| Summary: | 博士 === 國立臺灣科技大學 === 資訊工程系 === 101 === As information technologies advance and user-friendly interfaces develop, the interaction between humans and computers, information devices, and new consumer electronics is increasingly gaining attention. One example that most people can relate to is Apple’s innovation in HCI (Human-Computer Interface) which has been used on many products such as iPad and iPhone. Siri, the intelligent personal assistant, is a typical application of machine-learning Human-Computer Interface.
Algorithms in machine learning have been employed in many disciplines, including gesture recognition, speaker recognition, and product recommendation systems. While the existing learning algorithms compute and learn from a large quantity of data. In this study, in addition to ranking data through multiple stages, algorithm significantly improves the existing algorithms in two ways. Firstly, it considers the cost-sensitive issue in the ranking algorithm. It classifies and filters data to small quantities and applies the Boosting algorithm to achieve faster ranking performance. Secondly, it enhances the original binary classification by using the concordant and discordant. Results from experiments demonstrate that our proposed algorithm outperforms the conventional methods in three evaluation measures: P@n, MAP, and NDCG. We have also proved in applications in three different areas.
The proposed method was applied to three areas. The experimental results of hand gesture recognition reveal that the efficiency of system execution turns out to be satisfying and the suggested method is desired for application in hand gesture recognition. As for the outcome of average accuracy rate of gesture recognition is more than 98%, a rate of satisfactory. We do not deal the technology improvement with the DSP (Digital Signal Processing). We only process the voice signal converted to the native voice eigenvalue which used to voice recognize. The experiments of the speech recognition show that the recognition optimization procedures established by this study are able to increase the recognition rate to over 96% in the personal computing device and industrial personal computer. It is expected that in the future this voice management system will accurately and effectively identify speakers answering the voice response questionnaire and will successfully carry out the functions in the choice of answers, paying the way for the formation of a virtual customer service person. Finally, we use the Web as the Human-Computer Interface to implement and manage the orders delivered by proposed method. The proposed method in the VMI (Vendor Managed Inventory) system framework achieves an order fulfillment rate 99%, up from the previous 94.75%, or an increase of 4.25% in our experiment result on connector industry. The system is also expected to improve the production efficiency and global competitiveness of the said connector maker.
|
|---|
