轨迹分布模式学习的层次自组织神经网络方法

提出一个层次自组织神经网络模型，并将其应用于基于事件识别的轨迹分布模式学习中。该文利用神经元的侧向连接将神经元连成若干条线，每条线对应一个“内部网”。对应于层次神经网络模型，建立了两个领域，即神经元领域和“内部网”领域，两个领域内的神经元都要不同程度地改变权值，从而完成运动轨迹分布模式的学习。还给出了利用轨迹分布模式检测出局部可能的异常现象、检测整个运动轨迹所表示的事件是否为异常事件和目标行为预测的方法。实验进一步说明了该方法的可行性和有效性。     

基于视觉监控的操作手势轨迹分布模式研究

为准确学习飞行员操作手势的轨迹分布模式,提出一种改进的层次自组织映射方法。引入 秩和检验技术,结合编辑距离判断内部网的匹配程度,通过交叉验证使验证集获得误差最小,从而自适应取得判断异常的阈值。根据训练得到的轨迹分布模式检测操作过程中的局部异常,判断运动轨迹所表示的事件是否为异常事件,并预测手势将来行为轨迹。实验结果验证了改进方法的有效性。     

基于轨迹系数特征空间表示法的含有异常情况的自动运动学习

Techniques for understanding video object motion activity are becoming increasingly important with the widespread adoption of CCTV surveillance systems. Motion trajectories provide rich spatiotemporal information about an object's activity. This paper presents a novel technique for clustering of object trajectory-based video motion clips using basis function approximations. Motion cues can be extracted using a tracking algorithm on video streams from video cameras. In the proposed system, trajectories are treated as time series and modelled using orthogonal basis function representation. Various function approximations have been compared including least squares polynomial, Chebyshev polynomials, piecewise aggregate approximation, discrete Fourier transform (DFT), and modified DFT (DFT-MOD). A novel framework, namely iterative hierarchical semi-agglomerative clustering using learning vector quantization (Iterative HSACT-LVQ), is proposed for learning of patterns in the presence of significant number of anomalies in training data. In this context, anomalies are defined as atypical behavior patterns that are not represented by sufficient samples in training data and are infrequently occurring or unusual. The proposed algorithm does not require any prior knowledge about the number of patterns hidden in unclassified dataset. Experiments using complex real-life trajectory datasets demonstrate the superiority of our proposed Iterative HSACT-LVQ-based motion learning technique compared to other recent approaches.     

Minimal Structure of Self-Organizing HCMAC Neural Network Classifier

The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a self-organizing input space module to solve high-dimensional pattern classification problems. This novel neural network exhibits fast learning, a low memory requirement, automatic memory parameter determination and highly accurate high-dimensional pattern classification. However, the original architecture needs to be hierarchically expanded using a full binary tree topology to solve pattern classification problems according to the dimension of the input vectors. This approach creates many redundant GCMAC nodes when the dimension of the input vectors in the pattern classification problem does not exactly match that in the self-organizing HCMAC neural network. These redundant GCMAC nodes waste memory units and degrade the learning performance of a self-organizing HCMAC neural network. Therefore, this study presents a minimal structure of self-organizing HCMAC (MHCMAC) neural network with the same dimension of input vectors as the pattern classification problem. Additionally, this study compares the learning performance of this novel learning structure with those of the BP neural network,support vector machine (SVM), and original self-organizing HCMAC neural network in terms of ten benchmark pattern classification data sets from the UCI machine learning repository. In particular, the experimental results reveal that the self-organizing MHCMAC neural network handles high-dimensional pattern classification problems better than the BP, SVM or the original self-organizing HCMAC neural network. Moreover, the proposed self-organizing MHCMAC neural network significantly reduces the memory requirement of the original self-organizing HCMAC neural network, and has a high training speed and higher pattern classification accuracy than the original self-organizing HCMAC neural network in most testing benchmark data sets. The experimental results also show that the MHCMAC neural network learns continuous function well and is suitable for Web page classification.     

Self-organization of Dynamic Object Features Based on Bidirectional Training

This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.     

