The Experts below are selected from a list of 3564 Experts worldwide ranked by ideXlab platform
Alexandre Termier - One of the best experts on this subject based on the ideXlab platform.
-
Towards Sustainable Dairy Management - A Machine Learning Enhanced Method for Estrus Detection
2019Co-Authors: Kévin Fauvel, Véronique Masson, Elisa Fromont, Philippe Faverdin, Alexandre TermierAbstract:Our research tackles the challenge of milk production resource use efficiency in dairy farms with machine learning methods. Reproduction is a key factor for dairy farm performance since cows milk production begin with the birth of a calf. Therefore, detecting Estrus, the only period when the cow is susceptible to pregnancy, is crucial for farm efficiency. Our goal is to enhance Estrus Detection (performance, interpretability), especially on the currently undetected silent Estrus (35% of total Estrus), and allow farmers to rely on automatic Estrus Detection solutions based on affordable data (activity, temperature). In this paper, we first propose a novel approach with real-world data analysis to address both behavioral and silent Estrus Detection through machine learning methods. Second, we present LCE, a local cascade based algorithm that significantly outperforms a typical commercial solution for Estrus Detection, driven by its ability to detect silent Estrus. Then, our study reveals the pivotal role of activity sensors deployment in Estrus Detection. Finally, we propose an approach relying on global and local (behavioral versus silent) algorithm interpretability (SHAP) to reduce the mistrust in Estrus Detection solutions.
-
KDD - Towards Sustainable Dairy Management - A Machine Learning Enhanced Method for Estrus Detection
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019Co-Authors: Kévin Fauvel, Véronique Masson, Elisa Fromont, Philippe Faverdin, Alexandre TermierAbstract:Our research tackles the challenge of milk production resource use efficiency in dairy farms with machine learning methods. Reproduction is a key factor for dairy farm performance since cows milk production begin with the birth of a calf. Therefore, detecting Estrus, the only period when the cow is susceptible to pregnancy, is crucial for farm efficiency. Our goal is to enhance Estrus Detection (performance, interpretability), especially on the currently undetected silent Estrus (35% of total Estrus), and allow farmers to rely on automatic Estrus Detection solutions based on affordable data (activity, temperature). In this paper, we first propose a novel approach with real-world data analysis to address both behavioral and silent Estrus Detection through machine learning methods. Second, we present LCE, a local cascade based algorithm that significantly outperforms a typical commercial solution for Estrus Detection, driven by its ability to detect silent Estrus. Then, our study reveals the pivotal role of activity sensors deployment in Estrus Detection. Finally, we propose an approach relying on global and local (behavioral versus silent) algorithm interpretability (SHAP) to reduce the mistrust in Estrus Detection solutions.
Dheer Singh - One of the best experts on this subject based on the ideXlab platform.
-
saliva ferning an unorthodox Estrus Detection method in water buffaloes bubalus bubalis
Theriogenology, 2016Co-Authors: Ravinder Ravinder, R. K. Baithalu, Onnureddy Kaipa, Vijay Simha Baddela, Eshu Singhal Sinha, Prashant Singh, Varij Nayan, Chandra Sekhar Naidu Velagala, Suneel Kumar Onteru, Dheer SinghAbstract:Estrus Detection is a major problem in buffalo husbandry because of inconsistent expression of estrous signs at different seasons, and a high prevalence of the silent heat and postpartum anEstrus in this species. Around 50% of the Estrus events in buffaloes are currently undetected in the field conditions, resulting in a huge economic loss. Although the cervicovaginal fluid fern patterns confirm the Estrus for a breeding decision, the fluid discharge is absent during the silent-heat condition. Therefore, the present study focused on the crystallization patterns of the saliva as an alternative method for Estrus Detection in buffaloes. Saliva is a body fluid available regularly, and its ferning ability before ovulation was established in women. In this study, eight female nonpregnant Murrah buffaloes (Bubalus bubalis) were considered during two experimental periods of 3 months each. One period was in summer with five animals, and another period was in rainy season with three animals. Estrus was determined by the Estrus symptoms, ovarian ultrasonography, and salivary estradiol (E2) to progesterone (P4) ratio. A total of 450 saliva samples were collected from these animals on the daily basis. The salivary smear was prepared with 20 μL of the cell-free saliva on a clean glass slide, and its microscopic images were captured at a magnification of × 200. The images were used for fractal analysis as the salivary crystallization or fern patterns follow the fractal geometry. Saliva at Estrus showed a typical symmetrical fern-like crystallization patterns with significantly (P < 0.05) lower fractal dimension values. Salivary estradiol levels and E2/P4 ratio were significantly (P < 0.05) higher at the Estrus stage than those at the diEstrus stage. An average period of an estrous cycle was 21.7 ± 2.7 days (n = 18 estrous cycles) in buffaloes on the basis of distinct salivary crystallization patterns. The proportion of Estrus Detection by the salivary fern patterns was very significantly (P < 0.01) higher (0.84) than the proportion of Estrus Detection (0.5) in the field conditions. Altogether, salivary fern patterns along with the current methods can help reduce Estrus Detection problem in buffaloes.
