Automated Classification of Changes of Direction in Soccer Using Inertial Measurement Units

Changes of direction (COD) are an important aspect of soccer match play. Understanding the physiological and biomechanical demands on players in games allows sports scientists to effectively train and rehabilitate soccer players. COD are conventionally recorded using manually annotated time-motion video analysis which is highly time consuming, so more time-efficient approaches are required. The aim was to develop an automated classification model based on multi-sensor player tracking device data to detect COD > 45°. Video analysis data and individual multi-sensor player tracking data (GPS, accelerometer, gyroscopic) for 23 academy-level soccer players were used. A novel ‘GPS-COD Angle’ variable was developed and used in model training; along with 24 GPS-derived, gyroscope and accelerometer variables. Video annotation was the ground truth indicator of occurrence of COD > 45°. The random forest classifier using the full set of features demonstrated the highest accuracy (AUROC = 0.957, 95% CI = 0.956–0.958, Sensitivity = 0.941, Specificity = 0.772. To balance sensitivity and specificity, model parameters were optimised resulting in a value of 0.889 for both metrics. Similarly high levels of accuracy were observed for random forest models trained using a reduced set of features, accelerometer-derived variables only, and gyroscope-derived variables only. These results point to the potential effectiveness of the novel methodology implemented in automatically identifying COD in soccer players.

Download Full-text

A Tree Based Approach for Multi-class Classification of Surgical Procedures Using Structured and Unstructured Data

10.21203/rs.3.rs-253767/v1 ◽

2021 ◽

Author(s):

Tannaz Khaleghi ◽

َAlper Murat ◽

Suzan Arslanturk

Keyword(s):

Random Forest ◽

Ground Truth ◽

Initial Step ◽

Unstructured Data ◽

Classification Model ◽

Surgical Department ◽

Medical Coding ◽

Surgical Services ◽

Text Features ◽

Multi Class Classification

Abstract Background: In surgical department, CPT code assignment has been a complicated manual human effort, that entails significant related knowledge and experience. While there are several studies using CPTs to make predictions in surgical services, literature on predicting CPTs in surgical and other services using text features is very sparse. This study improves the prediction of CPTs by the means of informative features and novel re-prioritization algorithm. Methods: The input data used in this study is composed of both structured and unstructured data. The ground truth labels (CPTs) are obtained from medical coding databases using relative value units which indicates the major operational procedures in each surgery case. In the modeling process, we first utilize Random Forest multi-class classification model to predict the CPT codes. Second, we extract the key information such as label probabilities, feature importance measures, and medical term frequency. Then, the indicated factors are used in a novel algorithm to rearrange the alternative CPT codes in the list of potential candidates based on the calculated weights. Results: To evaluate the performance of both phases, prediction and complementary improvement, we report the accuracy scores of multi-class CPT prediction tasks for datasets of 5 key surgery case specialities. The Random Forest model performs the classification task with 74% to 76% when predicting the primary CPT versus the CPT set with respect to the two filtering conditions on CPT codes. The complementary algorithm improves the results from initial step by 8% on average. Furthermore, the incorporated text features enhanced the quality of the output by 20-35%. Conclusions: We have established a robust framework based on a decision tree predictive model. We predict the surgical codes more accurately and robust compared to the state-of-the-art deep neural structures which can help immensely in both surgery billing and scheduling purposes in such units.

Download Full-text

Line Extraction and Player Tracking in Tennis Videos

10.20944/preprints201706.0013.v1 ◽

2017 ◽

Author(s):

Volkan Erol

Keyword(s):

Video Analysis ◽

Automated Classification ◽

Line Extraction ◽

Sports Video ◽

Sports Video Analysis ◽

Detection And Tracking ◽

Player Tracking ◽

Camera Position ◽

Popular Subject

Sports video analysis is an interesting and emerging field in the domain of computer vision. It has become a very popular subject among scholars all over the world in the last decade due to the need of automated classification of events such as offsides, in/out situations, goals and so on. The most important problem in sports video analysis is detection and tracking of ball and players. Extraction of court lines is also another important problem since it is necessary in the classification of aforementioned events. In this study, considering some of the previous work on the subject, we develop a method for tracking the ball and players in tennis videos where the camera position and orientation is supposed fixed.

