Abstract
Precision Swine Farming has the potential to directly benefit swine health and industry profit by automatically monitoring the growth and health of pigs. We introduce the first system to use structural vibration to track animals and the first system for automated characterization of piglet group activities, including nursing, sleeping, and active times. PigSense uses physical knowledge of the structural vibration characteristics caused by pig-activity-induced load changes to recognize different behaviors of the sow and piglets. For our system to survive the harsh environment of the farrowing pen for three months, we designed simple, durable sensors for physical fault tolerance, then installed many of them, pooling their data to achieve algorithmic fault tolerance even when some do stop working. The key focus of this work was to create a robust system that can withstand challenging environments, has limited installation and maintenance requirements, and uses domain knowledge to precisely detect a variety of swine activities in noisy conditions while remaining flexible enough to adapt to future activities and applications. We provided an extensive analysis and evaluation of all-round swine activities and scenarios from our one-year field deployment across two pig farms in Thailand and the USA. To help assess the risk of crushing, farrowing sicknesses, and poor maternal behaviors, PigSense achieves an average of 97.8% and 94% for sow posture and motion monitoring, respectively, and an average of 96% and 71% for ingestion and excretion detection. To help farmers monitor piglet feeding, starvation, and illness, PigSense achieves an average of 87.7%, 89.4%, and 81.9% in predicting different levels of nursing, sleeping, and being active, respectively. In addition, we show that our monitoring of signal energy changes allows the prediction of farrowing in advance, as well as status tracking during the farrowing process and on the occasion of farrowing issues. Furthermore, PigSense also predicts the daily pattern and weight gain in the lactation cycle with 89% accuracy, a metric that can be used to monitor the piglets’ growth progress over the lactation cycle.
- [1] . 2019. Monitoring and control system approach for native threatened species. In Proceedings of the International Conference on Information Systems and Software Technologies (ICI2ST’19). IEEE, 85–91.Google ScholarCross Ref
- [2] . 2007. Maternal behavior in pigs. Horm. Behav. 52, 1 (2007), 78–85.Google ScholarCross Ref
- [3] . 2008. VoxNet: An interactive, rapidly-deployable acoustic monitoring platform. In Proceedings of the International Conference on Information Processing in Sensor Networks (IPSN’08). 371–382.
DOI: Google ScholarDigital Library - [4] . 2007. Piglet survival in early lactation: A review. J. Anim. Veterin. Adv. 6, 1 (2007).Google Scholar
- [5] . 2006. A smart and passive floor-vibration based fall detector for elderly. In Proceedings of the 2nd International Conference on Information & Communication Technologies. IEEE, 1003–1007.Google ScholarCross Ref
- [6] . 2019. Dependable sensing system for pig farming. In Proceedings of the IEEE Global Conference on Internet of Things (GCIoT’19). IEEE, 1–7.Google ScholarCross Ref
- [7] . 1984. Clinical study of mastitis-metritis-agalactia in sows in Illinois. J. Amer. Veterin. Med. Assoc. 185, 1 (1984), 70–73.Google Scholar
- [8] , , , and (Eds.). 2019. MQTT Version 5.0. OASIS Standard. Retrieved from https://docs.oasis-open.org/mqtt/mqtt/v5.0/os/mqtt-v5.0-os.docx.Google Scholar
- [9] . 2011. Genetic and environmental effects on piglet survival and maternal behaviour of the farrowing sow. Appl. Anim. Behav. Sci. 130, 1-2 (2011), 28–41.Google ScholarCross Ref
- [10] . 2021. PigNet: Failure-tolerant pig activity monitoring system using structural vibration. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week’21). 328–340.Google ScholarDigital Library
- [11] . 2018. VVRRM: Vehicular Vibration-based heart RR-interval monitoring system. In Proceedings of the 19th International Workshop on Mobile Computing Systems & Applications. ACM, 37–42.Google ScholarDigital Library
- [12] . 2020. OAC: Overlapping office activity classification through IoT-sensed structural vibration. In Proceedings of the IEEE/ACM 5th International Conference on Internet-of-Things Design and Implementation (IoTDI’20). IEEE, 216–222.Google ScholarCross Ref
- [13] . 2008. CITRIC: A low-bandwidth wireless camera network platform. In Proceedings of the 2nd ACM/IEEE International Conference on Distributed Smart Cameras. IEEE, 1–10.Google ScholarCross Ref
- [14] . 2021. MassHog: Weight-sensitive occupant monitoring for pig pens using actuated structural vibrations. In Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the ACM International Symposium on Wearable Computers (UbiComp’21). Association for Computing Machinery, New York, NY, 600–605.
