Three-axis Acceleration Data Research Articles

Utilizing Inertial Measurement Units for Detecting Dynamic Stability Variations in a Multi-Condition Gait Experiment.

This study proposes a wearable gait assessment method using inertial measurement units (IMUs) to evaluate gait ability in daily environments. By focusing on the estimation of the margin of stability (MoS), a key kinematic stability parameter, a method using a convolutional neural network, was developed to estimate the MoS from IMU acceleration time-series data. The relationship between MoS and other stability indices, such as the Lyapunov exponent and the multi-site time-series (MSTS) index, using data from five IMU sensors placed on various body parts was also examined. To simulate diverse gait conditions, treadmill speed was varied, and a knee-ankle-foot orthosis was used to restrict left knee extension, inducing gait asymmetry. The model achieved over 90% accuracy in classifying MoS in both forward and lateral directions using three-axis acceleration data from the IMUs. However, the correlation between MoS and the Lyapunov exponent or MSTS index was weak, suggesting that these indices may capture different aspects of gait stability.

Human behavior recognition method based on wearable devices

Abstract Human behavior recognition remains a prevalent subject of inquiry in contemporary scientific studies. Behavior recognition technology has penetrated into every aspect of our lives, mainly in video surveillance, health monitoring, and smart homes. Aiming at some people who need behavioral monitoring to prevent danger, a human behavior recognition method based on wearable devices is proposed, which first acquires the three-axis acceleration data of behavioral activities of such people through wearable devices and then performs sliding window segmentation and feature extraction on the acquired data and finally inputs the obtained features into the dual-directional long and short term memory framework (BiLSTM) model to complete the identification of human behavior. To affirm the method’s reliability, we performed activity detection tests on a dataset from UCI featuring a non-powered wearable sensor used by the senior population. The outcomes indicate that the method is proficient in identifying the routine daily activities of this demographic, demonstrating its practical utility.

Non-contact multimodal indoor human monitoring systems: A survey

Indoor human monitoring systems are integral in various applications. They leverage a wide range of sensors, including cameras, radio devices, and inertial measurement units, to collect extensive data from users and the environment. These sensors contribute distinct data modalities, encompassing video feeds from cameras, received signal strength indicators and channel state information from WiFi devices, and three-axis acceleration data from accelerometers. In this context, we present a comprehensive survey of multimodal approaches applied to indoor human monitoring systems, with a specific focus on their relevance in elderly care. Our survey primarily highlights non-contact technologies, particularly cameras and radio devices, as key components in the development of indoor human monitoring systems. Throughout this article, we explore well-established techniques for extracting features from multimodal data sources. Our exploration extends to methodologies for fusing these features and harnessing multiple modalities to improve the accuracy and robustness of machine learning models. Furthermore, we conduct comparative analysis across different data modalities in diverse human monitoring tasks and undertake a comprehensive examination of existing multimodal datasets. This extensive survey not only highlights the significance of indoor human monitoring systems but also emphasizes their versatile applications. In particular, we emphasize their critical role in enhancing the quality of elderly care, offering valuable insights into the development of non-contact monitoring solutions tailored to the needs of aging populations.

IDENTIFICATION OF CHATTER VIBRATIONS AND ACTIVE VIBRATION CONTROL BY USING THE SLIDING MODE CONTROLLER ON DRY TURNING OF TITANIUM ALLOY (TI6AL4V)

In recent years, with the development of sensor technologies, communication platforms, cyber-physical systems, storage technologies, internet applications and controller infrastructures, the way has been opened to produce competitive products with high quality and low cost. In turning, which is one of the important processes of machining, chatter vibrations are among the biggest problems affecting product quality, productivity and cost. There are many techniques proposed to reduce chatter vibrations for which the exact cause cannot be determined. In this study, an active vibration control based on the Sliding Mode Control (SMC) has been implemented in order to reduce and eliminate chatter vibration, which is undesirable for the turning process. In this context, three-axis acceleration data were collected from the cutting tool during the turning of Ti6Al4V. Finite Impulse Response (FIR) filtering, Fast Fourier Transform (FFT) analysis and integral process were carried out in order to use the raw acceleration data collected over the system in control. The system is modeled mathematically and an active control block diagram is created. It is observed that chattering decreased significantly after the application of active vibration control. The surface quality formed by the amplitude of the graph obtained after active control has been compared and verified with the data obtained from the actual manufacturing result.

