Risk-Based Screening for Thyroid Dysfunction during Pregnancy by Masanao Ohashi, Seishi Furukawa, Kaori Michikata, Katsuhide Kai, Hiroshi Sameshima, Tsuyomu Ikenoue

Get full text

Adversarial patch defense algorithm based on PatchTracker by Zhenjie XIAO, Shiyu HUANG, Feng YE, Liqing HUANG, Tianqiang HUANG

“…The application of deep neural networks in target detection has been widely adopted in various fields.However, the introduction of adversarial patch attacks, which add local perturbations to images to mislead deep neural networks, poses a significant threat to target detection systems based on vision techniques.To tackle this issue, an adversarial patch defense algorithm based on PatchTracker was proposed, leveraging the semantic differences between adversarial patches and image backgrounds.This algorithm comprised an upstream patch detector and a downstream data enhancement module.The upstream patch detector employed a YOLOV5 (you only look once-v5) model with attention mechanism to determine the locations of adversarial patches, thereby improving the detection accuracy of small-scale adversarial patches.Subsequently, the detected regions were covered with appropriate pixel values to remove the adversarial patches.This module effectively reduced the impact of adversarial examples without relying on extensive training data.The downstream data enhancement module enhanced the robustness of the target detector by modifying the model training paradigm.Finally, the image with removed patches was input into the downstream YOLOV5 target detection model, which had been enhanced through data augmentation.Cross-validation was performed on the public TT100K traffic sign dataset.Experimental results demonstrated that the proposed algorithm effectively defended against various types of generic adversarial patch attacks when compared to situations without defense measures.The algorithm improves the mean average precision (mAP) by approximately 65% when detecting adversarial patch images, effectively reducing the false negative rate of small-scale adversarial patches.Moreover, compared to existing algorithms, this approach significantly enhances the accuracy of neural networks in detecting adversarial samples.Additionally, the method exhibited excellent compatibility as it does not require modification of the downstream model structure.…”
Get full text

Reliability Analysis of Water Intake Based on MIKE Model by LIANG Zhihong, ZHENG Jiangli, CHEN Xiuhong, LIU Xia

“…The reliability of water intake is one of the main factors affecting the operation of the project,and is a prerequisite for the project to be put into use.Taking the 10 million-ton-level metallurgical new material industrial base in Wuzhou as the research object,based on the MIKE21 module in the MIKE software,this paper establishes a hydrodynamic model for verifying the reliability of the existing water intake scheme,as well as puts forward the corresponding countermeasures for the scheme with water intake risk.The results show that:①During the dry season,the water level of the Changzhou Water Control Project is relatively high,and the reservoir storage can meet the design water intake quantity of the project;②During the normal water period,the gates of Changzhou Water Control Project need to be opened to ensure the safety of flood control.If the inflow of the Shangxiaohe tributary of Xunjiang River is abundant,the project is guaranteed with water intake.If the inflow of the Shangxiaohe tributary is small,the project will have water intake risk;③Countermeasures such as dredging the river channel and lowering the water intake can effectively increase the water intake of the project,thereby avoiding the water intake risk of the project during the normal water period.The research results are of guiding significance for the construction of the 10 million-ton-level metallurgical new material industrial base in Wuzhou,and of theoretical significance for water intake reliability analysis through MIKE21.…”
Get full text

Characterizations of Chitosan-Based Polymer Electrolyte Photovoltaic Cells by M. H. Buraidah, L. P. Teo, S. R. Majid, R. Yahya, R. M. Taha, A. K. Arof

Get full text

Research on the incentive mechanism of trusted transactions based on blockchain by ZHANG Guiyu, LIU Bowen, LIANG Xiaochen, ZHANG Xiaoyan, LYU Chengjin, YU Sijia, LI Shuo

“…The mechanism adopted a distributed authentication strategy based on the reliability of user identity information of the computing network and constructed a trusted transaction entrustment certificate through the authorization of an impartial agency, realizing the trusted implementation of resource transaction tasks. …”
Get full text

Density-Based Penalty Parameter Optimization on C-SVM by Yun Liu, Jie Lian, Michael R. Bartolacci, Qing-An Zeng

“…Therefore, in this paper, we propose density-based penalty parameter optimization of C-SVM. The experiential results indicated that our proposed algorithm has outstanding performance with respect to both precision and recall.…”
Get full text

