Gyroscope Sensor Research Articles

Evaluation of Complementary Filter Method in Increasing the Performance of Motion Tracking Gloves for Virtual Reality Games

In the use of Virtual Reality-based video games, users need additional devices to interact, one of which is a Motion Tracking Glove. The Motion Tracking Glove is one of the enhancements that users can use to interact with objects in VR video games. To get the angle value, an accelerometer sensor is used in the MPU6050 module. However, the problem that arises is the accuracy of the sensor because VR demands a low error rate. The purpose of this study is to improve the accuracy of the angular value of the accelerometer sensor value with a complementary filter. Complementary filters can increase the accuracy of the accelerometer sensor by combining its value with the gyroscope sensor value. The Motion Tracking Glove is built using the Arduino Nano and the MPU6050 module to capture angles that move according to hand movements, to connect and exchange data to the main VR device, the Motion Tracking Glove using the Bluetooth module. The results are RMSE 0.6 and MAPE 2.5% with a static Motion Tracking Glove position without movement. In sending Motion Tracking Glove data using the Bluetooth module, the resulting delay time when sending ranges from 0.1 second to 0.4 seconds by trying to move the Motion Tracking Glove from 0 degrees to 90 degrees and back to 0 degrees.

Asymmetric Gait Analysis Using a DTW Algorithm with Combined Gyroscope and Pressure Sensor.

Walking is one of the most basic human activities. Various diseases may be caused by abnormal walking, and abnormal walking is mostly caused by disease. There are various characteristics of abnormal walking, but in general, it can be judged as asymmetric walking. Generally, spatiotemporal parameters can be used to determine asymmetric walking. The spatiotemporal parameter has the disadvantage that it does not consider the influence of the diversity of patterns and the walking speed. Therefore, in this paper, we propose a method to analyze asymmetric walking using Dynamic Time Warping (DTW) distance, a time series analysis method. The DTW distance was obtained by combining gyroscope data and pressure data. The experiment was carried out by performing symmetrical walking and asymmetrical walking, and asymmetric walking was performed as a simulation of hemiplegic walking by fixing one ankle using an auxiliary device. The proposed method was compared with the existing asymmetric gait analysis method. As a result of the experiment, a p-value lower than 0.05 was obtained, which proved that there was a statistically significant difference.

FSR and IMU sensors-based human gait phase detection and its correlation with EMG signal for different terrain walk

PurposeThe purpose of this paper is to present gait analysis for five different terrains: level ground, ramp ascent, ramp descent, stair ascent and stair descent.Design/methodology/approachGait analysis has been carried out using a combination of the following sensors: force-sensitive resistor (FSR) sensors fabricated in foot insole to sense foot pressure, a gyroscopic sensor to detect the angular velocity of the shank and MyoWare electromyographic muscle sensors to detect muscle’s activities. All these sensors were integrated around the Arduino nano controller board for signal acquisition and conditioning purposes. In the present scheme, the muscle activities were obtained from the tibialis anterior and medial gastrocnemius muscles using electromyography (EMG) electrodes, and the acquired EMG signals were correlated with the simultaneously attained signals from the FSR and gyroscope sensors. The nRF24L01+ transceivers were used to transfer the acquired data wirelessly to the computer for further analysis. For the acquisition of sensor data, a Python-based graphical user interface has been designed to analyze and display the processed data. In the present paper, the authors got motivated to design and develop a reliable real-time gait phase detection technique that can be used later in designing a control scheme for the powered ankle-foot prosthesis.FindingsThe effectiveness of the gait phase detection was obtained in an open environment. Both off-line and real-time gait events and gait phase detections were accomplished for the FSR and gyroscopic sensors. Both sensors showed their usefulness for detecting the gait events in real-time, i.e. within 10 ms. The heuristic rules and a zero-crossing based-algorithm for the shank angular rate correctly identified all the gait events for the locomotion in all five terrains.Practical implicationsThis study leads to an understanding of human gait analysis for different types of terrains. A real-time standalone system has been designed and realized, which may find application in the design and development of ankle-foot prosthesis having real-time control feature for the above five terrains.Originality/valueThe noise-free data from three sensors were collected in the same time frame from both legs using a wireless sensor network between two transmitters and a single receiver. Unlike the data collection using a treadmill in a laboratory environment, this setup is useful for gait analysis in an open environment for different terrains.