On-Board Unit (OBU)-Supported Longitudinal Driving Behavior Monitoring Using Machine Learning Approaches.

Driving behavior recognition can provide an important reference for the intelligent vehicle industry and probe vehicle-based traffic estimation. The identification of driving behavior using mobile sensing techniques such as smartphone- and vehicle-mounted terminals has gained significant attention in recent years. The present work proposed the monitoring of longitudinal driving behavior using a machine learning approach with the support of an on-board unit (OBU). Specifically, based on velocity, three-axis acceleration and three-axis angular velocity data were collected by a mobile vehicle terminal OBU; through the process of data preprocessing and feature extraction, seven machine learning algorithms, including support vector machine (SVM), random forest (RF), k-nearest neighbor algorithm (KNN), logistic regression (LR), BP neural network (BPNN), decision tree (DT), and the Naive Bayes (NB), were applied to implement the classification and monitoring of the longitudinal driving behavior of probe vehicles. The results show that the three classifiers SVM, RF and DT achieved good performances in identifying different longitudinal driving behaviors. The outcome of the present work could contribute to the fields of traffic management and traffic safety, providing important support for the realization of intelligent transport systems and the improvement of driving safety.

Commercial straight-deck trailer vibration and microclimate conditions during market-weight pig transport during summer

The objective of this study was to collect and quantify three-axis acceleration data from six locations within commercial pig transport trailers during summer. Two trucks with straight-deck trailers transporting two loads per day were observed for 5 consecutive days (N= 20). Accelerometers were placed under the floor of each trailer’s top and bottom decks (DECs) in the center of three sections (SECs): fore, middle, and aft. Data from each trailer section were processed to calculate z- and x,y-axis root mean square (RMS) values and vibration dose values (VDVs) during loading, transport, and unloading. There were no DEC × SEC interactions or SEC main effects for z-axis RMS or VDV during any transportation stage (P> 0.06). The bottom deck had a greater x,y-axis RMS than the top deck during all transportation stages (P< 0.01). The bottom deck had a greater x,y-axis VDV than the top deck during loading and transport (P< 0.03), but there was no difference (P= 0.52) during unloading. The bottom deck had a greater z-axis RMS and VDV than the top deck during loading and transport (P< 0.01), but there were no differences during unloading (P> 0.07). There were no SEC effects for x,y- and z-axis RMSs and VDVs during all transportation stages (P> 0.06). Acceleration values were compared with exposure action values (EAV; injury possible) and exposure limit values (ELV; injury likely) vibrations thresholds. Over the 5 observation days during all transport stages, a greater percentage of compartments violated both RMS and VDV thresholds in the x,y orientation (average 90%) than in the z orientation (average 76%). Overall, these data indicate that bottom decks experience greater three-axis vibrations than top decks in straight-deck trailers and that pigs on bottom decks may experience greater discomfort during transportation that could contribute to fatigue or the non-ambulatory condition.

Adaptations of Explainable Artificial Intelligence (XAI) to Agricultural Data Models with ELI5, PDPbox, and Skater using Diverse Agricultural Worker Data

We use explainable artificial intelligence (XAI) based on Explain Like I’m 5 (ELI5), Partial Dependency Plot box (PDPbox), and Skater to analyze diverse physical agricultural (agri-) worker datasets. We have developed various promising body-sensing systems to enhance agri-technical advancement, training and worker development, and security. This includes wearable sensing systems (WSSs) that can capture real-time three-axis acceleration and angular velocity data related to agri-worker motion by analyzing human dynamics and statistics in different agri-environments, such as fields, meadows, and gardens. After investigating the obtained time-series data using a novel program written in Python, we discuss our findings and recommendations with real agri-workers and managers. In this study, we use XAI and visualization to analyze diverse data of experienced and inexperienced agri-workers to develop an applied method for agri-directors to train agri-workers.