Download Full-text

A tree based approach for multi-class classification of surgical procedures using structured and unstructured data

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01665-w ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Tannaz Khaleghi ◽

Alper Murat ◽

Suzan Arslanturk

Keyword(s):

Random Forest ◽

State Of The Art ◽

Ground Truth ◽

Initial Step ◽

The State ◽

Unstructured Data ◽

Classification Model ◽

Surgical Department ◽

Text Features ◽

Multi Class Classification

Abstract Background In surgical department, CPT code assignment has been a complicated manual human effort, that entails significant related knowledge and experience. While there are several studies using CPTs to make predictions in surgical services, literature on predicting CPTs in surgical and other services using text features is very sparse. This study improves the prediction of CPTs by the means of informative features and a novel re-prioritization algorithm. Methods The input data used in this study is composed of both structured and unstructured data. The ground truth labels (CPTs) are obtained from medical coding databases using relative value units which indicates the major operational procedures in each surgery case. In the modeling process, we first utilize Random Forest multi-class classification model to predict the CPT codes. Second, we extract the key information such as label probabilities, feature importance measures, and medical term frequency. Then, the indicated factors are used in a novel algorithm to rearrange the alternative CPT codes in the list of potential candidates based on the calculated weights. Results To evaluate the performance of both phases, prediction and complementary improvement, we report the accuracy scores of multi-class CPT prediction tasks for datasets of 5 key surgery case specialities. The Random Forest model performs the classification task with 74–76% when predicting the primary CPT (accuracy@1) versus the CPT set (accuracy@2) with respect to two filtering conditions on CPT codes. The complementary algorithm improves the results from initial step by 8% on average. Furthermore, the incorporated text features enhanced the quality of the output by 20–35%. The model outperforms the state-of-the-art neural network model with respect to accuracy, precision and recall. Conclusions We have established a robust framework based on a decision tree predictive model. We predict the surgical codes more accurately and robust compared to the state-of-the-art deep neural structures which can help immensely in both surgery billing and scheduling purposes in such units.

Download Full-text

Video Analysis of Head Impact Sensor Data From Adolescent Soccer Players

Archives of Physical Medicine and Rehabilitation ◽

10.1016/j.apmr.2018.08.075 ◽

2018 ◽

Vol 99 (11) ◽

pp. e152

Author(s):

Colin Huber ◽

Declan Patton ◽

Kayleigh Jenkins ◽

Kristy Arbogast

Keyword(s):

Video Analysis ◽

Head Impact ◽

Sensor Data ◽

Soccer Players

Download Full-text

Transformer Oil Quality Assessment Using Random Forest with Feature Engineering

Energies ◽

10.3390/en14071809 ◽

2021 ◽

Vol 14 (7) ◽

pp. 1809

Author(s):

Mohammed El Amine Senoussaoui ◽

Mostefa Brahami ◽

Issouf Fofana

Keyword(s):

Machine Learning ◽

Random Forest ◽

Oil Quality ◽

Principal Component ◽

Condition Assessment ◽

Classification Performance ◽

Transformer Oil ◽

Classification Model ◽

Insulation Degradation ◽

Transformer Oils

Machine learning is widely used as a panacea in many engineering applications including the condition assessment of power transformers. Most statistics attribute the main cause of transformer failure to insulation degradation. Thus, a new, simple, and effective machine-learning approach was proposed to monitor the condition of transformer oils based on some aging indicators. The proposed approach was used to compare the performance of two machine-learning classifiers: J48 decision tree and random forest. The service-aged transformer oils were classified into four groups: the oils that can be maintained in service, the oils that should be reconditioned or filtered, the oils that should be reclaimed, and the oils that must be discarded. From the two algorithms, random forest exhibited a better performance and high accuracy with only a small amount of data. Good performance was achieved through not only the application of the proposed algorithm but also the approach of data preprocessing. Before feeding the classification model, the available data were transformed using the simple k-means method. Subsequently, the obtained data were filtered through correlation-based feature selection (CFsSubset). The resulting features were again retransformed by conducting the principal component analysis and were passed through the CFsSubset filter. The transformation and filtration of the data improved the classification performance of the adopted algorithms, especially random forest. Another advantage of the proposed method is the decrease in the number of the datasets required for the condition assessment of transformer oils, which is valuable for transformer condition monitoring.

Download Full-text

Extraction of Arecanut Planting Distribution Based on the Feature Space Optimization of PlanetScope Imagery

Agriculture ◽

10.3390/agriculture11040371 ◽

2021 ◽

Vol 11 (4) ◽

pp. 371

Author(s):

Yu Jin ◽

Jiawei Guo ◽

Huichun Ye ◽

Jinling Zhao ◽

Wenjiang Huang ◽

...

