Dataset Card for Horse-30

  Dataset Summary

Pose estimation is an important tool for measuring behavior, and thus widely used in technology, medicine and biology. Due to innovations in both deep learning algorithms and large-scale datasets pose estimation on humans has gotten very powerful. However, typical human pose estimation benchmarks, such as MPII pose and COCO, contain many different individuals (>10K) in different contexts, but only very few example postures per… See the full description on the dataset page: https://huggingface.co/datasets/mwmathis/Horse-30.

Pose estimation is an important tool for measuring behavior, and thus widely used in technology, medicine and biology. Due to innovations in both deep learning algorithms and large-scale datasets pose estimation on humans has gotten very powerful. However, typical human pose estimation benchmarks, such as MPII pose and COCO, contain many different individuals (>10K) in different contexts, but only very few example postures per individual. In real world application of pose estimation, users want to estimate the location of user-defined bodyparts by only labeling a few hundred frames on a small subset of individuals, yet want this to generalize to new individuals. Thus, one naturally asks the following question: Assume you have trained an algorithm that performs with high accuracy on a given (individual) animal for the whole repertoire of movement - how well will it generalize to different individuals that have slightly or a dramatically different appearance? Unlike in common human pose estimation benchmarks here the setting is that datasets have many (annotated) poses per individual (>200) but only few individuals (1-25). To allow the field to tackle this challenge, we developed a novel benchmark, called Horse-10, comprising 30 diverse Thoroughbred horses, for which 22 body parts were labeled by an expert in 8,114 frames. Horses have various coat colors and the “in-the-wild” aspect of the collected data at various Thoroughbred yearling sales and farms added additional complexity.

https://raw.githubusercontent.com/Masterx-AI/Project_Horse_Sruvival_Prognostication/main/horse.jpg" alt="">

Description:

Predict whether or not a horse can survive based upon past medical conditions.

Noted by the "outcome" variable in the data.

Content:

All of the binary representation have been converted into the words they actually represent. However, a fuller description is provided by the data dictionary (datadict.txt).

There are a lot of NA's in the data. This is the real struggle here. Try to find a way around it through imputation or other means.

Attribute Information:

1: surgery? 1 = Yes, it had surgery 2 = It was treated without surgery

2: Age 1 = Adult horse 2 = Young (< 6 months)

3: Hospital Number - numeric id - the case number assigned to the horse (may not be unique if the horse is treated > 1 time)

4: rectal temperature - linear - in degrees celsius. - An elevated temp may occur due to infection. - temperature may be reduced when the animal is in late shock - normal temp is 37.8 - this parameter will usually change as the problem progresses, eg. may start out normal, then become elevated because of the lesion, passing back through the normal range as the horse goes into shock 5: pulse - linear - the heart rate in beats per minute - is a reflection of the heart condition: 30 -40 is normal for adults - rare to have a lower than normal rate although athletic horses may have a rate of 20-25 - animals with painful lesions or suffering from circulatory shock may have an elevated heart rate

6: respiratory rate - linear - normal rate is 8 to 10 - usefulness is doubtful due to the great fluctuations

7: temperature of extremities - a subjective indication of peripheral circulation - possible values: 1 = Normal 2 = Warm 3 = Cool 4 = Cold - cool to cold extremities indicate possible shock - hot extremities should correlate with an elevated rectal temp.

8: peripheral pulse - subjective - possible values are: 1 = normal 2 = increased 3 = reduced 4 = absent - normal or increased p.p. are indicative of adequate circulation while reduced or absent indicate poor perfusion

9: mucous membranes - a subjective measurement of colour - possible values are: 1 = normal pink 2 = bright pink 3 = pale pink 4 = pale cyanotic 5 = bright red / injected 6 = dark cyanotic - 1 and 2 probably indicate a normal or slightly increased circulation - 3 may occur in early shock - 4 and 6 are indicative of serious circulatory compromise - 5 is more indicative of a septicemia

10: capillary refill time - a clinical judgement. The longer the refill, the poorer the circulation - possible values 1 = < 3 seconds 2 = >= 3 seconds