DOI: Google ScholarDigital Library - [15] . 1983. Customer installability of computer systems. Proc. Hum. Fact. Soc. Ann. Meet. 27, 6 (
Oct. 1983), 501–504.DOI: Google ScholarCross Ref - [16] . 2020. Evaluation of low-cost depth cameras for agricultural applications. Comput. Electron. Agric. 173 (2020), 105394.Google ScholarCross Ref
- [17] . 2017. COWLAR The smart collar for cows. Retrieved from http://www.cowlar.com/index.htm.Google Scholar
- [18] . 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 248–255.Google ScholarCross Ref
- [19] . 2019. African swine fever. Antivir. Res. 165 (2019), 34–41.Google ScholarCross Ref
- [20] . 2023. PigV2: Monitoring pig vital signs through ground vibrations induced by heartbeat and respiration. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys’22). Association for Computing Machinery, New York, NY, 1102–1108.
DOI: Google ScholarDigital Library - [21] . 2022. Stranger detection and occupant identification using structural vibrations. In Proceedings of the European Workshop on Structural Health Monitoring (EWSHM’22). Springer, 905–914.Google Scholar
- [22] . 2023. GaitVibe+: Enhancing structural vibration-based footstep localization using temporary cameras for in-home gait analysis. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys’22). Association for Computing Machinery, New York, NY, 1168–1174.
DOI: Google ScholarDigital Library - [23] . 2020. MD-Vibe: Physics-informed analysis of patient-induced structural vibration data for monitoring gait health in individuals with muscular dystrophy. In Proceedings of the ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the ACM International Symposium on Wearable Computers (UbiComp/ISWC’20 Adjunct). 525–531.
DOI: Google ScholarDigital Library - [24] . 2015. Dynamic cattle behavioural classification using supervised ensemble classifiers. Comput. Electron. Agric. 111 (2015), 18–28.Google ScholarDigital Library
- [25] . 2013. Sow-activity classification from acceleration patterns: A machine learning approach. Comput. Electron. Agric. 93 (2013), 17–26.Google ScholarDigital Library
- [26] . 2021. Structure- and sampling-adaptive gait balance symmetry estimation using footstep-induced structural floor vibrations. J. Eng. Mechan. 147, 2 (2021), 04020151.
DOI: Google ScholarCross Ref - [27] . 2017. Characterizing left-right gait balance using footstep-induced structural vibrations. Sensors Smart Struct. Technol. Civil, Mechan., Aerosp. Syst. 2017 10168, 724 (2017), 1016819.
DOI: Google ScholarCross Ref - [28] . 2016. Sow lying behaviors before, during and after farrowing. In Proceedings of the ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers.Google Scholar
- [29] . 2011. Poster: Smart buildings, sensor networks, and the internet of things. In Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems (SenSys’11). Association for Computing Machinery, New York, NY, 337–338.
DOI: Google ScholarDigital Library - [30] . 2020. Meat consumption (indicator). OECD Data.
DOI: Google ScholarCross Ref - [31] . 2002. Piglet-and stockperson-directed sow aggression after farrowing and the relationship with a pre-farrowing, human approach test. Appl. Anim. Behav. Sci. 75, 2 (2002), 115–132.Google ScholarCross Ref
- [32] . 1997. A review of livestock monitoring and the need for integrated systems. Comput. Electron. Agric. 17, 2 (1997), 139–159.
DOI: Google ScholarCross Ref - [33] . 1987. Measurement of rectal temperature to predict “mastitis, metritis and alagactia” (MMA) in sows after farrowing. Prevent. Veterin. Med. 5, 2 (1987), 133–139.Google ScholarCross Ref
- [34] . 2018. Impact of two light programs and two levels of dietary tryptophan for weanling piglets. Livest. Sci. 216 (2018), 191–196.Google ScholarCross Ref
- [35] . 2015. Behavioral classification of data from collars containing motion sensors in grazing cattle. Comput. Electron. Agric. 110 (2015), 91–102.Google ScholarDigital Library
- [36] . 2020. Use of wearable biometric monitoring devices to measure outcomes in randomized clinical trials: A methodological systematic review. BMC Med. 18, 1 (2020), 1–11.Google Scholar
- [37] . 2013. Assessment of lameness in sows using gait, footprints, postural behaviour and foot lesion analysis. Animal 7, 7 (2013), 1163–1173.