Analyses of Diverse Agricultural Worker Data with Explainable Artificial Intelligence: XAI based on SHAP, LIME, and LightGBM

We use recent explainable artificial intelligence (XAI) based on SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Light Gradient Boosting Machine (LightGBM) to analyze diverse physical agricultural (agri-) worker datasets. We have developed various promising body-sensing systems to enhance agri-technical advancement, training and worker development, and security. However, existing methods and systems are not sufficient for in-depth analysis of human motion. Thus, we have also developed wearable sensing systems (WS) that can capture real-time three-axis acceleration and angular velocity data related to agri-worker motion by analyzing human dynamics and statistics in different agri-fields, meadows, and gardens. After investigating the obtained time-series data using a novel program written in Python, we discuss our findings and recommendations with real agri-workers and managers. In this study, we use XAI and visualization to analyze diverse data of experienced and inexperienced agri-workers to develop an applied method for agri-directors to train agri-workers.

2 Vibration Profiles of Commercial Straight-Deck Trailers Transporting Market-Weight Pigs During Summer

Abstract The objective was to collect and quantify three-axis acceleration data from locations within commercial transport trailers shipping market weight pigs during summer. Two trucks and straight-deck trailers, owned and operated by a single producer, were observed during two loads per day for five consecutive days. Three-axis accelerometers were placed under top and bottom deck floors in the center of the fore, center, and aft compartments. Z-axis and combined x- and y-axis data were processed to generate root-mean-square (RMS) values and vibration dose values (VDV) during loading, trailer movement, and unloading. At all periods of the trip and both sets of axis data, there were no Deck × Area interactions (P > 0.11) for RMS and VDV values. During loading and movement, the bottom deck had greater z-axis RMS and VDV values than the top deck (P < 0.01), but there was no difference (P = 0.07) during unloading. There were no Area effects for z-axis RMS and VDV values during all time periods (P > 0.06). During all periods, the top deck had greater x,y-axis RMS values than the bottom deck (P < 0.02). During loading and movement, the bottom deck had greater x,y-axis VDV values than the top deck (P < 0.03), but there was no difference (P = 0.52) during unloading. There were no Area effects for x,y-axis RMS and VDV values during all time periods (P > 0.07). Individual trip RMS and VDV values were compared with exposure action values (EAV; injury possible) and exposure limit values (ELV; injury likely). At all parts of the trip, trailer RMS and VDV violated between 51% and 99% EAV and ELV thresholds. These data indicate top and bottom decks vibrate differently and pigs experience vibrations that may contribute to fatigued pig syndrome or the non-ambulatory condition.

Carrying Position-Independent Ensemble Machine Learning Step-Counting Algorithm for Smartphones.

Current step-count estimation techniques use either an accelerometer or gyroscope sensors to calculate the number of steps. However, because of smartphones unfixed placement and direction, their accuracy is insufficient. It is necessary to consider the impact of the carrying position on the accuracy of the pedometer algorithm, because of people carry their smartphones in various positions. Therefore, this study proposes a carrying-position independent ensemble step-counting algorithm suitable for unconstrained smartphones in different carrying positions. The proposed ensemble algorithm comprises a classification algorithm that identifies the carrying position of the smartphone, and a regression algorithm that considers the identified carrying position and calculates the number of steps. Furthermore, a data acquisition system that collects (i) label data in the form of the number of steps estimated from the Force Sensitive Resistor (FSR) sensors, and (ii) input data in the form of the three-axis acceleration data obtained from the smartphones is also proposed. The obtained data were used to allow the machine learning algorithms to fit the signal features of the different carrying positions. The reliability of the proposed ensemble algorithms, comprising a random forest classifier and a regression model, was comparatively evaluated with a commercial pedometer application. The results indicated that the proposed ensemble algorithm provides higher accuracy, ranging from 98.1% to 98.8%, at self-paced walking speed than the commercial pedometer application, and the machine learning-based ensemble algorithms can effectively and accurately predict step counts under different smart phone carrying positions.

