Search

This work advances the machine learning based GNSS positioning by demonstrating the potential of neural network to adapt to different challenging regions, such as dense urban and urban canyon. The adaptive nature of neural networks make it a promising alternative to solve the severe multipath errors in different urban scenarios. Combining both the region adapted neural network and the traditional Kalman Filter based algorithm, better measurement and positioning are performed for a specific urban area. This work integrates the region adapted neural networks with MediaTek's NeuroPilot framework to enable efficient computing on mobile devices. Our implementation deploys a 5-layer Multilayer-Perceptron (46K neurons) on MediaTek's APU 2.0 and achieves real-time performance for typical urban cases of 15 available satellites (4.5ms and 2.7MB memory access). The actual measurement results conclude that neural networks can adapt to urban areas and thus achieve better positioning accuracy (24% and 28% positioning accuracy improvement for Shenzhen and Hsinchu city respectively). Challenging urban areas, including canyons, buildings and dense foliage make the GNSS positioning an extremely complicated task. One of the major interference of GNSS signals is the multipath error, where signals are reflected, refracted and/or absorbed. Such phenomenon results in multiple paths of arrival for a GNSS receiver. Moreover, these harsh conditions get even worse since the environment complexity are highly varied across different cities, such as San Francisco, ShenZhen and HsinChu. This work demonstrates the capability of neural network to adapt to different regions. The adaptive nature of neural networks make it a promising alternative to solve the severe multipath errors in different urban scenarios. In the most of traditional designs, the Kalman Filter has been widely applied to GNSS positioning receiver. The filter performs smoothing, estimating and predicting in a sense of least-square methodology. The objective is to minimize the sum of squared residuals (the difference between a measured value and the fitted value provided by a model). With the assumption of Linear Time-Invariant (LTI) system with Gaussian noises, the result obtaining from Kalman Filter can be considered as an optimized one. However, when performing the positioning for multiple urban scenarios. The major challenge is to continuously adjust the Kalman Filter parameters to adapt to the environment of operation. To improve the accuracy of positioning, this work integrates the region adapted neural networks to refine portions of the GNSS receiver data. These enhanced GNSS receiver data are later feed into Kalman Filter. We propose a new method by applying a 5-layer Multilayer-Perceptron (46K neurons) to classify the quality of satellite signals. In our implementation, such signal quality classification is used to weight the GNSS receiver data. Based on the weighted GNSS receiver data, refined measurements are obtained and further served as the input to the Kalman Filter. As a real implementation of the system, the complexity of the neural network is kept small enough to be fitted into a mobile device which has memory and computation constraint. The proposed region adapted neural networks is evaluated in MediaTek's mobile platform with its NeuroPilot framework. In our implementation, a 5-layer Multilayer-Perceptron (46K neurons) is deployed on MediaTek's APU 2.0. With the processing cores of APU 2.0, the major neural network workloads can be offloaded from the traditional positioning unit. The resultant performance reaches 4.5ms and 2.7MB memory access (for typical urban cases of 15 available satellites), which fulfills the real-time requirement for a positioning system. Moreover, the real evaluation shows 24% and 28% positioning accuracy improvement compared to standard Kalman Filter in the urban areas of Shenzhen and HsinChu city, respectively. In conclusion, this work explores the benefits of using region adapted neural network, and integrate it with Kalman Filter based method to mitigate the effect caused by the corrupted measurements (e.g., multipath errors) in challenging urban areas.

In this article, we are going to discuss how machine learning can be adopted to MediaTek P60 platform in order to increase the capability to against the harsh enviroment, such as dense urban and urban canyon. With the mechanism of machine learning, the receiver will have better chance to identify the abnormality of measurement. These additional information can be provided to the traditional Kalman Filter (KF) based algorithm a better opportunity to select better measurement and mitigate the effect of abnormal measurement. Furthermore, the training result of machine learning might not be exactly the same due to the difference between devices. We are also exploring for the possibility to combine with AI (Artificial Intelligence) computation unit on mobile device in order to achieve the customized learning along with difference devices design. In the most common traditional design, the Kalman Filter (KF) has been widely applied to GNSS positioning receiver in the past decades. The filter plays the rule of smoothing, estimating and predicting in a sense of least-square methodology in order to minimize the sum of squared residuals ( a residuals being: the difference between a measured value and the fitted valued provided by a model). With the assumption of Linear Time-Invariant (LTI) system with Gaussian noises, the result obtaining from KF can be considered as an optimized one. In practical, the KF structure is simple and robust nature of recursive algorithm which is best suited for estimation on the go, instead of implementing a batch-filter when you are processing each measurement whenever it is sampled. This makes the KF one of the best methods to perform estimation on the fly. Also, even though it is rare that the optimal model exist in real-life applications, the filter often works well and appealing for resolving GNSS navigation and data fusion with sensor based measurements in automotive-control problems. As a matter of fact, even though the KF smoothing is also used extensively to correct statistical models of substantial uncertain variables when receivers operating under harsh working environments and tracking the received signal despite of being affected by time-variant signal fading or blockage. The major pursue of GNSS positioning/tracking algorithms is to provide reliable position fixes with optimal design of improved algorithm with special emphasis in their application on mobile terminals, wearable devices and the moving vehicles. The measurements used for fix are often referred to as high-sensitivity GNSS receivers, and the fact of keeping track of the received signal, as signal tracking which are typically sudden fading events with more than tens dB of signal attenuation in urban canyons and with blockage of the line-of-sight signals in moving portable devices. Moreover, in favor of incorporating with manufactures of mass-market GNSS capable devices, simple design on RF components and smaller or more crowded assembly on PCB are becoming important in wearable or capable devices. More wireless interference and in device jamming sources are aggravated when hardware implementation constraints need to be satisfied. In state of the art, the use of extended filter mitigates the measurement noise and allows the tracking operation under these harsh conditions. However, when people need more accurate and robust positioning results, lots of fine-tuned parameters and factor-functional design should be considered. The aim of this work will propose a synthetic machine learning design of a Kalman filter based architecture and evaluate the values for robust and high-sensitivity tracking in a GNSS capable smartphone. The expected results will make the algorithm designers easier to optimize the parameters for platform dependent varieties and make the navigation fix more accurate.

