A Fuzzy Logic-Based System for Indoor Localization Using WiFi in Ambient Intelligent Environments

García-Valverde, Teresa; García-Sola, Alberto; Hagras, Hani; Dooley, James; Callaghan, Vic; Botía, Juan A.

doi:10.1109/tfuzz.2012.2227975

Cited by 73 publications

(33 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, soft techniques have been used to develop both range-based and range-free localization estimation methods 11,12,13,14,15,16 22,23,26 . While calculating the location of a sensor of unknown location using nodes with known locations, the weight parameter is used to increase the impact of the node with the highest RSSI value on location determination.…”

Section: Fig1 Localization Algorithmsmentioning

confidence: 99%

Intelligent Centroid Localization Based on Fuzzy Logic and Genetic Algorithm

Tuncer¹

2017

IJCIS

View full text Add to dashboard Cite

For many of the applications in which wireless sensor networks are used, it is important to know from which nodes or what location useful information is acquired. The Global Positioning System (GPS) is conventionally used to determine location. However, GPS systems are not ideal for many applications due to their excessive power consumption and high cost. As an alternative to GPS, distance and location can be estimated through the usage of at least 3 nodes with known locations. Received Signal Strength Indication (RSSI) is the simplest and most inexpensive technique used to determine distance and location, and is a standard feature on every sensor. However, RSSI can be affected by noise and environmental obstacles. For this reason, it is difficult to set up a mathematical model for RSSI. This paper presents a conversion of the Centroid Localization (CL) method in determining the location of a sensor of unknown location to the Intelligent Centroid Localization (ICL) Method. Fuzzy logic and genetic algorithm are employed in the ICL method. RSSI values measured by anchor nodes are applied as inputs to the fuzzy system in the ICL developed. Anchor nodes have been assigned weight values to increase the effect of high-value RSSI nodes in positioning. Therefore the fuzzy system's output is defined as weight (w). The base values of the fuzzy system's output membership functions are adjusted using genetic algorithm to minimize location error. Toward observing the performance of the proposed ICL, comparisons with the both Centroid Localization method and APIT (Approximate Point In Triangle) algorithm have been provided. The localization error has been reduced to minimum levels.

show abstract

Section: Fig1 Localization Algorithmsmentioning

confidence: 99%

Intelligent Centroid Localization Based on Fuzzy Logic and Genetic Algorithm

Tuncer¹

2017

IJCIS

View full text Add to dashboard Cite

show abstract

“…Nowadays, with the developments in computer technology, and software engineering, the conventional trial and error approach has been replaced with modern computational techniques that provide important criteria such as the coverage of objects, collision of antennas, and number of antennas [15]. Computational evolutionary techniques such as Artificial Neural Networks [16], Fuzzy Logic [17], Genetic Algorithms (GA) [10,11,18], particle swarm optimization (PSO) [13,19,20], differential evolution (DE) [9], and hierarchical artificial bee colony algorithm [8] are points of interest for many scientists working with the RNP problem. In this respect, Han and Jie [21] proposed a novel optimization algorithm, namely, the multicommunity GA-PSO, for solving the problem of complicated RNP.…”

Section: Introductionmentioning

confidence: 99%

Introducing a Novel Hybrid Artificial Intelligence Algorithm to Optimize Network of Industrial Applications in Modern Manufacturing

Azizi

2017

Complexity

View full text Add to dashboard Cite

Recent advances in modern manufacturing industries have created a great need to track and identify objects and parts by obtaining real-time information. One of the main technologies which has been utilized for this need is the Radio Frequency Identification (RFID) system. As a result of adopting this technology to the manufacturing industry environment, RFID Network Planning (RNP) has become a challenge. Mainly RNP deals with calculating the number and position of antennas which should be deployed in the RFID network to achieve full coverage of the tags that need to be read. The ultimate goal of this paper is to present and evaluate a way of modelling and optimizing nonlinear RNP problems utilizing artificial intelligence (AI) techniques. This effort has led the author to propose a novel AI algorithm, which has been named "hybrid AI optimization technique," to perform optimization of RNP as a hard learning problem. The proposed algorithm is composed of two different optimization algorithms: Redundant Antenna Elimination (RAE) and Ring Probabilistic Logic Neural Networks (RPLNN). The proposed hybrid paradigm has been explored using a flexible manufacturing system (FMS), and results have been compared with Genetic Algorithm (GA) that demonstrates the feasibility of the proposed architecture successfully.

show abstract

“…This imprecision that T1FSs represent is in the form of membership functions, or linguistic values, and it is a powerful tool which is still widely used, for example, in synthetic aperture radar image change detection (Gong, Su, Jia, & Chen, 2014), conditional density estimation by using probabilistic fuzzy systems (van den Berg, Kaymak, & Almeida, 2013), predictive control of direct methanol fuel cells (W. Yang, Feng, & Zhang, 2014), fuzzy clustering via a granular gravitational technique (Sanchez, Castillo, Castro, & Melin, 2014), a support system for sellers in e-marketplaces (Kolomvatsos, Anagnostopoulos, & Hadjiefthymiades, 2014), image segmentation (Othman, Tizhoosh, & Khalvati, 2014), distributed filtering in sensor networks (Su, Wu, & Shi, 2013), indoor localization using WiFi (Garcia-Valverde et al, 2013), etc. Research in T1FLS is still ongoing despite the existence of more advanced FS representations (IT2FS and GT2FS), partly due to the fact that not all decision making situations require such advanced representations and T1FS…”

Section: Introductionmentioning

confidence: 99%