Problem Domain Experts Research Articles

Deep Learning and its Application for Healthcare Delivery in Low and Middle Income Countries.

As anyone who has witnessed firsthand knows, healthcare delivery in low-resource settings is fundamentally different from more affluent settings. Artificial Intelligence, including Machine Learning and more specifically Deep Learning, has made amazing advances over the past decade. Significant resources are now dedicated to problems in the field of medicine, but with the potential to further the digital divide by neglecting underserved areas and their specific context. In the general case, Deep Learning remains a complex technology requiring deep technical expertise. This paper explores advances within the narrower field of deep learning image analysis that reduces barriers to adoption and allows individuals with less specialized software skills to effectively employ these techniques. This enables a next wave of innovation, driven largely by problem domain expertise and the creative application of this technology to unaddressed concerns in LMIC settings. The paper also explores the central role of NGOs in problem identification, data acquisition and curation, and integration of new technologies into healthcare systems.

System of Diagnostic Systems framework and its application to the disharmony in Indonesian national security

AbstractAlthough many strategic problems are highly complex and dynamic, available strategic frameworks fail to provide satisfactory solution recommendation. To provide a strategic solution to this highly complex and dynamic problem contexts, we propose a new strategic framework called the System of Diagnostic Systems (SODS). As an empirical case, we apply the SODS framework to analyse the highly complex disharmony issue in the national security of the Republic of Indonesia. Using SODS, we can analyse the problem contexts of three phases of Indonesian security development in a precise manner. Based on the problem's parameterization (i.e., participants, complexity level, comprehensibility, and rationality), the SODS framework can provide the appropriate strategy and tools to mitigate the complex issue. The SODS recommendations were validated by a number of problem domain experts.

Interactive planning system for forest road location

This paper presents an interactive planning system for forest road location. This decision support system is based on an interactive heuristic approach referred to as interactive large neighborhood search, within which the user contributes in a cooperative manner to the optimization process. The objective of this cooperative optimization process is to exploit the problem-domain expertise of the user in order to, on the one hand, guide the search for a solution towards intuitively interesting parts of the solution space, and, on the other hand, generate more practical solutions that integrate aspects of the decision problem that are not captured by the heuristic objective function. This paper more specifically presents the user interface, the interaction mechanisms and the heuristic developed to support the cooperation between the computer and the user. We also present experimental results based on real problem instances, with an expert user. A comparison shows advantages for using the proposed interactive approach over a pure manual or pure automated approach.

Fuzzy logic approach and sensitivity analysis for agent-based crowd injury modeling

A crowd is a group of people attending a public gathering with some joint purpose, such as protesting against the government or celebrating an event. In some countries, these kinds of activities are the only way to express public displeasure with their government. The government’s reactions to such activities may or may not be tolerant. For this reason, such situations must be eliminated by recognizing when and how they are likely to occur, and then providing guidelines to mitigate them. In urban areas, police and military forces use non-lethal weapons (NLWs), such as rubber bullets or clubs, to control a violent and destructive crowd. In order to estimate the results of this engagement, ensuring minimum injuries and reaching an optimal end state, simulating such actions in a virtual environment is necessary. In this work, a fuzzy logic-based crowd injury model for determining the physical effects of NLWs is proposed. Fuzzy logic concepts can be applied to a problem by using linguistic rules, which are determined by problem domain experts. A group of police and military officers were consulted for a set of injury model rules, and those rules were then included in the simulation platform. Sensitivity analysis has been conducted to analyze parameters in the model. As a proof of the concept, a prototype system was implemented using the Repast Simphony agent-based simulation toolkit. Simulation results illustrated the effectiveness of the simulation framework.

MEPAR-miner: Multi-expression programming for classification rule mining

Classification and rule induction are two important tasks to extract knowledge from data. In rule induction, the representation of knowledge is defined as IF-THEN rules which are easily understandable and applicable by problem-domain experts. In this paper, a new chromosome representation and solution technique based on Multi-Expression Programming (MEP) which is named as MEPAR-miner ( Multi-Expression Programming for Association Rule Mining) for rule induction is proposed. Multi-Expression Programming (MEP) is a relatively new technique in evolutionary programming that is first introduced in 2002 by Oltean and Dumitrescu. MEP uses linear chromosome structure. In MEP, multiple logical expressions which have different sizes are used to represent different logical rules. MEP expressions can be encoded and implemented in a flexible and efficient manner. MEP is generally applied to prediction problems; in this paper a new algorithm is presented which enables MEP to discover classification rules. The performance of the developed algorithm is tested on nine publicly available binary and n-ary classification data sets. Extensive experiments are performed to demonstrate that MEPAR-miner can discover effective classification rules that are as good as (or better than) the ones obtained by the traditional rule induction methods. It is also shown that effective gene encoding structure directly improves the predictive accuracy of logical IF-THEN rules.

OBJECT ORIENTED ANALYSIS: AN INTRODUCTIONAND COMPARISONTO TRADITIONAL SYSTEMS ENGINEERING ANALYSIS METHODS

AbstractObject oriented analysis (OOA) is an analysis method that “examines requirements from the perspective of the classes and objects found in the … problem domain” (Korncoff, 1993). OOA allows systems engineers to analyze increasingly complex problem domains. Its methodology improves the communication between the system analyst, the problem domain experts, the managers, and the customers. Analysis results are more internally consistent through OOA methods, and commonalty of objects and functions are explicitly represented through the use of inheritance. Requirements specifications can be built that are more resilient to change, and analysis methods and results are structured for reuse. Finally, when products of the systems analysis and design processes includes software written in Ada (or another object oriented language), OOA provides a consistent underlying representation that minimizes the transition/translation problems often encountered between software and systems engineering efforts.This paper provides an introduction to OOA methods and its utility for systems engineering. A comparison between OOA and more traditional functions‐requirements‐allocations (FRA) analysis methods is discussed. A simple case study is presented to contrast traditional FRA and OOA methods.