一种基于粒子滤波的自适应运动目标跟踪方法

该文提出了一种基于粒子滤波的自适应运动目标跟踪方法。均值漂移算法是一种最优梯度下降法,通过迭代来搜索目标,从而实现对运动目标的跟踪。而粒子滤波是一种在非线性和非高斯情形下进行跟踪的强有力方法。该文首先对图像的直方图进行改进,提出了一种基于统计直方图分布的目标模型,然后通过这个模型将这两种方法有效地结合起来。根据跟踪的过程,自适应地调整参数,能够较好地处理图像序列中由于光线变化或遮挡所带来的影响。实验证明,该文所提出的方法与均值漂移方法相比,即使在复杂的情形下,也能够准确地对目标进行跟踪。     

基于分等级对象语义图模型的复杂目标自动识别方法研究

目标自动识别是图像处理领域的研究热点。针对现有方法的不足,该文提出一种新的基于分等级对象语义图模型的复杂目标自动识别方法。该方法通过构建分等级对象语义图模型增强对目标与背景间、目标部件间语义约束的利用,引入置信对象网络统计局部特性,利用消息机制传递对象间相互影响,实现概率语义分析。训练中还将产生式和判别式方法结合,提高了目标识别的准确度。在自然和遥感部分目标类别数据集上的测试结果表明,该方法能完成对多种类型和复杂结构目标的识别和提取,具有一定的实用价值。     

一种自适应B样条网络学习算法

本文提出Ｂ样网络的一种自适应学习算法,在这种算法中,网络隐层Ｂ样条基函数的个数根据训练数据自动确定,而非零Ｂ样条基函数对应的内结点位置和连接权通过梯度下降法迭代调整,计算机模拟结果表明该算法比现有的Ｂ样条网络学习算法更加有效和实用。     

自然背景中人造目标的自适应检测

本文介绍了一种在可见光和红外图像中，自动检测自然背景中人造目标的方法。该方法以分形结构做为自然背景的数学模型，利用自然背景和人造目标在分形特征上的固有相对差异检测人造目标，本文还介绍了自适应分形特征增强和组合图像检测方法，并以对实际图像的处理的结果，说明本文介绍的人造目标检测方法的效果。     

Adaptive Algorithms for Information Processing in Navigation Complexes of Mobile Ground Objects

Journal of Communications Technology and Electronics - In this paper, complex adaptive algorithms for information processing in navigation complexes of mobile ground objects based on satellite...     

Adaptive Retransmission Design for Wireless Federated Edge Learning

As a popular distributed machine learning framework, wireless federated edge learning(FEEL) can keep original data local, while uploading model training updates to protect privacy and prevent data silos. However, since wireless channels are usually unreliable, there is no guarantee that the model updates uploaded by local devices are correct, thus greatly degrading the performance of the wireless FEEL. Conventional retransmission schemes designed for wireless systems generally aim to maximize th...     

FORMI: Integrating Adaptive Fragmented Objects into Java RMI

Distributed object-oriented applications are commonly implemented atop middleware platforms such as CORBA, .NET Remoting, and Java remote method invocation (RMI). These platforms provide a simple mechanism to invoke methods of remote objects. Increasingly more applications are demanding nonfunctional properties such as fault tolerance, high availability, and adaptivity, which require extensions to distributed objects' basic interaction model. A fragmented-object model, such as the one Marc Shapiro proposed, can provide the required flexibility. It's far more generic and flexible than the traditional client-server approach. A fragmented object is a truly distributed object; it consists of multiple fragments located on multiple nodes. Such a model allows arbitrary partitioning of state and functionality on these fragments, and arbitrary internal interaction between fragments of a single object. We have investigated integrating a fragmented-object model into CORBA (AspectIX), which requires internal modifications to the CORBA object request broker. Our approach for transparently integrating fault-tolerant objects into .NET Remoting is also useful for seamlessly integrating fragmented objects. Our FORMI architecture integrates fragmented objects into Java RMI without requiring internal modifications to the RMI runtime     

An Adaptive Machine Learning Algorithm for Location Prediction

Context-awareness is viewed as one of the most important aspects in the emerging pervasive computing paradigm. Mobile context-aware applications are required to sense and react to changing environment conditions. Such applications, usually, need to recognize, classify and predict context in order to act efficiently, beforehand, for the benefit of the user. In this paper, we propose a novel adaptive mobility prediction algorithm, which deals with location context representation and trajectory prediction of moving users. Machine Learning (ML) is used for trajectory classification. Our algorithm adopts spatial and temporal on-line clustering, and relies on Adaptive Resonance Theory (ART) for trajectory prediction. The proposed algorithm applies a Hausdorff-like distance over the extracted trajectories handling location prediction. Since our approach is time-sensitive, the Hausdorff distance is considered more advantageous than a simple Euclidean norm. Two learning methods (non-reinforcement and reinforcement learning) are presented and evaluated. Finally, we compare our algorithm with Offline kMeans and Online kMeans algorithms. Our findings are very promising for the use of the proposed algorithm in mobile context aware applications.     

