This work explored the requirements of accurately and reliably predicting user intention using a deep learning methodology when performing fine-grained movements of the human hand. The focus was on combining a feature engineering process with the effective capability of deep learning to further identify salient characteristics from a biological input signal. 3 time domain features (root mean square, waveform length, and slope sign changes) were extracted from the surface electromyography (sEMG) signal of 17 hand and wrist movements performed by 40 subjects. The feature data was mapped to 6 sensor bend resistance readings from a CyberGlove II system, representing the associated hand kinematic data. These sensors were located at specific joints of interest on the human hand (the thumb's metacarpophalangeal joint, the proximal interphalangeal joint of each finger, and the radiocarpal joint of the wrist). All datasets were taken from database 2 of the NinaPro online database repository. A 3-layer long short-term memory model with dropout was developed to predict the 6 glove sensor readings using a corresponding sEMG feature vector as input. Initial results from trials using test data from the 40 subjects produce an average mean squared error of 0.176. This indicates a viable pathway to follow for this prediction method of hand movement data, although further work is needed to optimize the model and to analyze the data with a more detailed set of metrics.
Industry 4.0, also termed smart manufacturing, has revolutionized the industrial world with cutting-edge technologies such as collaborative robots and artificial intelligence etc. Productivity and efficiency are two key factors that determine the success level of manufacturing. Therefore, many manufacturers have become so eager to adopt adaptive, intuitive, collaborative and smart techniques to improve the production lines, including key manufacturing machines and equipment. Therefore, robotic systems are playing an increasingly vital role in many industrial sectors, as they decrease the need for human labour and increase automation level. In addition, material waste can be also reduced since robots provide stability and accuracy during work. In turn, production times are reduced as well. Consequently, smart manufacturing areas need more advanced, flexible, and smart robotic systems to respond to market size changes and customization processes. As a result, currently, great research efforts are made to enrich the interactions between humans and robots in the work environment. This paper presents an overview of Human-Robot Collaboration (HRC) systems being employed in smart manufacturing to exploit the benefits of human experience and the capabilities of robotic systems. The research gaps, challenges and future work directions on HRC are highlighted and analyzed towards smart manufacturing.
Artificial intelligence (AI) has received significant attention nearly from every part of the world because it is a critical technology approach to develop intelligent systems. The manufacturing sector is one part which exploits AI, especially in the product design stage towards smart manufacturing. The aim of this paper is to present an overview on how AI enhances the product design stage for smart manufacturing. First, the paper gives the overall understanding of smart manufacturing about its definition, importance, and characteristics. Then, it delivers a brief overview of product design and product design stages. The essential concepts of AI techniques as well as various AI applications in product design ranging from conceptual design, embodiment design and detail design are discussed. Finally, research challenges and future directions for using AI in product design are provided and discussed.
A cost-effective and accurate method to add or change sensors in an automated manufacturing line is essential in order to increase the flexibility and adaptability of production systems. In particular, small to medium enterprises (SMEs) and companies offering custom solutions can only compete in the highly interconnected age of Industry 4.0 if their operations are agile and dynamic. This paper presents a new, low-cost solution to this problem through the development of a Smart Sensor Box. The paper introduces the benefits of this highly adaptable system comparing it to currently available solutions, while testing conducted demonstrates the solution’s accuracy and repeatability. The layout and operational capabilities for three versions of the Smart Sensor Box are discussed in detail and example applications are presented.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.