Probability model of rock climbing recognition based on information fusion sensor time series

Rock climbing is a sports activity that integrates competition, entertainment, and culture. With the development of the economy and the improvement in living standards, rock climbing has embarked on a path of self-development and has entered the lives of urban youth at an increasingly rapid rate. This paper studies the probabilistic model of rock climbing recognition based on time series of multi-information fusion sensors so that climbers can climb more standardized. Based on practice, this paper has conducted research and design on the hardware platform and actually applied it to the rock climbing environment. Through reasonable processing of rock climbing process data of rock climbers, a variety of rock climbing state characteristics are successfully extracted for fusion. Aiming at the quasi-periodical characteristics of acceleration changes at different points during human movement, a method for identifying human movement patterns based on gait event information is designed. This method intercepts the three-axis acceleration data collected by each accelerometer through key gait events. A data set used to identify human movement patterns is established. A corresponding LDA classifier is established for each data set to identify the current movement pattern, and finally the classification results of all the classifiers are voted on. The final experiment shows that the system can identify the climbing movement of the climber within 3 s. The method can achieve 95.84% of the comprehensive recognition accuracy of the four state modes of rock climbing.

Automatic recognition method of cow ruminating behaviour based on edge computing

Timely monitoring of the ruminating behaviour of dairy cows is beneficial for obtaining relevant information on dairy cow health to predict dairy cow diseases for the first time. To date, various strategies for monitoring ruminating behaviour have been proposed, but the real-time monitoring of these strategies has not been fully realized. Based on edge computing, we proposed a real-time method to monitor the ruminating behaviour of dairy cows. In this work, a self-designed edge device was used to collect and process the three-axis acceleration signals of dairy cows in real-time, and then a rumination recognition algorithm was used to calculate the overall sliding geometric mean of the Euclidean distance between the feature sets in real-time, determine the adaptive threshold, and verify the ruminating behaviour by the sliding window. Finally, real-time recognition of the ruminating behaviour of dairy cows was completed on the edge device side, without requiring substantial calculation time and resources. The edge device uploaded cow ruminating information to the cloud in real-time every two hours, and the cloud further aggregated the ruminating information. Compared with the traditional method of uploading three-axis acceleration data, this cloud-end integrated system based on edge computing reduced the amount of uploaded data bytes by 99.9%. Our ruminating recognition has achieved the following performance values: precision (93.7%), recall (92.8%), F1-score (93.3%), specificity (97.4%) and accuracy (96.1%), indicating a good classification effect. This research provides a real-time and effective method for monitoring of cow ruminating behaviour, and the proposed system can be used in practical applications.

Ankle foot motion recognition based on wireless wearable sEMG and acceleration sensors for smart AFO

Ankle joint is one of the important anatomical structures of the human body, smart ankle-foot orthosis(AFO) can assist human walking and improve the ankle motion for patients. This study focused on ankle foot movements recognition based on data fusion via sEMG and acceleration sensors. A wireless signal acquisition system (WAS) was designed specifically, forming a platform to demonstrate and record individual sEMG and acceleration data simultaneously. In the experimental tests, three channel sEMG signals from Tibialis Anterior (TA), Gastrocnemius (GM) and Soleus (SO), as well as three-axis acceleration data of the ankle joints, were collected when subjects performed four kinds of typical motions including dorsiflexion, plantar flexion, eversion and inversion. A total of 21,600 frames of sEMG /acceleration action data were constructed and then different kinds of classification algorithms were studied to classify the motions by the principal component analysis (PCA) based data fusion signal features. Results showed that the classification accuracy of bi-directional long short-term memory (BiLSTM) algorithm performed the best compared with traditional networks such as support vector machine(SVM), artificial neural network (ANN) and reached 99.8 %. These results demonstrated the potential application for accurate ankle foot intent identification by sEMG and acceleration sensors, which provided the basis for further implementation of subsequent smart AFO manipulation.

The Performance of Post-Fall Detection Using the Cross-Dataset: Feature Vectors, Classifiers and Processing Conditions.

In this study, algorithms to detect post-falls were evaluated using the cross-dataset according to feature vectors (time-series and discrete data), classifiers (ANN and SVM), and four different processing conditions (normalization, equalization, increase in the number of training data, and additional training with external data). Three-axis acceleration and angular velocity data were obtained from 30 healthy male subjects by attaching an IMU to the middle of the left and right anterior superior iliac spines (ASIS). Internal and external tests were performed using our lab dataset and SisFall public dataset, respectively. The results showed that ANN and SVM were suitable for the time-series and discrete data, respectively. The classification performance generally decreased, and thus, specific feature vectors from the raw data were necessary when untrained motions were tested using a public dataset. Normalization made SVM and ANN more and less effective, respectively. Equalization increased the sensitivity, even though it did not improve the overall performance. The increase in the number of training data also improved the classification performance. Machine learning was vulnerable to untrained motions, and data of various movements were needed for the training.

