Mastitis Detection System Research Articles

Mastitis Detection System in Dairy Cow Milk based on Fuzzy Inference System using Electrical Conductivity and Power of Hydrogen Sensor Value

This study build a system for screening method to detect mastitis in dairy cow milk using Electrical Conductivity (EC) and Power of Hydrogen (pH) sensor. The value of EC and pH sensor is analyze using fuzzy logic to clarify the truth value between it. Mastitis in cows can cause loss and decrease milk production and quality in the dairy farmer industry. Currently, detecting mastitis in cow’s milk still done manually by looking at the color change of the milk and analyzing the cow behavior. This paper has designed a mastitis detection system using the Mamdani type fuzzy inference system and the final result will be displayed on an Android-based smartphone. From the test result, it was found that the system has 79.2% detection accuracy value. This system is suitable for alternative screening method that used to detect mastitis in dairy cow milk.

Changes in electrical conductivity, milk production rate and milk flow rate prior to clinical mastitis confirmation

Because a human observer is typically not present during milking process when automatic milking systems (AMS) are used, human observation is replaced by mastitis detection systems consisting of sensors and algorithms that create alerts. Several authors suggest that sensing systems to detect clinical mastitis (CM) are in need of improvement. The aim of this retrospective study was to observe trends over time of potential indicators of CM, thus identifying promising CM indicators and analysis methods. Data from a Northeastern USA commercial dairy farm with 1280 Holstein Friesian cows using 20 AMS units were used for the analysis. Over a one-year time period, there were 117 confirmed cases of CM in this herd. Thirty milking sessions prior to CM confirmation were used for this analysis (n = 3134). Of the 117 confirmed CM cases, 12% were in primiparous cows (L1), 24% in second lactation cows (L2) and 64% in third or greater lactation cows (L3+). Differences between group average CM-confirmed and non-CM quarters were observed prior to CM confirmation for quarter-level electrical conductivity (ECq), milk production rate (MPRq), average milk flow rate (AMFq) and peak milk flow rate (PMFq). Positive indications of CM were apparent well before confirmation of visual signs of CM for ECq and MPRq; however, positive indications for AMFq occurred only one day before CM confirmation. The combination of ECq, MPRq and AMFq is potentially useful for differentiating between an early (before visual signs of CM are manifested) detection and a false positive detection. Highlights Data from 1280 Holstein Friesian cows using 20 AMS units were used for the analysis The progression over time of changes in milk and milking characteristics was investigated in the period prior to clinical mastitis Changes in quarter electrical conductivity indicate it is possible to detect developing mastitis before clinical signs are manifested

An automated on-line clinical mastitis detection system using measurement of electrical parameters and milk production efficiency

This study aims to assess a novel method for automatic on-line detection of clinical mastitis in an automatic milking system using the measurement of electrical parameters, data of milk production efficiency and neural network from the novel mastitis detection sensor. The sensors were used to measure following 9 parameters: the quarter-level milk yield (MY; kg), average electrical conductivity in milking session (AEC; mS/cm), pH of milk (pH), temperatures of milk (TP; °C), milk production efficiency (MPE; kg/h) between successive milking sessions, milking time(MT; min), Milking efficiency (ME; kg/min), Milk production time(MPT; kg/h), cow number. The 9 measurements were inputted into a neural network to calculate the mastitis detection index. The network was trained with 44 healthy and 6 clinical mastitic cows. 42 of 44 healthy and 5 of 6 mastitic cows were classified correctly after training. The trained neural network predicted 164 of 176 healthy quarters correctly in different evaluation data sets. These results were better than the results obtained with the model usually used on the farm.

