Window Size Impact in Human Activity Recognition

@article{Baos2014WindowSI,
  title={Window Size Impact in Human Activity Recognition},
  author={Oresti Ba{\~n}os and Juan Manuel G{\'a}lvez and Miguel Damas and H{\'e}ctor Pomares and Ignacio Rojas},
  journal={Sensors (Basel, Switzerland)},
  year={2014},
  volume={14},
  pages={6474 - 6499}
}
Signal segmentation is a crucial stage in the activity recognition process; however, this has been rarely and vaguely characterized so far. [...] Key Result The study, specifically intended for on-body activity recognition systems, further provides designers with a set of guidelines devised to facilitate the system definition and configuration according to the particular application requirements and target activities.Expand
Investigation on the Effect of Different Window Size in Segmentation for Common Sport Activity
TLDR
It was found that 2.5 seconds window size represents the best trade-off in recognition of common sports activity, with an obtained accuracy above 90% and the preferably employed window size in detecting thecommon sports activity is determined. Expand
Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer
TLDR
A novel approach to activity signal segmentation for physical activity recognition where the window size is adaptively adjusted according to the probability of the signal belongs to a particular activity to achieve the most effective segmentation. Expand
Multiwindow Fusion for Wearable Activity Recognition
TLDR
This work proposes the use of multiple recognition systems operating on multiple window sizes and employs a weighted decision fusion mechanism to fairly leverage the potential yielded by each recognition system based on the target activity set. Expand
Basic Structure for Human Activity Recognition Systems: Preprocessing and Segmentation
TLDR
The challenges regarding the selection of window length, window type, choosing overlapping percentage, and the relation between window duration and performance have been investigated in the end. Expand
Hierarchical Signal Segmentation and Classification for Accurate Activity Recognition
TLDR
The paper presents the techniques employed in the team's (The Drifters) submission to the SHL recognition challenge, and proposes a hierarchical signal segmentation approach to deal with the problem of fixed-size windows. Expand
Segmentation and Recognition of Basic and Transitional Activities for Continuous Physical Human Activity
TLDR
A systematic human activity recognition method to recognize basic activities (BA) and transitional activities (TA) in a continuous sensor data stream and can deliver high accuracy with all activities considered is proposed and implemented. Expand
Dynamic sliding window method for physical activity recognition using a single tri-axial accelerometer
Previous studies on physical activity recognition have utilized various fixed window sizes for signal segmentation selected based on past experiments and hardware limitations. Specifically, there isExpand
Time Analysis in Human Activity Recognition
TLDR
This paper evaluates several strategies to combine sub-window information inside a window, obtaining important improvements for long windows and a state-of-the-art human activity recognition system based on Convolutional Neural Networks (CNNs). Expand
Varying behavior of different window sizes on the classification of static and dynamic physical activities from a single accelerometer.
TLDR
Differences in recognition accuracy for each activity highlight the utility of developing adaptive segmentation criteria, based on the duration of the activities. Expand
On specialized window lengths and detector based human activity recognition
TLDR
This paper proposes a method that optimizes the window length - individually for each target activity - based on a generic window length and combines individually optimized activity detectors into an Ensemble based recognition approach. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 96 REFERENCES
Parameter exploration for response time reduction in accelerometer-based activity recognition
TLDR
The proposed method can reduce the amount of calculation, achieve both high recognition accuracy and short response time, and output the recognition results in consistent times to reduce the jitter of response time. Expand
Fall Detection and Activity Recognition with Machine Learning
TLDR
The machine learning approach to activity recognition to be used in the Confidence project is described, where the attributes characterizing the user’s behavior and a machine learning algorithm must be selected. Expand
Human activity recognition based on a sensor weighting hierarchical classifier
TLDR
This paper presents a fusion classification methodology which takes into account the potential of the individual decisions yielded at both activity and sensor classification levels, and systematically outperforms the results obtained by traditional multiclass models which otherwise may require a high-dimensional feature space to acquire a similar performance. Expand
Daily living activity recognition based on statistical feature quality group selection
TLDR
Satisfactory results are achieved in both laboratory and semi-naturalistic activity living datasets for real problems using several classification models, thus proving that any body sensor location can be suitable to define a simple one-feature-based recognition system, with particularly remarkable accuracy and applicability in the case of the wrist. Expand
Activity Recognition from User-Annotated Acceleration Data
TLDR
This is the first work to investigate performance of recognition algorithms with multiple, wire-free accelerometers on 20 activities using datasets annotated by the subjects themselves, and suggests that multiple accelerometers aid in recognition. Expand
Sensor-Based Activity Recognition
TLDR
A comprehensive survey to examine the development and current status of various aspects of sensor-based activity recognition, making a primary distinction in this paper between data-driven and knowledge-driven approaches. Expand
Scalable Recognition of Daily Activities with Wearable Sensors
TLDR
This work records a realistic 10h data set and analyzes the performance of four different algorithms for the recognition of both low- and high-level activities, and suggests that the Recognition of high- level activities can be achieved with the same algorithms as therecognition of low-level Activities. Expand
Analyzing features for activity recognition
TLDR
This paper presents a systematic analysis of features computed from a real-world data set and shows how the choice of feature and the window length over which the feature is computed affects the recognition rates for different activities. Expand
Discriminative Temporal Smoothing for Activity Recognition from Wearable Sensors
TLDR
A novel sequential learning method is proposed that combines discriminative learning of individual input-output mappings using support vector machines (SVM) with generative learning to smooth temporal time-dependent activity sequences with a trained hidden Markov model (HMM) type transition probability matrix. Expand
A Survey on Human Activity Recognition using Wearable Sensors
TLDR
The state of the art in HAR based on wearable sensors is surveyed and a two-level taxonomy in accordance to the learning approach and the response time is proposed. Expand
...
1
2
3
4
5
...