-
Saliva ferning, an unorthodox Estrus Detection method in water buffaloes (Bubalus bubalis)
Theriogenology, 2016Co-Authors: Ravinder Ravinder, R. K. Baithalu, Onnureddy Kaipa, Vijay Simha Baddela, Eshu Singhal Sinha, Prashant Singh, Varij Nayan, Chandra Sekhar Naidu Velagala, Suneel Kumar Onteru, Dheer SinghAbstract:Estrus Detection is a major problem in buffalo husbandry because of inconsistent expression of estrous signs at different seasons, and a high prevalence of the silent heat and postpartum anEstrus in this species. Around 50% of the Estrus events in buffaloes are currently undetected in the field conditions, resulting in a huge economic loss. Although the cervicovaginal fluid fern patterns confirm the Estrus for a breeding decision, the fluid discharge is absent during the silent-heat condition. Therefore, the present study focused on the crystallization patterns of the saliva as an alternative method for Estrus Detection in buffaloes. Saliva is a body fluid available regularly, and its ferning ability before ovulation was established in women. In this study, eight female nonpregnant Murrah buffaloes (Bubalus bubalis) were considered during two experimental periods of 3 months each. One period was in summer with five animals, and another period was in rainy season with three animals. Estrus was determined by the Estrus symptoms, ovarian ultrasonography, and salivary estradiol (E2) to progesterone (P4) ratio. A total of 450 saliva samples were collected from these animals on the daily basis. The salivary smear was prepared with 20 μL of the cell-free saliva on a clean glass slide, and its microscopic images were captured at a magnification of × 200. The images were used for fractal analysis as the salivary crystallization or fern patterns follow the fractal geometry. Saliva at Estrus showed a typical symmetrical fern-like crystallization patterns with significantly (P
R. K. Baithalu - One of the best experts on this subject based on the ideXlab platform.
-
Vocal cues based Decision Support System for Estrus Detection in water buffaloes (Bubalus bubalis)
Computers and Electronics in Agriculture, 2019Co-Authors: Indu Devi, Pawan Singh, Kuldeep Dudi, S.s. Lathwal, A. P. Ruhil, Yajuvendra Singh, Rajeev Kumar Malhotra, R. K. Baithalu, Ranjana SinhaAbstract:Abstract To have more economic profitability from buffalo dairy business, timely Estrus Detection and right timed insemination is the key to success but accurate and timely Detection of Estrus period has remained a challenging task for the livestock breeders particularly in buffaloes. Silent Estrus is important factor which hamper reproductive performance in buffaloes. Proper Estrus Detection is the biggest constraint in attaining high conception rate in buffaloes. Contemporary practice for Estrus Detection relies on the visual observation of Estrus-specific behaviours/signs. This study proposes the design of a Decision Support System based on acoustic features of vocalization for Estrus Detection in buffaloes. Threshold values of acoustic features along with animal number were used as input variables. So, two types of conditions (positive Estrus and negative Estrus) were identified by DSS based on vocal cues of Murrah buffaloes. Accuracy and efficiency of DSS model for Estrus Detection were found to be 95% and 78.94%, respectively. This study explores the potential use of vocal cues for the development of algorithms for automation and precision livestock farming in commercial dairy buffalo farms. Moreover, this study is a proof that DSS based on animal calls may be a corrigible method to get clue about Estrus phase in buffaloes especially during daytime when chances of silent Estrus are more.
