scholarly journals GROF: Indoor Localization Using a Multiple-Bandwidth General Regression Neural Network and Outlier Filter

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3723 ◽  
Author(s):  
Zhang Chen ◽  
Jinlong Wang
Keyword(s):  
Neural Network ◽  
Environmental Changes ◽  
Indoor Localization ◽  
Software Radio ◽  
Indoor Positioning ◽  
General Regression Neural Network ◽  
Generalized Regression Neural Network ◽  
K Nearest Neighbor ◽  
Localization Accuracy ◽  
Practical Applications

In recent years, a variety of methods have been developed for indoor localization utilizing fingerprints of received signal strength (RSS) that are location dependent. Nevertheless, the RSS is sensitive to environmental variations, in that the resulting fluctuation severely degrades the localization accuracy. Furthermore, the fingerprints survey course is time-consuming and labor-intensive. Therefore, the lightweight fingerprint-based indoor positioning approach is preferred for practical applications. In this paper, a novel multiple-bandwidth generalized regression neural network (GRNN) with the outlier filter indoor positioning approach (GROF) is proposed. The GROF method is based on the GRNN, for which we adopt a new kind of multiple-bandwidth kernel architecture to achieve a more flexible regression performance than that of the traditional GRNN. In addition, an outlier filtering scheme adopting the k-nearest neighbor (KNN) method is embedded into the localization module so as to improve the localization robustness against environmental changes. We discuss the multiple-bandwidth spread value training process and the outlier filtering algorithm, and demonstrate the feasibility and performance of GROF through experiment data, using a Universal Software Radio Peripheral (USRP) platform. The experimental results indicate that the GROF method outperforms the positioning methods, based on the standard GRNN, KNN, or backpropagation neural network (BPNN), both in localization accuracy and robustness, without the extra training sample requirement.

scholarly journals DeepLocate: Smartphone Based Indoor Localization with a Deep Neural Network Ensemble Classifier

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 133 ◽  
Author(s):  
Imran Ashraf ◽  
Soojung Hur ◽  
Sangjoon Park ◽  
Yongwan Park
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Indoor Localization ◽  
Ensemble Classifier ◽  
Location Based Services ◽  
Magnetic Data ◽  
Neural Network Ensemble ◽  
Localization Accuracy ◽  
Mean Error ◽  
The Impact

A quickly growing location-based services area has led to increased demand for indoor positioning and localization. Undoubtedly, Wi-Fi fingerprint-based localization is one of the promising indoor localization techniques, yet the variation of received signal strength is a major problem for accurate localization. Magnetic field-based localization has emerged as a new player and proved a potential indoor localization technology. However, one of its major limitations is degradation in localization accuracy when various smartphones are used. The localization performance is different from various smartphones even with the same localization technique. This research leverages the use of a deep neural network-based ensemble classifier to perform indoor localization with heterogeneous devices. The chief aim is to devise an approach that can achieve a similar localization accuracy using various smartphones. Features extracted from magnetic data of Galaxy S8 are fed into neural networks (NNs) for training. The experiments are performed with Galaxy S8, LG G6, LG G7, and Galaxy A8 smartphones to investigate the impact of device dependence on localization accuracy. Results demonstrate that NNs can play a significant role in mitigating the impact of device heterogeneity and increasing indoor localization accuracy. The proposed approach is able to achieve a localization accuracy of 2.64 m at 50% on four different devices. The mean error is 2.23 m, 2.52 m, 2.59 m, and 2.78 m for Galaxy S8, LG G6, LG G7, and Galaxy A8, respectively. Experiments on a publicly available magnetic dataset of Sony Xperia M2 using the proposed approach show a mean error of 2.84 m with a standard deviation of 2.24 m, while the error at 50% is 2.33 m. Furthermore, the impact of devices on various attitudes on the localization accuracy is investigated.

scholarly journals Indoor Positioning System Based on Standardizing Waveform Tendency

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Xiaohua Li ◽  
Ge Yu
Keyword(s):  
Environmental Changes ◽  
Indoor Localization ◽  
Real Life ◽  
Dynamic Environment ◽  
Indoor Positioning ◽  
Positioning System ◽  
Kernel Extreme Learning Machine ◽  
Computationally Intensive ◽  
Learning Machine ◽  
Indoor Positioning System

