To reduce the cost to develop service robot applications, we have been developing PRINTEPS, an AI and service robot application development platform for end users. PRINTEPS provides a scenario editor to describe the workflows for robots' actions and human-robot interactions. The scenario editor enables the developer to create workflows while reusing the entire workflows or individual operation processes; however, since end users such as domain experts usually do not know functions and properties of robots, it is difficult to identify and modify the reusable parts to suit the purposes of reuse when reusing the entire workflows. In contrast, it is also difficult to work out different combinations of operation processes when reusing the individual operation processes. To solve these issues, this study proposes a teaching assistant (TA) robot design tool based on knowledge chunks reuse. Two public elementary school teachers created workflows for TA robots using the proposed tool, and each teacher conducted a lesson with TA robots once. Through questionnaires given to the teachers and pupils, the proposed tool and TA robots were evaluated to confirm their usefulness.

To develop service robot applications, it is necessary to acquire domain expert knowledge and develop the applications based on the knowledge. However, since, currently, many of these applications have been developed by engineers using the middleware for robots, the domain expert knowledge is embedded in the codes and is difficult to reuse. Therefore, it is considered necessary to have a tool that supports the development of the applications based on machine-readable knowledge of domain experts. We also believe that the machine-readable knowledge can be reused not only for service robots but also for novices in the domain. To address the problems, this paper proposes a knowledge chunk (KC) reuse support tool based on heterogeneous ontologies. In this study, the parts of the reusable workflow, indexes required for a search, and a movie recording of robots movement based on the parts of the workflow are collectively known as a KC. Using the framework of case-based reasoning, the proposed tool accumulates parts of reusable workflows as case examples based on heterogeneous ontologies and facilitates search and reuse of KCs. It promotes domain expert knowledge acquisition and supports novices to learn the knowledge. As a case study, we have applied the proposed tool to teaching assistant (TA) robots. Two public elementary school teachers created workflows for TA robots using the proposed tool, and each teacher conducted a lesson with TA robots once. Through questionnaires given to the teacher, the proposed tool and TA robot application were evaluated to confirm their usefulness.

Recently, robots have become increasingly familiar to humans as more and more service robots have been applied for use in various fields. The market for robots is expected to further expand in the next few decades, increasing the level of their involvement with humans. Based on this assumption, we have studied robots working cooperatively with humans at cafes, or classes that are conjointly conducted by a teacher and a robot. In contrast, in the current elementary school education system, there are increasing demands for not only transferring knowledge unilaterally from a teacher to pupils, but also inducing pupil’s voluntary commitment to learning while maintaining their motivation. This has led to various experiments being conducted at educational sites. However, research that has been conducted so far on support for teachers has targeted robots that work only as a supporter of the teachers, making it insufficient to achieve these educational goals. In this study, based on the goals described above, we introduced robots to class discussion sessions with small groups and constructed a “discussion support robot” to facilitate discussion among children. Here, the robots played two roles as a discussion participant and as a discussion facilitator to not only assist teachers to proceed with a discussion among children. Moreover, a discussion session was conducted in an actual elementary school using this system as a case study and evaluations made by the pupils and teachers were reviewed.

In recent years, Knowledge Transfer is one of the problems of business management. Companies are required to create a mechanism to transfer knowledge of experts to the next generation. Submitting work reports is one of examples of efforts to convert tacit knowledge to explicit knowledge. There are many companies letting their employees submit work reports after completion of their work. However, most of data is just accumulated, but it is not fully reused. Factors obstructing utilization of work report data are below; First, data of work reports is enormous and there are scattered descriptions concerning important business knowledge so that it is impossible to acquire business knowledge by reading work reports efficiently. Second, since work reports are plaintext, their structure cannot be seen so it is impossible to access the necessary information immediately. Therefore, in this research, we constructed a system that supports knowledge transfer by utilizing work report data. Specifically, we constructed domain ontologies that define the meaning of terms related to business knowledge and performed information extraction on work reports by using the domain ontology and sentence pattern matching. Then, based on the result of information extraction, a set of texts including business knowledge was selected. Finally, we constructed a system that provides business knowledge to users by using work report data as a knowledge source.

