Considering how congestion will propagate in the near future, understanding traffic congestion propagation has become crucial in GPS navigation systems for providing users with a more accurate estimated time of arrival (ETA). However, providing the exact ETA during congestion is a challenge owing to the complex propagation process between roads and high uncertainty regarding the future behavior of the process. Recent studies have focused on finding frequent congestion propagation patterns and determining the propagation probabilities. By contrast, this study proposes a novel time delay estimation method for traffic congestion propagation between roads using lag-specific transfer entropy (TE). Nonlinear normalization with a sliding window is used to effectively reveal the causal relationship between the source and target time series in calculating the TE. Moreover, Markov bootstrap techniques were adopted to quantify the uncertainty in the time delay estimator. To the best of our knowledge, the time delay estimation method presented in this article is the first to determine the time delay between roads for any congestion propagation pattern. The proposed method was validated using simulated data as well as real user trajectory data obtained from a major GPS navigation system applied in South Korea.
相關內容
In the present work, we describe a framework for modeling how models can be built that integrates concepts and methods from a wide range of fields. The information schism between the real-world and that which can be gathered and considered by any individual information processing agent is characterized and discussed, followed by the presentation of a series of the adopted requisites while developing the modeling approach. The issue of mapping from datasets into models is subsequently addressed, as well as some of the respectively implied difficulties and limitations. Based on these considerations, an approach to meta modeling how models are built is then progressively developed. First, the reference M* meta model framework is presented, which relies critically in associating whole datasets and respective models in terms of a strict equivalence relation. Among the interesting features of this model are its ability to bridge the gap between data and modeling, as well as paving the way to an algebra of both data and models which can be employed to combine models into hierarchical manner. After illustrating the M* model in terms of patterns derived from regular lattices, the reported modeling approach continues by discussing how sampling issues, error and overlooked data can be addressed, leading to the $M^{<\epsilon>}$ variant, illustrated respectively to number theory. The situation in which the data needs to be represented in terms of respective probability densities is treated next, yielding the $M^{<\sigma>}$ meta model, which is then illustrated respectively to a real-world dataset (iris flowers data). Several considerations about how the developed framework can provide insights about data clustering, complexity, collaborative research, deep learning, and creativity are then presented, followed by overall conclusions.
During the past decade, many anomaly detection approaches have been introduced in different fields such as network monitoring, fraud detection, and intrusion detection. However, they require understanding of data pattern and often need a long off-line period to build a model or network for the target data. Providing real-time and proactive anomaly detection for streaming time series without human intervention and domain knowledge is highly valuable since it greatly reduces human effort and enables appropriate countermeasures to be undertaken before a disastrous damage, failure, or other harmful event occurs. However, this issue has not been well studied yet. To address it, this paper proposes RePAD, which is a Real-time Proactive Anomaly Detection algorithm for streaming time series based on Long Short-Term Memory (LSTM). RePAD utilizes short-term historic data points to predict and determine whether or not the upcoming data point is a sign that an anomaly is likely to happen in the near future. By dynamically adjusting the detection threshold over time, RePAD is able to tolerate minor pattern change in time series and detect anomalies either proactively or on time. Experiments based on two time series datasets collected from the Numenta Anomaly Benchmark demonstrate that RePAD is able to proactively detect anomalies and provide early warnings in real time without human intervention and domain knowledge.
The class of Gibbs point processes (GPP) is a large class of spatial point processes in the sense that they can model both clustered and repulsive point patterns. They are specified by their conditional intensity, which for a point pattern $\mathbf{x}$ and a location $u$, is roughly speaking the probability that an event occurs in an infinitesimal ball around $u$ given the rest of the configuration is $\mathbf{x}$. The most simple, natural and easiest to interpret class of models is the class of pairwise interaction point processes where the conditional intensity depends on the number of points and pairwise distances between them. Estimating this function non parametrically has almost never been considered in the literature. We tackle this question and propose an orthogonal series estimation procedure of the log pairwise interaction function. Under some conditions provided on the spatial GPP and on the basis system, we show that this orthogonal series estimator is consistent and asymptotically normal. The estimation procedure is simple, fast and completely data-driven. We show its efficiency through simulation experiments and we apply it to three datasets.
Accurate prediction of human movements is required to enhance the efficiency of physical human-robot interaction. Behavioral differences across various users are crucial factors that limit the prediction of human motion. Although recent neural network-based modeling methods have improved their prediction accuracy, most did not consider an effective adaptations to different users, thereby employing the same model parameters for all users. To deal with this insufficiently addressed challenge, we introduce a meta-learning framework to facilitate the rapid adaptation of the model to unseen users. In this study, we propose a model structure and a meta-learning algorithm specialized to enable fast user adaptation in predicting human movements in cooperative situations with robots. The proposed prediction model comprises shared and adaptive parameters, each addressing the user's general and individual movements. Using only a small amount of data from an individual user, the adaptive parameters are adjusted to enable user-specific prediction through a two-step process: initialization via a separate network and adaptation via a few gradient steps. Regarding the motion dataset that has 20 users collaborating with a robotic device, the proposed method outperforms existing meta-learning and non-meta-learning baselines in predicting the movements of unseen users.