-
saliva ferning an unorthodox Estrus Detection method in water buffaloes bubalus bubalis
Theriogenology, 2016Co-Authors: Ravinder Ravinder, R. K. Baithalu, Onnureddy Kaipa, Vijay Simha Baddela, Eshu Singhal Sinha, Prashant Singh, Varij Nayan, Chandra Sekhar Naidu Velagala, Suneel Kumar Onteru, Dheer SinghAbstract:Estrus Detection is a major problem in buffalo husbandry because of inconsistent expression of estrous signs at different seasons, and a high prevalence of the silent heat and postpartum anEstrus in this species. Around 50% of the Estrus events in buffaloes are currently undetected in the field conditions, resulting in a huge economic loss. Although the cervicovaginal fluid fern patterns confirm the Estrus for a breeding decision, the fluid discharge is absent during the silent-heat condition. Therefore, the present study focused on the crystallization patterns of the saliva as an alternative method for Estrus Detection in buffaloes. Saliva is a body fluid available regularly, and its ferning ability before ovulation was established in women. In this study, eight female nonpregnant Murrah buffaloes (Bubalus bubalis) were considered during two experimental periods of 3 months each. One period was in summer with five animals, and another period was in rainy season with three animals. Estrus was determined by the Estrus symptoms, ovarian ultrasonography, and salivary estradiol (E2) to progesterone (P4) ratio. A total of 450 saliva samples were collected from these animals on the daily basis. The salivary smear was prepared with 20 μL of the cell-free saliva on a clean glass slide, and its microscopic images were captured at a magnification of × 200. The images were used for fractal analysis as the salivary crystallization or fern patterns follow the fractal geometry. Saliva at Estrus showed a typical symmetrical fern-like crystallization patterns with significantly (P < 0.05) lower fractal dimension values. Salivary estradiol levels and E2/P4 ratio were significantly (P < 0.05) higher at the Estrus stage than those at the diEstrus stage. An average period of an estrous cycle was 21.7 ± 2.7 days (n = 18 estrous cycles) in buffaloes on the basis of distinct salivary crystallization patterns. The proportion of Estrus Detection by the salivary fern patterns was very significantly (P < 0.01) higher (0.84) than the proportion of Estrus Detection (0.5) in the field conditions. Altogether, salivary fern patterns along with the current methods can help reduce Estrus Detection problem in buffaloes.
-
Saliva ferning, an unorthodox Estrus Detection method in water buffaloes (Bubalus bubalis)
Theriogenology, 2016Co-Authors: Ravinder Ravinder, R. K. Baithalu, Onnureddy Kaipa, Vijay Simha Baddela, Eshu Singhal Sinha, Prashant Singh, Varij Nayan, Chandra Sekhar Naidu Velagala, Suneel Kumar Onteru, Dheer SinghAbstract:Estrus Detection is a major problem in buffalo husbandry because of inconsistent expression of estrous signs at different seasons, and a high prevalence of the silent heat and postpartum anEstrus in this species. Around 50% of the Estrus events in buffaloes are currently undetected in the field conditions, resulting in a huge economic loss. Although the cervicovaginal fluid fern patterns confirm the Estrus for a breeding decision, the fluid discharge is absent during the silent-heat condition. Therefore, the present study focused on the crystallization patterns of the saliva as an alternative method for Estrus Detection in buffaloes. Saliva is a body fluid available regularly, and its ferning ability before ovulation was established in women. In this study, eight female nonpregnant Murrah buffaloes (Bubalus bubalis) were considered during two experimental periods of 3 months each. One period was in summer with five animals, and another period was in rainy season with three animals. Estrus was determined by the Estrus symptoms, ovarian ultrasonography, and salivary estradiol (E2) to progesterone (P4) ratio. A total of 450 saliva samples were collected from these animals on the daily basis. The salivary smear was prepared with 20 μL of the cell-free saliva on a clean glass slide, and its microscopic images were captured at a magnification of × 200. The images were used for fractal analysis as the salivary crystallization or fern patterns follow the fractal geometry. Saliva at Estrus showed a typical symmetrical fern-like crystallization patterns with significantly (P
Kévin Fauvel - One of the best experts on this subject based on the ideXlab platform.
-
Towards Sustainable Dairy Management - A Machine Learning Enhanced Method for Estrus Detection
2019Co-Authors: Kévin Fauvel, Véronique Masson, Elisa Fromont, Philippe Faverdin, Alexandre TermierAbstract:Our research tackles the challenge of milk production resource use efficiency in dairy farms with machine learning methods. Reproduction is a key factor for dairy farm performance since cows milk production begin with the birth of a calf. Therefore, detecting Estrus, the only period when the cow is susceptible to pregnancy, is crucial for farm efficiency. Our goal is to enhance Estrus Detection (performance, interpretability), especially on the currently undetected silent Estrus (35% of total Estrus), and allow farmers to rely on automatic Estrus Detection solutions based on affordable data (activity, temperature). In this paper, we first propose a novel approach with real-world data analysis to address both behavioral and silent Estrus Detection through machine learning methods. Second, we present LCE, a local cascade based algorithm that significantly outperforms a typical commercial solution for Estrus Detection, driven by its ability to detect silent Estrus. Then, our study reveals the pivotal role of activity sensors deployment in Estrus Detection. Finally, we propose an approach relying on global and local (behavioral versus silent) algorithm interpretability (SHAP) to reduce the mistrust in Estrus Detection solutions.
