A Comparison Study of Classifier Algorithms for Cross-Person Physical Activity Recognition

Multi-classification of national fitness test grades based on statistical analysis and machine learning

Physical fitness is a key element of a healthy life, and being overweight or lacking physical exercise will lead to health problems. Therefore, assessing an individual's physical health status from a non-medical, cost-effective perspective is essential. This paper aimed to evaluate the national physical health status through national physical examination data, selecting 12 indicators to divide the physical health status into four levels: excellent, good, pass, and fail. The existing challenge lies in the fact that most literature on physical fitness assessment mainly focuses on the two major groups of sports athletes and school students. Unfortunately, there is no reasonable index system has been constructed. The evaluation method has limitations and cannot be applied to other groups. This paper builds a reasonable health indicator system based on national physical examination data, breaks group restrictions, studies national groups, and hopes to use machine learning models to provide helpful health suggestions for citizens to measure their physical status. We analyzed the significance of the selected indicators through nonparametric tests and exploratory statistical analysis. We used seven machine learning models to obtain the best multi-classification model for the physical fitness test level. Comprehensive research showed that MLP has the best classification effect, with macro-precision reaching 74.4% and micro-precision reaching 72.8%. Furthermore, the recall rates are also above 70%, and the Hamming loss is the smallest, i.e., 0.272. The practical implications of these findings are significant. Individuals can use the classification model to understand their physical fitness level and status, exercise appropriately according to the measurement indicators, and adjust their lifestyle, which is an important aspect of health management.

Multi-dimensional task recognition for human-robot teaming: literature review

Human-robot teams collaborating to achieve tasks under various conditions, especially in unstructured, dynamic environments will require robots to adapt autonomously to a human teammate's state. An important element of such adaptation is the robot's ability to infer the human teammate's tasks. Environmentally embedded sensors (e.g., motion capture and cameras) are infeasible in such environments for task recognition, but wearable sensors are a viable task recognition alternative. Human-robot teams will perform a wide variety of composite and atomic tasks, involving multiple activity components (i.e., gross motor, fine-grained motor, tactile, visual, cognitive, speech and auditory) that may occur concurrently. A robot's ability to recognize the human's composite, concurrent tasks is a key requirement for realizing successful teaming. Over a hundred task recognition algorithms across multiple activity components are evaluated based on six criteria: sensitivity, suitability, generalizability, composite factor, concurrency and anomaly awareness. The majority of the reviewed task recognition algorithms are not viable for human-robot teams in unstructured, dynamic environments, as they only detect tasks from a subset of activity components, incorporate non-wearable sensors, and rarely detect composite, concurrent tasks across multiple activity components.

Machine Learning on Prediction of Relative Physical Activity Intensity Using Medical Radar Sensor and 3D Accelerometer

BACKGROUND

One of the most critical topics in sports safety today is the reduction in injury risks through controlled fatigue using non-invasive athlete monitoring. Due to the risk of injuries, it is prohibited to use accelerometer-based smart trackers, activity measurement bracelets, and smart watches for recording health parameters during performance sports activities. This study analyzes the synergy feasibility of medical radar sensors and tri-axial acceleration sensor data to predict physical activity key performance indexes in performance sports by using machine learning (ML). The novelty of this method is that it uses a 24 GHz Doppler radar sensor to detect vital signs such as the heartbeat and breathing without touching the person and to predict the intensity of physical activity, combined with the acceleration data from 3D accelerometers.

METHODS

This study is based on the data collected from professional athletes and freely available datasets created for research purposes. A combination of sensor data management was used: a medical radar sensor with no-contact remote sensing to measure the heart rate (HR) and 3D acceleration to measure the velocity of the activity. Various advanced ML methods and models were employed on the top of sensors to analyze the vital parameters and predict the health activity key performance indexes. three-axial acceleration, heart rate data, age, as well as activity level variances.