Merging datafiles containing information on overlapping sets of entities is a challenging task in the absence of unique identifiers, and is further complicated when some entities are duplicated in the datafiles. Most approaches to this problem have focused on linking two files assumed to be free of duplicates, or on detecting which records in a single file are duplicates. However, it is common in practice to encounter scenarios that fit somewhere in between or beyond these two settings. We propose a Bayesian approach for the general setting of multifile record linkage and duplicate detection. We use a novel partition representation to propose a structured prior for partitions that can incorporate prior information about the data collection processes of the datafiles in a flexible manner, and extend previous models for comparison data to accommodate the multifile setting. We also introduce a family of loss functions to derive Bayes estimates of partitions that allow uncertain portions of the partitions to be left unresolved. The performance of our proposed methodology is explored through extensive simulations. Code implementing the methodology is available at //github.com/aleshing/multilink .
Deep learning based models have had great success in object detection, but the state of the art models have not yet been widely applied to biological image data. We apply for the first time an object detection model previously used on natural images to identify cells and recognize their stages in brightfield microscopy images of malaria-infected blood. Many micro-organisms like malaria parasites are still studied by expert manual inspection and hand counting. This type of object detection task is challenging due to factors like variations in cell shape, density, and color, and uncertainty of some cell classes. In addition, annotated data useful for training is scarce, and the class distribution is inherently highly imbalanced due to the dominance of uninfected red blood cells. We use Faster Region-based Convolutional Neural Network (Faster R-CNN), one of the top performing object detection models in recent years, pre-trained on ImageNet but fine tuned with our data, and compare it to a baseline, which is based on a traditional approach consisting of cell segmentation, extraction of several single-cell features, and classification using random forests. To conduct our initial study, we collect and label a dataset of 1300 fields of view consisting of around 100,000 individual cells. We demonstrate that Faster R-CNN outperforms our baseline and put the results in context of human performance.
Proximal Policy Optimization (PPO) is a highly popular model-free reinforcement learning (RL) approach. However, in continuous state and actions spaces and a Gaussian policy -- common in computer animation and robotics -- PPO is prone to getting stuck in local optima. In this paper, we observe a tendency of PPO to prematurely shrink the exploration variance, which naturally leads to slow progress. Motivated by this, we borrow ideas from CMA-ES, a black-box optimization method designed for intelligent adaptive Gaussian exploration, to derive PPO-CMA, a novel proximal policy optimization approach that can expand the exploration variance on objective function slopes and shrink the variance when close to the optimum. This is implemented by using separate neural networks for policy mean and variance and training the mean and variance in separate passes. Our experiments demonstrate a clear improvement over vanilla PPO in many difficult OpenAI Gym MuJoCo tasks.
Latest deep learning methods for object detection provide remarkable performance, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and imbalance of the associated training sets, characterized by few positive and a large number of negative examples (i.e. background). Proposed approaches are based on end-to-end learning by back-propagation [22] or kernel methods trained with Hard Negatives Mining on top of deep features [8]. These solutions are effective, but prohibitively slow for on-line applications. In this paper we propose a novel pipeline for object detection that overcomes this problem and provides comparable performance, with a 60x training speedup. Our pipeline combines (i) the Region Proposal Network and the deep feature extractor from [22] to efficiently select candidate RoIs and encode them into powerful representations, with (ii) the FALKON [23] algorithm, a novel kernel-based method that allows fast training on large scale problems (millions of points). We address the size and imbalance of training data by exploiting the stochastic subsampling intrinsic into the method and a novel, fast, bootstrapping approach. We assess the effectiveness of the approach on a standard Computer Vision dataset (PASCAL VOC 2007 [5]) and demonstrate its applicability to a real robotic scenario with the iCubWorld Transformations [18] dataset.
In this paper, a novel image moments based model for shape estimation and tracking of an object moving with a complex trajectory is presented. The camera is assumed to be stationary looking at a moving object. Point features inside the object are sampled as measurements. An ellipsoidal approximation of the shape is assumed as a primitive shape. The shape of an ellipse is estimated using a combination of image moments. Dynamic model of image moments when the object moves under the constant velocity or coordinated turn motion model is derived as a function for the shape estimation of the object. An Unscented Kalman Filter-Interacting Multiple Model (UKF-IMM) filter algorithm is applied to estimate the shape of the object (approximated as an ellipse) and track its position and velocity. A likelihood function based on average log-likelihood is derived for the IMM filter. Simulation results of the proposed UKF-IMM algorithm with the image moments based models are presented that show the estimations of the shape of the object moving in complex trajectories. Comparison results, using intersection over union (IOU), and position and velocity root mean square errors (RMSE) as metrics, with a benchmark algorithm from literature are presented. Results on real image data captured from the quadcopter are also presented.
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information over small clips to generate more robust frame predictions. We conduct extensive ablative experiments on the newly released multi-person video pose estimation benchmark, PoseTrack, to validate various design choices of our model. Our approach achieves an accuracy of 55.2% on the validation and 51.8% on the test set using the Multi-Object Tracking Accuracy (MOTA) metric, and achieves state of the art performance on the ICCV 2017 PoseTrack keypoint tracking challenge.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191