Grip pattern is essential to understand how an object being held in hand. One of the solutions is to use the pressure sensing glove to capture the gripping pressure distributed on the surface of the palm. The objective of this project is to develop a data acquisition system for a gripping device that can capture the grip patterns when a person is gripping an object. The design comprises of Velostat sheet, rows, and columns of conductive threads, that are sandwiched and layered to form a glove with pressure sensor grids. Arduino is used to generate the signals for data acquisition and interface with the MATLAB program through serial communication. On the MATLAB, the sensor data are organized and represented in hand pattern color image. Voltage Divider Rule (VDR) was used in an experiment with different resistor values and the effect of the image patterns were observed. Another experiment has been designed to find out the grip consistency. The results show that resistor values 330ohm can cause the image pattern create noises. Meanwhile, 4.7kohm resistance value is sufficient to eliminate most of the noises made in the pattern images. In this paper, different grip images can be obtained from different grip activities, such as holding toothbrush, lifting dumbbell, and pressing syringe. Future works can be done in resolution improvement and grip pattern recognition.
Studies show that heavy machinery operators are exposed to risk factors of musculoskeletal diseases. However, there has yet to be a study investigating the grip analysis of heavy machinery control levers. This preliminary study aims to investigate the grip analysis of a system that emulates the push–pull operations, handle shapes, and resistance of wheel loader control lever systems. The system was designed, analysed, and optimised using Autodesk Inventor 2019 before fabrication and testing. It underwent usability testing for estimated and perceived grip force analysis (ergonomics analysis). The tests measured estimated force using a sensor glove, and perceived force using the Borg CR10 scale. The data were analysed using regression and paired t-tests. The findings suggested that pulling and high resistance factors required higher estimated force (339.50 N) and perceived force (5.625) than pushing and low resistance factors in manoeuvring the system (p < 0.05). The cylindrical handle required more estimated force (339.50 N) but less perceived force (4.5) than the spherical handle due to ergonomic design considerations (p < 0.05). Although there were inaccuracies in force measurement methods, the perceived method was still effective for data collection, since it is challenging to measure grip force in a real situation with heavy machinery. While this study was only a simulation, it provided researchers with ideas that may solve problems in the manipulation of heavy machinery control levers.
Pervasive Wi-Fi deployment has made Wi-Fi an economically convenient wireless platform for developing an Indoor Positioning System (IPS). This paper presents a zone-based IPS developed on Wi-Fi using fingerprinting technique with Probabilistic Neural Network (PNN) and Radial Basis Function Neural Network (RBFNN) to predict target positions. The zone-based IPS is deployed in an indoor environment (a faculty building) with four Wi-Fi modules separately placed. The indoor environment consists of office rooms and laboratories separated by concrete walls. A two-dimensional coordinate system and zone label are deployed to define each location. After that, data collection is performed on each location. The Wi-Fi Received Signal Strength (RSS) for every Wi-Fi module at each location is discovered, labelled with the location coordinate and zone value to form a fingerprint and finally stored in a database. Fingerprints in the database are then separated into training and testing sets for training and testing of PNN and RBFNN. The testing result shows that the mean positioning error for coordinate prediction of PNN and RBFNN is 3.84m and 6.91m, respectively. Although RBFNN has a large mean positioning error, RBFNN presented a zone positioning accuracy of 78.7%, which is close to the 82.2% accuracy presented by PNN.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.