- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 International Aegean Conference on Electrical Machines and Power Electronics (ACEMP) & 2019 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM) - Istanbul, Turkey (2019.8.27-2019.8.29)] 2019 International Aegean Conference on Electrical Machines and Power Electronics (ACEMP) & 2019 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM) - Highly efficient Multi-Junction Solar Cells Performance Improvement for AC Induction Motor Control Using the dsPIC30F Microcontroller
摘要： In-vehicle speech-based interaction between a driver and a driving agent should be performed without affecting the driving behavior. A driving agent provides information to the driver and helps his/her driving behavior and non-driving-related tasks, e.g., selecting music and giving weather information. In this paper, we focus on a method for determining utterance timings when a driving agent provides non-driving-related information. If a driving agent provides a driver with non-driving-related information at an inappropriate moment, it will distract his/her driving behavior and deteriorate his/her safety driving. To solve or to mitigate the problem, we propose a novel method for determining the utterance timing of a driving agent on the basis of a double articulation analyzer, which is an unsupervised nonparametric Bayesian machine learning method for detecting contextual change points. To verify the effectiveness of the method, we conduct two experiments. One is an experiment on a short circuit around a park in an urban area, and the other is an experiment on a long course in a town. The results show that the proposed method enables a driving agent to avoid inappropriate timing better than baseline methods.
关键词： Driving agent,machine learning,driving data,driver distraction,nonparametric Bayes
更新于2025-09-16 10:30:52
-
Laser-Induced Breakdown Spectroscopy Assisted by Machine Learning for Plastics/Polymers Identification
摘要： In the present work, Laser-Induced Breakdown Spectroscopy (LIBS) is used for the discrimination/identification of different plastic/polymeric samples having the same polymeric matrix but containing different additives (as e.g., fillers, flame retardants, etc.). For the classification of the different plastic samples, some machine learning algorithms were employed for the analysis of the LIBS spectroscopic data, such as the Principal Component Analysis (PCA) and the Linear Discriminant Analysis (LDA). The combination of LIBS technique with these machine learning algorithmic approaches, in particular the latter, provided excellent classification results, achieving identification accuracies as high as 100%. It seems that machine learning paves the way towards the application of LIBS technique for identification/discrimination issues of plastics and polymers and eventually of other classes of organic materials. Machine learning assisted LIBS can be a simple to use, efficient and powerful tool for sorting and recycling purposes.
关键词： laser-induced breakdown,polymers,LIBS,machine learning,identification of polymers,laser produced plasmas
更新于2025-09-16 10:30:52
-
Application of Scikit and Keras Libraries for the Classification of Iron Ore Data Acquired by Laser-Induced Breakdown Spectroscopy (LIBS)
摘要： Due to the complexity of, and low accuracy in, iron ore classification, a method of Laser‐Induced Breakdown Spectroscopy (LIBS) combined with machine learning is proposed. In the research, we collected LIBS spectra of 10 iron ore samples. At the beginning, principal component analysis algorithm was employed to reduce the dimensionality of spectral data, then we applied k‐nearest neighbor model, neural network model, and support vector machine model to the classification. The results showed that the accuracy of three models were 82.96%, 93.33%, and 94.07% respectively. The results also demonstrated that LIBS with machine learning model exhibits an excellent classification performance. Therefore, LIBS technique combined with machine learning can achieve a rapid, precise classification of iron ores, and can provide a completely new method for iron ores’ selection in the metallurgical industry.
关键词： machine learning,laser‐induced breakdown spectroscopy,iron ore,classification
更新于2025-09-16 10:30:52
-
Advanced DSP for Coherent Optical Fiber Communication
摘要： In this paper, we provide an overview of recent progress on advanced digital signal processing (DSP) techniques for high-capacity long-haul coherent optical fiber transmission systems. Not only the linear impairments existing in optical transmission links need to be compensated, but also, the nonlinear impairments require proper algorithms for mitigation because they become major limiting factors for long-haul large-capacity optical transmission systems. Besides the time domain equalization (TDE), the frequency domain equalization (FDE) DSP also provides a similar performance, with a much-reduced computational complexity. Advanced DSP also plays an important role for the realization of space division multiplexing (SDM). SDM techniques have been developed recently to enhance the system capacity by at least one order of magnitude. Some impressive results have been reported and have outperformed the nonlinear Shannon limit of the single-mode fiber (SMF). SDM introduces the space dimension to the optical fiber communication. The few-mode fiber (FMF) and multi-core fiber (MCF) have been manufactured for novel multiplexing techniques such as mode-division multiplexing (MDM) and multi-core multiplexing (MCM). Each mode or core can be considered as an independent degree of freedom, but unfortunately, signals will suffer serious coupling during the propagation. Multi-input–multi-output (MIMO) DSP can equalize the signal coupling and makes SDM transmission feasible. The machine learning (ML) technique has attracted worldwide attention and has been explored for advanced DSP. In this paper, we firstly introduce the principle and scheme of coherent detection to explain why the DSP techniques can compensate for transmission impairments. Then corresponding technologies related to the DSP, such as nonlinearity compensation, FDE, SDM and ML will be discussed. Relevant techniques will be analyzed, and representational results and experimental verifications will be demonstrated. In the end, a brief conclusion and perspective will be provided.
关键词： coherent detection,neural network,space division multiplexing,digital signal processing,nonlinearity compensation,machine learning,optical fiber communication,equalization
更新于2025-09-16 10:30:52
-
Photovoltaic defect classification through thermal infrared imaging using a machine learning approach
摘要： This study examines a deep learning and feature-based approach for the purpose of detecting and classifying defective photovoltaic modules using thermal infrared images in a South African setting. The VGG-16 and MobileNet models are shown to provide good performance for the classification of defects. The scale invariant feature transform (SIFT) descriptor, combined with a random forest classifier, is used to identify defective photovoltaic modules. The implementation of this approach has potential for cost reduction in defect classification over current methods.
