Junhua Ye - Academia.edu (original) (raw)
Papers by Junhua Ye
IEEE Access, 2021
The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its p... more The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its performance can be degraded in urban environments because of signal reflections or blockages. To address these GNSS outages, pedestrian dead reckoning (PDR) is commonly used due to its significant improvements in both the stability and continuity of positioning, which are dependent on three key factors: continuous absolute position, heading and step information. Signals of opportunity are commonly used in positioning, whereas the installation of Bluetooth low energy (BLE) sensors on lampposts can provide an opportunity for positioning and heading estimation in urban canyons. In this article, a system integrating the GNSS, PDR, and BLE techniques is implemented in smartphones to provide a real-time positioning solution for pedestrians, which includes a new position correction method based on BLE heading, a reliable heading estimation integrating BLE and inertial sensors, an unconstrained step detection method with high accuracy, and an extended Kalman filter (EKF) to integrate multiple sensors and techniques. In several field experiments, with improvements in availability and robustness, the heading accuracy of the proposed fusion approach could reach approximately 3 degrees; the positioning accuracy achieved between 2.7 m and 4.2 m, compared with a 30 m error from the GNSS alone. Simultaneously, this system could achieve a high positioning accuracy of 2.4 m with unconstrained smartphones in a mixed environment. The proposed system has been demonstrated to perform well in urban canyons.
Remote Sensing, Sep 18, 2019
This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combin... more This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combines smart phone internal MEMS sensors, GNSS and beacon observations together. Heading estimation is generally a key issue of the PDR algorithm. We design an orientation fusion algorithm to improve smart phone heading using MEMS measurements. Static and kinematic tests are performed, superiority of the improved heading algorithm is verified. We also present different heading processing solutions for comparison and analysis. Heading bias increases with time due to error accumulation and model inaccuracy. Thus, we develop a related heading calibration method based on beacons. This method can help correct smart phone headings continuously to decrease cumulative error. In addition to PDR, we also use GNSS and beacon measurements to integrate a fusion location. In the fusion procedure, we design related algorithms to adjust or limit the use of these different type observations to constrain large jumps in our Kalman filter model, thereby making the solution stable. Navigation experiments are performed in the streets of Mong Kok and Wanchai, which are typically the most crowded areas of Hong Kong, with narrow streets and many pedestrians, vehicles and tall buildings. The first experiment uses the strategy PDR + GNSS + beacon, in east-west orientation street, in which 10 m positioning error is improved from 30% (smart phone internal GNSS) to 80% and in south-north orientation street, in which 15 m positioning error is improved from 20% (smart phone internal GNSS) to 80%. The second experiment performs two long-distance tests without any beacons, in which the fusion scheme also has significant improvement, that is, 10 m positioning error is improved from 38% to 60%.
Sensors, Apr 30, 2020
Several pedestrian navigation solutions have been proposed to date, and most of them are based on... more Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors' measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods was also used for comparison. Test results show that the accuracy of motion mode recognition was improved from 89.9%, which was the highest accuracy and obtained by SVM (Support Vector Machine), to 90.74% (LSTM) and 91.92% (CNN); the accuracy of smartphone posture recognition was improved from 81.60% , which is the highest accuracy and obtained by NN (Neural Network), to 93.69% (LSTM) and 95.55% (CNN). We give a model transformation procedure based on the trained CNN network model, and then obtain the converted .t f lite model, which can be run in Android devices for real-time recognition. Real-time recognition experiments were performed in multiple scenes, a recognition model trained by the CNN network was deployed in a Huawei Mate20 smartphone, and the five most used pedestrian activities were designed and verified. The overall accuracy was up to 89.39%. Overall, the improvement of recognition capability based on deep learning algorithms was significant. Therefore, the solution was helpful to recognize comprehensive pedestrian activities during navigation. On the basis of the trained model, a navigation test was performed; mean bias was reduced by more than 1.1 m. Accordingly, the positioning accuracy was improved obviously, which is meaningful to apply DL in the area of pedestrian navigation to make improvements.