11: pain - a subjective judgement of the horse's pain level - possible values: 1 = alert, no pain 2 = depressed 3 = intermittent mild pain 4 = intermittent severe pain 5 = continuous severe pain - should NOT be treated as a ordered or discrete variable! - In general, the more painful, the more likely it is to require surgery - prior treatment of pain may mask the pain level to some extent

12: peristalsis - an indication of the activity in the horse's gut. As the gut becomes more distended or the horse becomes more toxic, the activity decreases - possible values: 1 = hypermotile 2 = normal 3 = hypomotile 4 = absent

13: abdominal distension - An IMPORTANT parameter. - possible values 1 = none 2 = slight 3 = moderate 4 = severe - an animal with abdominal distension is likely to be painful and have reduced gut motility. - a horse with severe abdominal distension is likely to require surgery just tio relieve the pressure

14: nasogastric tube - this refers to any gas coming out of the tube - possible values: 1 = none 2 = slight 3 = significant - a large gas cap in the stomach is likely to give the horse discomfort

15: nasogastric reflux - possible values 1 = none 2 = > 1 liter 3 = < 1 liter - the greater amount of reflux, the more likelihood that there is some serious obstruction to the fluid passage from the rest of the intestine

16: nasogastric reflux PH - linear - scale is from 0 to 14 with 7 being neutral - normal values are in the 3 to 4 range

17: rectal examination - feces - possible values 1 = normal 2 = increased 3 = decreased 4 = absent - absent feces probably indicates an obstruction

18: abdomen - possible values 1 = normal 2 = other 3 = firm feces in the large intestine 4 = distended small intestine 5 = distended large intestine - 3 is probably an obstruction caused by a mechanical impaction and is normally treated medically - 4 and 5 indicate a surgical lesion

19: packed cell volume - linear - the # of red cells by volume in the blood - normal range is 30 to 50. The level rises as the circulation becomes compromised or as the animal becomes dehydrat...

Context

Horse breeds are not a very easy task for recognition even for the human mind. What about algorithms?

Content

Dataset creating is in progress, so the full description will be a little bit later.

The images are labeled by the file prefixes. Labels correspond to the following horse breeds: 01=>Akhal-Teke; 02=>Appaloosa; 03=>Orlov Trotter; 04=>Vladimir Heavy Draft; 05=>Percheron; 06=>Arabian; 07=>Friesian

Acknowledgments

Some images contain fragments of copyright photos, so the database can be used without the consent of the image authors only for educational and research purposes.

Inspiration

How image recognition depends on different factors (a number of classes, a size in pixels, and so on)?

Horse10

## Overview

Horse10 is a dataset for computer vision tasks - it contains Horse annotations for 976 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Medium J218: COLUMBIA BLOOD AGAR WITH 10% HORSE BLOOD

When a rider maintains contact on the reins, rein tension will vary continuously in synchronicity with the horse's gait and stride. This continuous variation makes it difficult to isolate the rein tension variations that represent a rein tension signal, complicating interpretation of rein tension data from the perspective of horse-rider interaction. This study investigated (1) the characteristics of a rein tension signal and (2) horse response to a rein tension signal for backing, comparing pressure applied by a bit (bridle), or by a noseband (halter). Twenty Warmblood horses (10 young, 10 adult) wearing a rein tension meter were trained to step back in the aisle of a stable. The handler stood next to the horse's withers, applying tension on the reins until the horse stepped back. This was repeated eight times with the bridle and eight times with the halter. Data analysis was performed using mixed linear and logistic regression models. Horses displaying behaviors other than backing showed significantly increased response latency and rein tension. Inattentive behavior was significantly more common in the halter treatment and in young horses, compared with the bridle treatment and adult horses. Evasive behaviors with the head, neck, and mouth were significantly more common in the bridle treatment than in the halter treatment and the occurrence of head/neck/mouth behaviors increased with increasing rein tension and duration of the rein tension signal. When controlling for behavior, the horses responded significantly faster and to a lighter rein tension signal in the bridle treatment than in the halter treatment. By scrutinizing data on rein tension signals in relation to horse behavior and training exercise, more can be learnt about the horse's experience of the pressures applied and the timing of the release. This can assist in developing ways to evaluate rein tension in relation to correct use of negative reinforcement.

