Search

In this paper, reducing the number of necessary measuring points for estimating a reflected electromagnetic spectrum of a printed color patch is presented. In our previous work, a machine learning-based method was proven to be superior to Cubic Hermite interpolation in estimating spectrum based on six measured values provided by measuring reflection of six LED sources (400 nm, 457 nm, 517 nm, 572 nm, 632 nm, and 700 nm). Now, the new hypothesis is that the number of measuring points LEDs could be decreased without the significant loss of the spectrum estimation. The ECI2002 test chart was used to create the dataset, which was further divided into training and test subset. For all the colors on the test chart, the measurements were performed on printed patches with the device proposed in our previous work, as well as with the commercial spectrophotometer X-Rite i1 Publish Pro2, which were then used as the ground truth, or reference values. The Artificial Neural Networks were trained to estimate spectrums based on measurements acquired with our device. The results proved satisfactory even when the number of measuring points is reduced from six to three RGB LEDs (457 nm, 517 nm, and 632 nm). [ABSTRACT FROM AUTHOR]

This paper aims to improve the channel estimation (CE) in the indoor visible light communication (VLC) system. We propose a system that depends on a comparison between Deep Neural Networks (DNN) and Kalman Filter (KF) algorithm for two optical modulation techniques; asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) and direct current optical-orthogonal frequency division multiplexing (DCO-OFDM). The channel estimation can be evaluated by changing the rate of errors in the received bits, where increased error means a performance decrease of the system and vice versa. Receiving less errors at the receiver indicates improved channel estimation and system performance. Thus, the main aim of our proposal is decreasing the error rate by using different estimators. Using the simulation results with the metric parameter of bit error rate (BER) aims to determine the improvement ratio between different systems. The proposed model is trained with OFDM signal samples with labels, where the labels represent the received signal after applying OFDM travelling across the medium. At a BER = 10–3 with DCO-OFDM, the DNN outperforms KF with 1.6 dB (7.6%) at the bit energy per noise (E b / N o) axis. Also, for ACO-OFDM at BER = 10–3, the DNN achieves better results than KF by about 1.3 dB (8.12%) at the (E b / N o). At different values of M in QAM, the DNN outperforms KF for ACO-OFDM by average improvement of ~ 1 dB (~ 11.5%). [ABSTRACT FROM AUTHOR]

At present, human translation is characterized by low efficiency, high cost, high consumption of resources and time, so it is urgent to study automatic translation technology to meet the needs of information interaction and language communication in various countries under the background of economic globalization. In order to improve the performance of Chinese-English translation system, this study aims to use optical network transmission technology to optimize the translation process. This research is based on deep learning model and uses optical network transmission technology to implement Chinese-English translation system. The neural network model is used to train the Chinese-English translation, and then the data is transmitted to the cloud for translation using optical network transmission technology. Finally, the translation result is returned to the user. The system can learn by itself on the basis of analyzing source documents, and predict target translation output by extracting features. The system is equipped with a translation engine based on the data source, which can realize interactive translation, and the final output can be achieved by processing the predicted translation output and based on the translator's understanding. Through the design of simulation experiments for system detection, the results show that the Chinese English translation model system has a high translation quality. By comparing it with the baseline system, it can be seen that both of them can translate sentences normally in 8 PR cycles (PR * 8, about 18% KSMR), and the data set improvement rate is about + 35 BLEU, that is, 76 BLEU is finally achieved. This proves that users can maintain the translation accuracy while reducing the number of effective interactions by using the optimized translation model to translate the target text, showing the effectiveness. In this paper, an interactive Chinese English translation system is designed by combining deep learning with cloud computing. [ABSTRACT FROM AUTHOR]

This paper introduces the Hybrid Quantum Deep Neural Network (HQDNN), a pioneering model that amalgamates classical Convolutional Neural Network (CNN) architecture with Parameterized Quantum Circuits (PmQC) for image classification tasks. The background elucidates the intricacies of CNN and PmQC operations, emphasizing their respective components and functions. HQDNN comprises quantum convolutional and pooling layers alongside a classical fully connected layer, demonstrating its effectiveness through simulations on the MNIST dataset. Results reveal HQDNN's superior learning ability and classification performance compared to traditional CNN, particularly with the inclusion of a pooling layer. This work contributes to the evolution of quantum machine learning, opening avenues for the practical integration of quantum computing in image classification workflows. Future research may explore scalability and diverse applications of HQDNN, marking a promising convergence of quantum computing and deep learning methodologies. [ABSTRACT FROM AUTHOR]

