This book is an attempt to establish in the readers the importance of creating interoperable data stores and writing rules for handling this data. It also covers extracts from a few project dissertations and a research funded project that the author had supervised.⢠Describes the power of ontologies for better data management⢠Provides an overview of knowledge engineering including ontology engineering, tools and techniques⢠Provides sample development procedures for creating two domain ontologies.⢠Depicts the utility of ontological representation in situation awareness⢠Demonstrates recommendation engine for unconventional emergencies using a hybrid reasoning approach.⢠The text explains how to make better utilization of resources when emergency strikesGraduates and undergraduates doing courses in artificial intelligence, semantic web and knowledge engineering will find this book beneficial.
Frequently asked questions
Simply head over to the account section in settings and click on âCancel Subscriptionâ - itâs as simple as that. After you cancel, your membership will stay active for the remainder of the time youâve paid for. Learn more here.
At the moment all of our mobile-responsive ePub books are available to download via the app. Most of our PDFs are also available to download and we're working on making the final remaining ones downloadable now. Learn more here.
Both plans give you full access to the library and all of Perlegoâs features. The only differences are the price and subscription period: With the annual plan youâll save around 30% compared to 12 months on the monthly plan.
We are an online textbook subscription service, where you can get access to an entire online library for less than the price of a single book per month. With over 1 million books across 1000+ topics, weâve got you covered! Learn more here.
Look out for the read-aloud symbol on your next book to see if you can listen to it. The read-aloud tool reads text aloud for you, highlighting the text as it is being read. You can pause it, speed it up and slow it down. Learn more here.
Yes, you can access Understanding Semantics-Based Decision Support by Sarika Jain in PDF and/or ePUB format, as well as other popular books in Computer Science & Artificial Intelligence (AI) & Semantics. We have over one million books available in our catalogue for you to explore.
Semantics-based Decision Support - An Introduction
This book is an attempt to exploit the full potential of existing tools, techniques, and methodologies to provide situation awareness and advisory support to end-users in a seamless manner. The nature of information input to a Decision Support System (DSS) is majorly unstructured or semi-structured, making the decision-making process complex. The heterogeneity of information sources is easily dealt with by incorporating semantic technologies and hence facilitating intelligent situation awareness and decision support. This book presents to the reader the prototypical development of a knowledge-driven situation awareness and advisory support (KDSAAS) in the emergency domain. KDSAAS applies semantic technologies to provide real-time information in order to provide intelligent decision support. This introductory chapter advocates the importance and utilization of semantic data models in achieving semantic intelligence, which is a prerequisite for successful decision support systems. A few use cases demonstrating the importance of semantic technologies for decision support systems are also presented.
1.1 Decision Support
Decision making refers to the thought process of making a judgment to make a plan, solve a problem, react to a situation, or attain a goal. Decision making often involves argumentation, i.e., a process which involves thinking over alternative courses of action based on structured arguments. It involves becoming aware of and assessing the situations that may exist and events/actions that may take place. A decision support system (DSS) is required to assist the human counterparts in decision making by automating some of their tasks, i.e., by providing awareness of the situations and automated decision support. A DSS, also termed an advisory system, provides otherwise costly expertise and experience to human decision-makers in solving problems (which and how much resources to allocate, what actions to take, and others) [Inan et al. 2018, Jain 2018].
A DSS assists decision-makers at each level to achieve a scientific decision and improves the overall decision-making process. DSS research is very diverse and is influenced by various other areas, such as the social sciences. A DSS is composed of (i) the database (or knowledge base) that contains the relevant data; (ii) the model base and analytical tools to convert the data from the database to information; and (iii) the interface between the user and different components of the DSS.
Different authors have proposed different classifications of DSSs, none of which is accepted as a universal taxonomy. Based on the internal structure, a DSS can be classified as data-based, model-based, knowledge-based, communication-driven, or document-driven. A data-based DSS focuses on accessing and manipulating a large database for analysis purposes. A model-based DSS focuses on the application of models to solve a certain domain of problems, such as optimization, financial, or mathematical (simulation) models. In these DSSs, the model lies at the center and the data usage is minimal; the situation is analyzed by accessing and manipulating the model. A knowledge-based DSS is developed with the major focus on knowledge storage, representation, and management; it can suggest or recommend actions to managers. A communications-driven DSS concentrates on how people interact in groups and how decision making is done when a group of people collaborate and interact. A document-driven DSS analyzes a document collection, whether text or multimedia, to reach to a decision.
Most of these categories may be considered not as decision-oriented but rather as DSS tools. Based on the purpose of the DSS, they have been classified differently by different people, e.g., personal DSS (a DSS which focuses on and supports individuals), group DSS (a DSS which facilitates a group of people in reaching to a joint decision), negotiation DSS (a DSS in which negotiating is allowed on certain intermediate decisions), and business intelligence (a DSS performing data analysis of business information to convert it into actionable knowledge) [Arnott and Pervan 2005]. With the inclusion of Artificial Intelligence (AI) methods and techniques recently (fuzzy logic, knowledge bases, natural language programming (NLP), neural networks, genetic algorithms, and so forth), a lot of improvements can be seen in the working of DSSs. The new terminology thus common for DSSs is âIntelligent decision support systems.â An Intelligent DSS is able to mimic human intelligence, performcommon-sense reasoning, and context-sensitive reasoning, hence improving the ability of decision-makers.
