Kalman Filtering Framework-Based Real Time Target Tracking in Wireless Sensor Networks Using Generalized Regression Neural Networks

Jondhale, Satish R.; Deshpande, Rajkumar S.

doi:10.1109/jsen.2018.2873357

Cited by 109 publications

(61 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the previous work, 12 we have demonstrated how KF framework can refine the estimates trilateration technique irrespective of environmental dynamicity issues such as noise uncertainties in RSSI measurement as well as abrupt changes in target velocity. The sensor nodes are randomly deployed within the square field of size 150 × 150 m at a depth between 3 and 5 cm.…”

Section: Related Workmentioning

confidence: 99%

“…In Gumaida and Luo, 33 a novel Intelligent Water Drops (IWDs) localization algorithm is presented for an outdoor environment. 13,38,39 Yet, another modified GRNN-based algorithm, namely, GRNNα, has also been proven to be effective for 3-D localization. The RSSI is utilized to compute the internode distances.…”

Section: Related Workmentioning

confidence: 99%

“…It is basically a nonlinear optimization approach, which is based on optimizing the objective function in accordance with IWDs. 13,38 In this research work, we have proposed two GRNN-based algorithms, namely, GRNN + KF and GRNN + UKF. In Gumaida and Luo, 34 a novel advanced Particle Swarm Optimization (PSO)-based localization algorithm is presented for the outdoor environment.…”

Section: Related Workmentioning

confidence: 99%

“…39 It can be applied to any nonlinear regression problem surface. 13,38 As shown in Figure 1, the proposed GRNN architecture is composed of four operating layers, namely, an input layer, pattern layer, summation layer, and output layer.…”

Section: Localization Using General Regression Neural Networkmentioning

confidence: 99%

“…13,22,23 The major advantage of ANN-based localization approach is that there is no requirement of prior knowledge of the noise statistics. The lateration method is generally associated with high-localization errors because of inaccurate estimation of distances.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Efficient localization of target in large scale farmland using generalized regression neural network

Jondhale¹,

Deshpande²

2019

Int J Communication

Self Cite

View full text Add to dashboard Cite

Although simple to implement, the traditional trilateration technique is generally associated with significant location estimation errors because of highly nonlinear relationship between Received Signal Strength Indicator (RSSI) and distance. In case of agricultural farmland, there is always noise uncertainty in the RSSI measurements because of signal propagation issues such as NLOS, multipath propagation, and reflection. In the context of such environmental dynamicity, the localization algorithm must be efficient in terms of Localization Accuracy and Execution Speed to provide real-time performance. The Generalized Regression Neural Network (GRNN) is a noniterative highly parallel neural architecture with the capability to get trained quickly using very few training samples. This paper introduces a range free GRNN localization algorithm as an alternative to the traditional range-based trilateration technique for a large scale wheat farmland. This paper also presents the modified Optimal Fitted Parametric Exponential Decay Model (OFPEDM)-based signal path loss model to deal with the issue of environmental dynamicity. The evaluation of localization performance of the trilateration and the proposed GRNN-based approaches is carried out with the help of Wireless Sensor Network (WSN) using three path loss models, namely, Log Normal Shadow Fading (LNSM), Original OFPEDM, and proposed Modified OFPEDM. For all these implementations, the proposed GRNN algorithm demonstrates superior localization performance (localization accuracy of the order of few centimeters) over traditional trilateration irrespective of nonlinear system dynamics, path loss model, and environmental dynamicity. The execution speed of the proposed algorithm is of the order of few milliseconds. KEYWORDS general regression neural network (GRNN), optimal fitted parametric exponential decay model (OFPEDM), received signal strength Indicator (RSSI), wireless sensor network (WSN)

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Localization Using General Regression Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient localization of target in large scale farmland using generalized regression neural network

Jondhale¹,

Deshpande²

2019

Int J Communication

Self Cite

View full text Add to dashboard Cite

show abstract

Low power hardware design and its mathematical modeling for fast‐exact geolocalization system in wireless networks

Zaidi

Bouazzi

Al-Rayif

et al. 2022

Int J Communication

View full text Add to dashboard Cite

Summary A significant goal in achieving position calculation is to reduce and simplify the instructions that the Mobile Station (MS) has to accomplish in the location determination algorithm. Standard techniques widely used in many applications can be classified into Received Signal Strength Indicator (RSSI), Angle of Arrival (AoA), Time Difference of Arrival (TDoA), and Time of Arrival (ToA). However, all are almost determined by the standard trigonometric complex computation methods that are usually implemented in software where the complexity is considerable. The development of a simple and efficient technique for MS location estimation is the main objective of this paper. To design a modern hardware‐oriented algorithm, a new approach using simple Add‐and‐Shift operations in the computation is proposed and it can be implemented in a hardware target. In order to accelerate the geopositioning process, the Coordinate Rotation Digital Computer (CORDIC) algorithm has been used in this proposal. The proposed algorithm is simpler and faster than conventional ones; thus, complexity in terms of time, power consumption, and chip area has been reduced. Therefore, the algorithm is suitable for applications with limited computational and power resources. Based on comparisons with the state‐of‐the‐art algorithms, it is concluded that the proposed technique is more exact and less complex.

show abstract

Application of Supervised Learning Approach for Target Localization in Wireless Sensor Network

Jondhale¹,

Shubair²,

Labade³

et al. 2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Kalman Filtering Framework-Based Real Time Target Tracking in Wireless Sensor Networks Using Generalized Regression Neural Networks

Cited by 109 publications

References 25 publications

Efficient localization of target in large scale farmland using generalized regression neural network

Efficient localization of target in large scale farmland using generalized regression neural network

Low power hardware design and its mathematical modeling for fast‐exact geolocalization system in wireless networks

Application of Supervised Learning Approach for Target Localization in Wireless Sensor Network

Contact Info

Product

Resources

About