Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour

Walton, E. K.; Casey, Christy; Mitsch, Jürgen; Vázquez-Diosdado, Jorge A.; Yan, Jing; Dottorini, Tania; Ellis, Keith A.; Winterlich, Anthony; Kaler, Jasmeet

doi:10.1098/rsos.171442

Cited by 88 publications

(113 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results in Table 4 show basic evaluation measures for diagnosing by symptoms which achieves high‫‬ accuracy with percentage 0.97 % with error rate 0.03%. Table 5 shows its confusion matrix.For testing and evaluating performance of diagnosing by chest xray images, (155 chest x-ray images) were collected and classified by five experts in domain, then divided into four classes as shown in Table 6 Table7 shows statistical measures applied to determine the efficiency of diagnosing by images [27][28][29][30].…”

Section: Resultsmentioning

confidence: 99%

A Novel Intelligent System for Diagnosing some of Humans' Respiratory System Diseases

E.¹,

E.²,

A³

2019

IJCA

View full text Add to dashboard Cite

This paper presents a novel intelligent system for diagnosing some of humans' respiratory diseases. The proposed system aims to simulate the real medical diagnosing processes. It was adopted in diagnosis on two main parts; knowledge base (KB) and image processing (IP). This paper combines two diagnostic methods; the decision tree (DT) method which used J48 algorithm in WEKA 3.7, and the gray level cooccurrence matrix (GLCM) method for extracting second order statistical texture features of chest x-ray images. The weighted euclidean distance (WED) algorithm was used for feature matching. The final decision calculated by probability measure method for independent events, which is depending on "multiplication rule". The proposed system implemented via visual studio.net 2017; used for designing the main graphical user interface (GUI), MATLAB17; used for image processing diagnoses, and LabVIEW17; used for knowledge base diagnoses. The obtained results show that there is a good agreement between expert's diagnoses and proposed system diagnoses with a high accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%

A Novel Intelligent System for Diagnosing some of Humans' Respiratory System Diseases

E.¹,

E.²,

A³

2019

IJCA

View full text Add to dashboard Cite

show abstract

“…Figure 1 illustrates this process. The first phase classification was performed using our previously published algorithms in Walton et al [11], where we focused on the development of classification algorithms for standing, walking and lying in sheep, while the second phase classification was developed in the current study where we explicitly focus on discriminating between lame and nonlame samples within each of the different behaviours.…”

Section: Methodsmentioning

confidence: 99%

“…In this study, we extend our previous algorithmic approach [11] to classify sheep activity, using an earbased accelerometer and gyroscope sensor to investigate for the first time (i) if we could detect lameness in sheep using both accelerometer and gyroscope signals, (ii) which machine learning algorithms perform best at classifying lameness and what are the most important features for lameness classification and (iii) if we can classify lameness in sheep across a range of daily activities (walking, standing and lying).…”

Section: Introductionmentioning

confidence: 99%

Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep

et al. 2020

Self Cite

View full text Add to dashboard Cite

Lameness in sheep is the biggest cause of concern regarding poor health and welfare among sheep-producing countries. Best practice for lameness relies on rapid treatment, yet there are no objective measures of lameness detection. Accelerometers and gyroscopes have been widely used in human activity studies and their use is becoming increasingly common in livestock. In this study, we used 23 datasets (10 non-lame and 13 lame sheep) from an accelerometer-and gyroscope-based ear sensor with a sampling frequency of 16 Hz to develop and compare algorithms that can differentiate lameness within three different activities (walking, standing and lying). We show for the first time that features extracted from accelerometer and gyroscope signals can differentiate between lame and non-lame sheep while standing, walking and lying. The random forest algorithm performed best for classifying lameness with an accuracy of 84.91% within lying, 81.15% within standing and 76.83% within walking and overall correctly classified over 80% sheep within activities. Both accelerometer-and gyroscope-based features ranked among the top 10 features for classification. Our results suggest that novel behavioural differences between lame and non-lame sheep across all three activities could be used to develop an automated system for lameness detection.

show abstract

“…which included the evaluation of different window sizes (3s, 5s and 7s) with 50% overlap between two adjacent windows. In the research, the research involved two stages which were first to determine the best window sizes and second to obtain the highest performance of classifier used [31]. Based on previous researches also, it is mentioned that the shorter the window size, the faster a movement detection and at the same time improve the energy expenditure while larger window sizes are more suitable for complex movement recognition [27,30].…”

Section: Effect Of Window Size In Movement Recognitionmentioning

confidence: 99%

Common Sport Movement Recognition from Wearable Inertial Sensor

Amir as’ari*,

Shahar,

Ghazali

et al. 2020

IJRTE

View full text Add to dashboard Cite

Common sport movements are the fundamental movements in all kind of sports. There are lots of researches done on classifying sports movements but very few are focused on common sport movement which is the focus of this project. The main aim is to develop an automated algorithm that can detect the common sport movements into walking based and jumping based movement from the wearable inertial sensor. The inertial sensor signals obtained from ten subjects were processed and grouped into walking-based and jumping-based movements. Time-domain features were extracted from the signals. Finally, the classification and performance evaluation process is done by using three different classification models (Support Vector Machine (SVM), k Nearest Neighbor (k-NN) and Decision Tree) with fixed window size of 1.28 seconds at the first stage. At the second stage, the best model from the first stage was used to determine the best window size in extracting the features that represent the walking and jumping based movement. As a result, SVM algorithm with window size of 2 seconds produced the highest overall accuracy of 95.4 % which proved to be the best classification algorithm to classify the common sport movements into walking-based and jumping-based movements. It is hoped that the outcome from this project can be used as a part of developing the overall automated sport movement recognition which is useful for the analyst, coach or player to analyse the performance of the player as well as predicting total energy consumption in preventing the injury among the player

show abstract

Evaluation of sampling frequency, window size and sensor position for classification of sheep behaviour

Cited by 88 publications

References 37 publications

A Novel Intelligent System for Diagnosing some of Humans' Respiratory System Diseases

A Novel Intelligent System for Diagnosing some of Humans' Respiratory System Diseases

Automated detection of lameness in sheep using machine learning approaches: novel insights into behavioural differences among lame and non-lame sheep

Common Sport Movement Recognition from Wearable Inertial Sensor

Contact Info

Product

Resources

About