Rajiv Khosla

Engineering intelligent hybrid multi-agent systems

Preface. 1. Why Intelligent Hybrid Systems. 2. Methodologies. 3. Intelligent Fusion and Transformation Systems. 4. Intelligent Combination Systems. 5. Knowledge Discovery, Data Mining and Hybrid Systems. 6. Association Systems - Task Structure Level Associative Hybrid Architecture. 7. Intelligent Multi-Agent Hybrid Computational Architecture - Part I. 8. Intelligent Multi-Agent Hybrid Computational Architecture - Part II. 9. Alarm Processing - An Application of IMAHDA. 10. Agent Oriented Analysis and Design of the RTAPS - Part I. 11. Agent Oriented Analysis and Design of the RTAPS - Part II. 12. RTAPS Implementation. 13. From Data Repositories to Knowledge Repositories. 14. IMAHDA Revisited. Appendices: A. Input Features of the Animal Domain. B. Classes in the Animal Domain. C. TTS Power Network. D. TTS Substation Power Network. E. Real Time Alarm Data. Index.

RFID-based Hospital Real-time Patient Management System

In a health care context, the use RFID (radio frequency identification) technology can be employed for not only bringing down health care costs but also facilitate automating and streamlining patient identification processes in hospitals and use of mobile devices like PDA, smart phones, for design a health care management systems. In this paper, we outline a RFID model for designing a system in the health care. An application of the architecture is described in the area of RFID-based real-time hospital patient management system (HPMS).

Socially Assistive Robots in Elderly Care: A Mixed-Method Systematic Literature Review

The world’s population is aging, and developed countries are engaged in developing a new aged-care paradigm to reduce spiraling healthcare costs. Assistive technologies like Socially Assistive Robots (SAR) are being considered as enablers to support the process of care giving or keep elderly at home longer. This article reports a mixed-method systematic review of SAR in elderly care and recognizes its impact on elderly well-being, integrating evidence from qualitative and quantitative studies. It follows the principles explained in Cochrane Handbook for Systematic Reviews of Interventions and classifies interventions, measures, and outcomes of field trials of SAR in elderly care. Eighty-six studies in 37 study groups have been included. The findings imply positive effects of SAR on elderly well-being. Ten significant recommendations are made to help avoid the current limitations of existing research and to improve future research and its applicability. This review revealed that SAR can potentially enhance elderly well-being and decrease the workload on caregivers. There is a need for rigorous research methodology, person-centered care, caregiver expectation model, multimodal interaction, multimodal data collection, and modeling of culturally diverse groups to facilitate acceptability of SAR.

Using Nonadditive Fuzzy Integral to Assess Performances of Organizational Transformation Via Communities of Practice

Organizational transformations have been widely adopted by firms who wish to improve their competitive advantage to be better prepared to face external challenges. This research has chosen Communities of Practice (CoPs) as the subject of discussion for an assessment model to reform organizations that undertake CoPs for collective knowledge to enhance their core competencies. Given the interrelationships between criteria, this research uses the nonadditive fuzzy integral to develop a framework for the CoPs performance assessment. The purposes of this paper are to identify the key dimensions/criteria in the CoPs, to use fuzzy logic method to analyze the relative importance of each criterion, and to rank the criteria so that proper resources can be allocated while managing the CoPs. Through interviews with experts, four strategy alternatives and 16 criteria along four dimensions are generated. A survey of the CoPs practitioners is then conducted to compare the results of each criterion. The results will not only help organizations that intend to initiate changes via the CoPs activities to decide the ranking of their appraisal criteria, but it can also assist them in guiding the behavior of their staff while effectively monitoring and improving the performances of the CoPs

Mapping knowledge sharing traits to business strategy in knowledge based organisation

