Submit to Agriculture Review for Agriculture Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Agriculture (ISSN 2077-0472). This special issue belongs to the section "Digital Agriculture".

Deadline for manuscript submissions: closed (20 May 2023) | Viewed by 20641

Share This Special Issue

Special Issue Editors

Dr. Hao Li

E-Mail Website
Guest Editor

Department of Agricultural Structure Environment Engineering, China Agricultural University, Beijing, China
Interests: livestock environmental engineering; indoor environment and ventilation; precise ventilation of livestock houses; CFD; environmental control system and strategy
Special Issues, Collections and Topics in MDPI journals

Dr. Xiaoshuai Wang

E-Mail Website
Guest Editor

College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou, China
Interests: ventilation design and environmental control in livestock building; assessment of animal heat stress; precision livestock farming
Special Issues, Collections and Topics in MDPI journals

Dr. Qianying Yi

E-Mail Website
Guest Editor

Department of Engineering for Livestock Management, Leibniz Institute for Agricultural Engineering and Bioeconomy, Potsdam, Germany
Interests: design and control of natural ventilation system; Investigation of air movement inside and around buildings; determination of ventilation rate of naturally ventilated livestock buildings; modelling and reducing emissions in livestock buildings
Special Issues, Collections and Topics in MDPI journals

Dr. Kai Liu

E-Mail Website
Guest Editor

Department of Infectious Diseases and Public Health, Jockey club College of Veterinary Medicine and Life Science, City University of Hong Kong, Hong Kong SAR, China
Interests: precision livestock farming; animal housing and environment management; animal behavior and welfare
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The increasing need for high-quality protein has been largely ensured by developing livestock production systems. Modern highly intensive livestock farming has been adopted around the world for years and brought challenges to the livestock industry: e.g., the difficulties with environment control and the labor cost for the animal producers in taking care of the animals. Animal anomalies can normally be regarded as a sign of an improper environment, bad animal welfare, or diseases. However, the detection, prediction, and prevention of animal anomalies have always been a challenge. Computational advancements in both hardware and software have provided efficient approaches to the livestock industry. The CFD technology, machine vision, biological sensors, deep learning, etc., have all boosted the development and adaptation of precision livestock farming (PLF), generating novel approaches to the prediction, detection, and prevention of animal anomalies to improve the efficiency of animal production.

This Special Issue aims to attract novel and original contributions to the analysis, study, and proposal of innovative techniques applied to the prediction, detection, and prevention of animal anomalies, e.g., precision indoor environment control, automatic monitoring of animal behavior and stress, remote disease diagnosis, and environmental hazard emission control, helping to improve the living conditions of animals, optimizing the use of non-renewable resources, and providing a positive social and environmental impact.

Dr. Hao Li
Dr. Xiaoshuai Wang
Dr. Qianying Yi
Dr. Kai Liu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Agriculture is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

precision livestock farming
environmental control
airflow distribution
computational fluid dynamics
animal stress
animal behavior
environmental hazard emission
IoT
deep learning
sensors
computer vision
big data
modeling

Published Papers (12 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

11 pages, 1261 KiB

Open AccessArticle

The Effects of Space Allowance and Toy Provision on the Growth, Spatiotemporal Distribution of Behavior, and Pen Cleanliness of Finishing Pigs

by Yaqiong Zeng, Hao Wang, Bin Hu, Dingbiao Long, Jiaming Zhu, Zuohua Liu and Yongzhen Li

Agriculture 2023, 13(7), 1277; https://doi.org/10.3390/agriculture13071277 - 21 Jun 2023

