Weighted K-nearest Neighbor Fast Localization Algorithm Based on RSSI for Wireless Sensor Systems

2020 ◽  
Vol 13 (2) ◽  
pp. 295-301
Author(s):  
Lu Bai ◽  
Chenglie Du ◽  
Jinchao Chen
Keyword(s):  
Nearest Neighbor ◽  
Simulation Analysis ◽  
Computation Time ◽  
Wireless Sensor ◽  
Sensor Systems ◽  
Localization Algorithm ◽  
K Nearest Neighbor ◽  
Positioning Accuracy ◽  
Wireless Positioning ◽  
Computationally Intensive

Background: Wireless positioning is one of the most important technologies for realtime applications in wireless sensor systems. This paper mainly studies the indoor wireless positioning algorithm of robots. Methods: The application of the K-nearest neighbor algorithm in Wi-Fi positioning is studied by analyzing the Wi-Fi fingerprint location algorithm based on Received Signal Strength Indication (RSSI) and K-Nearest Neighbor (KNN) algorithm in Wi-Fi positioning. The KNN algorithm is computationally intensive and time-consuming. Results: In order to improve the positioning efficiency, improve the positioning accuracy and reduce the computation time, a fast weighted K-neighbor correlation algorithm based on RSSI is proposed based on the K-Means algorithm. Thereby achieving the purpose of reducing the calculation time, quickly estimating the position distance, and improving the positioning accuracy. Conclusion: Simulation analysis shows that the algorithm can effectively shorten the positioning time and improve the positioning efficiency in robot Wi-Fi positioning.

scholarly journals Indoor Localization Method Based on Regional Division with IFCM

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 559 ◽  
Author(s):  
Junhuai Li ◽  
Xixi Gao ◽  
Zhiyong Hu ◽  
Huaijun Wang ◽  
Ting Cao ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
Indoor Localization ◽  
Pearson Correlation ◽  
Computation Time ◽  
Access Point ◽  
Target Point ◽  
Localization Algorithm ◽  
K Nearest Neighbor ◽  
Localization Method ◽  
Regional Division

With the development of wireless technology, indoor localization has gained wide attention. The fingerprint localization method is proposed in this paper, which is divided into two phases: offline training and online positioning. In offline training phase, the Improved Fuzzy C-means (IFCM) algorithm is proposed for regional division. The Between-Within Proportion (BWP) index is selected to divide fingerprint database, which can ensure the result of regional division consistent with the building plane structure. Moreover, the Agglomerative Nesting (AGNES) algorithm is applied to accomplish Access Point (AP) optimization. In the online positioning phase, sub-region selection is performed by nearest neighbor algorithm, then the Weighted K-nearest Neighbor (WKNN) algorithm based on Pearson Correlation Coefficient (PCC) is utilized to locate the target point. After the evaluation on the effect of regional division and AP optimization of location precision and time, the experiments show that the average positioning error is 2.53 m and the average computation time of the localization algorithm based on PCC reduced by 94.13%.

A Study of Mobile Node Localization Algorithm Based on Ranging MCL for WSN

2012 ◽  
Vol 182-183 ◽  
pp. 2012-2018
Author(s):  
Wei Dong Tang ◽  
Bai Liu ◽  
Chao Qun Zhang ◽  
Jin Zhao Wu
Keyword(s):  
Wireless Sensor Network ◽  
Simulation Analysis ◽  
Mobile Node ◽  
Wireless Sensor ◽  
Motion Model ◽  
Localization Algorithm ◽  
Node Localization ◽  
Node Density ◽  
Positioning Accuracy ◽  
Key Technologies

Node localization is one of the key technologies in wireless sensor network. This paper proposed an improved RBDMCL algorithm based on traditional MCL algorithm, which can reduce the sampling areas and improve the positioning accuracy by building a node motion model. Then concludes by simulation analysis and comparison that RBDMCL has higher positioning accuracy than MCL in the anchor node density and node velocity.

