Gyroscope Sensor Research Articles

Comparative Analysis of Fall Detection Using Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) Algorithms

Fall detection is a critical area of research due to its implications for public health, particularly among older adults more vulnerable to fall-related injuries. This study explores the application of pervasive computing and machine learning algorithms in detecting falls using accelerometer and gyroscope sensors. Leveraging a dataset obtained from smartphone sensors, the study employs data processing techniques and classification algorithms, including K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN), to differentiate fall events from other activities. Evaluation metrics such as accuracy, precision, recall, and F1-score are utilized to assess the performance of the models. The results demonstrate the effectiveness of both the ANN and KNN models in accurately predicting fall detection with high precision and recall scores. The study highlights the potential of pervasive computing systems and machine learning methods to enhance fall detection capabilities, contributing to the development of proactive measures for ensuring the safety and well-being of individuals at risk of falls. Future research directions include exploring alternative algorithms and sensor modalities to improve fall detection systems further.

Calculation of the Point of Application (Centre of Pressure) of Force and Torque Imparted on a Spherical Object from Gyroscope Sensor Data, Using Sports Balls as Practical Examples.

This study investigates the determination of the centre of pressure (COP) on spherical sports objects such as cricket balls and footballs using gyroscope data from Inertial Measurement Units (IMUs). Conventional pressure sensors are not suitable for capturing the tangential forces responsible for torque generation. This research presents a novel method to calculate the COP solely from gyroscope data and avoids the complexity of isolating user-induced accelerations from IMU data. The COP is determined from the cross-product of consecutive torque vectors intersecting the surface of the sphere. Effective noise management techniques, including filtering and data interpolation, were employed to improve COP visualisation. Experiments were conducted using a smart cricket ball and a smart football. Validation tests using spin rates between 7.5 and 12 rps and torques ranging from 0.08 to 0.12 Nm confirmed consistent COP clustering around the expected positions. Further analysis extended to various spin bowling deliveries recorded using a smart cricket ball, and a curved football kick recorded using a smart football demonstrated the wide applicability of the method. The COPs of various spin bowling deliveries showed adjacent positions on the surface of the ball, traversing through backspin, sidespin and topspin, excluding the flipper and doosra deliveries. The calculation of the COP on the surface of the soccer ball could only be achieved by increasing the data sampling frequency sevenfold using curve fitting. Knowledge and use of the COP position offers significant advances in understanding and analysing ball dynamics in sports.

Wing-strain-based flight control of flapping-wing drones through reinforcement learning

Although drone technology has advanced rapidly, replicating the dynamic control and wind-sensing abilities of biological flight is still beyond reach. Biological studies reveal that insect wings are equipped with mechanoreceptors known as campaniform sensilla, which detect complex aerodynamic loads critical for flight agility. By leveraging robotic experiments designed to mimic these biological systems, we confirm that wing strain provides crucial information about the drone’s attitude angle, as well as the direction and velocity of the wind. We introduce a wing-strain-based flight controller that employs the aerodynamic forces exerted on a flapping drone’s wings to deduce vital flight data such as attitude and airflow without accelerometers and gyroscopic sensors. The present work spans five key experiments: initial validation of the wing strain sensor system for state information provision, control in a single degree of freedom movement environment with changing winds, control in a two degrees of freedom movement environment for gravitational attitude adjustment, a test for position control in windy conditions and a demonstration of precise flight path manipulation in a windless condition using only wing strain sensors. We have successfully demonstrated control of a flapping drone in various environments using only wing strain sensors, with the aid of a reinforcement-learning-driven flight controller. The demonstrated adaptability to environmental shifts will be beneficial across varied applications, from gust resistance to wind-assisted flight for autonomous flying robots.