Journal of Sensors, Dec 24, 2018
Precipitable water vapor (PWV) content detection is vital to heavy rain prediction; up to now, lo... more Precipitable water vapor (PWV) content detection is vital to heavy rain prediction; up to now, lots of different measuring methods and devices are developed to observe PWV. In general, these methods can be divided into two categories, ground-based or spacebased. In this study, we analyze the advantages and disadvantages of these technologies, compare retrieved atmosphere parameters by different RO (radio occultation) observations, like FORMOSAT-3/COSMIC (Formosa Satellite-3 and Constellation Observing System for Meteorology, Ionosphere, and Climate) and FY3C (China Feng Yun 3C), and assess retrieved PWV precision with a radiosonde. Besides, we interpolate PWV from NWP (numerical weather prediction) reanalysis data for more comparison and analysis with RO. Specifically, ground-based GNSS is of high precision and continuous availability to monitor PWV distribution; in our paper, we show cases to validate and compare GNSS retrieving PWV with a radiosonde. Except GNSS PWV, we give two different radio occultation sounding results, COSMIC and FY3C, to validate the precision to monitor PWV from space in a global area. FY3C results containing Beidou (China Beidou Global Satellite Navigation System) radio occultation events need to be emphasized. So, in our study, we get the retrieved atmospheric profiles from GPS and Beidou radio occultation observations and derive atmosphere PWV by a variational retrieval method based on these data over a global area. Besides, other space-based methods, such as microwave satellite, are also useful in detecting PWV distribution situations in a global area from space; in this study, we present a case of retrieved PWV using microwave satellite observation. NWP reanalysis data ECMWF (European Centre for Medium-Range Weather Forecasts) ERA-Interim and the new-generation reanalysis data ERA5 provide global grid atmosphere parameters, like surface temperature, different-level pressures, and precipitable water. We show cases of retrieved PWV and validate the precision with radiosonde results and compare new reanalysis dataset ERA5 with ERA-Interim, finding that ERA5 can get higher precision-retrieved atmosphere parameters and PWV. In the end, from our comparison, we find that the retrieved PWV from RO (FY3C and COSMIC) and ECMWF reanalysis data (ERA-Interim and ERA5) have a high positive correlation and that almost all R 2 values exceed 0.9, compare retrieved PWV with a radiosonde, and find that whether it is RO and ECMWF reanalysis data, ground-based GNSS, or microwave satellite, they all show small biases.
Computers and Electronics in Agriculture
IEEE Internet of Things Journal
Computers and Electronics in Agriculture
Computers and Electronics in Agriculture, 2022
IEEE Access, 2021
The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its p... more The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its performance can be degraded in urban environments because of signal reflections or blockages. To address these GNSS outages, pedestrian dead reckoning (PDR) is commonly used due to its significant improvements in both the stability and continuity of positioning, which are dependent on three key factors: continuous absolute position, heading and step information. Signals of opportunity are commonly used in positioning, whereas the installation of Bluetooth low energy (BLE) sensors on lampposts can provide an opportunity for positioning and heading estimation in urban canyons. In this article, a system integrating the GNSS, PDR, and BLE techniques is implemented in smartphones to provide a real-time positioning solution for pedestrians, which includes a new position correction method based on BLE heading, a reliable heading estimation integrating BLE and inertial sensors, an unconstrained step detection method with high accuracy, and an extended Kalman filter (EKF) to integrate multiple sensors and techniques. In several field experiments, with improvements in availability and robustness, the heading accuracy of the proposed fusion approach could reach approximately 3 degrees; the positioning accuracy achieved between 2.7 m and 4.2 m, compared with a 30 m error from the GNSS alone. Simultaneously, this system could achieve a high positioning accuracy of 2.4 m with unconstrained smartphones in a mixed environment. The proposed system has been demonstrated to perform well in urban canyons.
Sensors, 2020
Several pedestrian navigation solutions have been proposed to date, and most of them are based on... more Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors’ measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods ...
Remote Sensing, 2019
This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combin... more This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combines smart phone internal MEMS sensors, GNSS and beacon observations together. Heading estimation is generally a key issue of the PDR algorithm. We design an orientation fusion algorithm to improve smart phone heading using MEMS measurements. Static and kinematic tests are performed, superiority of the improved heading algorithm is verified. We also present different heading processing solutions for comparison and analysis. Heading bias increases with time due to error accumulation and model inaccuracy. Thus, we develop a related heading calibration method based on beacons. This method can help correct smart phone headings continuously to decrease cumulative error. In addition to PDR, we also use GNSS and beacon measurements to integrate a fusion location. In the fusion procedure, we design related algorithms to adjust or limit the use of these different type observations to constrain larg...
