportation mechanism to mitigate the oversmoothing effect in deep GNNs. Extensive experiments were conducted on various datasets to verify the efficacy and efficiency of BHGNN-RT. BHGNN-RT consistently outperforms state-of-the-art baselines, achieving up to 11.5% improvement in classification accuracy and 19.3% in entity clustering. Additional analyses confirm that optimizing message components, model layer and teleportation proportion further enhances the model performance. These results demonstrate the effectiveness and robustness of BHGNN-RT in capturing structural, directional information in directed heterogeneous graphs.

Understanding the complex architecture and functions of neural circuits is central to unraveling the mechanisms of multisensory integration. In this study, we analyzed the structural properties of the Drosophila adult brain to infer community structures within multisensory pathways. We adopt a network embedding method developed by ourselves, the Bidirectional Heterogeneous Graph Neural Network with Random Teleport (BHGNN-RT), designed to generate vector representations of neurons in a directed, heterogeneous brain connectome. This approach takes advantage of both structural connectivity and network heterogeneity features, enabling effective clustering of neurons and revealing hierarchical community architectures in olfactory and broader multisensory systems. We applied BHGNN-RT to the fly brain connectome to examine connectivity-based community organization in major neuronal classes along multisensory pathways, revealing distinct neural groups with unique connectivity patterns in the antennal lobe, lateral horn, mushroom body, and other brain regions. Further analysis showed how different neural groups contribute to the integration of sensory information in olfactory and multisensory systems. We also investigated the bilateral symmetry of the olfactory pathway, shedding light on how sensory signals are processed with ipsilateral and contralateral connections to ensure robust perception. Our findings demonstrate the utility of graph representation learning in analyzing the structural connectivity of complex neural systems. The insights gained from BHGNN-RT provide a deeper understanding of the community architecture in the Drosophila brain and contribute to a broader comprehension of the mechanisms underlying multisensory integration.