High-Accuracy, Vision-Based Attitude Estimation System for Air-Bearing Spacecraft Simulators

Air-bearing platforms for simulating the attitude dynamics of satellites require highly accurate ground truth systems. Commercial off-the-shelf motion-capture systems are used for this scope, although they are complex and expensive. This paper shows a novel and versatile method to estimate the attitude of rotational air-bearing platforms using a monocular camera and sets of fiducial LED markers. The work proposes a geometry-based, iterative algorithm that is significantly more accurate than other literature methods that involve solving the perspective-n-point problem. Additionally, autocalibration procedures to perform a preliminary estimation of the system parameters are shown. The developed methodology is deployed onto a Raspberry Pi 4 microcomputer and tested with an array of LEDs soldered on a custom printed circuit board. Data obtained with this setup are compared against simulations of the system to determine and validate its performance. The hardware setup is also validated against independent inclinometric and gyroscope sensor measurements. Simulation and test results show expected 1-sigma accuracies of 12 arcs and 37 arcs for about- and cross-boresight rotations of the platform, respectively, and average latency times of 6 ms.

МАТЕМАТИЧНІ МОДЕЛІ МОНІТОРИНГУ ВІДКЛАДЕНЬ ОЖЕЛЕДІ ТА ЗМІНИ СТРІЛИ ПРОВИСАННЯ ПРОВОДІВ ПОВІТРЯНИХ ЛІНІЙ ЕЛЕКТРОПЕРЕДАВАННЯ

The paper presents the results of studing the problem of monitoring the condition of an overhead power line wire. The known approaches to the formation of a device for monitoring the sagging boom and ice-coating on the line wires are analysed. It is shown that one of the most promising approaches is based on measuring the angle of inclination of the wire sagging curve near the point of its fixation on the support. It is shown that an unambiguous correlation between the slope angle of the sagging curve and the wire sagging arrow allows for an indirect measurement of the operating temperature of the wire in the absence of ice deposits. It has been shown that equipping the monitoring device with a temperature sensor will allow monitoring the weight of ice-coating and, if necessary, issuing a signal for organising anti-icing measures. Modification of the device with a three-axis gyroscopic sensor allows for additional monitoring of wind pressure on overhead line wires. The paper presents mathematical models for solving these problems of monitor-ing the condition of the wire.

Sea Horse Optimization-Deep Neural Network: A Medication Adherence Monitoring System Based on Hand Gesture Recognition.

Medication adherence is an essential aspect of healthcare for patients and is important for achieving medical objectives. However, the lack of standard techniques for measuring adherence is a global concern, making it challenging to accurately monitor and measure patient medication regimens. The use of sensor technology for medication adherence monitoring has received much attention lately since it makes it possible to continuously observe patients' medication adherence behavior. Sensor devices or smart wearables utilize state-of-the-art machine learning (ML) methods to analyze intricate data patterns and provide predictions accurately. The key aim of this work is to develop a sensor-based hand gesture recognition model to predict medication activities. In this research, a smart sensor device-based hand gesture prediction model is developed to recognize medication intake activities. The device includes a tri-axial gyroscope, geometric, and accelerometer sensors to sense and gather data from hand gestures. A smartphone application gathers hand gesture data from the sensor device, which is then stored in the cloud database in a .csv format. These data are collected, processed, and classified to recognize the medication intake activity using the proposed novel neural network model called Sea Horse Optimization-Deep Neural Network (SHO-DNN). The SHO technique is implemented to update the biases and weights and the number of hidden layers in the DNN model. By updating these parameters, the DNN model is improved in classifying the samples of hand gestures to identify the medication activities. The research model demonstrates impressive performance, with an accuracy of 98.59%, sensitivity of 97.82%, precision of 98.69%, and an F1 score of 98.48%. Hence, the proposed model outperformed the most available models in all the aforementioned aspects. The results indicate that this model is a promising approach for medication adherence monitoring in healthcare applications, instilling confidence in its effectiveness.

