International Symposium Knowledge and Systems Sciences 

About: International Symposium Knowledge and Systems Sciences is an academic conference. The conference publishes majorly in the area(s): Complex network & Decision support system. Over the lifetime, 78 publications have been published by the conference receiving 293 citations.

MANDY: Towards a Smart Primary Care Chatbot Application

Abstract: The paper reports on a proof-of-concept of \(\mathsf {Mandy}\), a primary care chatbot system created to assist healthcare staffs by automating the patient intake process. The chatbot interacts with a patient by carrying out an interview, understanding their chief complaints in natural language, and submitting reports to the doctors for further analysis. The system provides a mobile-app front end for the patients, a diagnostic unit, and a doctor’s interface for accessing patient records. The diagnostic unit consists of three main modules: An analysis engine for understanding patients symptom descriptions, a symptom-to-cause mapper for reasoning about potential causes, and a question generator for deriving further interview questions. The system combines data-driven natural language processing capability with knowledge-driven diagnostic capability. We evaluate our proof-of-concept on benchmark case studies and compare the system with existing medical chatbots.

Estimating the Optimal Number of Clusters in Categorical Data Clustering by Silhouette Coefficient

Abstract: The problem of estimating the number of clusters (say k) is one of the major challenges for the partitional clustering. This paper proposes an algorithm named k-SCC to estimate the optimal k in categorical data clustering. For the clustering step, the algorithm uses the kernel density estimation approach to define cluster centers. In addition, it uses an information-theoretic based dissimilarity to measure the distance between centers and objects in each cluster. The silhouette analysis based approach is then used to evaluate the quality of different clusterings obtained in the former step to choose the best k. Comparative experiments were conducted on both synthetic and real datasets to compare the performance of k-SCC with three other algorithms. Experimental results show that k-SCC outperforms the compared algorithms in determining the number of clusters for each dataset.

An Ontology-Based Knowledge Framework for Software Testing

Abstract: Software development is conceptually a complex, knowledge intensive and a collaborative activity, which mainly depends on knowledge and experience of the software developers. Effective software development relies on the knowledge collaboration where each and every software engineer shares his or her knowledge or acquires knowledge from others. Software testing which is a sub area of software engineering is related to various activities such as test planning, test case design, test implementation, test execution and test result analysis and they are all essential. Given great importance to knowledge for software testing, and the potential benefits of managing software testing knowledge, an ontological approach to represent the necessary software testing knowledge within the software testers context was developed. Using this approach, software testing ontology to include information needs identified for the software testing activities was designed. Competency questions (contextualized information) were used to determine the scope of the ontology and used to identify the contents of the ontology because contextualized information fulfills the expressiveness and reasoning requirements of the software testing ontology. SPARQL query was used to query the competency questions. A web based KM Portal was developed using semantic web technologies for knowledge representation. Software testers can annotate their testing knowledge with the support of ISTQB and IEEE 829-2008 terms. Both ontology experts and non-experts evaluated the developed ontology. We believe our software testing ontology can support other software organizations to improve the sharing of knowledge and learning practices.

A Fuzzy AHP-TOPSIS Approach for Selecting the Multimodal Freight Transportation Routes

Abstract: Multimodal transportation route selection strategy has become an important component in the main logistics and transportation. Route selection relies upon decision-based on real industry data and expert judgments. This paper proposes Fuzzy Analytic Hierarchy Process (AHP) and Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for prioritizing effectively the multimodal transportation routes to improve logistics system performance by constructing the possible routes considering transport cost, time, risk, and quality factors. Fuzzy AHP is used to determine weights for evaluation criteria and Fuzzy TOPSIS is used to aid the ranking of possible route alternatives. The empirical case study of coal manufacturing is conducted to illustrate a proposed methodology that enables to provide a more accurate, practical, and systematic decision support tool.

Generating Risk Maps for Evolution Analysis of Societal Risk Events

Abstract: The development of societal risk events has been heavily concerned by both the government and the public. Faced with ever-increasing information, people struggle to follow the evolution of societal risk events. In order to identify the evolution of societal risk events, this paper presents an improved algorithm based on the method of generating information maps. One real-world case is illustrated and the evaluation is given. The improved approach for the evolution analysis whose results show the promising performance may be used for post-operation analysis, and decision-making process for government management.