scholarly journals WiFi Indoor Localization with CSI Fingerprinting-Based Random Forest

Sensors ◽  
2018 ◽  
Vol 18 (9) ◽  
pp. 2869 ◽  
Author(s):  
Yanzhao Wang ◽  
Chundi Xiu ◽  
Xuanli Zhang ◽  
Dongkai Yang
Keyword(s):  
Random Forest ◽  
Nearest Neighbor ◽  
Indoor Localization ◽  
Multipath Fading ◽  
Wireless Channel ◽  
K Nearest Neighbor ◽  
Channel State ◽  
Memory Space ◽  
Positioning Systems ◽  
Localization Performance

WiFi fingerprinting indoor positioning systems have extensive applied prospects. However, a vast amount of data in a particular environment has to be gathered to establish a fingerprinting database. Deficiencies of these systems are the lack of universality of multipath effects and a burden of heavy workload on fingerprint storage. Thus, this paper presents a novel Random Forest fingerprinting localization (RFFP) method using channel state information (CSI), which utilizes the Random Forest model trained in the offline stage as fingerprints in order to economize memory space and possess a good anti-multipath characteristic. Furthermore, a series of specific experiments are conducted in a microwave anechoic chamber and an office to detail the localization performance of RFFP with different wireless channel circumstances, system parameters, algorithms, and input datasets. In addition, compared with other algorithms including K-Nearest-Neighbor (KNN), Weighted K-Nearest-Neighbor (WKNN), REPTree, CART, and J48, the RFFP method provides far greater classification accuracy as well as lower mean location error. The proposed method offers outstanding comprehensive performance including accuracy, robustness, low workload, and better anti-multipath-fading.

scholarly journals SDR Based Indoor Beacon Localization Using 3D Probabilistic Multipath Exploitation and Deep Learning

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1323 ◽  
Author(s):  
Donald L. Hall ◽  
Ram M. Narayanan ◽  
David M. Jenkins
Keyword(s):  
Deep Learning ◽  
Software Defined Radio ◽  
High Performance ◽  
Nearest Neighbor ◽  
Indoor Localization ◽  
Signal Propagation ◽  
Multipath Channel ◽  
K Nearest Neighbor ◽  
Positioning Systems ◽  
Channel Characteristics

Wireless indoor positioning systems (IPS) are ever-growing as traditional global positioning systems (GPS) are ineffective due to non-line-of-sight (NLoS) signal propagation. In this paper, we present a novel approach to learning three-dimensional (3D) multipath channel characteristics in a probabilistic manner for providing high performance indoor localization of wireless beacons. The proposed system employs a single triad dipole vector sensor (TDVS) for polarization diversity, a deep learning model deemed the denoising autoencoder to extract unique fingerprints from 3D multipath channel information, and a probabilistic k-nearest-neighbor (PkNN) to exploit the 3D multipath characteristics. The proposed system is the first to exploit 3D multipath channel characteristics for indoor wireless beacon localization via vector sensing methodologies, a software defined radio (SDR) platform, and multipath channel estimation.

scholarly journals Random Forest-based Fingerprinting Technique for Device-free Indoor Localization System

2021 ◽  
pp. 79-96
Author(s):  
Dwi Suroso ◽  
Refa Rupaksi ◽  
Aditya Krisnawan ◽  
Nur Siddiq
Keyword(s):  
Random Forest ◽  
Nearest Neighbor ◽  
Indoor Localization ◽  
Random Forest Algorithm ◽  
K Nearest Neighbor ◽  
Received Signal Strength Indicator ◽  
Actual Measurement ◽  
Artificial Neural Network Ann ◽  
Device Free ◽  
Simple Parameter

The device-free indoor localization (DFIL) research is gaining attention due to the popularity of location-based service (LBS)-based advertisement. In DFIL, a user or an object does not need to bring any device to be localized. In this paper, we propose the Wi-Fi-based DFIL and the random forest algorithm for the fingerprint-based technique. The simple parameter commonly used in indoor localization is the Received Signal Strength Indicator (RSSI). We apply the fingerprint technique because of its reliability to handle the RSSI fluctuation and time-varying effect in a static indoor environment. We conducted an actual measurement campaign to observe the DFIL's implementation visibility. The DFIL system works by comparing the database fingerprint in an empty open office with the database in which a person is inside the measurement area without bringing any devices. Thus, we have the device-free RSSI database for fingerprint technique from both empty rooms and RSSI affected by a person inside the room. We validated the random forest algorithm results by comparing them with the k-nearest neighbor (kNN) and artificial neural network (ANN). The results show that our proposed system's accuracy is better than kNN and ANN with a mean error of 0.63 m than kNN with 0.80 m and ANN with 1.01 m. Meanwhile, the precision of the random forest is 0.63 m, whereas kNN and ANN are 0.67 m and 0.80 m, showing that the random forest performed better. We concluded that our simple DFIL system is visible to apply with acceptable accuracy performance.

scholarly journals Machine Learning Based Indoor Localization using Wi-Fi Fingerprinting