Use of milk electrical conductivity for the differentiation of mastitis causing pathogens in Holstein cows

Mastitis is one of the most prevalent and costly diseases in dairy cattle. Key components for adequate mastitis control are the detection of early stages of infection, as well as the selection of appropriate management interventions and therapies based on the causal pathogens associated with the infection. The objective was to characterize the pattern of electrical conductivity (EC) in milk during intramammary infection, considering specific mastitis-causing pathogen groups involvement. Cows (n = 200) identified by an in-line mastitis detection system with a positive deviation ≥15% in the manufacturer’s proprietary algorithm for EC (high electrical conductivity (HEC)) were considered cases and enrolled in the study at the subsequent milking. One control (CON) cow, within normal ranges for EC, was matched to each case. A composite milk sample was collected aseptically from each cow for bacteriological culture. Milk yield (MY) and EC were recorded for each milking during ±7 days relative to enrollment. Milk cultures were categorized into gram positive (GP), gram negative (GN), other (OTH) and no growth (NOG). Data were submitted for repeated-measures analysis with EC as the dependent variable and EC status at day −1, bacteriological culture category, parity number, stage of lactation and days relative to sampling as main independent variables. Average (± standard error (SE)) EC was greater in HEC than in CON cows (12.5 ± 0.5 v. 10.8 ± 0.5 mS/cm) on the day of identification (day −1). Milk yield on day −1 was greater in CON than in HEC (37.6 ± 5.1 v. 33.5 ± 5.2 kg). For practical management purposes, average EC on day −1 was similar for the different bacteriological culture categories: 11.4 ± 0.6, 11.7 ± 0.5, 12.3 ± 0.8 and 11.7 ± 0.5 mS/cm in GN, GP, OTH and NOG, respectively. Parity number was only associated with day −1 EC in HEC group, with the greatest EC values in parity 3 (12.3 ± 0.3 mS/cm), followed by parity 2 (11.9 ± 0.2 mS/cm), parity >3 (11.6 ± 0.5 mS/cm) and primiparous cows (11.2 ± 0.2 mS/cm). An effect on EC for the interaction of day relative to identification by pathogen gram category was observed. The same interaction effect was observed on daily MY. Overall, the level of variation for MY and EC between- and within-cows was substantial, and as indicated by the model diagnostic procedures, the magnitude of the variance in the cows in the CON group resulted in deviations from normality in the residuals. We concluded that characteristic temporal patterns in EC and MY in particular pathogen groups may provide indications for differentiation of groups of mastitis-causing pathogens. Further research to build detection models including EC, MY and cow-level factors is required for accurate differentiation.

Micro-controlled design of portable cattle mastitis detection system

This work presents a novel handheld mastitis detection device for detecting mastitis in dairy cattle, as well as a cattle management information system for managing cattle health information. The management information system comprises of three major subsystems—a mastitis detection device, an information display device, and a cloud database. The mastitis detection device detects and evaluates the degree of mastitis immediately before milking operations are carried out. The information display device shows the health information of the dairy cattle obtained from a cloud database and the database manages the milk production of a dairy farm. The combination of these two devices helps the dairy farmer to verify the mastitis of cattle effectively and find its health information rapidly.

Dynamic forecasting of individual cow milk yield in automatic milking systems

Accurate forecasting of dairy cow milk yield is useful to dairy farmers, both in relation to financial planning and for detection of deviating yield patterns, which can be an indicator of mastitis and other diseases. In this study we developed a dynamic linear model (DLM) designed to forecast milk yields of individual cows per milking, as they are milked in milking robots. The DLM implements a Wood's function to account for the expected total daily milk yield. It further implements a second-degree polynomial function to account for the effect of the time intervals between milkings on the proportion of the expected total daily milk yield. By combining these 2 functions in a dynamic framework, the DLM was able to continuously forecast the amount of milk to be produced in a given milking. Data from 169,774 milkings on 5 different farms in 2 different countries were used in this study. A separate farm-specific implementation of the DLM was made for each of the 5 farms. To determine which factors would influence the forecast accuracy, the standardized forecast errors of the DLM were described with a linear mixed effects model (lme). This lme included lactation stage (early, middle, or late), somatic cell count (SCC) level (nonelevated or elevated), and whether or not the proper farm-specific version of the DLM was used. The standardized forecast errors of the DLM were only affected by SCC level and interactions between SCC level and lactation stage. Therefore, we concluded that the implementation of Wood's function combined with a second-degree polynomial is useful for dynamic modeling of milk yield in milking robots, and that this model has potential to be used as part of a mastitis detection system.