Slow task scheduling algorithm based on node identification by Yun-fei CUI, Xin-ming LI, Yi LI, Dong LIU

Subjects: “…big data…”
Get full text

Multi-FPGA Partitioning Method Based on Topological Levelization by Nabil Kerkiz, Amr Elchouemi, Don Bouldin

“…The first approach is a hierarchical partitioning method based on topological ordering (HP). The second approach is a recursive algorithm based on the Fiduccia and Mattheyses bipartitioning heuristic (RP). …”
Get full text

Fast QTMT partition decision based on deep learning by Shuang PENG, Xiaodong WANG, Zongju PENG, Fen CHEN

Subjects: Get full text

Behavior Identification Based on Geotagged Photo Data Set by Guo-qi Liu, Yi-jia Zhang, Ying-mao Fu, Ying Liu

“…The popularity of mobile devices has produced a set of image data with geographic information, time information, and text description information, which is called geotagged photo data set. …”
Get full text

Web-based learning support systems: adaptability and intelligence by Algimantas Kurlavičius

“…Structure of Intellectual Web-Based Learning Support System of many agents, which guarantees flexible and adaptive individual learning support en­vironment is introduced. …”
Get full text

Robotic Arm Motion Planning Based on an Improved PRM by You Dazhang, Zhao Hengyi, Song Luwen

“…Redundant node pruning and progressive route pruning based on dichotomous interpolation were adopted to make the path more approximate to the optimal solution. …”
Get full text

A Blockchain-Based Protocol for Fair Delivery for Receipts by M. Francisca Hinarejos, Josep-Lluis Ferrer-Gomila, Andreu-Pere Isern-Deyà, Gerardo-Francisco Chévez-Alvarado

“…., for services that provide recipients with certain documents, such as sanctions, summonses, or requirements, which are often sent by public administrations) has traditionally been provided through protocols based on the use of trusted third parties (TTPs). …”
Get full text

Spatiotemporal Video Denoising Based on Adaptive Thresholding and Clustering by Ali Abdullah Yahya, Jieqing Tan, Benyu Su, Kui Liu, Ali Naser Hadi

“…In this paper we propose a novel video denoising method based on adaptive thresholding and K-means clustering. …”
Get full text

Distributed aggregate algorithm for average query based on WSN by LIU Cai-ping1, LI Ren-fa1, LIU Xi-ping2

“…A distributed aggregate algorithm （DAA） for average query based on WSN was proposed. …”
Get full text

Deep factorization machine model based on attention capsule by Yiran GU, Zhupeng YAO, Haigen YANG

“…Aiming at the problems of single feature combination of recommendation model, resolution of a large amount of valuable feature information, and over-fitting in deep learning, a new attentional scoring mechanism called attention capsule was designed, and a deep factorization machine model based on attention capsule was proposed.Users’ historical clicking and candidate items were processed through weight calculation based on the DeepFM model, reducing the impact of irrelevant features on the model, and the differential impact of different historical behaviors on users’ interests was fully explored.The adaptive regularization formulation was added to the training, which effectively reduced over-fitting without affecting the training speed.The comparison test on two public data sets shows that the proposed model is significantly enhanced in loss function and GAUC compared to other models.…”
Get full text

Peltier Elements-based Human Brain Hypothermia Treatment by Rabab Talib Abdullah, Sadik Kamel Gharghan, Ahmed J. Abid

Get full text

Research of ASP service compination model based on workflow by WU Xiao-dong, BU Jia-jun, CHEN Chun

Subjects: “…ASP…”
Get full text

Chemical Potential-Based Modeling of Shale Gas Transport by Jisheng Kou, Lingyun Chen, Amgad Salama, Jianchao Cai

“…Modeling of gas flow in shale media has become a crucial and useful tool to estimate shale gas production accurately. …”
Get full text

Synthesis of extended fluorinated tripeptides based on the tetrahydropyridazine scaffold by Thierry Milcent, Pascal Retailleau, Benoit Crousse, Sandrine Ongeri

“…The synthesis of tripeptides incorporating new fluorinated heterocyclic hydrazino acids, based on the tetrahydropyridazine scaffold is described. …”
Get full text