DOI: Google ScholarCross Ref - [38] . 2003. Fault-tolerant clustering of wireless sensor networks. In Proceedings of the IEEE Wireless Communications and Networking Conference (WCNC’03). 1579–1584.
DOI: Google ScholarCross Ref - [39] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770–778.Google ScholarCross Ref
- [40] . 2000. Optimal design of fault tolerant sensor networks. In Proceedings of the IEEE International Conference on Control Applications. 467–472.
DOI: Google ScholarCross Ref - [41] . 1995. Reducing pig mortality through supervision during the perinatal period. J. Anim. Sci. 73, 12 (1995), 3543–3551.Google ScholarCross Ref
- [42] . 2019. Livestock Monitoring. Retrieved from https://www.allflex.global/livestock-monitoring/.Google Scholar
- [43] . 2001. Behavior and performance of lactating sows and piglets reared indoors or outdoors. J. Anim. Sci. 79, 10 (2001), 2571–2579.Google ScholarCross Ref
- [44] . 2014. Automatic monitoring of pig locomotion using image analysis. Livest. Sci. 159 (2014), 141–148.Google ScholarCross Ref
- [45] . 2021. Automatic behavior and posture detection of sows in loose farrowing pens based on 2D-video images. Front. Anim. Sci. 2, Nov. (2021), 1–13.
DOI: Google ScholarCross Ref - [46] . 2019. An association analysis of sow parity, live-weight and back-fat depth as indicators of sow productivity. Animal 13, 3 (2019), 622–630.Google ScholarCross Ref
- [47] . 2011. Prediction of feather damage in laying hens using optical flows and Markov models. J. Roy. Soc. Interf. 8, 57 (2011), 489–499.Google ScholarCross Ref
- [48] . 2016. Automatic recognition of aggressive behavior in pigs using a kinect depth sensor. Sensors 16, 5 (2016), 631.Google ScholarCross Ref
- [49] . 2019. Practical monitoring of undergrown pigs for IoT-based large-scale smart farm. IEEE Access 7 (2019), 173796–173810.Google ScholarCross Ref
- [50] . 2019. Development and application of an image acquisition system for characterizing sow behaviors in farrowing stalls. Comput. Electron. Agric. 163 (2019), 104866.Google ScholarDigital Library
- [51] . 2020. Ethogram-based automatic wild animal monitoring through inertial sensors and GPS data. Ecol. Inform. 59 (2020), 101112.Google ScholarCross Ref
- [52] . 2021. Characterizing lactating sow posture in farrowing crates utilizing automated image capture and wearable sensors. In Proceedings of the European Conference on Agricultural Engineering AgEng 2021, 634–642.Google Scholar
- [53] . 2001. The influence of sow behaviour on piglet mortality due to crushing in an open farrowing system. Anim. Sci. 72, 1 (2001), 19–28.
DOI: Google ScholarCross Ref - [54] . 2001. Vocalisations of the adult female domestic pig during a standard human approach test and their relationships with behavioural and heart rate measures. Appl. Anim. Behav. Sci. 72, 1 (2001), 23–39.
DOI: Google ScholarCross Ref - [55] . 2017. Automated tracking to measure behavioural changes in pigs for health and welfare monitoring. Scient. Rep. 7, 1 (2017), 1–12.Google Scholar
- [56] . 2002. Neonatal-piglet weight variation and its relation to pre-weaning mortality and weight gain on commercial farms. Prevent. Veterin. Med. 56, 2 (2002), 119–127.
DOI: Google ScholarCross Ref - [57] . 2018. Human gait monitoring using footstep-induced floor vibrations across different structures. In Proceedings of the ACM International Joint Conference and International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. 1382–1391.Google ScholarDigital Library
- [58] . 2020. Step-level occupant detection across different structures through footstep-induced floor vibration using model transfer. J. Eng. Mechan. 146, 3 (2020), 1–18.
DOI: Google ScholarCross Ref - [59] . 2018. Occupant localization using footstep-induced structural vibration. Mechan. Syst. Sig. Process. 112 (2018), 77–97.Google ScholarCross Ref
- [60] . 2016. Characterizing wave propagation to improve indoor step-level person localization using floor vibration. Sensors Smart Struct. Technol. Civil, Mechan., Aerosp. Syst. 2016 9803, Apr. (2016), 980305.