Field validation of protocols developed to evaluate in-line mastitis detection systems

This paper reports on a field validation of previously developed protocols for evaluating the performance of in-line mastitis-detection systems. The protocols outlined 2 requirements of these systems: (1) to detect cows with clinical mastitis (CM) promptly and accurately to enable timely and appropriate treatment and (2) to identify cows with high somatic cell count (SCC) to manage bulk milk SCC levels. Gold standard measures, evaluation tests, performance measures, and performance targets were proposed. The current study validated the protocols on commercial dairy farms with automated in-line mastitis-detection systems using both electrical conductivity (EC) and SCC sensor systems that both monitor at whole-udder level. The protocol for requirement 1 was applied on 3 commercial farms. For requirement 2, the protocol was applied on 6 farms; 3 of them had low bulk milk SCC (128×103cells/mL) and were the same farms as used for field evaluation of requirement 1. Three farms with high bulk milk SCC (270×103 cells/mL) were additionally enrolled. The field evaluation methodology and results were presented at a workshop including representation from 7 international suppliers of in-line mastitis-detection systems. Feedback was sought on the acceptance of standardized performance evaluation protocols and recommended refinements to the protocols. Although the methodology for requirement 1 was relatively labor intensive and required organizational skills over an extended period, no major issues were encountered during the field validation of both protocols. The validation, thus, proved the protocols to be practical. Also, no changes to the data collection process were recommended by the technology supplier representatives. However, 4 recommendations were made to refine the protocols: inclusion of an additional analysis that ignores small (low-density) clot observations in the definition of CM, extension of the time window from 4 to 5 milkings for timely alerts for CM, setting a maximum number of 10 milkings for the time window to detect a CM episode, and presentation of sensitivity for a larger range of false alerts per 1,000 milkings replacing minimum performance targets. The recommended refinements are discussed with suggested changes to the original protocols. The information presented is intended to inform further debate toward achieving international agreement on standard protocols to evaluate performance of in-line mastitis-detection systems.

Mastitis diagnosis in ten Galician dairy herds (NW Spain) with automatic milking systems

Over the last few years, the adoption of automatic milking systems (AMS) has experienced significant increase. However, hardly any studies have been conducted to investigate the distribution of mastitis pathogens in dairy herds with AMS. Because quick mastitis detection in AMS is very important, the primary objective of this study was to determine operational reliability and sensibility of mastitis detection systems from AMS. Additionally, the frequency of pathogen-specific was determined. For this purpose, 228 cows from ten farms in Galicia (NW Spain) using this system were investigated. The California Mastitis Test (CMT) was considered the gold-standard test for mastitis diagnosis and milk samples were analysed from CMT-positive cows for the bacterial examination. Mean farm prevalence of clinical mastitis was 9% and of 912 milk quarters examined, 23% were positive to the AMS mastitis detection system and 35% were positive to the CMT. The majority of CMT-positive samples had a score of 1 or 2 on a 1 (lowest mastitis severity) to 4 (highest mastitis severity) scale. The average sensitivity and specificity of the AMS mastitis detection system were 58.2% and 94.0% respectively being similar to other previous studies, what could suggest limitations for getting higher values of reliability and sensibility in the current AMSs. The most frequently isolated pathogens were Streptococcus dysgalactiae (8.8%), followed by Streptococcus uberis (8.3%) and Staphylococcus aureus (3.3%). The relatively high prevalence of these pathogens indicates suboptimal cleaning and disinfection of teat dipping cups, brushes and milk liners in dairy farms with AMS in the present study.

Effect of sensor systems for cow management on milk production, somatic cell count, and reproduction