IEEE Internet of Things Journal, Mar 15, 2023
IEEE Access, 2021
The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its p... more The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its performance can be degraded in urban environments because of signal reflections or blockages. To address these GNSS outages, pedestrian dead reckoning (PDR) is commonly used due to its significant improvements in both the stability and continuity of positioning, which are dependent on three key factors: continuous absolute position, heading and step information. Signals of opportunity are commonly used in positioning, whereas the installation of Bluetooth low energy (BLE) sensors on lampposts can provide an opportunity for positioning and heading estimation in urban canyons. In this article, a system integrating the GNSS, PDR, and BLE techniques is implemented in smartphones to provide a real-time positioning solution for pedestrians, which includes a new position correction method based on BLE heading, a reliable heading estimation integrating BLE and inertial sensors, an unconstrained step detection method with high accuracy, and an extended Kalman filter (EKF) to integrate multiple sensors and techniques. In several field experiments, with improvements in availability and robustness, the heading accuracy of the proposed fusion approach could reach approximately 3 degrees; the positioning accuracy achieved between 2.7 m and 4.2 m, compared with a 30 m error from the GNSS alone. Simultaneously, this system could achieve a high positioning accuracy of 2.4 m with unconstrained smartphones in a mixed environment. The proposed system has been demonstrated to perform well in urban canyons.
Remote Sensing, Sep 18, 2019
This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combin... more This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combines smart phone internal MEMS sensors, GNSS and beacon observations together. Heading estimation is generally a key issue of the PDR algorithm. We design an orientation fusion algorithm to improve smart phone heading using MEMS measurements. Static and kinematic tests are performed, superiority of the improved heading algorithm is verified. We also present different heading processing solutions for comparison and analysis. Heading bias increases with time due to error accumulation and model inaccuracy. Thus, we develop a related heading calibration method based on beacons. This method can help correct smart phone headings continuously to decrease cumulative error. In addition to PDR, we also use GNSS and beacon measurements to integrate a fusion location. In the fusion procedure, we design related algorithms to adjust or limit the use of these different type observations to constrain large jumps in our Kalman filter model, thereby making the solution stable. Navigation experiments are performed in the streets of Mong Kok and Wanchai, which are typically the most crowded areas of Hong Kong, with narrow streets and many pedestrians, vehicles and tall buildings. The first experiment uses the strategy PDR + GNSS + beacon, in east-west orientation street, in which 10 m positioning error is improved from 30% (smart phone internal GNSS) to 80% and in south-north orientation street, in which 15 m positioning error is improved from 20% (smart phone internal GNSS) to 80%. The second experiment performs two long-distance tests without any beacons, in which the fusion scheme also has significant improvement, that is, 10 m positioning error is improved from 38% to 60%.
Sensors, Apr 30, 2020
Several pedestrian navigation solutions have been proposed to date, and most of them are based on... more Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors' measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods was also used for comparison. Test results show that the accuracy of motion mode recognition was improved from 89.9%, which was the highest accuracy and obtained by SVM (Support Vector Machine), to 90.74% (LSTM) and 91.92% (CNN); the accuracy of smartphone posture recognition was improved from 81.60% , which is the highest accuracy and obtained by NN (Neural Network), to 93.69% (LSTM) and 95.55% (CNN). We give a model transformation procedure based on the trained CNN network model, and then obtain the converted .t f lite model, which can be run in Android devices for real-time recognition. Real-time recognition experiments were performed in multiple scenes, a recognition model trained by the CNN network was deployed in a Huawei Mate20 smartphone, and the five most used pedestrian activities were designed and verified. The overall accuracy was up to 89.39%. Overall, the improvement of recognition capability based on deep learning algorithms was significant. Therefore, the solution was helpful to recognize comprehensive pedestrian activities during navigation. On the basis of the trained model, a navigation test was performed; mean bias was reduced by more than 1.1 m. Accordingly, the positioning accuracy was improved obviously, which is meaningful to apply DL in the area of pedestrian navigation to make improvements.
