- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2020 IEEE 33rd International Conference on Micro Electro Mechanical Systems (MEMS) - Vancouver, BC, Canada (2020.1.18-2020.1.22)] 2020 IEEE 33rd International Conference on Micro Electro Mechanical Systems (MEMS) - A Novel Fabrication Process of Nano-Cavity Coupled Plasmonic Structures for Colormetric Sensing
摘要： This paper develops and validates a universally applicable computational comprehensive concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs. One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, R?ssler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise three NDE NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.
关键词： Cellular neural networks (CNNs)-based neurocomputing,CNN processor concept as a universal differential equation model solver,CNN-based ultrafast solving of nonlinear differential equations (NDEs),nonlinear adaptive optimization (NAOP)
更新于2025-09-19 17:13:59
-
[IEEE 2019 Compound Semiconductor Week (CSW) - Nara, Japan (2019.5.19-2019.5.23)] 2019 Compound Semiconductor Week (CSW) - Novel Composite Substrates for Thin Film AlGaInP-based High Power LEDs
摘要： This paper develops and validates a universally applicable computational comprehensive concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs. One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, R?ssler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise three NDE NDE solver concept. For illustration purposes, models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.
关键词： nonlinear adaptive optimization (NAOP),CNN processor concept as a universal solver,Cellular neural networks (CNNs)-based neurocomputing,CNN-based ultrafast solving of nonlinear differential equations (NDEs)
更新于2025-09-19 17:13:59
-
CNN based automatic detection of photovoltaic cell defects in electroluminescence images
摘要： Automatic defect detection is gaining huge importance in photovoltaic (PV) field due to limited application of manual/visual inspection and rising production quantities of PV modules. This study is conducted for automatic detection of PV module defects in electroluminescence (EL) images. We presented a novel approach using light convolutional neural network architecture for recognizing defects in EL images which achieves state of the art results of 93.02 % on solar cell dataset of EL images. It requires less computational power and time. It can work on an ordinary CPU computer while maintaining real time speed. It takes only 8.07 milliseconds for predicting one image. For proposing light architecture, we perform extensive experimentation on series of architectures. Moreover, we evaluate data augmentation operations to deal with data scarcity. Overfitting appears a significant problem; thus, we adopt appropriate strategies to generalize model. The impact of each strategy is presented. In addition, cracking patterns and defects that can appear in EL images are reviewed; which will help to label new images appropriately for predicting specific defect types upon availability of large data. The proposed framework is experimentally applied in lab and can help for automatic defect detection in field and industry.
关键词： PV cell cracking,Automatic defect detection,Convolutional neural network (CNN),Electroluminescence,Deep learning,Photovoltaic (PV) modules
更新于2025-09-19 17:13:59
-
[IEEE TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON) - Kochi, India (2019.10.17-2019.10.20)] TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON) - Speech Enabled Visual Question Answering using LSTM and CNN with Real Time Image Capturing for assisting the Visually Impaired
摘要： The proposed work benefits visually impaired individuals in identifying objects and visualizing scenarios around them independent of any external support. In such a situation, the surrounding and ask an open-ended question, classification question, counting question or yes/no question to the application by speech input. The proposed application uses Visual Question Answering (VQA) to integrate image processing and natural language processing which is also capable of speech to text translation and vice versa that helps to identify, recognize and thus obtain details of any particular image. The work uses a classical CNN-LSTM model where image features and language features are computed separately and combined at a later stage using image features and word embedding obtained from the question and runs a multilayer perceptron on the combined features to obtain the results. The model achieves an accuracy of 57 per cent. The model can also be utilized to develop cognitive interpretation better in kids. As the application is speech enabled it is best suited for the visually impaired with an easy to use GUI.
关键词： VGG16,Visually Impaired,Keras Neural Network Library,ImageNet,gTTS,Feature extraction,Image Recognition,VQA,Word2Vec,Speech Recognition,Glove vector,CNN,Multi Layer Perceptron,LSTM
更新于2025-09-16 10:30:52
-
Dilated residual learning with skip connections for real-time denoising of laser speckle imaging of blood flow in a log-transformed domain
摘要： Laser speckle contrast imaging (LSCI) is a wide-field and noncontact imaging technology for mapping blood flow. Although the denoising method based on block-matching and filtering three-dimensional (BM3D) was proposed to improve its signal-to-noise ratio (SNR) significantly, the processing time makes it difficult to realize real-time denoising. Furthermore, it is still difficult to obtain an acceptable level of SNR with a few raw speckle images given the presence of significant noise and artifacts. A feed-forward denoising convolutional neural network (DnCNN) achieves state-of-the-art performance in denoising nature images and is efficiently accelerated by GPU. However, it performs poorly in learning with original speckle contrast images of LSCI owing to the inhomogeneous noise distribution. Therefore, we propose training DnCNN for LSCI in a log-transformed domain to improve training accuracy and it achieves an improvement of 5.13 dB in the peak signal-to-noise ratio (PSNR). To decrease the inference time and improve denoising performance, we further propose a dilated deep residual learning network with skip connections (DRSNet). The image-quality evaluations of DRSNet with five raw speckle images outperform that of spatially average denoising with 20 raw speckle images. DRSNet takes 35 ms (i.e., 28 frames per second) for denoising a blood flow image with 486 × 648 pixels on an NVIDIA 1070 GPU, which is approximately 2.5 times faster than DnCNN. In the test sets, DRSNet also improves 0.15 dB in the PSNR than that of DnCNN. The proposed network shows good potential in real-time monitoring of blood flow for biomedical applications.