Rompi Pintar Pengendara Menggunakan Sensor Kemiringan Untuk Kebutuhan Keselamatan Berbasis IOT

Traffic accidents often occur in everyday life. Many factors cause traffic accidents to occur. Contributors to the high number of traffic accidents are two-wheeled drivers. So an air vest is needed that can reduce the effects of impact if an accident occurs. In this research, an air vest for two-wheeled riders will be designed. Equipped with an IoT-based tilt sensor. This research designs an IoT-based air vest for two-wheeled riders to reduce the impact effects during an accident. This vest is equipped with a tilt sensor which is similar to the function of airbags in four-wheeled vehicles. The way the vest works is that when the sensor detects a certain tilt programmed into the Arduino, the vest will inflate. The main components of this vest are the Arduino Uno ATMega 328 and the MPU-6050 gyroscope sensor. Prototype testing showed a 60% success rate with a development time of 7-10 seconds. However, hands-on testing provided satisfactory results with a 100% success rate and consistent development time of 7-10 seconds. This vest is expected to improve the safety of everyday two-wheeled riders.

Design of 2-DOF Thrust vector control system for Rockets and Missiles

This paper outlines the development and implementation of a Thrust Vector Control (TVC) system tailored specifically for solid propellant rocket engines, aimed at enhancing the portability of hybrid and liquid propellant rocket systems. The proposed system ensures trajectory stability and rapid response to flight emergencies by effectively addressing external perturbations like wind. Key components are Gyroscopic (GYRO) sensors, good micro-controller, and Servo motors, collectively referred to as Thrust vectoring components, which dynamically adjust thrust direction opposite to the rocket's trajectory to maintain stability. Drawing from an extensive literature review analyzing existing TVC system designs, with a focus on thrust characteristics and engine combustion timings, the design integrates considerations of geometric properties, kinematics, forces, energy requirements, safety, cost, and control methods, aligning with both mechanical and avionic design principles. The anticipated outcome is an advancement in rocket propulsion technology, characterized by improved angular speed control, trajectory linearity, and rapid response capabilities.

A Multi-Sensing IoT System for MiC Module Monitoring during Logistics and Operation Phases.

Modular integrated construction (MiC) is now widely adopted by industry and governments. However, its fragile and delicate logistics are still a concern for impeding project performance. MiC logistic operations involve rigorous multimode transportation, loading-unloading, and stacking during storage. Such processes may induce latent and intrinsic damage to the module. This damage causes safety hazards during assembly and deteriorates the module's structural health during the building use phase. Also, additional inspection and repairs before assembly cause uncertainties and can delay the whole supply chain. Therefore, continuous monitoring of the module's structural response during MiC logistics and the building use phase is vital. An IoT-based multi-sensing system is developed, integrating an accelerometer, gyroscope, and strain sensors to measure the module's structural response. The compact, portable, wireless sensing devices are designed to be easily installed on modules during the logistics and building use phases. The system is tested and calibrated to ensure its accuracy and efficiency. Then, a detailed field experiment is demonstrated to assess the damage, safety, and structural health during MiC logistic operations. The demonstrated damage assessment methods highlight the application for decision-makers to identify the module's structural condition before it arrives on site and proactively avoid any supply chain disruption. The developed sensing system is directly helpful for the industry in monitoring MiC logistics and module structural health during the use phase. The system enables the researchers to investigate and improve logistic strategies and module design by accessing detailed insights into the dynamics of MiC logistic operations.

Unmanned ground vehicle (UGV) based automated construction progress measurement of road using LSTM

PurposeCurrent solutions for monitoring the progress of pavement construction (such as collecting, processing and analysing data) are inefficient, labour-intensive, time-consuming, tedious and error-prone. In this study, an automated solution proposes sensors prototype mounted unmanned ground vehicle (UGV) for data collection, an LSTM classifier for road layer detection, the integrated algorithm for as-built progress calculation and web-based as-built reporting.Design/methodology/approachThe crux of the proposed solution, the road layer detection model, is proposed to develop from the layer change detection model and rule-based reasoning. In the beginning, data were gathered using a UGV with a laser ToF (time-of-flight) distance sensor, accelerometer, gyroscope and GPS sensor in a controlled environment. The long short-term memory (LSTM) algorithm was utilised on acquired data to develop a classifier model for layer change detection, such as layer not changed, layer up and layer down.FindingsIn controlled environment experiments, the classification of road layer changes achieved 94.35% test accuracy with 14.05% loss. Subsequently, the proposed approach, including the layer detection model, as-built measurement algorithm and reporting, was successfully implemented with a real case study to test the robustness of the model and measure the as-built progress.Research limitations/implicationsThe implementation of the proposed framework can allow continuous, real-time monitoring of road construction projects, eliminating the need for manual, time-consuming methods. This study will potentially help the construction industry in the real time decision-making process of construction progress monitoring and controlling action.Originality/valueThis first novel approach marks the first utilization of sensors mounted UGV for monitoring road construction progress, filling a crucial research gap in incremental and segment-wise construction monitoring and offering a solution that addresses challenges faced by Unmanned Aerial Vehicles (UAVs) and 3D reconstruction. Utilizing UGVs offers advantages like cost-effectiveness, safety and operational flexibility in no-fly zones.