Viewed by 1031

Abstract

Excretion and lying are key behavioral factors that cause pen fouling, thereby affecting pig welfare, pathogen fecal–oral transmission, and air quality in pig housing. This study investigated the effect of space allowance and toy provision on the spatiotemporal distribution of pigs’ excreting and lying behavior, as well as the score of floor cleanliness in finishing pig pens. A total of 144 Landrace × Yorkshire × Duroc hybrid fattening pigs were randomly assigned to 12 part-slatted pens at stocking densities of 0.75, 1.05, and 1.35 m²/pig with 12 pigs per pen, and 2 pens at each density level were provided with hanging chains and rubber stars as toys. The results showed that for the average daily gain (ADG) of the pigs, the main effect of space allowance was significant (p < 0.05). The ADG at the stocking density level of 1.35 m²/pig was significantly higher than 0.75 and 1.05 m²/pig (p < 0.05). The ADG of the pigs at a density of 0.75 m²/pig in the toys group was significantly higher than the no toys group (p < 0.05). When occupied space was limited, the provision of toys was beneficial to the growth performance of the pigs. Space allowance and toy provision did not affect the time-varying regularity of the pigs but had a certain impact on the areas where the two behaviors occurred. At a density of 1.35 m²/pig, the excreting rate in the corner areas of the slatted floor and the lying rate in the middle area of the solid floor were significantly higher than at a density of 0.75 and 1.05 m²/pig (p < 0.05). Under the conditions of this study, when the stocking density was 1.35 m²/pig and toys were provided, the average daily gain of the pigs was the highest, and the pigs excreted more in the defined excretion area, lay more in the lying area, and the cleanliness of the lying area was also higher. In the case of space constraints, the provision of toys can offset some of the adverse effects of space constraints on pig growth and pen cleanliness. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

16 pages, 6167 KiB

Open AccessArticle

Effects of Ventilation Fans and Type of Partitions on the Airflow Speeds of Animal Occupied Zone and Physiological Parameters of Dairy Pre-Weaned Calves Housed Individually in a Barn

by Wanying Zhao, Christopher Y. Choi, Xinyi Du, Huiyuan Guan, Hao Li and Zhengxiang Shi

Agriculture 2023, 13(5), 1002; https://doi.org/10.3390/agriculture13051002 - 01 May 2023

Cited by 1 | Viewed by 1167

Abstract

Calves raised in barns are usually kept in individual pens separated by either solid or mesh partitions. To quantify the effects that the two types of partition have on airflow speed in an axial-ventilated-barn, the indoor environment of a calf barn was simulated using computational fluid dynamics (CFD) with validation accomplished by means of direct measurement. To ascertain the effects that two types of partition have on the physiological parameters and health of pre-weaned calves, 24 calves (3–11-day-olds) were selected, equally divided into four groups and sequestered as follows: calves placed in pens separated by solid partitions receiving “low-speed” or “high-speed” airflow; calves separated by mesh partitions receiving “low-speed” or “high-speed” airflow. The results of the CFD simulation showed that the percentage of airflow speed that exceeded 0.5 m s⁻¹ at a height of 0.4 m above the floor of the animal occupied zone where calves were separated by mesh partitions was 88%, while the speed was 66–70% for calves separated by solid partitions. The duration of treatment provided to the calves in the MP-LA (mesh partitions and subjected to a low-speed airflow) and MP-HA (mesh partitions and subjected to a high-speed airflow) groups, were both lower than the SP-LA (solid partitions and subjected to a low-speed airflow) and SP-HA (solid partitions and subjected to a high-speed airflow) groups. We conclude that when the fan is operating, contact between calves separated by mesh partitions produces no negative impact on the health of calves; furthermore, this arrangement can provide a higher airflow speed than that delivered to calves raised in pens separated by solid partitions, especially to those calves in pens farther from the fans. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

14 pages, 2481 KiB

Open AccessCommunication

Sensor-Generated Data for Evaluation of Subclinical Mastitis Treatment Effectiveness with Garlic Extract (Allicin) in Dairy Cattle

by Ramūnas Antanaitis, Lina Anskienė, Karina Džermeikaitė, Dovilė Bačėninaitė, Aloyzas Januškauskas, Kęstutis Sincevičius, Walter Baumgartner and Anton Klein