基于Hausdorff距离的非刚体目标自适应轮廓跟踪

本文提出了一种基于Ｈａｕｓｄｏｒｆ距离的非刚体目标的轮廓跟踪算法。它的特点在于从二维序列图像中提取非刚体目标的二维可变模板，从而实现对非刚体运动目标的跟踪。此算法的主要思想在于将空间运动的非刚体目标的二维图像变化分解成二维运动变化和二维形状变化，从而加大了模板适应力，辅以过零点检测及金字塔快速搜索算法，可以实现非刚体目标的快速跟踪。最后，本文给出了对人体轮廓进行跟踪的实验结果。     

Learning Adaptive Temporal Radio Maps for Signal-Strength-Based Location Estimation

In wireless networks, a client's locations can be estimated using the signals received from various signal transmitters. Static fingerprint-based techniques are commonly used for location estimation, in which a radio map is built by calibrating signal-strength values in the offline phase. These values, compiled into deterministic or probabilistic models, are used for online localization. However, the radio map can be outdated when the signal-strength values change with time due to environmental dynamics, and repeated data calibration is infeasible or expensive. In this paper, we present a novel algorithm, known as LEMT (Location Estimation using Model Trees), to reconstruct a radio map using real-time signal- strength readings received at the reference points. This algorithm can take into account real-time signal-strength values at each time point and make use of the dependency between the estimated locations and reference points. We show that this technique can effectively accommodate the variations of signal strength over different time periods without the need to rebuild the radio maps repeatedly. We demonstrate the effectiveness of our proposed technique on realistic data sets collected from an 802.11b wireless network and a RFID-based network.     

基于HSV颜色空间的自适应性运动目标检测

格拉斯曼尼(Grassmannian)算法是一种可以由高度不完整信息追踪子空间的在线学习算法,它在视频运动目标跟踪时具有鲁棒性和低复杂度等优点,可以应用在视频前景与背景的实时分离的情况.针对格拉斯曼尼算法在前景分离中,面对室内全局光线突变会产生大量噪声的问题,提出了一种优化的预处理方法.通过HSV色彩空间变换对视频进行阴影检测,根据阈值判断光线变化情况并自适应调整前景内容,最终实现在光照变化情况下的运动目标检测,并有效去除了原格拉斯曼尼算法在光线突变会产生的大量噪声,提高了对光照变化的鲁棒性.     

Adaptive Clustered Federated Learning for Heterogeneous Data in Edge Computing

Mobile Networks and Applications - Although federated learning has been widely used in collaborative training of machine learning models, its practical uses are still challenged by heterogeneous...     

Federated Reinforcement Learning with Adaptive Training Times for Edge Caching

To relieve the backhaul link stress and reduce the content acquisition delay, mobile edge caching has become one of the promising approaches.In this paper, a novel federated reinforcement learning(FRL) method with adaptive training times is proposed for edge caching. Through a new federated learning process with the asynchronous model training process and synchronous global aggregation process, the proposed FRL-based edge caching algorithm mitigates the performance degradation brought by the non...     

Reinforcement Learning Based Mobility Adaptive Routing for Vehicular Ad-Hoc Networks

Vehicular ad-hoc networks (VANETs) is drawing more and more attentions in intelligent transportation system to reduce road accidents and assist safe driving. However, due to the high mobility and uneven distribution of vehicles in VANETs, multi-hops communication between the vehicles is still particularly challenging. Considering the distinctive characteristics of VANETs, in this paper, an adaptive routing protocol based on reinforcement learning (ARPRL) is proposed. Through distributed Q-Learning algorithm, ARPRL constantly learns and obtains the fresh network link status proactively with the periodic HELLO packets in the form of Q table update. Therefore, ARPRL’s dynamic adaptability to network changes is improved. Novel Q value update functions which take into account the vehicle mobility related information are designed to reinforce the Q values of wireless links by exchange of HELLO packets between neighbor vehicles. In order to avoid the routing loops caused in Q learning process, the HELLO packet structure is redesigned. In addition, reactive routing probe strategy is applied in the process of learning to speed up the convergence of Q learning. Finally, the feedback from the MAC layer is used to further improve the adaptation of Q learning to the VANETs environment. Through simulation experiment result, we show that ARPRL performs better than existing protocols in the form of average packet delivery ratio, end-to-end delay and number hops of route path while network overhead remains within acceptable ranges.     

