SPME‐GC‐TOFMS, E‐nose, and sensory evaluation were used to explore the volatile organic compounds (VOCs) in four Chinese Yunnan coffee at three conditions (beans, ground powder, and brewed coffee). VOCs were detected by GC‐TOFMS and compared the difference between all samples, depending on the VOCs in the coffee sample. The E‐nose was used for rapid detection to differentiate the sample. The two results are analyzed by principal component analysis (PCA). Quantitative description analysis (QDA) was used to evaluate the flavor profiles of coffee samples. The results shown that GC‐TOFMS detected 412, 498, and 294 VOCs in roasted, ground powder, and brewed coffee, respectively. The PCA of SPME‐GC‐TOFMS results shown that Nankang coffee was mainly related to ketone compounds; the aroma of Hongguang coffee was determined by dimethyl disulfide and acetic acid; pyrazine and ketone compounds were important to Hainan coffee; ketone and ester compounds were dominated in Xinghuan coffee. The results of E‐nose shown that the first two principal components (PCs) accounted for 97.3%, 92.5%, and 93.8% of variances in roasted, ground powder, and brewed coffee, respectively. The different brands of coffee samples at the same condition shown separated locations on the PCA results of E‐nose. Sensory evaluation shown the special flavor of coffee samples, Nankang coffee with a bake flavor, Hongguang coffee had chocolate and nutty flavors, Hainan coffee had the caramel‐like aroma, and the aroma Xinghuan coffee was sweet. This study could provide a better understanding of Chinese coffee produced in Yunnan province.

In recent years, machine learning methods has been widely used in various fields, such as finance, spatial sciences, smart grid, intelligent transportation, renewable energy, agriculture, especially medicine. In the era of big medical data, the advantage of machine learning is that it can predict and diagnose through the analysis of a large number of clinical data, and its performance is very close and competitive to or even better than the performance of clinicians. This paper focuses on the application of machine learning techniques in the field of stomatology and detailedly describes application cases involving oral cancer, dental caries, periodontitis, dental pulp diseases, periapical lesions, oral implants, and orthodontics. Finally, the research obstacles and future work are discussed.

Convolutional neural network (CNN) models have recently demonstrated impressive classification and recognition performance on image and video processing scope. In this paper, we investigate the application of CNN to identifying modulation classes for digitally modulated signals. First, the received baseband data samples of modulated signal are gathered up and transformed to generate the constellationlike training images for convolutional networks. Among the resulting training images, the proposed convolutional gray image is preferred for network training and inference because of the lower computational burden. Second, we propose to use a multiple-scale convolutional neural network (MSCNN) as the classifier. The skip-connection technique is deployed for mitigating the negative effect of vanishing gradients and overfitting during the network training process. Numerical simulations have been carried out to validate the effectiveness of the proposed scheme, the results show that the proposed scheme outperforms the traditional algorithms in terms of classification accuracy.INDEX TERMS Convolutional neural network, automatic modulation classification, deep learning.

No abstract

In real world industrial applications, the working environment of a bearing varies with time, and some unexpected vibration noises from other equipment are inevitable. In order to improve the anti-noise performance of neural networks, a new prediction model and a multi-channel sample generation method are proposed to address the above problem. First, we proposed a multi-channel sample representation method based on the envelope time–frequency spectrum of a different channel and subsequent three-dimensional filtering to extract the fault features of samples. Second, we proposed a multi-channel data fusion neural network (MCFNN) for bearing fault discrimination, where the dropout technique is used in the training process based on a dataset with a wide rotation speed and various loads. In a noise-free environment, our experimental results demonstrated that the proposed method can reach a higher fault classification of 99.00%. In a noisy environment, the experimental results show that for the signal-to-noise ratio (SNR) of 0 dB, the fault classification averaged 11.80% higher than other methods and 32.89% higher under a SNR of −4 dB.