Characteristics of the datasets used for the statistical analyses of covering data regarding WFFS effects from 10 German studbooks of riding horses, in dependence of the applied restrictions.

The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset. They were collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton.

The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.

Here are the classes in the dataset, as well as 10 random images from each: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck

The classes are completely mutually exclusive. There is no overlap between automobiles and trucks. "Automobile" includes sedans, SUVs, things of that sort. "Truck" includes only big trucks. Neither includes pickup trucks.

Rapidata Animals-10

We took this existing Animals-10 dataset from kaggle and cleaned it using Rapidata's crowd, as detailed in this blog post. If you get value from this dataset and would like to see more in the future, please consider liking it.

  Dataset Details

10 classes: Butterfly, Cat, Chicken, Cow, Dog, Elephant, Horse, Sheep Spider, Squirrel 23554 Images In total, 124k labels were collected by human annotators, so each image is cross-validated on average by 5… See the full description on the dataset page: https://huggingface.co/datasets/Rapidata/Animals-10.

Current profile data from Downward-looking ADCP #01 on FPF Thunder Horse, 2.819000e+01N, 8.850000e+01W, 2007/01/02 00:09 through 2007/12/21 23:50 _NCProperties=version=1|netcdflibversion=4.4.1.1|hdf5libversion=1.8.19 acknowledgement=Data collection funded by various oil industry operators in accordance with BSEE Notice to Lessees cdm_data_type=TimeSeriesProfile cdm_profile_variables=time, profile_id cdm_timeseries_variables=platform, latitude, longitude, instrument, crs contributor_name=BP Inc Conventions=CF-1.6, ACDD-1.3, IOOS Metadata Profile Version 1.2, COARDS Easternmost_Easting=-88.5 featureType=TimeSeriesProfile geospatial_bounds=POINT (28.19 -88.5) geospatial_bounds_crs=EPSG:4326 geospatial_bounds_vertical_crs=EPSG:5703 geospatial_lat_max=28.19 geospatial_lat_min=28.19 geospatial_lat_units=degrees_north geospatial_lon_max=-88.5 geospatial_lon_min=-88.5 geospatial_lon_units=degrees_east geospatial_vertical_max=905.1 geospatial_vertical_min=72.9 geospatial_vertical_positive=down geospatial_vertical_resolution=32 geospatial_vertical_units=m history=Generated by convert_to_nc.py version 0.0.1 id=urn:ioos:sensor:WMO:42887.02:ADCP.01 infoUrl=www.woodsholegroup.com institution=GCOOS instrument=In Situ/Laboratory Instruments > Profilers/Sounders > Acoustic Sounders > ADCP > Acoustic Doppler Current Profiler instrument_vocabulary=GCMD Earth Science Keywords. Version 8.4 keywords_vocabulary=GCMD Science Keywords naming_authority=com.woodsholegroup NCProperties=version=1netcdflibversion=4.6.0hdf5libversion=1.10.1 Northernmost_Northing=28.19 platform=In Situ Ocean-based Platforms > OCEAN PLATFORM/OCEAN STATIONS > DRILLING PLATFORMS platform_name=Thunder Horse platform_vocabulary=GCMD Earth Science Keywords. Version 8.4 processing_level=Data QA'd by WHG oceanographer program=BSEE Notice to Lessees 2018-G01 and predecessors project=WHG NTL Data Processing and QA Subcontract to GCOOS sea_name=Gulf of Mexico source=T Horse BP -2819-8850-070102-071221-42887-01-10.mat sourceUrl=(local files) Southernmost_Northing=28.19 standard_name_vocabulary=CF Standard Name Table v67 station_type=FPF subsetVariables=platform, latitude, longitude, instrument, crs, time, profile_id time_coverage_duration=P0Y11M19DT23H41M0S time_coverage_end=2007-12-21T23:50:00Z time_coverage_resolution=10 time_coverage_start=2007-01-02T00:09:00Z water_depth=1844 Westernmost_Easting=-88.5 wmo_platform_code=42887

The Equine Death and Breakdown report lists horses that have broken down, been injured, or have died at New York State race tracks.

