Pattern Mining-Based Pig Behavior Analysis for Health and Welfare Monitoring

Abstract

The increasing popularity of pigs has prompted farmers to increase pig production to meet the growing demand. However, while the number of pigs is increasing, that of farm workers has been declining, making it challenging to perform various farm tasks, the most important among them being managing the pigs' health and welfare. This study proposes a pattern mining-based pig behavior analysis system to provide visualized information and behavioral patterns, assisting farmers in effectively monitoring and assessing pigs' health and welfare. The system consists of four modules: (1) data acquisition module for collecting pigs video; (2) detection and tracking module for localizing and uniquely identifying pigs, using tracking information to crop pig images; (3) pig behavior recognition module for recognizing pig behaviors from sequences of cropped images; and (4) pig behavior analysis module for providing visualized information and behavioral patterns to effectively help farmers understand and manage pigs. In the second module, we utilize ByteTrack, which comprises YOLOx as the detector and the BYTE algorithm as the tracker, while MnasNet and LSTM serve as appearance features and temporal information extractors in the third module. The experimental results show that the system achieved a multi-object tracking accuracy of 0.971 for tracking and an F1 score of 0.931 for behavior recognition, while also highlighting the effectiveness of visualization and pattern mining in helping farmers comprehend and manage pigs' health and welfare.

Keywords: association rule mining; data visualization; pig behavior analysis; pig behavior recognition; pig health and welfare; sequential pattern mining.

Figure 1

Overall structure of the pattern mining-based pig behavior analysis system.

Figure 2

Chord diagram which enables visualization and identification of the interrelationships among aggressive pigs.

Figure 3

Hexbin plot which enables visualization of the locations where aggressive behaviors occurred in the pigpen.

Figure 4

Pixel distance–time plot which enables visualization of the pigs’ movement patterns: (a) combined pixel distance–time plot for Pig1 and Pig3, (b) pixel distance–time plot for Pig1, and (c) pixel distance–time plot for Pig3.

Figure 5

Box plot illustrating the variations of the pigs’ aggressive behaviors.

Figure 6

Descriptive statistical analysis interface: proposed system screenshot.

Figure 7

Data mining interface: proposed system screenshot.