Machine learning-based classification of structured light modes under turbulence and eavesdropping effects.

This paper considers the classification of multiplexed structured light modes, aiming to bolster communication reliability and data transfer rates, particularly in challenging scenarios marked by turbulence and potential eavesdropping. An experimental free-space optic (FSO) system is established to transmit 16 modes [8-ary Laguerre Gaussian (LG) and 8-ary superposition LG (Mux-LG) mode patterns] over a 3-m FSO channel, accounting for interception threats and turbulence effects. To the best of authors' knowledge, this paper is the first to consider both factors concurrently. We propose four machine/deep learning algorithms-artificial neural network, support vector machine, 1D convolutional neural network, and 2D convolutional neural network-for classification purposes. By fusing the outputs of these methods, we achieve promising classification results exceeding 92%, 81%, and 69% in cases of weak, moderate, and strong turbulence, respectively. Structured light modes exhibit significant potential for a variety of real-world applications where reliable and high-capacity data transmission is crucial.

Multievent localization for loop-based Sagnac sensing system using machine learning.

In optical sensing applications such as pipeline monitoring and intrusion detection systems, accurate localization of the event is crucial for timely and effective response. This paper experimentally demonstrates multievent localization for long perimeter monitoring using a Sagnac interferometer loop sensor and machine learning techniques. The proposed method considers the multievent localization problem as a multilabel multiclassification problem by dividing the optical fiber into 250 segments. A deep neural network (DNN) model is used to predict the likelihood of event occurrence in each segment and accurately locate the events. The sensing loop comprises 106.245 km of single-mode fiber, equivalent to ∼50 km of effective sensing distance. The training dataset is constructed in simulation using VPItransmissionMaker, and the proposed machine learning model's complexity is reduced by using discrete cosine transform (DCT). The designed DNN is tested for event localization in both simulation and experiment. The simulation results show that the proposed model achieves an accuracy of 99% in predicting the location of one event within one segment error, an accuracy of 95% in predicting the location of one event out of the two within one segment error, and an accuracy of 78% in predicting the location of the two events within one segment error. The experimental results validate the simulation ones, demonstrating the proposed model's effectiveness in accurately localizing events with high precision. In addition, the paper includes a discussion on extending the proposed model to sense more than two events simultaneously.

Real-Time Detection of Intruders Using an Acoustic Sensor and Internet-of-Things Computing.

Modern home automation systems include features that enhance security, such as cameras and radars. This paper proposes an innovative home security system that can detect burglars by analyzing acoustic signals and instantly notifying the authorized person(s). The system architecture incorporates the concept of the Internet of Things (IoT), resulting in a network and a user-friendly system. The proposed system uses an adaptive detection algorithm, namely the "short-time-average through long-time-average" algorithm. The proposed algorithm is implemented by an IoT device (Arduino Duo) to detect people's acoustical activities for the purpose of home/office security. The performance of the proposed system is evaluated using 10 acoustic signals representing actual events and background noise. The acoustic signals were generated by the sounds of keys shaking, the falling of a small object, the shrinking of a plastic bag, speaking, footsteps, etc. The effects of different algorithms' parameters on the performance of the proposed system have been thoroughly investigated.

Strain FBG-Based Sensor for Detecting Fence Intruders Using Machine Learning and Adaptive Thresholding.

This paper demonstrates an intruder detection system using a strain-based optical fiber Bragg grating (FBG), machine learning (ML), and adaptive thresholding to classify the intruder as no intruder, intruder, or wind at low levels of signal-to-noise ratio. We demonstrate the intruder detection system using a portion of a real fence manufactured and installed around one of the engineering college's gardens at King Saud University. The experimental results show that adaptive thresholding can help improve the performance of machine learning classifiers, such as linear discriminant analysis (LDA) or logistic regression algorithms in identifying an intruder's existence at low optical signal-to-noise ratio (OSNR) scenarios. The proposed method can achieve an average accuracy of 99.17% when the OSNR level is <0.5 dB.

Performance investigation of an ambiguity function-shaped waveform (AFSW) using a photonics-based radar system.

In this work, we investigate the performance of an ambiguity function-shaped waveform (AFSW) using a millimeter-wave photonics-based radar system at 100 GHz. An AFSW is a radar waveform whose ambiguity function can be shaped to increase the peak-to-sidelobe ratio (PSR) for better detectability of targets in a desired range/velocity region. To the best of the authors' knowledge, this paper is the first in the literature that investigates the performance of such a waveform in a photonics-based radar system. We experimentally compare the AFSW performance to the conventional frequency-modulated continuous wave (FMCW). The experimental results show the ability of the AFSW to achieve a PSR of 38.35 dB compared to the PSR of 14.5 dB obtained using the conventional FMCW. Moreover, we investigate the effects of some optical system impairments on the AFSW, such as: (i) optical modulator nonlinearity, (ii) optical modulator bias drift, and (iii) sampling offset error between the transmitter and receiver.

Discriminative strain and temperature sensing using a ring-hyperbolic tangent fiber sensor.