We describe and analyze a dataset that comprises horse movement. Data was collected during a forelimb and hindlimb lameness induction study. Forelimb and Hindlimb lameness were induced on separate days and a baseline measurement (no induction) was conducted before each induction. The dataset comprises 85 individual datasets, where 39 belong to the forelimb lameness part (n = 10 horses, where for each horse the following datasets are present: baseline in hand (n=10), baseline ridden (n=10), induction in hand (n=9) and induction ridden (n=10)) and 46 belong to the hindlimb lameness part (n = 12 horses, where for each horse the following datasets are present: baseline in hand (n = 12), baseline ridden (n = 12), induction in hand (n = 11), induction ridden (n = 11)). Fifteen sensor devices were attached to the horse and one on the rider, the locations of which can be found in the readme file. The devices, among others, contained a 3-axis accelerometer, gyroscope, and magnetometer that were sampled at 500 Hz. To demonstrate how this dataset can be used, we evaluated the kinematic adaptations to forelimb and hindlimb lameness during in hand and ridden walk, trot and tölt.

Using a split sample design 30 ejaculates from 10 different stallions were analyzed as fresh spermatozoa, and another aliquot from the same ejaculate was analyzed as a frozen thawed sample. The proteome was studied under both conditions using UHPLC/MS/MS and bioinformatic analysis conducted to identify discriminant variables between both conditions.

This dataset is about book subjects. It has 1 row and is filtered where the books is Vetting the horse. It features 10 columns including number of authors, number of books, earliest publication date, and latest publication date.

Summary of a group of Thoroughbred horses (n = 20) at the time of placement into an inspiratory muscle training treatment (n = 10) or control (n = 10) group based on when they finished exercise training and their current exercise workload.

Bit-related oral lesions are common and may impair horse welfare. The aim of this study was to investigate the prevalence of oral lesions and their risk factors in a sample of Finnish event horses. The rostral part of the oral cavity (the bit area) of 208 event horses (127 warmbloods, 52 coldbloods, and 29 ponies) was examined in a voluntary inspection after the last competition phase, i.e., the cross-country test. Acute lesions were observed in 52% (109/208) of the horses. The lesion status was graded as no acute lesions for 48% (99/208), mild for 22% (45/208), moderate for 26% (55/208) and severe for 4% (9/208) of the horses. The inner lip commissure was the most common lesion location observed in 39% (81/208) of the horses. A multivariable logistic regression model with data of 174 horses was applied to risk factor analysis. Horses wearing thin (10–13 mm) (OR 3.5, CI 1.4–8.7) or thick (18–22 mm) (OR 3.4, CI 1.4–8.0) bits had a higher risk of moderate/severe lesion status than horses wearing middle-sized (14–17 mm) bits (P = 0.003). Breed was associated with moderate/severe lesion status (P = 0.02). The risk was higher for warmbloods (reference group) and coldbloods (OR 2.0, CI 0.88–4.7) compared with ponies (OR 0.2, CI 0.04–0.87). Mares were at higher risk of moderate/severe lesion status (OR 2.2, CI 1.1–4.5) than geldings (reference group) (P = 0.03). Bar lesions were more common in horses with unjointed bits (40%, 8/20) than with basic double-jointed (10%, 5/52), formed double-jointed (8%, 6/78) or single-jointed bits (5%, 2/40) (Fisher's exact test, P = 0.002). The results of this study suggest that thin and thick bits and mare sex should be considered risk factors for mouth lesions. In addition, in this sample ponies had smaller risk for lesions than other horse breeds. We encourage adopting bit area monitoring as a new routine by horse handlers and as a welfare measure by competition organizers for randomly drawn horses.

