Flex Sensors Research Articles

Prosthetic robotic arm design using flex sensors for implementation in human assistive application

Prosthetic robotic arm design using flex sensors for implementation in human assistive application

Hand Gesture Recognition and Conversion to Speech for Speech Impaired

The primary method of interaction between individuals is communication. In the case of speech-impaired people, the communication between them and normal people is not understandable by the latter as the former communicates through gestures and sign language. In the case of speech-impaired. Today, the Internet of Things (IoT) can be used for gesture recognition and to convert gestures into audible speech. In this project, a prototype is created such that the gesture or the sign language that is communicated is recognized by the flex sensors connected to the fingertips of a plain glove. The ESP32 microcontroller recognizes the gesture and converts it into the text format and this text format is updated onto the Google Firebase and is converted to speech form thus producing the text onto the OLED display sensor and the converted speech for communication in the mobile application Kodular Companion.

Iot Based Sensor Network for Crack & Bend Monitoring in Railway Track

Abstract: In India railway is one of the most common means of transport, which is the fourth largest railway community in the world. Even though Indian railways has an outstanding boom, it remains plagued because of some of the major issues like problem in gate crossing, fire accidents and problem in the track which remains unmonitored causing derailment. The tracks contract and expand due to changes in season. Due to this crack may develop on the track. This proposed system identifies the cracks and the obstacles on the track using sensors The project railway crack and object detection are a forward step to improving the railway system. The system performs two main functions. The first one is detecting the crack on the railway track by using the Flex sensor and the second one is detecting the object by using IR sensor.

A Novel Soft Robotic Exoskeleton System for Hand Rehabilitation and Assistance Purposes

During the last decade, soft robotic systems, such as actuators and grippers, have been employed in various commercial applications. Due to the need to integrate robotic mechanisms into devices operating alongside humans, soft robotic systems concentrate increased scientific interest in tasks with intense human–robot interaction, especially for human-exoskeleton applications. Human exoskeletons are usually utilized for assistance and rehabilitation of patients with mobility disabilities and neurological disorders. Towards this direction, a fully functional soft robotic hand exoskeleton system was designed and developed, utilizing innovative air-pressurized soft actuators fabricated via additive manufacturing technologies. The CE-certified system consists of a control glove that copies the motion from the healthy hand and passes the fingers configuration to the exoskeleton applied on the affected hand, which consists of a soft exoskeleton glove (SEG) controlled with the assistance of one-axis flex sensors, micro-valves, and a proportional integral derivative (PID) controller. Each finger of the SEG moves independently due to the finger-dedicated motion control system. Furthermore, the real-time monitoring and control of the fabricated SEG are conducted via the developed software. In addition, the efficiency of the exoskeleton system was investigated through an experimental validation procedure with the involvement of healthy participants (control group) and patients, which evaluated the efficiency of the system, including safety, ergonomics, and comfort in its usage.

Flex Sensors Controlled Animatronics Hand

This paper focuses on understanding the simple and unique technique that is used for human robot interaction in robotic hand gesture replication system. The aims to fabricate a dual module system which synchronizes the real hand gesture with mechanical movement of the designed hand module at the output end in real time. The first part input module (IM) is user-controlled module which detects the real hand movement and convert it into signals and the signals are transmitted wirelessly to a receiver module comprising of a mechanical animatronics hand that will process the incoming signals and performs the mechanical movement in coherence with the received signal. Arduino boards integrated with their own microcontrollers and Xbee antennas are used to control both the input and output modules for the completion of the perform gesture. The input module comprises of a glove integrated with flex sensors and the Arduino board. 3D structure which is modeled as the real hand with the servo motors installed on it is used as an output module for the replication of the generated gesture from input module. This paper describes that advantages of Flex Sensors Controlled Animatronics Hand are in the environment which obstructs the physical approach of the humans and is not feasible for the human body. Nuclear power plants or nuclear weapon production areas, sophisticated chemical or pharmaceutical factories, bomb disposal department and Firefighting agencies etc. In all of these scenarios, Personal control is essential yet environment restricts the physical presence of human, therefore, this technique can be used as an alternative to automation so that an individual can operate under such conditions without physically being present at the location, preventing any unforeseen accidents and human casualties.

