In recent years, Human-Computer Interaction (HCI) has become a significant part of modern life as it has improved human performance in the completion of daily tasks in using computerised systems. The increase in the variety of bio-sensing and wearable technologies on the market has propelled designers towards designing more efficient, effective and fully natural User-Interfaces (UI), such as the Brain-Computer Interface (BCI) and the Muscle-Computer Interface (MCI). BCI and MCI have been used for various purposes, such as controlling wheelchairs, piloting drones, providing alphanumeric inputs into a system and improving sports performance. Various challenges are experienced by workers in a warehouse environment. Because they often have to carry objects (referred to as hands-full) it is difficult to interact with traditional devices. Noise undeniably exists in some industrial environments and it is known as a major factor that causes communication problems. This has reduced the popularity of using verbal interfaces with computer applications, such as Warehouse Management Systems. Another factor that effects the performance of workers are action slips caused by a lack of concentration during, for example, routine picking activities. This can have a negative impact on job performance and allow a worker to incorrectly execute a task in a warehouse environment. This research project investigated the current challenges workers experience in a warehouse environment and the technologies utilised in this environment. The latest automation and identification systems and technologies are identified and discussed, specifically the technologies which have addressed known problems. Sensory technologies were identified that enable interaction between a human and a computerised warehouse environment. Biological and natural behaviours of humans which are applicable in the interaction with a computerised environment were described and discussed. The interactive behaviours included the visionary, auditory, speech production and physiological movement where other natural human behaviours such paying attention, action slips and the action of counting items were investigated. A number of modern sensory technologies, devices and techniques for HCI were identified with the aim of selecting and evaluating an appropriate sensory technology for MCI. iii MCI technologies enable a computer system to recognise hand and other gestures of a user, creating means of direct interaction between a user and a computer as they are able to detect specific features extracted from a specific biological or physiological activity. Thereafter, Machine Learning (ML) is applied in order to train a computer system to detect these features and convert them to a computer interface. An application of biomedical signals (bio-signals) in HCI using a MYO Armband for MCI is presented. An MCI prototype (MCIp) was developed and implemented to allow a user to provide input to an HCI, in a hands-free and hands-full situation. The MCIp was designed and developed to recognise the hand-finger gestures of a person when both hands are free or when holding an object, such a cardboard box. The MCIp applies an Artificial Neural Network (ANN) to classify features extracted from the surface Electromyography signals acquired by the MYO Armband around the forearm muscle. The MCIp provided the results of data classification for gesture recognition to an accuracy level of 34.87% with a hands-free situation. This was done by employing the ANN. The MCIp, furthermore, enabled users to provide numeric inputs to the MCIp system hands-full with an accuracy of 59.7% after a training session for each gesture of only 10 seconds. The results were obtained using eight participants. Similar experimentation with the MYO Armband has not been found to be reported in any literature at submission of this document. Based on this novel experimentation, the main contribution of this research study is a suggestion that the application of a MYO Armband, as a commercially available muscle-sensing device on the market, has the potential as an MCI to recognise the finger gestures hands-free and hands-full. An accurate MCI can increase the efficiency and effectiveness of an HCI tool when it is applied to different applications in a warehouse where noise and hands-full activities pose a challenge. Future work to improve its accuracy is proposed.
Identifer | oai:union.ndltd.org:netd.ac.za/oai:union.ndltd.org:nmmu/vital:27160 |
Date | January 2016 |
Creators | Zadeh, Seyed Amirsaleh Saleh, Greyling, Jean |
Publisher | Nelson Mandela Metropolitan University, Faculty of Business and Economic Sciences |
Source Sets | South African National ETD Portal |
Language | English |
Detected Language | English |
Type | Thesis, Masters, MCom |
Format | xviii, 225 leaves, pdf |
Rights | Nelson Mandela Metropolitan University |
Page generated in 0.0019 seconds