This study presents the signal processing techniques applied on a 9.4/18.8 GHz harmonic radar, which is used to investigate behaviours of small insects such as bees, beetles and butterflies. It is still a challenge to achieve high accuracy and long detection range simultaneously in a harmonic pulse radar system. The authors combine the spread spectrum technology with the classic pulse harmonic radar system to overcome the dilemma between accuracy and detection range. The processing gain of the pseudo-random code from the spread spectrum technology is used to increase the sensitivity and makes the system able to detect the signal with the weak power strength below the system noise level. To eliminate the effect caused by the local leakage, the signal-processing method provided to cancel the leakage through applying the symmetric property of the autocorrelation function of the pseudo-random code. In the field tests, the proposed system achieves a 60 m detection range within 1 m ranging accuracy by using 1.75 W transmitting power corresponding to 40.430 dBW equivalent-isotropically radiated power (EIRP). It is estimated to extend to at least 900 m detection range by using a 3 kW transmitting power corresponding to 72.771 dBW EIRP.

This paper presents a 9.4/18.8-GHz harmonic radar to investigate the behavior of bees with colony collapse disorder. The challenges of using harmonic radar for bee searching include the requirements of high range accuracy and high sensitivity. A new harmonic radar using the pseudorandom code positioning technique to simultaneously achieve high range accuracy and high sensitivity is proposed. This study also proposes a new method to cancel the local leakage to further improve sensitivity. To realize the transponder, a compact antenna is designed using the topology characteristics of the composite right/left-handed transmission-line concept. The measured sensitivity of the transceiver is -120 dBm, which is 27 dB lower than the noise level. Field testing results demonstrate a 60-m detection range within 1-m distance error with 1.75-W transmitting power. The significant improvement of the sensitivity and the range accuracy reveal the advantages of applying the code-positioning technique to the harmonic radar.

We propose a 9.4/18.8 GHz portable harmonic radar for bee searching to investigate colony collapse disorder of bees in the world. This harmonic radar uses Pseudorandom (PRN) code principle to achieve high sensitivity. An analog real time processing circuit for portable application is proposed. This high sensitivity radar can detect the −106 dBm signal, which is 13 dB below the −93 dBm noise level. The field test has been performed to verify the function, and the transponder can be found in the grass within the 1-m distance.

This study focuses on touchless positioning sensing devices using infrared (IR) LED and proximity sensor. The signals from a set of proximity sensors are used to determine the position of the hand through the trilateration method. The distances between hand and sensors can be obtained from proximity sensors. The positioning results of hand are verified over mobile devices. The system allows a user intuitively to interact with the mobile device in real time. This design can waive the necessary of touching the touch panel or screen of mobile device. The experimental results show that the system power consumption is less than 30 mW per minute. The standard deviations of the x-axis and y-axis positioning are 0.06cm and 0.024 cm respectively at a fixed reference point. The maximum range of the z-axis is about 4~15cm in typical indoor ambient light.

A cooperative Wicoxon method is provided in this paper. The Wilcoxon method is used to detect which visible satellites are affected by the reflected signal. A cooperative procedure is combined with the Wilcoxon method by using the communication ability of Vehicular Ad-hoc NETwork (VANET) [1] to mitigate the multipath effect.

This paper demonstrates a 9.4/18.8 GHz harmonic radar for bee searching to investigate the phenomenon of colony collapse disorder (CCD). The radar system transmits a pulsed coarse/acquisition code (C/A code) signal with 0° and 90° shift key modulation and then receives the C/A code signal from transponders attached on the bees in BPSK modulation. Using the technique of C/A code positioning, a distance resolution of 0.15 m is achieved. The transponders are designed to minimize the effect from the bodies of bees. The outdoor experiments indicate the sensitivity of the radar system to be −95 dBm and with the distance of 65 m with 6-W peak power. With 3-kW peak power, the distance at which the bees can be located is expected to be 450 m.