A Tutorial Introduction to Decision Theory

“…In this paper, a decision theory [18] based object classification using a Bayesian decision theory (BDT) [19] approach is proposed, which is easy to implement and works under uncertainty making it well-suited for IoT. In IoT, there are different objects in the environment and these objects need to be classified into two or more mutually exclusive sets.…”

Section: Proposed Workmentioning

confidence: 99%

Object Classification based Context Management for Identity Management in Internet of Things

Mahalle¹,

Prasad

2013

IJCA

View full text Add to dashboard Cite

As computing technology is becoming more tightly coupled into dynamic and mobile world of the Internet of Things (IoT), security mechanism is more stringent, flexible and less intrusive. Scalability issue in IoT makes identity management (IdM) of ubiquitous objects more challenging, and there is a need of context-aware access control solution for IdM. Confronting uncertainty of different types of objects in IoT is not easy. This paper presents the logical framework for object classification in context aware IoT, as richer contextual information creates an impact on the access control. This paper proposes decision theory based object classification to provide contextual information and context management. Simulation results show that the proposed object classification is useful to improve network lifetime. Results also give motivation of object classification in terms of energy consumption. This paper also presents proof of concept and time analysis of the proposed decision theory based object classification.

show abstract

“…Value of information (VOI) analysis, is a way of evaluating the management benefits of collecting additional information to reduce uncertainties before making a decision (Raiffa & Schlaifer 1961;North 1968;Runge, Converse & Lyons 2011).…”

Section: Value Of Informationmentioning

confidence: 99%

“…Decision-theory provides a rational procedure for discriminating between alternative decisions or actions, when the outcomes of these decisions are uncertain (Raiffa & Schlaifer 1961;North 1968). …”

Section: Decision Theorymentioning

confidence: 99%

“…Value of information (VOI) analysis can explicitly indicate the optimal management decision that arises from new information, as obtained through monitoring or research, versus existing information (Raiffa & Schlaifer 1961;North 1968;Runge, Converse & Lyons 2011). It evaluates the benefit of collecting additional information for management decision making to reduce uncertainties before making a decision.…”

Section: Decision Tools For Monitoring Multiple Threatsmentioning

confidence: 99%

See 1 more Smart Citation

Effective monitoring for biodiversity conservation

Bal¹

View full text Add to dashboard Cite

Monitoring of biodiversity is expensive and can detract resources for managing biodiversity. Given limited resources for conservation, it is not only important to assess the choices we make for managing biodiversity but also those for monitoring biodiversity. This entails considering the benefits and costs of alternative monitoring strategies, and selecting the ones that best inform and improve management decisions. However, understanding which aspects of an ecosystem to monitor (e.g. which species, threat, or indicator) to make effective management decisions is a challenging task. This is especially true when we are faced with large uncertainties, such as those regarding the drivers of change when species are impacted by multiple threats. Although optimal monitoring approaches for conservation decision-making under limited resources have gained popularity over the last decade, similar approaches for monitoring and indicator selection to inform the management of multiple threats for biodiversity have received relatively little attention. In this thesis, I contribute to the theory and tools for selecting monitoring strategies and indicators to improve management decisions, with a focus on multi-species, multi-threat systems. The four objectives of my thesis are: (1) to review current approaches for selecting indicator species for biodiversity management; (2) to assess the value of monitoring species for managing multiple threats; (3) to assess the relative influence of uncertainty and expected benefits of management on monitoring decisions for multiple threats; and (4) to develop a simple indicator selection tool based on a return on investment framework for managing multi-species, multi-threat systems.The thesis starts with a systematic review of the conservation literature, in chapter two, to assess the extent to which the selection of indicator species for biodiversity management explicitly considers management objectives and the management outcomes of monitoring. I find that most indicator selection studies focus on improving the monitoring efficiency rather than the management effectiveness, potentially leading to ineffective indicators. Recommendations are provided to improve indicator selection for management decision-making. I also propose a decision framework for selecting indicator species and identify decision-analytic approaches to evaluate alternative monitoring choices that are further developed in the remainder of the thesis.In chapter three, I use value of information analysis to investigate how monitoring alternative species subject to multiple threats improves our ability to inform the management of these threats.iii Specifically, I compare the effectiveness of different monitoring approaches to learn about the threats i.e. monitoring just species and monitoring with experimental manipulation of threats. My results show that monitoring species alone is unlikely to provide useful information for threat management when there is uncertainty about the effect of multiple threats. Instead, an ...

show abstract

A Tutorial Introduction to Decision Theory

Cited by 106 publications

References 12 publications

Insights from Science into Business and Economics: Roadmap to a Fiasco Prevention Theory

Insights from Science into Business and Economics: Roadmap to a Fiasco Prevention Theory

Object Classification based Context Management for Identity Management in Internet of Things

Effective monitoring for biodiversity conservation

Contact Info

Product

Resources

About