Agriculture 2023, 13(5), 972; https://doi.org/10.3390/agriculture13050972 - 27 Apr 2023

Viewed by 1530

Abstract

The aim of this study was to determine the impact of subclinical mastitis treatment in dairy cattle on biomarkers registered with in-line sensors such as milk yield (MY), electric milk conductivity (EC), rumination time (RT), and somatic cell count (SCC). At the start of the experiment, all cows according to SCC level were divided into two groups: healthy cows (n = 30, with SCCs less than 200,000 per mL and without the growth of bacteria in the milk samples) and cows with subclinical mastitis (n = 32), with SCC levels greater than 200,000 per mL and with growth of bacteria. Streptococcus spp. was found in 15 samples, and Strep. uberis was found in 17 samples. Streptococcus spp. and Strep. uberis were sensitive to amoxicillin and calvulanic acid. According to these results, 32 cows with subclinical mastitis were treated with two treatment protocols: one 1 (n = 16) and two (n = 16). In the first protocol, we used SCC boluses and nonsteroidal anti-inflammatory drugs (SCCB and NSAID). The second protocol consists of intramammary antibiotics and anti-inflammatory medications (Synulox LC and NSAIDs). All parameters (MY, EC, RT, and SCC) were recorded with Lely Astronaut^® A3 milking robots on the day of mastitis diagnosis (0 day) and 14 days after treatment began. All animal experimental procedures were approved by the ethical committee; the approval number is PK01696. On the basis of our findings, we may infer that SCC boluses and NSAIDs are effective in treating subclinical mastitis. After 14 days of treatment, the electrical conductivity of milk in cows treated with AB and NSAID was also higher in all quarters of the udder compared to cows treated with SCCB + NSAID. The RT of cows on disease diagnosis day of cows treated with AB and NSAID was 11.41% lower compared to cows treated with SCCB and NSAID, while the RT of cows after 14 days treated with AB and NSAID was 7.01% lower compared to cows treated with SCCB and NSAID. On the practical side, for treatment of subclinical mastitis, we recommend using a feed supplement SCC bolus (one per os) with a composition containing Meloxicam 20 mg with a single subcutaneous injection at a dosage of 2.5 mL per 100 kg body weight. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

18 pages, 4488 KiB

Open AccessArticle

Predicting Ventilation Rate in a Naturally Ventilated Dairy Barn in Wind-Forced Conditions Using Machine Learning Techniques

by Mengbing Cao, Qianying Yi, Kaiying Wang, Jiangong Li and Xiaoshuai Wang

Agriculture 2023, 13(4), 837; https://doi.org/10.3390/agriculture13040837 - 06 Apr 2023

Cited by 1 | Viewed by 1594

Abstract

Precise ventilation rate estimation of a naturally ventilated livestock building can benefit the control of the indoor environment. Machine learning has become a useful technique in many research fields and might be applied to ventilation rate prediction. This paper developed a machine-learning model for ventilation rate prediction from batch computational fluid dynamics (CFD) simulation results. By comparing deep neural networks (DNN), support vector regression (SVR), and random forest (RF), the best machine learning algorithm was selected. By comparing the modeling scheme of direct single-output (ventilation rate) and indirect multiple-output (predict averaged air velocities normal to the openings, then calculate the ventilation rate), the performances of the machine learning models widely applied in ventilation rate prediction were evaluated. In addition, this paper further evaluated the impact of adding indoor air velocity measurement in ventilation rate prediction. The results showed that the modeling performance of the DNN algorithm (Mean Absolute Percentage Error (MAPE) = 20.1%) was better than those of the SVR (MAPE = 23.2%) and RF algorithm (MAPE = 21.0%). The scheme of multiple-output performed better (MAPE < 8%) than the single-output scheme (MAPE = 20.1%), where MAPE was the mean absolute percentage error. Additionally, the comparison of modeling schemes with different inputs showed that the predictive accuracy could be improved by adding indoor velocities to the inputs. The MAPE decreased from 7.7% in the scheme without indoor velocity to 4.4% in the scheme with one indoor velocity, and 3.1% in the scheme with two indoor velocities. The location of the additional air velocity affected the accuracy of the predictive model, with the ones at the bottom layer performing better in the prediction than those at the top layer. This study enables a real-time and accurate prediction of the ventilation rate of a barn and provides a recommendation for optimal indoor sensor placement. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

