The intelligent crack detection method is an important guarantee for the realization of intelligent operation and maintenance, and it is of great significance to traffic safety. In recent years, the recognition of road pavement cracks based on computer vision has attracted increasing attention. With the technological breakthroughs of general deep learning algorithms in recent years, detection algorithms based on deep learning and convolutional neural networks have achieved better results in the field of crack recognition. In this paper, deep learning is investigated to intelligently detect road cracks, and Faster R-CNN and Mask R-CNN are compared and analyzed. The results show that the joint training strategy is very effective, and we are able to ensure that both Faster R-CNN and Mask R-CNN complete the crack detection task when trained with only 130+ images and can outperform YOLOv3. However, the joint training strategy causes a degradation in the effectiveness of the bounding box detected by Mask R-CNN.
Background: Epigenetic alterations are involved in most cancers, but its application in cancer diagnosis is still limited. More practical and intuitive methods to detect the aberrant expressions from clinical samples using highly sensitive biomarkers are needed. In this study, we developed a novel approach in identifying, visualizing, and quantifying the biallelic and multiallelic expressions of an imprinted gene panel associated with cancer status. We evaluated the normal and aberrant expressions measured using the imprinted gene panel to formulate diagnostic models which could accurately distinguish the imprinting differences of normal and benign cases from cancerous tissues for each of the ten cancer types. Results: The Quantitative Chromogenic Imprinted Gene In Situ Hybridization (QCIGISH) method developed from a 1013-case study which provides a visual and quantitative analysis of non-coding RNA allelic expressions identified the guanine nucleotide-binding protein, alpha-stimulating complex locus (GNAS), growth factor receptor-bound protein (GRB10), and small nuclear ribonucleoprotein polypeptide N (SNRPN) out of five tested imprinted genes as efficient epigenetic biomarkers for the early-stage detection of ten cancer types. A binary algorithm developed for cancer diagnosis showed that elevated biallelic expression (BAE), multiallelic expression (MAE), and total expression (TE) measurements for the imprinted gene panel were associated with cell carcinogenesis, with the formulated diagnostic models achieving consistently high sensitivities (91-98%) and specificities (86-98%) across the different cancer types.
Municipal solid waste incineration (MSWI) has been widely used due to its benefits in reducing waste and recovering energy. However, MSWI fly ash and bottom ash are increasing rapidly, causing harm to human health and the environment. This paper discussed the production process, physical and chemical properties, leaching properties, pretreatment methods, and applications of fly ash and bottom ash. By summarizing the previous literature, it is found that MSWI fly ash and bottom ash have mechanical properties similar to natural aggregate. Many beneficial attempts have been made in cement concrete aggregates, ceramic raw materials, and highway engineering materials. Due to concerns about the leaching of heavy metals in fly ash, its application in highway engineering is limited. The application of bottom ash in asphalt pavement is rare because of the side effect on the performance of asphalt mixture. Considering the solidification effect of cement on heavy metals and the low cost of fly ash and bottom ash, the application in cement-stabilized macadam base has broad application prospects. This is beneficial to reduce the construction cost and promote the process of waste incineration, especially in developing countries.
Heavy metals are not only hazardous to environment and public health, but they degrade the physicochemical and biological properties of soils increasing difficulty to the redevelopment of contaminated sites. This study proposes a method for reinforcing contaminated soils with fiber and cement. The feasibility of using wheat straw as fiber reinforcement is discussed. The strength of heavy metal-contaminated soil reinforced with wheat straw and cement is investigated through laboratory testing. Twelve groups of soil samples were prepared at three fiber contents (i.e., 0.1%, 0.2%, and 0.3% by weight), three water contents (i.e., 9%, 12%, and 15%), and three cement contents (i.e., 5%, 7.5%, and 10% by weight). Unconfined compression strength (UCS) was tested after 28 days of curing period and various freeze-thaw cycles. The testing results show that the increase in the number of freeze-thaw cycles results in the decrease of UCS. The inclusion of fiber reinforcement within cemented soil causes an increase in the UCS and changes the brittle behavior of cemented soil to a more ductile one. The UCS of the fiber-reinforced soils first increases, then decreases with the increase of water content, and reaches the maximum value at the optimum moisture content.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.