Polyphonic sound event localization and detection based on Multiple Attention Fusion ResNet.

Sound event localization and detection have been applied in various fields. Due to the polyphony and noise interference, it becomes challenging to accurately predict the sound event and their occurrence locations. Aiming at this problem, we propose a Multiple Attention Fusion ResNet, which uses ResNet34 as the base network. Given the situation that the sound duration is not fixed, and there are multiple polyphonic and noise, we introduce the Gated Channel Transform to enhance the residual basic block. This enables the model to capture contextual information, evaluate channel weights, and reduce the interference caused by polyphony and noise. Furthermore, Split Attention is introduced to the model for capturing cross-channel information, which enhances the ability to distinguish the polyphony. Finally, Coordinate Attention is introduced to the model so that the model can focus on both the channel information and spatial location information of sound events. Experiments were conducted on two different datasets, TAU-NIGENS Spatial Sound Events 2020, and TAU-NIGENS Spatial Sound Events 2021. The results demonstrate that the proposed model significantly outperforms state-of-the-art methods under multiple polyphonic and noise-directional interference environments and it achieves competitive performance under a single polyphonic environment.

Recent Advances in Flexible Pressure Sensors Based on MXene Materials.

In the past decade, with the rapid development of wearable electronics, medical health monitoring, the Internet of Things, and flexible intelligent robots, flexible pressure sensors have received unprecedented attention. As a very important kind of electronic component for information transmission and collection, flexible pressure sensors have gained a wide application prospect in the fields of aerospace, biomedical and health monitoring, electronic skin, and human-machine interface. In recent years, MXene has attracted extensive attention because of its unique 2D layered structure, high conductivity, rich surface terminal groups, and hydrophilicity, which has brought a new breakthrough for flexible sensing. Thus, it has become a revolutionary pressure-sensitive material with great potential. In this work, the recent advances of MXene-based flexible pressure sensors are reviewed from the aspects of sensing type, sensing mechanism, material selection, structural design, preparation strategy, and sensing application. The methods and strategies to improve the performance of MXene-based flexible pressure sensors are analyzed in details. Finally, the opportunities and challenges faced by MXene-based flexible pressure sensors are discussed. This review will bring the research and development of MXene-based flexible sensors to a new high level, promoting the wider research exploitation and practical application of MXene materials in flexible pressure sensors.

[Hyperspectral imaging technology distinguishes between Puerariae Lobatae Radix and Puerariae Lobatae Caulis].

Puerariae Lobatae Radix, the dried root of Pueraria lobata, is a traditional Chinese medicine with a long history. Puerariae Lobatae Caulis as an adulterant is always mixed into Puerariae Lobatae Radix for sales in the market. This study employed hyperspectral imaging(HSI) to distinguish between the two products. VNIR lens(spectral scope of 410-990 nm) and SWIR lens(spectral scope of 950-2 500 nm) were used for image acquiring. Multi-layer perceptron(MLP), partial least squares discriminant analysis(PLS-DA), and support vector machine(SVM) were employed to establish the full-waveband models and select the effective wavelengths for the distinguishing between Puerariae Lobatae Caulis and Puerariae Lobatae Radix, which provided technical and data support for the development of quick inspection equipment based on HSI. The results showed that MLP model outperformed PLS-DA and SVM models in the accuracy of discrimination with full wavebands in VNIR, SWIR, and VNIR+SWIR lens, which were 95.26%, 99.11%, and 99.05%, respectively. The discriminative band selection(DBS) algorithm was employed to select the effective wavelengths, and the discrimination accuracy was 93.05%, 98.05%, and 98.74% in the three different spectral scopes, respectively. On this basis, the MLP model combined with the effective wavelengths within the range of 2 100-2 400 nm can achieve the accuracy of 97.74%, which was close to that obtained with the full waveband. This waveband can be used to develop quick inspection devices based on HSI for the rapid and non-destructive distinguishing between Puerariae Lobatae Radix and Puerariae Lobatae Caulis.

A Self-Supervised Anomaly Detector of Fruits Based on Hyperspectral Imaging.

Hyperspectral imaging combined with chemometric approaches is proven to be a powerful tool for the quality evaluation and control of fruits. In fruit defect-detection scenarios, developing an unsupervised anomaly detection framework is vital, as defect sample preparation is labor-intensive and time-consuming, especially for exploring potential defects. In this paper, a spectral-spatial, information-based, self-supervised anomaly detection (SSAD) approach is proposed. During training, an auxiliary classifier is proposed to identify the projection axes of principal component (PC) images that were transformed from the hyperspectral data cubes. In test time, the fully connected layer of the learned classifier was used as a 'spectral-spatial' feature extractor, and the feature similarity metric was adopted as the score function for the downstream anomaly evaluation task. The proposed network was evaluated with two fruit data sets: a strawberry data set with bruised, infected, chilling-injured, and contaminated test samples and a blueberry data set with bruised, infected, chilling-injured, and wrinkled samples as anomalies. The results show that the SSAD yielded the best anomaly detection performance (AUC = 0.923 on average) over the baseline methods, and the visualization results further confirmed its advantage in extracting effective 'spectral-spatial' latent representation. Moreover, the robustness of SSAD is verified with the data pollution experiment; it performed significantly better than the baselines when a portion of anomalous samples was involved in the training process.