Self Balancing Robot using Arduino

Abstract: This research paper presents the design, development, and implementation of an Arduino micro controller-based selfbalancing robot. This study looks at how sensors, actuators, and control algorithms can work together to provide stable and dependable balance control. The Two-Wheeled Self-Balancing Robot (TWSBR) was controlled in this work using a Proportional, Integral, and Differential (PID) controller. The suggested system makes use of a PID control algorithm for accurate motor speed adjustment and an inertial measurement unit (IMU) for real-time orientation monitoring of the robot[4]. The two DC stepper motors applied the proper amount of torque in the right direction, which allowed the structure to maintain a vertical equilibrium state. The robot measures its tilt and angular velocity with a gyroscope sensor. The outcomes of the experiments indicate that the suggested method is efficient in preserving equilibrium in different circumstances, highlighting the possibilities of Arduino based systems for the creation of self-governing robotic systems. Through iterative testing and improvement [2], the objective is to build a selfbalancing robot that is sturdy and steady and can navigate and adapt to various surfaces and disturbances.

Arduino Based Flight Control Card Design and Quadcopter Integration

Unmanned aerial vehicles are used quite widely today, especially quadcopters, which we often encounter in areas such as the defense industry, agriculture, and civil aviation. Dec Jul Flight control cards are the products with the highest cost among these products, especially for someone who has a hobby in civilian life or who is curious about electronics and aviation, so it is quite expensive to supply or produce these vehicles. We are designing and producing a cost-effective, easily accessible, and affordable flight control card by using Arduino and Gyroscope sensors in the works we are planning. At the same time, a design is considered one in which the user can code as open-source hardware. The project has two working areas, hardware and software. The work in the hardware field involves designing the flight control board through the drawing program, producing printed circuits for the designed board, and integrating Arduino Mega and other components into this board. On the software side, it is the control algorithm and flight software coding via Arduino IDE. Due to the fact that it has a large number of libraries, it is accessible and understandable to most people, so the Arduino IDE program has been used.

Decision Tree-Based Direction Detection Using IMU Data in Autonomous Robots

Location detection plays a crucial role in various applications. In this study, a machine learning (ML) method using inertial measurement unit (IMU) data was developed to determine direction with the Global Positioning System (GPS). In this study, an electronic board was designed using an Arduino Mega, Altimu-10 IMU sensor, GPS module, and SD card module. This electronic board was placed on a car to create a new dataset. This dataset consists of 1952x11 data. The dataset was obtained using accelerometer (x, y, z), gyroscope (x, y, z), compass (x, y, z), and GPS sensor data. The Decision Tree Algorithm was proposed for direction determination in this study. The angles between each position and the previous position were calculated using the latitude and longitude values obtained from the collected data. Then, the data were divided into 4 classes: North, East, South, and West, based on specific angle ranges. Finally, a direction detection model was developed using IMU data in the proposed method, achieving an accuracy of approximately 82.11%.