A smartphone-based multimodal indoor tracking system

The great popularity of smartphones, together with the increasingly important aim of providing context-aware services, has spurred interest in developing indoor tracking systems. Accurate tracking and localization systems are seen as key services for most context-aware applications. Research projects making use of radio signals detected by radio interfaces and the data captured by sensors commonly integrated in most smartphones have already shown promising and better results than location solutions based on a single data source. In this paper, we present a multi-sensor tracking system built by incrementally integrating state-of-the-art models of the Wi-Fi interface and the accelerometer, gyroscope and magnetometer sensors of a smartphone. Our proposal consists of a simple calibration phase of the tracking system, which involves enabling simultaneous data gathering from all three sensors and the Wi-Fi interface. Taking the Wi-Fi signal model as baseline, four different configurations are evaluated by incrementally adding and integrating the models of the other three sensors. The experimental results reveal a mean error accuracy of 60 cm in the case when the tracking system makes use of all four data sources. Our results also include a spatial characterization of the accuracy and processing power requirements of the proposed solution. Our main findings demonstrate the feasibility of developing accurate localization indoor tracking systems using current smartphones without the need for additional hardware.

S-Guard: Multisensor Embedded Obstructive Sleep Apnea and Bruxism Real-Time Data Transmission Intraoral Appliance Device

Obstructive sleep apnea (OSA) and bruxism are widely recognized as common forms of sleep obstruction in modern everyday life. The most representative and conventional treatment method using continuous positive airway pressure has a critical problem owing to its high inconvenience. A relatively modern alternative solution is the mandibular advancement device, but it still has no monitoring function for patient compliance. Therefore, this research proposes Sleep Guard (s-Guard), a multisensor embedded OSA monitoring intraoral appliance device based on Internet-of-Things technology. Relevant health information monitoring sensors, such as temperature, gyroscope, accelerometer, and SpO2 sensors, were embedded for real-time health monitoring. Results showed an average transmission speed of 91,870.19 bytes per second, a successful connection check rate of 100%, and a wireless data stream error rate of 0.1%. Overall, the actual speed, connection, and error test results revealed the robust functioning of s-Guard in real monitoring scenarios. This research is envisioned to greatly enhance patient compliance when treating OSA or bruxism and is also expected to motivate other sensors to be embedded in our proposed model for the application of other disease areas.

WITHDRAWN: Mobile phone user behavior's recognition using gyroscope sensor and ML algorithms

Many people died in the street due to mobile phone using. The use of the mobile phone is related to unsafe crossing behaviour as they distractions on the road. Several studies have linked crash risk and distraction. Distracted pedestrian behaviour is a substantial public health concern. The present study focused on recognising mobile phone users’ pedestrian behaviours by proposing mobile phone users’ behaviour recognition model using a gyroscope sensor and ML algorithms. In the methodology, this study discloses three useful stages. In the first phase, a data set of mobile phone users was collected using gyroscope sensors. Secondly, signal segmentation, feature extraction, and feature selection were made in the pre-processing phase. Thirdly, the classification and validation process were conducted in this phase using three machine learning algorithms: SVM, Random forest, and KNN. Findings demonstrate that 300 samples are gathered for mobile phone users’ behaviour for each scenario. 90 features are extracted from each sample based on statistical calculation. The classification and validation findings demonstrate that the random forest algorithm’s highest accuracy is 90.89% after the feature selection process.

Tracking Control of an Autonomous Head Feeding Combine

This study aims to develop an autonomous combine harvester. A manual steering combine harvester was modified autonomously using navigation systems of an RTK-DGPS, a gyroscope, and crawler speed sensors. These sensors could determine the combine position and heading required to guide the path. The control system is processed for these navigation sensors' data to make the decision of combine movement. Moreover, it commands the actuator to move the steering lever mechanism. The steering control's desired heading angle was determined from lateral error, heading error, and the traveling speed. In this study, the combined harvester's average forward traveling speed was set at 0.17 m/s, adjusted to a navigation sensor's sampling rate of 5 Hz and the steering mechanism delay. The preliminary test showed the combine could turn by pivoting one of its tracks which turned the radius was into 0.4 m. Furthermore, a guidance control system of the combine harvester was developed based on this test result. The developed guidance control system was successfully guiding the combine to follow the harvesting path. The test results showed that the root mean square of the lateral error was less than 0.1 m.

