arXiv subjects

Bernhard Sick

Publications and source records attributed to Bernhard Sick.

104 records · Page 6Linked to original sources

arXiv2018

Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure

In future traffic scenarios, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation based on data or information exchange. This article presents an approach to cooperative tracking of cyclists using smart devices and infrastructure-based sensors. A smart device is carried by the cyclists and an intersection is equipped with a wide angle stereo camera system. Two tracking models are presented and compared. The first model is based on the stereo camera system detections only, whereas the second model cooperatively combines the camera based detections with velocity and yaw rate data provided by the smart device. Our aim is to overcome limitations of tracking approaches based on single data sources. We show in numerical evaluations on scenes where cyclists are starting or turning right that the cooperation leads to an improvement in both the ability to keep track of a cyclist and the accuracy of the track particularly when it comes to occlusions in the visual system. We, therefore, contribute to the safety of vulnerable road users in future traffic.

cs.CY↗

arXiv2018

A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generation

In this article, we propose a novel ensemble technique with a multi-scheme weighting based on a technique called coopetitive soft gating. This technique combines both, ensemble member competition and cooperation, in order to maximize the overall forecasting accuracy of the ensemble. The proposed algorithm combines the ideas of multiple ensemble paradigms (power forecasting model ensemble, weather forecasting model ensemble, and lagged ensemble) in a hierarchical structure. The technique is designed to be used in a flexible manner on single and multiple weather forecasting models, and for a variety of lead times. We compare the technique to other power forecasting models and ensemble techniques with a flexible number of weather forecasting models, which can have the same, or varying forecasting horizons. It is shown that the model is able to outperform those models on a number of publicly available data sets. The article closes with a discussion of properties of the proposed model which are relevant in its application.

stat.AP↗

arXiv2018

Highly Automated Learning for Improved Active Safety of Vulnerable Road Users

Highly automated driving requires precise models of traffic participants. Many state of the art models are currently based on machine learning techniques. Among others, the required amount of labeled data is one major challenge. An autonomous learning process addressing this problem is proposed. The initial models are iteratively refined in three steps: (1) detection and context identification, (2) novelty detection and active learning and (3) online model adaption.

cs.AI↗

arXiv2018

Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning

Avoiding collisions with vulnerable road users (VRUs) using sensor-based early recognition of critical situations is one of the manifold opportunities provided by the current development in the field of intelligent vehicles. As especially pedestrians and cyclists are very agile and have a variety of movement options, modeling their behavior in traffic scenes is a challenging task. In this article we propose movement models based on machine learning methods, in particular artificial neural networks, in order to classify the current motion state and to predict the future trajectory of VRUs. Both model types are also combined to enable the application of specifically trained motion predictors based on a continuously updated pseudo probabilistic state classification. Furthermore, the architecture is used to evaluate motion-specific physical models for starting and stopping and video-based pedestrian motion classification. A comprehensive dataset consisting of 1068 pedestrian and 494 cyclist scenes acquired at an urban intersection is used for optimization, training, and evaluation of the different models. The results show substantial higher classification rates and the ability to earlier recognize motion state changes with the machine learning approaches compared to interacting multiple model (IMM) Kalman Filtering. The trajectory prediction quality is also improved for all kinds of test scenes, especially when starting and stopping motions are included. Here, 37\% and 41\% lower position errors were achieved on average, respectively.

cs.CV↗

arXiv2018

Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network

In this article, we present a novel approach to detect starting motions of cyclists in real world traffic scenarios based on Motion History Images (MHIs). The method uses a deep Convolutional Neural Network (CNN) with a residual network architecture (ResNet), which is commonly used in image classification and detection tasks. By combining MHIs with a ResNet classifier and performing a frame by frame classification of the MHIs, we are able to detect starting motions in image sequences. The detection is performed using a wide angle stereo camera system at an urban intersection. We compare our algorithm to an existing method to detect movement transitions of pedestrians that uses MHIs in combination with a Histograms of Oriented Gradients (HOG) like descriptor and a Support Vector Machine (SVM), which we adapted to cyclists. To train and evaluate the methods a dataset containing MHIs of 394 cyclist starting motions was created. The results show that both methods can be used to detect starting motions of cyclists. Using the SVM approach, we were able to safely detect starting motions 0.506 s on average after the bicycle starts moving with an F1-score of 97.7%. The ResNet approach achieved an F1-score of 100% at an average detection time of 0.144 s. The ResNet approach outperformed the SVM approach in both robustness against false positive detections and detection time.