Creating a Scoring System with an Armband Wearable Device for Table Tennis Forehand Loop Training: Combined Use of the Principal Component Analysis and Artificial Neural Network.

Background: This study presents an intelligent table tennis e-training system based on a neural network (NN) model that recognizes data from sensors built into an armband device, with the component values (performances scores) estimated through principal component analysis (PCA). Methods: Six expert male table tennis players on the National Youth Team (mean age 17.8 ± 1.2 years) and seven novice male players (mean age 20.5 ± 1.5 years) with less than 1 year of experience were recruited into the study. Three-axis peak forearm angular velocity, acceleration, and eight-channel integrated electromyographic data were used to classify both player level and stroke phase. Data were preprocessed through PCA extraction from forehand loop signals. The model was trained using 160 datasets from five experts and five novices and validated using 48 new datasets from one expert and two novices. Results: The overall model’s recognition accuracy was 89.84%, and its prediction accuracies for testing and new data were 93.75% and 85.42%, respectively. Principal components corresponding to the skills “explosive force of the forearm” and “wrist muscle control” were extracted, and their factor scores were standardized (0–100) to score the skills of the players. Assessment results indicated that expert scores generally fell between 60 and 100, whereas novice scores were less than 70. Conclusion: The developed system can provide useful information to quantify expert-novice differences in fore-hand loop skills.

Measurement of the three-axis vibration, temperature, and relative humidity profiles of commercial transport trailers for pigs.

The objective of this study was to collect and interpret three-axis acceleration, temperature, and relative humidity data from six locations within commercial transport trailers shipping market-weight pigs. Transport was observed in Kansas (n = 15) and North Carolina (n = 20). Prior to loading, three-axis accelerometers were affixed to six locations on the trailers: top fore (TF), top center (TC), top aft (TA), bottom fore (BF), bottom center (BC), and bottom aft (BA) compartments. Data were post-processed to calculate root-mean-square (RMS) accelerations and vibration dose values (VDV) in the vertical direction and the horizontal plane. These values were compared with exposure action values (EAV) and exposure limit values (ELV), vibration levels deemed uncomfortable and potentially dangerous to humans. Additionally, RMS and VDV were compared among the trailer compartments. The vertical RMS accelerations for all compartments exceeded the EAV for loads measured in Kansas, and for the majority of the compartments measured in North Carolina. Many compartments, specifically the BA compartment from all trips, exceeded the vertical ELV. Regardless of where the data were collected, fewer compartments exceeded the EAV in the horizontal orientation. Only BA compartments exceeded the ELV in the horizontal orientation. There were Area × Level interactions for vertical and horizontal RMS and VDV (P < 0.01). The BF compartment had a greater vertical RMS value than the TF, TC, and BC (P < 0.02) compartments, but did not differ (P = 0.06) from the TA compartment. The vertical RMS of the TA compartment did not differ from the TF, TC, and BC compartments (P > 0.13). The BF compartment had a greater (P = 0.02) vertical VDV value than the TC location, but did not differ from the other locations (P > 0.16). All other locations did not differ in vertical VDV (P > 0.12). The BF compartment had greater horizontal RMS than the TC and TA compartments (P < 0.01), but did not differ from TF and BC compartments (P > 0.12). All other compartments did not differ in horizontal RMS (P > 0.34). All compartments, aside from the BA compartment, did not differ in horizontal VDV (P > 0.19). Vibration analyses indicated the BA compartment had the greatest vertical and horizontal vibrations and a large percentage of the compartments exceed the EAV and ELV, which indicated pigs may have experienced uncomfortable trips that could cause discomfort or fatigue.

Detection of Road-Surface Anomalies Using a Smartphone Camera and Accelerometer.