MCM划分的自组织神经网络

本文在提出一个直接和间接相联模块间相似性的表示方法的基础上，提出了一个基于自组织神经网络的性能驱动ＭＣＭ划分的神经学习方法。算法求解如何在高层设计中将功能模块分配到ＭＣＭ芯片中。算法不仅考虑了模块间的相似关系，还考虑了ＭＣＭ的版图结构；具有芯片间连线数目最少和时钟周期最短双重优化目标；能使连线尽量产生在相邻近的芯片之间；能满足时延、散热和面积约束。文中还提出了一个层次神经网络模型和面积约束下的ＭＣ     

Behavior pattern extraction by trajectory analysis

Trajectory clustering and behavior pattern extraction are the foundations of research into activity perception of objects in motion. In this paper, a new framework is proposed to extract behavior patterns through trajectory analysis. Firstly, we introduce directional trimmed mean distance (DTMD), a novel method used to measure similarity between trajectories. DTMD has the attributes of anti-noise, self-adaptation and the capability to determine the direction for each trajectory. Secondly, we use a hierarchical clustering algorithm to cluster trajectories. We design a length-weighted linkage rule to enhance the accuracy of trajectory clustering and reduce problems associated with incomplete trajectories. Thirdly, the motion model parameters are estimated for each trajectory’s classification, and behavior patterns for trajectories are extracted. Finally, the difference between normal and abnormal behaviors can be distinguished.     

Quantitative object motion prediction by an ART2 and Madaline combined neural network

An ART2 and a Madaline combined neural network is applied to predicting object motions in dynamic environments. The ART2 network extracts a set of coherent patterns of the object motion by its self-organizing and unsupervised learning features. The identified patterns are directed to the Madaline network to generate a quantitative prediction of the future motion states. The method does not require any presumption of the mathematical models, and is applicable to a variety of situations.     

Motion-based behaviour learning, profiling and classification in the presence of anomalies

Techniques for understanding video object motion activity are becoming increasingly important with the widespread adoption of CCTV surveillance systems. Motion trajectories provide rich spatiotemporal information about an object's activity. This paper presents a novel technique for clustering and classification of motion. In the proposed motion learning system, trajectories are treated as time series and modelled using modified DFT (discrete fourier transform)-based coefficient feature space representation. A framework (iterative HSACT-LVQ (hierarchical semi-agglomerative clustering-learning vector quantization)) is proposed for learning of patterns in the presence of significant number of anomalies in training data. A novel modelling technique, referred to as m-Mediods, is also proposed that models the class containing n members with m Mediods. Once the m-Mediods-based model for all the classes have been learnt, the classification of new trajectories and anomaly detection can be performed by checking the closeness of said trajectory to the models of known classes. A mechanism based on agglomerative approach is proposed for anomaly detection. Our proposed techniques are validated using variety of simulated and complex real life trajectory data sets.     

Context in temporal sequence processing: a self-organizing approachand its application to robotics

A self-organizing neural net for learning and recall of complex temporal sequences is developed and applied to robot trajectory planning. We consider trajectories with both repeated and shared states. Both cases give rise to ambiguities during reproduction of stored trajectories which are resolved via temporal context information. Feedforward weights encode spatial features of the input trajectories, while the temporal order is learned by lateral weights through delayed Hebbian learning. After training, the net model operates in an anticipative fashion by always recalling the successor of the current input state. Redundancy in sequence representation improves noise and fault robustness. The net uses memory resources efficiently by reusing neurons that have previously stored repeated/shared states. Simulations have been carried out to evaluate the performance of the network in terms of trajectory reproduction, convergence time and memory usage, tolerance to fault and noise, and sensitivity to trajectory sampling rate. The results show that the model is fast, accurate, and robust. Its performance is discussed in comparison with other neural-networks models.     

A self-organizing HCMAC neural-network classifier

This paper presents a self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural-network classifier, which contains a self-organizing input space module and an HCMAC neural network. The conventional CMAC can be viewed as a basis function network (BFN) with supervised learning, and performs well in terms of its fast learning speed and local generalization capability for approximating nonlinear functions. However, the conventional CMAC has an enormous memory requirement for resolving high-dimensional classification problems, and its performance heavily depends on the approach of input space quantization. To solve these problems, this paper presents a novel supervised HCMAC neural network capable of resolving high-dimensional classification problems well. Also, in order to reduce what is often trial-and-error parameter searching for constructing memory allocation automatically, proposed herein is a self-organizing input space module that uses Shannon's entropy measure and the golden-section search method to appropriately determine the input space quantization according to the various distributions of training data sets. Experimental results indicate that the self-organizing HCMAC indeed has a fast learning ability and low memory requirement. It is a better performing network than the conventional CMAC for resolving high-dimensional classification problems. Furthermore, the self-organizing HCMAC classifier has a better classification ability than other compared classifiers.     