Wearable Device for Women Safety and Defence

Women are the most integral part of any economy primarily. Many crimes against them are not being reported because of society’s hypocritic point of view. Various types of humiliations and mistreatment are being faced by the victims who try to report their assaults from society. Only one of four cases lead to conviction trails in India. In this project, a smart device for women’s safety which automates the emergency alert system by using pressure sensor, pulse-rate sensor and Gyroscope sensor to detect a possible atrocity automatically. The system also have manual system with a push button which can be press by the women in critical situation, but during panic situation it is not possible to press the push button .The automatic system help in this situation. A GSM and GPS system is used in order to alert about the unusual situation and location to the relatives and police, image of attacker also sent to police by a camera system which helps to identify the criminal. Another module of shock system is implemented along with the system. A cancel button is also added to avoid false message to the authorities.

Track and Teach: Identifying Key Movement Patterns in Endoscopic Transurethral Enucleation of the Prostate

Purpose: We evaluated a system for noninvasive quantitative motion tracking to recognize differences in the movement pattern of experienced surgeons and beginners. Since performing endoscopic procedures requires extensive training, and tissue damage due to disruptive movements with sudden acceleration is possible, the learning curve for beginners is of clinical relevance. Steepening this curve may improve patient outcome. Materials and Methods: We used a commercial gyroscope sensor with a wireless data link, which was attached to the resectoscope handle (RH). After recording, orientation was retrieved by application of the calculated rotation matrices to the RH vector relative to the sensor under the boundary condition of rotational movement around and quasi-constant distance to the pivot point at pelvic floor level. Data alignment, normalization, interpolation, and analysis were performed in custom software scripts. Results: Experienced surgeons and beginners were recorded in n = 36 and n = 14 holmium laser enucleation of the prostate (HoLEP), respectively. Prostate size, patient age, and recorded procedure duration were comparable. Mean lever angle of the individual normalized motion patterns was considerably lower (19.28 ± 0.54° [SEM]) in the advanced than in the beginners’ group (24.52 ± 1.00°; p = 0.0001). Further parameters such as velocity and motion variation demonstrated additional differences between both groups. Conclusions: We demonstrate the feasibility of motion tracking in HoLEP. Pronounced differences exist between different stages of surgeon experience with this procedure. The method can easily be adopted to aide young surgeons in resectoscope handling and identification of improvable motion patterns. Damage to the pelvic floor and surrounding tissue may thus be reduced.

Applications and Prospects of Mems Sensors in Automotive

MEMS sensor is a new type of sensor and is made by micro-electronic and micro-mechanical processing technology. It has many advantages such as small volume, light weight, low cost, low power consumption, high reliability, suitable for mass production, easy integration and intelligent realization. It is widely used in the automobile, effectively improving the performance of the automobile sensor, promoting the progress of the automobile industry and the intelligent automobile. This paper mainly discusses the market size of MEMS sensors and their applications in the automotive field, focusing on MEMS pressure sensors, MEMS acceleration sensors and gyroscope sensors. The development direction of MEMS sensors in the automotive field is forecasted.

INDOOR LOCALIZATION USING ACCELEROMETER AND GYROSCOPE SMARTPHONE BASED

Indoor localization is one of the more accurate technologies to be used to determine indoors or buildings. Pedestrian Dead Reckoning (PDR) is a method of determining the user's position by adding a method that occurs to a known initial position. The displacement that occurs is estimated with the help of an accelerometer sensor attached to the user as a step detector and to determine the direction towards the user using a gyroscope sensor. System testing is carried out in the Institut Teknologi Sumatera’s campus environment on the 2nd floor of Building C and D. The results from the detection of steps get an error rate of 1.13% using a threshold of 0.8.

