A Chaos Theoretic Approach to Animal Activity Recognition

Sturm, Valentin; Efrosinin, Dmitry; Efrosinina, N.; Roland, Leonie; Iwersen, M.; Drillich, M.; Auer, Wolfgang

doi:10.1007/s10958-019-04199-9

Cited by 13 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The question remains as how to use this graphical information to classify each time episode as a particular state. Automatic classification of behavior from time-series using a chaos-theory approach is a relatively recent development and has been used for human motion and fatigue detection, electromyogram signals, and accelerometer data of calves, Drosophila, and mice; however, empirical applications remain extremely limited [16,21,22,29,30].…”

Section: Diurnal Signals and Attractor Parametersmentioning

confidence: 99%

“…Different features (or invariants) can be used to characterize reconstructed state-space; e.g., including correlation dimensions, approximate entropy, the Lyapunov exponent, Euclidean and Mahalanobis distances, and topological features [17,21,31,32]. However, there are neither straightforward criteria to be used in selecting them [14], nor guidance in relation to diving behavior, so we departed from the most basic considerations (see Materials and Methods and the Supporting Information).…”

Section: Diurnal Signals and Attractor Parametersmentioning

confidence: 99%

“…This can help in identifying recurrent dynamics and predominant states of diving behavior. However, in studies of animal behavior in general, and aquatic locomotion in particular, this potentially powerful tool has not yet been widely applied [21,22]. May 27, 2022 1/26…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Strange attractor of a narwhal (Monodon monoceros)

Podolskiy

Heide‐Jørgensen

2022

Preprint

View full text Add to dashboard Cite

Detecting structures within the continuous diving behavior of marine animals is challenging, and no universal framework is available. We captured such diverse structures using chaos theory. By applying time-delay embedding to exceptionally long dive records (83 d) from the narwhal, we reconstructed the state-space portrait. Using measures of chaos, we detected a diurnal pattern and its seasonal modulation, classified data, and found how sea-ice appearance shifts time budgets. There is more near-surface rest but deeper dives at solar noon, and more intense diving during twilight and at night but to shallower depths (likely following squid); sea-ice appearance reduces rest. The introduced geometrical approach is simple to implement and potentially helpful for mapping and labeling long-term behavioral data, identifying differences between individual animals and species, and detecting perturbations.

show abstract

Section: Diurnal Signals and Attractor Parametersmentioning

confidence: 99%

Section: Diurnal Signals and Attractor Parametersmentioning

confidence: 99%

See 1 more Smart Citation

Strange attractor of a narwhal (Monodon monoceros)

Podolskiy

Heide‐Jørgensen

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…At the same time, sheer volume of videos and images generated these days necessitate the need of an automatic action recognition system. Action recognition is useful in many applications including real-time surveillance [2][3], crowd behavior monitoring [4] [5], bio-mechanical analysis of actions for sports and medicine [6] [7], anomaly detection [8] [9], automatic video organization / tagging [10] [11], health care [12] [13], elder care [14] [15], child/animal monitoring [16] and video censoring [17].…”

Section: Introductionmentioning

confidence: 99%

Predicting Actions in Videos and Action-Based Segmentation Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

In this paper, we propose a technique to recognize multiple actions in a video using deep learning. The proposed approach is concerned with interpreting the overall context of a video and transforming it into one or more appropriate actions. In order to cope with multiple actions in a video, our proposed technique first determines the individual segments/shots in a video using intersections of color histograms. The segmented parts are then fed to the action recognition system comprising a combination of a Convolution Neural Network (CNN) and a Long-Short-Term Memory (LSTM) network trained on our action vocabulary. The segments are then labeled according to their predicted actions and a compact set of distinct actions is produced. Using the corpus generated by the shot detection phase, which includes the location of key frames in shots, and start/end timestamps of a shot, we can also perform video segmentation based on an action query. Hence, the proposed technique can be used for a number of tasks such as content censoring, on-demand scene retrieval, video summarizing, and query based scene/video retrieval, to name a few. The proposed technique also stands aprat from the existing approaches which either do not take into account the motion information for action prediction or do not perform action-based video segmentation. The experimental results presented in this paper show that the proposed technique not only finds the the complete set of actions present in the video, but can also find all the relevant parts in a video based on an action query.

show abstract

“…Each person has their own typical habits and activities. Therefore, it is not possible to predefine normal activity sequences, which has been done, for example, by Sturm et al (2019), or activity sequences, that represent exceptions. The model is built on the basis of observations, so it learns the daily routine independently.…”

Section: Introductionmentioning

confidence: 99%

A cyber-physical environment for detecting exceptional and dangerous human behavior in the home by sensors and its verification by computer simulation

Arbeiter¹,

Maier²,

Spöck

2020

Adaptive Behavior

View full text Add to dashboard Cite

Today aging of society is becoming increasingly important. Many people want to live at home as long as possible. Very often this leads to accidents at home, which are unnoticed for a long time and therefore cause severe complications. We propose a cyber-physical system consisting of sensors for motion, light, temperature, and so on, which monitors the behavior of elderly people but is non-invasive in the sense that the persons are not observed by a camera and must not wear certain sensors on their body. Unusual behavior or accidents are registered in-time by a change point detection algorithm based on Markov chains, which does not store any data with the exception of the last datum, so that also the integrity of the elderly people is preserved. For verification of this algorithm, a cyber-physical test environment has been programmed which allows to simulate human common and uncommon behavior in house during day and night. This simulation environment is based on behavior trees and decision theory. The verification results suggest that the implemented cyber-physical system for change point and anomaly detection could be successfully used in the real environment of elderly people to give them help in-time when an accident occurs.

show abstract

A Chaos Theoretic Approach to Animal Activity Recognition

Cited by 13 publications

References 14 publications

Strange attractor of a narwhal (Monodon monoceros)

Strange attractor of a narwhal (Monodon monoceros)

Predicting Actions in Videos and Action-Based Segmentation Using Deep Learning

A cyber-physical environment for detecting exceptional and dangerous human behavior in the home by sensors and its verification by computer simulation

Contact Info

Product

Resources

About