Flex Sensors Research Articles

The Effectiveness Obstructive Sleep Apnea Monitoring Using Telemedicine Smartphone System (TmSS)

Data at the world health organization shows that around more than 100 million people worldwide suffer from Obstructive Sleep Apnea (OSA) and most sufferers go undetected. The purpose of this study is to develop an apnea monitor that can detect the symptoms of Obstructive Sleep Apnea using the Telemedicine Smartphone System (TmSS). The contribution of this study is the generation of telemedicine systems in sleep apnea monitoring devices. So that the monitoring tools can be effective and efficient when used, then the Obstructive Sleep Apnea monitoring tool is made with the TmSS system that can transmit data values wirelessly and in real-time. This tool uses a flex sensor to detect patient breathing. The output generated by the sensor is then conditioned on an analog signal conditioner (PSA) circuit. The signal output from the PSA is processed on the ATMega 328 microcontroller to get the respiration value which is then sent via Bluetooth HC-05 and displayed on an android smartphone device which will also display a warning notification in the event of stopping breathing (apnea). Based on the results of the measurement of respiration values compared with standard equipment produces the highest error value of 6.98% and the lowest of 0.00%. The tool can send data respiration values using the TmSS system properly. This tool can be implemented to detect the symptoms of Obstructive Sleep Apnea.

Human Signature Identification Using IoT Technology and Gait Recognition

This study aimed to develop an autonomous design system for recognizing the subject by gait posture. Gait posture is a type of non-verbal communication characteristic of each person, and can be considered a signature used in identification. This system can be used for diagnosis. The system helps aging or disabled subjects to identify incorrect posture to recover the gait. Gait posture gives information for subject identification using leg movements and step distance as characteristic parameters. In the current study, the inertial measurement units (IMUs) located in a mobile phone were used to provide information about the movement of the upper and lower leg parts. A resistive flex sensor (RFS) was used to obtain information about the foot contact with the ground. The data were collected from a target group comprising subjects of different age, height, and mass. A comparative study was undertaken to identify the subject after the gait posture. Statistical analysis and a machine learning algorithm were used for data processing. The errors obtained after training data are presented at the end of the paper and the obtained results are encouraging. This article proposes a method of acquiring data available to anyone by using indispensable devices purchased by all users such as mobile phones.

Design of Effective Smart Communication System for Impaired People

In communication medium, sharing a conversation dialogue between the normal person and deaf and dumb person is one of the challenging tasks still. The dumb person can practice hand gesture language in their community but not to others. This research article focuses to minimize the difficulty level between these two communities with smart glove devices. Besides, the author believes that result of the proposed model provides a good impact on the dump community. The smart glove contains input, control, and output module to get, process, and display the data respectively. Our proposed model is used to help these communities to interact with each other continuously without any error. The proposed model is constructed with good specification flex sensors. Little change of resistance in flex sensor is providing changes in their gesture language. So this orientation direction is calculated well and gives better results over existing methods. The wireless set can be made with Bluetooth technologies here. Here the gestures are assigned based on the alphabet letter. The sign language performs and gives audible output in the display section of the proposed model. It gives good results in our experimental setup. This research work focuses on good recognition rate, accuracy, and efficiency. The good recognition rate shows the continuous conversation between the two persons. Moreover, this research article compares the recognition rate, accuracy, and efficiency of the proposed model with an existing model.

Smart Glove for Deaf

Smart glove is used to help deaf to interpret their communication. This tools is an interesting topic to be explored because its need improvement for the feature that user friendly and easy to used. In this paper, flex sensor and accelero-gyro is used. By using this tools, all of the sign language will be interpreted based on system database that registered before. Then, all of data will be displayed as text in the smartphone. The results prove that the proposed method can interpret the language system correctly.

A prototype of IoT-based smart system to support motorcyclists safety

This study described the prototype of the smart system for support safety riding using the Internet of Things (IoT) technology. This system consists of connectivity objects like helmets, motorcycles, and riders/people (via smartphone). The system is pervasive in helmets and motorcycle with several main electronic components, including NodeMCU micro controller, accelerometer-gyroscope sensor, a GPS (Global Positioning System) module, flex sensor, buzzer, and relay. The helmet, motorcycles, and riders then are connected with others through the internet with the android application interface. The application can monitor real-time status and location riders using firebases’s real-time database. This system has four features, which are a combination of previous related works, namely helmet detection, drowsiness detection, accident detection, and notification with the accident’s location that can be tracked by others. The results of this system prototype experiment showed that all features of the system are running well. The accuracy value for helmet detection is 100%, drowsiness detection is 87%, and accident detection is 90%. Rider status and location can be monitored and tracked by others via the android application.