Posture monitoring device for abnormal spine musculoskeletal detection using flex sensor

During activity of daily living involving standing, sitting or maneuvering, humans are typically susceptible to neck and shoulder strain, and other musculoskeletal conditions, severity of which may lead to posture deformity. To prevent these clinical conditions, we developed a low-cost and user-friendly posture monitor mainly built on a single flex sensor. The design was based on abnormal posture detection by a flex sensor whose signal triggers a buzzer to notify the user or care giver of these clinical conditions. Through Arduino IDE, an ATmega328 microcontroller controlled the sequence of the flex sensing to the audible alarm output. The buzzer was designed to go off automatically when the user adjusts his/her posture to normalcy. With a sensitivity of 84.6% during testing of this device, the developed posture monitoring device could be adjudged effective and suitable to monitor people's posture while sitting or standing especially in environments where menial jobs are prevalent. In these individuals, this device may prevent deformity prone diseases that may warrant surgical intervention for correction.

Smart glove for sign language translation

The development of a wearable device-based sign language translator is discussed in this study. It can translate sign language into both speech and text. The glove-based gadget can read the motions of one arm and five fingers. The system consists of an accelerometer and five flex sensors to measure finger bending and arm motions, respectively. Based on the interaction of these sensors, the gadget can recognize specific motions that in American Sign Language (ASL) correspond to the alphabet and convert them into speech and text using a mobile phone application. The hardware design of the device is mostly explained in this publication. The gadget displayed an average value of 0.6 s to translate a sign language into speech and text based on early trial results on six simple sign languages, demonstrating the applicability of the suggested device.

End-Side Gesture Recognition Method for UAV Control

Traditional heavy and complex control equipment such as remote controllers (RCs) and ground stations (GSs) are not able to meet the fast and flexible control requirements of unmanned aerial vehicles (UAVs) in complex environments. This article thus proposes a gesture recognition method for the control of UAVs. To achieve the goal of gestural manipulation of UAVs, this method can accurately recognize a variety of gestures and convert the gestures into corresponding UAV control commands. First, the wireless data glove incorporates flex sensors, and inertial sensors are used to gather gesture datasets. The trained neural network model is then deployed on the data glove based on an STM32 microcontroller for real-time gesture recognition, in which the backpropagation (BP) network is used for static gesture recognition and the bidirectional gated recurrent unit (Bi-GRU) network is used for dynamic gesture recognition. Finally, the gesture is converted into the control command and sent to the aircraft terminal to control the UAV. Using the UAV simulation test on the simulation platform, the recognition accuracy of the basic UAV control commands corresponding to ten static gestures is found to be 100%, and the mean recognition accuracy of the UAV mode-switching commands corresponding to five dynamic gestures is 98.4% indicating that the gesture recognition effect of the system is perfect. Mission testing performed in the scene constructed in the simulation environment demonstrates that the UAV can respond rapidly to gestures, and the method proposed in this article can achieve real-time and stable control of the UAV on the end side.

Exploiting domain transformation and deep learning for hand gesture recognition using a low-cost dataglove

Hand gesture recognition is one of the most widely explored areas under the human–computer interaction domain. Although various modalities of hand gesture recognition have been explored in the last three decades, in recent years, due to the availability of hardware and deep learning algorithms, hand gesture recognition research has attained renewed momentum. In this paper, we evaluate the effectiveness of a low-cost dataglove for classifying hand gestures in the light of deep learning. We have developed a cost-effective dataglove using five flex sensors, an inertial measurement unit, and a powerful microcontroller for onboard processing and wireless connectivity. We have collected data from 25 subjects for 24 static and 16 dynamic American sign language gestures for validating our system. Moreover, we proposed a novel Spatial Projection Image-based technique for dynamic hand gesture recognition. We also explored a parallel-path neural network architecture for handling multimodal data more effectively. Our method produced an F1-score of 82.19% for static gestures and 97.35% for dynamic gestures from a leave-one-out-cross-validation approach. Overall, this study demonstrates the promising performance of a generalized hand gesture recognition technique in hand gesture recognition. The dataset used in this work has been made publicly available.