2019 ◽  
Vol 8 (3) ◽  
pp. 502-506
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Nearest Neighbor ◽  
Indoor Localization ◽  
The Internet ◽  
Location Prediction ◽  
K Nearest Neighbor ◽  
Data Types ◽  
Specific Location ◽  
Web Access

The aim of indoor localization is to locate the objects inside a location wirelessly. This paper reports the models that predict the location along with floor and coordinates from the WAPs (Web Access Points) signal strengths of a user who connects to the internet at a specific location which had three locations. Starting with the cleaning of data, then assigning attributes into proper data types, making subset of dataset for each location, examining each column, and normalizing WAPs rows in order to build models. Different algorithms have been used to predict the location, floor, and coordinates of a logged in user. The models that have been used in this paper are k-Nearest Neighbor (k-NN) for location prediction, random forest for floor prediction and regression with k-NN for coordinate prediction.

scholarly journals Evaluation of Three Different Machine Learning Methods for Object-Based Artificial Terrace Mapping—A Case Study of the Loess Plateau, China

2021 ◽  
Vol 13 (5) ◽  
pp. 1021
Author(s):  
Hu Ding ◽  
Jiaming Na ◽  
Shangjing Jiang ◽  
Jie Zhu ◽  
Kai Liu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Loess Plateau ◽  
Water Conservation ◽  
Nearest Neighbor ◽  
Gradient Boosting ◽  
K Nearest Neighbor ◽  
The Loess Plateau ◽  
Object Based ◽  
Extreme Gradient Boosting

Artificial terraces are of great importance for agricultural production and soil and water conservation. Automatic high-accuracy mapping of artificial terraces is the basis of monitoring and related studies. Previous research achieved artificial terrace mapping based on high-resolution digital elevation models (DEMs) or imagery. As a result of the importance of the contextual information for terrace mapping, object-based image analysis (OBIA) combined with machine learning (ML) technologies are widely used. However, the selection of an appropriate classifier is of great importance for the terrace mapping task. In this study, the performance of an integrated framework using OBIA and ML for terrace mapping was tested. A catchment, Zhifanggou, in the Loess Plateau, China, was used as the study area. First, optimized image segmentation was conducted. Then, features from the DEMs and imagery were extracted, and the correlations between the features were analyzed and ranked for classification. Finally, three different commonly-used ML classifiers, namely, extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN), were used for terrace mapping. The comparison with the ground truth, as delineated by field survey, indicated that random forest performed best, with a 95.60% overall accuracy (followed by 94.16% and 92.33% for XGBoost and KNN, respectively). The influence of class imbalance and feature selection is discussed. This work provides a credible framework for mapping artificial terraces.

Quantifying the Influence of Achievement Emotions for Student Learning in MOOCs

2020 ◽  
pp. 073563312096731
Author(s):  
Bowen Liu ◽  
Wanli Xing ◽  
Yifang Zeng ◽  
Yonghe Wu
Keyword(s):  
Random Forest ◽  
Nearest Neighbor ◽  
Online Courses ◽  
Learning Performance ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Achievement Emotions ◽  
Integrative Framework ◽  
Emotional Interaction ◽  
Performance Results

Massive Open Online Courses (MOOCs) have become a popular tool for worldwide learners. However, a lack of emotional interaction and support is an important reason for learners to abandon their learning and eventually results in poor learning performance. This study applied an integrative framework of achievement emotions to uncover their holistic influence on students’ learning by analyzing more than 400,000 forum posts from 13 MOOCs. Six machine-learning models were first built to automatically identify achievement emotions, including K-Nearest Neighbor, Logistic Regression, Naïve Bayes, Decision Tree, Random Forest, and Support Vector Machines. Results showed that Random Forest performed the best with a kappa of 0.83 and an ROC_AUC of 0.97. Then, multilevel modeling with the “Stepwise Build-up” strategy was used to quantify the effect of achievement emotions on students’ academic performance. Results showed that different achievement emotions influenced students’ learning differently. These findings allow MOOC platforms and instructors to provide relevant emotional feedback to students automatically or manually, thereby improving their learning in MOOCs.

scholarly journals Modeling Barrier Island Habitats Using Landscape Position Information

2019 ◽  
Vol 11 (8) ◽  
pp. 976
Author(s):  
Nicholas M. Enwright ◽  
Lei Wang ◽  
Hongqing Wang ◽  
Michael J. Osland ◽  
Laura C. Feher ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Nearest Neighbor ◽  
Learning Algorithms ◽  
Barrier Island ◽  
Barrier Islands ◽  
Machine Learning Algorithms ◽  
Landscape Position ◽  
K Nearest Neighbor ◽  
Island Habitats