Grasp to See-Object Classification Using Flexion Glove with Support Vector Machine.

This paper proposes an object classification method using a flexion glove and machine learning. The classification is performed based on the information obtained from a single grasp on a target object. The flexion glove is developed with five flex sensors mounted on five finger sleeves, and is used for measuring the flexion of individual fingers while grasping an object. Flexion signals are divided into three phases, and they are the phases of picking, holding and releasing, respectively. Grasping features are extracted from the phase of holding for training the support vector machine. Two sets of objects are prepared for the classification test. One is printed-object set and the other is daily-life object set. The printed-object set is for investigating the patterns of grasping with specified shape and size, while the daily-life object set includes nine objects randomly chosen from daily life for demonstrating that the proposed method can be used to identify a wide range of objects. According to the results, the accuracy of the classifications are achieved 95.56% and 88.89% for the sets of printed objects and daily-life objects, respectively. A flexion glove which can perform object classification is successfully developed in this work and is aimed at potential grasp-to-see applications, such as visual impairment aid and recognition in dark space.

PROTOTYPE SISTEM KENDALI ROBOT ARM GRIPPER MANIPULATOR MENGGUNAKAN FLEX SENSOR DAN MPU6050 BERBASIS INTERNET OF THINGS

In this sophisticated era a lot of human work that has begun to be done by robots. Robots are used to facilitate work that can not be done by humans, such as moving an item in a dangerous place. One of the robots created to facilitate human work is a robot that has a shape like a human arm called the arm gripper manipulator. Arm gripper manipulator is a robot that has the ability to move like a human arm. The manipulator arm consists of joint, link, and end-effector. This research designed a control system of the robot arm gripper manipulator with 2 modes, gesture mode and IoT mode. The microcontroller used is Arduino Mega 2560 with flex sensor control and MPU 6050 inertia measurement unit sensor in gesture mode and IoT control mode with time average errors in 5 movements is 2.08%. The overall test results of the robot arm gripper manipulator can be controlled with gesture mode and IoT mode. Normal 0 false false false EN-US X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0in; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri",sans-serif; mso-ansi-language:IN; mso-fareast-language:EN-US;} Abstract . In this sophisticated era a lot of human work that has begun to be done by robots. Robots are used to facilitate work that can not be done by humans, such as moving an item in a dangerous place. One of the robots created to facilitate human work is a robot that has a shape like a human arm called the arm gripper manipulator. Arm gripper manipulator is a robot that has the ability to move like a human arm. The manipulator arm consists of joint, link, and end-effector. This research designed a control system of the robot arm gripper manipulator with 2 modes, gesture mode and IoT mode. The microcontroller used is Arduino Mega 2560 with flex sensor control and MPU 6050 inertia measurement unit sensor in gesture mode and IoT control mode with time average errors in 5 movements is 2.08%. The overall test results of the robot arm gripper manipulator can be controlled with gesture mode and IoT mode.

Training with Agency-Inspired Feedback from an Instrumented Glove to Improve Functional Grasp Performance.

Sensory feedback from wearables can be effective to learn better movement through enhanced information and engagement. Facilitating greater user cognition during movement practice is critical to accelerate gains in motor function during rehabilitation following brain or spinal cord trauma. This preliminary study presents an approach using an instrumented glove to leverage sense of agency, or perception of control, to provide training feedback for functional grasp. Seventeen able-bodied subjects underwent training and testing with a custom-built sensor glove prototype from our laboratory. The glove utilizes onboard force and flex sensors to provide inputs to an artificial neural network that predicts achievement of “secure” grasp. Onboard visual and audio feedback was provided during training with progressively shorter time delay to induce greater agency by intentional binding, or perceived compression in time between an action (grasp) and sensory consequence (feedback). After training, subjects demonstrated a significant reduction (p < 0.05) in movement pathlength and completion time for a functional task involving grasp-move-place of a small object. Future work will include a model-based algorithm to compute secure grasp, virtual reality immersion, and testing with clinical populations.