In order to develop services utilizing robots, various AI element technologies and multiple robots and sensors must be integrated. However, at present, it takes a lot of cost to develop such integrated intelligent applications. Currently, we have been developing PRactical INTEligent aPplicationS (PRINTEPS), which is a user-centric platform to develop integrated intelligent applications only by combining five types of modules such as knowledge-based reasoning, speech dialogue, image sensing, motion management, and machine learning. In this paper, we report on a multi-robot teahouse at a university campus festival as a practical application of PRINTEPS. We also report the evaluation of the robot teahouse from the viewpoint of the service quality based on the questionnaires of the customers who experienced the robot teahouse.

Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.

While AI applications are very popular in many domains, they should be harmonious with domain exerts and end users. Furthermore, in order to develop such harmonious AI applications, we need agile AI platforms for not only developers but domain experts. Currently, we have developed Practical Intelligent applications (PRINTEPS), which is a user-centric platform to develop integrated intelligent applications. This paper evaluates the service quality of a multi-robot cafe at a campus festival and reports on the cafe as a practical application of PRINTEPS. It is not clear if robot services are perceived as attractive and/or valuable, and how the concept of robot services could lead to customer satisfaction. Therefore, the evaluation of the quality of such services is necessary to identify the key factors that could contribute to improving customer satisfaction. The objective of this study is to contribute to the realization of practical and economically feasible robot services by obtaining effective knowledge for improving customer satisfaction. This will be achieved through the evaluation of the service quality of the multi-robot cafe.

PRINTEPS is currently being developed as a total intelligent application, which has sub systems for knowledge-based reasoning, speech dialogue, image sensing, motion planning, and machine learning, in order to support end users on easily developing intelligent applications for human-machine collaboration. In this paper, a lesson application for collaborative teaching among a robot, laptop PC, sensor, teachers and students was developed with PRINTEPS. The implementation lesson was performed in a science class for six grade elementary students.

We are developing PRactical INTEligent aPplicationS (PRINTEPS), which is a user-centric platform to develop integrated intelligent applications only by combining four types of modules such as knowledge-based reasoning, speech dialog, image sensing and motion management. PRINTEPS supports end users to participate in AI applications design (user participation design) and to develop applications easily. This paper introduces the architecture and applications of PRINTEPS for robot teahouse robot where multiple people and robots cooperate.

PRINTEPS is currently being developed as a total intelligent application, which has sub systems for knowledge-based reasoning, speech dialogue, image sensing, motion planning, and machine learning, in order to support end users on easily developing intelligent applications for human-machine collaboration. In this paper, a lesson application for collaborative teaching among a robot, laptop PC, sensor, teachers and students was developed with PRINTEPS. The implementation lesson was performed in a science class for six grade elementary students.

We are developing PRactical INTEligent aPplicationS (PRINTEPS), which is a user-centric platform to develop integrated intelligent applications only by combining four types of modules such as knowledge-based reasoning, speech dialog, image sensing and motion management. PRINTEPS supports end users to participate in AI applications design (user participation design) and to develop applications easily. This paper introduces the architecture and applications of PRINTEPS for robot teahouse robot where multiple people and robots cooperate.

Recently, smart glasses have been applied in field work, with which a worker goes well during work by contacting a support operator from a remote location. The worker, however, cannot go well if the support operator is not there. To solve the issues, the paper discusses how a work system should be developed by integrating smart glasses with a question-answering module. We design the work knowledge acquired from skilled people and manuals as a work flow, rule base, goal tree, domain ontologies and RDF data. Workers follow work process by referring to the work flow, referring to multimedia, and receiving answers from the question-answering module incorporated with a knowledge base for questions that are raised during the work. The authors conducted a demonstration experiment and found that workers could perform the work more autonomously by importing the system.

