Exploring the factors associated with expert systems success

As the widespread use and company dependency on Expert Systems increase, so does the need to assess their value and to ensure implementation success. This study identified and empirically tested eight major variables proposed in the literature as determinants of ES success, in this case measured in terms of user satisfaction. IBM's Corporate Manufacturing Expert Systems Project Center collected information from 69 project managers to support the study. The results clearly support the hypothesized relationships and suggest the need for ES project managers to pay special attention to these determinants of ES implementation success. ES success is directly related to the quality of developers and of the ES shells used, end-user characteristics and degree of user involvement in ES development, as each has been defined in this study. For exploratory purposes, the component items for each of these major variables were correlated with the components of user satisfaction. Based on the results, several recommendations are proposed for ES project managers to enhance the likelihood of project success, including: adding problem difficulty as a criterion for ES application selection; increasing ES developer training to improve their people skills, ability to model and to use a systems approach in solving business problems; shaping end-user attitudes and expectations regarding ES; improving the selection of domain experts; more thoroughly understanding the ES impact on end-user jobs; restricting the acquisition of ES shells based on a proposed set of criteria; and ensuring a proper match of ES development techniques and tools to the business problem at hand.

Download Full-text

A Comparison of Hardcopy and Expert System Presentation of Network Operator Assistance Guides

Proceedings of the Human Factors Society Annual Meeting ◽

10.1177/154193128703100703 ◽

1987 ◽

Vol 31 (7) ◽

pp. 706-709

Author(s):

D. C. Antonelli

Keyword(s):

Expert System ◽

Expert Systems ◽

User Satisfaction ◽

Systems Approach ◽

Presentation Order ◽

Hard Copy ◽

Network Operator ◽

Typical Problem ◽

Successful Solution ◽

Similar Information

Operator's Guides have traditionally been used for the communication of information. Some recent work by de Bachtin (1985) has shown that in certain programming applications, expert systems can be used to perform the same function with increased user satisfaction. The current study addresses an SNA network assistance application and compares a conventional hard copy user's manual to an expert system designed to convey similar information. The performance of eight naive assistance operators attempting to solve eight typical problem scenarios was evaluated. Each operator performed all tasks. Presentation order was counterbalanced. Measures included probability of successful solution and time of solution. Performance was superior using the expert systems approach for all measures.

Download Full-text

Stakeholder Engagement in Business Intelligence (BI) Solutions - A Case Study in End User Involvement

i-manager’s Journal on Management ◽

10.26634/jmgt.3.2.260 ◽

2008 ◽

Vol 3 (2) ◽

pp. 19-33

Author(s):

Richard M. Kesner ◽

Keyword(s):

Business Intelligence ◽

Stakeholder Engagement ◽

User Involvement ◽

End User ◽

End User Involvement

Download Full-text

Assessing Team Detailing End-user Satisfaction

10.21236/ada427712 ◽

2004 ◽

Author(s):

Kimberly P. Whittam ◽

Zannette A. Uriell ◽

Rorie N. Harris

Keyword(s):

User Satisfaction ◽

End User

Download Full-text

Effect of the COVID ‐19 induced phase of massive telehealth uptake on end‐user satisfaction

Internal Medicine Journal ◽

10.1111/imj.15222 ◽

2021 ◽

Vol 51 (2) ◽

pp. 206-214

Author(s):

Nicole J. Bate ◽

Simon C. Xu ◽

Maurizio Pacilli ◽

Lynden J. Roberts ◽

Chris Kimber ◽

...

Keyword(s):

User Satisfaction ◽

End User

Download Full-text

Results of the Behavioral Health Readiness Evaluation and Decision-Making Instrument Study

Military Medicine ◽

10.1093/milmed/usaa401 ◽

2021 ◽

Vol 186 (Supplement_1) ◽

pp. 142-152

Author(s):

Justin M Curley ◽

Katie L Nugent ◽

Kristina M Clarke-Walper ◽

Elizabeth A Penix ◽

James B Macdonald ◽

...