Road surfaces should be maintained in excellent condition to ensure the safety of motorists. To this end, there exist various road-surface monitoring systems, each of which is known to have specific advantages and disadvantages. In this study, a smartphone-based dual-acquisition method system capable of acquiring images of road-surface anomalies and measuring the acceleration of the vehicle upon their detection was developed to explore the complementarity benefits of the two different methods. A road test was conducted in which 1896 road-surface images and corresponding three-axis acceleration data were acquired. All images were classified based on the presence and type of anomalies, and histograms of the maximum variations in the acceleration in the gravitational direction were comparatively analyzed. When the types of anomalies were not considered, it was difficult to identify their effects using the histograms. The differences among histograms became evident upon consideration of whether the vehicle wheels passed over the anomalies, and when excluding longitudinal anomalies that caused minor changes in acceleration. Although the image-based monitoring system used in this research provided poor performance on its own, the severity of road-surface anomalies was accurately inferred using the specific range of the maximum variation of acceleration in the gravitational direction.

RETRACTED: Preventive monitoring of basketball players' knee pads based on IoT wearable devices

The Internet of Things based on the rapid development of Internet intelligence for the wearable device The Internet is where shooting performance can be tracked and remote analysis has prompted us to develop a form of basketball player device. The purpose of this article is to evaluate basketball coaches who use the system with particular emphasis on identifying players using micro sensors. An online survey was conducted by basketball coaches from international basketball related associations and social networking sites. Based on the data, therefore, how player tracking is obtained, as well as the range and players, to promote Wii surveillance, multiple responses, compromised standards at the Licert level, and collected through open-ended questions this research can propose annual scale and real-time analysis, seamless throw movement system design professional basketball player. It depends on angular velocity data. Three different basketball shoes, a built-in motion sensor and three-axis acceleration data can be collected about. Three basketball dribble, jump, turn around. A new research analysis tool has been developed to shoot the individual ideological actions of each player. Developmental tools have been shown to be closer than conventional knee pads. The results show that the system can accurately estimate the average difference basketball players. In analytical mode, extended wrist activity in other sports can develop the most important player skill level.

Recognition Technology of Athlete’s Limb Movement Combined Based on the Integrated Learning Algorithm

Human motion recognition based on inertial sensor is a new research direction in the field of pattern recognition. It carries out preprocessing, feature selection, and feature selection by placing inertial sensors on the surface of the human body. Finally, it mainly classifies and recognizes the extracted features of human action. There are many kinds of swing movements in table tennis. Accurately identifying these movement modes is of great significance for swing movement analysis. With the development of artificial intelligence technology, human movement recognition has made many breakthroughs in recent years, from machine learning to deep learning, from wearable sensors to visual sensors. However, there is not much work on movement recognition for table tennis, and the methods are still mainly integrated into the traditional field of machine learning. Therefore, this paper uses an acceleration sensor as a motion recording device for a table tennis disc and explores the three‐axis acceleration data of four common swing motions. Traditional machine learning algorithms (decision tree, random forest tree, and support vector) are used to classify the swing motion, and a classification algorithm based on the idea of integration is designed. Experimental results show that the ensemble learning algorithm developed in this paper is better than the traditional machine learning algorithm, and the average recognition accuracy is 91%.

Detecting Unsafe Conditions of a Lathe using an Artificial Neural Network with Three-axis Acceleration Data

Detecting unsafe conditions of a lathe is critical to prevent hazards in a workplace. This study proposed an artificial neural network (ANN) model to classify the state of a lathe into one of the nine conditions (two normal conditions and seven unsafe conditions) based on three-axis acceleration data. The two normal conditions were (1) idle and (2) normal processing. The seven unsafe conditions included unsafe states of a lathe (i.e., eccentric rotation, chipping, improper workpiece fixation, and base looseness) and a worker (i.e., glove contact, hair contact, and necklace contact). The acceleration data for each condition were measured for 30 s using a small lathe and smoothed with the moving average. The datasets were randomly divided into three different sets for training (70%), validation (15%), and testing (15%). The ANN model was trained using the training and validation sets and its performance was evaluated using the testing set. The testing results showed that the classification accuracy of the ANN model proposed in this study (100%) was better than that of a multiclass linear support vector machine model (68%). The procedure and the ANN model established in this study can be utilized to detect unsafe conditions of a lathe and other industrial machines.