This paper presents a robust distributed weighted least-square scaling localization algorithm based on the local network feature. It first filters out 1-hop gross ranging errors of the unknown nodes by using the threshold parameters of extreme ranging overestimates and extreme ranging underestimate with the local network feature, and then employs Gauss-kernel- weighted least squares to position nodes. Simulation results confirm that this localization scheme outperforms traditional weighted least squares, which does not adopt outlier identification scheme. The localization accuracy of the unknown nodes which are directly related to the outliers improves remarkably.
In the recent years, the availability of accurate vehicle position becomes more urgent. The global navigation satellite systems/inertial navigation system (GNSS/INS) is the most used integrated navigation scheme for land vehicles, which utilizes the Kalman filter (KF) to optimally fuse GNSS measurement and INS prediction for accurate and robust localization. However, the uncertainty of the process noise covariance and the measurement noise covariance has a significant impact on Kalman filtering performance. Traditional KF-based integrated navigation methods configure the process noise covariance and measurement noise covariance with predefined constants, which cannot adaptively characterize the various and dynamic environments, and obtain accurate and continuous positioning results under complex environments. To obtain accurate and robust localization results under various complex and dynamic environments, in this article, we propose a novel noise covariance estimation algorithm for the GNSS/INS-integrated navigation using multitask learning model, which can simultaneously estimate the process noise covariance and measurement noise covariance for the KF. The predicted multiplication factors are used to dynamically scale process noise covariance matrix and measurement noise covariance matrix respectively according to the inputs of raw inertial measurement. Extensive experiments are conducted on our collected practical road data set under three typical complex urban scenarios, such as, avenues, viaducts, and tunnels. Experimental results demonstrate that compared with the traditional KF-based integrated navigation algorithm with predefined fixed settings, our proposed method reduces 77.13% positioning error.
The existing localization technology with single mode is limited in accuracy and robustness. To obtain higher accuracy, this paper proposes a novel indoor localization algorithm with WI-FI and Bluetooth. The approach is based on the Bayesian filtering and performs data-level fusion to get the final position estimate. In addition, idea of simulated annealing algorithm is learned into it that makes our algorithm can find the global optimal value in probability. Experimental results demonstrate that the proposed localization algorithm outperforms the single mode localization with accuracy and robustness.
Pedestrian navigation with daily smart devices has become a vital issue over the past few years and the accurate heading estimation plays an essential role in it. Compared to the pedestrian dead reckoning (PDR) based solutions, this article constructs a scalable error model based on the inertial navigation system and proposes an adaptive heading estimation algorithm with a novel method of relative static magnetic field detection. To mitigate the impact of magnetic fluctuation, the proposed algorithm applies a two-way Kalman filter process. Firstly, it achieves the historical states with the optimal smoothing algorithm. Secondly, it adjusts the noise parameters adaptively to reestimate current attitudes. Different from the pedestrian dead reckoning-based solution, the error model system in this article contains more state information, which means it is more sensitive and scalable. Moreover, several experiments were conducted, and the experimental results demonstrate that the proposed heading estimation algorithm obtains better performance than previous approaches and our system outperforms the PDR system in terms of flexibility and accuracy.
Recent years, the use of widely covered Wi-Fi signal to achieve accurate indoor positioning has become a research hotspot. The Wi-Fi Positioning Algorithm based on the existing RF Fingerprint can obtain high positioning accuracy, but there is a big shortage of large deployment and maintenance cost. In order to reduce the cost of Wi-Fi fingerprints collection, this paper utilizes the RSS collected by the consumers using the mobile phone for electronic payment, constructs the low cost crowdsourcing Wi-Fi RF Fingerprint, and realizes the shop-level accurate positioning with CNN. Based on the feature of CNN extraction from local to global, this paper constructs a characteristic group which includes signal intensity, user transaction time and shop information. The statistics of each feature in the statistical interval are obtained by using the interval of 1 to 23 days before the current time. The Min-Max normalization of the statistical value is to avoid inconsistencies in the data distribution caused by the loss of data. In this way, the feature map of window length and statistic feature is constructed, the different feature groups of Wi-Fi and Shop are used as input matrices of multiple CNN, then the other manual features are combined to train a CNN positioning classifier to realize the position estimation of shop-level. A large number of experimental data tests show that the proposed algorithm can obtain higher positioning accuracy by 91% compared with the positioning algorithm based on LR(Logistic Regression), AdaBoost and XGBoost.
Recent rapid rise of indoor location based services for smartphones has further increased the importance of precise localization of Wi-Fi Access Point (AP). However, most existing AP localization algorithms either exhibit high errors or need specialized hardware in practical scenarios. In this paper, we propose a novel RSSI gradient-based AP localization algorithm. It consists of the following three major steps: firstly, it uses the local received signal strength variations to estimate the direction (minus gradient) of AP, then employs a direction clustering method to identify and filter measurement outliers, and finally adopts triangulation method to localize AP with the selected gradient directions. Experimental results demonstrate that the average localization error of our proposed algorithm is less than 2 meters, far outperforming that of the weighted centroid approach.
Wireless sensor networks (WSN) is uniquely characterized by its limited resources and often deployed in remote and harsh environments. It is highly dynamic, prone to faults and usually kept unattended. Therefore, proper management of WSN and its limited resources is highly desirable for an effective and efficient functioning of the network. By introducing state machines and publish/subscribe scheme, a light-weight and dynam- ically reconfigurable management architecture for WSN is proposed, which is called DRMA. By dynamically config- uring the data collection mode and processing method, it supports application dynamics and new application addi- tions, which in practice are very desirable to make applica- tions better meet a big diversity of real needs. The result of simulation shows that DRMA can collection and process data timely and accurately.
Stride length and walking distance estimation are becoming a key aspect of many applications. One of the methods of enhancing the accuracy of pedestrian dead reckoning is to accurately estimate the stride length of pedestrians. Existing stride length estimation (SLE) algorithms present good performance in the cases of walking at normal speed and the fixed smartphone mode (handheld). The mode represents a specific state of the carried smartphone. The error of existing SLE algorithms increases in complex scenes with many mode changes. Considering that stride length estimation is very sensitive to smartphone modes, this paper focused on combining smartphone mode recognition and stride length estimation to provide an accurate walking distance estimation. We combined multiple classification models to recognize five smartphone modes (calling, handheld, pocket, armband, swing). In addition to using a combination of time-domain and frequency-domain features of smartphone built-in accelerometers and gyroscopes during the stride interval, we constructed higher-order features based on the acknowledged studies (Kim, Scarlett, and Weinberg) to model stride length using the regression model of machine learning. In the offline phase, we trained the corresponding stride length estimation model for each mode. In the online prediction stage, we called the corresponding stride length estimation model according to the smartphone mode of a pedestrian. To train and evaluate the performance of our SLE, a dataset with smartphone mode, actual stride length, and total walking distance were collected. We conducted extensive and elaborate experiments to verify the performance of the proposed algorithm and compare it with the state-of-the-art SLE algorithms. Experimental results demonstrated that the proposed walking distance estimation method achieved significant accuracy improvement over existing individual approaches when a pedestrian was walking in both indoor and outdoor complex environments with multiple mode changes.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)