Design and Implementation of a Chatbot for Kurdish Language Speakers Using Chatfuel Platform

Chatbot is a software agent that is used to conduct intelligent conversations between machines and humans. Chatbots are mostly depend on Natural Language Processing (NLP). In this paper, the design and implementation of a chatbot are provided to help Kurdish speakers in using online conversations via texts to find answers instead of direct contact with human agents. The NLP-based software agent is implemented using the Chatfuel platform. Chatfuel uses artificial intelligence to communicate with humans by simulating human conversations through voice commands or texts. The proposed chatbot is tested on an electronic tourist guide that helps visitors to the religious places in the mountainous village of Barzanja that is located in Iraqi Kurdistan. The case study is conducted by using three-hundred questions and answers. One hundred volunteers participated in this study. The participant asks a question and the bot provides an answer if it recognizes the question, otherwise it provides a default answer along with a suggestion of how to use the system properly. The data of these experiment is collected, analyzed, and problems regarding Kurdish language are detected. Designing software agents for processing Kurdish texts faces many challenges. Kurdish texts have not yet been processed using natural language processing (NLP). In addition, Kurdish font disorder and the lack of standardized keyboards and writing styles makes processing Kurdish text difficult. Furthermore, Kurdish language consists of variety of different dialects with different typing styles. In this research, we specifically focus on the design of a software agent for the Central Kurdish (Sorani) dialect. We managed to solve some of the problems related to the Kurdish language and suggest solutions to others.

Optimizing Personalized Touristic Itineraries by a Multiobjective Evolutionary Algorithm

The paper presents an electronic tourist guide, relying on an evolutionary optimizer, able to plan personalized multiple-day itineraries by considering several contrasting objectives. Since the itinerary planning can be modeled as an extension of the NP-complete team orienteering problem with time windows, a multiobjective evolutionary optimizer is proposed to find in reasonable times near-optimal solutions to such an extension. This optimizer automatically designs the itinerary by aiming at maximizing the tourists’ satisfaction as a function of their personal preferences and environmental constraints, such as operating hours, visiting times and accessibility of the points of interests, and weather forecasting. Experimental evaluations have demonstrated that the proposed optimizer is effective in different simulated operating conditions.

Utilizing Cloud Computing in Developing a Mobile Location-Aware Tourist Guide System

Cloud Computing technologies support mobile applications and overcome the low computation resources and limited data storage by providing an on-demand access with pay-as-use rule to large number of computing resources. In this paper, the author describes the architecture of an electronic tourist guide system (Trip@Cloud) as mobile cloud computing application wherein the tourists can access cloudy information in ubiquitous and pervasive manner. The information needs not to be over the user's mobile device, but it will be downloaded to user's device according to user's location and the Internet status connection. The interaction between the mobile device and the cloud is done when possible and transparently from the user. The existing architectures of partitioning the application between the device and the cloud depends deeply on the CPU workloads. The author’s application's nature is different from these applications and this represents the main contribution. The idea is to download the data to the user's device according to the current user location. Therefore the partitioning is done for the data to be sent to the mobile device. This idea is applied by developing a tourist guide application where the data to be installed is very huge and the mobile storage device is very limited.

Research on Key Techniques of ETG System

By analyzing the features of ETG (Electronic Tourist Guide) system, this paper discussed the key technologies about its implementation: Map matching, attractions positioning and guide, route planning. We focus on solving map matching problem based on interpolation method and weight-based map matching algorithm, then we propose an attractions positioning and guide process; and also working on the route planning problem through an improved Ant colony algorithm.