- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Imbalanced Learning-Based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
摘要： Change detection is a quite challenging task due to the imbalance between unchanged and changed class. In addition, the traditional difference map generated by log-ratio is subject to the speckle, which will reduce the accuracy. In this letter, an imbalanced learning-based change detection is proposed based on PCA network (PCA-Net), where a supervised PCA-Net is designed to obtain the robust features directly from given multitemporal synthetic aperture radar (SAR) images instead of a difference map. Furthermore, to tackle with the imbalance between changed and unchanged classes, we propose a morphologically supervised learning method, where the knowledge in the pixels near the boundary between two classes is exploited to guide network training. Finally, our proposed PCA-Net can be trained by the data sets with available reference maps and applied to a new data set, which is quite practical in change detection projects. Our proposed method is veri?ed on ?ve sets of multiple temporal SAR images. It is demonstrated from the experiment results that with the knowledge in training samples from the boundary, the learned features bene?t change detection and make the proposed method outperform than supervised methods trained by randomly drawing samples.
关键词： Change detection,imbalance learning,synthetic aperture radar (SAR) images,PCA network (PCA-Net)
更新于2025-09-23 15:23:52
-
[Lecture Notes in Computational Vision and Biomechanics] Computer Aided Intervention and Diagnostics in Clinical and Medical Images Volume 31 || Deep Neural Architecture for Localization and Tracking of Surgical Tools in Cataract Surgery
摘要： Over the last couple of decades, the quality of surgical interventions has improved owing to the use of computer vision and robotic assistance. One such application of computer vision, namely, detection of surgical tools in videos is gaining attention of the medical image processing community. The main motivation for detection, localization, and annotation of surgical tools is to develop applications for surgical workflow analysis. Such an analysis can aid in report generation, real-time decision support, etc. Cataract surgery is one of the common surgical procedure where surgeons do have direct visual access to the surgical site. Extremely small tools are used for this procedure and the surgeons observe the surgical site through a surgical microscope. In such cases, detecting the presence of tools can act an additional aid to the surgeon as well as other surgical staffs. We propose a framework consisting of a Convolutional Neural Network (CNN) which learns to distinguish and detect the presence of various surgical tools by learning robust features from the frames of a surgical video. Various deep neural architectures are hence evaluated for the task of detecting tools. The baseline models used for the purpose are pretrained on Imagenet dataset and they render upto 50% prediction accuracy. All the experiments have been validated on the dataset released as part of the Cataracts Grand Challenge. A framework for localization and detection of tools has also been proposed, which is capable of extracting visual features from glimpses of an image, by adaptively selecting and processing only the selected regions at high resolution.
关键词： Multiple tool detection,Cataract surgery,CNN,Glimpse network,Deep neural architectures,Class imbalance
更新于2025-09-23 15:23:52
-
Precompensation and System Parameters Estimation for Low-Cost Nonlinear Tera-Hertz Transmitters in the Presence of I/Q Imbalance
摘要： Tera-Hertz (THz) transmission can offer several attractive applications, yet developing low-cost energy-efficient THz devices is at an early stage. The most promising low-cost THz transmitter architecture in the literature is the so-called frequency-multiplier-last architecture. However, it is incapable of transmitting quadrature amplitude modulation (QAM) due to the architecture's inherent nonlinear distortions. We study such nonlinear THz communication systems by incorporating the nonlinearity aspects of the low-cost THz devices and the inphase and quadrature (I/Q) imbalance effect into the signal model. Then, we propose a precompensation scheme to compensate the nonlinearity and I/Q imbalance effects, thus enabling the QAM-capable frequency-multiplier-last architecture for THz systems. The proposed precompensation scheme requires the knowledge of the system parameters. To estimate the system parameters, we propose a maximum-likelihood estimator and its practical implementation via an alternating estimation algorithm. We also derive closed-form expressions for the Cramér–Rao lower bounds (CRLBs) of the system parameters estimation, and design the pilot sequence used in estimating the system parameters. Numerical results show that the proposed precompensation schemes overcome the prominent problems experienced in the existing THz systems, namely severe nonlinear distortions of the modulation symbols as well as spectral spreading and/or large spectrum sidelobes, and mitigate the I/Q imbalance effect.
