Yingdong Wang;Tiantian Liang;Jianxiong Yang;Jian Liu
An adaptive finite time composite fault tolerant control strategy based on an optimized neural network for Attitude control systems (ACSs) of satellites is proposed considering the state time-varying delays, concurrent actuator and sensor faults, system uncertainties, modelable external disturbance and operating noise. An uncertain time-varying state space model for ACSs of satellites is established, and sensor faults are equivalent to actuator-like faults. A disturbance observer is designed for estimating the modelable external disturbance, and an improved dwarf mongoose optimization (DMO) algorithm based on the Levy flight distribution is utilized to optimize the basis function of hyperbasis function neural networks to better estimate the augmented actuator faults that include the actuator fault and the actuator-like fault. Furthermore, an adaptive finite time composite fault-tolerant controller is proposed, which includes the delay-dependent feedback control law, disturbance estimation based-disturbance compensation law and the adaptive fault compensation law based on the augmented fault estimation using the improved DMO-hyper basis function neural network. The finite time boundness of the close-loop dynamics to the uncertainties, operating noise, and augmented actuator faults and the robustness of the measurement to the uncertainties, operating noise and augmented actuator faults are analyzed, and the observer and controller design is formulated as the linear matrix inequalities. Simulation examples for ACSs in different working conditions are considered to exhibit the proposed method's effectiveness.
{"title":"Neuro-adaptive finite time composite fault tolerant control for attitude control systems of satellites","authors":"Yingdong Wang;Tiantian Liang;Jianxiong Yang;Jian Liu","doi":"10.1029/2023RS007744","DOIUrl":"10.1029/2023RS007744","url":null,"abstract":"An adaptive finite time composite fault tolerant control strategy based on an optimized neural network for Attitude control systems (ACSs) of satellites is proposed considering the state time-varying delays, concurrent actuator and sensor faults, system uncertainties, modelable external disturbance and operating noise. An uncertain time-varying state space model for ACSs of satellites is established, and sensor faults are equivalent to actuator-like faults. A disturbance observer is designed for estimating the modelable external disturbance, and an improved dwarf mongoose optimization (DMO) algorithm based on the Levy flight distribution is utilized to optimize the basis function of hyperbasis function neural networks to better estimate the augmented actuator faults that include the actuator fault and the actuator-like fault. Furthermore, an adaptive finite time composite fault-tolerant controller is proposed, which includes the delay-dependent feedback control law, disturbance estimation based-disturbance compensation law and the adaptive fault compensation law based on the augmented fault estimation using the improved DMO-hyper basis function neural network. The finite time boundness of the close-loop dynamics to the uncertainties, operating noise, and augmented actuator faults and the robustness of the measurement to the uncertainties, operating noise and augmented actuator faults are analyzed, and the observer and controller design is formulated as the linear matrix inequalities. Simulation examples for ACSs in different working conditions are considered to exhibit the proposed method's effectiveness.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"59 1","pages":"1-29"},"PeriodicalIF":1.6,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139072335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jun Jiang;Shuli Song;Weili Zhou;Qinghui Liu;Houcai Chen;Yongchen Jiang;Tianyu Zhou;Tarig A. Ali;Wei Li
The tropospheric delay acquired by the Global Navigation Position System (GPS) Precise Point Positioning (PPP) is continuous and steady, less affected by rainfall. The Water Vapor Radiometer (WVR) can provide real-time meteorological parameters but is more sensitive to high-frequency information in troposphere. To explore the use of WVR-retrieved tropospheric delay and assist other geodetic techniques for atmospheric correction, the tropospheric delay from WVR and co-located GPS at Shanghai, Beijing, Kunming, and Urumqi stations in China are compared. For the inconsistent values of WVR-PPP zenith wet delay, the variations of the tropospheric delay from WVR and GPS before and after the rainfall were statistically analyzed. The results suggest that, for the rain rate ranging from 0.1 to 50 mm/hr, the impact of rainfall on WVR could last from 10 min before to 30 min after the rainfall. With filtering WVR data based on meteorological parameters and rain rate, the zenith wet delay between WVR and PPP at Shanghai shows good consistency, the root mean square (RMS) is 6.11 mm, correlation is 0.997, and the RMS in the other three stations ranges from 16.35 to 25.16 mm (correlation ranges in 0.794–0.951). The analysis indicates that the tropospheric delay of WVR is reliable to be applied to space geodetic techniques correction in real-time with filtering to reduce the effect of rainfall, water vapor, and liquid water variability.