Predictive Uncertainty Estimation Using Deep Learning for Soft Robot Multimodal Sensing

The mechanical compliance of soft robots comes at a cost of higher uncertainty in their sensing and perception, which deteriorates the accuracy of predictive models. Predictive uncertainty, which expresses the confidence behind model predictions, is necessary to compensate for the loss of accuracy in soft robot perceptive models. Nevertheless, developing a general framework to capture uncertainties is further challenged by the complex dynamics of soft robots and the difficulties in sensorizing them. In this work, we present a predictive uncertainty estimation framework based on deep learning for soft robot multimodal sensing. We show that the framework can learn to quantify uncertainty and thus is able to express the confidence associated with the predictions during inference. Being data-driven, it is scalable to different types of soft robots and sensor modalities. We demonstrate the framework on a complex multimodal sensing task where a single flex sensor is used to predict the full-body configuration of a soft actuator, as well as the magnitude and location of external contact force. We also discuss how predictive uncertainties are critical to achieve safe learning and model interpretability in soft robotics.

Home-Based Online Multisensory Arm Rehabilitation Monitoring System

Arm rehabilitation activities need to be monitored continuously in terms of analysis by experts within sufficient information to discover arm dysfunction and disorders such as stroke early. Although there are numerous previous researches about the home-based rehabilitation procedures and arm performance, some drawbacks still exist. For example, current rehabilitation devices are too complicated and required supervision by qualified therapists rather than their high prices. Moreover, data from these devices take much time to be sent to doctors for monitoring purpose. Therefore, this paper proposes a home-based online multisensory arm rehabilitation monitoring system. This system is designed through three main stages which are data acquisition, data processing, and data logging respectively. Data acquisition is by three different types of sensors; flex sensor (for arm’s bending), force-sensitive resistors (for hand fingers’ forces) and accelerometer (for arm movement directions). In data processing, Arduino Mega Controller and ESP Wi-Fi shield are used to design Internet of Things (IoT) web-based system (ThingSpeak) for data logging that allows doctors to diagnose stroke recovery and give feedbacks for patients. Overall, this project showed a robust system for arm rehabilitation using portable, user-friendly, and low power consumption devices at a low cost.

Intelligent sowing depth regulation system based on Flex sensor and Mamdani fuzzy model for a no-till planter

Sowing depth has an important impact on the performance of no-tillage planters, it is one of the key factors to ensure rapid germination. However, the consistency of sowing depth is easily affected by the complex environment of no-tillage operation. In order to improve the performance of no-tillage planters and improve the control precision of sowing depth, an intelligent depth regulation system was designed. Three Flex sensors installed on the inner surface of the gauge wheel at 120° intervals were used to monitor the downward force exerted by the seeding row unit against ground. The peak value of the output voltage of the sensor increased linearly with the increase of the downward force. In addition, the pneumatic spring was used as a downforce generator, and its intelligent regulation model was established by the Mamdani fuzzy algorithm, which can realize the control of the downward force exerted by the seeding row unit against ground and ensure the proper seeding depth. The working process was simulated based on MATLAB-Simulink, and the results showed that the Mamdani fuzzy model performed well in changing the pressure against ground. Field results showed that when the operating speed was 6 km/h, 8 km/h and 10 km/h, the error of the system's control of sowing depth was ±9 mm, ±12 mm, and ±22 mm, respectively, and its sowing performance was significantly higher than that of the unadjusted passive operation. Keywords: Flex sensor, Mamdani fuzzy model, sowing depth, intelligent regulation system, no-till planter DOI: 10.25165/j.ijabe.20211406.5939 Citation: Li M W, Xia X M, Zhu L T, Zhou R Y, Huang D Y. Intelligent sowing depth regulation system based on Flex sensor and Mamdani fuzzy model for a no-till planter. Int J Agric & Biol Eng, 2021; 14(6): 145–152.

Sign Language Recognition System

In this paper an attempt has been made to design a sign language recognition system. An intelligent glove has been designed to automate the communication between a deaf-mute with others by converting sign language into speech or understandable language. The sensory gloves provide data of the human hand shape or movement and translate it to text and speech. It comprises hardware and software for translating sensor data. It is wearable devices that can be put on human hands and convert hand's gestures into signs letter by letter and send the data into the firebase for further processing. The glove is equipped with flex sensors and an inertial measurement unit to recognize the movement by monitoring the finger orientation and hand motion in three-dimensional spaces that senses a person's gestures in the form of finger bend and hand fist tilt. The Hall sensor has been used to process and collect data for training and model development. The three different machine learning algorithms, i.e., support vector machine, Naive Bayes, decision tree, have been used for analysis. It has been observed that the support vector machine has the highest accuracy, i.e., 90%. After Analyzing, the data has been sent to the speech converting function, and then audible results have been produced.

