Piecewise linear approximation of sensor signals is a well-known technique in the fields of data Mining and Activity Recognition. In this context, several algorithms have been developed, some of them with the purpose ...
详细信息
Piecewise linear approximation of sensor signals is a well-known technique in the fields of data Mining and Activity Recognition. In this context, several algorithms have been developed, some of them with the purpose to be performed on resource constrained microcontroller architectures of wireless sensor nodes. While microcontrollers are usually constrained in computational power and memory resources, all state-of-the-art piecewise linear approximation techniques either need to buffer sensordata or have an execution time depending on the segment's length. In the paper at hand, we propose a novel piecewise linear approximation algorithm, with a constant computational complexity as well as a constant memory complexity. Our proposed algorithm's worst-case execution time is one to three orders of magnitude smaller and its average execution time is three to seventy times smaller compared to the state-of-the-art Piecewise Linear Approximation (PLA) algorithms in our experiments. In our evaluations, we show that our algorithm is time and memory efficient without sacrificing the approximation quality compared to other state-of-the-art piecewise linear approximation techniques, while providing a maximum error guarantee per segment, a small parameter space of only one parameter, and a maximum latency of one sample period plus its worst-case execution time.
We report in this paper on a wireless sensor network deployment at railway tracks to monitor and analyze the vibration patterns caused by trains passing by. We investigate in particular a system that relies on having ...
详细信息
ISBN:
(纸本)9780769550411
We report in this paper on a wireless sensor network deployment at railway tracks to monitor and analyze the vibration patterns caused by trains passing by. We investigate in particular a system that relies on having a distributed network of sensor nodes that individually contain efficient feature extraction algorithms and classifiers that fit the restricted hardware resources, rather than using few complex and specialized sensors. A feasibility study is described on the raw data obtained from a real-world deployment on one of Europe's busiest railroad sections, which was annotated with the help of video footage and contains vibration patterns of 186 trains. These trains were classified in 6 types by various methods, the best performing at an accuracy of 97%. The trains' length in wagons was estimated with a mean-squared error of 3.98. Visual inspection of the data shows further opportunities in the estimation of train speed and detection of worn-out cargo wheels.
We report in this paper on a wireless sensor network deployment at railway tracks to monitor and analyze the vibration patterns caused by trains passing by. We investigate in particular a system that relies on having ...
详细信息
ISBN:
(纸本)9781479902064
We report in this paper on a wireless sensor network deployment at railway tracks to monitor and analyze the vibration patterns caused by trains passing by. We investigate in particular a system that relies on having a distributed network of sensor nodes that individually contain efficient feature extraction algorithms and classifiers that fit the restricted hardware resources, rather than using few complex and specialized sensors. A feasibility study is described on the raw data obtained from a real-world deployment on one of Europe's busiest railroad sections, which was annotated with the help of video footage and contains vibration patterns of 186 trains. These trains were classified in 6 types by various methods, the best performing at an accuracy of 97%. The trains' length in wagons was estimated with a mean-squared error of 3.98. Visual inspection of the data shows further opportunities in the estimation of train speed and detection of worn-out cargo wheels.
Environmental monitoring applications are designed for supplying derived and often integrated information by tracking and analyzing phenomena. To determine the condition of a target place, they employ a geosensor netw...
详细信息
Environmental monitoring applications are designed for supplying derived and often integrated information by tracking and analyzing phenomena. To determine the condition of a target place, they employ a geosensor network to get the heterogeneous sensordata. To effectively handle a large volume of sensordata, applications need a dataabstraction model, which supports the summarized data representation by encapsulating raw data. For faster data processing to answer a user's queries with representative attributes of an abstracted model, we propose such a dataabstraction model, the Layered Slopes in Grid for sensor data abstraction (LSGSA), which is based on the SGSA. In a single grid-based layer for each sensor type, collected data is represented by slope directional vectors in two layered slopes, such as height and surface. To answer a user query in a central monitoring server, LSGSA is used to reduce the time needed to extract event features from raw sensordata as a preprocessing step for interpreting the observed data. The extracted features are used to understand the current data trends and the progress of a detected phenomenon without accessing raw sensordata.
Many sensor network applications observe trends over an area by regularly sampling slow-moving values such as humidity or air pressure (for example in habitat monitoring). Another well-published type of application ai...
详细信息
ISBN:
(纸本)9781424483891
Many sensor network applications observe trends over an area by regularly sampling slow-moving values such as humidity or air pressure (for example in habitat monitoring). Another well-published type of application aims at spotting sporadic events, such as sudden rises in temperature or the presence of methane, which are tackled by detection on the individual nodes. This paper focuses on a zone between these two types of applications, where phenomena that cannot be detected on the nodes need to be observed by relatively long sequences of sensor samples. An algorithm that stems from data mining is proposed that abstracts the raw sensordata on the node into smaller packet sizes, thereby minimizing the network traffic and keeping the essence of the information embedded in the data. Experiments show that, at the cost of slightly more processing power on the node, our algorithm performs a shape abstraction of the sensed time series which, depending on the nature of the data, can extensively reduce network traffic and nodes' power consumption.
Environmental observation applications are designed for monitoring phenomena using heterogeneous sensordata types and for providing derived and often integrated information. To effectively handle such a large variety...
详细信息
ISBN:
(纸本)9783540874720
Environmental observation applications are designed for monitoring phenomena using heterogeneous sensordata types and for providing derived and often integrated information. To effectively handle such a large variety of different sensors, both in scale and type and data volume, we propose a geosensorabstraction for large-scale geosensor networks. Our SGSA(Slope Grid for sensor data abstraction) represents collected data in single grid-based layers, and allows for summarizing the measured data in various integrated grid layers. Within each cell, a slope vector is used to represents the trend of the observed sensordata. This slope is used as a simplifying factor for processing queries over several sensor types. To handle dynamic sensordata, the proposed abstraction model also supports rapid data update by using a mapping table. This model can be utilized as a data representation model in various geosensor network applications.
暂无评论