Keyword(s):

Random Forest ◽

Satellite Imagery ◽

Feature Space ◽

Kappa Coefficient ◽

Classification Model ◽

Support Vector ◽

Textural Feature ◽

Monitoring Accuracy ◽

Areca Catechu ◽

High Level

The remote sensing extraction of large areas of arecanut (Areca catechu L.) planting plays an important role in investigating the distribution of arecanut planting area and the subsequent adjustment and optimization of regional planting structures. Satellite imagery has previously been used to investigate and monitor the agricultural and forestry vegetation in Hainan. However, the monitoring accuracy is affected by the cloudy and rainy climate of this region, as well as the high level of land fragmentation. In this paper, we used PlanetScope imagery at a 3 m spatial resolution over the Hainan arecanut planting area to investigate the high-precision extraction of the arecanut planting distribution based on feature space optimization. First, spectral and textural feature variables were selected to form the initial feature space, followed by the implementation of the random forest algorithm to optimize the feature space. Arecanut planting area extraction models based on the support vector machine (SVM), BP neural network (BPNN), and random forest (RF) classification algorithms were then constructed. The overall classification accuracies of the SVM, BPNN, and RF models optimized by the RF features were determined as 74.82%, 83.67%, and 88.30%, with Kappa coefficients of 0.680, 0.795, and 0.853, respectively. The RF model with optimized features exhibited the highest overall classification accuracy and kappa coefficient. The overall accuracy of the SVM, BPNN, and RF models following feature optimization was improved by 3.90%, 7.77%, and 7.45%, respectively, compared with the corresponding unoptimized classification model. The kappa coefficient also improved. The results demonstrate the ability of PlanetScope satellite imagery to extract the planting distribution of arecanut. Furthermore, the RF is proven to effectively optimize the initial feature space, composed of spectral and textural feature variables, further improving the extraction accuracy of the arecanut planting distribution. This work can act as a theoretical and technical reference for the agricultural and forestry industries.

Download Full-text

Improving Medication Regimen Recommendation for Parkinson’s Disease Using Sensor Technology

Sensors ◽

10.3390/s21103553 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3553

Author(s):

Jeremy Watts ◽

Anahita Khojandi ◽

Rama Vasudevan ◽

Fatta B. Nahab ◽

Ritesh A. Ramdhani

Keyword(s):

Parkinson’S Disease ◽

Time Series ◽

Parkinson's Disease ◽

Random Forest ◽

Treatment Planning ◽

Time Series Data ◽

Classification Model ◽

Series Data ◽

Demographic Information ◽

Subjective Data

Parkinson’s disease medication treatment planning is generally based on subjective data obtained through clinical, physician-patient interactions. The Personal KinetiGraph™ (PKG) and similar wearable sensors have shown promise in enabling objective, continuous remote health monitoring for Parkinson’s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to cluster patients based on levodopa regimens and response. The resulting clusters are then used to enhance treatment planning by providing improved initial treatment estimates to supplement a physician’s initial assessment. We apply k-means clustering to a dataset of within-subject Parkinson’s medication changes—clinically assessed by the MDS-Unified Parkinson’s Disease Rating Scale-III (MDS-UPDRS-III) and the PKG sensor for movement staging. A random forest classification model was then used to predict patients’ cluster allocation based on their respective demographic information, MDS-UPDRS-III scores, and PKG time-series data. Clinically relevant clusters were partitioned by levodopa dose, medication administration frequency, and total levodopa equivalent daily dose—with the PKG providing similar symptomatic assessments to physician MDS-UPDRS-III scores. A random forest classifier trained on demographic information, MDS-UPDRS-III scores, and PKG time-series data was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 86.9%, an F1 score of 90.7%, and an AUC of 0.871. A model that relied solely on demographic information and PKG time-series data provided the next best performance with an accuracy of 83.8%, an F1 score of 88.5%, and an AUC of 0.831, hence further enabling fully remote assessments. These computational methods demonstrate the feasibility of using sensor-based data to cluster patients based on their medication responses with further potential to assist with medication recommendations.

Download Full-text

ASSOCIATIVE CLASSIFICATION OF MAMMOGRAMS BASED ON PARALLEL MINING OF IMAGE BLOCKS

Biomedical Engineering Applications Basis and Communications ◽

10.4015/s1016237212500470 ◽

2012 ◽

Vol 24 (06) ◽

pp. 513-524

Author(s):

Mohsen Alavash Shooshtari ◽

Keivan Maghooli ◽

Kambiz Badie

Keyword(s):

Association Rules ◽

Classification Systems ◽

Classification Model ◽

Automated Classification ◽

Associative Classification ◽

Classification Problems ◽

Association Rules Mining ◽

Parallel Mining ◽

Transactional Databases ◽

Unique Decision

One of the main objectives of data mining as a promising multidisciplinary field in computer science is to provide a classification model to be used for decision support purposes. In the medical imaging domain, mammograms classification is a difficult diagnostic task which calls for development of automated classification systems. Associative classification, as a special case of association rules mining, has been adopted in classification problems for years. In this paper, an associative classification framework based on parallel mining of image blocks is proposed to be used for mammograms discrimination. Indeed, association rules mining is applied to a commonly used mammography image database to classify digital mammograms into three categories, namely normal, benign and malign. In order to do so, first images are preprocessed and then features are extracted from non-overlapping image blocks and discretized for rule discovery. Association rules are then discovered through parallel mining of transactional databases which correspond to the image blocks, and finally are used within a unique decision-making scheme to predict the class of unknown samples. Finally, experiments are conducted to assess the effectiveness of the proposed framework. Results show that the proposed framework proved successful in terms of accuracy, precision, and recall, and suggest that the framework could be used as the core of any future associative classifier to support mammograms discrimination.