Eye power and pressure detection using MEMS sensor

Though the technology has been a boon to us in many ways, continuous watching of digital displays would definitely cause power related problems to the eyes. Power problems are common in all age groups irrespective of the age, Children are facing the critical eye issues by keenly watching the television, they are not even aware of the issue what they are going through. The spectacles are sometimes not effective over the increase in power. Hence the detection of power based vision would reduce the problems. Presbyopia is caused due to ageing factors, whereas myopia and hypermetropia are farsightedness and short sightedness common among the young people who are the victims of being attracted by harmful rays radiating digital displays. To overcome these problems mems based lens is designed as an implant using hydrogel material with flex sensors, which is presented here.

Design of a fluid-driven 3D printed spinal posture corrector

Abstract Application of 3D printing materials is increasing in the recent bio-medical engineering applications. Neglectful attitude toward body posture could bring the formation of spinal diseases. Improver posture during the working process induces the pain at the lower back and pectoral kyphosis. Disregard of treatment at the initial stage will further deteriorate the spinal disorder and force surgical intervention. The paper discussed several important factors together with the 3D printed spine. Thereby, this paper purpose corrector device, which intended to adjust the posture of the spine in daily life and form proper posture habits for the user. The device is equipped with a flex sensor, which detects forward spinal bending, whereas the IMU sensor measures the side motion of the body. The novel fluid-driven mechanism carries out the motion of the spinal skeleton. The origami-inspired skeleton is capable of imitating the movement of the real backbone. Under negative pressure, the skeleton constructs correct spine curvature. The algorithm inside the microcontroller processes data from the sensor and controls the actuator. A simple manufacturing process makes the design suitable for customized production.

Wearable Device for Yogic Breathing with Real-Time Heart Rate and Posture Monitoring.

Background:Yogic breathing also called as “Pranayama” is practiced with inhalation (Pooraka), holding the breath for some time (Kumbhaka) and then exhalation (Rechaka). The effective methods of yogic breathing keep oneself healthy and also improves immunity power. The yogic breathing can be practiced irrespective of one's age and gender and even in the office which helps to reduce the stress. To get the best results through yoga, a person has to follow certain timings and sit in a correct posture. Although many devices are existing in the market to monitor heart rate, posture and breathing during physical activity, there is a need of a device which is simple, cheap, and easy to use without an additional requirement of a smartphone. Moreover, the proposed device is able to evaluate the breathing data by transmitting it to a webpage through a Wi-Fi hotspot of the Microcontroller.Methods:The developed device has two subsystems: (i) A wrist subsystem to measure the heart rate, visual aid of breathing and vibration feedback for kapalabhati. (ii) A waist subsystem to monitor the posture with help of flex sensor and the results are displayed on the display of the wrist device. It also provides vibration feedback. The inertial measurement unit is used for breath detection. The subsystems are communicated through SPI communication. The breathing data are transmitted to a webpage through a Wi-Fi hotspot of the microcontroller.Results:The various yogic breathing and normal breathing exercises are tested on different normal subjects using the developed device and analyzed. The heart rate and beats per minute are evaluated. The heart rate sensor is validated using a standard medical device and it is observed that there was a 97.4% accuracy.Conclusion:The results show that the device is able to accurately monitor different kinds of breathing and additionally provide heart rate and posture information while performing the breathing exercises.

Toward the Minimum Number of Wearables to Recognize Signer-Independent Italian Sign Language With Machine-Learning Algorithms

Sign languages (SL) can aid in improving the communication between deaf and hearing communities, but only a limited number of hearing individuals understand it. SL recognition systems tackle this issue by using sensors to acquire gesture data, later converted into spoken or written language by means of machine learning algorithms. Within this frame, we propose a wearable electronic-based system for achieving automatic signer-independent recognition of Italian SL. The system is used for recognizing ten signs performed by 17 inexperienced signers. The wearable electronics measure hand, arm, and forearm gestures, by means of a sensory glove (equipped with ten flex sensors) and six Inertial Measurement Units (IMUs). We adopt three classifiers: Artificial Neural Network (ANN), k-Nearest Neighbors and Support Vector Machine, with ANN outperforming the others with an accuracy of 95.07%. However, the real key and novel aspect of this work concerns exploring the importance of each sensor for the overall classification accuracy, with the aim of determining the minimum number of sensors (and so minimizing the complexity of the wearable system) necessary to guarantee an acceptable accuracy. As a result, we could drop out three of the six IMUs, obtaining an accuracy as high as 93.91%. In addition, this valuable result was obtained using a signer-independent approach, which makes the application closer to a real-life situation.