Machine Learning is an important field of research in current trends. The extended field of machine learning is Deep Learning and is used for various research areas such as neural networks, image and signal processing, pattern recognition, etc. The handwritten digit recognition is an important task or process included in various applications such as car number plate recognition, staff identity number detection, etc. This paper proposed the design and analysis of various deep learning algorithms such as deep neural networks, convolutional neural networks, LeNet-5, AlexNet and MiniVGGNet for handwritten digit recognition using MNIST dataset. [ABSTRACT FROM AUTHOR]

This paper extends previous studies work on the application of Machine Learning (ML) to distortion compensation in optical communication systems with optical fibers nonlinear coefficients (γ) that exceed current industry standards e.g. γ > 1.4 W - 1 k m - 1 . To quantify the improvement afforded by ML methods under different transmission conditions the procedures are applied to a model of a typical single-frequency optical communication system with, a 3200 km fiber length, double polarization, and a 16-QAM modulation format. The performance of both transmitters and receivers that incorporate Neural Networks (NNs) are then examined over a wide range of γ values. In all cases considered, the system Q-factor is improved although the degree of enhancement is dependent on the signal to noise ratio. The ML structures that were investigated include Siamese neural networks (SNN) implemented at the receiver end as well as two-stage architectures that employ NNs at the transmitter together with a classifier at the receiver side. Classifiers ranging from simple decision tree structures to boosting, forests, extra trees, and Multi-layer perceptron (MLP) were further examined and found to provide significant enhancement for γ > 4 W - 1 k m - 1 . The optimal performance for highly nonlinear systems was achieved for two-stage systems with random forest or extra tree classifiers. Finally, empirical equations for each ML technique were derived that relate the Q-factor enhancement and the value of γ , and the number of triplet terms that are input into the neural network. These results could potentially be employed to relax manufacturing constraints and accordingly reduce system costs. [ABSTRACT FROM AUTHOR]

In this paper, electronic semiconductor characterization using reverse-back procedure was applied to different photoacoustic responses aiming to find effective ambipolar diffusion coefficient and a bulk lifetime of the minority carriers. The main idea was to find the small fluctuations in investigated parameters due to detecting possible unwanted sample contaminations and temperature variations during the measurements. The mentioned procedure was based on the application of neural networks. Knowing that in experiments the contaminated surfaces of the sample can play a significant role in the global recombination process that we are measuring and that the unintentionally introduced defects of the sample crystal lattice could vary the carrier lifetime by several orders of magnitude, a method of PA signal adjustment by the reverse-back procedure is developed, based on the changes of the carrier electronic parameters. [ABSTRACT FROM AUTHOR]

In this paper, the influence of the input and output data scaling and normalization on the neural network overall performances is investigated aimed at inverse problem-solving in photoacoustics of semiconductors. The logarithmic scaling of the photoacoustic signal amplitudes as input data and numerical scaling of the sample thermal parameters as output data are presented as useful tools trying to reach maximal network precision. Max and min–max normalizations to the input data are presented to change their numerical values in the dataset to common scales, without distorting differences. It was demonstrated in theory that the largest network prediction error of all targeted parameters is obtained by a network with non-scaled output data. Also, it was found out that the best network prediction was achieved with min–max normalization of the input data and network predicted output data scale within the range of [1–10]. Network training and prediction performances analyzed with experimental input data show that the benefits and improvements of input and output scaling and normalization are not guaranteed but are strongly dependent on a specific problem to be solved. [ABSTRACT FROM AUTHOR]

This paper introduces the possibility of the determination of optical absorption and reflexivity coefficient of silicon samples using neural networks and reverse-back procedure based on the photoacoustics response in the frequency domain. Differences between neural network predictions and parameters obtained with standard photoacoustic signal correction procedures are used to adjust our experimental set-up due to the instability of the optical excitation source and the state (contamination) of the illuminated surface. It has been shown that the changes of the optical absorption values correspond to the light source wavelength fluctuations, while changes in the reflexivity coefficient, obtained in this way, correspond to the small effect of the ultrathin layer formation of SiO2 due to the natural process of surface oxidation. [ABSTRACT FROM AUTHOR]

In this paper, a novel optimization technique is proposed for designing photonic devices. The suggested approach relies on the use of radial bases function based artificial neural network (RBF-ANN) which shows an excellent performance in comparison with the conventional artificial neural network technique. The robustness of the suggested RBF-ANN approach is demonstrated through the numerical precision and fast convergence of the design cycle performed on a typical slanted rib waveguide polarization rotator, and ultra-flattened zero dispersion photonic crystal fiber. [ABSTRACT FROM AUTHOR]