Individual percentages, median fluorescent intensities and concentrations for each horse that were used to generate figure graphs are compiled in labeled data tables. (A) Percentage of IgE+ monocytes out of total cells in unsorted, MACS sorted and MACS+FACS sorted samples from 18 different horses in Fig 2D. (B) Percentage of CD23- cells out of total IgE+ monocytes in Fig 3D. (C) Clinical scores of allergic in in Fig 4A. (D) Percentage of IgE+ monocytes out of total monocytes in Fig 4C. (E) Percentage of CD16+ cells out of total IgE+ monocytes in Fig 4D. (F) Serum total IgE (ng/ml) measured by bead-based assay in Fig 5A. (G) IgE median fluorescent intensity (MFI) of IgE mAb 176 (Alexa Fluor 488) on IgE+ monocytes in Fig 5B. (H) Combined serum total IgE and IgE MFI on IgE+ monocytes in Fig 5C. (I) Percentage of monocytes out of total IgE+ cells in Fig 6A. (J) Secreted concentration of IL-10 (pg/ml), IL-4 (pg/ml), IFN? (MFI) and IL-17A (MFI) as measured by bead-based assay in Fig 6B. (K) Percentage of CD16+ cells out of total IgE- CD14+ monocytes. B-H,K show allergic (n = 7) and nonallergic (n = 7) horses, J shows allergic (n = 8) and nonallergic (n = 8) horses in October 2019. C-H,K show data points collected from April 2018-March 2019. (XLSX)

This dataset is about book subjects. It has 5 rows and is filtered where the books is The sporting horse : in pursuit of equine excellence. It features 10 columns including number of authors, number of books, earliest publication date, and latest publication date.

IntroductionThe recent discovery of Theileria haneyi, a tick-borne hemoparasite that causes mild clinical signs of equine piroplasmosis, has added complexity to the diagnosis of this reportable disease, which is prevalent among equids globally. Knowledge gaps regarding competent tick vectors that can transmit T. haneyi and the recent outbreak of Haemaphysalis longicornis in the US has prompted us to conduct this study. Our objective was to investigate whether H. longicornis can transstadially transmit T. haneyi to horses.Materials and methodsHaemaphysalis longicornis larvae (0.5 g) and nymphs (n = 500) were fed on a splenectomized T. haneyi-infected horse for parasite acquisition. During the tick feeding period, parasitemia was monitored using nested PCR (nPCR) and blood smear analysis. The acquisition ticks fed until repletion and were transferred to an incubator for molting. Concomitantly, red blood cells (RBCs) were collected from the acquisition horse for further infection. Freshly molted nymphs (n = 282) and adults (n = 212), 22 offsprings of the acquisition larvae and nymphs, respectively, were placed on two individual naïve spleen-intact horses for transstadial parasite transmission. Another naïve horse was inoculated with 1 mL of RBCs from the acquisition horse. After tick infestation and RBC inoculation, the transmission horses were monitored for 38 days for the presence of T. haneyi DNA in their peripheral blood using nPCR, as well as for any clinical signs of infection.Results and discussionThe splenectomized acquisition horse developed canonical signs of acute T. haneyi infection during tick acquisition. The percentage of parasitized RBCs in the acquisition horse varied between 2.2 and 8.1% during the tick feeding stage. Out of a subset of 10 engorged larvae that fed on the acquisition horse, all ticks tested nPCR positive for T. haneyi. However, only 4 out of 10 engorged nymphs that fed on the acquisition horse tested PCR positive for T. haneyi. We found no evidence for the presence of parasite DNA in the transmission ticks or in the horse’s blood nor did we observe any clinical signs of T. haneyi infection in the transmission horses. In contrast, the horse inoculated with RBCs from the acquisition horse tested nPCR positive for T. haneyi 15 days after inoculation. It showed parasites in blood smear and developed canonical clinical signs of acute infection.ConclusionThe findings show that H. longicornis ticks cannot transstadially transmit T. haneyi to horses.