Abstract. Detecting abnormal event from video sequences is an important problem in computer vision and pattern recognition and a large number of algorithms have been devised to tackle this problem. Previous state-based approaches all suffer from the problem of deciding the appropriate number of states and it is often difficult to do so except using a trial-and-error approach, which may be infeasible in real-world applications. Yet in this paper, we have proposed a more accurate and flexible algorithm for abnormal event detection from video sequences. Our three-phase approach first builds a set of weak classifiers using Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), and then proposes an ensemble learning algorithm to filter out abnormal events. In the final phase, we will derive abnormal activity models from the normal activity model to reduce the FP (False Positive) rate in an unsupervised manner. The main advantage of our algorithm over previous ones is to naturally capture the underlying feature in abnormal event detection via HDP-HMM. Experimental results on a real-world video sequence dataset have shown the effectiveness of our algorithm. 1

Detecting abnormal activities from sensor readings is an important research problem in activity recognition. A number of different algorithms have been proposed in the past to tackle this problem. Many of the previous state-based approaches suffer from the problem of failing to decide the appropriate number of states, which are difficult to find through a trial-and-error approach, in real-world applications. In this paper, we propose an accurate and flexible framework for abnormal activity recognition from sensor readings that involves less human tuning of model parameters. Our approach first applies a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), which supports an infinite number of states, to automatically find an appropriate number of states. We incorporate a Fisher Kernel into the One-Class Support Vector Machine (OCSVM) model to filter out the activities that are likely to be normal. Finally, we derive an abnormal activity model from the normal activity models to reduce false positive rate in an unsupervised manner. Our main contribution is that our proposed HDP-HMM models can decide the appropriate number of states automatically, and that by incorporating a Fisher Kernel into the OCSVM model, we can combine the advantages from generative model and discriminative model. We demonstrate the effectiveness of our approach by using several real-world datasets to test our algorithm’s performance. 1

Abstract—The machine learning and pervasive sensing technologies found in smart homes offer unprecedented opportunities for providing health monitoring and assistance to individuals experiencing difficulties living independently at home. In order to monitor the functional health of smart home residents, we need to design technologies that recognize and track activities that people normally perform as part of their daily routines. Although approaches do exist for recognizing activities, the approaches are applied to activities that have been pre-selected and for which labeled training data is available. In contrast, we introduce an automated approach to activity tracking that identifies frequent activities that naturally occur in an individual’s routine. With this capability we can then track the occurrence of regular activities to monitor functional health and to detect changes in an individual’s patterns and lifestyle. In this paper we describe our activity mining and tracking approach and validate our algorithms on data collected in physical smart environments.

Abstract—We present an activity-recognition system for assisted living applications and smart homes. While existing systems tend to rely on expensive computation of comparatively largedimension data sets, ours leverages information from a small number of fundamentally different sensor measurements that provide context information pertaining the person’s location, and action information by observing the motion of the body and arms. Camera nodes are placed on the ceiling to track people in the environment, and place them in the context of a building map where areas and objects of interest are premarked. Additionally, a single inertial sensor node is placed on the subject’s arm to infer arm pose, heading and motion frequency using an accelerometer, gyroscope and magnetometer. These four measurements are parsed using a lightweight hierarchy of finite state machines, yielding recognition rates with high precision and recall values (0.92 and 0.93, respectively). I.

March 2009This work was carried out under the supervision of Prof. Gal A. Kaminka,

Abstract — The prevalence of obesity is a growing, worldwide health concern. Self-monitoring of eating consumption is widely recognized as a necessity for weight loss. In this paper we describe a novel method for automated monitoring of eating. Our method uses a single sensor that is worn on the wrist, similar in form to a watch. Wrist orientation was captured at a rate of 60 Hz for an entire day while four subjects conducted their natural daily routine. In our first experiment, we manually segmented the wrist motion data according to task logs kept by the subjects, and developed an algorithm to classify the tasks, achieving an accuracy of 91%. In our second experiment, we automatically segmented the wrist motion data in order to detect eating sessions, achieving a detection accuracy of 82%. Our methods will enable new opportunities in the study of dietetics, weight loss and management, nutrition, and health monitoring.

Abstract—Providing accurate and opportune information on people’s activities and behaviors is one of the most important tasks in pervasive computing. Innumerable applications can be visualized, for instance, in medical, security, entertainment, and tactical scenarios. Despite human activity recognition (HAR) being an active field for more than a decade, there are still key aspects that, if addressed, would constitute a significant turn in the way people interact with mobile devices. This paper surveys the state of the art in HAR based on wearable sensors. A general architecture is first presented along with a description of the main components of any HAR system. We also propose a twolevel taxonomy in accordance to the learning approach (either supervised or semi-supervised) and the response time (either offline or online). Then, the principal issues and challenges are discussed, as well as the main solutions to each one of them. Twenty eight systems are qualitatively evaluated in terms of recognition performance, energy consumption, obtrusiveness, and flexibility, among others. Finally, we present some open problems and ideas that, due to their high relevance, should be addressed in future research. Index Terms—Human-centric sensing; machine learning; mobile applications; context awareness. I.