RESULTS

The ML models recognized the physical activity intensity and estimated the energy expenditure on a realistic level. Leave-one-out (LOO) cross-validation (CV), as well as out-of-sample testing (OST) methods, have been used to evaluate the level of accuracy in activity intensity prediction. The energy expenditure prediction with three-axial accelerometer sensors by using linear regression provided 97-99% accuracy on selected sports (cycling, running, and soccer). The ML-based RPE results using medical radar sensors on a time-series heart rate (HR) dataset varied between 90 and 96% accuracy. The expected level of accuracy was examined with different models. The average accuracy for all the models (RPE and METs) and setups was higher than 90%.

CONCLUSIONS

The ML models that classify the rating of the perceived exertion and the metabolic equivalent of tasks perform consistently.

Empirical Comparison between Deep and Classical Classifiers for Speaker Verification in Emotional Talking Environments

Speech signals carry various bits of information relevant to the speaker such as age, gender, accent, language, health, and emotions. Emotions are conveyed through modulations of facial and vocal expressions. This paper conducts an empirical comparison of performances between the classical classifiers: Gaussian Mixture Model (GMM), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial neural networks (ANN); and the deep learning classifiers, i.e., Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU) in addition to the ivector approach for a text-independent speaker verification task in neutral and emotional talking environments. The deep models undergo hyperparameter tuning using the Grid Search optimization algorithm. The models are trained and tested using a private Arabic Emirati Speech Database, Ryerson Audio–Visual Database of Emotional Speech and Song dataset (RAVDESS) database, and a public Crowd-Sourced Emotional Multimodal Actors (CREMA) database. Experimental results illustrate that deep architectures do not necessarily outperform classical classifiers. In fact, evaluation was carried out through Equal Error Rate (EER) along with Area Under the Curve (AUC) scores. The findings reveal that the GMM model yields the lowest EER values and the best AUC scores across all datasets, amongst classical classifiers. In addition, the ivector model surpasses all the fine-tuned deep models (CNN, LSTM, and GRU) based on both evaluation metrics in the neutral, as well as the emotional speech. In addition, the GMM outperforms the ivector using the Emirati and RAVDESS databases.

Wearable Sensor-Based Human Activity Recognition with Hybrid Deep Learning Model

It is undeniable that mobile devices have become an inseparable part of human’s daily routines due to the persistent growth of high-quality sensor devices, powerful computational resources and massive storage capacity nowadays. Similarly, the fast development of Internet of Things technology has motivated people into the research and wide applications of sensors, such as the human activity recognition system. This results in substantial existing works that have utilized wearable sensors to identify human activities with a variety of techniques. In this paper, a hybrid deep learning model that amalgamates a one-dimensional Convolutional Neural Network with a bidirectional long short-term memory (1D-CNN-BiLSTM) model is proposed for wearable sensor-based human activity recognition. The one-dimensional Convolutional Neural Network transforms the prominent information in the sensor time series data into high level representative features. Thereafter, the bidirectional long short-term memory encodes the long-range dependencies in the features by gating mechanisms. The performance evaluation reveals that the proposed 1D-CNN-BiLSTM outshines the existing methods with a recognition rate of 95.48% on the UCI-HAR dataset, 94.17% on the Motion Sense dataset and 100% on the Single Accelerometer dataset.

Design and Implementation of Human Motion Recognition Information Processing System Based on LSTM Recurrent Neural Network Algorithm

With the comprehensive development of national fitness, men, women, young, and old in China have joined the ranks of fitness. In order to increase the understanding of human movement, many researches have designed a lot of software or hardware to realize the analysis of human movement state. However, the recognition efficiency of various systems or platforms is not high, and the reduction ability is poor, so the recognition information processing system based on LSTM recurrent neural network under deep learning is proposed to collect and recognize human motion data. The system realizes the collection, processing, recognition, storage, and display of human motion data by constructing a three-layer human motion recognition information processing system and introduces LSTM recurrent neural network to optimize the recognition efficiency of the system, simplify the recognition process, and reduce the data missing rate caused by dimension reduction. Finally, we use the known dataset to train the model and analyze the performance and application effect of the system through the actual motion state. The final results show that the performance of LSTM recurrent neural network is better than the traditional algorithm, the accuracy can reach 0.980, and the confusion matrix results show that the recognition of human motion by the system can reach 85 points to the greatest extent. The test shows that the system can recognize and process the human movement data well, which has great application significance for future physical education and daily physical exercise.

