Refine
Document Type
- Article (3)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- CNN (1)
- GCN (1)
- Volmer–Weber growth (1)
- abnormality detection (1)
- fusion (1)
- layer-by-layer (LbL) (1)
- machine learning (1)
- metal–organic frameworks (1)
- multi-network (1)
- musculoskeletal radiographs (1)
Institute
- Biochemie und Chemie (3) (remove)
In this study, a portable electronic nose (E-nose) prototype is developed using metal oxide semiconductor (MOS) sensors to detect odors of different wines. Odor detection facilitates the distinction of wines with different properties, including areas of production, vintage years, fermentation processes, and varietals. Four popular machine learning algorithms—extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and backpropagation neural network (BPNN)—were used to build identification models for different classification tasks. Experimental results show that BPNN achieved the best performance, with accuracies of 94% and 92.5% in identifying production areas and varietals, respectively; and SVM achieved the best performance in identifying vintages and fermentation processes, with accuracies of 67.3% and 60.5%, respectively. Results demonstrate the effectiveness of the developed E-nose, which could be used to distinguish different wines based on their properties following selection of an optimal algorithm.
The layer‐by‐layer (LbL) method is a well‐established method for the growth of surface‐attached metal–organic frameworks (SURMOFs). Various experimental parameters, such as surface functionalization or temperature, have been identified as essential in the past. In this study, inspired by these recent insights regarding the LbL SURMOF growth mechanism, the impact of reactant solutions concentration on LbL growth of the Cu2(F4bdc)2(dabco) SURMOF (F4bdc2−=tetrafluorobenzene‐1,4‐dicarboxylate and dabco=1,4‐diazabicyclo‐[2.2.2]octane) in situ by using quartz‐crystal microbalance and ex situ with a combination of spectroscopic, diffraction and microscopy techniques was investigated. It was found that number, size, and morphology of MOF crystallites are strongly influenced by the reagent concentration. By adjusting the interplay of nucleation and growth, we were able to produce densely packed, yet thin films, which are highly desired for a variety of SURMOF applications.
This study proposes a novel multi-network architecture consisting of a multi-scale convolution neural network (MSCNN) with fully connected graph convolution network (GCN), named MSCNN-GCN, for the detection of musculoskeletal abnormalities via musculoskeletal radiographs. To obtain both detailed and contextual information for a better description of the characteristics of the radiographs, the designed MSCNN contains three subnetwork sequences (three different scales). It maintains high resolution in each sub-network, while fusing features with different resolutions. A GCN structure was employed to demonstrate global structure information of the images. Furthermore, both the outputs of MSCNN and GCN were fused through the concat of the two feature vectors from them, thus making the novel framework more discriminative. The effectiveness of this model was verified by comparing the performance of radiologists and three popular CNN models (DenseNet169, CapsNet, and MSCNN) with three evaluation metrics (Accuracy, F1 score, and Kappa score) using the MURA dataset (a large dataset of bone X-rays). Experimental results showed that the proposed framework not only reached the highest accuracy, but also demonstrated top scores on both F1 metric and kappa metric. This indicates that the proposed model achieves high accuracy and strong robustness in musculoskeletal radiographs, which presents strong potential for a feasible scheme with intelligent medical cases.