Understanding human mobility is essential for the development of smart cities and social behavior research. Human mobility models may be used in numerous applications, including pandemic control, urban planning, and traffic management. The existing models' accuracy in predicting users' mobility patterns is less than 25%. The low accuracy may be justified by the flexible nature of the human movement. Indeed, humans are not rigid in their daily movement. In addition, the rigid mobility models may result in missing the hidden regularities in users' records. Thus, we propose a novel perspective to study and analyze human mobility patterns and capture their flexibility. Typically, the mobility patterns are represented by a sequence of locations. We propose to define the mobility patterns by abstracting these locations into a set of places. Labeling these locations will allow us to detect close-to-reality hidden patterns. We present IMAP, an Individual huMAn mobility Patterns visualizing platform. Our platform enables users to visualize a graph of the places they visited based on their history records. In addition, our platform displays the most frequent mobility patterns computed using a modified PrefixSpan approach.

A Thai customer receiving food served by a homemade robotic automated guided vehicle called UBOT-01 at a diner in Hang Dong, Chiang Mai province, northern Thailand yesterday. The owner of an eatery in Thailand built an automated guided vehicle robot to work as a waiter serving food to customers, mainly aimed at saving hiring costs and attracting customers. The diner's UBOT-01 is a portable robot that operates by following a guided magnetic tape marked on the floor for navigation with safety sensors to detect obstacles.

Diners wait at their table at Sri Trat Thai restaurant in Sukhumvit Soi 33. Seatris, web-based restaurant management software from Germany, is introducing its machine learning technology in Thailand as part of the company's business expansion efforts in Asean market. The company's machine learning technology has been applied to what they call "smart table", which includes online booking and an automatic waitlist system. The technology is touted to boost efficiency for restaurants. Seatris has now opened its doors to fine and casual dining restaurants as well as hotels in Bangkok, Singapore, Hong Kong, Indonesia and Vietnam.

One of the biggest challenges in the development and deployment of spoken dialogue systems is the design of the spoken language generation module. This challenge arises from the need for the generator to adapt to many features of the dialogue domain, user population, and dialogue context. A promising approach is trainable generation, which uses general-purpose linguistic knowledge that is automatically adapted to the features of interest, such as the application domain, individual user, or user group. In this paper we present and evaluate a trainable sentence planner for providing restaurant information in the MATCH dialogue system. We show that trainable sentence planning can produce complex information presentations whose quality is comparable to the output of a template-based generator tuned to this domain. We also show that our method easily supports adapting the sentence planner to individuals, and that the individualized sentence planners generally perform better than models trained and tested on a population of individuals. Previous work has documented and utilized individual preferences for content selection, but to our knowledge, these results provide the first demonstration of individual preferences for sentence planning operations, affecting the content order, discourse structure and sentence structure of system responses. Finally, we evaluate the contribution of different feature sets, and show that, in our application, n-gram features often do as well as features based on higher-level linguistic representations.