To improve management on dairy herds, sensor systems have been developed that can measure physiological, behavioral, and production indicators on individual cows. It is not known whether using sensor systems also improves measures of health and production in dairy herds. The objective of this study was to investigate the effect of using sensor systems on measures of health and production in dairy herds. Data of 414 Dutch dairy farms with (n=152) and without (n=262) sensor systems were available. For these herds, information on milk production per cow, days to first service, first calving age, and somatic cell count (SCC) was provided for the years 2003 to 2013. Moreover, year of investment in sensor systems was available. For every farm year, we determined whether that year was before or after the year of investment in sensor systems on farms with an automatic milking system (AMS) or a conventional milking system (CMS), or whether it was a year on a farm that never invested in sensor systems. Separate statistical analyses were performed to determine the effect of sensor systems for mastitis detection (color, SCC, electrical conductivity, and lactate dehydrogenase sensors), estrus detection for dairy cows, estrus detection for young stock, and other sensor systems (weighing platform, rumination time sensor, fat and protein sensor, temperature sensor, milk temperature sensor, urea sensor, β-hydroxybutyrate sensor, and other sensor systems). The AMS farms had a higher average SCC (by 12,000cells/mL) after sensor investment, and CMS farms with a mastitis detection system had a lower average SCC (by 10,000cells/mL) in the years after sensor investment. Having sensor systems was associated with a higher average production per cow on AMS farms, and with a lower average production per cow on CMS farms in the years after investment. The most likely reason for this lower milk production after investment was that on 96% of CMS farms, the sensor system investment occurred together with another major change at the farm, such as a new barn or a new milking system. Most likely, these other changes had led to a decrease in milk production that could not be compensated for by the use of sensor systems. Having estrus detection sensor systems did not improve reproduction performance. Labor reduction was an important reason for investing in sensor systems. Therefore, economic benefits from investments in sensor systems can be expected more from the reduction in labor costs than from improvements in measures of health and production in dairy herds.

Development of protocols to evaluate in-line mastitis-detection systems

This paper proposes and discusses a methodology to evaluate the performance of automated mastitis-detection systems with respect to their practical value on farm. The protocols are based on 3 on-farm requirements: (1) to detect cows with clinical mastitis promptly and accurately to enable timely and appropriate treatment, (2) to identify cows with high somatic cell count to manage bulk milk SCC levels, and (3) to report the mastitis infection status of cows at the end of lactation to support decisions on individual cow dry-cow therapy. Separate protocols for each requirement are proposed and discussed, including gold standards, evaluation tests, performance indicators, and performance targets. Aspects that require further research or clarification are identified. Actual field data are used as examples. Further debate is invited, the aim being to achieve international agreement on how to evaluate and report performance of different mastitis-detection technologies. Better performance information will allow farmers to compare different mastitis-detection systems sensibly and fairly before investing. Also, the use of evaluation protocols should help technology providers to refine current, or develop new, automated mastitis-detection systems. Such developments are likely to accelerate adoption of these systems, potentially leading to improved animal health, milk quality, and labor productivity.

Mastitis alert preferences of farmers milking with automatic milking systems

The aim of this study was to assess farmers’ preferences for the performance characteristics of mastitis detection systems. Additionally, we looked at whether certain groups of farmers could be distinguished with specific preferences. Farmers’ opinions concerning mastitis detection systems, as well as general information about the farm and the farmer, were investigated with a standard questionnaire. The second part of the questionnaire was specifically aimed at elucidating preferences. Definitions of time windows and performance parameters, such as sensitivity and specificity, were incorporated into characteristics of a detection system (attributes) that reflect farmers’ daily experience. Based on data from 139 farmers, we concluded that, on average, they prefer a clinical mastitis detection system that produces a low number of false alerts, while alerting in good time and with emphasis on the more severe cases. These 3 attributes were evaluated as more important than the 3 other attributes, representing the costs of the detection system, the number of missed cases, and how long before clinical signs alerts need to be given. Variation in importance per attribute, however, was high, denoting that farmers’ preferences differ considerably. Although some significant relationships were found between farm characteristics and attributes, no clear groups of farmers with specific preferences could be distinguished. Based on these results, we advise making detection systems adaptable for the farmers to satisfy their preferences and to match the circumstances on the farm. Furthermore, these results support that for evaluation of detection algorithms comparisons have to be made at high levels of specificity (e.g., 99%) and time windows have to be kept small (preferably no more than 24h).

An automated in-line clinical mastitis detection system using measurement of conductivity from foremilk of individual udder quarters

