Proceedings of the 1st International Conference on Control and Computer Vision最新文献

Dynamic Search Space Particle Swarm Optimization Approach for Portfolio Optimization 动态搜索空间粒子群组合优化方法

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232666

C. Feng, Yijiang Dong, Yuehan Jiang, Maopeng Ran

{"title":"Dynamic Search Space Particle Swarm Optimization Approach for Portfolio Optimization","authors":"C. Feng, Yijiang Dong, Yuehan Jiang, Maopeng Ran","doi":"10.1145/3232651.3232666","DOIUrl":"https://doi.org/10.1145/3232651.3232666","url":null,"abstract":"The multi-objective programming model of portfolio investment is based on the Markowitz portfolio theory with risk and return considered in the meantime. There have been many studies for portfolio optimization problem and over recent years heuristic techniques are widely used and proved to have good performance. The main purpose of the present study is the solving of portfolio optimization problem by using Particle Swarm Optimization (PSO). Thus in this paper, we propose an approach based on a dynamic search space particle swarm optimization algorithm (DSSPSO) for the portfolio selection problem. DSSPSO is proposed to improve the performance of PSO combining the classical particle swarm optimization algorithm philosophy and population entropy. To verify the effectiveness of the algorithm, we used the closing prices of thirty sample stocks in Chinese stock market and carried out several sets of experiments. The results show that DSSPSO approach is suitable in portfolio optimization and is able to find securities portfolio with certain interests at low risk. Also we evaluate the effect of the value of risk aversion parameter on the results and found that the algorithm can effectively control risk. Furthermore, two groups of contrast experiments are carried out to substantiate the conclusion and suggest the application for future predictions.","PeriodicalId":365064,"journal":{"name":"Proceedings of the 1st International Conference on Control and Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116149323","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

Smart Gloves: A novel 3-D Work Space Generation for Compound Two Hand Gestures 智能手套:一种新的复合手势的三维工作空间生成

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232670

H. Bhardawaj, Mohit Dhaker, K. Sivani, H. Vardhan

引用次数: 2

Research and Implementation of Image Encryption System Based on Plaintext Association 基于明文关联的图像加密系统的研究与实现

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232663

Biaobiao Wang, Hengjian Li

引用次数: 0

Palmprint Template Protection Scheme with Matrix Transformation 基于矩阵变换的掌纹模板保护方案

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232662

Hengjian Li, Jian Qiu, Changzhi Yu

引用次数: 0

Death Escape: A Case Study of Merging Ubiquitous Activities into a Hardcore Computer Game 《死亡逃脱:将无处不在的活动融入硬核电脑游戏的案例研究

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232655

Prawit Yasothorn, Tachasit Chueprasert, Witchaya Towongpaichayont

引用次数: 0

Automatic Detection of Round Timber in Digital Images Using Random Decision Forests Algorithm 基于随机决策森林算法的数字图像圆木自动检测

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232667

Y. V. Chiryshev, A. Kruglov, Anastasia Atamanova

引用次数: 4

Ultrasonic Ray-Tracing Based Endocardial Surface Reconstruction 基于超声射线追踪的心内膜表面重建

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232654

Rao Fu, Yifan Fu, Cheng Wen, Riqing Chen, Chunxu Shen, Jian Wu

{"title":"Ultrasonic Ray-Tracing Based Endocardial Surface Reconstruction","authors":"Rao Fu, Yifan Fu, Cheng Wen, Riqing Chen, Chunxu Shen, Jian Wu","doi":"10.1145/3232651.3232654","DOIUrl":"https://doi.org/10.1145/3232651.3232654","url":null,"abstract":"Accurate and fast reconstruction of the endocardium is a fundamental step for performing a successful ablation operation. This paper proposes an ultrasonic ray-tracing based endocardial surface reconstruction algorithm, which utilizes a new proposed non-contact ultrasonic catheter. The proposed catheter is composed of an electromagnetic position sensor and three miniature transducers, and it can sample a point cloud from the targeted endocardium in real-time. The 3D Delaunay triangulation of the sampled point cloud is first calculated, and then each tetrahedron is marked internal or external via ultrasonic ray-tracing and the boundary of all internal tetrahedra is extracted as a coarse surface mesh. Finally, HC Laplacian is applied to smooth the coarse mesh for the benefit of avoiding shrinkages. The basic idea of the proposed surface reconstruction algorithm relies on the fact that tetrahedra intersecting with the ultrasonic rays provide a volumetric estimation of the measured heart. Simulations on a heart phantom are given to support the superiority of the proposed algorithm. Compared to the prior arts, the proposed algorithm could reconstruct a realistic endocardial surface while preserving the features of vena cava and atrium appendage without shrinkages.","PeriodicalId":365064,"journal":{"name":"Proceedings of the 1st International Conference on Control and Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130153146","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

Convolutional Visual Feature Learning: A Compositional Subspace Representation Perspective 卷积视觉特征学习:一种组合子空间表示视角

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232672

M. Teow

引用次数: 1

Object Tracking based on KCF and Sparse Prototypes 基于KCF和稀疏原型的目标跟踪

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232659

Xiaojia Xie, Feng Wu, Qiong Liu

{"title":"Object Tracking based on KCF and Sparse Prototypes","authors":"Xiaojia Xie, Feng Wu, Qiong Liu","doi":"10.1145/3232651.3232659","DOIUrl":"https://doi.org/10.1145/3232651.3232659","url":null,"abstract":"Recently, many correlation filter-based tracking methods have received lots of attention and achieved great success in visual object tracking. Among correlation filter-based methods, the most influential one is kernelized correlation filter (KCF) which has excellent performance both in efficiency and accuracy. However, due to the virtual nature of cyclic shifts samples, the training and detecting of KCF are imprecise. To alleviate the influence of virtual samples, we take the following two measures. 1) We extract image patches at positions of samples which have local maximum KCF responses and treat them as candidates. We further evaluate their true responses. 2) Instead of estimate the target position directly according to the KCF results, we use the sparse prototypes (SP) as the target model to evaluate the similarities between candidates and target. The results of KCF and SP are combined by adaptive weight to estimate the target position. In addition, KCF degrades due to its unreasonable update scheme. To do reliable update, we set different update modes and generate an adaptive update rate based on two tracking confidence indices. Experiments on a commonly used tracking benchmark show that the proposed method improves KCF about 8% on the average success rate and 10% on the precision, and achieves better performance than other state-of-the-art trackers.","PeriodicalId":365064,"journal":{"name":"Proceedings of the 1st International Conference on Control and Computer Vision","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126156620","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

Estimation of Cauliflower Weight Based on Multiple Linear Regression Modelling 基于多元线性回归模型的菜花重量估计

Proceedings of the 1st International Conference on Control and Computer Vision Pub Date : 2018-06-15 DOI: 10.1145/3232651.3232656

Xia-Xia Guo, Gui-hong Zhou, Hong Cheng

引用次数: 1