The effect of hyperparameter search on artificial neural network in human activity recognition

In the last decade, many researchers applied shallow and deep networks for human activity recognition (HAR). Currently, the trending research line in HAR is applying deep learning to extract features and classify activities from raw data. However, we observed that, authors of previous studies have not performed an efficient hyperparameter search on their artificial neural network (shallow or deep)-based classifier. Therefore, in this article, we demonstrate the effect of the random and Bayesian parameter search on a shallow neural network using five HAR databases. The result of this work shows that a shallow neural network with correct parameter optimization can achieve similar or even better recognition accuracy than the previous best deep classifier(s) on all databases. In addition, we draw conclusions about the advantages and disadvantages of the two hyperparameter search techniques according to the results.

Mobile Deep Learning System That Calculates UVI Using Illuminance Value of User's Location

Ultraviolet rays are closely related with human health and, recently, optimum exposure to the UV rays has been recommended, with growing importance being placed on correct UV information. However, many countries provide UV information services at a local level, which makes it impossible for individuals to acquire user-based, accurate UV information unless individuals operate UV measurement devices with expertise on the relevant field for interpretation of the measurement results. There is a limit in measuring ultraviolet rays’ information by the users at their respective locations. Research about how to utilize mobile devices such as smartphones to overcome such limitation is also lacking. This paper proposes a mobile deep learning system that calculates UVI based on the illuminance values at the user’s location obtained with mobile devices’ help. The proposed method analyzed the correlation between illuminance and UVI based on the natural light DB collected through the actual measurements, and the deep learning model’s data set was extracted. After the selection of the input variables to calculate the correct UVI, the deep learning model based on the TensorFlow set with the optimum number of layers and number of nodes was designed and implemented, and learning was executed via the data set. After the data set was converted to the mobile deep learning model to operate under the mobile environment, the converted data were loaded on the mobile device. The proposed method enabled providing UV information at the user’s location through a mobile device on which the illuminance sensors were loaded even in the environment without UVI measuring equipment. The comparison of the experiment results with the reference device (spectrometer) proved that the proposed method could provide UV information with an accuracy of 90–95% in the summers, as well as in winters.

Capturing accelerometer outputs in healthy volunteers under normal and simulated-pathological conditions using ML classifiers

Wearable devices offer a possible solution for acquiring objective measurements of physical activity. Most current algorithms are derived using data from healthy volunteers. It is unclear whether such algorithms are suitable in specific clinical scenarios, such as when an individual has altered gait. We hypothesized that algorithms trained on healthy population will result in less accurate results when tested in individuals with altered gait. We further hypothesized that algorithms trained on simulated-pathological gait would prove better at classifying abnormal activity. We studied healthy volunteers to assess whether activity classification accuracy differed for those with healthy and simulated-pathological conditions. Healthy participants (n=30) were recruited from the University of Leeds to perform nine predefined activities under healthy and simulated-pathological conditions. Activities were captured using a wrist-worn MOX accelerometer (Maastricht Instruments, NL). Data were analyzed based on the Activity-Recognition-Chain process. We trained a Neural-Network, Random-Forests, k-Nearest-Neighbors (k-NN), Support-Vector-Machines (SVM) and Naive Bayes models to classify activity. Algorithms were trained four times; once with `healthy' data, and once with `simulated-pathological data' for each of activity-type and activity-task classification. In activity-type instances, the SVM provided the best results; the accuracy was 98.4% when the algorithm was trained and then tested with unseen data from the same group of healthy individuals. Accuracy dropped to 52.8% when tested on simulated-pathological data. When the model was retrained with simulated-pathological data, prediction accuracy for the corresponding test set was 96.7%. Algorithms developed on healthy data are less accurate for pathological conditions. When evaluating pathological conditions, classifier algorithms developed using data from a target sub-population can restore accuracy to above 95%.