关键词： Blood flow,convolutional neural network (CNN),laser speckle contrast imaging (LSCI),dilated convolution,skip connection
更新于2025-09-16 10:30:52
-
GAN-Based Augmentation for Improving CNN Performance of Classification of Defective Photovoltaic Module Cells in Electroluminescence Images
摘要： Electroluminescence (EL) imaging is an effective way for the examining of photovoltaic (PV) modules. Compared with manual analysis, using Convolutional Neural Network (CNN) for classification is much more convenient but it requires a certain amount of annotated training samples which cannot be acquired handily. In this paper, we present a method for augmenting the existing dataset of EL images using Generative Adversarial Networks (GANS) and propose a model called AC-PG GAN aiming at this. Three chosen CNN models are used to examine the effectiveness of the proposed GAN model and have achieved an improvement of the classification accuracy with the augmented dataset after some adjustment and the maximum improvement is up to 14%.
关键词： Data Augmentation,Electroluminescence,Photovoltaic Modules,GAN,CNN
更新于2025-09-16 10:30:52
-
Automatic Detection and Segmentation of Laser Stripes for Industrial Measurement
摘要： Laser stripe plays an important role in industrial vision measurement as the major auxiliary feature. Existing researches mainly focus on the application of small size parts. However, with the increase of field of view, it is difficult to extract laser stripes robustly in varying field measurement situations for the complex background, low proportion and uneven characteristic of laser stripes. To increase the measurement adaptability in complex environment, an automatic laser stripe detection and segmentation algorithm is proposed. First, the dataset is constructed by a large number of image patches collected in the field and laboratory, and laser stripe patches in the imbalanced dataset are expanded by data augmentation method. Next, the detection of the laser stripe is initially realized based on the training results of the convolutional neural network (CNN), and then the laser stripe is accurately detected by non-feature filtering criteria based on area constraints. Finally, a sub-regional feature clustering method is proposed to realize effective segmentation of uneven laser stripes. A large number of verification experiments have been carried out in both laboratory and field, and the results show that the proposed method can achieve automatic and accurate extraction of laser strips, which has strong adaptability to both the complex background in the field and the uneven brightness characteristic of laser stripes, satisfying the engineering requirements of large-scale parts field measurement.
关键词： detection and segmentation,stereo-vision measurement,CNN,laser stripe,large industrial part
更新于2025-09-16 10:30:52
-
[IEEE 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) - Amsterdam, Netherlands (2019.9.24-2019.9.26)] 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) - Knowledge Transfer via Convolution Neural Networks for Multi-Resolution Lawn Weed Classification
摘要： Weed identi?cation and classi?cation are essential and challenging tasks for site-speci?c weed control. Object-based image analysis making use of spatial information is adopted in this study for the weed classi?cation because the spectral similarity between the weeds and crop is high. With the availability of a wide range of sensors, it is likely to capture weed imagery at various altitudes and with different speci?cations of the sensor. In this paper, we propose a novel method using transfer learning to deal with multi-resolution images from various sensors via Convolutional Neural Networks (CNN). CNN trained for a typical image data set and the trained weights are transferred to other data sets of different resolutions. In this way, the new data sets can be classi?ed by ?ne-tuning the network using a small number of training samples, which reduces the need of big data to train the model. To avoid over-?tting during the ?ne-tuning, small deep learning architecture is proposed and investigated using the parameters of the initial layers of pre-trained model. The sizes of training samples are investigated for their impact on the performance of ?ne-tuning. Experiments were conducted with ?eld data, which show that the proposed method outperforms the direct training method in terms of recognition accuracy and computation cost.
关键词： Hyperspectral images,Resolution,Convolutional Neural Network (CNN),Weed Mapping,Transfer Learning
更新于2025-09-12 10:27:22
-
Multi-Site Photovoltaic Forecasting Exploiting Space-Time Convolutional Neural Network
摘要： The accurate forecasting of photovoltaic (PV) power generation is critical for smart grids and the renewable energy market. In this paper, we propose a novel short-term PV forecasting technique called the space-time convolutional neural network (STCNN) that exploits the location information of multiple PV sites and historical PV generation data. The proposed structure is simple but effective for multi-site PV forecasting. In doing this, we propose a greedy adjoining algorithm to preprocess PV data into a space-time matrix that captures spatio-temporal correlation, which is learned by a convolutional neural network. Extensive experiments with multi-site PV generation from three typical states in the US (California, New York, and Alabama) show that the proposed STCNN outperforms the conventional methods by up to 33% and achieves fairly accurate PV forecasting, e.g., 4.6–5.3% of the mean absolute percentage error for a 6 h forecasting horizon. We also investigate the effect of PV sites aggregation for virtual power plants where errors from some sites can be compensated by other sites. The proposed STCNN shows substantial error reduction by up to 40% when multiple PV sites are aggregated.
关键词： CNN,spatio-temporal correlation,multi-site photovoltaic forecasting,space-time matrix
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Precise Extraction of Built-Up Area Using Deep Features
摘要： Built-up area is one of the most important objects in remote sensing image analysis, therefore extracting built-up area automatically has attracted wide attention. Deep convolution neural network (CNN) was proposed to improve poor generalization ability of artificial features which had been adopted by traditional automatic extraction methods. In this paper, a more efficient CNN model is proposed to extract the deep features of remote sensing images, and then a graph model based on deep features is constructed to the full image for built-up area extraction. The experiments demonstrate that it has very good performance on the satellite remote sensing image data set.
关键词： Built-up area extraction,CNN,remote Sensing,cosine similarity,Graph cut
更新于2025-09-11 14:15:04