Based on RSSI Ranging Technology for DV-Hop Localization Algorithm of Wireless Sensor Network

2012 ◽  
Vol 442 ◽  
pp. 360-365 ◽  
Author(s):  
Yang Jun Zhong
Keyword(s):  
Wireless Sensor Networks ◽  
Wireless Sensor Network ◽  
Approximate Calculation ◽  
Wireless Sensor ◽  
Localization Algorithm ◽  
Positioning Accuracy ◽  
Original Algorithm ◽  
Approximate Distance ◽  
Anchor Nodes ◽  
Simulation Results

For the DV-Hop algorithm of wireless sensor networks,there is an error arising problem that anchor nodes and location node hop distance is only an approximate calculation. A method based on the original Algorithm introducing RSSI ranging technique is proposed.Using RSSI ranging technology,we accord that if the anchor nodes is only a hop away from the location node,then decide whether using the DV-Hop algorithm to approach to the approximate distance between them. Simulation results show that the algorithm can effectively improve the error problems of calculating the hop distance between the anchor nodes and the location nodes, meanwhile improve the positioning accuracy of the node.

Improved Indoor Geo-Localization System

2019 ◽  
pp. 183-206
Author(s):  
Abdaoui Noura ◽  
Ismahène Hadj Khalifa ◽  
Sami Faiz
Keyword(s):  
Sensor Networks ◽  
Recent Progress ◽  
Nearest Neighbor ◽  
Low Energy ◽  
Wireless Sensor ◽  
Detection Accuracy ◽  
K Nearest Neighbor ◽  
Smart Object ◽  
Low Energy Consumption ◽  
Localization Systems

In the concept of internet of things (IOT), physical position of smart object is very useful for relevant function over sensor networks. However, the invalid information of indoor geo-localization systems relative to these wireless sensor compromises the intelligence of IOT network. Therefore, this chapter produces the recent progress in the indoor geo-localization systems and the IOTs area. It defines the best indoor geo-localization technologies that meet their needs while respecting the constraints related to sensor networks. This framework combines between simplicity of Bluetooth low energy (BLE), popular wi-fi infrastructure, and the k-nearest neighbor (KNN) algorithm (in order to filter the initial fingerprint dataset). This new conception increases real-time detection accuracy and guarantees the low energy consumption.

Improving the Performance of kNN in the MapReduce Framework Using Locality Sensitive Hashing

2019 ◽  
Vol 10 (4) ◽  
pp. 1-16
Author(s):  
Sikha Bagui ◽  
Arup Kumar Mondal ◽  
Subhash Bagui
Keyword(s):  
Nearest Neighbor ◽  
Parallel Implementation ◽  
Block Size ◽  
Computation Time ◽  
Locality Sensitive Hashing ◽  
K Nearest Neighbor ◽  
Mapreduce Framework ◽  
Data Set ◽  
Data Object ◽  
Very Large Datasets

In this work the authors present a parallel k nearest neighbor (kNN) algorithm using locality sensitive hashing to preprocess the data before it is classified using kNN in Hadoop's MapReduce framework. This is compared with the sequential (conventional) implementation. Using locality sensitive hashing's similarity measure with kNN, the iterative procedure to classify a data object is performed within a hash bucket rather than the whole data set, greatly reducing the computation time needed for classification. Several experiments were run that showed that the parallel implementation performed better than the sequential implementation on very large datasets. The study also experimented with a few map and reduce side optimization features for the parallel implementation and presented some optimum map and reduce side parameters. Among the map side parameters, the block size and input split size were varied, and among the reduce side parameters, the number of planes were varied, and their effects were studied.