A smart point-of-care compliance monitoring solution for brace treatment of adolescent idiopathic scoliosis patients

Scoliosis is a medical condition which occurs in adolescents, where an individual's spine develops curvature. A Thoracolumbosacral orthosis (TLSO) is a type of brace used as a long term treat-ment method to control the lateral curvature of the spine in adolescent idiopathic scoliosis (AIS). However, compliance of the daily prescribed duration and tightness of the brace is a big challenge, which plays a significant role in the success of brace treatment. In this paper, we designed and de-veloped a wearable multi-modal sensor solution, which is embedded into the AIS patient's brace. The custom-designed hardware consists of a sensor board, a force sensor & housing, a miniature triaxial accelerometer and gyroscope sensor. The force sensor records the force being exerted by the patient's brace padding, while the accelerometer and gyroscope sensors capture upper trunk movements, providing cues to determine the patient's activities and lifestyle to help with more accurate estimation of the two key parameters, including 1) the in-brace tightness level 2) the duration of the brace wear, in an unsupervised manner. Furthermore, we presented a signal pro-cessing and data analytic methodology to identify the duration and tightness of the brace wear, in addition to identifying various patient activities based on the fusion of continuous force and iner-tial motion sensor recordings. We, specifically, derived a signal processing activity identification method using power spectral density estimation of the sensor data recordings. Then, we evaluate of the effectiveness of brace treatment in a pervasive manner. The proposed method evaluates the duration of brace wear through the process of segmentation and calculates the tightness level of the brace by estimating the baseline force per segment of data. This analysis is done when the patient performs activities including sitting, standing, climbing, walking, running and lying. We investigated an experimental scenario in which the patient performs a series of pre-defined activ-ities at home during day-long segments of brace wear. All analysis is performed using pervasive sensor data recordings. The experimental results demonstrated that we achieved an overall accu-racy of 99.8%, 100% and 99.9% for patients 1, 2 and 3 respectively for semi-supervised activity detection. We continued our compliance study for approximately a month. The level of tight-ness of brace-fit gradually reduced over a period of 2 weeks by 30% as the compliance of brace treatment increased from 7% to 90% on average. Given our experimental results and objective observations, our proposed system is capable of arranging for re-fitting sessions automatically so that the physician can adjust the brace tightness levels for a more effective brace treatment. • Brace treatment for AIS patients is long-term & pervasive demanding self-compliance. • Pervasive monitoring can provide two key factors of duration and tightness of the brace-wear. • We design a multimodal smart brace monitoring system to estimate the two factors. • We design a robust signal processing recipe to undertake unsupervised recordings. • Our experiments demonstrated that our system generates reliable & robust estimates.

Early Detection of Freezing of Gait during Walking Using Inertial Measurement Unit and Plantar Pressure Distribution Data.

Freezing of gait (FOG) is a sudden and highly disruptive gait dysfunction that appears in mid to late-stage Parkinson’s disease (PD) and can lead to falling and injury. A system that predicts freezing before it occurs or detects freezing immediately after onset would generate an opportunity for FOG prevention or mitigation and thus enhance safe mobility and quality of life. This research used accelerometer, gyroscope, and plantar pressure sensors to extract 861 features from walking data collected from 11 people with FOG. Minimum-redundancy maximum-relevance and Relief-F feature selection were performed prior to training boosted ensembles of decision trees. The binary classification models identified Total-FOG or No FOG states, wherein the Total-FOG class included data windows from 2 s before the FOG onset until the end of the FOG episode. Three feature sets were compared: plantar pressure, inertial measurement unit (IMU), and both plantar pressure and IMU features. The plantar-pressure-only model had the greatest sensitivity and the IMU-only model had the greatest specificity. The best overall model used the combination of plantar pressure and IMU features, achieving 76.4% sensitivity and 86.2% specificity. Next, the Total-FOG class components were evaluated individually (i.e., Pre-FOG windows, Freeze windows, transition windows between Pre-FOG and Freeze). The best model detected windows that contained both Pre-FOG and FOG data with 85.2% sensitivity, which is equivalent to detecting FOG less than 1 s after the freeze began. Windows of FOG data were detected with 93.4% sensitivity. The IMU and plantar pressure feature-based model slightly outperformed models that used data from a single sensor type. The model achieved early detection by identifying the transition from Pre-FOG to FOG while maintaining excellent FOG detection performance (93.4% sensitivity). Therefore, if used as part of an intelligent, real-time FOG identification and cueing system, even if the Pre-FOG state were missed, the model would perform well as a freeze detection and cueing system that could improve the mobility and independence of people with PD during their daily activities.

