scholarly journals Classification of Aggressive Movements Using Smartwatches

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6377
Author(s):  
Franck Tchuente ◽  
Natalie Baddour ◽  
Edward D. Lemaire
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Aggressive Behavior ◽  
Naive Bayes ◽  
Poor Performance ◽  
Naïve Bayes ◽  
Classification Model ◽  
Support Vector ◽  
Care Providers ◽  
K Nearest Neighbors

Recognizing aggressive movements is a challenging task in human activity recognition. Wearable smartwatch technology with machine learning may be a viable approach for human aggressive behavior classification. This research identified a viable classification model and feature selector (CM-FS) combination for separating aggressive from non-aggressive movements using smartwatch data and determined if only one smartwatch is sufficient for this task. A ranking method was used to select relevant CM-FS models across accuracy, sensitivity, specificity, precision, F-score, and Matthews correlation coefficient (MCC). The Waikato environment for knowledge analysis (WEKA) was used to run 6 machine learning classifiers (random forest, k-nearest neighbors (kNN), multilayer perceptron neural network (MP), support vector machine, naïve Bayes, decision tree) coupled with three feature selectors (ReliefF, InfoGain, Correlation). Microsoft Band 2 accelerometer and gyroscope data were collected during an activity circuit that included aggressive (punching, shoving, slapping, shaking) and non-aggressive (clapping hands, waving, handshaking, opening/closing a door, typing on a keyboard) tasks. A combination of kNN and ReliefF was the best CM-FS model for separating aggressive actions from non-aggressive actions, with 99.6% accuracy, 98.4% sensitivity, 99.8% specificity, 98.9% precision, 0.987 F-score, and 0.984 MCC. kNN and random forest classifiers, combined with any of the feature selectors, generated the top models. Models with naïve Bayes or support vector machines had poor performance for sensitivity, F-score, and MCC. Wearing the smartwatch on the dominant wrist produced the best single-watch results. The kNN and ReliefF combination demonstrated that this smartwatch-based approach is a viable solution for identifying aggressive behavior. This wrist-based wearable sensor approach could be used by care providers in settings where people suffer from dementia or mental health disorders, where random aggressive behaviors often occur.

scholarly journals Predicting Student’s Performance Using Machine Learning Algorithm

2021 ◽  
pp. 53-58
Author(s):  
Sheela Rani P ◽  
Dhivya S ◽  
Dharshini Priya M ◽  
Dharmila Chowdary A
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Prediction Model ◽  
Naive Bayes ◽  
Learning Algorithm ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Learning Approaches ◽  
K Nearest Neighbors

Machine learning is a new analysis discipline that uses knowledge to boost learning, optimizing the training method and developing the atmosphere within which learning happens. There square measure 2 sorts of machine learning approaches like supervised and unsupervised approach that square measure accustomed extract the knowledge that helps the decision-makers in future to require correct intervention. This paper introduces an issue that influences students' tutorial performance prediction model that uses a supervised variety of machine learning algorithms like support vector machine , KNN(k-nearest neighbors), Naïve Bayes and supplying regression and logistic regression. The results supported by various algorithms are compared and it is shown that the support vector machine and Naïve Bayes performs well by achieving improved accuracy as compared to other algorithms. The final prediction model during this paper may have fairly high prediction accuracy .The objective is not just to predict future performance of students but also provide the best technique for finding the most impactful features that influence student’s while studying.

Preliminary Screening of COVID-19 Infection Employing Machine Learning Techniques From Simple Blood Profile

2021 ◽  
Vol 6 (3) ◽  
pp. 35-47
Author(s):  
Anirudh Reddy Cingireddy ◽  
Robin Ghosh ◽  
Supratik Kar ◽  
Venkata Melapu ◽  
Sravanthi Joginipeli ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Naive Bayes ◽  
Albert Einstein ◽  
Naïve Bayes ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Blood Profile ◽  
Molecular Tests ◽  
Large Populations

Frequent testing of the entire population would help to identify individuals with active COVID-19 and allow us to identify concealed carriers. Molecular tests, antigen tests, and antibody tests are being widely used to confirm COVID-19 in the population. Molecular tests such as the real-time reverse transcription-polymerase chain reaction (rRT-PCR) test will take a minimum of 3 hours to a maximum of 4 days for the results. The authors suggest using machine learning and data mining tools to filter large populations at a preliminary level to overcome this issue. The ML tools could reduce the testing population size by 20 to 30%. In this study, they have used a subset of features from full blood profile which are drawn from patients at Israelita Albert Einstein hospital located in Brazil. They used classification models, namely KNN, logistic regression, XGBooting, naive Bayes, decision tree, random forest, support vector machine, and multilayer perceptron with k-fold cross-validation, to validate the models. Naïve bayes, KNN, and random forest stand out as the most predictive ones with 88% accuracy each.