A GSM based Resource Allocation technique to control Autonomous Robotic Glove for Spinal Cord Implant paralysed Patients using Flex Sensors

The autonomous robotic glove is designed for paralysed patients, so they would be able to control several electrical appliances around them as well as send an alert message to a particular person. Developing countries are trying to abate the problems of these patients as they depend on others to control nearby appliances both in home and in hospital. In this research we proposed a solution by development &amp; implementation of robotic glove. The research implementation consists of two parts. First part is transmitter and second part is receiver. Transmitter part mainly consists of flex sensors, Arduino uno and HC-11. Flex sensors are used to convert finger movements into different voltage levels, while Arduino is used to read this information from flex sensors and convey it to arduino mega on receiving end as programed by predefined gestures. HC-11 is a serial wireless communication transceiver module which is used to transmit information from Arduino uno to arduino mega on receiving side. Receiver side consist of HC-11, arduino mega, Global system for mobile communication (GSM) module, Optocoupler and Triac. Arduino-Mega is used to read the received information and perform action accordingly. On this side we have different electrical appliances which are controlled by hand gestures of patients as well as GSM module which is used to send different messages to associated person. Opto-coupler is used to isolate low power receiving circuit from high power load circuit. Triac is used for switching of AC supply. It is portable, requires low operating power on a single lithium-ion rechargeable battery and having less weight thus user friendly and affordable.

Sign Language Recognition System Using Cnn

In this study, we have built an automatic sign language translation system for deaf and dumb persons to communicate with ordinary people. According to the Statistics Department of the Taiwan Ministry of Health and Welfare, there are 119,682 hearing impaired persons, and 14,831 voice function or language dysfunctions. The Deaf and dumb persons’ account for 11.7% of the population with physical and mental disabilities. However, there are only 488 qualified people with the sign language translation skill certificate, which shows the importance of automatic sign language translation systems. This system collects 11 signals including five fingers’ curvature, 3-axis gyroscope and 3-axis accelerometer from left and right hand separately. In addition, a total of 22 signals are collected by the two sensors, Flex sensor and GY-521 six-axis with single-board computer Arduino MEGA 2560; and then uploaded to server via ESP-01S Wi-Fi module. While server receives the 22 signals, it converts to a RGB picture using PHP program. As a result, we can compare the picture with the model trained by TensorFlow and the compared result is stored in the database. Meanwhile, the comparison stored in database which can be accessed by APP programs would be displayed on the screen of the mobile device and be read aloud. The TensorFlow training model collects 25 sign language gestures, each based on 100 training gesture pictures, and a sign language recognition training model is Convolutional Neural Network (CNN). In this study, the results of the sign language recognition training model are further confirmed by 10 people other than those in training database. So far, the indeed recognition rate of sign language is about 84.4%, and the system response time is about 2.243 seconds.

Design and Testing of Flexibility Sensors to be Used in Agricultural Engineering Applications

Flexibility sensors are used to measure bending response of flexible materials which are employed in different technologies. They can be produced with easily available and low-cost materials. Its compactness, lightness and low power consumption makes this sensor ideal for manifold as well as any applications needs to monitor changes in shape or bending behavior. In this paper essential steps needed to design a custom-made, longer and cost effective flex sensor are discussed. It was found that selection of resistor, temperature dependency, and maximum possible length are major criteria to be considered. The best resistor yields the widest range was determined to be 100 Ω with maximum length of 75 cm. Another important finding of the study was the need of temperature compensation.

Design and development of the sEMG-based exoskeleton strength enhancer for the legs

This paper reviews the different exoskeleton designs and presents a working prototype of a surface electromyography (EMG) controlled exoskeleton to enhance the strength of the lower leg. The Computer Aided Design (CAD) model of the exoskeleton is designed, 3D printed with respect to the golden ratio of human anthropometry, and tested structurally. The exoskeleton control system is designed on the LabVIEW National Instrument platform and embedded in myRIO. Surface EMG sensors (sEMG) and flex sensors are used coherently to create different state filters for the EMG, human body posture and control for the mechanical exoskeleton actuation. The myRIO is used to process sEMG signals and send control signals to the exoskeleton. Thus, the complete exoskeleton system consists of sEMG as primary sensor and flex sensor as a secondary sensor while the whole control system is designed in LabVIEW. FEA simulation and tests show that the exoskeleton is suitable for an average human weight of 62 kg plus excess force with different reactive spring forces. However, due to the mechanical properties of the exoskeleton actuator, it will require an additional lift to provide the rapid reactive impulse force needed to increase biomechanical movement such as squatting up. Finally, with the increasing availability of such assistive devices on the market, the important aspect of ethical, social and legal issues have also emerged and discussed in this paper.