Data Mining to Select Relevant Variables Influencing External and Internal Workload of Elite Blind 5-a-Side Soccer.

(1) Background: Data mining has turned essential when exploring a large amount of information in performance analysis in sports. This study aimed to select the most relevant variables influencing the external and internal load in top-elite 5-a-side soccer (Sa5) using a data mining model considering some contextual indicators as match result, body mass index (BMI), scoring rate and age. (2) Methods: A total of 50 top-elite visually impaired soccer players (age 30.86 ± 11.2 years, weight 77.64 ± 9.78 kg, height 178.48 ± 7.9 cm) were monitored using magnetic, angular and rate gyroscope (MARG) sensors during an international Sa5 congested fixture tournament.; (3) Results: Fifteen external and internal load variables were extracted from a total of 49 time-related and peak variables derived from the MARG sensors using a principal component analysis as the most used data mining technique. The principal component analysis (PCA) model explained 80% of total variance using seven principal components. In contrast, the first principal component of the match was defined by jumps, take off by 24.8% of the total variance. Blind players usually performed a higher number of accelerations per min when losing a match. Scoring players execute higher DistanceExplosive and Distance21–24 km/h. And the younger players presented higher HRAVG and AccMax. (4) Conclusions: The influence of some contextual variables on external and internal load during top elite Sa5 official matches should be addressed by coaches, athletes, and medical staff. The PCA seems to be a useful statistical technique to select those relevant variables representing the team’s external and internal load. Besides, as a data reduction method, PCA allows administrating individualized training loads considering those relevant variables defining team load behavior.

Smartwatch-Based Eating Detection: Data Selection for Machine Learning from Imbalanced Data with Imperfect Labels.

Understanding people’s eating habits plays a crucial role in interventions promoting a healthy lifestyle. This requires objective measurement of the time at which a meal takes place, the duration of the meal, and what the individual eats. Smartwatches and similar wrist-worn devices are an emerging technology that offers the possibility of practical and real-time eating monitoring in an unobtrusive, accessible, and affordable way. To this end, we present a novel approach for the detection of eating segments with a wrist-worn device and fusion of deep and classical machine learning. It integrates a novel data selection method to create the training dataset, and a method that incorporates knowledge from raw and virtual sensor modalities for training with highly imbalanced datasets. The proposed method was evaluated using data from 12 subjects recorded in the wild, without any restriction about the type of meals that could be consumed, the cutlery used for the meal, or the location where the meal took place. The recordings consist of data from accelerometer and gyroscope sensors. The experiments show that our method for detection of eating segments achieves precision of 0.85, recall of 0.81, and F1-score of 0.82 in a person-independent manner. The results obtained in this study indicate that reliable eating detection using in the wild recorded data is possible with the use of wearable sensors on the wrist.

Sleep Pattern Study with Respect to Binaural Beats Using Sensors and Mobile Application

Sleep disorders are common among people in the present lifestyle and this may occur due to irregular sleep patterns. The disordered sleep pattens arise due to various reasons and can be prevented by ensuring a relaxed and deep sleep for everyone. Binaural beats are the stimuli that are set to a particular rhythm and generated to get the required audio frequency to synchronize with the brainwaves. This paper focuses on the effects and analysis of binaural beat response on the brain waves of adults and how they help to induce sleep for an individual. This work highlights the results that were obtained by performing the real time hardware experiments accordingly. The head movement is recorded from the experiment using the readings from the accelerometer and gyroscope sensors which are depicted by the angle coordinates based on two conditions, first when the subjects fall asleep without application of binaural beats and second when minimal frequency of binaural beats are applied close to their ears. Using the real time hardware experiment values, an application is created to differentiate the cases of with and without binaural beats application. In order to validate the real time experiment with an application, a statistical analysis is done from the obtained real time hardware results depicting the sleep pattern by performing corresponding tests.

