Here is a list of publications somehow related to our problem.

Bible :)

  1. Numerical recipes in C

Animal illness prediction

  1. Similarity networks for classification: a case study in the Horse Colic problem from Lluís Belanche and Jerónimo Hernández
  2. Predicting Lameness in Sheep Activity Using Tri-Axial Acceleration Signals

Activity detection

  1. Validity and practical utility of accelerometry for the measurement of in-hand physical activity in horses
  2. Development of Equine Gait Recognition Algorithm
  3. A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data
  4. Creating a behavioural classification module for acceleration data: using a captive surrogate for difficult to observe species
  5. A User-Adaptive Algorithm for Activity Recognition Based on K-Means Clustering, Local Outlier Factor, and Multivariate Gaussian Distribution it looks like the problem they solve can be solved by thresholding magnitude value….But method is interesting if we want make clusterization “on board”…
  6. A Feature Selection-Based Framework for Human Activity Recognition Using Wearable Multimodal Sensors

Ballistocardiography

1.SHORT-TERM HEART RATE VARIABILITY AS A GENERAL INDICATOR OF HEALTH ESTIMATED BY BALLISTOCARDIOGRAPHY USING A HYDRAULIC BED SENSOR IN ELDER
2.Physiological Parameter Estimation Using a Head-mounted Wearable Device - this article has a good description of algoritm of pulse and breath rate extraction from accelerometer data. It was used as a base for horse heart rate estimation research

Patern recognition

  1. A new neural network approach for seismic event detection - should check of applicability to unusual activity detection during colic (paid article from IEEE)

Patents

  1. Mobile animal surveillance and distress monitoring NightWatch24 US Patent N9629340
  2. Supervision System of Evolution of a horse