19 pages, 2696 KiB

Open AccessArticle

Deep Learning for Laying Hen Activity Recognition Using Wearable Sensors

by Mohammad Shahbazi, Kamyar Mohammadi, Sayed M. Derakhshani and Peter W. G. Groot Koerkamp

Agriculture 2023, 13(3), 738; https://doi.org/10.3390/agriculture13030738 - 22 Mar 2023

Cited by 5 | Viewed by 1750

Abstract

Laying hen activities in modern intensive housing systems can dramatically influence the policies needed for the optimal management of such systems. Intermittent monitoring of different behaviors during daytime cannot provide a good overview, since daily behaviors are not equally distributed over the day. This paper investigates the application of deep learning technology in the automatic recognition of laying hen behaviors equipped with body-worn inertial measurement unit (IMU) modules in poultry systems. Motivated by the human activity recognition literature, a sophisticated preprocessing method is tailored on the time-series data of IMU, transforming it into the form of so-called activity images to be recognized by the deep learning models. The diverse range of behaviors a laying hen can exhibit are categorized into three classes: low-, medium-, and high-intensity activities, and various recognition models are trained to recognize these behaviors in real-time. Several ablation studies are conducted to assess the efficacy and robustness of the developed models against variations and limitations common for an in situ practical implementation. Overall, the best trained model on the full-feature acquired data achieves a mean accuracy of almost 100%, where the whole process of inference by the model takes less than 30 milliseconds. The results suggest that the application of deep learning technology for activity recognition of individual hens has the potential to accurately aid successful management of modern poultry systems. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

15 pages, 3077 KiB

Open AccessArticle

Investigation on Minimum Ventilation, Heating, and Energy Consumption of Pig Buildings in China during Winter

by Fei Qi, Hao Li, Xuedong Zhao, Jinjun Huang and Zhengxiang Shi

Agriculture 2023, 13(2), 319; https://doi.org/10.3390/agriculture13020319 - 28 Jan 2023

Cited by 3 | Viewed by 1291

Abstract

Ventilation and heating can be necessary for pig production during winter in China. However, it is challenging to balance the ventilation rate and heat loss due to the ventilation. Therefore, it is essential to design the minimum ventilation and heating load properly in order to reduce energy loss. In this paper, a VBA (Visual Basic for Applications) model based on energy balance is established. Meteorological data, pig body masses, outdoor temperatures, feeding densities, and building envelope thermal insulance factors were involved in the model. A model pig house with a length and width of 110 m × 15 m was used to investigate the ventilation, heating time, load, and power consumption in different climate zones, i.e., Changchun, Beijing, Nanning, Wuhan, and Guiyang, representing five major climate regions in China. Based on the simulation results, the models of minimum ventilation and heating load were fitted. The results showed that there is a logarithmic relationship between the minimum ventilation volume and body mass, R² = 0.9673. The R² of heating load models for nursery pigs and fattening pigs were 0.966 and 0.963, respectively, considering the feeding area, the outside temperature, the body masses of the nursery and fattening pigs, and the thermal insulance factor of the enclosure. The heating requirements of commercial pig houses within the same building envelope followed the trend in Changchun > Beijing > Guiyang > Wuhan > Nanning. Increasing the building envelope’s thermal insulance factor or using precision heating could reduce the pig house’s power consumption. The analysis of the heating load and energy consumption of winter pig houses in various climate regions provided a reference for precise environmental control and the selection of building thermal insulance factors in China. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