Designing Flex Sensor Gloves with Temperature Sensor & Pulse Sensor to Help Stroke Patients

Stroke patients often have trouble in daily interactions, when the patient communicated with people who are guarding them. If the distance between the patient and their guard is far, this will make it difficult for the stroke patient to communicate. Therefore, this research designed a prototype glove with a flex sensor installed as a communication tool to aid stroke patients. The designed glove is paired with five flexible sensors to enable nurses easily to read the five-finger movement signals. This tool is also equipped with DS18B20 temperature and pulse sensors capable of monitoring the physical condition of stroke patients in real-time. Testing the flex sensor glove prototype was carried out by measuring temperature & heart rate through pulse and temperature sensors. The output data is in the form of text and sound displayed on the LCD and heard through the speaker through the DFPlayer mini module. The body temperature was measured using the DS18B20 temperature sensor and compared with an Avico digital thermometer which has an average error of 0.1%, indicating adequacy. The heart rate test results through the pulse sensor were compared with measurements obtained using measure heart rate correctly. Instant heart rate, which has an average error of 0.7%, hence, it can

Towards a telehealth infrastructure supported by machine learning on edge/fog for Parkinson's movement screening

Approximately 10 million people worldwide live with Parkinson's disease (PD), a progressive and incurable neurological movement disorder. Symptomatic treatment is available for PD but requires patients to make periodic clinic visits (2–3 times per year) for symptom assessment. Advanced telehealth technologies can enhance clinical care for PD but warrant an Internet-of-Things-based (IoT) infrastructure that can enable symptom monitoring in out-of-clinic settings, such as homes. In this paper, we present an edge and Fog device-based IoT framework and a machine learning-based telehealth infrastructure that can detect and classify hand movement tasks based on a clinical test (UPDRS) for remote symptom assessment. We used a pair of smart gloves integrated with finger flex sensors, an inertial measurement unit (IMU), and a wireless embedded system (i.e., an edge device) to record the hand movements. The edge device (ESP32) detected the activity on the edge node and transmitted the data to the Fog node for classification. The Fog node (Raspberry pi) hosted the Machine Learning (ML) based activity classification models to classify UPDRS-based hand movement tasks. In this paper, we present the development of edge-fog-supported ML infrastructure. To develop ML models, we utilized the data of 9 participants (five healthy and four people with PD) who performed hand movements tasks while wearing the smart gloves. We developed and tested different classification models such as K-nearest neighbors (KNN), Support Vector Machine (SVM), and Decision Tree (DT) to identify which one fits best for such an edge-fog infrastructure for remote symptom assessment. Results showed that the SVM model outperformed others by giving 94% training, 94% testing, and 93% validation accuracy with a mean inference time of 560 μs on the Fog node. Our preliminary results are promising to further our research in deploying the edge-fog-driven ML-based telehealth infrastructure in real-world settings. • Development of Edge-Fog-supported telehealth IoT infrastructure. • Development and assessment of Machine Learning classifiers for hand movement activity classification. • Deployment and evaluation of the ML classification models on the Fog infrastructure. • Demonstration of how an edge-fog computing architecture can be useful for telehealth applications, including movement assessment, symptom tracking, and symptom management.

Hand Gesture based Speech Recognition system for Hard of Hearing People

Abstract: For people who are intellectually challenged, this document provides a sign to speech translator. In contemporary society, the dumb have very little ability to converse with the normal person. Therefore, they are unable to interact with common people until common people, like ourselves, learn how to communicate through sign language. Dumb sign language is not something that everyone can learn because it is so challenging to perfect. Because of this, nobody can go and talk to these physically challenged persons. So, here is a system that would make it possible for those who are illiterate to speak with everyone. With today's technology, even the deaf may communicate by making hand gestures. Each hand gesture is set to play back a different audio message. Hand motions were captured by a flex sensor and an accelerometer, and the microcontroller then accepted these inputs. The flex sensor tracks hand movements and detects deflections, converting them into the right signals that trigger the system to produce recorded sound signals for transmission via the speakers. There are many different Arduino Boards available right now, and they can be used for a variety of things. The Arduino Mega 2560 is the ideal solution since it is the most cost-effective, allows faster computing, and can integrate and interface various sensors while consuming less power. The device under discussion is basically made up of a glove and a microcontroller-based system. Four strategically placed flex sensors are included in the data glove.