Trajectory generation and modulation using dynamic neural networks

Generation of desired trajectory behavior using neural networks involves a particularly challenging spatio-temporal learning problem. This paper introduces a novel solution, i.e., designing a dynamic system whose terminal behavior emulates a prespecified spatio-temporal pattern independently of its initial conditions. The proposed solution uses a dynamic neural network (DNN), a hybrid architecture that employs a recurrent neural network (RNN) in cascade with a nonrecurrent neural network (NRNN). The RNN generates a simple limit cycle, which the NRNN reshapes into the desired trajectory. This architecture is simple to train. A systematic synthesis procedure based on the design of relay control systems is developed for configuring an RNN that can produce a limit cycle of elementary complexity. It is further shown that a cascade arrangement of this RNN and an appropriately trained NRNN can emulate any desired trajectory behavior irrespective of its complexity. An interesting solution to the trajectory modulation problem, i.e., online modulation of the generated trajectories using external inputs, is also presented. Results of several experiments are included to demonstrate the capabilities and performance of the DNN in handling trajectory generation and modulation problems.     

Constrained self-organizing feature map to preserve feature extraction topology

In many classification problems, it is necessary to consider the specific location of an n-dimensional space from which features have been calculated. For example, considering the location of features extracted from specific areas of a two-dimensional space, as an image, could improve the understanding of a scene for a video surveillance system. In the same way, the same features extracted from different locations could mean different actions for a 3D HCI system. In this paper, we present a self-organizing feature map able to preserve the topology of locations of an n-dimensional space in which the vector of features have been extracted. The main contribution is to implicitly preserving the topology of the original space because considering the locations of the extracted features and their topology could ease the solution to certain problems. Specifically, the paper proposes the n-dimensional constrained self-organizing map preserving the input topology (nD-SOM-PINT). Features in adjacent areas of the n-dimensional space, used to extract the feature vectors, are explicitly in adjacent areas of the nD-SOM-PINT constraining the neural network structure and learning. As a study case, the neural network has been instantiate to represent and classify features as trajectories extracted from a sequence of images into a high level of semantic understanding. Experiments have been thoroughly carried out using the CAVIAR datasets (Corridor, Frontal and Inria) taken into account the global behaviour of an individual in order to validate the ability to preserve the topology of the two-dimensional space to obtain high-performance classification for trajectory classification in contrast of non-considering the location of features. Moreover, a brief example has been included to focus on validate the nD-SOM-PINT proposal in other domain than the individual trajectory. Results confirm the high accuracy of the nD-SOM-PINT outperforming previous methods aimed to classify the same datasets.

     

Parallel Implementation of a Machine Learning Algorithm on GPU

The capability for understanding data passes through the ability of producing an effective and fast classification of the information in a time frame that allows to keep and preserve the value of the information itself and its potential. Machine learning explores the study and construction of algorithms that can learn from and make predictions on data. A powerful tool is provided by self-organizing maps (SOM). The goal of learning in the self-organizing map is to cause different parts of the network to respond similarly to certain input patterns. Because of its time complexity, often using this method is a critical challenge. In this paper we propose a parallel implementation for the SOM algorithm, using parallel processor architecture, as modern graphics processing units by CUDA. Experimental results show improvements in terms of execution time, with a promising speed up, compared to the CPU version and the widely used package SOM_PAK.     

基于深度学习的GPS轨迹去匿名研究

移动互联网和LBS技术的高速发展使得位置服务提供商可以轻松收集到大量用户位置轨迹数据,近期研究表明,深度学习方法能够从轨迹数据集中提取出用户身份标识等隐私信息.然而现有工作主要针对社交网络采集的签到点轨迹,针对GPS轨迹的去匿名研究则较为缺乏.因此,对基于深度学习的GPS轨迹去匿名技术开展研究.首先提出一种GPS轨迹数...     

Adaptive computer-generated forces for simulator-based training

Simulator-based training is in constant pursuit of increasing level of realism. The transition from doctrine-driven computer-generated forces (CGF) to adaptive CGF represents one such effort. The use of doctrine-driven CGF is fraught with challenges such as modeling of complex expert knowledge and adapting to the trainees’ progress in real time. Therefore, this paper reports on how the use of adaptive CGF can overcome these challenges. Using a self-organizing neural network to implement the adaptive CGF, air combat maneuvering strategies are learned incrementally and generalized in real time. The state space and action space are extracted from the same hierarchical doctrine used by the rule-based CGF. In addition, this hierarchical doctrine is used to bootstrap the self-organizing neural network to improve learning efficiency and reduce model complexity. Two case studies are conducted. The first case study shows how adaptive CGF can converge to the effective air combat maneuvers against rule-based CGF. The subsequent case study replaces the rule-based CGF with human pilots as the opponent to the adaptive CGF. The results from these two case studies show how positive outcome from learning against rule-based CGF can differ markedly from learning against human subjects for the same tasks. With a better understanding of the existing constraints, an adaptive CGF that performs well against rule-based CGF and human subjects can be designed.     