自适应通用学习框架改进FLDA的人脸识别

针对传统的Fisher线性判别分析(FLDA)算法在处理单训练样本人脸识别时由于类内散布矩阵为零而不能进行特征提取的问题,提出了一种基于自适应通用学习框架改进FLDA的人脸识别算法。首先选取一个合适的通用训练样本集,计算其类内散布矩阵和样本平均向量;然后,利用双线性表示算法预测单训练样本的类内、类间散布矩阵,巧妙地解决了单训练样本类内散布矩阵为零的问题;最后,利用Fisher线性判别分析进行特征提取,同时借助于最近邻分类器完成人脸的识别。在Yale及FERET两大通用人脸数据库上的实验验证了所提算法的有效性及可靠性,实验结果表明,相比其他几种较为先进的单样本人脸识别算法,所提算法取得了更好的识别效果。     

Adaptive Learning Based View Synthesis Prediction for Multi-View Video Coding

In the applications of Free View TV, pre-estimated depth information is available to synthesize the intermediate views as well as to assist multi-view video coding. Existing view synthesis prediction schemes generate virtual view picture only from interview pictures. However, there are many types of signal mismatches caused by depth errors, camera heterogeneity or illumination difference across views and these mismatches decrease the prediction capability of virtual view picture. In this paper, we propose an adaptive learning based view synthesis prediction algorithm to enhance the prediction capability of virtual view picture. This algorithm integrates least square prediction with backward warping to synthesize the virtual view picture, which not only utilizes the adjacent views information but also the temporal decoded information to adaptively learn the prediction coefficients. Experiments show that the proposed method reduces the bitrates by up to 18 % relative to the multi-view video coding standard, and about 11 % relative to the conventional view synthesis prediction method.     

Learning the Dynamics and Time-Recursive Boundary Detection of Deformable Objects

We propose a principled framework for recursively segmenting deformable objects across a sequence of frames. We demonstrate the usefulness of this method on left ventricular segmentation across a cardiac cycle. The approach involves a technique for learning the system dynamics together with methods of particle-based smoothing as well as nonparametric belief propagation on a loopy graphical model capturing the temporal periodicity of the heart. The dynamic system state is a low-dimensional representation of the boundary, and the boundary estimation involves incorporating curve evolution into recursive state estimation. By formulating the problem as one of state estimation, the segmentation at each particular time is based not only on the data observed at that instant, but also on predictions based on past and future boundary estimates. Although this paper focuses on left ventricle segmentation, the method generalizes to temporally segmenting any deformable object.     

注意和习得对目标听辨能力的影响

在实验室条件下对不同注意状态的对象进行了听阈和噪声掩蔽纯音阈值的测试,并且设计实施了目标声听辨的训练实验,训练项目包括纯音听辨、无意义语音听辨和常见目标声听辨。结果显示,人耳的听力水平与注意的集中程度显著相关,习得经验对目标声听辨能力有积极的影响,且表现出一定的规律。     

Adaptive and Learning Control for SI Engine Model With Uncertainties

Air--fuel ratio control is a challenging control problem for port-fuel-injected and throttle-body-fuel-injected spark ignition (SI) engines, since the dynamics of air manifold and fuel injection of the SI engines are highly nonlinear and often with unmodeled uncertainties and disturbance. This paper presents nonlinear control approaches for multi-input multi-output engine models, by developing adaptive control and learning control design methods. Theoretical proofs are established that ensure that proposed controllers are able to give asymptotical tracking performance. As a comparison, the method applying global linearizing controller can give accurate tracking for the engine model without uncertainty and disturbance, but it fails to keep tracking performance when uncertainty is incorporated into the system. Adaptive control and learning control approaches are capable of dealing with both constant uncertainty and time-varying periodic uncertainty. Simulation results illustrate the efficacy of the proposed controllers.      

Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification

Unsupervised person re-identification(Re-ID)aims to improve the model's scalability and ob-tain better Re-ID results in the unlabeled data domain.In this paper,...