The Weighted Localization Algorithm Based on RSSI Calibration

2012 ◽  
Vol 236-237 ◽  
pp. 1010-1014
Author(s):  
Ning Hui He ◽  
Hong Sheng Li ◽  
Guang Rong Bian
Keyword(s):  
Wireless Sensor Network ◽  
Signal Strength ◽  
The Other ◽  
Wireless Sensor ◽  
Network Node ◽  
Localization Algorithm ◽  
Node Localization ◽  
Positioning Accuracy ◽  
Location Algorithm ◽  
Beacon Node

This paper introduces the first wireless sensor network node localization in two ways, one is based on the RSSI ranging approach, and the other is based on the weighted centric location algorithm, as a result of environmental factors, the same RSSI value the distance ，but the corresponding values are not always the same, these two methods do not consider the environmental impact to the RSSI value. Therefore, we consider combining the distance and signal strength information as a reference to correct each beacon node weights， in order to improve positioning accuracy.

scholarly journals Automatic amyotrophic lateral sclerosis detection using tunable Q-factor wavelet transform

2020 ◽  
Vol 9 (4) ◽  
pp. 744
Author(s):  
Abdelouahad Achmamad ◽  
Abdelali Belkhou ◽  
Atman Jbari
Keyword(s):  
Amyotrophic Lateral Sclerosis ◽  
Wavelet Transform ◽  
Nearest Neighbor ◽  
Neuromuscular Disorders ◽  
Computation Time ◽  
Support Vector ◽  
Q Factor ◽  
K Nearest Neighbor ◽  
Emg Signal ◽  
Lateral Sclerosis

Early diagnosis of amyotrophic lateral sclerosis (ALS) based on electromyography (EMG) is crucial. The processing of a non-stationary EMG signal requires powerful multi-resolution methods. Our study analyzes and classifies the EMG signals. In the present work, we introduce a novel flexible method for classification of EMG signals using tunable Q-factor wavelet transform (TQWT). Different sub-bands generated by the TQWT technique were served to extract useful information related to energy and then the calculated features were selected using a filter selection (FS) method. The effectiveness of the feature selection step resulted not only in the improvement of classification performance but also in reducing the computation time of the classification algorithm. The selected feature subsets were used as inputs to multiple classifier algorithms, namely, k-nearest neighbor (k-NN), least squares support vector machine (LS-SVM) and random forest (RF) for automated diagnosis. The experimental results show better classification measures with k-NN classifier compared with LS-SVM and RF. The robustness of the classification task was tested using a ten-fold cross-validation method. The outcomes of our proposed approach can be exploited to aid clinicians in neuromuscular disorders detection.

scholarly journals Recognition of The Baby Footprint Characteristics Using Wavelet Method and K-Nearest Neighbor (K-NN)

2021 ◽  
Vol 12 (1) ◽  
pp. 41
Author(s):  
I Made Aris Satia Widiatmika ◽  
I Nyoman Piarsa ◽  
Arida Ferti Syafiandini
Keyword(s):  
Nearest Neighbor ◽  
Individual Recognition ◽  
Computation Time ◽  
K Nearest Neighbor ◽  
Birth Process ◽  
Security Systems ◽  
Wavelet Method ◽  
Biometric Technology ◽  
Test Computation ◽  
Object Feature

Individual recognition using biometric technology can be utilized in creating security systems that are important in modern life. The individuals recognition in hospitals generally done by conventional system so it makes more time in taking identity. A newborn baby will proceed an identity tagging after birth process is complete. This identity using a bracelet filled with names and ink stamps on paper that will be prone to damage or crime. The solution is to store the baby's identity data digitally and carry out the baby's identification process. This system can increase safety and efficiency in storing a baby's footprint image. The implementation of baby's footprint image identification starting from the acquisition of baby's footprint image, preprocessing such as selecting ROI size baby's footprint object, feature extraction using wavelet method and classification process using K-Nearest Neighbor (K-NN) method because this method has been widely used in several studies of biometric identification systems. The test data came from 30 classes with 180 images test right and left baby's footprint. The identification results using 200x500 size ROI with level 4 wavelet decomposition get recognition results with an accuracy of 99.30%, 90.17% precision, and 89.44% recall with a test computation time of 8.0370 seconds.  

Sign in / Sign up

Export Citation Format

Share Document