Prediction of Breast Cancer Using Machine Learning

2020 ◽  
Vol 13 (5) ◽  
pp. 901-908
Author(s):  
Somil Jain ◽  
Puneet Kumar
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Random Forest ◽  
Prediction Accuracy ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Classification Algorithms ◽  
Breast Cancer Dataset

Background:: Breast cancer is one of the diseases which cause number of deaths ever year across the globe, early detection and diagnosis of such type of disease is a challenging task in order to reduce the number of deaths. Now a days various techniques of machine learning and data mining are used for medical diagnosis which has proven there metal by which prediction can be done for the chronic diseases like cancer which can save the life’s of the patients suffering from such type of disease. The major concern of this study is to find the prediction accuracy of the classification algorithms like Support Vector Machine, J48, Naïve Bayes and Random Forest and to suggest the best algorithm. Objective:: The objective of this study is to assess the prediction accuracy of the classification algorithms in terms of efficiency and effectiveness. Methods: This paper provides a detailed analysis of the classification algorithms like Support Vector Machine, J48, Naïve Bayes and Random Forest in terms of their prediction accuracy by applying 10 fold cross validation technique on the Wisconsin Diagnostic Breast Cancer dataset using WEKA open source tool. Results:: The result of this study states that Support Vector Machine has achieved the highest prediction accuracy of 97.89 % with low error rate of 0.14%. Conclusion:: This paper provides a clear view over the performance of the classification algorithms in terms of their predicting ability which provides a helping hand to the medical practitioners to diagnose the chronic disease like breast cancer effectively.

scholarly journals Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Elizabeth Ford ◽  
Philip Rooney ◽  
Seb Oliver ◽  
Richard Hoile ◽  
Peter Hurley ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Health Service ◽  
Naive Bayes ◽  
Case Control ◽  
Naïve Bayes ◽  
Support Vector ◽  
Clinical Practice Research Datalink ◽  
Patient Records

Abstract Background Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a machine-learning model to identify patients who have or who are developing dementia, but are currently undetected as having the condition by the GP. Methods We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged >65y with a diagnosis of dementia (cases) and matched them 1:1 by sex and age to patients with no evidence of dementia (controls). We developed a list of 70 clinical entities related to the onset of dementia and recorded in the 5 years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, naïve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination. Results The final analysis included data on 93,120 patients, with a median age of 82.6 years; 64.8% were female. The naïve Bayes model performed least well. The logistic regression, support vector machine, neural network and random forest performed very similarly with an AUROC of 0.74. The top features retained in the logistic regression model were disorientation and wandering, behaviour change, schizophrenia, self-neglect, and difficulty managing. Conclusions Our model could aid GPs or health service planners with the early detection of dementia. Future work could improve the model by exploring the longitudinal nature of patient data and modelling decline in function over time.

scholarly journals On the Analysis of Machine Learning Classifiers to Detect Traffic Congestion in Vehicular Networks

2019 ◽  
Author(s):  
Lucas Carvalho ◽  
Maycon Silva ◽  
Edimilson Santos ◽  
Daniel Guidoni
Keyword(s):  
Machine Learning ◽  
Traffic Congestion ◽  
Vehicular Networks ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Applied Machine Learning ◽  
Routing Methods

Problems related to traffic congestion and management have become common in many cities. Thus, vehicle re-routing methods have been proposed to minimize the congestion. Some of these methods have applied machine learning techniques, more specifically classifiers, to verify road conditions and detect congestion. However, better results may be obtained by applying a classifier more suitable to domain. In this sense, this paper presents an evaluation of different classifiers applied to the identification of the level of road congestion. Our main goal is to analyze the characteristics of each classifier in this task. The classifiers involved in the experiments here are: Multiple Layer Neural Network (MLP), K-Nearest Neighbors (KNN), Decision Trees (J48), Support Vector Machines (SVM), Naive Bayes and Tree Augment Naive Bayes.

scholarly journals Machine Learning Approaches Applied to GC-FID Fatty Acid Profiles to Discriminate Wild from Farmed Salmon

Foods ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1622
Author(s):  
Liliana Grazina ◽  
P. J. Rodrigues ◽  
Getúlio Igrejas ◽  
Maria A. Nunes ◽  
Isabel Mafra ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fatty Acid ◽  
Random Forest ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Learning Approaches ◽  
Machine Learning Classifiers ◽  
Farmed Salmon ◽  
Learning Classifiers