{"title":"Consistency of the troposphere wet delay from water vapor radiometer and co-located GPS station","authors":"Jun Jiang;Shuli Song;Weili Zhou;Qinghui Liu;Houcai Chen;Yongchen Jiang;Tianyu Zhou;Tarig A. Ali;Wei Li","doi":"10.1029/2022RS007642","DOIUrl":"10.1029/2022RS007642","url":null,"abstract":"The tropospheric delay acquired by the Global Navigation Position System (GPS) Precise Point Positioning (PPP) is continuous and steady, less affected by rainfall. The Water Vapor Radiometer (WVR) can provide real-time meteorological parameters but is more sensitive to high-frequency information in troposphere. To explore the use of WVR-retrieved tropospheric delay and assist other geodetic techniques for atmospheric correction, the tropospheric delay from WVR and co-located GPS at Shanghai, Beijing, Kunming, and Urumqi stations in China are compared. For the inconsistent values of WVR-PPP zenith wet delay, the variations of the tropospheric delay from WVR and GPS before and after the rainfall were statistically analyzed. The results suggest that, for the rain rate ranging from 0.1 to 50 mm/hr, the impact of rainfall on WVR could last from 10 min before to 30 min after the rainfall. With filtering WVR data based on meteorological parameters and rain rate, the zenith wet delay between WVR and PPP at Shanghai shows good consistency, the root mean square (RMS) is 6.11 mm, correlation is 0.997, and the RMS in the other three stations ranges from 16.35 to 25.16 mm (correlation ranges in 0.794–0.951). The analysis indicates that the tropospheric delay of WVR is reliable to be applied to space geodetic techniques correction in real-time with filtering to reduce the effect of rainfall, water vapor, and liquid water variability.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-13"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138823396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The global navigation satellite system radio occultation technique is achieving increasing significance and extensive promotion in the remote sensing of near-earth atmosphere, climate, and ionosphere in recent three decades. Nowadays, many communities become interested in developing commercial mode in occultation measurement by launching massive nano- or cube satellite constellations at low costs. The TJU#01 is the first meteorological satellite of Tianjin Yunyao Aerospace Technology Co., Ltd. which was successfully launched into space on 7 December 2021. The occultation antenna onboard the satellite is able to probe both the ionosphere and atmosphere at multi-frequencies including GPS, GLONASS, and BEIDOU systems. The microsatellite applies the same occultation antenna to receive both the atmospheric and ionospheric occultations at 100 and 1 Hz respectively. 100 Hz narrow band power and wide band power data are downloaded to the ground to generate high-rate signal-to-noise ratio (SNR) series and applied to ionospheric scintillation exploration. In this paper, the primary parameters of the satellite and occultation antenna are introduced, as well as the ionospheric data processing methodologies. The initial ionospheric products of TJU#01 are evaluated after one-month in orbit. The TJU#01 results have a good agreement with the co-located ground ionosonde data and COSMIC-2 observations. The new satellite and its follow-on missions have great capabilities and potentials in the ionospheric and space weather researches.
{"title":"The ionospheric exploration based on TJU#01 meteorological microsatellite mission: Initial results","authors":"M. J. Wu;P. Guo;F. H. Li;N. F. Fu;X. Ma;Y. Cheng","doi":"10.1029/2023RS007677","DOIUrl":"10.1029/2023RS007677","url":null,"abstract":"The global navigation satellite system radio occultation technique is achieving increasing significance and extensive promotion in the remote sensing of near-earth atmosphere, climate, and ionosphere in recent three decades. Nowadays, many communities become interested in developing commercial mode in occultation measurement by launching massive nano- or cube satellite constellations at low costs. The TJU#01 is the first meteorological satellite of Tianjin Yunyao Aerospace Technology Co., Ltd. which was successfully launched into space on 7 December 2021. The occultation antenna onboard the satellite is able to probe both the ionosphere and atmosphere at multi-frequencies including GPS, GLONASS, and BEIDOU systems. The microsatellite applies the same occultation antenna to receive both the atmospheric and ionospheric occultations at 100 and 1 Hz respectively. 100 Hz narrow band power and wide band power data are downloaded to the ground to generate high-rate signal-to-noise ratio (SNR) series and applied to ionospheric scintillation exploration. In this paper, the primary parameters of the satellite and occultation antenna are introduced, as well as the ionospheric data processing methodologies. The initial ionospheric products of TJU#01 are evaluated after one-month in orbit. The TJU#01 results have a good agreement with the co-located ground ionosonde data and COSMIC-2 observations. The new satellite and its follow-on missions have great capabilities and potentials in the ionospheric and space weather researches.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-16"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138823608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Motivated by applications in unmanned aerial based ground penetrating radar for detecting buried landmines, we consider the problem of imaging small point like scatterers situated in a lossy medium below a random rough surface. Both the random rough surface and the absorption in the lossy medium significantly impede the target detection and imaging process. Using principal component analysis we effectively remove the reflection from the air-soil interface. We then use a modification of the classical synthetic aperture radar imaging functional to image the targets. This imaging method introduces a user-defined parameter, δ, which scales the resolution by √δ allowing for target localization with sub wavelength accuracy. Numerical results in two dimensions illustrate the robustness of the approach for imaging multiple targets. However, the depth at which targets are detectable is limited due to the absorption in the lossy medium.
