Loading...
8 results
Search Results
Now showing 1 - 8 of 8
- Motion sensors for Knee angle recognition in muscle rehabilitation solutionsPublication . Franco, Tiago; Oliveira, Leonardo Sestrem de; Henriques, Pedro Rangel; Alves, Paulo; Pereira, Maria João; Brandão, Diego; Leitão, Paulo; Silva, AlfredoThe progressive loss of functional capacity due to aging is a serious problem that can compromise human locomotion capacity, requiring the help of an assistant and reducing independence. The NanoStim project aims to develop a system capable of performing treatment with electrostimulation at the patient’s home, reducing the number of consultations. The knee angle is one of the essential attributes in this context, helping understand the patient’s movement during the treatment session. This article presents a wearable system that recognizes the knee angle through IMU sensors. The hardware chosen for the wearables are low cost, including an ESP32 microcontroller and an MPU-6050 sensor. However, this hardware impairs signal accuracy in the multitasking environment expected in rehabilitation treatment. Three optimization filters with algorithmic complexity O(1) were tested to improve the signal’s noise. The complementary filter obtained the best result, presenting an average error of 0.6 degrees and an improvement of 77% in MSE. Furthermore, an interface in the mobile app was developed to respond immediately to the recognized movement. The systems were tested with volunteers in a real environment and could successfully measure the movement performed. In the future, it is planned to use the recognized angle with the electromyography sensor.
- Practical implementation of a hybrid indoor localization systemPublication . Oliveira, Leonardo Sestrem de; Leitão, Paulo; Rayel, Ohara KerusauskasIndoor localization systems occupy a significant role to track objects during their life cycle, e.g., related to retail, logistics and mobile robotics. These positioning systems use several techniques and technologies to estimate the position of each object, and face several requirements such as position accuracy, security, coverage range, energy consumption and cost. This master thesis describes a real-world scenario implementation, based on Bluetooth Low Energy (BLE) beacons, evaluating a Hybrid Indoor Positioning System (H-IPS) that combines two RSSI-based approaches: Multilateration (MLT) and Fingerprinting (FP). The objective is to track a target node, assuming that the object follows a linear motion model. It was employed Kalman Filter (KF) to decrease the positioning errors of the MLT and FP techniques. Furthermore a Track-to-Track Fusion (TTF) is performed on the two KF outputs in order to maximize the performance. The results show that the accuracy of H-IPS overcomes the standalone FP in 21%, while the original MLT is outperformed in 52%. Finally, the proposed solution demonstrated a probability of error < 2 m of 80%, while the same probability for the FP and MLT are 56% and 20%, respectively.
- Data acquisition, conditioning and processing system for a wearable-based biostimulationPublication . Oliveira, Leonardo Sestrem de; Kaizer, Raul; Gonçalves, João; Leitão, Paulo; Teixeira, João Paulo; Lima, José; Franco, Tiago; Carvalho, José AugustoData acquisition by electromyography, as well as the muscle stimulation, has become more accessible with the new developments in the wearable technology and medicine. In fact, for treatments, games or sports, it is possible to find examples of the use of muscle signals to analyse specific aspects related, e.g., to disease, injuries or movement impulses. However, these systems are usually expensive, does not integrate data acquisition with the muscle stimulation and does not exhibit an adaptive control behaviour that consider the pathology and the patient response. This paper presents a wearable system that integrates the signal acquisition and the electrostimulation using dry thin-film titanium-based electrodes. The acquired data is transmitted to a mobile application running on a smartphone by using Bluetooth Low Energy (BLE) technology, where it is analysed by employing artificial intelligence algorithms to provide customised treatments for each patient profile and type of pathology, and taking into consideration the feedback of the acquired electromyography signal. The acquired patient’s data is also stored in a secure cloud database to support the physician to analyse and follow-up the clinical results from the rehabilitation process.