How do you visit: Identifying addicts from large-scale transit records via scenario deep embedding

Identification of individuals based on transit modes is of great importance in user tracking systems. However, identifying users in real-life studies is not trivial owing to the following challenges: 1) activity data containing both temporal and spatial context are high-order and sparse; 2) traditional two-step classifiers depend on trajectory patterns as input features, which limits accuracy especially in the case of scattered and diverse data; 3) in some cases, there are few positive instances and they are difficult to detect. Therefore, approaches involving statistics-based or trajectory-based features do not work effectively. Deep learning methods also suffer from the problem of how to represent trajectory vectors for user classification. Here, we propose a novel end-to-end scenario-based deep learning method to address these challenges, based on the observation that individuals may visit the same place for different reasons. We first define a scenario using critical places and related trajectories. Next, we embed scenarios via path-based or graph-based approaches using extended embedding techniques. Finally, a two-level convolution neural network is constructed for the classification. Our model is applied to the problem of detection of addicts using transit records directly without feature engineering, based on real-life data collected from mobile devices. Based on constructed scenario with dense trajectories, our model outperforms classical classification approaches, anomaly detection methods, state-of-the-art sequential deep learning models, and graph neural networks. Moreover, we provide statistical analyses and intuitiveexplanations to interpret the characteristics of resident and addict mobility. Our method could be generalized to other trajectory-related tasks involving scattered and diverse data.

     

基于深度学习的多目标跟踪关联模型设计

近年来, 深度学习在计算机视觉领域的应用取得了突破性进展, 但基于深度学习的视频多目标跟踪(Multiple object tracking, MOT)研究却相对甚少, 而鲁棒的关联模型设计是基于检测的多目标跟踪方法的核心.本文提出一种基于深度神经网络和度量学习的关联模型:采用行人再识别(Person re-identification, Re-ID)领域中广泛使用的度量学习技术和卷积神经网络(Convolutional neural networks, CNNs)设计目标外观模型, 即利用三元组损失函数设计一个三通道卷积神经网络, 提取更具判别性的外观特征构建目标外观相似度; 再结合运动模型计算轨迹片间的关联概率.在关联策略上, 采用匈牙利算法, 首先以逐帧关联方式得到短小可靠的轨迹片集合, 再通过自适应时间滑动窗机制多级关联, 输出各目标最终轨迹.在2DMOT2015、MOT16公开数据集上的实验结果证明了所提方法的有效性, 与当前一些主流算法相比较, 本文方法取得了相当或者领先的跟踪效果.     

Associative learning method in a hypercolumn model

We propose an associatively learnable hypercolumn model (AHCM). A hyper-column model is a self-organized, competitive, and hierarchical multilayer neural network. It is derived from the neocognitron by replacing each S cell and C cell with a two-layer hierarchical self-organizing map. The HCM can recognize images with variant object size, position, orientation and spatial resolution. However, feature maps may integrate some features extracted in the lower layer even if the features are extracted from input data which belong to different categories. The learning algorithm of the HCM causes this problem because it is an unsupervised learning used by a self-organizing map. An associative learning method is therefore introduced, which is derived from the HCM by appending associative signals and associative weights to traditional input data and connection weights, respectively. The AHCM was applied to hand-shape recognition. We found that the AHCM could generate an appropriate feature map and higher recognition accuracy compared with the HCM. This work was presented in part at the 11th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006     

基于双Kohonen神经网络的Web用户访问模式挖掘算法

本文根据Kohonen自组织特征映射神经网络中学习阶段的性质,运用双Kohonen神经网络组合成新的自组织训练挖掘模型,先使用粗调整训练,加快模型学习速度,紧接着使用微调整训练,提高模型学习精度。实验结果表明,本文提出的双Kohonen神经网络挖掘模型,相对于标准Kohonen神经网络在训练速度和收敛效果上都有一定程度的提高,改善了聚类效果,为挖掘用户的多种兴趣提供了一种可行的方法。