Keyword(s):

Decision Making ◽

Behavioral Health ◽

User Satisfaction ◽

Safety Issue ◽

Walter Reed Army Institute ◽

End User ◽

Chi Square ◽

Proficiency Level ◽

Wide Range ◽

Decision Making Support

ABSTRACT Introduction Recent reports have demonstrated behavioral health (BH) system and individual provider challenges to BH readiness success. These pose a risk to winning on the battlefield and present a significant safety issue for the Army. One of the most promising areas for achieving better BH readiness results lies in improving readiness decision-making support for BH providers. The Walter Reed Army Institute of Research (WRAIR) has taken the lead in addressing this challenge by developing and empirically testing such tools. The results of the Behavioral Health Readiness Evaluation and Decision-Making Instrument (B-REDI) field study are herein described. Methods The B-REDI study received WRAIR Institutional Review Board approval, and BH providers across five U.S. Army Forces Command installations completed surveys from September 2018 to March 2019. The B-REDI tools/training were disseminated to 307 providers through random clinic assignments. Of these, 250 (81%) providers consented to participate and 149 (60%) completed both initial and 3-month follow-up surveys. Survey items included a wide range of satisfaction, utilization, and proficiency-level outcome measures. Analyses included examinations of descriptive statistics, McNemar’s tests pre-/post-B-REDI exposure, Z-tests with subgroup populations, and chi-square tests with demographic comparisons. Results The B-REDI resulted in broad, statistically significant improvements across the measured range of provider proficiency-level outcomes. Net gains in each domain ranged from 16.5% to 22.9% for knowledge/awareness (P = .000), from 11.1% to 15.8% for personal confidence (P = .001-.000), and from 6.2% to 15.1% for decision-making/documentation (P = .035-.002) 3 months following B-REDI initiation, and only one (knowledge) failed to maintain a statistically significant improvement in all of its subcategories. The B-REDI also received high favorability ratings (79%-97% positive) across a wide array of end-user satisfaction measures. Conclusions The B-REDI directly addresses several critical Army BH readiness challenges by providing tangible decision-making support solutions for BH providers. Providers reported high degrees of end-user B-REDI satisfaction and significant improvements in all measured provider proficiency-level domains. By effectively addressing the readiness decision-making challenges Army BH providers encounter, B-REDI provides the Army BH health care system with a successful blueprint to set the conditions necessary for providers to make more accurate and timely readiness determinations. This may ultimately reduce safety and mission failure risks enterprise-wide, and policymakers should consider formalizing and integrating the B-REDI model into current Army BH practice.

Download Full-text

Model-based diagnosis of the space shuttle main engine

Artificial intelligence for engineering design analysis and manufacturing ◽

10.1017/s0890060400003036 ◽

1992 ◽

Vol 6 (3) ◽

pp. 131-148 ◽

Cited By ~ 6

Author(s):

Martin O. Hofmann ◽

Thomas L. Cost ◽

Michael Whitley

Keyword(s):

Space Shuttle ◽

Diagnostic System ◽

End User ◽

Reasoning Process ◽

Domain Experts ◽

Model Based ◽

Knowledge Based ◽

Modeling Analysis ◽

Engine Design ◽

Main Engine

The process of reviewing test data for anomalies after a firing of the Space Shuttle Main Engine (SSME) is a complex, time-consuming task. A project is under way to provide the team of SSME experts with a knowledge-based system to assist in the review and diagnosis task. A model-based approach was chosen because it can be adapted to changes in engine design, is easier to maintain, and can be explained more easily. A complex thermodynamic fluid system like the SSME introduces problems during modeling, analysis, and diagnosis which have as yet been insufficiently studied. We developed a qualitative constraint-based diagnostic system inspired by existing qualitative modeling and constraint-based reasoning methods which addresses these difficulties explicitly. Our approach combines various diagnostic paradigms seamlessly, such as the model-based and heuristic association-based paradigms, in order to better approximate the reasoning process of the domain experts. The end-user interface allows expert users to actively participate in the reasoning process, both by adding their own expertise and by guiding the diagnostic search performed by the system.

Download Full-text