cs.CV↗

arXiv2017

Self-Adaptation of Activity Recognition Systems to New Sensors

Traditional activity recognition systems work on the basis of training, taking a fixed set of sensors into account. In this article, we focus on the question how pattern recognition can leverage new information sources without any, or with minimal user input. Thus, we present an approach for opportunistic activity recognition, where ubiquitous sensors lead to dynamically changing input spaces. Our method is a variation of well-established principles of machine learning, relying on unsupervised clustering to discover structure in data and inferring cluster labels from a small number of labeled dates in a semi-supervised manner. Elaborating the challenges, evaluations of over 3000 sensor combinations from three multi-user experiments are presented in detail and show the potential benefit of our approach.

cs.CV↗

arXiv2017

Organic Computing in the Spotlight

Organic Computing is an initiative in the field of systems engineering that proposed to make use of concepts such as self-adaptation and self-organisation to increase the robustness of technical systems. Based on the observation that traditional design and operation concepts reach their limits, transferring more autonomy to the systems themselves should result in a reduction of complexity for users, administrators, and developers. However, there seems to be a need for an updated definition of the term "Organic Computing", of desired properties of technical, organic systems, and the objectives of the Organic Computing initiative. With this article, we will address these points.

cs.MA↗

arXiv2016

Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data

In our today's information society more and more data emerges, e.g.~in social networks, technical applications, or business applications. Companies try to commercialize these data using data mining or machine learning methods. For this purpose, the data are categorized or classified, but often at high (monetary or temporal) costs. An effective approach to reduce these costs is to apply any kind of active learning (AL) methods, as AL controls the training process of a classifier by specific querying individual data points (samples), which are then labeled (e.g., provided with class memberships) by a domain expert. However, an analysis of current AL research shows that AL still has some shortcomings. In particular, the structure information given by the spatial pattern of the (un)labeled data in the input space of a classification model (e.g.,~cluster information), is used in an insufficient way. In addition, many existing AL techniques pay too little attention to their practical applicability. To meet these challenges, this article presents several techniques that together build a new approach for combining AL and semi-supervised learning (SSL) for support vector machines (SVM) in classification tasks. Structure information is captured by means of probabilistic models that are iteratively improved at runtime when label information becomes available. The probabilistic models are considered in a selection strategy based on distance, density, diversity, and distribution (4DS strategy) information for AL and in a kernel function (Responsibility Weighted Mahalanobis kernel) for SVM. The approach fuses generative and discriminative modeling techniques. With 20 benchmark data sets and with the MNIST data set it is shown that our new solution yields significantly better results than state-of-the-art methods.

stat.ML↗

arXiv2016

Variational Bayesian Inference for Hidden Markov Models With Multivariate Gaussian Output Distributions

Hidden Markov Models (HMM) have been used for several years in many time series analysis or pattern recognitions tasks. HMM are often trained by means of the Baum-Welch algorithm which can be seen as a special variant of an expectation maximization (EM) algorithm. Second-order training techniques such as Variational Bayesian Inference (VI) for probabilistic models regard the parameters of the probabilistic models as random variables and define distributions over these distribution parameters, hence the name of this technique. VI can also bee regarded as a special case of an EM algorithm. In this article, we bring both together and train HMM with multivariate Gaussian output distributions with VI. The article defines the new training technique for HMM. An evaluation based on some case studies and a comparison to related approaches is part of our ongoing work.

cs.LG↗

arXiv2016

Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers

After data selection, pre-processing, transformation, and feature extraction, knowledge extraction is not the final step in a data mining process. It is then necessary to understand this knowledge in order to apply it efficiently and effectively. Up to now, there is a lack of appropriate techniques that support this significant step. This is partly due to the fact that the assessment of knowledge is often highly subjective, e.g., regarding aspects such as novelty or usefulness. These aspects depend on the specific knowledge and requirements of the data miner. There are, however, a number of aspects that are objective and for which it is possible to provide appropriate measures. In this article we focus on classification problems and use probabilistic generative classifiers based on mixture density models that are quite common in data mining applications. We define objective measures to assess the informativeness, uniqueness, importance, discrimination, representativity, uncertainty, and distinguishability of rules contained in these classifiers numerically. These measures not only support a data miner in evaluating results of a data mining process based on such classifiers. As we will see in illustrative case studies, they may also be used to improve the data mining process itself or to support the later application of the extracted knowledge.