Bladeless Wind Turbine Triboelectric Nanogenerator for Effectively Harvesting Random Gust Energy

AbstractIn the environment, there is an abundance of gust energy which is challenging to harvest with conventional rotating wind turbines, such as the gusts generated by passing vehicles along roadsides. Addressing the irregular and low‐frequency characteristics of gusts, a bladeless wind turbine triboelectric nanogenerator (BWT‐TENG) with enhanced aerodynamic performance is proposed, enabling effective harvesting of random gust energy. First, a bladeless wind turbine with a cylindrical bluff body shape is designed, and its aerodynamic principles under gust‐driven conditions are elucidated through the computational fluid dynamics method. Subsequently, parameter optimization is conducted for the multilayered TENG. Systematic experiments demonstrated that the BWT‐TENG achieved a peak power density of 4.08 W m−3 driven by a gust of 10 m s−1, and can even operate at frequencies as low as 0.1 Hz. Finally, experiments showcased the BWT‐TENG powering a warning light in a simulated rainfall environment and harvesting gust energy from vehicles passing by real roadside to power wireless gyroscopic sensors, thereby achieving self‐powered structural health monitoring of roads or bridges. This work provides a novel strategy for utilizing TENGs in the harvest of environmental gust energy and demonstrates the vast potential of TENGs in the field of self‐powered structural health monitoring.

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F1 score, accuracy, precision, and recall. Model performance was high, with F1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments.

Design of Non-Intrusive Online Monitoring System for Traction Elevators

With the increase in elevator usage, more and more elevator real-time monitoring equipment is being applied to the operation of elevators. Traditional elevator monitoring equipment adopts a multi-sensor decentralized installation and layout, and the monitoring accuracy is low, which directly affects the effective alarm of the monitoring system; however, existing online monitoring systems cannot quickly alarm for faults. Aiming to solve the above problems, an elevator online monitoring system based on narrow-band Internet of Things (NB-IoT) is designed. The system is highly integrated with an STM32 main control chip, a six-axis acceleration gyroscope sensor, and an air pressure sensor to realize the edge calculation of the monitoring system. At the same time, this paper eliminates the temperature drift of the pressure sensor by using a temperature compensation algorithm and inputs the extracted characteristic parameters into the BP neural network for training to eliminate the zero drift so as to obtain the real-time height data of the elevator. The six-axis acceleration gyroscope sensor is used to calculate the posture so as to avoid the problem that a three-axis acceleration sensor or a three-axis gyroscope sensor alone cannot obtain accurate posture data. In order to further improve the monitoring accuracy, the peak-to-peak value of the signal is calculated by using a 95% confidence interval algorithm to reduce the suppression of the high-frequency components of the signal by noise and ensure that the signal has a large signal-to-noise ratio so that the obtained elevator car posture and vibration operation data are more accurate. Finally, the effectiveness of the proposed method is verified by experiments.

Reliable detection of generalized convulsive seizures using an off-the-shelf digital watch: A multisite phase 2 study.

The aim of this study was to develop a machine learning algorithm using an off-the-shelf digital watch, the Samsung watch (SM-R800), and evaluate its effectiveness for the detection of generalized convulsive seizures (GCS) in persons with epilepsy. This multisite epilepsy monitoring unit (EMU) phase 2 study included 36 adult patients. Each patient wore a Samsung watch that contained accelerometer, gyroscope, and photoplethysmographic sensors. Sixty-eight time and frequency domain features were extracted from the sensor data and were used to train a random forest algorithm. A testing framework was developed that would better reflect the EMU setting, consisting of (1) leave-one-patient-out cross-validation (LOPO CV) on GCS patients, (2) false alarm rate (FAR) testing on nonseizure patients, and (3) "fixed-and-frozen" prospective testing on a prospective patient cohort. Balanced accuracy, precision, sensitivity, and FAR were used to quantify the performance of the algorithm. Seizure onsets and offsets were determined by using video-electroencephalographic (EEG) monitoring. Feature importance was calculated as the mean decrease in Gini impurity during the LOPO CV testing. LOPO CV results showed balanced accuracy of .93 (95% confidence interval [CI] = .8-.98), precision of .68 (95% CI = .46-.85), sensitivity of .87 (95% CI = .62-.96), and FAR of .21/24 h (interquartile range [IQR] = 0-.90). Testing the algorithm on patients without seizure resulted in an FAR of .28/24 h (IQR = 0-.61). During the "fixed-and-frozen" prospective testing, two patients had three GCS, which were detected by the algorithm, while generating an FAR of .25/24 h (IQR = 0-.89). Feature importance showed that heart rate-based features outperformed accelerometer/gyroscope-based features. Commercially available wearable digital watches that reliably detect GCS, with minimum false alarm rates, may overcome usage adoption and other limitations of custom-built devices. Contingent on the outcomes of a prospective phase 3 study, such devices have the potential to provide non-EEG-based seizure surveillance and forecasting in the clinical setting.