{"title":"Synthetic aperture radar imaging below a random rough surface","authors":"Arnold D. Kim;Chrysoula Tsogka","doi":"10.1029/2023RS007712","DOIUrl":"10.1029/2023RS007712","url":null,"abstract":"Motivated by applications in unmanned aerial based ground penetrating radar for detecting buried landmines, we consider the problem of imaging small point like scatterers situated in a lossy medium below a random rough surface. Both the random rough surface and the absorption in the lossy medium significantly impede the target detection and imaging process. Using principal component analysis we effectively remove the reflection from the air-soil interface. We then use a modification of the classical synthetic aperture radar imaging functional to image the targets. This imaging method introduces a user-defined parameter, δ, which scales the resolution by √δ allowing for target localization with sub wavelength accuracy. Numerical results in two dimensions illustrate the robustness of the approach for imaging multiple targets. However, the depth at which targets are detectable is limited due to the absorption in the lossy medium.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-16"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138573492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. Mmame;J. A. E. Stephenson;A. D. M. Walker;Z. Mtumela;J. P. S. Rash
Two magnetospheric phenomena are commonly observed in both SuperDARN (Dual Auroral Radar Network) and ground-based magnetometer network data. These are ULF pulsations driven by magnetohydrodynamic waves, and flow bursts in the high latitude ionosphere driven by magnetic reconnection. Possible connections between these two phenomena are investigated. TRINNI (Tail Reconnection during IMF Northward, Non-substorm Intervals) events, high-speed ionospheric flows resulting from magnetotail reconnection during IMF Bz-positive but By-dominant periods, have been investigated by many researchers. These events produce measurable enhancements of the cross polar cap potential. Four previously reported TRINNI events have been analyzed using SuperDARN data, together with high-latitude magnetometer data which show simultaneous ULF pulsations. Fourier analysis of the cross polar cap potential measured by SuperDARN and two magnetic field components revealed common spectral peaks in the 1-5 mHz range. The signals were narrow-band filtered and complex demodulation was performed to construct the analytic signals, allowing determination of amplitude and phase. In all four events the magnetic field and potential signals showed similar wave packet structure with large-amplitude oscillations at a common frequency for periods of the order of hours. During these periods the phase differences between the field and potential remained constant. It is argued that this phase locking suggests a causal link between the two oscillations, so that the TRINNIs could be the source of the magnetic pulsations, or they at least share a common driver.