cs.LG↗

arXiv2016

Detecting Novel Processes with CANDIES -- An Holistic Novelty Detection Technique based on Probabilistic Models

In this article, we propose CANDIES (Combined Approach for Novelty Detection in Intelligent Embedded Systems), a new approach to novelty detection in technical systems. We assume that in a technical system several processes interact. If we observe these processes with sensors, we are able to model the observations (samples) with a probabilistic model, where, in an ideal case, the components of the parametric mixture density model we use, correspond to the processes in the real world. Eventually, at run-time, novel processes emerge in the technical systems such as in the case of an unpredictable failure. As a consequence, new kinds of samples are observed that require an adaptation of the model. CANDIES relies on mixtures of Gaussians which can be used for classification purposes, too. New processes may emerge in regions of the models' input spaces where few samples were observed before (low-density regions) or in regions where already many samples were available (high-density regions). The latter case is more difficult, but most existing solutions focus on the former. Novelty detection in low- and high-density regions requires different detection strategies. With CANDIES, we introduce a new technique to detect novel processes in high-density regions by means of a fast online goodness-of-fit test. For detection in low-density regions we combine this approach with a 2SND (Two-Stage-Novelty-Detector) which we presented in preliminary work. The properties of CANDIES are evaluated using artificial data and benchmark data from the field of intrusion detection in computer networks, where the task is to detect new kinds of attacks.

cs.LG↗

arXiv2015

A New Vision of Collaborative Active Learning

Active learning (AL) is a learning paradigm where an active learner has to train a model (e.g., a classifier) which is in principal trained in a supervised way, but in AL it has to be done by means of a data set with initially unlabeled samples. To get labels for these samples, the active learner has to ask an oracle (e.g., a human expert) for labels. The goal is to maximize the performance of the model and to minimize the number of queries at the same time. In this article, we first briefly discuss the state of the art and own, preliminary work in the field of AL. Then, we propose the concept of collaborative active learning (CAL). With CAL, we will overcome some of the harsh limitations of current AL. In particular, we envision scenarios where an expert may be wrong for various reasons, there might be several or even many experts with different expertise, the experts may label not only samples but also knowledge at a higher level such as rules, and we consider that the labeling costs depend on many conditions. Moreover, in a CAL process human experts will profit by improving their own knowledge, too.

cs.LG↗

arXiv2015

The Responsibility Weighted Mahalanobis Kernel for Semi-Supervised Training of Support Vector Machines for Classification

Kernel functions in support vector machines (SVM) are needed to assess the similarity of input samples in order to classify these samples, for instance. Besides standard kernels such as Gaussian (i.e., radial basis function, RBF) or polynomial kernels, there are also specific kernels tailored to consider structure in the data for similarity assessment. In this article, we will capture structure in data by means of probabilistic mixture density models, for example Gaussian mixtures in the case of real-valued input spaces. From the distance measures that are inherently contained in these models, e.g., Mahalanobis distances in the case of Gaussian mixtures, we derive a new kernel, the responsibility weighted Mahalanobis (RWM) kernel. Basically, this kernel emphasizes the influence of model components from which any two samples that are compared are assumed to originate (that is, the "responsible" model components). We will see that this kernel outperforms the RBF kernel and other kernels capturing structure in data (such as the LAP kernel in Laplacian SVM) in many applications where partially labeled data are available, i.e., for semi-supervised training of SVM. Other key advantages are that the RWM kernel can easily be used with standard SVM implementations and training algorithms such as sequential minimal optimization, and heuristics known for the parametrization of RBF kernels in a C-SVM can easily be transferred to this new kernel. Properties of the RWM kernel are demonstrated with 20 benchmark data sets and an increasing percentage of labeled samples in the training data.

cs.LG↗

arXiv2012

Lower Bound Bayesian Networks - An Efficient Inference of Lower Bounds on Probability Distributions in Bayesian Networks

We present a new method to propagate lower bounds on conditional probability distributions in conventional Bayesian networks. Our method guarantees to provide outer approximations of the exact lower bounds. A key advantage is that we can use any available algorithms and tools for Bayesian networks in order to represent and infer lower bounds. This new method yields results that are provable exact for trees with binary variables, and results which are competitive to existing approximations in credal networks for all other network structures. Our method is not limited to a specific kind of network structure. Basically, it is also not restricted to a specific kind of inference, but we restrict our analysis to prognostic inference in this article. The computational complexity is superior to that of other existing approaches.

cs.AI↗