An Intelligent Decision Support System (IDSS) for Nutrition Therapy: Infrastructure, Decision Support, and Knowledge Management Design

Introduction

Nutrition therapy is a science-based, yet holistic approach to nutritional counseling rooted in the conviction that food is a form of medicine that can heal, protect, nurture and support good health. Food provides energy and building materials for countless substances that are essential for the growth and survival of every human being (Mahan, Escott-Stump, & Raymond, 2012). Macronutrients¹ contribute the total required energy, but ultimately the energy they yield is available for the work of the muscles and organs of the body. Release of energy for the synthesis, movement, and other functions requires the micronutrients² which function as coenzymes, co-catalyst, and buffers in the miraculous, watery arena of metabolism. States of nutritional deficiency or excess occur when nutrient intake does not match an individual's requirements for optimal health, and we have to keep balance of nutrient intake and nutrient requirements (Mahan, Escott-Stump, & Raymond, 2012).

Decision making is a process of choosing among alternative courses of action for the purpose of attaining a goal or goals (Turban & Aronson & Liang, 2007; Turban & Volonino, 2010; Laudon & Laudon, 2012). Decision making is a prestigious scientific, social, and economic endeavor. Therefore, a decision making situation involves partial, incomplete, or inexact information. A decision support system (DSS) is defined as “interactive computer-based system, which helps decision makers utilize data and models to solve unstructured problems” (Gorry & Scott Morton, 1971). In some decision situations, the support offered by data and model management alone may not be sufficient. Expert systems (ES) provide additional support to substitute for human expertise through supplying the necessary knowledge; however, several other intelligent technologies can be used to support decision situations that require expertise (Turban & Aronson & Liang, 2007). ES are influential systems that assist decision making and apply in a variety of problem domains (Buchanan & Smith, 2003).

Thus, decision makers use their experiences to handle difficult situations, or in complex decisions, it often turns to experts for advice. They recall similar experiences and learn from them what to do with similar new situations for which exact replicas are unavailable. When this approach to problem-solving is computerized, we call it machine learning, and its primary tools are artificial neural networks (ANN) (Turban, Aronson, & Liang, 2007).

The concept of how neurons work in the human brain is utilized in performing computations on computers artificially. Researchers felt that the neurons are responsible for the human capacity to learn, and it is in this sense that the physical structure is being emulated by a neural network to accomplish machine learning. Each computational unit computes some function of inputs and passes the result to connect units in the network. Accordingly, newly learnt information as a produced knowledge of the system comes out of the entire network of the neurons (Ross, 2004; Turban, Aronson, & Liang, 2007).

Researchers usually combine fuzzy logic methods with other artificial intelligence (AI) methods, such as ES and ANN, to boost their accuracy in decision making process (Turban, Aronson, & Liang, 2007). Therefore, in this paper, we establish fuzzy logic to deal with inexact, incomplete and overall uncertainty of human experiences.