关键词： photovoltaic,SIFT,machine learning,defect classification,random forest,deep learning,support vector machine,defect detection,infrared thermography
更新于2025-09-12 10:27:22
-
Forecasting Photovoltaic Power Generation via an IoT Network Using Nonlinear Autoregressive Neural Network
摘要： This research work is an attempt to introduce modern computing techniques as a potential decision-making tool in the field of renewable energy supply and management. We aim to demystify and take advantage of the concept of neural networks to predict the conversion of solar energy by a photovoltaic unit. In order to do so, a smart meter will be built and connected to a low power photovoltaic panel, the smart meter once in operation will capture a set of data, send them autonomously to a remote server over a LoRa IoT network which will be then processed to make predictions about the amount of power produced. Using Non Linear Autoregressive Neural Networks (NARX) with Matlab and Thingspeak IoT data capture, the results are favourable for open loop configuration although closed loop can be further improved, recommendations for the same are made at the end.
关键词： Photovoltaic,IoT Network,LoRa,Autoregressive Neural Network,Machine Learning,Supervised Learning
更新于2025-09-12 10:27:22
-
Dielectric or Plasmonic Mie Object at Air-Liquid Interface: The Transferred and the Travelling Momentum of Photon
摘要： In this article, considering the inhomogeneous or heterogeneous background, we have demonstrated that if the background and the half-immersed object are both non-absorbing, the transferred photon momentum to the pulled object can be considered as the one of Minkowski exactly at the interface. In contrast, the presence of loss inside matter, either in the half-immersed object or in the background, causes optical pushing of the object. Our analysis suggests: for half-immersed plasmonic or lossy dielectric, the ‘transferred’ momentum of photon can mathematically be modelled as the type of Minkowski and also of Abraham. However, according to a final critical analysis: the idea of Abraham momentum transfer has been rejected. Hence, an obvious question arises: ‘whence the Abraham momentum?’. It is demonstrated: though the ‘transferred’ momentum to a half-immersed Mie object (lossy or lossless) can better be considered as the Minkowski momentum; Lorentz force analysis suggests that the momentum of a photon travelling through the continuous background, however, can be modelled as the type of Abraham. Finally, as an interesting sidewalk, a machine learning based system has been developed to predict the time-averaged force within a very short time avoiding time-consuming full wave simulation.
关键词： optical force laws,dielectric interface,Abraham-Minkowski controversy,machine learning,optical tractor beams,optical pulling force
更新于2025-09-12 10:27:22
-
[IEEE 2019 21st International Conference on Transparent Optical Networks (ICTON) - Angers, France (2019.7.9-2019.7.13)] 2019 21st International Conference on Transparent Optical Networks (ICTON) - Neuromorphic Processing for Optical Communications
摘要： Neuromorphic computing has been recently demonstrated as a lucrative technology for communications systems. Optical neuromorphic technology enables implementation of machine learning algorithms in optical domain. We will discuss the recent progress, as well as, advantages and challenges of such technology for high speed and energy efficient signal processing.
关键词： optical signal processing,neuromorphic processing,fiber-optic communications,machine learning,neural networks
更新于2025-09-12 10:27:22
-
Estimation and forecast accuracy of regional photovoltaic power generation with upscaling method using the large monitoring data in Kyushu, Japan
摘要： In order to optimize photovoltaic (PV) output curtailment control, forecasting a regional PV power generation are an important issue. Its estimation is also important as a basic step prior to forecasts. Upscaling algorithm is general approach for evaluating and forecasting a regional PV power generation because the number of monitored plants is usually limited. However, the method leads to large error when the characteristics of monitored plants differ from those of unknown plants in a region. In this paper, we analysed the errors on estimation and forecast of regional PV power generation with upscaling method by using monitoring data obtained from 2219 small PV plants in Kyushu, Japan. As the results, random sampling method has sufficient accuracy for day-ahead and short-term forecasts in case of the large number of reference plants, and unlike forecasts the minimum estimation error does not remain flat and continued to decrease as the number of power plants increased.
关键词： Photovoltaic,Forecasts,Optimization,Estimation algorithms,Power control,Machine learning
更新于2025-09-12 10:27:22
-
Intelligent 2-dimensional soft decision enabled by k-means clustering for VCSEL-based 112-Gbps PAM-4 and PAM-8 optical interconnection
摘要： In this work, we proposed an intelligent 2-dimensional soft decision (2D SD) enabled by k-means clustering, for vertical-cavity surface-emitting laser (VCSEL) based 112-Gbps PAM-4 and PAM-8 optical interconnection. At high modulation speed, VCSEL based link suffers from severe level nonlinearity, level-dependent noise and inter-symbol interference (ISI). For characterizing the above-mentioned three distortions, 2D signaling is performed through time-slotted mapping of PAM. Without extra requirement of Monte Carlo approach, channel conditional probability density function (PDF) can be intelligently estimated using inline data, thanks to 2D k-means machine learning. Thus, improved precision of log likelihood ratio (LLR) can be realized by additional consideration of nonlinearity, level-dependent noise and ISI. Both simulations and experiments have been carried out for proof-of-concept investigations on VCSEL and multimode fiber (MMF) links. 112-Gbps PAM-4 and PAM-8 signaling have been experimentally realized using a commercial-product-level VCSEL with 100-m MMF transmission. The results indicate significant improvement of the proposed k-means 2D SD without training using prior-known sequences.
关键词： multidimensional signal processing,optical fiber communication,Decision support systems,machine learning
更新于2025-09-12 10:27:22