1 code implementation • Mathematics 2022 • Xiaobao Yang 1, 2, *, Wentao Wang 3, Junsheng Wu 4, Chen Ding 3, Sugang Ma 3 and Zhiqiang Hou 3
Abstract: Feature pyramid networks and attention mechanisms are the mainstream methods to improve the detection performance of many current models.
no code implementations • elsvier 2022 • Camila Alves Dias1(&), Jéssica C. S. Bueno2, Eduardo N. Borges1, Silvia S. C. Botelho1, Graçaliz Pereira Dimuro1, 2, Giancarlo Lucca3, Javier Fernandéz3, Humberto Bustince3, 4, and Paulo Lilles Jorge Drews Junior1
The Choquet integral is an aggregation function studied and applied in several areas, as, e. g., in classification problems.
1 code implementation • https://www.nature.com 2022 • Zhiming Cui 1, 2, 3, Yu Fang 1, Lanzhuju Mei 1, Bojun Zhang4, 10, BoYu5, Jiameng Liu1, Caiwen Jiang1, Yuhang Sun1, Lei Ma1, Jiawei Huang1, Yang Liu6, Yue Zhao7✉, Chunfeng Lian8✉, Zhongxiang Ding9✉, Min Zhu4✉ & Dinggang Shen1, 3✉ Accurate
In addition, it consistently obtains accurate results on the challenging cases with variable dental abnormalities, with the average Dice scores of 91. 5% and 93. 0% for tooth and alveolar bone segmentation.
no code implementations • Front Immunol. 2021 • Chenjie Qiu, 1, † Wenxiang Shi, 2, † Huili Wu, 3, † Shenshan Zou, 1 Jianchao Li, 1 Dong Wang, 1 Guangli Liu, 1 Zhenbiao Song, 1 Xintao Xu, 1 Jiandong Hu, corresponding author 1, * and Hui Gengcorresponding author 1, *
We finally used qRT–PCR to detect the expression levels of four genes in colon cancer cell lines and obtained results consistent with the prediction.
no code implementations • Optics Express 2021 • Fei Jiang, 1 ZHENHAI ZHANG, 1, 5 ZIXIAO LU, 2 HONGLANG LI, 2, 6 YAHUI TIAN, 3 YIXIN ZHANG, 4 AND XUPING ZHANG4
The results show that, the proposed method can well suppress the noise and signal distortion caused by the laser frequency drift, laser phase noise, and interference fading, while recover the acoustic signals with high fidelity.
no code implementations • IOP Publishing Ltd 2021 • Ping Wan1, Hongli He2, Ling Guo1, Jiancheng Yang1 and Jie Li3, 2
Simulation results imply that the proposed model performs effectively in data generation of real-world bridge monitoring factors and improves the performance of bridge health evaluation.
no code implementations • IEEE 2020 • SHIWEN ZHANG 1, 2, (Member, TINGTING YAO3, WEI LIANG 4, VOUNDI KOE ARTHUR SANDOR4, AND KUAN-CHING LI 5, (Senior Member, IEEE)
In this article, aiming at a multi-keywords query in LBS, we propose a novel efficient and privacy-preserving multi-keyword query scheme (PPMQ) over the outsourced cloud, which satisfies the requirements of the location and query content privacy protection, query efficiency, the confidentiality of LBS data and scalability regarding the data users.
no code implementations • 13 Mar 2020 • James R. Stieger 1, 2, Stephen Engel 2, Haiteng Jiang 1, Christopher C. Cline 2, Mary Jo Kreitzer 2, Bin He 1*
Alpha-band activity in EEG signals, recorded in the volitional resting state during task performance, showed a parallel increase over sessions, and predicted final BCI performance.
no code implementations • https://www.mdpi.com/journal/sensors 2020 • Xiaowei Lu1, 2, Yunfeng Ai1and Bin Tian3, *
Abstract: Road boundary detection is an important part of the perception of autonomous driving.
1 code implementation • 2019 IEEE 2019 • Zongxu Pan1, 2*, Xianjie Bao1, Yueting Zhang1, Bowei Wang1, Quanzhi An1, 3, and Bin Lei1, 2
Different from classification networks that predict the category of one sample, the Siamese network implements a metric learning to measure the similarity between two samples.
no code implementations • Remote Sens 2019 • Mohammad Rostami 1, 2, *OrcID, Soheil Kolouri 1OrcID, Eric Eaton 2 and Kyungnam Kim 1
Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be much more challenging, and for various reasons, using crowdsourcing platforms is not feasible for labeling the SAR domain data.
no code implementations • IEEE Access 7: 12467-12475 (2019) 2019 • XIAOYU GUO1, HUI ZHANG1, 2, HAIJUN YANG 3, LIANYUAN XU4, AND ZHIWEN YE1
This network structure utilizes RNN to extract higher level contextual representations of words and CNN to obtain sentence features for the relation classification task.
1 code implementation • AAAI 2019 • Yu-Lun Liu, Yi-Tung Liao, Yen-Yu Lin, Yung-Yu Chuang1, 2
In addition to the cycle consistency loss, we propose two extensions: motion linearity loss and edge-guided training.
2 code implementations • IJCAI-19 2019 • Shengnan Guo, 2 Youfang Lin, 3 Ning Feng, 3 Chao Song, 1, 2 Huaiyu Wan 1, 2, 3∗
The output of the three components are weighted fused to generate the final prediction results.
Ranked #14 on Traffic Prediction on PeMS07
1 code implementation • IJCAI-19 2019 • Shen Fang 1, Qi Zhang 1, Gaofeng Meng 1, 2, Shiming Xiang 1, 2 and Chunhong Pan 1
Predicting traffic flow on traffic networks is a very challenging task, due to the complicated and dynamic spatial-temporal dependencies between different nodes on the network.
no code implementations • IEEE 2017 • Agus Khumaidi1, Eko Mulyanto Yuniarno1, 2, Mauridhi Hery Purnomo1, 2 1 Department of Electrical Engineering, 2 Department of Computer Engineering, Institut Teknologi Sepuluh Nopember Surabaya, Indonesia
Results of the classification used to get the category of weld defects with high accuracy as a variable of a weld inspection process whether the weld is pass the standard or not.
no code implementations • 地 球 物 理 学 报 2007 • 唐秋华1, 2, 3, 刘保华2, 陈永奇3, 周兴华2, 丁继胜2
学习向量量化(Learning Vector Quantization, LVQ)神经网络在声学底质分类中具有广泛应用. 常用的LVQ 神经网络存在神经元未被充分利用以及算法对初值敏感的问题, 影响底质分类精度. 本文提出采用遗传算法 (Genetic Algorithms, GA)优化神经网络的初始值, 将GA与LVQ神经网络结合起来, 迅速得到最佳的神经网络初始权 值向量, 实现对海底基岩、砾石、砂、细砂以及泥等底质类型的快速、准确识别. 将其应用于青岛胶州湾海区底质分