In the last decade, there has been an increasing demand for wild-captured fish, which attains higher prices compared to farmed species, thus being prone to mislabeling practices. In this work, fatty acid composition coupled to advanced chemometrics was used to discriminate wild from farmed salmon. The lipids extracted from salmon muscles of different production methods and origins (26 wild from Canada, 25 farmed from Canada, 24 farmed from Chile and 25 farmed from Norway) were analyzed by gas chromatography with flame ionization detector (GC-FID). All the tested chemometric approaches, namely principal components analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE) and seven machine learning classifiers, namely k-nearest neighbors (kNN), decision tree, support vector machine (SVM), random forest, artificial neural networks (ANN), naïve Bayes and AdaBoost, allowed for differentiation between farmed and wild salmons using the 17 features obtained from chemical analysis. PCA did not allow clear distinguishing between salmon geographical origin since farmed samples from Canada and Chile overlapped. Nevertheless, using the 17 features in the models, six out of the seven tested machine learning classifiers allowed a classification accuracy of ≥99%, with ANN, naïve Bayes, random forest, SVM and kNN presenting 100% accuracy on the test dataset. The classification models were also assayed using only the best features selected by a reduction algorithm and the best input features mapped by t-SNE. The classifier kNN provided the best discrimination results because it correctly classified all samples according to production method and origin, ultimately using only the three most important features (16:0, 18:2n6c and 20:3n3 + 20:4n6). In general, the classifiers presented good generalization with the herein proposed approach being simple and presenting the advantage of requiring only common equipment existing in most labs.

scholarly journals Using Machine Learning to Build a Classification Model for IoT Networks to Detect Attack Signatures

2020 ◽  
Vol 12 (6) ◽  
pp. 99-116
Author(s):  
Mousa Al-Akhras ◽  
Mohammed Alawairdhi ◽  
Ali Alkoudari ◽  
Samer Atawneh
Keyword(s):  
Machine Learning ◽  
Naive Bayes ◽  
Denial Of Service ◽  
Learning Algorithms ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Security And Privacy ◽  
K Nearest Neighbors ◽  
Detection Model

Internet of things (IoT) has led to several security threats and challenges within society. Regardless of the benefits that it has brought with it to the society, IoT could compromise the security and privacy of individuals and companies at various levels. Denial of Service (DoS) and Distributed DoS (DDoS) attacks, among others, are the most common attack types that face the IoT networks. To counter such attacks, companies should implement an efficient classification/detection model, which is not an easy task. This paper proposes a classification model to examine the effectiveness of several machine-learning algorithms, namely, Random Forest (RF), k-Nearest Neighbors (KNN), and Naïve Bayes. The machine learning algorithms are used to detect attacks on the UNSW-NB15 benchmark dataset. The UNSW-NB15 contains normal network traffic and malicious traffic instants. The experimental results reveal that RF and KNN classifiers give the best performance with an accuracy of 100% (without noise injection) and 99% (with 10% noise filtering), while the Naïve Bayes classifier gives the worst performance with an accuracy of 95.35% and 82.77 without noise and with 10% noise, respectively. Other evaluation matrices, such as precision and recall, also show the effectiveness of RF and KNN classifiers over Naïve Bayes.

A Novel Machine Learning Algorithm Predicts Dementia With Lewy Bodies Versus Parkinson’s Disease Dementia Based on Clinical and Neuropsychological Scores

2021 ◽  
pp. 089198872199355
Author(s):  
Anastasia Bougea ◽  
Efthymia Efthymiopoulou ◽  
Ioanna Spanou ◽  
Panagiotis Zikos
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Neuropsychological Tests ◽  
Naive Bayes ◽  
Learning Algorithm ◽  
Naïve Bayes ◽  
Classification Model ◽  
Support Vector ◽  
Ensemble Model ◽  
Machine Learning Algorithm

Objective: Our aim was to develop a machine learning algorithm based only on non-invasively clinic collectable predictors, for the accurate diagnosis of these disorders. Methods: This is an ongoing prospective cohort study ( ClinicalTrials.gov identifier NCT number NCT04448340) of 78 PDD and 62 DLB subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. We used predictors such as clinico-demographic characteristics, 6 neuropsychological tests (mini mental, PD Cognitive Rating Scale, Brief Visuospatial Memory test, Symbol digit written, Wechsler adult intelligence scale, trail making A and B). We investigated logistic regression, K-Nearest Neighbors (K-NNs) Support Vector Machine (SVM), Naïve Bayes classifier, and Ensemble Model for their ability to predict successfully PDD or DLB diagnosis. Results: The K-NN classification model had an accuracy 91.2% of overall cases based on 15 best clinical and cognitive scores achieving 96.42% sensitivity and 81% specificity on discriminating between DLB and PDD. The binomial logistic regression classification model achieved an accuracy of 87.5% based on 15 best features, showing 93.93% sensitivity and 87% specificity. The SVM classification model had an accuracy 84.6% of overall cases based on 15 best features achieving 90.62% sensitivity and 78.58% specificity. A model created on Naïve Bayes classification had 82.05% accuracy, 93.10% sensitivity and 74.41% specificity. Finally, an Ensemble model, synthesized by the individual ones, achieved 89.74% accuracy, 93.75% sensitivity and 85.73% specificity. Conclusion: Machine learning method predicted with high accuracy, sensitivity and specificity PDD or DLB diagnosis based on non-invasively and easily in-the-clinic and neuropsychological tests.

Sign in / Sign up

Export Citation Format

Share Document