关键词： precompensation,estimation,QAM,I/Q imbalance,nonlinear distortion,Low-cost,Tera-Hertz
更新于2025-09-23 15:22:29
-
Blind Joint Polarization Demultiplexing and IQ Imbalance Compensation for M-QAM Coherent Optical Communications
摘要： A novel joint polarization demultiplexing and IQ imbalance compensation scheme for coherent optical communications that uses global update is proposed and analyzed through numerical simulations. We describe the system model and derive its related equations. Next, we formulate our blind M -QAM arbitrary approach based on EASI algorithm and using the second order statistics of the observed signals. A comparison of the proposed joint method with the traditional CMA for polarization demultiplexing followed by BASS for IQ imbalance compensation is also reported. Evaluated metrics (EVM, MSE, BER) demonstrate its effectiveness compared with CMA cascaded with BASS algorithm.
关键词： CMA,Joint algorithm,BER,IQ imbalance compensation,MSE,EVM,Optical communications,Polarization demultiplexing
更新于2025-09-23 15:21:01
-
Hybrid perovskite light emitting diodes under intense electrical excitation
摘要： Hybrid perovskite semiconductors represent a promising platform for color-tunable light emitting diodes (LEDs) and lasers; however, the behavior of these materials under the intense electrical excitation required for electrically-pumped lasing remains unexplored. Here, we investigate methylammonium lead iodide-based perovskite LEDs under short pulsed drive at current densities up to 620 A cm?2. At low current density (J < 10 A cm?2), we ?nd that the external quantum ef?ciency (EQE) depends strongly on the time-averaged history of the pulse train and show that this curiosity is associated with slow ion movement that changes the internal ?eld distribution and trap density in the device. The impact of ions is less pronounced in the high current density regime (J > 10 A cm?2), where EQE roll-off is dominated by a combination of Joule heating and charge imbalance yet shows no evidence of Auger loss, suggesting that operation at kA cm?2 current densities relevant for a laser diode should be within reach.
关键词： ion movement,electrical excitation,lasers,Auger loss,light emitting diodes,Hybrid perovskite semiconductors,Joule heating,external quantum efficiency,charge imbalance
更新于2025-09-23 15:21:01
-
[IEEE 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Sozopol, Bulgaria (2019.9.6-2019.9.8)] 2019 IEEE 8th International Conference on Advanced Optoelectronics and Lasers (CAOL) - Laser Stimulation of Retina and Optic Nerve in Children with Anisometropic Amblyopia
摘要： Extreme learning machine (ELM) is emerged as an effective, fast, and simple solution for real-valued classification problems. Various variants of ELM were recently proposed to enhance the performance of ELM. Circular complex-valued extreme learning machine (CC-ELM), a variant of ELM, exploits the capabilities of complex-valued neuron to achieve better performance. Another variant of ELM, weighted ELM (WELM) handles the class imbalance problem by minimizing a weighted least squares error along with regularization. In this paper, a regularized weighted CC-ELM (RWCC-ELM) is proposed, which incorporates the strength of both CC-ELM and WELM. Proposed RWCC-ELM is evaluated using imbalanced data sets taken from Keel repository. RWCC-ELM outperforms CC-ELM and WELM for most of the evaluated data sets.
关键词： extreme learning machine,Real valued classification,complex valued neural network,class imbalance problem,regularization,weighted least squares error
更新于2025-09-23 15:19:57
-
Single-Layer Dual-Band Polarization-Selective Metafilm with Independently Controlled and Closely Spaced Shielding Bands
摘要： Spatially distributed transmissions in coordinated multipoint (CoMP) systems can lead to mean channel power imbalance (CPI) at the receiver. Similar imbalance also occurs in distributed antenna and co-located multi-antenna systems due to inaccurate antenna calibration. This paper studies performance impact of power imbalance on some practical CoMP methods with limited feedback. We derive approximate analytical expressions of asymptotic capacity, optimal amplitude weights, as well as signal-to-noise ratio gain for a few methods under analysis. Numerical results validate the analysis and show impacts of erroneous feedback under CPI. Results demonstrate that CPI has significant negative impact on the CoMP performance. Furthermore, our results reveal that amplitude information at transmitter is crucial and detrimental effect of CPI can be effectively compensated by using long-term amplitude information at transmitter. Moreover, additional short-term amplitude feedback shows insignificant gain when a large number of diversity antennas in base stations or CoMP suffer from feedback errors. In fact, a sparsely quantized phase and long-term power information feedback can lead to performance very close to the use of full channel state information at the transmitter.
关键词： transmit beamforming,Coordinated multipoint transmission,distributed antenna system,channel power imbalance
更新于2025-09-23 15:19:57
-
Phase-Compensated Optical Fiber-Based Ultrawideband Channel Sounder
摘要： Extreme learning machine (ELM) is emerged as an effective, fast, and simple solution for real-valued classification problems. Various variants of ELM were recently proposed to enhance the performance of ELM. Circular complex-valued extreme learning machine (CC-ELM), a variant of ELM, exploits the capabilities of complex-valued neuron to achieve better performance. Another variant of ELM, weighted ELM (WELM) handles the class imbalance problem by minimizing a weighted least squares error along with regularization. In this paper, a regularized weighted CC-ELM (RWCC-ELM) is proposed, which incorporates the strength of both CC-ELM and WELM. Proposed RWCC-ELM is evaluated using imbalanced data sets taken from Keel repository. RWCC-ELM outperforms CC-ELM and WELM for most of the evaluated data sets.
关键词： extreme learning machine,Real valued classification,complex valued neural network,class imbalance problem,regularization,weighted least squares error
更新于2025-09-23 15:19:57
-
[IEEE 2019 PhotonIcs & Electromagnetics Research Symposium - Spring (PIERS-Spring) - Rome, Italy (2019.6.17-2019.6.20)] 2019 PhotonIcs & Electromagnetics Research Symposium - Spring (PIERS-Spring) - Resonant Production of an Ultrarelativistic Electron-Positron Pair by a Gamma Quantum in the Field of a Nucleus and a Laser Wave
摘要： When and why people change their mobile phones are important issues in mobile communications industry, because it will impact greatly on the marketing strategy and revenue estimation for both mobile operators and manufactures. It is a promising way to take use of big data to analyze and predict the phone changing event. In this paper, based on mobile user big data, ?rst through statistical analysis, we ?nd that three important probability distributions, i.e., power-law, log-normal, and geometric distribution, play an important role in the user behaviors. Second, the relationships between eight selected attributes and phone changing are built, for example, young people have greater intention to change their phones if they are using the phones belonging to the low occupancy phones or feature phones. Third, we veri?ed the performance of four prediction models on phone changing event under three scenarios. Information gain ratio was used to implement attribute selection and then sampling method, cost-sensitive together with standard classi?ers were used to solve imbalanced phone changing event. Experiment results show our proposed enhanced backpropagation neural network in the undersampling scenario can attain better prediction performance.
关键词： imbalance problem,attribute selection,phone changing prediction,machine learning,Mobile big data
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - An Economic and Environmental Assessment of Residential Rooftop Photovoltaics with Second Life Batteries in the US
摘要： Extreme learning machine (ELM) is emerged as an effective, fast, and simple solution for real-valued classification problems. Various variants of ELM were recently proposed to enhance the performance of ELM. Circular complex-valued extreme learning machine (CC-ELM), a variant of ELM, exploits the capabilities of complex-valued neuron to achieve better performance. Another variant of ELM, weighted ELM (WELM) handles the class imbalance problem by minimizing a weighted least squares error along with regularization. In this paper, a regularized weighted CC-ELM (RWCC-ELM) is proposed, which incorporates the strength of both CC-ELM and WELM. Proposed RWCC-ELM is evaluated using imbalanced data sets taken from Keel repository. RWCC-ELM outperforms CC-ELM and WELM for most of the evaluated data sets.
关键词： extreme learning machine,Real valued classification,complex valued neural network,class imbalance problem,regularization,weighted least squares error
更新于2025-09-19 17:13:59