Fingerprint-based location positoning using improved KNN

Liang, Xiaomei; Gou, Xuerong; Liu, Yong

doi:10.1109/icnidc.2012.6418711

Cited by 26 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the inappropriate choice of K value leads to the bad performance of classification. An improved KNN algorithm is introduced in literature [25]. The method mainly improves the KNN algorithm by the calculation of feature weights and distance weights.…”

Section: Weighed Knn Video Semantic Analysis Based On Optimizatimentioning

confidence: 99%

“…The classification recognition precision of video features for different methods are shown in Table I when we set the size of dictionary with 49 144 u , 0 T with [10,15,20,25,30].During the experiment, the recognition results of the following methods are compared: classify the sparse representation video features processed by KSVD dictionary optimization algorithm with SVM method (KSVD-SVM), classify the sparse representation video features processed by kernel discriminative KSVD dictionary optimization algorithm with SVM method (KDKSVD-SVM) and classify the sparse representation video features processed …”

Section: T Valuesmentioning

confidence: 99%

See 1 more Smart Citation

A Video Semantic Analysis Method Based on Kernel Discriminative Sparse Representation and Weighted KNN

Shan

Zhan

Mao

et al. 2013

2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical A

View full text Add to dashboard Cite

To improve the classification performance of sparse representation features, a method of video semantic analysis based on kernel discriminative sparse representation and weighted KNN is proposed in this paper. A discriminative model is built by introducing kernel category function to KSVD dictionary optimization algorithm, mapping the sparse representation features into high-dimensional space. Then the optimal dictionary is generated and applied to compute the sparse representation coefficients of video features. Finally, the video semantic analysis is made by means of weighed KNN method based on optimization sparse representation. Before the video semantic analysis, genetic algorithm is used to get global optimal features and reduce the dimension. Furthermore, the kernel function is introduced to establish discrimination about sparse representation features and the classification vote result is weighed, the purpose of which is to improve the accuracy and rationality of video semantic analysis. The experimental results show that the proposed method significantly improves the discrimination of sparse representation features and is 22.33% higher in accuracy compared with the traditional SVM method based on KSVD. The method is suitable for the classification of video features with nonlinear relationship, tolerating not only the noise but also interference problems in video shot.

show abstract

Section: Weighed Knn Video Semantic Analysis Based On Optimizatimentioning

confidence: 99%

Section: T Valuesmentioning

confidence: 99%

A Video Semantic Analysis Method Based on Kernel Discriminative Sparse Representation and Weighted KNN

Shan

Zhan

Mao

et al. 2013

2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical A

View full text Add to dashboard Cite

show abstract

“…In this paper, we further develop the researches on RSSI-based fingerprint positioning schemes, which were presented in the references [10,11,12,13]. In data collection, the feedback filter is used to obtain reliable and stable RSSI values.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it is difficult to get a suitable signal transmission when indoor environment is complicated and changeable. There are many different indoor positioning methods for wireless network [1], for example, time-based positioning [2], angle-based positioning [3], received signal strength indicator(RSSI) based modeling positioning [4,5,6] and RSSI-based fingerprint positioning [7,8,9,10,11,12,13]. In current indoor positioning systems, the approaches of RSSI-based modeling positioning and RSSI-based fingerprint positioning are relatively mature.…”

Section: Introductionmentioning

confidence: 99%

“…The researches on fingerprint positioning were presented in the references [10,11,12], where k-nearest neighbor matching algorithm was used to search for K neighbor closest between classes of reference points and locate measured point based on Euclidean distance. However, the estimated values of measured points' coordinates were calculated by averaging the coordinates of valid reference points which may decrease the accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

RSSI-Based Fingerprint Positioning System for Indoor Wireless Network

Yang

Zhang

2014

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. This paper presents a direct explicit method of the fingerprint positioning for indoor wireless network. In data collection, for the purpose of a reliable and stable signal, a feedback filter is added to the sampler. In positioning phase, the location clustering technique is used to exclude invalid reference points. Then a matching algorithm based on RSSI correlation coefficient is proposed, which can improve positioning accuracy. The example in the paper illustrates the effectiveness of the proposed positioning scheme.

show abstract

Indoor localization using FM radio and DTMB signals

Wang

Zhao

et al. 2016

Radio Science

View full text Add to dashboard Cite

Indoor localization systems based on Wi‐Fi signal strength fingerprinting techniques are widely used in office buildings. However, a general problem of these systems pertains to Wi‐Fi signal degradation due to the environmental factors. And also, these systems cannot be used in the environments not covered with Wi‐Fi signals or the environments with only a single Wi‐Fi access point. In this paper, a new indoor location fingerprinting system using both FM radio and Digital Television Terrestrial Multimedia Broadcasting (DTMB) signals is proposed. First, the indoor location fingerprinting using FM radio and DTMB signals is theoretically analyzed to confirm its feasibility. Then, a specially designed combined strength fingerprinting location algorithm is proposed for the location system, which is achieved on the USRP2 platform. Finally, the system is tested in a typical indoor environment. The theoretical analysis and the tests show that the indoor location fingerprinting system using FM radio and DTMB signals has a similar localization accuracy to the Wi‐Fi signal strength fingerprinting location system, while it has a wider coverage area, a lower maintenance cost, and more stable signal strength, which makes it a practical indoor positioning method.

show abstract

Fingerprint-based location positoning using improved KNN

Cited by 26 publications

References 7 publications

A Video Semantic Analysis Method Based on Kernel Discriminative Sparse Representation and Weighted KNN

A Video Semantic Analysis Method Based on Kernel Discriminative Sparse Representation and Weighted KNN

RSSI-Based Fingerprint Positioning System for Indoor Wireless Network

Indoor localization using FM radio and DTMB signals

Contact Info

Product

Resources

About