13 pages, 36229 KiB

Open AccessArticle

Systems to Monitor the Individual Feeding and Drinking Behaviors of Growing Pigs Based on Machine Vision

by Yanrong Zhuang, Kang Zhou, Zhenyu Zhou, Hengyi Ji and Guanghui Teng

Agriculture 2023, 13(1), 103; https://doi.org/10.3390/agriculture13010103 - 29 Dec 2022

Cited by 5 | Viewed by 1543

Abstract

Feeding and drinking behaviors are important in pig breeding. Although many methods have been developed to monitor them, most are too expensive for pig research, and some vision-based methods have not been integrated into equipment or systems. In this study, two systems were designed to monitor pigs’ feeding and drinking behaviors, which could reduce the impact of the image background. Moreover, three convolutional neural network (CNN) algorithms, VGG19, Xception, and MobileNetV2, were used to build recognition models for feeding and drinking behaviors. The models trained by MobileNetV2 had the best performance, with the recall rate higher than 97% in recognizing pigs, and low mean square error (RMSE) and mean absolute error (MAE) in estimating feeding (RMSE = 0.58 s, MAE = 0.21 s) and drinking durations (RMSE = 0.60 s, MAE = 0.12 s). In addition, the two best models trained by MobileNetV2 were combined with the LabVIEW software development platform, and a new software to monitor the feeding and drinking behaviors of pigs was built that can automatically recognize pigs and estimate their feeding and drinking durations. The system designed in this study can be applied to behavioral recognition in pig production. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

13 pages, 2591 KiB

Open AccessArticle

Effects of Body-Mounted Inertial Measurement Unit (IMU) Backpacks on Space Use and Behaviors of Laying Hens in a Perchery System

by Luwei Nie, Qian Hu, Qin Tong, Chao Liang, Baoming Li, Mingxia Han, Yuling You, Xingyan Yue, Xiao Yang and Chaoyuan Wang

Agriculture 2022, 12(11), 1898; https://doi.org/10.3390/agriculture12111898 - 11 Nov 2022

Viewed by 1404

Abstract

Body-mounted sensors have significantly enhanced our understanding of individual animals through location tracking, behavior monitoring, and activity determination. However, attaching sensors may alter the behavior of the tested animals, which would, potentially, invalidate the collected data. The objective of this study was to evaluate the effects of wearable backpacks on space use (feeder, nest box, and perch) and behaviors (aggressive, comfort, and locomotion behaviors) of laying hens in a perchery system. Nineteen laying hens were reared for 21 days, and each was fitted with a lightweight inertial measurement unit (IMU) backpack on day 0. Instantaneous scan samples were adopted to record the number of laying hens, using each space at a 5-min interval over the 16 h lights-on period at −6 d to −1 d, 1 d to 4 d, and 10 d to 15 d. Six hens were randomly selected for observation of behaviors during six 20-min periods at −5 d to −3 d, and 13 d to 15 d. Feeder use reduced at 1 d to 4 d, 11 d, and 13 d to 15 d, and nest box use reduced at 1 d, 3 d, and 10 d to 12 d, while it increased on 15 d. Hens perched more often at 1 d to 4 d and 10 d to 14 d. Space use was affected by wearing a backpack in the first few days after installation. As hens gradually accustomed to the devices, the effects on feeder, nest box, and perch use disappeared at 10 d, 13 d and 15 d, respectively. The diurnal pattern of hens using the nest box largely returned to the state before being backpacked, and there were slight recoveries in the use of feeder and perch use during the 15-day trial period. There was no observed difference in the amount of pecking, preening bouts, aerial ascent/descent, or the time spent on preening and walking at −5 d to −3 d and 13 d to 15 d. No differences were found in body weight and plumage condition score between 0 d and 16 d. The results demonstrated that the IMU backpack only had marginal and non-lasting effects on space use and behaviors of laying hens, and it seems suitable for further behavioral research after short-term acclimation. However, when the diurnal pattern serves as the variable of interest, researchers need to re-evaluate the effect of the device on birds, rather than implying there is no effect. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