Recently, the use of service robots has increased considerably and their social contribution is expected. It is desirable that a robot, as a provider of operational information, can answer questions in both the open domain and intended operations, to respond to questions in a manner that satisfies users. This paper proposes a question answering system that can respond to questions in both intended operations and open domain by linking an ontology, which is semi-automatically built from Wikipedia (Wikipedia-based ontology), with a domain ontology.

Analyzing big data with fixed scheme, the analysis does not become sometimes enough with less data. We should have more data with scheme free including picture, movies, map, news and social media and then integrate them in order to get the analysis more effective. Here is discussed how to integrate various kinds of heterogeneous data to do so. Taking case studies to support road reconstruction planning, we integrate six kinds of domestic data: traffic accident data, road traffic census data, street view with G-map, YouTube, Twitter, and News. In addition, we discuss usefulness of integration and reference of various kinds of data.

Traffic behavior surveys by hand require both a lot of money and human resources. Recently, traffic behavior surveys using information technology have been carried out. In this study, we propose a method to extract staying points from GPS-based positional data and identify the types of staying facilities by using Google Places API, a facility ontology, the regularity which is analyzed from trip chains about traffic behavior. This method could identify 68.5% types of staying facilities correctly in the evaluation using GPS location data from the Traffic Behavior Survey in Nagasaki.

Previously, we constructed the Japanese Wikipedia Ontology (JWO) via a semi-automatic process using the Japanese Wikipedia, but it had problems due to a lack of upper classes and appropriate definitions of properties. Thus, the aim of the current stu

Japanese Wikipedia Ontology, which we have constructed semi-automatically from Japanese Wikipedia, has problems of lacking upper classes and appropriate definition of properties. The purpose of our research is to complement the upper classes in Japanese Wikipedia Ontology and build up a class hierarchy with properties by integrating Japanese Wikipedia Ontology and Japanese Word Net. In this paper, we propose a method to build up the class hierarchy with properties by lifting up common properties that are defined in sibling classes to more upper classes in Japanese Wikipedia Ontology. We also introduce an attempt to integrate Japanese Wikipedia Ontology and Japanese Word Net.

WioNA (Wikipedia Ontology NAo) is proposed to build much better HRI by integrating four elements: Japanese speech interface, semantic interpretation, Japanese Wikipedia Ontology and Robot Action Ontology. WioNA is implemented on a humanoid robot "Nao". In WioNA, we developed two ontologies: Japanese Wikipedia Ontology and Robot Action Ontology. Japanese Wikipedia Ontology has a large size of concept hierarchy and instance network with many properties from Japanese Wikipedia (semi) automatically. By giving Japanese Wikipedia Ontology to Nao as wisdom, Nao can dialogue with users on many topics of various fields. Robot Action Ontology, in contrast, is built by organizing various performable actions of Nao to control and generate robot actions. Aligning Robot Action Ontology with Japanese Wikipedia Ontology enables Nao to perform related actions to dialogue topics. To show the validities of WioNA, we describe human-robot conversation logs of two case studies whose dialogue topics are sport and rock singer. These case studies show us how HRI goes well in WioNA with these topics.

Here is discussed how to learn a large scale of ontology from Japanese Wikipedia. The learned ontology includes the following properties: rdfs:subClassOf (IS-A relationships), rdf:type (class-instance relationships), owl:Object/DatatypeProperty (Infobox triples), rdfs:domain (property domains), and skos:altLabel (synonyms). Experimental case studies show us that the learned Japanese Wikipedia Ontology goes better than already existing general linguistic ontologies, such as EDR and Japanese WordNet, from the points of building costs and structure information richness.

Our approach aims to provide a mechanism for recommending long tail items to knowledge workers. The approach employs collaborative filtering using browsing features of identified key population of the diffusion of information. We conducted analytic experiment for a novel recommendation algorithm based on the browsing features of identified selected users and discovered that the first 10 users accessing a particular page play the key role in information spread. The evaluation indicated that our approach is effective for long tail recommendation.

