哈工大计算机学院哪些研究室,自然计算研究室

科研成果:

[ 1]A new Q-learning algorithm based

on the metropolis criterion. IEEE Transactions On Systems, Man, And

Cybernetics—Part B: Cybernetics, 2004, 34 (5): 2140-

2143

[ 2]Evolutionary tree

reconstruction using structural expectation maximization and

homotopy. Genetics and Molecular Research (GMR)

(accepted)

[ 3]Research of immune system

response simulation based on cell automata. Chinese Journal of

Electronics, 2006, 15(4A): 785-788

[ 4]Application of nonlinear

color matching model to four-color ink-jet printing. Journal of

Harbin Institute of Technology (New Series). 2002, 9(3):

270-275

[ 5]A simulated annealing-based

algorithm for traveling salesman problem. Journal of Harbin

Institute of Technology (New Series). 1997, 4(4):

35-38

[

6]基于自适应数据剪辑策略的Tri-training算法.《计算机学报》,2007,30(8):1213-1226

[

7]基于BP网络的色彩匹配方法研究.《计算机学报》,2000,23(8):819-823

[

8]评价函数驱动的抖动模式的研究.《软件学报》,1998,9(5):383-389

[

9]基于Tri-training和数据剪辑的半监督聚类算法.《软件学报》(已录用)

[10]基于熟人联盟及扩充合同网协议的多智能体协商模型.《计算机研究与发展》,2006,43(7):1155-1160

[11]一种基于信息增益与费用评价函数的特征选择准则.《计算机研究与发展》,1999,36(7):788-793

[12]基于划分策略和填充曲线的抖动模式研究.《计算机辅助设计与图形学学报》,2001,13(4):319-323

[13]基于BACON系统实现彩色图像黑白打印方法的自动化.《计算机辅助设计与图形学学报》,2001,13(8):747-751

[14]系统发生树构建技术综述.《电子学报》,2006,34(11):2047-2052

[15]RNA二级结构预测方法综述.《电子学报》(已录用)

[16]基于偏最小二乘回归分析的混色数据学习算法研究.《电子学报》,2001,29(3):429-431

[17]基于样本空间学习算法的彩色匹配方法研究.《自动化学报》,2001,27(2):186-193

[18]基于规则和模糊线性规划表示的专家系统研究.《高技术通讯》,2004,14(7):1-

4

[19]一种快速的间接关联挖掘算法.《高技术通讯》,2004,14(7):49-

52

[20]专家系统中知识库组织与维护技术的研究.《高技术通讯》,2002,12(2):1-

4,9

[21]一种新的面向属性归纳中概念层次技术研究.《管理科学学报》,2004,7(1):65-72

[22]基于progressive多序列比对方法求解多序列比对得启发式算法.《生物信息学》,2005,3(4):171-174

[23]Improving the efficiency of p-ECR

moves in evolutionary tree search methods based on Maximum

Likelihood by neighbor joining. In The Symposium of Computations in

Bioinformatics and Bioscience (SCBB'07: Aug. 13-15, 2007), Iowa,

USA (accepted)

[24]Tri-training and data editing

based semi-supervised clustering algorithm.In 5th Mexican

International Conference on Artificial Intelligence (MICAI 2006),

Lecture Notes in Artificial Intelligence, 2006, Volume 4293:

641-651

[25]A permutation-based genetic

algorithm for predicting RNA secondary structure-a practicable

approach. The 2nd International Conference on Fuzzy Systems and

Knowledge Discovery (FSKD), Lecture Notes in Artificial

Intelligence (LNAI) 3614. 2005, 861-864

[26]RNA secondary structure

prediction based on forest representation and Genetic Algorithm. In

The 3rd International Conference on Natural Computation (ICNC'07),

2007 (accepted)

[27]An improved quick algorithm for

aligning DNA/RNA sequences quickly. CIS'07, 2007 International

Conference on Computational Intelligence and Security (CIS), Dec

15-19, 2007 Harbin, China (accepted)

[28]Simulations of protein folding

process. In The 2007 International Conference on Bioinformatics and

Computational Biology (BIOCOMP'07: June 25-28, 2007),Las Vegas,

Nevada, USA:387-391

[29]A MAS communication model based

on star-ring structure. In Proceedings of the Sixth International

Conference of Machine Learning and Cybernetics (ICMLC2007)

(accepted)

[30]A method to edge-detection of

moving objects from video. In the 2007 International Conference on

Image Processing, Computer Vision, and Pattern Recognition

(IPCV'07: June 25-28, 2007), Las Vegas, Nevada, USA

(accepted)

[31]Simulating the mutation of

antibody of human immune system. In Proceeding of 2005

International Conference on Neural Networks and Brain (ICNN&B

2005), Beijing, P. R. China, 2005: 240-244

[32]Evaluation criteria on

down-compatibility degree of fuzzy inference mechanism. In

Proceedings of the Fourth International Conference on Machine

Learning and Cybernetics (ICMLC2005), Guangzhou, P. R. China:

2418-2423

[33]Q_learning based on active backup

and memory mechanism. In Proceeding of the Third International

Conference on Machine Learning and Cybernetics (ICMLC 2004),

Shanghai, P. R. China: 271-275

[34]Research on knowledge

representation and inference based on extended weighted fuzzy

logic. In Proceeding of the Second International Symposium on

Intelligent Information Technology in Agriculture (ISIITA),

Beijing, P. R. China, 2003: 95-98

[35]Research of dithering pattern

based on evolutionary algorithm and space_filling curve. In

Proceedings of 2001 International Conference on Management Science

& Engineering, Harbin, P. R. China, 2001: 590-594

[36]“计算生物学中的学习算法研究”,省杰出青年基金项目,2006-2008

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
目标检测(Object Detection)是计算机视觉领域的一个核心问题,其主要任务是找出图像中所有感兴趣的目标(物体),并确定它们的类别和位置。以下是对目标检测的详细阐述: 一、基本概念 目标检测的任务是解决“在哪里?是什么?”的问题,即定位出图像中目标的位置并识别出目标的类别。由于各类物体具有不同的外观、形状和姿态,加上成像时光照、遮挡等因素的干扰,目标检测一直是计算机视觉领域最具挑战性的任务之一。 二、核心问题 目标检测涉及以下几个核心问题: 分类问题:判断图像中的目标属于哪个类别。 定位问题:确定目标在图像中的具体位置。 大小问题:目标可能具有不同的大小。 形状问题:目标可能具有不同的形状。 三、算法分类 基于深度学习的目标检测算法主要分为两大类: Two-stage算法:先进行区域生成(Region Proposal),生成有可能包含待检物体的预选框(Region Proposal),再通过卷积神经网络进行样本分类。常见的Two-stage算法包括R-CNN、Fast R-CNN、Faster R-CNN等。 One-stage算法:不用生成区域提议,直接在网络中提取特征来预测物体分类和位置。常见的One-stage算法包括YOLO系列(YOLOv1、YOLOv2、YOLOv3、YOLOv4、YOLOv5等)、SSD和RetinaNet等。 四、算法原理 以YOLO系列为例,YOLO将目标检测视为回归问题,将输入图像一次性划分为多个区域,直接在输出层预测边界框和类别概率。YOLO采用卷积网络来提取特征,使用全连接层来得到预测值。其网络结构通常包含多个卷积层和全连接层,通过卷积层提取图像特征,通过全连接层输出预测结果。 五、应用领域 目标检测技术已经广泛应用于各个领域,为人们的生活带来了极大的便利。以下是一些主要的应用领域: 安全监控:在商场、银行
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值