17 pages, 2466 KiB

Open AccessArticle

Automatic Position Detection and Posture Recognition of Grouped Pigs Based on Deep Learning

by Hengyi Ji, Jionghua Yu, Fengdan Lao, Yanrong Zhuang, Yanbin Wen and Guanghui Teng

Agriculture 2022, 12(9), 1314; https://doi.org/10.3390/agriculture12091314 - 26 Aug 2022

Cited by 9 | Viewed by 2414

Abstract

The accurate and rapid detection of objects in videos facilitates the identification of abnormal behaviors in pigs and the introduction of preventive measures to reduce morbidity. In addition, accurate and effective pig detection algorithms provide a basis for pig behavior analysis and management decision-making. Monitoring the posture of pigs can enable the detection of the precursors of pig diseases in a timely manner and identify factors that impact pigs’ health, which helps to evaluate their health status and comfort. Excessive sitting represents abnormal behavior when pigs are frustrated in a restricted environment. The present study focuses on the automatic recognition of standing posture and lying posture in grouped pigs, which shows a lack of recognition of sitting posture. The main contributions of this paper are as follows: A human-annotated dataset of standing, lying, and sitting postures captured by 2D cameras during the day and night in a pig barn was established, and a simplified copy, paste, and label smoothing strategy was applied to solve the problem of class imbalance caused by the lack of sitting postures among pigs in the dataset. The improved YOLOX has an average precision with an intersection over union threshold of 0.5 (AP_0.5) of 99.5% and average precision with an intersection over union threshold of 0.5–0.95 (AP_0.5–0.95) of 91% in pig position detection; an AP_0.5 of 90.9% and an AP_0.5–0.95 of 82.8% in sitting posture recognition; a mean average precision with intersection over union threshold of 0.5 (mAP_0.5) of 95.7% and a mean average precision with intersection over union threshold of 0.5–0.95 (mAP_0.5–0.95) of 87.2% in all posture recognition. The method proposed in our study can improve the position detection and posture recognition of grouped pigs effectively, especially for pig sitting posture recognition, and can meet the needs of practical application in pig farms. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

13 pages, 16573 KiB

Open AccessArticle

DepthFormer: A High-Resolution Depth-Wise Transformer for Animal Pose Estimation

by Sicong Liu, Qingcheng Fan, Shanghao Liu and Chunjiang Zhao

Agriculture 2022, 12(8), 1280; https://doi.org/10.3390/agriculture12081280 - 22 Aug 2022

Cited by 1 | Viewed by 1785

Abstract

Animal pose estimation has important value in both theoretical research and practical applications, such as zoology and wildlife conservation. A simple but effective high-resolution Transformer model for animal pose estimation called DepthFormer is provided in this study to address the issue of large-scale models for multi-animal pose estimation being problematic with limited computing resources. We make good use of a multi-branch parallel design that can maintain high-resolution representations throughout the process. Along with two similarities, i.e., sparse connectivity and weight sharing between self-attention and depthwise convolution, we utilize the delicate structure of the Transformer and representative batch normalization to design a new basic block for reducing the number of parameters and the amount of computation required. In addition, four PoolFormer blocks are introduced after the parallel network to maintain good performance. Benchmark evaluation is performed on a public database named AP-10K, which contains 23 animal families and 54 species, and the results are compared with the other six state-of-the-art pose estimation networks. The results demonstrate that the performance of DepthFormer surpasses that of other popular lightweight networks (e.g., Lite-HRNet and HRFormer-Tiny) when performing this task. This work can provide effective technical support to accurately estimate animal poses with limited computing resources. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

