1. |
- Li, Jing, et al.
(author)
-
Fabrication and application of polyurea formaldehyde-bioasphalt microcapsules as a secondary modifier for the preparation of high self-healing rate SBS modified asphalt
- 2020
-
In: Construction and Building Materials. - : Elsevier. - 0950-0618 .- 1879-0526. ; 246
-
Journal article (peer-reviewed)abstract
- In this study, microcapsules were prepared from polyurea formaldehyde (as microcapsules wall) and bio-asphalt (as microcapsules core) and were in turn applied to prepare microcapsule-styrene-butadiene styrene (microcapsule/SBS) modified asphalt. When the asphalt wall was broken, the bio-asphalt (core) drifted out and was well blended with the SBS modified asphalt to repair the damaged gap, thereby improving the self-healing ability of the pristine SBS modified asphalt. Ductility test showed that the healing rate of microcapsule/SBS modified asphalt was much greater than that of pure SBS modified asphalt. Dynamic shear rheometer and multi-stress creep recovery tests revealed that microcapsule/SBS modified asphalt exhibited better viscoelasticity, high temperature stability (by thermogravimetric analysis) and rutting resistance than pure SBS modified asphalt attributed to the even dispersion of microcapsules in SBS as confirmed by fluorescent microscopy. Compared with the pure SBS modified asphalt, the storage modulus and loss modulus of 0.4% microcapsule/SBS modified asphalt increased by 24.8% and 17.7% at 46 degrees C, respectively. Scanning electron microscopy and transmission electron microscopy analyses revealed spherical morphology of the microcapsules with wrinkled depressions on the surface, while the wall of microcapsule coated the core. This study can be envisioned of great promise for the preparation of alternative types of modified asphalt for practical applications in construction and highway industries.
|
|
2. |
- Wang, Zhaorong, et al.
(author)
-
Classification of Bone Marrow Cells Based on Dual-Channel Convolutional Block Attention Network
- 2024
-
In: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 12, s. 96205-96219
-
Journal article (peer-reviewed)abstract
- Morphological differentiation between myeloblasts and monoblasts is pivotal for the majority of acute myeloid leukemia (AML) diagnosis in clinical settings. Manual morphology-based classification of blasts encounters challenges due to the limited differentiation of these bone marrow cells (BMC) of early stages. Hence, the utilization of artificial intelligence is essential to assist in the classification of these cells. 4001 single-cell images of monoblasts and myeloblasts were collected from Taizhou Hospital to form the BMC-1 dataset. The main novelties and features of the proposed method are as follows: 1) A maximum connected domain extraction method grounded in the watershed algorithm is introduced to efficiently eliminate stained impurity cells from single cell images. 2) A dynamic focal loss is introduced to gradually focus on difficult-to-classify samples as the training progresses. 3) A dual-channel convolutional block attention network (DCCBANet) is introduced to enhance feature extraction. It employs attention mechanisms to focus on key features, utilizing ordinary convolution for local feature extraction, dilated convolution for global feature extraction, and a decreasing dilation rate sequence to preserve detailed information. A macro F1-score (macro_F) of 96.8% is achieved on the BMC-1 validation dataset. Additionally, the presence of multiple differentiation types of granulocytes pose difficulties in granulocytes distinction. To further validate the efficacy of our proposed method on multi-classification tasks, we collected 6626 granulocyte single-cell images from Taizhou Hospital. Augmenting the dataset with 2441 granulocyte single-cell images from the public dataset BM_cytomorphology addressed sample shortages, forming the BMC-2 dataset. We applied our model to the BMC-2 dataset for experiments and ultimately achieved a macro_F of 87.49%. Our proposed method effectively distinguishes monoblasts and myeloblasts and excels in the classification of granulocytes.
|
|