Deep reinforcement learning achieves multifunctional morphing airfoil control

Smooth camber morphing aircraft offer increased control authority and improved aerodynamic efficiency. Smart material actuators have become a popular driving force for shape changes, capable of adhering to weight and size constraints and allowing for simplicity in mechanical design. As a step towards creating uncrewed aerial vehicles (UAVs) capable of autonomously responding to flow conditions, this work examines a multifunctional morphing airfoil’s ability to follow commands in various flows. We integrated an airfoil with a morphing trailing edge consisting of an antagonistic pair of macro fiber composites (MFCs), serving as both skin and actuator, and internal piezoelectric flex sensors to form a closed loop composite system. Closed loop feedback control is necessary to accurately follow deflection commands due to the hysteretic behavior of MFCs. Here we used a deep reinforcement learning algorithm, Proximal Policy Optimization, to control the morphing airfoil. Two neural controllers were trained in a simulation developed through time series modeling on long short-term memory recurrent neural networks. The learned controllers were then tested on the composite wing using two state inference methods in still air and in a wind tunnel at various flow speeds. We compared the performance of our neural controllers to one using traditional position-derivative feedback control methods. Our experimental results validate that the autonomous neural controllers were faster and more accurate than traditional methods. This research shows that deep learning methods can overcome common obstacles for achieving sufficient modeling and control when implementing smart composite actuators in an autonomous aerospace environment.

Intelligent System using Flex Sensor for the Assessment of Parkinson's Disease

Parkinson's disease is a progressive nervous system disorder that affects movement which is prevalent in a large number of the world’s population and progressively deteriorates over time. A prognostic system using flex sensors was used to detect tremors in people to assess the severity, progression and chances of regression of the disease. The electronic components used are: an Arduino Nano, five novel flex sensors made of a carbon material known as velostat and a glove onto which the sensors are attached at each finger to record movements and bending. The glove is worn by the patient and every time a tremor is detected; sensors send signals to the Arduino which are converted to bend angles using the change in resistance. The tremor signals are sent in the form of resistances and then converted to voltage. The voltage is then plotted as a function of the bend angle of the flex sensor. A threshold was determined using the sudden and rapid tremors, causing a change in resistance from which the severity and stage of Parkinson’s in the patient can be inferred. This system can be useful for patients who have come out of therapy but still have recurring symptoms.

Sensor evaluation for hand grip strength

<p>This paper discusses the evaluation of the sensors used in the hand grip strength glove. The glove comprises of flex and force resisting sensors. Force resisting sensor determines the force applied by various parts of the palm, while the flex sensor determines the flexion of the fingers. These sensors are placed in a specific position on the glove to obtain correct data when the glove is used. The glove has two modes, which are pencil grip mode and object grip mode. The sensors determine which mode the glove is in depending on the gesture made. The glove is examined using a pencil and a cylindrical object to evaluate the strength of the grip. After gripping the object or pencil, the system evaluates the force applied using the sensors. This data is transferred to a computer for further analysis using a trained model. The model was able to achieve an accuracy of 90.8%.</p>

Twisted and coiled polymer muscle actuated soft 3D printed robotic hand with Peltier cooler for drug delivery in medical management

Many robotic hands have been proposed to have unique designs and capabilities, focusing on sensing, actuation, and control. This paper presents experimental studies on a soft 3D-printed robotic hand whose fingers are actuated by twisted and coiled polymer (TCP<sub>FL</sub>) muscles, driven by resistive heating, and cooled by water and Peltier mechanism (thermoelectric cooling) for increasing the actuation frequency. The hand can be utilized for pick and place applications of drugs in clinical settings, which may be repetitive for humans. A combination of ABS plastic and thermoplastic polyurethane material is used to additively manufacture the robotic hand. The hand along with a housing tank for the muscles and Peltier coolers has a length of 380 mm and weighs 560 gm. The fabrication process of the TCP<sub>FL</sub> actuators coiled with 160 µm diameter nichrome wires is presented. The actuation frequency in the air for TCP<sub>FL </sub>is around 0.01 Hz. This study shows the effect of water and Peltier cooling on improving the actuation frequency of the muscles to 0.056 Hz. Experiments have been performed with a flex sensor integrated at the back of each finger to calculate its bend-extent while being actuated by the TCP<sub>FL</sub> muscles. All these experiments are also used to optimize the TCP<sub>FL</sub> actuation. Overall, a low-cost and lightweight 3D printed robotic hand is presented in this paper, which significantly increases the actuation performance with the help of cooling methods, that can be used in applications in medical management.