In this paper, we present an evaluation of learning algo- rithms of a novel rule evaluation support method for post- processing of mined results with rule evaluation models based on objective indices. Post-processing of mined results is one of the key processes in a data mining process. How- ever, it is difficult for human experts to completely evaluate several thousands of rules from a large dataset with noises. To reduce the costs in such rule evaluation task, we have de- veloped the rule evaluation support method with rule evalu- ation models, which learn from objective indices for mined classification rules and evaluations by a human expert for each rule. To enhance adaptability of rule evaluation mod- els, we introduced a constructive meta-learning system to choose proper learning algorithms. Then, we have done the case study on the meningitis data mining as an actual prob- lem.

In this paper, we present a novel rule evaluation support method for post-processing of mined results with rule evaluation models based on objective indices. Post-processing of mined results is one of the key issues to make a data mining process successfully. However, it is difficult for human experts to evaluate many thousands of rules from a large dataset with noises completely. To reduce the costs of rule evaluation procedures, we have developed the rule evaluation support method with rule evaluation models, which are obtained with objective indices of mined classification rules and evaluations of a human expert for each rule. To evaluate performances of learning algorithms for constructing rule evaluation models, we have done a case study on the meningitis data mining as an actual problem. Then we discuss the availability of our rule evaluation support method.

In this paper, we present a novel rule evaluation support method for post-processing of mined results with rule evaluation models based on objective indexes. Post-processing of mined results is one of the key issues to make a data mining process successfully. However, it is difficult for human experts to evaluate many thousands of rules from a large dataset with noises completely. To reduce the costs of rule evaluation procedures, we have developed the rule evaluation support method with rule evaluation models, which are obtained with objective rule evaluation indexes and evaluations of a human expert for each rule. Since the method is needed more accurate rule evaluation models, we have compared learning algorithms to construct rule evaluation models with the actual meningitis data mining result and actual rule sets from UCI datasets. Then we show the availability of our adaptive rule evaluation support method.

In this paper, we propose an ontology-based framework that integrates existing Web applications into Web portals. The framework helps Web portal developers to discover, evaluate, and execute semantically composed services on the Web. Parameter passings on service composition are associated using service ontology. Semi-automated source code generation reduces the cost of system development. We show the proposed technologies are useful for constructing statically composed service integration system for current Web world.

Coordinating Web Services dynamically revolutionizes how each business collaborates for its performance improvement, so that many IT researchers are recently focusing on them. In order to make the coordination really effective in business, we have to take viewpoints from business models. Though several specifications and approaches were proposed for the coordination, there are no clear relationships between them and business models yet. In this paper, we propose a framework for Web Services coordination based on business models. We have focused on integrating supports for business model management and Web Services based business application development. The framework provides two kinds of repositories for business model management and application development respectively. These repositories enable us to reuse existing models and manage relationships between them, so that we can rapidly reflect business model changes on Web Services coordination.

In order to model software processes based on ontologies engineering techniques, this paper presents a methodology to manually construct the following ontologies: an object ontology based on constituent elements for objects, and a process ontology based on relationships between inputs and outputs, such as subsumption relationships. Next, using the constructed ontologies, software process plans are generated for user queries, with both user interaction and constraint satisfaction by generate and test paradigm. Furthermore, experimental results show that the methodology works well in generating software process plans for a query about a software process plan from a basic design and to a detailed design.

Describes work in progress on developing a diagnostic expert system called MODEST (MOdel-based Diagnostic Expert SysTem). MODEST has been being developed for the purpose of providing a robust framework for diagnostic expert systems. It is built based on the paradigm of model-based diagnosis, dividing the task of diagnosis into three subtasks (namely, hypothesis generation, hypothesis testing and hypothesis classification) and exploiting multifarious knowledge and strategies to perform each subtask. So far, the hypothesis generation and testing parts of MODEST have been successfully implemented and tested in diagnosing possible faults in the domain of refrigeration plants, with promising results.>