Computer Vision Classification of Barley Flour Based on Spatial Pyramid Partition Ensemble

Imaging sensors are largely employed in the food processing industry for quality control. Flour from malting barley varieties is a valuable ingredient in the food industry, but its use is restricted due to quality aspects such as color variations and the presence of husk fragments. On the other hand, naked varieties present superior quality with better visual appearance and nutritional composition for human consumption. Computer Vision Systems (CVS) can provide an automatic and precise classification of samples, but identification of grain and flour characteristics require more specialized methods. In this paper, we propose CVS combined with the Spatial Pyramid Partition ensemble (SPPe) technique to distinguish between naked and malting types of twenty-two flour varieties using image features and machine learning. SPPe leverages the analysis of patterns from different spatial regions, providing more reliable classification. Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), J48 decision tree, and Random Forest (RF) were compared for samples' classification. Machine learning algorithms embedded in the CVS were induced based on 55 image features. The results ranged from 75.00% (k-NN) to 100.00% (J48) accuracy, showing that sample assessment by CVS with SPPe was highly accurate, representing a potential technique for automatic barley flour classification.

A Comparison of Machine Learning and Deep Learning Techniques for Activity Recognition using Mobile Devices

We have compared the performance of different machine learning techniques for human activity recognition. Experiments were made using a benchmark dataset where each subject wore a device in the pocket and another on the wrist. The dataset comprises thirteen activities, including physical activities, common postures, working activities and leisure activities. We apply a methodology known as the activity recognition chain, a sequence of steps involving preprocessing, segmentation, feature extraction and classification for traditional machine learning methods; we also tested convolutional deep learning networks that operate on raw data instead of using computed features. Results show that combination of two sensors does not necessarily result in an improved accuracy. We have determined that best results are obtained by the extremely randomized trees approach, operating on precomputed features and on data obtained from the wrist sensor. Deep learning architectures did not produce competitive results with the tested architecture.

Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition

The most significant barrier to success in human activity recognition is extracting and selecting the right features. In traditional methods, the features are chosen by humans, which requires the user to have expert knowledge or to do a large amount of empirical study. Newly developed deep learning technology can automatically extract and select features. Among the various deep learning methods, convolutional neural networks (CNNs) have the advantages of local dependency and scale invariance and are suitable for temporal data such as accelerometer (ACC) signals. In this paper, we propose an efficient human activity recognition method, namely Iss2Image (Inertial sensor signal to Image), a novel encoding technique for transforming an inertial sensor signal into an image with minimum distortion and a CNN model for image-based activity classification. Iss2Image converts real number values from the X, Y, and Z axes into three color channels to precisely infer correlations among successive sensor signal values in three different dimensions. We experimentally evaluated our method using several well-known datasets and our own dataset collected from a smartphone and smartwatch. The proposed method shows higher accuracy than other state-of-the-art approaches on the tested datasets.

A User-Adaptive Algorithm for Activity Recognition Based on K-Means Clustering, Local Outlier Factor, and Multivariate Gaussian Distribution

Mobile activity recognition is significant to the development of human-centric pervasive applications including elderly care, personalized recommendations, etc. Nevertheless, the distribution of inertial sensor data can be influenced to a great extent by varying users. This means that the performance of an activity recognition classifier trained by one user’s dataset will degenerate when transferred to others. In this study, we focus on building a personalized classifier to detect four categories of human activities: light intensity activity, moderate intensity activity, vigorous intensity activity, and fall. In order to solve the problem caused by different distributions of inertial sensor signals, a user-adaptive algorithm based on K-Means clustering, local outlier factor (LOF), and multivariate Gaussian distribution (MGD) is proposed. To automatically cluster and annotate a specific user’s activity data, an improved K-Means algorithm with a novel initialization method is designed. By quantifying the samples’ informative degree in a labeled individual dataset, the most profitable samples can be selected for activity recognition model adaption. Through experiments, we conclude that our proposed models can adapt to new users with good recognition performance.