Design and Development of a Sign Language to Speech Converter for Dumb People

The Purpose of this work is to develop an interactive device to help dumb people. This is a special electronic device for the mute people which enables them to communicate with normal people by means of customized sign language system. Sign language is the medium for expressing feelings and thoughts using symbols and different patterns made by the bending of fingers. Flex sensor detects the angle of bend of each finger and sends analo signal to the processor. By processing the signal Speech synthesizer makes desired voice output. The device has been more interactive as output quality of voice is quite natural and can be customized as required.

Rancang Bangun AirMouse Menggunakan Sarung Tangan Bersensor Berbasis ESP32

Digital interactions are still commonly using indirect media such as mouse and keyboard to provide user input in the form of two-dimensional data. Therefore, to provide intuition in virtual interactions, it is possible to add media that can draw directly in the air or a flat surface that will track hand movements and overall finger position. In this research, we try to track hand movements in real time by capturing the position of the hand and finger curvature using a wearable sensor equipped with an Inertial Measurement Unit (IMU) sensor and a flex sensor installed by the user. Then the system will identify the position of the user's finger bending. and the location indicated by the sensors installed to move the cursor on the screen and simulate left-click and right-click hand movements as with a traditional mouse. By using this system, users can interact with the computer more naturally and get the accuracy of cursor movement with the accuracy of finger movement translation reaching more than 85% and the translation of hand movements to mouse cursor movements is on average 73% for shapes that use straight lines. and 23.4% on curved lines such as circles and other shapes.

Robotic Hand Wirelessly Controlled by User Worn Glove

A robotic hand was designed to be remotely controlled by a user worn a glove. The glove used flex sensors to detect the position of the user’s fingers and then sent those positions to the corresponding fingers of the robotic hand via microcontrollers. The microcontrollers regulated the servo motors in order to move the robotic hand into a position mimicking the user. The robotic hand was modeled after the human hand but with only one degree of freedom for each finger, meaning the finger will only move from fully extended to fully curled without movement in any other directions. A wrist was attached to the robotic hand and it also moved with one degree of freedom. The robotic hand was completely 3-D printed out of ABS plastic and a tendon-servo system was used to flex the fingers. Elastic cord was used to extend the fingers back into the outstretched position when the servos relaxed the tendons. Several joint types for the hand were modeled and tested including ball and socket joints and revolute joints. Haptic feedback was included in the design by adding vibrational motors to the glove, and pressure sensors to the robotic hand, allowing hand-to-glove feedback. The hand was designed to be able to hold items ranging from the size of a golf ball to a tennis ball, including irregularly shaped objects within the range commonly held by human hands.

Wearable Virtual Keyboard for Visually Impaired Person

Wearable devices are the future of mobile technology, with all the exciting possibilities they offer in terms of ease of usage, compactness, and the ergonomical aspects of such devices. They provide easy accessibility for not only people seeking easier, faster and flexible ways of communicating information between devices, but also individuals with limited mobility, needing disability assistance and with partial or complete blindness. But for the widespread market of upcoming, new-age technology such as wearables, there aren’t a lot of options supporting outputs on peripherals other than a screens. As possible future prospects of wearable technology can be their use in virtual environments - to ease navigation in a simulated reality, in healthcare to provide more efficient and quick input of patient data while diagnosing diseases and prescribing medicines, and so on. In this paper, we discuss the making and workings of a wearable keyboard glove that can be used as a keyboard after being connected to a mobile device, smartwatch, or laptop. The setup consists of gloves that have Bluetooth, Switches, and flex sensors. The device can be used as a keyboard by using a combination of the results from the Flex Sensors that are mounted on the fingers. The device measures the movement of the fingers, records the gesture, and maps a character to each gesture. The gestures are recognized by measuring the change in resistance of the flex sensors and then converting them to an angle through a scaling formula. These values are then divided into three equal parts using a mapping function. This effectively gives us three different positions for each finger to recognize spread into 4 fingers. Switches are also provided for the thumb fingers to detect its position. This provides us with a theoretical total number of gestures of 162. The said gesture is sent via Bluetooth to the paired smart device.