http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
An Effective WSSENet-Based Similarity Retrieval Method of Large Lung CT Image Databases
Yi Zhuang,Shuai Chen,Nan Jiang,Hua Hu 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.7
With the exponential growth of medical image big data represented by high-resolution CT images(CTI), the high-resolution CTI data is of great importance for clinical research and diagnosis. The paper takes lung CTI as an example to study. Retrieving answer CTIs similar to the input one from the large-scale lung CTI database can effectively assist physicians to diagnose. Compared with the conventional content-based image retrieval(CBIR) methods, the CBIR for lung CTIs demands higher retrieval accuracy in both the contour shape and the internal details of the organ. In traditional supervised deep learning networks, the learning of the network relies on the labeling of CTIs which is a very time-consuming task. To address this issue, the paper proposes a Weakly Supervised Similarity Evaluation Network (WSSENet) for efficiently support similarity analysis of lung CTIs. We conducted extensive experiments to verify the effectiveness of the WSSENet based on which the CBIR is performed.
Wang, Yang,Zhuang, Lili,Chen, Xuan,Xu, Man,Li, Zuochen,Jin, Yi Elsevier 2017 Animal reproduction science Vol.187 No.-
<P><B>Abstract</B></P> <P>This study was undertaken to investigate the dynamics of protein ubiquitination in pig gametes and their micro-environments, as well as to explore the action of deubiquitinases (DUBs) in sperm-oocyte binding. Protein ubiquitination states were evaluated by in the ejaculated sperm, seminal plasma, epididymal sperm, oocytes, zona pellucida (ZP) and follicular fluid (FF) by western blotting. Different concentrations of PR-619, a non-selective inhibitor of DUBs, were used to treat oocytes during <I>in vitro</I> maturation (IVM), the maturation rate, amount of ubiquitinated ZP proteins, and ZP solubility were assessed. The PR-619 was also used to treat sperms during capacitation, then the ubiquitinated amounts of acrosin inhibitor (AI) proteins were evaluated. The number of sperm attached to the ZP of each oocyte was subsequently determined after gamete co-incubation. The study indicates the existence of ubiquitinated proteins (76kDa) in sperm, seminal plasma, oocytes, and follicular fluid (FF). The amount of ubiquitinated ZP proteins changed as growth of follicles progressed. Treatment with PR-619 at 10 and 15μM concentrations during IVM reduced the maturation rate of pig oocytes (<I>P</I> <0.05), while treatments with 10μM of PR-619 extended the ZP dissolution time (<I>P </I><0.05). Treatment with PR-619 enhanced AI ubiquitination and improved amounts of 30-kDa ubiquitinated proteins (<I>P </I><0.05). Treatment with PR-619 at the 10μM dose effectively reduced the number of sperm attached to per oocyte (<I>P<</I> 0.05). Ubiquitinated proteins were present in gametes and their micro-environments. The DUBs were important in regulating pig gamete ubiquitination and sperm-oocyte binding.</P>
Infrared and Visible Image Fusion Method Based On Three Stages of Discrete Wavelet Transform
Lingchao Zhan,Yi Zhuang 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.5
For infrared images, the performance of texture details in the target scene is not good, and for visible images, the performance is constrained by illumination and environment. An image fusion method is proposed here, its characteristic is getting three different discrete wavelet fusion methods together. The method has three stages, in the first two stages, the infrared and visible images are fused using different wavelet fusion rules, the two fusion results from the first and the second stage are fused again using another wavelet fusion rule, and then we get the final fusion result. The result proves that, compared with the similar research methods, the proposed method can ensure the quality and enhance the spatial detail of the fused image.
An Efficient Block Index Scheme with Segmentation for Spatio-Textual Similarity Join
( Yiming Xiang ),( Yi Zhuang ),( Nan Jiang ) 한국인터넷정보학회 2017 KSII Transactions on Internet and Information Syst Vol.11 No.7
Given two collections of objects that carry both spatial and textual information in the form of tags, a Spatio-Textual-based object Similarity JOIN (ST-SJOIN) retrieves the pairs of objects that are textually similar and spatially close. In this paper, we have proposed a block index-based approach called BIST-JOIN to facilitate the efficient ST-SJOIN processing. In this approach, a dual-feature distance plane (DFDP) is first partitioned into some blocks based on four segmentation schemes, and the ST-SJOIN is then transformed into searching the object pairs falling in some affected blocks in the DFDP. Extensive experiments on real and synthetic datasets demonstrate that our proposed join method outperforms the state-of- the-art solutions.
Using Color Composition Diagrams as a Medium for Promoting Better-balanced Diet
Yao Dai,Yi-Lin Zhuang,Nan-Ling Yeh,Jun Pana,I-Ping Chen 한국색채학회 2017 AIC 2017 Jeju Vol.2017 No.10
We aim to design an App that helps people establish an increased awareness on their daily diet in a highly playful manner. The core concept of this App is to use color information of food photographs people take before meals to give users feedback on how to balance their diets. A healthy food and an unhealthy food color template were created through the following process: using the guideline provided by WHO (World Health Organization), we collected thousands of images of healthy and unhealthy food. The collective color attributes (hue composition, weights of redness, greenness, yellowness, and blueness, average luminance, general contrast) of each of the two groups were derived to render a visualizable color composition template. This way, all the incoming food pictures taken by the user can be compared to the healthy and the unhealthy template. Instead of informing the user ‘You should take more protein.’, our App gives feedback like ‘Maybe you should try more RED.’ Our user experience assessment shows that users enjoy playing with such graphic interface and will potentially pay more attention to their daily diets.
A Double-Layer Heartbeat Detection Algorithm Orienting to Embedded Heterogeneous Cluster
Zhu Wei,Zhuang Yi,Xu Chaoqun 보안공학연구지원센터 2015 International Journal of Grid and Distributed Comp Vol.8 No.3
The heartbeat detection is an important technology to detect faults of cluster nodes. This paper proposes a Double-layer Heartbeat Detection Model and a Double-layer Heartbeat Detection Algorithm (DLHB) orienting to embedded heterogeneous clusters to obtain high availability of embedded heterogeneous clusters. This algorithm divides the nodes in the embedded heterogeneous cluster into different areas by their physical positions. In each node area, a node is selected as the master control node. The inter-area detection uses heartbeat ring mechanism. The intra-area detection can only be made among master control nodes. The experiment results show that, DLHB is more accurate in prediction compared with DHB, and can detect faults concurrently occurring on multiple nodes with less time compared with the heartbeat ring algorithm.