Journal of Sensors, Dec 24, 2018
Precipitable water vapor (PWV) content detection is vital to heavy rain prediction; up to now, lo... more Precipitable water vapor (PWV) content detection is vital to heavy rain prediction; up to now, lots of different measuring methods and devices are developed to observe PWV. In general, these methods can be divided into two categories, ground-based or spacebased. In this study, we analyze the advantages and disadvantages of these technologies, compare retrieved atmosphere parameters by different RO (radio occultation) observations, like FORMOSAT-3/COSMIC (Formosa Satellite-3 and Constellation Observing System for Meteorology, Ionosphere, and Climate) and FY3C (China Feng Yun 3C), and assess retrieved PWV precision with a radiosonde. Besides, we interpolate PWV from NWP (numerical weather prediction) reanalysis data for more comparison and analysis with RO. Specifically, ground-based GNSS is of high precision and continuous availability to monitor PWV distribution; in our paper, we show cases to validate and compare GNSS retrieving PWV with a radiosonde. Except GNSS PWV, we give two different radio occultation sounding results, COSMIC and FY3C, to validate the precision to monitor PWV from space in a global area. FY3C results containing Beidou (China Beidou Global Satellite Navigation System) radio occultation events need to be emphasized. So, in our study, we get the retrieved atmospheric profiles from GPS and Beidou radio occultation observations and derive atmosphere PWV by a variational retrieval method based on these data over a global area. Besides, other space-based methods, such as microwave satellite, are also useful in detecting PWV distribution situations in a global area from space; in this study, we present a case of retrieved PWV using microwave satellite observation. NWP reanalysis data ECMWF (European Centre for Medium-Range Weather Forecasts) ERA-Interim and the new-generation reanalysis data ERA5 provide global grid atmosphere parameters, like surface temperature, different-level pressures, and precipitable water. We show cases of retrieved PWV and validate the precision with radiosonde results and compare new reanalysis dataset ERA5 with ERA-Interim, finding that ERA5 can get higher precision-retrieved atmosphere parameters and PWV. In the end, from our comparison, we find that the retrieved PWV from RO (FY3C and COSMIC) and ECMWF reanalysis data (ERA-Interim and ERA5) have a high positive correlation and that almost all R 2 values exceed 0.9, compare retrieved PWV with a radiosonde, and find that whether it is RO and ECMWF reanalysis data, ground-based GNSS, or microwave satellite, they all show small biases.
Computers and Electronics in Agriculture
IEEE Internet of Things Journal
Computers and Electronics in Agriculture
Computers and Electronics in Agriculture, 2022
IEEE Access, 2021
The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its p... more The global navigation satellite system (GNSS) is widely used in smartphone positioning, but its performance can be degraded in urban environments because of signal reflections or blockages. To address these GNSS outages, pedestrian dead reckoning (PDR) is commonly used due to its significant improvements in both the stability and continuity of positioning, which are dependent on three key factors: continuous absolute position, heading and step information. Signals of opportunity are commonly used in positioning, whereas the installation of Bluetooth low energy (BLE) sensors on lampposts can provide an opportunity for positioning and heading estimation in urban canyons. In this article, a system integrating the GNSS, PDR, and BLE techniques is implemented in smartphones to provide a real-time positioning solution for pedestrians, which includes a new position correction method based on BLE heading, a reliable heading estimation integrating BLE and inertial sensors, an unconstrained step detection method with high accuracy, and an extended Kalman filter (EKF) to integrate multiple sensors and techniques. In several field experiments, with improvements in availability and robustness, the heading accuracy of the proposed fusion approach could reach approximately 3 degrees; the positioning accuracy achieved between 2.7 m and 4.2 m, compared with a 30 m error from the GNSS alone. Simultaneously, this system could achieve a high positioning accuracy of 2.4 m with unconstrained smartphones in a mixed environment. The proposed system has been demonstrated to perform well in urban canyons.
Sensors, 2020
Several pedestrian navigation solutions have been proposed to date, and most of them are based on... more Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors’ measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods ...
Remote Sensing, 2019
This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combin... more This study presents a comprehensive urban canyon pedestrian navigation scheme. This scheme combines smart phone internal MEMS sensors, GNSS and beacon observations together. Heading estimation is generally a key issue of the PDR algorithm. We design an orientation fusion algorithm to improve smart phone heading using MEMS measurements. Static and kinematic tests are performed, superiority of the improved heading algorithm is verified. We also present different heading processing solutions for comparison and analysis. Heading bias increases with time due to error accumulation and model inaccuracy. Thus, we develop a related heading calibration method based on beacons. This method can help correct smart phone headings continuously to decrease cumulative error. In addition to PDR, we also use GNSS and beacon measurements to integrate a fusion location. In the fusion procedure, we design related algorithms to adjust or limit the use of these different type observations to constrain larg...
IEEE Internet of Things Journal, Mar 15, 2023