超级极光雷达网和地基磁强计网络数据中通常观测到两种磁层现象。这两种现象是由磁流体动力学波驱动的超低频脉冲和由磁重联驱动的高纬度电离层流动爆发。对这两种现象之间可能存在的联系进行了研究。TRINNI（IMF 向北、非次级风暴期间的磁尾再连接）事件是许多研究人员研究的对象，它是在 IMF Bz 为正但 By 为主导期间磁尾再连接产生的高速电离层流动。这些事件会产生可测量的交叉极冠电势增强。利用超级雷达网数据和高纬度磁强计数据分析了之前报告的四次 TRINNI 事件，这些数据显示了同时发生的超低频脉动。对超级雷达网测量的跨极冠电势和两个磁场分量进行的傅里叶分析显示，在 1-5 mHz 范围内存在共同的频谱峰。对这些信号进行窄带滤波和复数解调，以构建分析信号，从而确定振幅和相位。在所有四次事件中，磁场和电势信号都显示出类似的波包结构，在一个共同频率上出现大振幅振荡，振荡周期大约为数小时。在此期间，磁场和电势之间的相位差保持不变。有人认为，这种相位锁定表明这两种振荡之间存在因果联系，因此 TRINNIs 可能是磁脉冲的来源，或者它们至少有一个共同的驱动因素。
{"title":"Observations of ULF pulsations during TRINNI events","authors":"B. Mmame;J. A. E. Stephenson;A. D. M. Walker;Z. Mtumela;J. P. S. Rash","doi":"10.1029/2023RS007833","DOIUrl":"10.1029/2023RS007833","url":null,"abstract":"Two magnetospheric phenomena are commonly observed in both SuperDARN (Dual Auroral Radar Network) and ground-based magnetometer network data. These are ULF pulsations driven by magnetohydrodynamic waves, and flow bursts in the high latitude ionosphere driven by magnetic reconnection. Possible connections between these two phenomena are investigated. TRINNI (Tail Reconnection during IMF Northward, Non-substorm Intervals) events, high-speed ionospheric flows resulting from magnetotail reconnection during IMF Bz-positive but By-dominant periods, have been investigated by many researchers. These events produce measurable enhancements of the cross polar cap potential. Four previously reported TRINNI events have been analyzed using SuperDARN data, together with high-latitude magnetometer data which show simultaneous ULF pulsations. Fourier analysis of the cross polar cap potential measured by SuperDARN and two magnetic field components revealed common spectral peaks in the 1-5 mHz range. The signals were narrow-band filtered and complex demodulation was performed to construct the analytic signals, allowing determination of amplitude and phase. In all four events the magnetic field and potential signals showed similar wave packet structure with large-amplitude oscillations at a common frequency for periods of the order of hours. During these periods the phase differences between the field and potential remained constant. It is argued that this phase locking suggests a causal link between the two oscillations, so that the TRINNIs could be the source of the magnetic pulsations, or they at least share a common driver.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-18"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139022882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The temporal behavior of the Martian ionosphere is highly variable due to various dynamic processes including space weather events. Here, we study the effect of solar flares and coronal mass ejections (CMEs) on the Martian ionosphere for two selected solar events in 2011 and 2015, using the publicly available Mars EXpress (MEX) radio occultation (RO) data (MaRS). We developed a data processing software that converts the calibrated Radio Occultation (RO) Doppler data to scientifically valuable atmospheric profiles. Using this software and previously unexplored MaRS observations, the variations in ionospheric parameters (electron density profiles and total electron content (TEC)) are calculated in order to evaluate the ionospheric changes due to solar flares and CMEs. The RO measurements mostly available 1-4 days apart from the peak events, showed no evident change in the TEC nor in the shape of electron density profiles except for a possible gradual decrease in altitude of M2 (main layer) peak density following the arrival of CMEs. To better quantify the effect of solar events on electron density profiles, RO observations near the time of arrival of solar flares and CMEs are crucial. This can be achieved by frequent RO measurements by various Mars orbiters including spacecraft-to-spacecraft measurements assisted by multi-instrument monitoring of the ionosphere.
