scholarly journals An Absorbing Markov Chain Model to Predict Dairy Cow Calving Time

Sensors ◽  
2021 ◽  
Vol 21 (19) ◽  
pp. 6490
Author(s):  
Swe Zar Maw ◽  
Thi Thi Zin ◽  
Pyke Tin ◽  
Ikuo Kobayashi ◽  
Yoichiro Horii
Keyword(s):  
Markov Chain ◽  
Dairy Cow ◽  
Markov Chain Model ◽  
Dairy Farm ◽  
Transient State ◽  
Machine Learning Techniques ◽  
Chain Model ◽  
Expected Time ◽  
Absorbing Markov Chain ◽  
Learning Techniques

Abnormal behavioral changes in the regular daily mobility routine of a pregnant dairy cow can be an indicator or early sign to recognize when a calving event is imminent. Image processing technology and statistical approaches can be effectively used to achieve a more accurate result in predicting the time of calving. We hypothesize that data collected using a 360-degree camera to monitor cows before and during calving can be used to establish the daily activities of individual pregnant cows and to detect changes in their routine. In this study, we develop an augmented Markov chain model to predict calving time and better understand associated behavior. The objective of this study is to determine the feasibility of this calving time prediction system by adapting a simple Markov model for use on a typical dairy cow dataset. This augmented absorbing Markov chain model is based on a behavior embedded transient Markov chain model for characterizing cow behavior patterns during the 48 h before calving and to predict the expected time of calving. In developing the model, we started with an embedded four-state Markov chain model, and then augmented that model by adding calving as both a transient state, and an absorbing state. Then, using this model, we derive (1) the probability of calving at 2 h intervals after a reference point, and (2) the expected time of calving, using their motions between the different transient states. Finally, we present some experimental results for the performance of this model on the dairy farm compared with other machine learning techniques, showing that the proposed method is promising.

Application of Markov Chain Model to Corporate Manpower Planning: A Nigeria Local Government Hub Example

2013 ◽  
Vol 824 ◽  
pp. 514-526 ◽  
Author(s):  
A.C. Igboanugo
Keyword(s):  
Markov Chain ◽  
Local Government ◽  
Markov Chain Model ◽  
Manpower Planning ◽  
Chain Model ◽  
Government Organizations ◽  
Absorbing Markov Chain ◽  
Long Run ◽  
Definite Pattern ◽  
Absorbing States

A corporate manpower planning study, seeking to gain insight into, and hence, attempt tounwrapthe wider meanings of a long-run manpower practice inherent in a set of data obtained from one of the 774 Local Government Organizations in Nigeria, was conducted. The data which spanned over a period of twenty years, relate to six states recruitment, staff stock, training, interdiction, wastage, and retirement and, in particular were found to possess Markov properties, especially stochastic regularity, and therefore had absorbing Markov Chain model fitted into the set. Our results suggest that staff habituate substantial number of times (47) among non-absorbing states before subsequent absorption into any of the two absorbing states. And, again, 52% of the workforce gracefully attain retirement while 48% regrettably get wasted. Agreeably, it seemed that the absorbing Markov Chain model employed has established a definite pattern of manpower flow in the organization as a sure-thing principle rather than a chance mechanism.

scholarly journals Markov Chain Modeling of HIV, Tuberculosis, and Hepatitis B Transmission in Ghana

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Clement Twumasi ◽  
Louis Asiedu ◽  
Ezekiel N. N. Nortey
Keyword(s):  
Markov Chain ◽  
Hepatitis B ◽  
Discrete Time ◽  
Transition Probabilities ◽  
Markov Chain Model ◽  
Chain Model ◽  
Disease Dynamics ◽  
Epidemiological Models ◽  
Discrete Time Markov Chain ◽  
Expected Time

Several mathematical and standard epidemiological models have been proposed in studying infectious disease dynamics. These models help to understand the spread of disease infections. However, most of these models are not able to estimate other relevant disease metrics such as probability of first infection and recovery as well as the expected time to infection and recovery for both susceptible and infected individuals. That is, most of the standard epidemiological models used in estimating transition probabilities (TPs) are not able to generalize the transition estimates of disease outcomes at discrete time steps for future predictions. This paper seeks to address the aforementioned problems through a discrete-time Markov chain model. Secondary datasets from cohort studies were collected on HIV, tuberculosis (TB), and hepatitis B (HB) cases from a regional hospital in Ghana. The Markov chain model revealed that hepatitis B was more infectious over time than tuberculosis and HIV even though the probability of first infection of these diseases was relatively low within the study population. However, individuals infected with HIV had comparatively lower life expectancies than those infected with tuberculosis and hepatitis B. Discrete-time Markov chain technique is recommended as viable for modeling disease dynamics in Ghana.

Stochastic economic evaluation of dairy farm reproductive performance

2015 ◽  
Vol 95 (1) ◽  
pp. 59-70 ◽  
Author(s):  
Afshin S. Kalantari ◽  
Victor E. Cabrera
Keyword(s):  
Markov Chain ◽  
Economic Evaluation ◽  
Reproductive Performance ◽  
Transition Probabilities ◽  
Markov Chain Model ◽  
Dairy Farm ◽  
Chain Model ◽  
Baseline Scenario ◽  
State Variables ◽  
Net Return

Kalantari, A. S. and Cabrera, V. E. 2015. Stochastic economic evaluation of dairy farm reproductive performance. Can. J. Anim. Sci. 95: 59–70. The objective of this study was to assess the economic value of reproductive performance in dairy farms under uncertain and variable conditions. Consequently, the study developed methods to introduce stochasticity into transition probabilities of a Markov chain model. A robust Markov chain model with 21-d stage length and three state variables, parity, days in milk, and days in pregnancy, was developed. Uncertainty was added to all transition probabilities, milk production level, and reproductive costs. The model was run for 10 000 replications after introducing each random variable. The expected net return (US$ cow−1 yr−1±standard deviation) was $3192±75.0 for the baseline scenario that had 15% 21-d pregnancy rate (21-d PR). After verifying the model's behavior, it was run for 2000 replications to study the effect of changing 21-d PR from 10 to 30% with one-unit-percentage interval. The economic gain of changing 21-d PR from 10 to 30% resulted in a US$75 cow−1 yr−1, and this overall increase in the net return was observed mainly due to the lower reproductive and culling cost and higher calf value. The gain was even greater when milk price and milk cut-off threshold decreased.

Sign in / Sign up

Export Citation Format

Share Document