Underground Parking Lot Navigation System Using Long-Term Evolution Signal.

Some of the shopping malls, airports, hospitals, etc. have underground parking lots where hundreds of vehicles can be parked. However, first-time visitors find it difficult to determine their current location and need to keep moving the vehicle to find an empty parking space. Moreover, they need to remember the parked location, and find a nearby staircase or elevator to move toward the destination. In such a situation, if the user location can be estimated, a new navigation system can be offered, which can assist users. This study presents an underground parking lot navigation system using long-term evolution (LTE) signals. As the proposed system utilizes LTE network signals for which the infrastructure is already installed, no additional infrastructure is required. To estimate the location of the vehicle, the signal strength of the LTE signal is accumulated, and the location of the vehicle is estimated by comparing it with the previously stored database of the LTE received signal strength (RSS). In addition, the acceleration and gyroscope sensors of a smartphone are used to improve the vehicle position estimation performance. The effectiveness of the proposed system is verified by conducting an experiment in a large shopping-mall underground parking lot where approximately 500 vehicles can be parked. From the results of the experiment, an error of less than an average of 10 m was obtained, which shows that seamless navigation is possible using the proposed system even in an environment where GNSS does not function.

Remotely Operated underwater Vehicle (ROV) stabilization with Artificial Neural Networks (ANN)

The purpose of this research is to produce a system that can stabilize REMOTELY OPERATED UNDERWATER VEHICLE (ROV) using an ARTIFICIAL NEURAL NETWORK (ANN) smart system. The way the system works is done by reading the input in the form of an Accelerometer and Gyroscope sensor which is then processed using a microcontroller and the output is PWM (Pulse Width Modulation) which is interpreted by the ESC (Electronic Speed Control) driver to move the motor according to the speed it should be. In addition, the microcontroller also has to determine which direction the motorbike can go against from the ocean currents or the source of the shock it receives. ANN in this system is used to determine the size of the ROV’s freedom of air so that the motor can withstand any unstable external shocks (air currents) and still maintain its position and position.

Classification of Agriculture Farm Machinery Using Machine Learning and Internet of Things

In this paper, we apply the multi-class supervised machine learning techniques for classifying the agriculture farm machinery. The classification of farm machinery is important when performing the automatic authentication of field activity in a remote setup. In the absence of a sound machine recognition system, there is every possibility of a fraudulent activity taking place. To address this need, we classify the machinery using five machine learning techniques—K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and Gradient Boosting (GB). For training of the model, we use the vibration and tilt of machinery. The vibration and tilt of machinery are recorded using the accelerometer and gyroscope sensors, respectively. The machinery included the leveler, rotavator and cultivator. The preliminary analysis on the collected data revealed that the farm machinery (when in operation) showed big variations in vibration and tilt, but observed similar means. Additionally, the accuracies of vibration-based and tilt-based classifications of farm machinery show good accuracy when used alone (with vibration showing slightly better numbers than the tilt). However, the accuracies improve further when both (the tilt and vibration) are used together. Furthermore, all five machine learning algorithms used for classification have an accuracy of more than 82%, but random forest was the best performing. The gradient boosting and random forest show slight over-fitting (about 9%), but both algorithms produce high testing accuracy. In terms of execution time, the decision tree takes the least time to train, while the gradient boosting takes the most time.

Character Recognition on Time Series Data collected from Smartphone Sensors

In the modern era, smartphones have become part and parcel of life. The exponential increase in the number of smartphone users has given rise to a copious amount of data. Although the data produced by smartphones are of various types, this paper mainly focuses on the usage of sensory data produced by smartphones. This paper explores the field of recognizing characters with the aid of time-series sensor data. The primary focus of the research is to utilize recurrent neural networks to predict the digits 0 - 9 and characters A - Z. The objective achieved was by the help of sensor data that included the readings of Accelerometer, Magnetometer, Gyroscope, and Linear Accelerometer sensors providing information with respect to three-axis x, y, and z, having an interval of 0.01 seconds between two corresponding values. We succeeded in achieving the accuracy of 93.60% on the training data and 89.51% on the testing data.