AIM: To assess a novel method for automatic in-line detection of clinical mastitis. METHODS: For a brief period at the start of milking for each cow, electrical conductivity of foremilk was measured for each quarter in turn, using a single sensor installed in the long milk tube (LMT) about 1.5 m downstream from the milking-machine claw. Sequential separation of flow between udder quarters was achieved by control of pulsation to individual teatcups within a conventional cluster. The ratio of conductivity values between quarters was used as an indicator of mastitis status. The concept was evaluated initially in a pilot trial in a 200-cow herd milked in a 23-stall swing-over herringbone milking parlour. It was then tested rigorously in a field trial in a 640-cow herd milked in a 50-stall rotary milking parlour. Both trials were conducted in the Waikato region of New Zealand. In the latter trial, sensor results were compared with visual inspection of a commercial in-line mastitis filter fitted to each milking unit. These filters were inspected for clots immediately after every cow's milking, for 3 weeks. The dataset of approximately 27,000 individual milkings was tested against several published or potential alter- native ‘gold standards’ for diagnosing clinical mastitis. RESULTS: In the pilot trial, 12–14 clinical events were detected out of 19 true clinical quarters, with a false-alert rate of between three and five false electrical-conductivity alerts per 1,000 individual milkings. In the more rigorous field trial, sensitivity ranged from 68 to 88%, and the false-alert rate (false-alert episodes per 1,000 individual milkings) ranged from 2.3 to 7.0. CONCLUSION: The novel clinical mastitis detection system, based on separation of the flow and measurement of electrical conductivity from foremilk of individual udder quarters, has the potential to provide a new tool for helping farmers to monitor clinical mastitis in herds milked with conventional clusters.

Indicators of inflammation in the diagnosis of mastitis.

Mastitis affects the quality of milk and is a potential health risk for the other cows. In a well managed dairy herd, in addition to clinical mastitis, subclinical mastitis should be efficiently detected. Bacteriological sampling is not feasible as a routine test to identify subclinical mastitis, and indirect tests of mastitis are more suitable for selecting cows with intramammary infections for subsequent bacteriological sampling. Mastitis affects the composition of milk, and the degree of changes depends on the infecting agent and the inflammatory response. Indicators of inflammation in the milk which can be determined using rapid, reliable and easy routine techniques, can be used for the early detection of mastitis. The measuring of the somatic cell count in milk is the standard method, but the analysis technique is problematic for routine use in herds. The most promising parameters for monitoring subclinical mastitis are milk N-acetyl-beta-D-glucosaminidase activity, lactose, and electrical conductivity along with some other indicators such as optical and milk flow measurements, preferably with an inter-quarter evaluation included in the test. Acute phase proteins, haptoglobin and serum amyloid A, are also potential candidates for mastitis monitoring. New mastitis detection systems which can be adapted into on-line use are urgently needed, since dairy units are growing bigger and automatic milking systems are being taken into use.

Application of a neural network to analyse on-line milking parlour data for the detection of clinical mastitis in dairy cows

As part of research towards an on-line mastitis detection system, standard back-propagation neural networks to classify healthy and clinical mastitic quarters were explored. The usage of back-propagation neural networks is discussed. A neural network for clinical mastitis detection is presented. This network used automatically collected quarter electrical conductivity data as input. The network was trained with 17 healthy and 13 clinical mastitic quarters. All healthy and 12 of 13 mastitic quarters were classified correctly after training. The trained neural network predicted 34 of 38 healthy quarters correctly in different evaluation data sets. For mastitic quarters, related data had to be used, and 21 of 38 mastitic quarters were classified correctly. We concluded that a back-propagation neural network could indeed separate healthy from clinical quarters in an experimental setting. Further development should include the use of different input parameters and comparisons with other analysis techniques.

Comparison of Electrical Conductivity of Milk with Other Indirect Methods for Detection of Subclinical Mastitis

Efficacy of detecting subclinical mastitis by electrical conductivity of milk was compared with that of other indirect methods including chloride, sodium, potassium, lactose, bovine serum albumin, and somatic cell count of milk. Quarter samples of foremilk, strippings, and bucket milk were obtained from 75 cows at the afternoon milking over 8 wk, Infection of quarters was ascertained by bacteriological analysis.Electrical conductivity, chloride, and sodium content of milk were more accurate for predicting infection status of quarters than were other variables. Most variables were more accurate in predicting infection when measures were in strippings rather than in foremilk or bucket milk. For measures in strippings, misclassifications by electrical conductivity were 11.2 and 15.5% for false positives and false negatives. The accuracy of the electrical conductivity of milk for detection of subclinical mastitis compared favorably with all indirect methods. Accuracy of detection and adaptability to both manual and automatic cow-side mastitis detection systems indicate that the method has considerable potential as a screening test for subclinical mastitis.