-
KDD - Towards Sustainable Dairy Management - A Machine Learning Enhanced Method for Estrus Detection
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019Co-Authors: Kévin Fauvel, Véronique Masson, Elisa Fromont, Philippe Faverdin, Alexandre TermierAbstract:Our research tackles the challenge of milk production resource use efficiency in dairy farms with machine learning methods. Reproduction is a key factor for dairy farm performance since cows milk production begin with the birth of a calf. Therefore, detecting Estrus, the only period when the cow is susceptible to pregnancy, is crucial for farm efficiency. Our goal is to enhance Estrus Detection (performance, interpretability), especially on the currently undetected silent Estrus (35% of total Estrus), and allow farmers to rely on automatic Estrus Detection solutions based on affordable data (activity, temperature). In this paper, we first propose a novel approach with real-world data analysis to address both behavioral and silent Estrus Detection through machine learning methods. Second, we present LCE, a local cascade based algorithm that significantly outperforms a typical commercial solution for Estrus Detection, driven by its ability to detect silent Estrus. Then, our study reveals the pivotal role of activity sensors deployment in Estrus Detection. Finally, we propose an approach relying on global and local (behavioral versus silent) algorithm interpretability (SHAP) to reduce the mistrust in Estrus Detection solutions.
Koji Yoshioka - One of the best experts on this subject based on the ideXlab platform.
-
An attempt at Estrus Detection in cattle by continuous measurements of ventral tail base surface temperature with supervised machine learning.
The Journal of reproduction and development, 2020Co-Authors: Shogo Higaki, Hongyu Darhan, Chie Suzuki, Tomoko Suda, Reina Sakurai, Koji YoshiokaAbstract:We aimed to determine the effectiveness of Estrus Detection based on continuous measurements of the ventral tail base surface temperature (ST) with supervised machine learning in cattle. ST data were obtained through 51 Estrus cycles on 11 female cattle (six Holsteins and five Japanese Blacks) using the tail-attached sensor. Three Estrus Detection models were constructed with the training data (n = 17) using machine learning techniques (random forest, artificial neural network, and support vector machine) based on 13 features extracted from sensing data (indicative of Estrus-associated ST changes). Estrus Detection abilities of the three models on test data (n = 34) were not statistically different among models in terms of sensitivity and precision (range 50.0% to 58.8% and 60.6% to 73.1%, respectively). The relatively poor performance of the models might indicate the difficulty of separating Estrus-associated ST changes from Estrus-independent fluctuations in ST.
-
Wearable wireless Estrus Detection sensor for cows
Computers and Electronics in Agriculture, 2016Co-Authors: L. Mattias Andersson, Koji Yoshioka, Hironao Okada, Ryotaro Miura, Yi Zhang, Hiroshi Aso, Toshihiro ItohAbstract:Abstract Breeding is an important part of all livestock farming. Accurately detecting Estrus, the period during which insemination should occur, is critical in order to maintain production and profit. However, conventional Estrus Detection depends on ocular inspection of the animals by skilled labour and this practice is expensive and relatively inefficient. Here, a wireless intravaginal probe for cattle capable of automatizing the process based on measurements of conductivity and temperature as well as movement sensing is presented and tested in-situ. These parameters can all be used independently to detect Estrus. A good conformity between the data collected with this probe and established Estrus patterns is demonstrated. Furthermore, the magnitude of natural daily variations and their impact on the individual parameters are discussed together with the impact of extraordinary events such as stress. Compared to existing alternatives, a multi-parameter approach like this is shown to be capable of much higher reliability, and also to be much more resistant to disturbances. The demonstrated system is very power efficient and capable of years of continuous isolated operation. Small to intermediate farm environments can be covered by the probe transmitters themselves with a single receiver unit, while bigger areas are handled with battery powered repeater units.
-
Wearable wireless sensor for Estrus Detection in cows by conductivity and temperature measurements
2015 IEEE SENSORS, 2015Co-Authors: L. Mattias Andersson, Hironao Okada, Ryotaro Miura, Yi Zhang, Toshihiro Itoh, Koji YoshiokaAbstract:A probe for wireless monitoring of the vaginal conductivity and temperature in cows has been developed, manufactured, and tested in-situ for approximately 48 hours. The cow was filmed during testing, and events and activities correlated with the obtained data. This allowed systematic variations due to stress, position and activity, as well as circadian patterns, to be identified. The probe has three electrode pairs for conductivity measurements that are probed consecutively, which allow electrode position related variations to be investigated. One of the main applications of this type of sensor is automated Estrus Detection, which is of high economic importance to farmers. Prior work has mainly relied on manual and/or implanted probes, both of which are inconvenient for commercial applications, and the collected data has usually consisted of a relatively limited number of points. This probe collects data from multiple positions at user defined intervals for extended periods of time, thus giving a much more complete picture of the behavior of the investigated quantities.