Barrier islands are dynamic environments because of their position along the marine–estuarine interface. Geomorphology influences habitat distribution on barrier islands by regulating exposure to harsh abiotic conditions. Researchers have identified linkages between habitat and landscape position, such as elevation and distance from shore, yet these linkages have not been fully leveraged to develop predictive models. Our aim was to evaluate the performance of commonly used machine learning algorithms, including K-nearest neighbor, support vector machine, and random forest, for predicting barrier island habitats using landscape position for Dauphin Island, Alabama, USA. Landscape position predictors were extracted from topobathymetric data. Models were developed for three tidal zones: subtidal, intertidal, and supratidal/upland. We used a contemporary habitat map to identify landscape position linkages for habitats, such as beach, dune, woody vegetation, and marsh. Deterministic accuracy, fuzzy accuracy, and hindcasting were used for validation. The random forest algorithm performed best for intertidal and supratidal/upland habitats, while the K-nearest neighbor algorithm performed best for subtidal habitats. A posteriori application of expert rules based on theoretical understanding of barrier island habitats enhanced model results. For the contemporary model, deterministic overall accuracy was nearly 70%, and fuzzy overall accuracy was over 80%. For the hindcast model, deterministic overall accuracy was nearly 80%, and fuzzy overall accuracy was over 90%. We found machine learning algorithms were well-suited for predicting barrier island habitats using landscape position. Our model framework could be coupled with hydrodynamic geomorphologic models for forecasting habitats with accelerated sea-level rise, simulated storms, and restoration actions.

scholarly journals Application of Deep Convolutional Neural Networks and Smartphone Sensors for Indoor Localization

2019 ◽  
Vol 9 (11) ◽  
pp. 2337 ◽  
Author(s):  
Imran Ashraf ◽  
Soojung Hur ◽  
Yongwan Park
Keyword(s):  
Magnetic Field ◽  
Nearest Neighbor ◽  
Indoor Localization ◽  
Scene Recognition ◽  
Localization Error ◽  
K Nearest Neighbor ◽  
Current Location ◽  
Smartphone Sensors ◽  
The Impact ◽  
Localization Systems

Indoor localization systems are susceptible to higher errors and do not meet the current standards of indoor localization. Moreover, the performance of such approaches is limited by device dependence. The use of Wi-Fi makes the localization process vulnerable to dynamic factors and energy hungry. A multi-sensor fusion based indoor localization approach is proposed to overcome these issues. The proposed approach predicts pedestrians’ current location with smartphone sensors data alone. The proposed approach aims at mitigating the impact of device dependency on the localization accuracy and lowering the localization error in the magnetic field based localization systems. We trained a deep learning based convolutional neural network to recognize the indoor scene which helps to lower the localization error. The recognized scene is used to identify a specific floor and narrow the search space. The database built of magnetic field patterns helps to lower the device dependence. A modified K nearest neighbor (mKNN) is presented to calculate the pedestrian’s current location. The data from pedestrian dead reckoning further refines this location and an extended Kalman filter is implemented to this end. The performance of the proposed approach is tested with experiments on Galaxy S8 and LG G6 smartphones. The experimental results demonstrate that the proposed approach can achieve an accuracy of 1.04 m at 50 percent, regardless of the smartphone used for localization. The proposed mKNN outperforms K nearest neighbor approach, and mean, variance, and maximum errors are lower than those of KNN. Moreover, the proposed approach does not use Wi-Fi for localization and is more energy efficient than those of Wi-Fi based approaches. Experiments reveal that localization without scene recognition leads to higher errors.

scholarly journals Non-Contact Sensing Testbed for Post-Surgery Monitoring by Exploiting Artificial-Intelligence

2020 ◽  
Vol 10 (14) ◽  
pp. 4886 ◽  
Author(s):  
Mohammed Ali Mohammed Al-hababi ◽  
Muhammad Bilal Khan ◽  
Fadi Al-Turjman ◽  
Nan Zhao ◽  
Xiaodong Yang
Keyword(s):  
Artificial Intelligence ◽  
Health Care ◽  
Software Defined Radio ◽  
Orthogonal Frequency Division Multiplexing ◽  
Nearest Neighbor ◽  
Wireless Channel ◽  
Weight Lifting ◽  
K Nearest Neighbor ◽  
Post Surgery ◽  
Contact Sensing

Non-contact health care monitoring is a unique feature in the emerging 5G networks that is achieved by exploiting artificial intelligence (AI). The ratio of the number of health care problems and patients is increasing exponentially and creating burgeoning data. The integration of AI and Internet of things (IoT) systems enables us to increase the huge volume of data to be generated. The approach by which AI is applied to the IoT systems enhances the intelligence of the health care system. In post-surgery monitoring of the patient, timely consultation is essential before further loss. Unfortunately, even after the advice of the doctor to the patient, he/she may forget to perform the activity in the correct way, which may lead to complications in recovery. In this research, the idea is to design a non-contact sensing testbed using AI for the classification of post-surgery activities. Universal software-defined radio peripheral (USRP) is utilized to collect the data of spinal cord operated patients during weight lifting activity. The wireless channel state information (WCSI) is extracted by using orthogonal frequency division multiplexing (OFDM) technique. AI applies machine learning to classify the correct and wrong way of weight lifting activity that was considered for experimental analysis. The accuracy achieved by the proposed testbed by using a fine K-nearest neighbor (FKNN) algorithm is 99.6%.

Sign in / Sign up

Export Citation Format

Share Document