DOI: Google ScholarCross Ref - [61] . 2016. Non-infectious causes of pre-weaning mortality in piglets. Livest. Sci. 184 (2016), 46–57.
DOI: Google ScholarCross Ref - [62] . 2013. Assessment of lameness and claw lesions in sows. Livest. Sci. 156, 1-3 (2013), 10–23.
DOI: Google ScholarCross Ref - [63] . 2019. RTX 2070 Super. Retrieved from https://www.nvidia.com/en-us/geforce/graphics-cards/rtx-2070-super/.Google Scholar
- [64] . 2008. Using movement sensors to detect the onset of farrowing. Biosyst. Eng. 100, 2 (2008), 281–285.Google ScholarCross Ref
- [65] . 2014. Automated video analysis of pig activity at pen level highly correlates to human observations of behavioural activities. Livest. Sci. 160 (2014), 132–137.Google ScholarCross Ref
- [66] . 2017. Animal behavior and well-being symposium: The common swine industry audit: Future steps to assure positive on-farm animal welfare utilizing validated, repeatable and feasible animal-based measures. J. Anim. Sci. 95, 3 (
Mar. 2017), 1372–1381.DOI: Google ScholarCross Ref - [67] . 2019. Fine-grained recognition of activities of daily living through structural vibration and electrical sensing. In Proceedings of the 6th ACM International Conference on Systems for Energy-efficient Buildings, Cities, and Transportation. 149–158.Google ScholarDigital Library
- [68] . 2014. BOES: Building occupancy estimation system using sparse ambient vibration monitoring. In Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2014, Vol. 9061. International Society for Optics and Photonics, 90611O.Google Scholar
- [69] . 2017. SurfaceVibe: Vibration-based tap & swipe tracking on ubiquitous surfaces. In Proceedings of the 16th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN’17). IEEE, 197–208.Google ScholarDigital Library
- [70] . 2015. Indoor person identification through footstep induced structural vibration. In Proceedings of the 16th International Workshop on Mobile Computing Systems and Applications (HotMobile’15)81–86.
DOI: Google ScholarDigital Library - [71] . 2017. Collaboratively adaptive vibration sensing system for high-fidelity monitoring of structural responses induced by pedestrians. Front. Built Environ. 3 (2017), 28.Google ScholarCross Ref
- [72] . 2017. Footprintid: Indoor pedestrian identification through ambient structural vibration sensing. Proc. ACM Interact., Mob., Wear. Ubiq. Technol. 1, 3 (2017), 1–31.Google ScholarDigital Library
- [73] . 2015. Social stress as a cause of diseases in farm animals: Current knowledge and future directions. Veterin. J. 206, 1 (2015), 15–21.Google Scholar
- [74] . 2018. Automatic recognition of flock behavior of chickens with convolutional neural network and kinect sensor. Int. J. Pattern Recog. Artif. Intell. 32, 07 (2018), 1850023.Google ScholarCross Ref
- [75] Feini Qu, Brendan D. Stoeckl, Peter M. Gebhard, Todd J. Hullfish, Josh R. Baxter, and Robert L. Mauck. 2018. A wearable magnet-based system to assess activity and joint flexion in humans and large animals. Annals of Biomedical Engineering 46 (2018), 2069–2078.Google Scholar
- [76] . 2011. An in-depth look at batch farrowing. J. Anim. Veterin. Adv. (2011).Google Scholar
- [77] . 2016. Detecting heat events in dairy cows using accelerometers and unsupervised learning. Comput. Electron. Agric. 128 (2016), 20–26.Google ScholarDigital Library
- [78] . 2017. Geophone SM-24. Retrieved from https://www.sparkfun.com/products/11744.Google Scholar
- [79] . 2017. Pork industry productivity analysis. National Pork Board Report. Retrieved from https://www.pork.org/wp-content/uploads/2018/09/2018-pork-industry-productivity-analysis.pdf.Google Scholar
- [80] . 2004. Sensor network design for fault tolerant estimation. International J. Adapt. Contr. Sig. Process. 18, 1 (2004), 55–72.
DOI: Google ScholarCross Ref - [81] . 1983. Effects of vibration, noise and restraint on heart rate, blood pressure and renal blood flow in the pig. J. Roy. Soc. Med. 76, 10 (1983), 841–847.
