Time series classification (TSC) aims to predict the class label of a given time series. Modern applications such as appliance modelling require to model an abundance of long time series, which makes it difficult to use many state-of-the-art TSC techniques due to their high computational cost and lack of interpretable outputs. To address these challenges, we propose a novel TSC method: the Supervised Time Series Forest (STSF). STSF improves the classification efficiency by examining only a (set of) sub-series of the original time series, and its tree-based structure allows for interpretable outcomes. STSF adapts a top-down approach to search for relevant sub-series in three different time series representations prior to training any tree classifier, where the relevance of a sub-series is measured by feature ranking metrics (i.e., supervision signals). Experiments on extensive real datasets show that STSF achieves comparable accuracy to state-of-the-art TSC methods while being significantly more efficient, enabling TSC for long time series.
An area is k-covered if every point of the area is covered by at least k sensors. K-coverage is necessary for many applications, such as intrusion detection, data gathering, and object tracking. It is also desirable in situations where a stronger environmental monitoring capability is desired, such as military applications. In this paper, we study the problem of k-coverage in deterministic homogeneous deployments of sensors. We examine the three regular sensor deployments - triangular, square and hexagonal deployments - for k-coverage of the deployment area, for k ≥ 1. We compare the three regular deployments in terms of sensor density. For each deployment, we compute an upper bound and a lower bound on the optimal distance of sensors from each other that ensure k-coverage of the area. We present the results for each k from 1 to 20 and show that the required number of sensors to k-cover the area using uniform random deployment is approximately 3-10 times higher than regular deployments.
Modern sensor-equipped smartphones have attracted significant research interest in the pervasive community for recognizing and creating context-aware applications at a personal or community scale level. In this paper, we propose a proof of concept Do-Not-Disturb (DND) service that can a) determine a user's context relevant for DND service from the built-in smartphone sensors and b) correctly predict the DND status based on the given context such as being in a meeting, sleeping, or working at the office. In this preliminary study, we investigate whether sensor data can be clustered to represent user contexts. We use standard machine learning techniques to learn the relationship between a user's context and the corresponding DND status (available or unavailable). Given a user's current context, the DND service predicts a DND status and configures the mobile device accordingly. Our preliminary experiment demonstrates that the proposed system can achieve a prediction accuracy of up to 90% when trained with sufficient data.
This technical report presents a geometric approach on the formal description of ordering on curves through space. Curves are usually considered as topological mappings from parameter sets to space and not described in a geometric framework. In contrast, we introduce oriented curves in an axiomatic framework as geometric entities on the same level as points and straight lines. This account does not require any numerical information and therefore enables a qualitative characterization of oriented curves. Oriented curves can for instance be used to represent trajectories of moving objects. They are basically atemporal and therefore allow temporal as well as non-temporal interpretations. Since oriented curves need not to be straight, they provide a generalized notion of direction. This report contains the formal part of this enterprise including the axioms, definitions, theorems and proofs. The general framework and an application is described by Eschenbach, Habel & Kulik (1999).
Activity-Based ride-sharing is a new paradigm which enhances the current model based on fixed origins and destinations, namely trip-based ride-sharing. In this new model, a user issues a ride-sharing request with his origin and the activity he wants to perform at any convenient destination. Then, the system computes the travel plans and users will be suggested the optimal destinations, which may be common to many users. In this way, the set of possible destinations for each user is expanded and further distance savings can be made as we have already shown in our previous work [1, 3]. In this paper, we show Activity-Based ride-sharing in action through our web-service-based framework, which is able to suggest routes and meeting points for many users in a city-scale scenario.
This report describes the development and finalization of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL 2019), held in Chicago, Illinois, USA, November 5-8, 2019. The attendance for the 2019 conference was 397, the second highest in the history of ACM SIGSPATIAL. Historically, what is now the ACM SIGSPATIAL conference started as a series of workshops and symposia in 1993. Its aim was to promote the interdisciplinary discussions among researchers, developers, users, and practitioners and fostering research in all aspects of Geographic Information Systems --- hence the original workshop acronym ACM GIS. The focus was on novel systems based on geospatial data and knowledge. It continued its mission of providing a forum for original research results, addressing conceptual, design, and implementation aspects of geospatial data ranging from applications, user interfaces and visualization, to data storage, query processing, indexing and data mining. The conference is now the premier annual event of the ACM Special Interest Group on Spatial Information (ACM SIGSPATIAL).