- Titanium based dry electrodes for biostimulation and data acquisitionPublication . Conselheiro, Raul; Lopes, Claudia; Azevedo, Nelson; Leitao, Paulo; Agulhari, Cristiano; Veloso, H.; Vaz, F.; Gonçalves, João Lucas; Franco, Tiago; Oliveira, Leonardo Sestrem deWet electrodes rely on conductive electrolyte gel for proper perfor- mance, usually presenting high setup time and being disposable or requiring time-consuming cleaning methods. Skin irritation and signal quality deterioration are some of the problems that may occur with these electrodes. Therefore, to overcome these drawbacks, 3D printed bases using Fused Deposition Modelling (FDM) with Polylactic acid (PLA), Polyurethane (PU) and Cellulose filaments were functionalized with titanium (Ti) and titanium-nitride (TiN) thin films and dopped with copper (Cu). The electrodes, implemented using different diameters, were used to record electromyography (EMG) signals proceeded by biostimula- tion sessions to access their electrical and mechanical characteristics and com- pare them to that of commercial AgCl/Ag electrodes. The results show that TiN and TiNCu0.45 dry electrodes present results similar to wet AgCl/Ag electrodes for data acquisition. To be comparable to usual carbon electrodes for muscle stimulation, they need some conductivity improvements to lower the necessary voltage. Besides, the endurance of the thin films must be enhanced as well as the adhesion to the polymer.
- myHealth: a mobile App for home muscle rehabilitationPublication . Franco, Tiago; Henriques, Pedro Rangel; Alves, Paulo; Pereira, Maria João; Oliveira, Leonardo Sestrem de; Leitão, Paulo; Silva, AlfredoThe constant loss of functional capacity due to aging can lead to a less active and dignified life, especially if the necessary care is not taken. One of the treatments for muscle rehabilitation is electrostimulation, but it may require two or three visits to the clinic per week. In this paper is proposed a mobile application that serves as a key for minimizing the number of visits to the clinic. The proposed treatment for muscle rehabilitation is through a wearable system that can provide electrostimulation at the patient’s home. The developed application called myHealth will serve as the interface between the patient and the physician. Besides managing the treatment sessions, the app is also in charge of operating the wearable system during the session. Thus, the communication defined between the systems is flexible; some parameter can be adjusted during the session. In this way, algorithms that can improve treatment performance can be implemented in the future. The tests performed showed that the app could successfully execute all the steps of the proposed home treatment scenario. Index Terms—mhealth, electrostimulation, wearable
- Low-cost indoor localization system combining multilateration and Kalman filterPublication . Oliveira, Leonardo Sestrem de; Rayel, Ohara Kerusauskas; Leitão, PauloIndoor localization systems play an important role to track objects during their life-cycle in indoor environments, e.g., related to retail, logistics and mobile robotics. These positioning systems use several techniques and technologies to estimate the position of each object, and face several requirements such as position accuracy, security, range of coverage, energy consumption and cost. This paper describes a practical implementation of a BLE (Bluetooth Low Energy) based localization system that combines multilateration and Kalman filter techniques to achieve a low cost solution, maintaining a good position accuracy. The proposed approach was experimentally tested in an indoor environment, with the achieved results showing a clear low cost system presenting an increase of the estimated position accuracy by 10% for an average error of 2.33 meters
- COVID-19 time series predictionPublication . Oliveira, Leonardo Sestrem de; Gruetzmacher, Sarah; Teixeira, João PauloThe Artificial Neural Network (ANN) is a computer technique that uses a mathematical model to represent a simpler form of the biologic neural structure. It is formed by many processing units and its intelligent behavior comes from the iterations between these units. One application of the ANN is for time series prediction algorithms, where the network learns the behavior of time dependent data and it is able to predict future values. In this work, the ANN is applied in predicting the number of COVID-19 confirmed cases and deaths and also the future seven days for the time series of Brazil, Portugal and the United States. From the simulations it is possible to conclude that the prediction of confirmed cases and deaths from COVID-19 have been successfully made by the ANN. Overall, the ANN with a specific test set had a Mean Squared Error (MSE) 50% higher than the ANN with a random test set. The combination of the sigmoidal and linear activation functions and the Levenberg-Marquardt training function had the lowest MSE for all cases
- Hybrid indoor localization system combining multilateration and fingerprintingPublication . Oliveira, Leonardo Sestrem de; Rayel, Ohara; Leitão, PauloIndoor localization systems enable object tracking, e.g., related to retail, logistics and mobile robotics during their life cycle. This paper describes a real-world scenario implementation, based on Bluetooth Low Energy (BLE) beacons, evaluating a hybrid indoor positioning system (H-IPS) that combines two RSSI-based approaches: Multilateration (MLT) and Fingerprinting (FP). In addition, a Kalman Filter (KF) was employed to decrease the positioning errors of both techniques. Furthermore a track-to-track fusion (TTF) is performed on the two KF outputs to maximize the performance. The results show that the accuracy of H-IPS overcomes the standalone FP in 21%, while the original MLT is outperformed in 52%. Finally, the proposed solution demonstrated a probability of error < 2 m of 80%, while the same probability for the FP and MLT were 56% and 20%, respectively.