Mohamad Hafis Izran Ishak

A conceptual model of the automated credibility assessment of the volunteered geographic information

The use of Volunteered Geographic Information (VGI) in collecting, sharing and disseminating geospatially referenced information on the Web is increasingly common. The potentials of this localized and collective information have been seen to complement the maintenance process of authoritative mapping data sources and in realizing the development of Digital Earth. The main barrier to the use of this data in supporting this bottom up approach is the credibility (trust), completeness, accuracy, and quality of both the data input and outputs generated. The only feasible approach to assess these data is by relying on an automated process. This paper describes a conceptual model of indicators (parameters) and practical approaches to automated assess the credibility of information contributed through the VGI including map mashups, Geo Web and crowd – sourced based applications. There are two main components proposed to be assessed in the conceptual model – metadata and data. The metadata component comprises the indicator of the hosting (websites) and the sources of data / information. The data component comprises the indicators to assess absolute and relative data positioning, attribute, thematic, temporal and geometric correctness and consistency. This paper suggests approaches to assess the components. To assess the metadata component, automated text categorization using supervised machine learning is proposed. To assess the correctness and consistency in the data component, we suggest a matching validation approach using the current emerging technologies from Linked Data infrastructures and using third party reviews validation. This study contributes to the research domain that focuses on the credibility, trust and quality issues of data contributed by web citizen providers.

Engaging indigenous people as geo-crowdsourcing sensors for ecotourism mapping via mobile data collection: a case study of the Royal Belum State Park

ABSTRACT Web 2.0 and the proliferation of built-in Global Positioning System (GPS) on smartphones have influenced the increase of geo-crowdsourcing activities in a number of different contexts. The aim of this paper is to evaluate the performance of indigenous people’s use of mobile collection applications that are embedded in a smartphone to facilitate ecotourism asset mapping. In order to achieve this, field usability testing was conducted where structured observational method was used to assess the performance. The findings indicate majority of them can complete the data entry tasks using mobile data collection. The performance of data entries using radio button, icons, camera and audio methods were identified as better than free text and drop-down list methods. There was a correlation between the level of education with the ability of using radio button, drop-down list and image icon as data entry methods. The paper also discusses the extent of local knowledge relating to ecotourism within the community. The findings should be useful in the understanding of the design of mobile geo-crowdsourcing tools for use within other contexts that focus on data collection by semiliterate and indigenous groups.

Fuzzy Logic System in Quantifying Human Driving Skill for Human Adaptive Mechatronics

Human Adaptive Mechatronic (HAM) is an enhance system for Human Machine System (HMS). Instead of one-way relationship between human and machine, HAM system provides two-way relationship between human and machine in order to assist human and to improve human skills in operating the machine. Driving a car is an example of applications where HAM system can be applied. One of the problems of HAM is to quantify the human skill for operating the machine. Therefore, this paper proposed a method to quantify human driving skill using Fuzzy Logic System (FLS). In order to get the best design of FLS for quantifying human driving skill, twelve designs of FLS were designed and tested using computer simulation software. The best design from all twelve designs is then been compared with other method of quantifying human skill for verification. Results show that the design of membership functions for input and output have big impact to the accuracy of the output.

Racer: A Simulated Environment Driving Simulator to Investigate Human Driving Skill

The identification and the quantification of human skill is one of the major characteristics to be considered in designing an algorithm for Human Adaptive Mechatronics (HAM) application. This paper focuses on studying the Racer software, as well as the relationship of data gained and the simulated environment. The fact that Racer is chosen as the tool is described. This paper discusses the details about the software used; Racer as the driving simulator environment during the experiment. The experimental setup, data extraction process and data conversion are explained further in this paper. The experimental results meet the purpose of data collection which provides variety set of data, including many options for cars and tracks. As a conclusion, Racer is a suitable software to be used. The utmost important, the further study of this research will help during the development of car assistance system.

Comparisons of skill index algorithm in driving for human adaptive mechatronics

Currently, Human Machine System (HMS) considers being a proven technology, which has gained an important role in various human activities. One of the most recent developments in this area is Human Adaptive Mechatronics (HAM) approach for enhancing human skills. This approach therefore is different compared to an ordinary HMS, in terms of its ability to adapt to the changes in its environment and in the human changing level of skills. The crucial issue in HAM is in evaluating the human skills level on machine operation. Therefore, this paper discussed about the comparisons between the proposed formula to quantify and classify the skill index of human operator with the Fuzzy Logic and other formula. An experiment using a driving car simulator is carried out to clarify those formulas in machine manipulation system. From the comparison it is found that the proposed formulas give better result compared to Fuzzy Logic System and other formula.