Wireless capsule endoscopy (WCE) has developed rapidly over the last several years and now enables physicians to examine the gastrointestinal tract without surgical operation. However, a large number of images must be analyzed to obtain a diagnosis. Deep convolutional neural networks (CNNs) have demonstrated impressive performance in different computer vision tasks. Thus, in this work, we aim to explore the feasibility of deep learning for ulcer recognition and optimize a CNN-based ulcer recognition architecture for WCE images. By analyzing the ulcer recognition task and characteristics of classic deep learning networks, we propose a HAnet architecture that uses ResNet-34 as the base network and fuses hyper features from the shallow layer with deep features in deeper layers to provide final diagnostic decisions. 1,416 independent WCE videos are collected for this study. The overall test accuracy of our HAnet is 92.05%, and its sensitivity and specificity are 91.64% and 92.42%, respectively. According to our comparisons of F1, F2, and ROC-AUC, the proposed method performs better than several off-the-shelf CNN models, including VGG, DenseNet, and Inception-ResNet-v2, and classical machine learning methods with handcrafted features for WCE image classification. Overall, this study demonstrates that recognizing ulcers in WCE images via the deep CNN method is feasible and could help reduce the tedious image reading work of physicians. Moreover, our HAnet architecture tailored for this problem gives a fine choice for the design of network structure.
Under the existence of the unknown target acceleration, guidance law that guarantees imposing a predetermined impact angle relative to a maneuvering target's flight direction is proposed in this paper. The prespecified impact angle is defined in terms of a time-varying desired line of sight angle for a maneuvering target. Then, the problem of impact angle guidance law design is transformed to a problem of state tracking. To deal with the unknown target acceleration, an extended state observer is utilized to estimate it instead of simply treating it as zero. In order to avoid the singularity in the terminal phase of guidance and eliminates the need of a priori knowledge of the uncertainty upper bound, an adaptive nonsingular terminal sliding mode control scheme is adopted to design the sliding surface. The switching gain is not necessary to be determined in advance but adjusted according to the adaptive rule. Numerical simulations are implemented to demonstrate the effectiveness of the proposed guidance law.
Microcapsule/nanocapsule and encapsulation techniques have great potential for devices of functional materials. Also, electrospinning has attracted great attention for the fabrication of microstructures and nanostructures. The fluidity after melting limits the application of phase-transformation thermochromic materials. In this study, with the melt coaxial electrospinning technique, a phase-transformation thermochromic material was encapsulated in poly(methyl methacrylate) nanofibers. A device of this phase-transformation thermochromic material was realized. With a poly(methyl methacrylate) shell with good optical transmission and a thermoresponsive core made of crystal violet lactone, bisphenol A, and 1-tetradecanol core, the fibers had good thermal energy management, fluorescent thermochromism, and reversibility. The fabrication of thermochromic core-shell nanofibers has further potential in the preparation of temperature sensors with good fluorescence signals and body-temperature calefactive materials with intelligent thermal energy absorption, retention, and release.
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.