Tool use has allowed humans to become one of the most successful species. However, tool-assisted foraging has also pushed many of our prey species to extinction or endangerment, a technology-driven process thought to be uniquely human. Here, we demonstrate that tool-assisted foraging on shellfish by long-tailed macaques (Macaca fascicularis) in Khao Sam Roi Yot National Park, Thailand, reduces prey size and prey abundance, with more pronounced effects where the macaque population size is larger. We compared availability, sizes and maturation stages of shellfish between two adjacent islands inhabited by different-sized macaque populations and demonstrate potential effects on the prey reproductive biology. We provide evidence that once technological macaques reach a large enough group size, they enter a feedback loop - driving shellfish prey size down with attendant changes in the tool sizes used by the monkeys. If this pattern continues, prey populations could be reduced to a point where tool-assisted foraging is no longer beneficial to the macaques, which in return may lessen or extinguish the remarkable foraging technology employed by these primates.
Following over 20 years of research on the climatic effects on biodiversity we now have strong evidence that climate change affects phenology, fitness, and distribution ranges of different taxa, including birds. Bird phenology likely responds to changes in local weather. It is also affected by climatic year-to-year variations on larger scales. Although such scale-related effects are common in ecology, most studies analyzing the effects of climate change were accomplished using climatic information on a single spatial scale. In this study, we aimed at determining the scale-dependent sensitivity of breeding phenology and success to climate change in a migratory passerine bird, the barn swallow (Hirundo rustica). For both annual broods, we investigated effects of local weather (local scale) and the North Atlantic Oscillation (NAO, large scale) on the timing of breeding and breeding success. Consistent with previous studies in migratory birds we found that barn swallows in Eastern Germany bred progressively earlier. At the same time, they showed reduced breeding success over time in response to recent climatic changes. Responses to climatic variation were observed on both local and large climatic scales, but they differed with respect to the ecological process considered. Specifically, we found that the timing of breeding was primarily influenced by large-scale NAO variations and to a lesser extent by local weather on the breeding grounds. Conversely, climatic conditions on the local scale affected breeding success, exclusively. The observed decrease in breeding success over years is likely a consequence of scale-related mismatches between climatic conditions during different breeding phases. This provides further evidence that a species' response of earlier breeding may not be enough to cope with climate change. Our results emphasize the importance of considering the response of ecological processes along different climatic scales in order to better understand the complexity of climate change effects on biodiversity.
Route planning in current route guidance systems is primarily based on the shortest path strategy (e.g., suggesting a path that minimizes the travel distance between source and destination) for an individual driver. A drawback of such an approach is that there is a high probability that many drivers, who share the same source and destination, follow the same route. This can lead to over-saturated road links. We propose a simple yet effective multiple path routing algorithm that addresses this limitation. The proposed algorithm augments the A* search algorithm with a randomization component, which helps to perturb the order of the searched nodes and to produce diversified routes for different drivers with the same source and destination. Our algorithm enables decentralized route allocations, i.e., each vehicle computes its own route without a central server. We validate the performance of the proposed algorithm through microscopic traffic simulation. Experiments for various traffic scenarios show that our algorithm achieves a good path diversification while reducing the average travel time compared to the traditional shortest path algorithm.
'/%3e%3c/defs%3e%3cpath fill='%23012169' d='M0 0h10080v5040H0z'/%3e%3cpath stroke='%23fff' stroke-width='.6' d='m0 0 6 3m0-3L0 3' clip-path='url(%23b)' transform='scale(840)'/%3e%3cpath stroke='%23e4002b' stroke-width='.4' d='m0 0 6 3m0-3L0 3' clip-path='url(%23c)' transform='scale(840)'/%3e%3cpath stroke='%23fff' stroke-width='840' d='M2520 0v2520M0 1260h5040'/%3e%3cpath stroke='%23e4002b' stroke-width='504' d='M2520 0v2520M0 1260h5040'/%3e%3cg fill='%23fff'%3e%3cuse xlink:href='%23d' x='2520' y='3780'/%3e%3cuse xlink:href='%23a' x='7560' y='4200'/%3e%3cuse xlink:href='%23a' x='6300' y='2205'/%3e%3cuse xlink:href='%23a' x='7560' y='840'/%3e%3cuse xlink:href='%23a' x='8680' y='1869'/%3e%3cuse xlink:href='%23e' x='8064' y='2730'/%3e%3c/g%3e%3c/svg%3e)