Estimating the indoor position of users in commercial buildings remains a significant challenge to date. Although the WiFi-based indoor localization has been widely explored in many works by employing received signal strength (RSS) patterns as the features, they usually lead to inaccurate results as the RSS could be easily affected by the indoor environmental dynamics. Besides, existing methods are computationally intensive, which have a high time consumption that makes them unsuitable for real-life applications. In order to deal with those issues, we propose to use standardizing waveform tendency (SWT) of RSS for indoor positioning. We show that the proposed SWT is robust to the noise generated by the dynamic environment. We further develop a novel smartphone indoor positioning system by integrating SWT and kernel extreme learning machine (KELM) algorithm. Extensive real-world positioning experiments are conducted to demonstrate the superiority of our proposed model in terms of both positioning accuracy and robustness to environmental changes when comparing with state-of-the-art baselines.

Generalized Regression Neural Network (GRNN) for the Prediction of CRDI Engine Responses Fuelled with Pongamia Biodiesel

2021 ◽  
Vol 08 (01) ◽  
pp. 5-12
Author(s):  
Nithyananda BS ◽  
Keyword(s):  
Neural Network ◽  
Direct Injection ◽  
Injection Pressure ◽  
Cost Effective ◽  
General Regression Neural Network ◽  
Generalized Regression Neural Network ◽  
Injection Timing ◽  
Performance Parameters ◽  
Performance And Emission ◽  
Testing Dataset

The application of General Regression Neural Network (GRNN) for the prediction of performance and emission responses of Common Rail Direct Injection (CRDI) engine using B5, B10 and B20 blend of pongamia biodiesel is presented in this paper. Data required for the prediction is obtained through experimentation on CRDI engine by varying parameters like injection pressure, injection timing and fuel preheating temperature. The experiments were conducted based on L9 Taguchi Orthogonal Array (OA). The experimental values for performance parameters like brake thermal efficiency, specific fuel consumption and emission parameters like CO, Nox and HC were recorded and used for GRNN. GRNN model is trained with 70% of samples and is validated with testing dataset of 30% by selecting optimum spread parameter (σ). The proposed model was found to be reliable and provides a cost effective way for determining performance parameters of engine. The results presented in this study substantially promote the use of GRNN model for the prediction of parameters in CRDI engine.

scholarly journals An Infrastructure-Free Indoor Localization Algorithm for Smartphones

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3317 ◽  
Author(s):  
Qu Wang ◽  
Haiyong Luo ◽  
Aidong Men ◽  
Fang Zhao ◽  
Yan Huang
Keyword(s):  
Magnetic Field ◽  
Indoor Localization ◽  
Indoor Positioning ◽  
Single Step ◽  
Tracking Algorithm ◽  
Shopping Mall ◽  
Observation Model ◽  
Ambient Light ◽  
Location Based Service ◽  
Localization Accuracy

Accurate indoor positioning technology provides location-based service for a variety of applications. However, most existing indoor localization approaches (e.g., Wi-Fi and Bluetooth-based methods) rely heavily on positioning infrastructure, which prevents their large-scale deployment and limits the range at which they are applicable. Here, we proposed an infrastructure-free indoor positioning and tracking approach, termed LiMag, which used ubiquitous magnetic field and ambient lights (e.g., fluorescent, incandescent, and light-emitting diodes (LEDs)) without containing modulated information. We conducted an in-depth study on both the advantages and the challenges in leveraging magnetic field and ambient light intensity for indoor localization. Based on the insights from this study, we established a hybrid observation model that took full advantage of both the magnetic field and ambient light signals. To address the low discernibility of the hybrid observation model, LiMag first generated a single-step fingerprint model by vectorizing consecutive hybrid observations within each step. In order to accurately track users, a lightweight single-step tracking algorithm based on the single-step fingerprints and the particle filter framework was designed. LiMag leveraged the walking information of users and several single-step fingerprints to generate long trajectory fingerprints that exhibited much higher location differentiation ability than the single-step fingerprint. To accelerate particle convergence and eliminate the accumulative error of single-step tracking algorithm, a long trajectory calibration scheme based on long trajectory fingerprints was also introduced. An undirected weighted graph model was constructed to decrease the computational overhead resulting from this long trajectory matching. In addition to typical indoor scenarios including offices, shopping malls and parking lots, we also conducted experiments in more challenging scenarios, including large open-plan areas as well as environments characterized by strong sunlight. Our proposed algorithm achieved a 75th percentile localization accuracy of 1.8 m and 2.2 m, respectively, in the office and shopping mall tested. In conclusion, our LiMag algorithm provided location-based service of infrastructure-free with significantly improved localization accuracy and coverage, as well as satisfactory robustness inside complex indoor environments.

