Fuzzy logic and MCDA in IoT resources classification

Dilli, Renato; Argou, Amanda; Pilla, Maurı́cio L.; Pernas, Ana Marilza; Reiser, Renata; Yamin, Adenauer

doi:10.1145/3167132.3167216

Cited by 12 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The matrix is normalized to fall in the range from 0 to 1.As shown in Table 9, the overall weight is computed followed by proximity to ideal case in Table 11. Finally the IoT Light sensors are ranked based on the computed rank index score as shown in The proposed approach is compared with basic AHP-AHP and AHP-TOPSIS approach [18] for ranking. As shown in fig.…”

Section: Implementation and Results Discussionmentioning

confidence: 99%

“…The proposed model for finding the most pertennet IoT resources is based on fuzzy logic [18] based user preference computation, objective weight computation technique based on entropy approach, multicriteria decision making techniques TOPSIS. As per the IoTResource model , each IoT device which offer multiple services have spatial, temporal, QOS attributes associated with it which needs to be monitored (telemetric).…”

Section: Proposed Iot Resource Discovery and Ranking Modelmentioning

confidence: 99%

See 1 more Smart Citation

MULTI CRITERIA DECISION BASED RANKED DISCOVERY FRAMEWORK FOR IoT RESOURCESN

Chikkamannur¹

2021

INDJCSE

View full text Add to dashboard Cite

The growth rate of Internet of Things (IoT) ecosystem has led to an enormous pool of heterogeneous IoT resources with similar capabilities. Providing the right IoT resource at the right time is an indispensible requirement for user application performance. In this paper, we propose a framework for returning the most pertinent IoT resource based on ranking, as the user query response. Proposed Multi Criteria Decision making framework computes the weights of the various criteria based on fuzzy logic user preference and entropy based objective weight. This computed weights for the criteria are applied on approach Technique for Order Preference by Similarity to Ideal solution (TOPSIS). Effectiveness of the proposed approach is compared with current state of work. Also real time testbed experiment based study is carried out to demonstrate the effectiveness and robustness of proposed approach.

show abstract

Section: Implementation and Results Discussionmentioning

confidence: 99%

Section: Proposed Iot Resource Discovery and Ranking Modelmentioning

confidence: 99%

MULTI CRITERIA DECISION BASED RANKED DISCOVERY FRAMEWORK FOR IoT RESOURCESN

Chikkamannur¹

2021

INDJCSE

View full text Add to dashboard Cite

show abstract

“…Fuzzy sets are often used to reflect the inherent subjectivity and imprecision in evaluation processes (Tavana and Sodenkamp 2010), with the linguistic variables of fuzzy logic lending themselves to representing human preferences for example in multi-criteria decision analysis (Yatsalo et al 2017;Dilli et al 2018;Ajibade et al 2019;Das and Pal 2020). As fuzzy logic and fuzzy thinking are suitable for the representation of knowledge, or even intuition, the proposed method is designed to make use of knowledge which can be valuable to improve the assessment of biodiversity in LCA.…”

Section: Development Of the Field Equationmentioning

confidence: 99%

Moving beyond land use intensity types: assessing biodiversity impacts using fuzzy thinking

Lindner

Eberle

Knuepffer

et al. 2021

Int J Life Cycle Assess

View full text Add to dashboard Cite

Purpose The impact of land use on biodiversity is a topic that has received considerable attention in life cycle assessment (LCA). The methodology to assess biodiversity in LCA has been improved in the past decades. This paper contributes to this progress by building on the concept of conditions for maintained biodiversity. It describes the theory for the development of mathematical functions representing the impact of land uses and management practices on biodiversity. Methods The method proposed here describes the impact of land use on biodiversity as a decrease in biodiversity potential, capturing the impact of management practices. The method can be applied with weighting between regions, such as ecoregions. The biodiversity potential is calculated through functions that describe not only parameters which are relevant to biodiversity, for example, deadwood in a forest, but also the relationships between those parameters. For example, maximum biodiversity would hypothetically occur when the nutrient balance is ideal and no pesticide is applied. As these relationships may not be readily quantified, we propose the use of fuzzy thinking for biodiversity assessment, using AND/OR operators. The method allows the inclusion of context parameters that represent neither the management nor the land use practice being investigated, but are nevertheless relevant to biodiversity. The parameters and relationships can be defined by either literature or expert interviews. We give recommendations on how to create the biodiversity potential functions by providing the reader with a set of questions that can help build the functions and find the relationship between parameters. Results and discussion We present a simplified case study of paper production in the Scandinavian and Russian Taiga to demonstrate the applicability of the method. We apply the method to two scenarios, one representing an intensive forestry practice, and another representing lower intensity forestry management. The results communicate the differences between the two scenarios quantitatively, but more importantly, are able to provide guidance on improved management. We discuss the advantages of this condition-based approach compared to pre-defined intensity classes. The potential drawbacks of defining potential functions from industry-derived studies are pointed out. This method also provides a less strict approach to a reference situation, consequently allowing the adequate assessment of cases in which the most beneficial biodiversity state is achieved through management practices. Conclusions The originality of using fuzzy thinking is that it enables land use management practices to be accounted for in LCA without requiring sub-categories for different intensities to be explicitly established, thus moving beyond the classification of land use practices. The proposed method is another LCIA step toward closing the gap between land use management practices and biodiversity conservation goals.

show abstract

“…It deals with approximation rather than precision. Fuzzy logic also provides a medium to represent linguistic variables (in natural language) that in-turn express human's reasoning capabilities [8]. Let us take an example from an IoT search requirement scenario to better understand the importance of fuzzy logic and how its association with context parameters uplifts the competence of the search system.…”

Section: Fuzzy Logic and Its Importance In Iotmentioning

confidence: 99%

Context-Oriented User-Centric Search System for the IoT Based on Fuzzy Clustering

Pattar¹,

Cr²,

Vala³

et al. 2020

Advances in Computational Intelligence, Security and Internet of Things

View full text Add to dashboard Cite

The Internet of Things (IoT) paradigm envisions to support the creation of several applications that aids in the betterment of the society from various sectors such as environment, finance, industry etc. These applications are to be user-centric for their larger acceptance by the society. With the increase in the number of sensors that should are getting connected to the IoT infrastructure, there is an augmented increase in the amount of data generated by these sensors. Therefore it becomes a fundamental requirement to search for the sensors that produce the most applicable data required by the application. In this regard, context parameters of the sensors and the application users can be utilized to effectively filter out sensors from a large group. This paper proposes a sensor search scheme based on semantic-weights and fuzzy clustering. We have modified the traditional fuzzy c-means clustering algorithm by incorporating the semantic and context attributes of the sensors to obtain fuzzy clusters. During the query resolution phase, the query is directed to the most appropriate cluster. These clusters are formed through the use of linguistic variables rather than quantitative attributes and thus aid in effective user-centric search results. Experimental results indicate that the proposed scheme achieves better performance when compared to the existing techniques.

show abstract

Fuzzy logic and MCDA in IoT resources classification

Cited by 12 publications

References 4 publications

MULTI CRITERIA DECISION BASED RANKED DISCOVERY FRAMEWORK FOR IoT RESOURCESN

MULTI CRITERIA DECISION BASED RANKED DISCOVERY FRAMEWORK FOR IoT RESOURCESN

Moving beyond land use intensity types: assessing biodiversity impacts using fuzzy thinking

Context-Oriented User-Centric Search System for the IoT Based on Fuzzy Clustering

Contact Info

Product

Resources

About