Distributed learning and multi-objectivity in traffic light control

Traffic jams and suboptimal traffic flows are ubiquitous in modern societies, and they create enormous economic losses each year. Delays at traffic lights alone account for roughly 10% of all delays in US traffic. As most traffic light scheduling systems currently in use are static, set up by human experts rather than being adaptive, the interest in machine learning approaches to this problem has increased in recent years. Reinforcement learning (RL) approaches are often used in these studies, as they require little pre-existing knowledge about traffic flows. Distributed constraint optimisation approaches (DCOP) have also been shown to be successful, but are limited to cases where the traffic flows are known. The distributed coordination of exploration and exploitation (DCEE) framework was recently proposed to introduce learning in the DCOP framework. In this paper, we present a study of DCEE and RL techniques in a complex simulator, illustrating the particular advantages of each, comparing them against standard isolated traffic actuated signals. We analyse how learning and coordination behave under different traffic conditions, and discuss the multi-objective nature of the problem. Finally we evaluate several alternative reward signals in the best performing approach, some of these taking advantage of the correlation between the problem-inherent objectives to improve performance.     

基于神经网络集成学习的冷连轧板形预测

为了实现对冷连轧带钢出口板形的预测,基于粒子群算法对小波神经网络进行了优化,将优化后的网络作为基学习器,并通过bagging算法构建集成学习预测模型,进行冷连轧带钢板形的预测.以某1 450 mm冷连轧生产线数据作为样本,比较了该模型与未经优化的小波神经网络和单个学习器的预测效果.结果表明,集成学习模型预测的带钢出口板...     

高速接入网云计算平台的大数据挖掘算法研究

随着移动高速接入网络的发展,网络流量显著增加,但移动终端使计算和存储受限。利用有限的人工智能应用大数据挖掘、云计算有利于解决这些冲突,提高用户体验。针对大数据挖掘算法的移动互联网特性,联合考虑云计算和大数据挖掘,并充分考虑数据传输效率和拓扑移动接入开展研究。仿真结果表明：该算法是有效的。     

Stability analysis and motion planning strategies with fuzzy coordinator and learning for mobile base robotic part macro/micro-assembly tasks

This paper addresses problems of a mobile base robot’s part assembly. This process can be broken down into two phases. First, a macro-assembly, bringing a part to an assembly hole or a receptacle (target) for a purpose of a part mating. For the macro-manipulation task, a stability analysis of a mobile base robot subject to disturbances, such as an external impact force and torque as well as a tipping movement, is discussed. The mobile robotic system is stabilized by balancing the system moment through a fuzzy coordinator. Simulations are performed by applying external forces and torque to the system and adding disturbances to the mobile base’s tipping movement. Second, a micro-assembly, mating a part with a target. For the micro-manipulation task, two learning methodologies are presented. First, a learning strategy to minimize the entropy, uncertainty, and eliminate unneeded events in the plan related to avoiding jamming is described. An entropy function, which is a useful measure of the variability and the information in terms of uncertainty, is introduced to measure its overall performance of a task execution related to the part mating. Next, a fuzzy stochastic learning method, based on the probability of a fuzzy set and a modified distance metric, to update the probability of a plan composed of fuzzy events used for the part mating task is introduced. The degree of uncertainty associated with the fuzzy event of plan is used as an optimality criterion, or cost function, e.g. minimum Hamming distance, for a specific task execution. The above techniques are applicable to a wide range of mobile robotic tasks including pick and place operations, maneuvering around workspace, manufacturing, part mating, or complex assembly tasks.     

基于CS优化深度学习卷积神经网络的目标检测算法

目前对于形状比较复杂且密集摆放的工件,传统的工业机器人视觉分拣技术已经无法有效检测和识别。因此,为了提高生产线上分拣工件检测的准确率,提出了一种基于布谷鸟搜索算法(Cuckoo Search,CS)优化深度学习卷积神经网络(Convolutional Neural Network,CNN)的目标检测算法。首先对视觉分拣系统的组成进行了分析。然后采用经典的Faster R-CNN的模型结构来实现目标检测,并将CS优化算法应用到CNN模型的参数训练中,解决了反向传播的局部最优问题,同时提高了迭代速度。工件检测实验结果表明:相比于传统的CNN模型,提出CS-CNN模型具有更好的目标检测的准确率,提高了网络的收敛速度。     

基于曲率和给定精度的激光扫描数据自适应采样与建模技术

分析并指出了现有提取曲面原始形状信息方法的缺陷，提出了一种从曲率和精度出发来对激光扫描线自适应采样的方法，并构建曲面模型技术，通过实例验证了这种方法的可行性。     

Investigation on particle swarm optimisation for feature selection on high-dimensional data: local search and selection bias

Feature selection is an essential step in classification tasks with a large number of features, such as in gene expression data. Recent research has shown that particle swarm optimisation (PSO) is a promising approach to feature selection. However, it also has potential limitation to get stuck into local optima, especially for gene selection problems with a huge search space. Therefore, we developed a PSO algorithm (PSO-LSRG) with a fast “local search” combined with a gbest resetting mechanism as a way to improve the performance of PSO for feature selection. Furthermore, since many existing PSO-based feature selection approaches on the gene expression data have feature selection bias, i.e. no unseen test data is used, 2 sets of experiments on 10 gene expression datasets were designed: with and without feature selection bias. As compared to standard PSO, PSO with gbest resetting only, and PSO with local search only, PSO-LSRG obtained a substantial dimensionality reduction and a significant improvement on the classification performance in both sets of experiments. PSO-LSRG outperforms the other three algorithms when feature selection bias exists. When there is no feature selection bias, PSO-LSRG selects the smallest number of features in all cases, but the classification performance is slightly worse in a few cases, which may be caused by the overfitting problem. This shows that feature selection bias should be avoided when designing a feature selection algorithm to ensure its generalisation ability on unseen data.     

基于局部特征和深度神经网络的人脸性别判别模型研究

深度学习方法可以自动发现更佳数据以改善分类器性能。然而,在计算机视觉任务中,比如性别识别问题,有时候很难直接从整个图像进行学习。因此,提出一种新的基于局部特征和深度神经网络的人脸性别识别模型。首先,该模型从输入图像中提取数个局部特征,并将这些特征反馈给判别图像的深度神经网络,然后根据图像所属标签将每个局部特征分类。最后,使用简单的投票方案对整体图像进行判决。在FERET和CAS-PEAL-R1两个人脸图像资料库上进行了人脸性别分类实验,结果显示提出的方法优于其他深度学习方法,具有较好的准确性和稳定性。