In this paper, a new and an accurate artificial neural network approach (ANN) is presented for the analysis and design of photonic crystal fibers (PCFs). The new ANN approach is based on the radial basis functions which offer a very quick convergence and high efficiency during the ANN learning. The accuracy of the suggested approach is demonstrated via the excellent agreement between the results obtained using the presented approach and the results of the full vectorial finite difference method (FVFDM). In addition, a new design of highly birefringence PCF with low losses for the two polarized modes is presented using the proposed approach. [ABSTRACT FROM AUTHOR]

Artificial Neural Networks are developed as an important technique for equalization and have been widely used to mitigate the nonlinear effects in coherent optical systems. For the compensation of nonlinearities in coherent optical orthogonal frequency division multiplexing technique, the most popular artificial neural network model is a multilayer perceptron (MLP), as it is able to perform complex mapping between input and output spaces with significant success. However due to the complexity of multilayer perceptron nonlinear equalizer (MLP-NLE) model training of neural network is difficult. To overcome computational complexity issues of MLP-NLE, a single neuron based functional link artificial neural network nonlinear equalizer (FLANN-NLE) has been developed in this paper. Better performance of an equalizer is attributed to the usage of aPSO-BP algorithm for training the FLANN-NLE. The proposed FLANN-NLE surpasses the existing works both in terms of Q-Factor and computational complexity. For a fiber length of 1000 km and at launch power of −6 dBm, the improvement in Q-Factor is approximately equal to 3.3 and 1 dB in contrast to the previously reported values of approximately 3 and 0.7 dB at bit rate of 40 and 80 Gbps respectively. [ABSTRACT FROM AUTHOR]

In this article, we propose and demonstrate a generalized machine learning (ML) approach to analyse the various optical properties of the Fiber Bragg grating (FBGs), namely effective refractive index, bandwidth, reflectivity and wavelength. For this purpose, three commonly used variants of FBG, namely conventional, π phase-shifted and chirped ones are investigated and the reflected spectra of the aforementioned FBGs are predicted using ab initio artificial neural networks (ANNs). We implemented a simple and fast-training feed-forward ANN and established the efficacy of our model by predicting the output spectrum with minute details for unknown device parameters along with non-linear and complex behaviour of the spectrum. Thus, our proposed ANN model is capable of predicting various key optical properties and reproducing the exact spectrum accurately and quickly, providing a cost-effective solution for efficient and precise modelling. [ABSTRACT FROM AUTHOR]

In this article, a method for determination of photoacoustic detector transfer function as an accurate representation of microphone frequency response is presented. The method is based on supervised machine learning techniques, classification and regression, performed by two artificial neural networks. The transfer function is obtained by determining the microphone type and characteristic parameters closely related to its filtering properties. This knowledge is crucial within the signal correction procedure. The method is carefully designed in order to maintain requirements of photoacoustic experiment accuracy, reliability and real-time performance. The networks training is performed using large base of theoretical signals simulating frequency response of three types of commercial electret microphones frequently used in photoacoustic measurements extended with possible flat response of the so-called ideal microphone. The method test is performed with simulated and experimental signals assuming the usage of open-cell photoacoustic set-up. Experimental testing leads to the microphone transfer function determination used to correct the experimental signals, targeting the "true" undistorted photoacoustic response which can be further used in material characterization process. [ABSTRACT FROM AUTHOR]

A novel method for the continual, cuff-less estimation of the systolic blood pressure (SBP) and diastolic blood pressure (DBP) values based on signal complexity analysis of the photoplethysmogram (PPG) and the electrocardiogram (ECG) is reported. The proposed framework estimates the blood pressure (BP) values obtained from signals generated from 14 volunteers subjected to a series of exercise routines. Herein, the physiological signals were first pre-processed, followed by the extraction of complexity features from both the PPG and ECG. Subsequently the complexity features were used in regression models (artificial neural network (ANN), support vector machine (SVM) and LASSO) to predict the BP. The performance of the approach was evaluated by calculating the mean absolute error and the standard deviation of the predicted results and compared with the recommendations made by the British Hypertension Society (BHS) and Association for the Advancement of Medical Instrumentation. Complexity features from the ECG and PPG were investigated independently, along with the combined dataset. It was observed that the complexity features obtained from the combination of ECG and PPG signals resulted to an improved estimation accuracy for the BP. The most accurate DBP result of 5.15 ± 6.46 mmHg was obtained from ANN model, and SVM generated the most accurate prediction for the SBP which was estimated as 7.33 ± 9.53 mmHg. Results for DBP fall within recommended performance of the BHS but SBP is outside the range. Although initial results are promising, further improvements are required before the potential of this approach is fully realised. [ABSTRACT FROM AUTHOR]