Download Full-text

Predicting Parkinson’s Disease Medication Regimen Using Sensor Technology

10.21203/rs.3.rs-198765/v1 ◽

2021 ◽

Author(s):

Jeremy Watts ◽

Anahita Khojandi ◽

Rama Vasudevan ◽

Fatta B. Nahab ◽

Ritesh Ramdhani

Keyword(s):

Parkinson’S Disease ◽

Parkinson's Disease ◽

Random Forest ◽

Classification Model ◽

Sensor Data ◽

Sensor Technology ◽

Medication Regimen ◽

Levodopa Dose ◽

Subjective Data ◽

Random Forest Classification

Abstract Parkinson’s disease (PD) medication treatment planning is generally based on subjective data through in-office, physicianpatient interactions. The Personal KinetiGraphTM (PKG) has shown promise in enabling objective, continuous remote health monitoring for Parkinson’s patients. In this proof-of-concept study, we propose to use objective sensor data from the PKG and apply machine learning to subtype patients based on levodopa regimens and response. We apply k-means clustering to a dataset of with-in-subject Parkinson’s medication changes—clinically assessed by the PKG and Hoehn & Yahr (H&Y) staging. A random forest classification model was then used to predict patients’ cluster allocation based on their respective PKG data and demographic information. Clinically relevant clusters were developed based on longitudinal dopaminergic regimens—partitioned by levodopa dose, administration frequency, and total levodopa equivalent daily dose—with the PKG increasing cluster granularity compared to the H&Y staging. A random forest classifier was able to accurately classify subjects of the two most demographically similar clusters with an accuracy of 87:9 ±1:3

Download Full-text

A Geological and Spatial Approach to Prehistoric Archaeological Surveys on Small Islands: Case Studies from Maluku Barat Daya, Indonesia

Kapata Arkeologi ◽

10.24832/kapata.v13i2.458 ◽

2018 ◽

Vol 14 (1) ◽

pp. 1 ◽

Cited By ~ 3

Author(s):

Shimona Kealy ◽

Lucas Wattimena ◽

Sue O'Connor

Keyword(s):

Satellite Images ◽

Ground Truth ◽

Develop Model ◽

Archaeological Sites ◽

Model Parameters ◽

Small Islands ◽

Archaeological Survey ◽

Spatial Approach ◽

Island Group ◽

Survey Results

Survei arkeologi sangat penting untuk penemuan dan interpretasi sisa-sisa yang ditinggalkan oleh aktivitas manusia prasejarah. Saat ini penginderaan jarak jauh dan model prediktif telah meningkatkan jangkauan dan keberhasilan survei arkeologi, namun survei pejalan kaki untuk mengembangkan parameter model dan prediksi kebenaran dasar masih penting untuk keberhasilan suatu penemuan. Penelitian ini merupakan hasil survei arkeologi tahun 2017 di Pulau Babar Besar dan Pulau Wetang yang termasuk dalam bagian dari kelompok Kepulauan Babar, Maluku Barat Daya, Indonesia. Tercatat sebanyak 62 situs arkeologi ditemukan di kedua pulau tersebut, tujuh diantaranya merupakan situs lukisan cadas baru yang ditemukan di Pulau Wetang. Hasil survei ini menunjukkan keberhasilan penggunaan peta geologi dan topografi di samping citra satelit dalam mendeteksi daerah prospektif untuk survei. Hasil penelitian ini juga menunjukkan bahwa pemahaman karakteristik geologi daerah yang lebih rinci dan komparatif diperlukan sebelum dilakukan survei jarak jauh yang lebih lanjut di wilayah Maluku Barat Daya, Indonesia.Archaeological surveys are essential to the discovery and interpretation of remains left by past human activities. While remote sensing and predictive models have greatly improved the reach and success of archaeological survey, pedestrian surveys to develop model parameters and ground-truth predictions is still imperative for successful discoveries. Here we present the results of the 2017 archaeological survey of islands Babar Besar and Wetang in the Babar Island Group, Maluku Barat Daya, Indonesia. A total of 62 archaeological sites were recorded between the two islands; seven of which represent new rock art sites on Wetang island. Our survey results indicate the successful use of geological and topographic maps alongside satellite images in detecting prospective regions for survey. Results also indicate however that a more detailed and comparative understanding of the regions geology is required before more advanced forms of remote survey are conducted in the Maluku Barat Daya region.

Download Full-text