Detection of Adulteration in Infant Formula Based on Ensemble Convolutional Neural Network and Near-Infrared Spectroscopy.

Adulteration in dairy products has received world-wide attention, and at the same time, near infrared (NIR) spectroscopy has proven to be a promising tool for adulteration detection given its advantages of real-time response and non-destructive analysis. Regardless, the accurate and robust NIR model for adulteration detection is hard to achieve in practice. Convolutional neural network (CNN), as a promising deep learning architecture, is difficult to apply to such chemometrics tasks due to the high risk of overfitting, despite the breakthroughs it has made in other fields. In this paper, the ensemble learning method based on CNN estimators was developed to address the overfitting and random initialization problems of CNN and applied to the determination of two infant formula adulterants, namely hydrolyzed leather protein (HLP) and melamine. Moreover, a probabilistic wavelength selection method based on the attention mechanism was proposed for the purpose of finding the best trade-off between the accuracy and the diversity of the sub-models in ensemble learning. The overall results demonstrate that the proposed method yielded superiority regression performance over the comparison methods for both studied data sets, and determination coefficients (R2) of 0.961 and 0.995 were obtained for the HLP and the melamine data sets, respectively.

Heart sound classification using the SNMFNet classifier.

OBJECTIVE: Heart sound classification still suffers from the challenges involved in achieving high accuracy in the case of small samples. Dimension reduction attempts to extract low-dimensional features with more discriminability from high-dimensional spaces or raw data, and is popular in learning predictive models that target small sample problems. However, it can also be harmful to classification, because any reduction has the potential to lose information containing category attributes. APPROACH: For this, a novel SNMFNet classifier is designed to directly associate the dimension reduction process with the classification procedure used for promoting feature dimension reduction to follow the approach that is beneficial for classification, thus making the low-dimensional features more distinguishable and addressing the challenge facing heart sound classification in small samples. MAIN RESULTS: We evaluated our method and representative methods using a public heart sound dataset. The experimental results demonstrate that our method outperforms all comparative models with an obvious improvement in small samples. Furthermore, even if used with relatively sufficient samples, our method performs at least as well as the baseline that uses the same high-dimensional features. SIGNIFICANCE: The proposed SNMFNet classifier significantly to improves the small sample problem in heart sound classification.

Convolutional neural network for hyperspectral data analysis and effective wavelengths selection.

Fusion of spectral and spatial information has been proved to be an effective approach to improve model performance in near-infrared hyperspectral data analysis. Regardless, most of the existing spectral-spatial classification methods require fairly complex pipelines and exact selection of parameters, which mainly depend on the investigator's experience and the object under test. Convolutional neural network (CNN) is a powerful tool for representing complicated data and usually works with few "hand-engineering", making it an appropriate candidate for developing a general and automatic approach. In this paper, a two-branch convolutional neural network (2B-CNN) was developed for spectral-spatial classification and effective wavelengths (EWs) selection. The proposed network was evaluated by three classification data sets, including herbal medicine, coffee bean and strawberry. The results showed that the 2B-CNN obtained the best classification accuracies (96.72% in average) when compared with support vector machine (92.60% in average), one dimensional CNN (92.58% in average), and grey level co-occurrence matrix based support vector machine (93.83% in average). Furthermore, the learned weights of the two-dimensional branch in 2B-CNN were adopted as the indicator of EWs and compared with the successive projections algorithm. The 2B-CNN models built with wavelengths selected by the weight indicator achieved the best accuracies (96.02% in average) among all the examined EWs models. Different from the conventional EWs selection method, the proposed algorithm works without any additional retraining and has the ability to comprehensively consider the discriminative power in spectral domain and spatial domain.

Margin-Based Pareto Ensemble Pruning: An Ensemble Pruning Algorithm That Learns to Search Optimized Ensembles.

The ensemble pruning system is an effective machine learning framework that combines several learners as experts to classify a test set. Generally, ensemble pruning systems aim to define a region of competence based on the validation set to select the most competent ensembles from the ensemble pool with respect to the test set. However, the size of the ensemble pool is usually fixed, and the performance of an ensemble pool heavily depends on the definition of the region of competence. In this paper, a dynamic pruning framework called margin-based Pareto ensemble pruning is proposed for ensemble pruning systems. The framework explores the optimized ensemble pool size during the overproduction stage and finetunes the experts during the pruning stage. The Pareto optimization algorithm is used to explore the size of the overproduction ensemble pool that can result in better performance. Considering the information entropy of the learners in the indecision region, the marginal criterion for each learner in the ensemble pool is calculated using margin criterion pruning, which prunes the experts with respect to the test set. The effectiveness of the proposed method for classification tasks is assessed using datasets. The results show that margin-based Pareto ensemble pruning can achieve smaller ensemble sizes and better classification performance in most datasets when compared with state-of-the-art models.