scholarly journals An RSS Transform—Based WKNN for Indoor Positioning

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5685
Author(s):  
Rong Zhou ◽  
Yexi Yang ◽  
Puchun Chen
Keyword(s):  
Real Time ◽  
Nearest Neighbor ◽  
Environmental Changes ◽  
Indoor Positioning ◽  
Test Point ◽  
Gaussian Kernel ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Positioning Accuracy ◽  
Time Performance

An RSS transform–based weighted k-nearest neighbor (WKNN) indoor positioning algorithm, Q-WKNN, is proposed to improve the positioning accuracy and real-time performance of Wi-Fi fingerprint–based indoor positioning. To smooth the RSS fluctuation difference caused by acquisition equipment, time, and environment changes, base Q is introduced in Q-WKNN to transform RSS to Q-based RSS, based on the relationship between the received signal strength (RSS) and physical distance. Analysis of the effective range of base Q indicates that Q-WKNN is more suitable for regions with noticeable environmental changes and fixed access points (APs). To reduce the positioning time, APs are selected to form a Q-WKNN similarity matrix. Adaptive K is applied to estimate the test point (TP) position. Commonly used indoor positioning algorithms are compared to Q-WKNN on Zenodo and underground parking databases. Results show that Q-WKNN has better positioning accuracy and real-time performance than WKNN, modified-WKNN (M-WKNN), Gaussian kernel (GK), and least squares-support vector machine (LS-SVM) algorithms.

scholarly journals Pattern Layer Reduction for a Generalized Regression Neural Network by Using a Self–Organizing Map

2018 ◽  
Vol 28 (2) ◽  
pp. 411-424 ◽  
Author(s):  
Serkan Kartal ◽  
Mustafa Oral ◽  
Buse Melis Ozyildirim
Keyword(s):  
Neural Network ◽  
Training Data ◽  
General Regression Neural Network ◽  
Training Dataset ◽  
Generalized Regression Neural Network ◽  
Self Organizing Map ◽  
Performance Loss ◽  
Pattern Layer ◽  
Benchmark Test Functions ◽  
Self Organizing

Abstract In a general regression neural network (GRNN), the number of neurons in the pattern layer is proportional to the number of training samples in the dataset. The use of a GRNN in applications that have relatively large datasets becomes troublesome due to the architecture and speed required. The great number of neurons in the pattern layer requires a substantial increase in memory usage and causes a substantial decrease in calculation speed. Therefore, there is a strong need for pattern layer size reduction. In this study, a self-organizing map (SOM) structure is introduced as a pre-processor for the GRNN. First, an SOM is generated for the training dataset. Second, each training record is labelled with the most similar map unit. Lastly, when a new test record is applied to the network, the most similar map units are detected, and the training data that have the same labels as the detected units are fed into the network instead of the entire training dataset. This scheme enables a considerable reduction in the pattern layer size. The proposed hybrid model was evaluated by using fifteen benchmark test functions and eight different UCI datasets. According to the simulation results, the proposed model significantly simplifies the GRNN’s structure without any performance loss.

scholarly journals An Optimized Recursive General Regression Neural Network Oracle for the Prediction and Diagnosis of Diabetes

2018 ◽  
pp. 1-11 ◽  
Author(s):  
Dana Bani-Hani ◽  
Pruthak Patel ◽  
Tasneem Alshaikh
Keyword(s):  
Neural Network ◽  
Performance Metrics ◽  
Prediction Models ◽  
Probabilistic Neural Network ◽  
General Regression Neural Network ◽  
Medical Decision ◽  
Support Vector ◽  
Pima Indians ◽  
K Nearest Neighbor ◽  
General Regression