Top-Down Design Method of a Time Domain Accelerometer with Adjustable Resolution.

A top-down design methodology and implementation of a time domain sensor is presented in this paper. The acceleration resolution of the time domain sensor is equal to the time-measurement accuracy divided by the sensor sensitivity. Combined with the sensitivity formula, the acceleration resolution is proportional to the vibration amplitude, the time-measurement accuracy, and the third power of the resonant frequency. According to the available time-measurement accuracy and the desired acceleration resolution, the parameters including the vibration amplitude and the resonant frequency were theoretically calculated. The geometrical configuration of the time domain sensor device was designed based on the calculated parameters. Then, the designed device was fabricated based on a standard silicon-on-insulator process and a matched interface circuit was developed for the fabricated device. Experimental results demonstrated that the design methodology is effective and feasible. Moreover, the implemented sensor works well. In addition, the acceleration resolution can be tuned by adjusting the time-measurement accuracy and the vibration amplitude. All the reported results of this work can be expanded to other time domain inertial sensors, e.g., a gyroscope or tilt sensor.

GyroLock: A Gyroscopic implementation for privacy Protection

GyroLock is a smartphone application designed to prevent the snatching of cell phones. Given the significant role that mobile devices play in an increasingly digital environment, certain actions carried out in public settings can pose a high level of danger and have negative consequences. The gyro lock solution utilizes the gyroscope sensor in the phone to promptly secure the device when it detects abrupt, erratic, and disordered motions, similar to those associated with theft. The motion detection feature serves to prevent any unauthorized individual from physically extracting your personal and sensitive data from the program. The program is highly intuitive, allowing users to easily enable features or customize them according to their environment and personal preferences. GyroLock enhances device safety by allowing users to customize the sensitivity of motion detection and activate the service. Gyrolock will enhance client services by offering automated and immediate reactions to suspected cases of theft. This enhances the safety and reassurance of consumers while reducing the dangers linked to data theft and loss.

Feasibility of a portable respiratory training system with a gyroscope sensor.

A portable respiratory training system with a gyroscope sensor (gyroscope respiratory training system [GRTS]) was developed and the feasibility of respiratory training was evaluated. Simulated respiratory waveforms from a respiratory motion phantom and actual respirator waveforms from volunteers were acquired using the GRTS and Respiratory Gating for Scanners system (RGSC). Respiratory training was evaluated by comparing the stability and reproducibility of respiratory waveforms from patients undergoing expiratory breath-hold radiation therapy, with and without the GRTS. The stability and reproducibility of respiratory waveforms were assessed by root mean square error and gold marker placement-based success rate of expiratory breath-hold, respectively. The absolute mean difference for sinusoidal waveforms between the GRTS and RGSC was 2.0%. Among volunteers, the mean percentages of errors within ±15% of the respiratory waveforms acquired by the GRTS and RGSC were 96.1% for free breathing and 88.2% for expiratory breath-hold. The mean root mean square error and success rate of expiratory breath-hold (standard deviation) with and without the GRTS were 0.65 (0.24) and 0.88 (0.89) cm and 91.0% (6.9) and 89.1% (11.6), respectively. Respiratory waveforms acquired by the GRTS exhibit good agreement with waveforms acquired by the RGSC. Respiratory training with the GRTS reduces inter-patient variability in respiratory waveforms, thereby improving the success of expiratory breath-hold radiation therapy. A respiratory training system with a gyroscope sensor is inexpensive and portable, making it ideal for respiratory training. This is the first report concerning clinical implementation of a respiratory training system.