18 pages, 4150 KiB

Open AccessArticle

Predicting the Feed Intake of Cattle Based on Jaw Movement Using a Triaxial Accelerometer

by Luyu Ding, Yang Lv, Ruixiang Jiang, Wenjie Zhao, Qifeng Li, Baozhu Yang, Ligen Yu, Weihong Ma, Ronghua Gao and Qinyang Yu

Agriculture 2022, 12(7), 899; https://doi.org/10.3390/agriculture12070899 - 21 Jun 2022

Cited by 9 | Viewed by 1933

Abstract

The use of an accelerometer is considered as a promising method for the automatic measurement of the feeding behavior or feed intake of cattle, with great significance in facilitating daily management. To address further need for commercial use, an efficient classification algorithm at a low sample frequency is needed to reduce the amount of recorded data to increase the battery life of the monitoring device, and a high-precision model needs to be developed to predict feed intake on the basis of feeding behavior. Accelerograms for the jaw movement and feed intake of 13 mid-lactating cows were collected during feeding with a sampling frequency of 1 Hz at three different positions: the nasolabial levator muscle (P1), the right masseter muscle (P2), and the left lower lip muscle (P3). A behavior identification framework was developed to recognize jaw movements including ingesting, chewing and ingesting–chewing through extreme gradient boosting (XGB) integrated with the hidden Markov model solved by the Viterbi algorithm (HMM–Viterbi). Fourteen machine learning models were established and compared in order to predict feed intake rate through the accelerometer signals of recognized jaw movement activities. The developed behavior identification framework could effectively recognize different jaw movement activities with a precision of 99% at a window size of 10 s. The measured feed intake rate was 190 ± 89 g/min and could be predicted efficiently using the extra trees regressor (ETR), whose R², RMSE, and NME were 0.97, 0.36 and 0.05, respectively. The three investigated monitoring sites may have affected the accuracy of feed intake prediction, but not behavior identification. P1 was recommended as the proper monitoring site, and the results of this study provide a reference for the further development of a wearable device equipped with accelerometers to measure feeding behavior and to predict feed intake. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Figure 1

15 pages, 4635 KiB

Open AccessArticle

Effect of Fans’ Placement on the Indoor Thermal Environment of Typical Tunnel-Ventilated Multi-Floor Pig Buildings Using Numerical Simulation

by Xiaoshuai Wang, Mengbing Cao, Feiyue Hu, Qianying Yi, Thomas Amon, David Janke, Tian Xie, Guoqiang Zhang and Kaiying Wang

Agriculture 2022, 12(6), 891; https://doi.org/10.3390/agriculture12060891 - 20 Jun 2022

Cited by 4 | Viewed by 1857

Abstract

An increasing number of large pig farms are being built in multi-floor pig buildings (MFPBs) in China. Currently, the ventilation system of MFPB varies greatly and lacks common standards. This work aims to compare the ventilation performance of three popular MFPB types with different placement of fans using the Computational Fluid Dynamics (CFD) technique. After being validated with field-measured data, the CFD models were extended to simulate the air velocity, air temperature, humidity, and effective temperature of the three MFPBs. The simulation results showed that the ventilation rate of the building with outflowing openings in the endwall and fans installed on the top of the shaft was approximately 25% less than the two buildings with fans installed on each floor. The ventilation rate of each floor increased from the first to the top floor for both buildings with a shaft, while no significant difference was observed in the building without a shaft. Increasing the shaft’s width could mitigate the variation in the ventilation rate of each floor. The effective temperature distribution at the animal level was consistent with the air velocity distribution. Therefore, in terms of the indoor environmental condition, the fans were recommended to be installed separately on each floor. Full article

(This article belongs to the Special Issue Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities)

► Show Figures

Journal Menu

Journal Browser

Application of Novel Approaches for Prediction, Detection, and Prevention of Animal Anomalies in Livestock Facilities

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI