- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Effective Building Extraction From High-Resolution Remote Sensing Images With Multitask Driven Deep Neural Network
摘要： Building extraction from high-resolution remote sensing images has widely been studied for its great signi?cance in obtaining geographic information. Many methods based on deep learning have been tried for the task; however, there is still much to explore about designing layers or modules for remote sensing data and taking full use of the unique features of buildings like shape and boundary. In this letter, an end-to-end network architecture based on U-Net is proposed. The U-Net architecture is modi?ed with Xception module for remote sensing images to extract effective features. Also, multitask learning is adopted to incorporate the structure information of buildings. Two standard data sets (Massachusetts building data set and Vaihingen Data set) of high-resolution remote sensing images are selected to test our model and it achieves state-of-the-art results.
关键词： Building extraction,multitask learning,Xception module,deep neural network,remote sensing image
更新于2025-09-10 09:29:36
-
Smart Plant Factory (The Next Generation Indoor Vertical Farms) || Plant Factories with Artificial Lighting (PFALs): Benefits, Problems, and Challenges
摘要： The bene?ts, unsolved problems, and challenges for plant factories with arti?cial lighting (PFALs) are discussed. The remarkable bene?ts are high resource use ef?ciency, high annual productivity per unit land area, and production of high-quality plants without using pesticides. Major unsolved problems are high initial investment, electricity cost, and labor cost. A major challenge for the next-generation smart PFAL is the introduction of advanced technologies such as arti?cial intelligence with the use of big data, genomics, and phenomics (or methodologies and protocols for noninvasive measurement of plant-speci?c traits related to plant structure and function).
关键词： Smart LED lighting system,Cultivation system module (CSM),Phenotyping,Annual productivity,Standardization,Arti?cial intelligence,Resource use ef?ciency (RUE)
更新于2025-09-10 09:29:36
-
[IEEE 2018 International Conference on Information , Communication, Engineering and Technology (ICICET) - Pune, India (2018.8.29-2018.8.31)] 2018 International Conference on Information , Communication, Engineering and Technology (ICICET) - Simulation of Dual Axis Solar Tracking System
摘要： Photovoltaic (PV) panel is used to convert solar energy into electricity. Increase in collection of solar radiations by Photovoltaic (PV) panel rises electricity output from it. By tracking the movement of sun, PV panel can be always positioned in such a way that it can collect maximum amount of solar radiations. This paper presents MATLAB simulation model of Dual Axis Solar Tracking System (DASTS), in which the PV panel can be rotated along two axes of rotation to track both east to west and north to south movement of sun. East to west angle selector and north to south angle selector provide particular angles to PV panel according to particular illuminance level at particular time of the day to rotate and position PV panel in such a way that it can always faces the sun. Readings of voltage, current and power obtain from PV panel with Dual Axis Solar Tracking System are taken at different times of the day and they are compared with readings of voltage, current and power obtain from fixed PV panel at different times of the day.
关键词： Modeling and simulation,Photovoltaic (PV) module,Angle selector
更新于2025-09-10 09:29:36
-
Rearrangeable and exchangeable optical module with system-on-chip for wearable functional near-infrared spectroscopy system
摘要： We developed a system-on-chip (SoC)-incorporated light-emitting diode (LED) and avalanche photo-diode (APD) modules to improve the usability and flexibility of a fiberless wearable functional near-infrared spectroscopy (fNIRS) system. The SoC has a microprocessing unit and programmable circuits. The time division method and the lock-in method were used for separately detecting signals from different positions and signals of different wavelengths, respectively. Each module autonomously works for this time-divided-lock-in measurement with a high sensitivity for haired regions. By supplying t3.3 V of power and base and data clocks, the LED module emits both 730- and 855-nm wavelengths of light, amplitudes of which are modulated in each lock-in frequency generated from the base clock, and the APD module provides the lock-in detected signals synchronizing with the data clock. The SoC provided many functions, including automatic-power-control of the LED, automatic judgment of detected power level, and automatic-gain-control of the programmable gain amplifier. The number and the arrangement of modules can be adaptively changed by connecting this exchangeable modules in a daisy chain and setting the parameters dependent on the probing position. Therefore, users can configure a variety of arrangements (single- or multidistance combinations) of them with this module-based system.
关键词： wearable,functional near-infrared spectroscopy,system-on-chip,module-based system
更新于2025-09-10 09:29:36
-
Classification via weighted kernel CNN: application to SAR target recognition
摘要： The conventional convolutional neural network (CNN) has proven to be effective for synthetic aperture radar (SAR) target recognition. However, the relationship between different convolutional kernels is not taken into account. The lack of the relationship limits the feature extraction capability of the convolutional layer to a certain extent. To address this problem, this paper presents a novel method named weighted kernel CNN (WKCNN). WKCNN integrates a weighted kernel module (WKM) into the common CNN architecture. The WKM is proposed to model the interdependence between different kernels, and thus to improve the feature extraction capability of the convolutional layer. The WKM consists of variables and activations. The variable represents the weight of the convolutional kernel. The activation is a mapping function which is used to determine the range of the weight. To adjust the variable adaptively, back propagation (BP) algorithm for the WKM is derived. The training of the WKM is driven by optimizing the cost function according to the BP algorithm, and three training modes are presented and analysed. SAR target recognition experiments are conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset, and the results show the superiority of the proposed method.
关键词： SAR target recognition,weighted kernel module,convolutional neural network,back propagation algorithm,MSTAR dataset
更新于2025-09-10 09:29:36
-
Fault detection in trackers for PV systems based on a pattern recognition approach
摘要： In many photovoltaic (PV) power plants, the PV modules are installed in trackers. In these systems, the PV modules are fixed in a mobile structure to always maintain a perpendicular position to the brightest point in the sky, obtaining in this way the maximum power from the sun, during the all day. Nevertheless, these systems are subject to problems that reduce their efficiency. Thus, visual inspection or complex methods can be used to detect this problem. However, these systems normally result in delays or are expensive. To overcome these problems, this paper proposes a new method for that detection. This, method is based on the pattern recognition analysis. Thus, through the analysis of the images of the several solar panels, the PV module that presents a problem in the tracker will be detected. The orientation of the PV modules is determined using the centroid of the PV cells after applying an image pre‐processing stage. The angle is calculated using the statistical moments or by the slope of the line joining two centroids of the PV cells that are located at the vertices of the PV module. Several test cases are presented to verify the efficiency of the proposed approach.
关键词： pattern recognition,image processing,tracker,PV power plant,fault detection,PV module
更新于2025-09-10 09:29:36
-
[IEEE 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - Bangalore, India (2018.9.19-2018.9.22)] 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI) - FPGA based Ultrasonic thickness measuring device
摘要： This paper aims at the development of ultrasound based thickness measurement device. A Spartan 6 FPGA from Xilinx has been used in the hardware design along with external parallel Analog to Digital and digital to Analog converter. The device is interfaced with a PC or laptop through USB cable. A measurement and control software is developed using MATLAB for conceptual level and final Graphical User Interface has been developed in .NET to transfer different user defined control parameters to the hardware and receive the captured signal. Ultrasonic probes are used to generate and receive physical sound wave in pulse-echo mode. Time of flight (ToF) based calculations are used for deriving the subject dimension.
关键词： ADC Module,Contact Transducer,DAC Module,NDT,Ultrasonic testing,Spartan XC6SLX9 FPGA
更新于2025-09-09 09:28:46
-
End-of-life of silicon PV panels: A sustainable materials recovery process
摘要： In this paper, the management of end-of-life PV modules based on an advanced eco-sustainable process has been presented and discussed. The thermal removal of the polymeric compounds contained in c-Si PV modules has been investigated to separate and recover Si, Ag, Cu, Al and glass. A two-step thermal process has been employed. In the first step, the rear polymeric layer has been removed without emissions of dangerous fluorinated substances. In the second step, the remaining polymers have been completely removed with low volatile organic compounds (VOCs) emissions. The polymers degradation has been studied at combustion equivalent ratios U varying from 0.5 to 2 and at 500 °C. The materials recovery has been evaluated from an environmental point of view and optimized by considering the energy cost, through the identification of the best operating conditions, in terms of temperature, time, atmosphere and gas flow. One hour of heat treatment and a slightly oxidizing atmosphere have been enabled to separate and recover the different materials of the module. The elemental compositions of the PV sample and the residue condensed organic products have been determined. The gaseous degradation products have been characterized by gas chromatographic analysis (GC).
关键词： Recycling,Photovoltaic module,Thermal treatment,Polymer removal,Energy consumption
更新于2025-09-09 09:28:46
-
Investigation on the degradation indicators of short-circuit tests in 1.2?kV SiC MOSFET power modules
摘要： This paper provides a comprehensive investigation on both static characteristics and short-circuit performance of 1.2 kV SiC MOSFET power modules with 2nd generation planar technology. The experimental approach is based on the static characteristics measurements and the short-circuit tests with gradual increase of pulse time duration. If any variation of the static characteristics appears, the time duration of next short-circuit tests would keep the same with the last pulse duration (approach 1) or increase continuously (approach 2). The results of the short-circuit waveforms show a gate degradation which is further con?rmed with the measurement of the gate leakage current. Additionally, other degradation indicators, including positive shift of threshold voltage, drain leakage current and on-state resistance increase are evidenced and discussed in this paper. These can be used for early prediction of the degradation and failure in the short-circuit conditions.
关键词： SiC MOSFET,SiC power module,Short-circuit,Degradation indicators
更新于2025-09-09 09:28:46
-
Systematic Investigation of Spontaneous Emission Quantum Efficiency Drop up to 800K for Future Power Electronics Applications
摘要： Future high-density power electronics applications may require optoelectronic devices for gate drive. Thus, a systematic study of optoelectronic material from 10 K to 800 K has been performed to understand the potential of the high-temperature operation of optoelectronic devices. The temperature dependence of the photoluminescence (PL) of InGaN/GaN multiple quantum wells (MWQs) was studied. The integrated PL intensity dropped by an order of magnitude at 800 K as compared to 10 K. The spontaneous emission quantum efficiency was calculated from the power-law relation linking the integrated PL signal and the excitation pump power. The validation of the traditional ABC model for solid-state lighting is extended to 800 K. This work demonstrates the feasibility of developing high-temperature optoelectronic devices, which have operating temperatures over 500 K.
关键词： high temperature photoluminescence,high temperature efficiency,power dependent photoluminescence,InGaN/GaN MWQs,power module,quantum temperature optoelectronics
更新于2025-09-09 09:28:46