DOI: Google ScholarCross Ref - [82] . 2020. OptiStructures: Fabrication of room-scale interactive structures with embedded Fiber Bragg Grating optical sensors and displays. Proc. ACM Interact., Mob., Wear. Ubiq. Technol. 4, 2 (2020), 1–21.Google ScholarDigital Library
- [83] . 2012. Part 1: T, 2012.
Technical Report . USDA–APHIS–VS, CEAH. Retrieved from https://www.aphis.usda.gov/animal_health/nahms/swine/downloads/swine2012/Swine2012_dr_PartI.pdf.Google Scholar - [84] . 2016. Consequences for piglet performance of group housing lactating sows at one, two, or three weeks post-farrowing. PloS One 11, 6 (2016), e0156581.Google ScholarCross Ref
- [85] . 2013. Effect of farrowing duration, parity number and the type of anti-inflammatory drug on postparturient disorders in sows: A clinical study. Tropic. Anim. Health Product. 45, 4 (2013), 1071–1077.
DOI: Google ScholarCross Ref - [86] . 2008. An automated sensor-based method of simple behavioural classification of sheep in extensive systems. Comput. Electron. Agric. 64, 1 (2008), 19–26.Google ScholarDigital Library
- [87] . 2003. Sow activity level, frequency of standing-to-lying posture changes and anti-crushing behaviour—Within sow-repeatability and interactions with nursing behaviour and piglet performance. Appl. Anim. Behav. Sci. 83, 1 (2003), 29–40.
DOI: Google ScholarCross Ref - [88] . 2002. Nursing behaviour of sows during 5 weeks lactation and effects on piglet growth. Appl. Anim. Behav. Sci. 76, 2 (2002), 93–104.Google ScholarCross Ref
- [89] . 1970. Rayleigh and Lamb Waves: Physical Theory and Applications. Plenum Press.Google Scholar
- [90] . 2015. Movement, resting, and attack behaviors of wild pumas are revealed by tri-axial accelerometer measurements. Movem. Ecol. 3, 1 (2015), 2.Google ScholarCross Ref
- [91] . 2016. A novel behavioral model of the pasture-based dairy cow from GPS data using data mining and machine learning techniques. J. Dairy Sci. 99, 3 (2016), 2063–2075.Google ScholarCross Ref
- [92] . 2009. Nest-building behaviour in sows and consequences for pig husbandry. Livest. Sci. 124, 1-3 (2009), 1–8.Google ScholarCross Ref
- [93] . 2018. Feeding behavior recognition for group-housed pigs with the faster R-CNN. Comput. Electron. Agric. 155 (2018), 453–460.Google ScholarCross Ref
- [94] . 2019. Automatic individual pig detection and tracking in pig farms. Sensors 19, 5 (2019), 1188.Google ScholarCross Ref
- [95] . 2004. Hardware design experiences in ZebraNet. In Proceedings of the 2nd International Conference on Embedded Networked Sensor Systems. 227–238.Google ScholarDigital Library
- [96] . 2018. Automatic recognition of lactating sow postures from depth images by deep learning detector. Comput. Electron. Agric. 147, Feb. (2018), 51–63.
DOI: Google ScholarCross Ref
Index Terms
- PigSense: Structural Vibration-based Activity and Health Monitoring System for Pigs
Recommendations
PigV2: Monitoring Pig Vital Signs through Ground Vibrations Induced by Heartbeat and Respiration
SenSys '22: Proceedings of the 20th ACM Conference on Embedded Networked Sensor SystemsPig vital sign monitoring (e.g., estimating the heart rate (HR) and respiratory rate (RR)) is essential to understand the stress level of the sow and detect the onset of parturition. It helps to maximize peri-natal survival and improve animal well-being ...
A computer vision-based approach for respiration rate monitoring of group housed pigs
Highlights- Develop a measuring system capable of monitoring RR in real-time for group-housed pigs.
AbstractIn recent years, respiration rate (RR) monitoring using video data has been explored by researchers with relatively good success. However, the approaches used so far require the manual identification of the region of interest (ROI) in ...
Design and implementation of wireless sensor network based livestock activity monitoring system
FGIT'11: Proceedings of the Third international conference on Future Generation Information TechnologyRecently in Korea, for the damage caused by the outbreak of livestock diseases such as foot-and-mouth disease and AI has been serious, in order to reduce the damage caused by such livestock diseases, it is necessary to develop collection and analysis ...
Comments