{"title":"Analysis of two selected solar events in 2011 and 2015 with Mars express radio occultation data","authors":"Ananya Krishnan;Ozgur Karatekin;Sebastien Verkercke;Gregoire Henry;Beatriz Sánchez-Cano;Olivier Witasse","doi":"10.1029/2023RS007784","DOIUrl":"10.1029/2023RS007784","url":null,"abstract":"The temporal behavior of the Martian ionosphere is highly variable due to various dynamic processes including space weather events. Here, we study the effect of solar flares and coronal mass ejections (CMEs) on the Martian ionosphere for two selected solar events in 2011 and 2015, using the publicly available Mars EXpress (MEX) radio occultation (RO) data (MaRS). We developed a data processing software that converts the calibrated Radio Occultation (RO) Doppler data to scientifically valuable atmospheric profiles. Using this software and previously unexplored MaRS observations, the variations in ionospheric parameters (electron density profiles and total electron content (TEC)) are calculated in order to evaluate the ionospheric changes due to solar flares and CMEs. The RO measurements mostly available 1-4 days apart from the peak events, showed no evident change in the TEC nor in the shape of electron density profiles except for a possible gradual decrease in altitude of M2 (main layer) peak density following the arrival of CMEs. To better quantify the effect of solar events on electron density profiles, RO observations near the time of arrival of solar flares and CMEs are crucial. This can be achieved by frequent RO measurements by various Mars orbiters including spacecraft-to-spacecraft measurements assisted by multi-instrument monitoring of the ionosphere.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-14"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138717141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Muhammad Saleem;Muhammad Irfan;Mubarak A. Alanazi;Shahid Atiq
In this paper, a 2-bit water-based programmable digital metasurface for beam steering and backscatter field reduction applications is presented, a reflective and transmissive type water based programmable metasurface (WPMS) for RCS reduction and the antenna's beam steering is suggested, respectively. It has been demonstrated that a 2-bit water-based programmable unit cell can reduce RCS by changing its state (0/1). If the unit cell channel is empty, the state is "0," if the channel is filled, the state is "1." So at different resonance frequencies, the four phase and reflection coefficient responses are achieved as "00"01"10"11". This functionality enables beam steering in both the elevation and azimuth axis and also backscattering reduction of the antenna. Furthermore, the impacts of the number of unit cells and reflection phase states on the far-field pattern are examined. Beam steering of ±45° in the elevation is attained with 10-dB impedance bandwidth of 4.25–4.40 GHz, radiation gain of more than 7.1 dBi is maintained. With the present antenna, it is possible to achieve volumetric beamsteering performance directly. The patterns of far-field radiation that are predicted theoretically coincide well with full waves simulations. As such, the proposed prototype can be a good option for applications that require a low RCS platform including beam steering in radars, 5G/6G, etc.
{"title":"2-Bit programmable metasurface for low radar cross section antenna and beam steering applications","authors":"Muhammad Saleem;Muhammad Irfan;Mubarak A. Alanazi;Shahid Atiq","doi":"10.1029/2023RS007767","DOIUrl":"10.1029/2023RS007767","url":null,"abstract":"In this paper, a 2-bit water-based programmable digital metasurface for beam steering and backscatter field reduction applications is presented, a reflective and transmissive type water based programmable metasurface (WPMS) for RCS reduction and the antenna's beam steering is suggested, respectively. It has been demonstrated that a 2-bit water-based programmable unit cell can reduce RCS by changing its state (0/1). If the unit cell channel is empty, the state is \"0,\" if the channel is filled, the state is \"1.\" So at different resonance frequencies, the four phase and reflection coefficient responses are achieved as \"00\"01\"10\"11\". This functionality enables beam steering in both the elevation and azimuth axis and also backscattering reduction of the antenna. Furthermore, the impacts of the number of unit cells and reflection phase states on the far-field pattern are examined. Beam steering of ±45° in the elevation is attained with 10-dB impedance bandwidth of 4.25–4.40 GHz, radiation gain of more than 7.1 dBi is maintained. With the present antenna, it is possible to achieve volumetric beamsteering performance directly. The patterns of far-field radiation that are predicted theoretically coincide well with full waves simulations. As such, the proposed prototype can be a good option for applications that require a low RCS platform including beam steering in radars, 5G/6G, etc.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 12","pages":"1-9"},"PeriodicalIF":1.6,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138632118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Presented here are the results of an investigation conducted to determine the effectiveness of deep learning (DL)-based systems utilizing the power of transfer learning for detecting breast cancer in histopathological images. It is shown that DL models that are not specifically developed for breast cancer detection can be trained using transfer learning to effectively detect breast cancer in histopathological images. The outcome of the analysis enables the selection of the best DL architecture for detecting cancer with high accuracy. This should facilitate pathologists to achieve early diagnoses of breast cancer and administer appropriate treatment to the patient. The experimental work here used the BreaKHis database consisting of 7909 histopathological pictures from 82 clinical breast cancer patients. The strategy presented for DL training uses various image processing techniques for extracting various feature patterns. This is followed by applying transfer learning techniques in the deep convolutional networks like ResNet, ResNeXt, SENet, Dual Path Net, DenseNet, NASNet, and Wide ResNet. Comparison with recent literature shows that ResNext-50, ResNext-101, DPN131, DenseNet-169 and NASNet-A provide an accuracy of 99.8%, 99.5%, 99.675%, 99.725%, and 99.4%, respectively, and outperform previous studies.
