2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI)最新文献

A Deep Residual Networks Accelerator on FPGA 基于FPGA的深度残留网络加速器

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778613

Yaqian Zhao, Xin Zhang, Xing Fang, Long Li, Xuelei Li, Zhenhua Guo, Xucheng Liu

{"title":"A Deep Residual Networks Accelerator on FPGA","authors":"Yaqian Zhao, Xin Zhang, Xing Fang, Long Li, Xuelei Li, Zhenhua Guo, Xucheng Liu","doi":"10.1109/ICACI.2019.8778613","DOIUrl":"https://doi.org/10.1109/ICACI.2019.8778613","url":null,"abstract":"Deep residual networks plays an important role in deep learning and is widely used for image classification due to its high recognition rate. Moreover, with the increase of amount of data in the data center and embedded systems, performance and power consumption becomes the key issue. FPGA is an excellent solution, it’s more and more promising to accelerate deep learning inference due to the low latency and low energy consumption. In this paper, we present an OpenCL-based acceleration framework on FPGA for deep residual networks, which shown excellent performance and high energy efficiency ratio. Furthermore, we proposed a new strategy to deal with fully-connected layers, and also proposed an optimization strategy for 1×1 filters. In order to valid our proposal, we evaluate our framework on Intel Arria 10 devices. Evaluation results show that the ResNet50 Network on our framework can achieve a performance of 54img/s or 1.2img/s/W, which is 47% higher than that of the state-of-the- art FPGA-based design on the same device. Moreover, it’s also a competitive result compared to NVidia’s M4 GPUs.","PeriodicalId":213368,"journal":{"name":"2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124230729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Sequential Pattern Learning via Kernel Alignment 基于核对齐的顺序模式学习

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778473

Miao Cheng, Weibin Yang, Yonggang Li, Shichao Zhang, A. Tsoi, Yuanyan Tang

引用次数: 3

An Online Variational Inference and Ensemble Based Multi-label Classifier for Data Streams 基于在线变分推理和集成的数据流多标签分类器

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778594

Thi Thu Thuy Nguyen, T. Nguyen, Alan Wee-Chung Liew, Shilin Wang, Tiancai Liang, Yongjian Hu

引用次数: 3

Parallel Mesh Deformation Method Using Support Vector Regression for Aerodynamics 基于支持向量回归的空气动力学并行网格变形方法

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778562

Haixiang Liao, Xiang Gao

{"title":"Parallel Mesh Deformation Method Using Support Vector Regression for Aerodynamics","authors":"Haixiang Liao, Xiang Gao","doi":"10.1109/ICACI.2019.8778562","DOIUrl":"https://doi.org/10.1109/ICACI.2019.8778562","url":null,"abstract":"Mesh deformation technique is widely applied in unsteady aerodynamic simulation involving moving boundaries like fluid-structure coupling and shape optimization. This kind of method redistributes the position of grid points in accordance with the movement of the computational domain without changing their connectivity relations. In this paper, we regard the dynamic mesh problem as a nonlinear distribution problem, and present an efficient parallel mesh deformation method based on the support vector regression (SVR). In each time step, the proposed method first trains three SVRs using the coordinates of the boundary points and their known displacements in each direction as training data, and then predicts the displacements of the internal points of the mesh using the SVRs. After deforming the mesh, a dual-time step flow solver is used to solve the governing equations. Two kinds of parallel strategies are applied for different types of movement. For pre-known moving boundary cases, only a special CPU process is assigned to train the SVRs one time step earlier than the flow computing, so that the training cost will be hidden. For unpredictable moving boundary case, to ensure the consistency of the method running in parallel, the training part of the method is executed with all global boundary points in each decomposed domain. Therefore, each CPU needs to maintain a copy of the entire boundary points via a point-to-point communication. The internal evaluation of the method is predicted separately in each decomposed domain without any data dependency. An oscillatory and transient pitching airfoil case is simulated to demonstrate the applicability of the proposed mesh deformation method, and its parallel efficiency for the second strategy is over 60% with 64 cores.","PeriodicalId":213368,"journal":{"name":"2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125599474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Indoor Localization Fusion Algorithm Based on Signal Filtering optimization Of Multi-sensor 基于多传感器信号滤波优化的室内定位融合算法

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778463

T. Gu, Yanhao Tang, Ruomei Wang, Linfa Lu, Zhongshuai Wang, Liang Chang

引用次数: 8

Stage Actor Tracking Method Based on Kalman Filter 基于卡尔曼滤波的舞台演员跟踪方法

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778580

Chao Lv, Jun Yin, Yuntian Gao

引用次数: 0

Irrigation Prediction Model with BP Neural Network Improved by Genetic Algorithm in Orchards 遗传算法改进的BP神经网络果园灌溉预测模型

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778528

Jiaxing Xie, Guosheng Hu, Chuting Lin, Peng Gao, Daozong Sun, Xiuyun Xue, Xin Xu, Jianmei Liu, Huazhong Lu, Weixing Wang

{"title":"Irrigation Prediction Model with BP Neural Network Improved by Genetic Algorithm in Orchards","authors":"Jiaxing Xie, Guosheng Hu, Chuting Lin, Peng Gao, Daozong Sun, Xiuyun Xue, Xin Xu, Jianmei Liu, Huazhong Lu, Weixing Wang","doi":"10.1109/ICACI.2019.8778528","DOIUrl":"https://doi.org/10.1109/ICACI.2019.8778528","url":null,"abstract":"The orchard irrigation is susceptible significantly to various environmental factor but the approach to predict water demand of irrigation remains an outstanding challenge up to now. In this paper, a prediction model of irrigation based on GA-BP neural network has been proposed in orchards, which selects three environmental factors including air temperature, soil moisture content and light intensity as the input of back. propagation neural network. In order to overcome BP’s disadvantage of being easily stuck in a local minimum, genetic algorithm is used to optimize the weight and threshold of neural network. The results showed that the GA-BP neural network model can express the nonlinear relationship between the water demand of litchi and the main environmental factors more accurately. The mean absolute percentage error (MAPE) is only 0.0283, and the correlation coefficient of the target and output value is 0.9799. Hence, the model can provide a theoretical basis for the further development of the intelligent irrigation decision system of litchi orchards.","PeriodicalId":213368,"journal":{"name":"2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125075014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

A 2D Observation Model-Based Algorithm for Blind Single Image Super-Resolution Reconstruction 一种基于二维观测模型的单幅图像盲超分辨率重建算法

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778603

Liqin Huang, Youshen Xia

引用次数: 0

Fault Diagnosis Method of Wind Turbine Bearing Based on Improved Intrinsic Time-scale Decomposition and Spectral Kurtosis 基于改进内禀时间尺度分解和谱峰度的风电轴承故障诊断方法

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778629

Ying Zhang, Chao Zhang, Xinyuan Liu, Wei Wang, Yu Han, Na Wu

引用次数: 4

Integral Terminal Sliding Mode-Based Flight Control for Quadrotor UAVs 基于积分终端滑模的四旋翼无人机飞行控制

2019 Eleventh International Conference on Advanced Computational Intelligence (ICACI) Pub Date : 2019-06-07 DOI: 10.1109/ICACI.2019.8778599

Yue-nan Wang, Ke-cai Cao

引用次数: 3