Knowledge-driven Intelligent DSS is the amalgamation of Knowledge Management (KM) and AI technologies to decision support. A knowledge-driven Intelligent DSS stores knowledge and assists humans in solving problems as any human companion would do. It has basically two components: a knowledge store with a representation scheme and an inference engine for reasoning.
1.2 Situation Awareness
Decision making is a stressful task, and it becomes even more stressful when thousands of lives depend on it. One of the important decision-makers in every nation is the government. At times, the government doesnât have an efficient way of finding resources such as trained professionals, medical services, rescue teams, and so on, when emergencies happen. When the decisions made are not the ones, many times it results in casualties which could have been avoided. Decision makers need to handle a very large and complex historical data store and quickly reach decisions. However, the way information is presented to them, and even the amount of information generated, may be so vague and inapposite that the decision-makers are not aware of the situation at hand. This leads to poor resource estimation and inaccurate action prediction, putting victimsâ lives at risk. For handling problems like these, a government needs an effective and efficient way to remove all the knowledge barriers from its path so that it can make quicker and more informed decisions to take advantage of the most opportunities to save lives and belongings [Kantorovitch et al. 2017, Nwiabu 2020].
Situation awareness is about being able to identify and process information. In a daily routine, situation awareness refers to the real-time minute-to-minute consciousness or perception of the whereabouts and minute details of the state of affairs in a given enterprise. A knowledge-driven Intelligent DSS has all the capabilities to represent and store knowledge in a manner that is required by decision-makers for making better decisions. The knowledge stores thus developed facilitate integrated information retrieval, which supports interoperability between different use cases for ease of management. They can store all historical events that have happened for a domain. These knowledge stores must be designed in a manner to overcome the problem of static and incomplete representation of knowledge, hence allowing better information sharing in an efficient and effective manner. Algorithms can then be developed for required use cases, such as providing situation awareness and resource management through browsing the knowledge, searching some concept in the knowledge stores, and submitting queries. This book provides a perspective on how semantic technologies (STs) can be used to narrate and outline situations, improving understanding and realization of the situation. STs give a detailed account of and portray the semantics that are related to information [Patel and Jain 2019].
1.3 Paradigm Shift from Data to Knowledge
In order to guide our actions and achieve desired goals, human beings need to connect pieces of information together. Similarly, machines need to climb the steps up the wisdom hierarchy (commonly called the DIKW pyramid). The DIKW pyramid shows the hierarchy from data to wisdom: data (raw facts), information (defining relationships), knowledge (explicit information), and wisdom (thinking and acting using knowledge) [Koltay 2020]. Some applications require a combination of different domain knowledge to solve problems so that an appropriate action or conclusion can be deduced. However, combining domain knowledge is a very complex task, and it requires too much memory and time if the information is not organized in a proper format. A large amount of data comes from different places, which generates heterogeneity problem. The heterogeneity of data produces variation in meaning or ambiguity in the interpretation of entities; as a result, it prevents information sharing between systems. Therefore, without identification of the semantic mappings between entities, we cannot communicate, interact, collaborate, or share information across applications or use different knowledge sources in one application. Various approaches have been proposed to achieve solutions to these problems, but achieving optimal performance remains an open challenge. We need to convert data into knowledge artifacts to achieve interoperability; the most critical success factor is efficient and effective knowledge sharing across applications, organizations, and decision-makers, which in turn requires KM techniques.
Knowledge Management refers to collecting, processing, and organizing knowledge. The way information is organized has an effect on the processes or operations that are used to manipulate the entities of the information [Evangelou et al. 2005]. McCarthy1 in 1955 coined the term âArtificial Intelligenceâ for the capacity that allows machines to behave as intelligently as human beings. All the components of a DSSâthe knowledge base, the model base, and the user interfaceâemploy KM and AI techniques. These techniques help by improving the critical thinking of experts and recommending the next course of action [Bughin et al. 2017, Gasser and Almeida 2017]. This develops competitive intelligence, retaining employeesâ expertise and sharing best practices. Formalization of knowledge is a question of both structure and function. Real-world problems use real-time systems that are resource constrained: they should work very effectively and accurately within the given resource for the system response. For any intelligent machine, the focus is on the representation of knowledge in such a manner that inferences can be drawn efficiently and effectively within the resource constraints (data, time, space, etc.). For decades, in order to interface with real-world objects and enable cooperation between applications and services, it has been the duty of human counterparts to understand semantics (meaning) and make it machine processable. To plan and integrate existing data resources and make them shareable, we need to model semantics.
Though traditional data models scale well for many core data integration and storage requirements, they are often unable to cope with the dynamic nature of todayâs world. This is where STs exc...
Table of contents
Cover
Half Title
Title Page
Copyright Page
Table of Contents
Foreword
Preface
About the Author
Acknowledgment
Acronyms and Abbreviations
1 Semantics-based Decision Support - An Introduction
2 Semantic Technologies as Enabler
3 Semantics-Based Decision Support for Unconventional Emergencies