{"title":"Breast cancer detection based on simplified deep learning technique with histopathological image using BreaKHis database","authors":"Tania Afroz Toma;Shivazi Biswas;Md Sipon Miah;Mohammad Alibakhshikenari;Bal S. Virdee;Sandra Fernando;Md Habibur Rahman;Syed Mansoor Ali;Farhad Arpanaei;Mohammad Amzad Hossain;Md Mahbubur Rahman;Ming-bo Niu;Naser Ojaroudi Parchin;Patrizia Livreri","doi":"10.1029/2023RS007761","DOIUrl":"https://doi.org/10.1029/2023RS007761","url":null,"abstract":"Presented here are the results of an investigation conducted to determine the effectiveness of deep learning (DL)-based systems utilizing the power of transfer learning for detecting breast cancer in histopathological images. It is shown that DL models that are not specifically developed for breast cancer detection can be trained using transfer learning to effectively detect breast cancer in histopathological images. The outcome of the analysis enables the selection of the best DL architecture for detecting cancer with high accuracy. This should facilitate pathologists to achieve early diagnoses of breast cancer and administer appropriate treatment to the patient. The experimental work here used the BreaKHis database consisting of 7909 histopathological pictures from 82 clinical breast cancer patients. The strategy presented for DL training uses various image processing techniques for extracting various feature patterns. This is followed by applying transfer learning techniques in the deep convolutional networks like ResNet, ResNeXt, SENet, Dual Path Net, DenseNet, NASNet, and Wide ResNet. Comparison with recent literature shows that ResNext-50, ResNext-101, DPN131, DenseNet-169 and NASNet-A provide an accuracy of 99.8%, 99.5%, 99.675%, 99.725%, and 99.4%, respectively, and outperform previous studies.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 11","pages":"1-18"},"PeriodicalIF":1.6,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138491116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. K. B. Sangeetha;Virendra Singh Kushwah;K. Sumangali;R. Sangeetha;Kiruba Thangam Raja;Sandeep Kumar Mathivanan
Land cover changes from rural or natural habitats to impervious surfaces that support various human activities are called urbanization. The evaluation of policy alternatives for future expansion and the promotion of sustainable urban development therefore place great emphasis on the mapping, analysis, and monitoring of land cover changes in metropolitan environments. By assessing changes in relevant environmental indicators at a range of scales, from local to regional, this study seeks to determine the rate of urbanization and analyze its impact on the environment in and around two key cities in Tamilnadu. Chennai and Madurai are the urban areas under investigation. The results are based on classifications of medium to high spatial resolution optical satellite images from 1995 to 2020. Various classification approaches with combinations of spectral, shape, and texture input information were combined to achieve high classification accuracy. Based on the categories, environmental indicators were created and used to calculate the impact of urbanization on the environment. The findings show that each research area experienced varying degrees of urban expansion and environmental impact. Urban areas grew tenfold between 1995 and 2015, according to a study comparing Chennai and Madurai. To evaluate the spatiotemporal dynamics of urbanization and its environmental impact in various metropolitan regions, this research shows the value of combining urban and environmental indicators with remote sensing data.
{"title":"Effect of urbanization through land coverage classification","authors":"S. K. B. Sangeetha;Virendra Singh Kushwah;K. Sumangali;R. Sangeetha;Kiruba Thangam Raja;Sandeep Kumar Mathivanan","doi":"10.1029/2023RS007816","DOIUrl":"10.1029/2023RS007816","url":null,"abstract":"Land cover changes from rural or natural habitats to impervious surfaces that support various human activities are called urbanization. The evaluation of policy alternatives for future expansion and the promotion of sustainable urban development therefore place great emphasis on the mapping, analysis, and monitoring of land cover changes in metropolitan environments. By assessing changes in relevant environmental indicators at a range of scales, from local to regional, this study seeks to determine the rate of urbanization and analyze its impact on the environment in and around two key cities in Tamilnadu. Chennai and Madurai are the urban areas under investigation. The results are based on classifications of medium to high spatial resolution optical satellite images from 1995 to 2020. Various classification approaches with combinations of spectral, shape, and texture input information were combined to achieve high classification accuracy. Based on the categories, environmental indicators were created and used to calculate the impact of urbanization on the environment. The findings show that each research area experienced varying degrees of urban expansion and environmental impact. Urban areas grew tenfold between 1995 and 2015, according to a study comparing Chennai and Madurai. To evaluate the spatiotemporal dynamics of urbanization and its environmental impact in various metropolitan regions, this research shows the value of combining urban and environmental indicators with remote sensing data.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"58 11","pages":"1-13"},"PeriodicalIF":1.6,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136262864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：