Globalization has resulted in increasing use of knowledge as competitive weapon in many organizations nowadays. In this context, an increasing number of organizations are focusing on communities of practice (CoPs) orientated knowledge management (KM) studies and the links between KM and organizational business strategy. This link is an important determinant of organizational performance. While KM business strategy (linked to organization business strategy) is important, knowledge sharing behavior of knowledge workers is a critical enabler of effective knowledge management and organizational performance. That is, organizations invest resources in creating CoPs for competitive advantage and lack of suitable candidates will result in loss of momentum and less knowledge sharing in CoPs and there by underutilizing the resources. The aim of this research is to identify the personality traits to portrait the features of knowledge workers suitable for CoPs oriented KM and business strategy. Four KM business strategies have been established in this paper in light of organization performance orientation and KM implementation mode and traits of knowledge workers are mapped to different business strategies. The most significant personality traits of knowledge sharing behavior have been analyzed to determine the suitable traits for different type business strategies. Thus contributions of this paper include (a) defining a model which links four business strategies with CoPs orientated KM model and knowledge sharing behavior model (based on revised Five Factor Model); (b) mapping of personality traits of knowledge workers with four business strategies; (c) providing a guideline to knowledge based organizations for seamless integration of business strategy with CoPs oriented KM and compatible knowledge workers and d) more effective utilization of organizational resources to facilitate improvement in organizational performance.

Index evaluations and business strategies on communities of practice

Business strategies and index evaluations on communities of practice (CoPs) could be the prevailing way for group learning and innovation building within firms. As firms grow in size, scope, and complexity, CoPs members who regularly engage in sharing and learning based on common interests, could improve organizational performance. Due to multi-criteria consideration and uncertain information handling, the purpose of this research is to use the fuzzy multi-criteria decision making (MCDM) method to analyze various index priorities and strategy preferences of CoPs, by undertaking empirical studies of Industrial Technology Research Institute (ITRI) in Taiwan. Fourteen units in survey case were given fifty-seven questionnaires about their priorities towards sixteen different pairs of criteria. Additionally, they were also asked to estimate their four highest achievable business strategies. These evaluation criteria include satisfying multi-dimensions to capable operators. Under each of the four first-tier dimensions, four second-tier criteria are used to assess and echo their first-tier dimensions. The findings of this paper can promote performance value of implementing knowledge management systems and modelling of competitive strategies for CoPs.

Intelligent hybrid multi-agent architecture for engineering complex systems

In this paper we outline an intelligent hybrid multi-agent architecture for engineering complex systems. The hybrid multi-agent architecture is described at the task structure level. The architecture has been successfully applied in a real time alarm processing and fault diagnosis system in a power system control centre with good performance results.

An online multi-agent e-sales recruitment system

E-recruitment area has emerged as an important e-business function in the past few years. We describe a novel e-recruitment multiagent application for recruitment and benchmarking of salespersons. Most existing approaches to recruitment rely on the interview process or on psychometric techniques. Both these approaches have had limited success. We describe a multiagent e-sales recruitment system (e-SRS), which integrates a selling behavioral model with expert systems and soft computing techniques like fuzzy-K-means for predicting the selling behavior profile of a sales candidate.

Separating the wheat from the chaff: An intelligent sales recruitment and benchmarking system

The need for computer-based intelligent techniques for recruitment and retention of employees in a highly competitive global market has grown significantly in the last decade. Salesperson recruitment is a critical task for most organisations. Existing approaches for salesperson recruitment primarily rely on filtering of applications based on selection criteria followed by interviews. Some organisations also include personality testing based on psychometric techniques. The high turnover of salesperson in the industry suggests limited success of these procedures. Additionally, existing approaches lack benchmarking methods. In this paper we describe design and development of an intelligent sales recruitment and benchmarking system (ISRBS) for recruitment and benchmarking of salespersons. ISRBS design represents operation of the findings and outcomes based on actual field studies and random surveys of salespersons as well as development of models for measuring independent and dependent variables related to selling behaviour. The main contributions of the paper are (i) Developing an on line selling behaviour profiling technique based on integration of intelligent system techniques like expert systems and fuzzy sets, psychology based selling behaviour model, and AHP techniques, and (ii) an objective and novel selling behaviour benchmarking technique to facilitate modelling of organisation based benchmarks and cultural fits. An earlier version of this system has been commercially used in the industry in Australia. ISRBS integrates psychology based selling behaviour model with artificial intelligence techniques and soft computing methods for selling behaviour profiling and benchmarking.

Use of fuzzy feature vectors and neural networks for case retrieval in case based systems

Case-based reasoning is a subset of artificial intelligence and expert systems, and is a powerful mechanism for developing systems that can learn from and adapt past experiences to solve current problems. One of the main tasks involved in the design of case-based systems is determining the features that make up a case and finding a way to index these cases in a case-base for efficient and correct retrieval. This paper looks at how the use of fuzzy feature vectors and neural networks can improve the indexing and retrieval steps in case-based systems.