Diabetes is a serious, chronic disease that has been seeing a rise in the number of cases and prevalence over the past few decades. It can lead to serious complications and can increase the overall risk of dying prematurely. Data-oriented prediction models have become effective tools that help medical decision-making and diagnoses in which the use of machine learning in medicine has increased substantially. This research introduces the Recursive General Regression Neural Network Oracle (RGRNN Oracle) and is applied on the Pima Indians Diabetes dataset for the prediction and diagnosis of diabetes. The R-GRNN Oracle (Bani-Hani, 2017) is an enhancement to the GRNN Oracle developed by Masters et al. in 1998, in which the recursive model is created of two oracles: one within the other. Several classifiers, along with the R-GRNN Oracle and the GRNN Oracle, are applied to the dataset, they are: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Probabilistic Neural Network (PNN), Gaussian Naïve Bayes (GNB), K-Nearest Neighbor (KNN), and Random Forest (RF). Genetic Algorithm (GA) was used for feature selection as well as the hyperparameter optimization of SVM and MLP, and Grid Search (GS) was used to optimize the hyperparameters of KNN and RF. The performance metrics accuracy, AUC, sensitivity, and specificity were recorded for each classifier.

scholarly journals Intrusion Detection Based on Device-Free Localization in the Era of IoT

Symmetry ◽  
2019 ◽  
Vol 11 (5) ◽  
pp. 630 ◽  
Author(s):  
Lingjun Zhao ◽  
Chunhua Su ◽  
Huakun Huang ◽  
Zhaoyang Han ◽  
Shuxue Ding ◽  
...  
Keyword(s):  
Neural Network ◽  
Intrusion Detection ◽  
Nearest Neighbor ◽  
Classification Problem ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Localization Accuracy ◽  
Background Elimination ◽  
Localization Performance ◽  
Device Free

Device-free localization (DFL) locates targets without being equipped with the attached devices, which is of great significance for intrusion detection or monitoring in the era of the Internet-of-Things (IoT). Aiming at solving the problems of low accuracy and low robustness in DFL approaches, in this paper, we first treat the RSS signal as an RSS-image matrix and conduct a process of eliminating the background to dig out the variation component with distinguished features. Then, we make use of these feature-rich images by formulating DFL as an image classification problem. Furthermore, a deep convolutional neural network (CNN) is designed to extract features automatically for classification. The localization performance of the proposed background elimination-based CNN (BE-CNN) scheme is validated with a real-world dataset of outdoor DFL. In addition, we also validate the robust performance of the proposal by conducting numerical experiments with different levels of noise. Experimental results demonstrate that the proposed scheme has an obvious advantage in terms of improving localization accuracy and robustness for DFL. Particularly, the BE-CNN can maintain the highest localization accuracy of 100%, even in noisy conditions when the SNR is over −5 dB. The BE-based methods can outperform all the corresponding raw data-based methods in terms of the localization accuracy. In addition, the proposed method can outperform the comparison methods, deep neural network with autoencoder, K-nearest-neighbor (KNN), support vector machines (SVM), etc., in terms of the localization accuracy and robustness.

scholarly journals Indoor Topological Localization Using a Visual Landmark Sequence

2019 ◽  
Vol 11 (1) ◽  
pp. 73 ◽  
Author(s):  
Jiasong Zhu ◽  
Qing Li ◽  
Rui Cao ◽  
Ke Sun ◽  
Tao Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Environmental Changes ◽  
Indoor Localization ◽  
Temporal Variations ◽  
Indoor Environments ◽  
Topological Map ◽  
Matching Algorithm ◽  
Visual Landmark ◽  
Topological Localization ◽  
Appearance Matching

This paper presents a novel indoor topological localization method based on mobile phone videos. Conventional methods suffer from indoor dynamic environmental changes and scene ambiguity. The proposed Visual Landmark Sequence-based Indoor Localization (VLSIL) method is capable of addressing problems by taking steady indoor objects as landmarks. Unlike many feature or appearance matching-based localization methods, our method utilizes highly abstracted landmark sematic information to represent locations and thus is invariant to illumination changes, temporal variations, and occlusions. We match consistently detected landmarks against the topological map based on the occurrence order in the videos. The proposed approach contains two components: a convolutional neural network (CNN)-based landmark detector and a topological matching algorithm. The proposed detector is capable of reliably and accurately detecting landmarks. The other part is the matching algorithm built on the second order hidden Markov model and it can successfully handle the environmental ambiguity by fusing sematic and connectivity information of landmarks. To evaluate the method, we conduct extensive experiments on the real world dataset collected in two indoor environments, and the results show that our deep neural network-based indoor landmark detector accurately detects all landmarks and is expected to be utilized in similar environments without retraining and that VLSIL can effectively localize indoor landmarks.

Sign in / Sign up

Export Citation Format

Share Document