Usability and affective issues of using automatic speech recognition technology to interact with an automated teller machine (ATM) are investigated in two experiments. The first uncovered dialogue patterns of ATM users for the purpose of designing the user interface for a simulated speech ATM system. Applying the Wizard-of-Oz methodology, multiple mapping and word spotting techniques, the speech driven ATM accommodates bilingual users of Bahasa Melayu and English. The second experiment evaluates the usability of a hybrid speech ATM, comparing it with a simulated manual ATM. The aim is to investigate how natural and fun can talking to a speech ATM be for these first-time users. Subjects performed the withdrawal and balance enquiry tasks. The ANOVA was performed on the usability and affective data. The results showed significant differences between systems in the ability to complete the tasks as well as in transaction errors. Performance was measured on the time taken by subjects to complete the task and the number of speech recognition errors that occurred. On the basis of user emotions, it can be said that the hybrid speech system enabled pleasurable interaction. Despite the limitations of speech recognition technology, users are set to talk to the ATM when it becomes available for public use.
Matched MeSH terms: Human Engineering/instrumentation
Traffic police riders are exposed to prolonged static postures causing significant angular deviation of the musculoskeletal, including the lumbar angle (L1-L5). This postural alteration contributes to awkward posture, musculoskeletal disorders and spinal injury, especially in the lower back area, as it is one of the most severe modern diseases nowadays. Thus, the study aimed to evaluate the effect of lumbar support with a built-in massager system on spinal angle profiles among traffic police riders. A randomised controlled trial (pre-testpost-test control design) was used to assess spinal angle pattern while riding the high-powered motorcycle for 20 minutes. Twenty-four traffic police riders were randomly selected to participate and 12 riders were assigned to the control group and 12 riders to the experimental group. The pre-test and post-test were conducted at a one-week interval. Each participant was required to wear a TruPosture Smart Shirt (to monitor spinal posture). The TruPosture Apps recorded the spinal angle pattern. The data indicated that the police riders using motorcycle seat with lumbar support and built-in massager system showed a huge improvement in maintaining posture which only involves slight spinal angle deviation changes from the spinal reference angle throughout the 20 minutes ride. The data collected then were analysed using the Mann-Whitney test and Wilcoxon signed-ranked test to verify a statistically significant difference between and within the control and experimental groups. There were significant differences in all sensors between the control group and experimental groups (p<0.05) and within the experimental group. According to the findings, it can be said that the ergonomic intervention prototype (lumbar support with built-in massager system) successfully helps to maintain and improve the natural curve of the spinal posture. This indirectly would reduce the risk of developing musculoskeletal disorders and spinal injury among traffic police riders.
Matched MeSH terms: Human Engineering/instrumentation*