Brillouin fiber sensors have demonstrated strong capability in discriminative and high-sensitivity multiparameter measurements. In this study, we proposed and numerically investigated novel ring core fiber-based stimulated Brillouin scattering for the simultaneous measurement of temperature and strain. The novel fiber, referred to as ring hyperbolic tangent (R-HTAN) fiber, is characterized by a shape parameter (α) that controls the optical refractive index and longitudinal acoustic velocity profiles. Numerical modal simulations indicated that the Brillouin gain spectrum contained multiple widely spaced and high-gain peaks, which were attributed to the strong interaction between the optical linearly polarized mode (i.e., LP0,1 as a pump wave) and multiple high-order longitudinal acoustic modes. The designed R-HTAN fiber enabled the discriminative sensing of temperature and strain with levels that clearly surpassed values recently reported in the literature. In case of straight R-HTAN fiber (α = 0), the maximum C(α=0)T and C(α=0)ε are 1.928 MHz/ ∘C and 0.087 MHz, respectively. In case of graded R-HTAN fiber (α = 1), the maximum C(α=1)T and C(α=1)ε are 1.872 MHz/ ∘C and 0.0842 MHz/µÉ›, respectively. The errors associated with temperature measurements (maximum δT(α=0) = 0.0846 ∘C and maximum δT(α=1) = 7.4184 ∘C) and strain measurements (maximum δɛ(α=0) = 0.7250 µÉ› and maximum δɛ(α=1) = 7.4184 µÉ›) demonstrated that the proposed fiber could be a promising candidate for next-generation Brillouin sensing systems for enabling temperature and strain discrimination.

Reconfigurable photonics-based millimeter wave signal aggregation for non-orthogonal multiple access.

A reconfigurable optical-to-electrical signal aggregation is proposed, for the first time, using optical signal processing and photo-mixing technology. Two optically modulated quadrature phase-shift keying (QPSK) signals are aggregated into a single 16-quadrature amplitude modulation (16-QAM) signal and, simultaneously, carried over a 28-GHz millimeter wave (MMW) carrier using an optimized heterodyne beating process through a single photodiode. To demonstrate the system reconfigurability, aggregation of two optical binary phase-shift keying signals is mapped into MMW QPSK or four-level pulse amplitude modulation signals by controlling the relative phases and amplitudes, respectively, of the input signals. In addition, the aggregation of two 16-QAM signals into a 256-QAM signal and the aggregation of three QPSK signals into a 64-QAM format are achieved. Besides, we report the effect of laser phase noise on signal aggregation performance. The de-aggregation of the aggregated MMW signals is performed electrically using a successive interference cancellation algorithm. Moreover, a proof-of-concept experiment is conducted to validate the numerical simulations. Two 1-Gbaud BPSK (1 Gbps) and QPSK (2 Gbps) optical signals are optically transmitted over a 20-km single-mode fiber as MMW over fiber signals. Then, the signals are aggregated into QPSK (2 Gbps) and 16-QAM (4 Gbps) 28-GHz MMW signals, respectively. The aggregated signal is further transmitted over a 1-m wireless channel. The performance of the proposed system is evaluated using bit error rate and error vector magnitude metrics.

Deep convolutional neural networks for COVID-19 automatic diagnosis.

This article is mainly concerned with COVID-19 diagnosis from X-ray images. The number of cases infected with COVID-19 is increasing daily, and there is a limitation in the number of test kits needed in hospitals. Therefore, there is an imperative need to implement an efficient automatic diagnosis system to alleviate COVID-19 spreading among people. This article presents a discussion of the utilization of convolutional neural network (CNN) models with different learning strategies for automatic COVID-19 diagnosis. First, we consider the CNN-based transfer learning approach for automatic diagnosis of COVID-19 from X-ray images with different training and testing ratios. Different pre-trained deep learning models in addition to a transfer learning model are considered and compared for the task of COVID-19 detection from X-ray images. Confusion matrices of these studied models are presented and analyzed. Considering the performance results obtained, ResNet models (ResNet18, ResNet50, and ResNet101) provide the highest classification accuracy on the two considered datasets with different training and testing ratios, namely 80/20, 70/30, 60/40, and 50/50. The accuracies obtained using the first dataset with 70/30 training and testing ratio are 97.67%, 98.81%, and 100% for ResNet18, ResNet50, and ResNet101, respectively. For the second dataset, the reported accuracies are 99%, 99.12%, and 99.29% for ResNet18, ResNet50, and ResNet101, respectively. The second approach is the training of a proposed CNN model from scratch. The results confirm that training of the CNN from scratch can lead to the identification of the signs of COVID-19 disease.

Free space optic channel monitoring using machine learning.

Free space optic (FSO) is a type of optical communication where the signal is transmitted in free space instead of fiber cables. Because of this, the signal is subject to different types of impairments that affect its quality. Predicting these impairments help in automatic system diagnosis and building adaptive optical networks. Using machine learning for predicting the signal impairments in optical networks has been extensively covered during the past few years. However, for FSO links, the work is still in its infancy. In this paper, we consider predicting three channel parameters in FSO links that are related to amplified spontaneous emission (ASE) noise, turbulence, and pointing errors. To the best of authors knowledge, this work is the first to consider predicting FSO channel parameters under the effect of more than one impairment. First, we report the performance of predicting the FSO parameters using asynchronous amplitude histogram (AAH) and asynchronous delay-tap sampling (ADTS) histogram features. The results show that ADTS histogram features provide better prediction accuracy. Second, we compare the performance of support vector machine (SVM) regressor and convolutional neural network (CNN) regressor using ADTS histogram features. The results show that CNN regressor outperforms SVM regressor for some cases, while for other cases they have similar performance. Finally, we investigate the capability of CNN regressor for predicting the channel parameters for three different transmission speeds. The results show that the CNN regressor has good performance for predicting the OSNR parameter regardless of the value of transmission speed. However, for the turbulence and pointing errors, the prediction under low speed transmission is more accurate than under high speed transmission.

mmW Rotman Lens-Based Sensing: An Investigation Study.

A Rotman lens is a wideband true-time delay device. Due to its simplistic structure with wave/signal routing capabilities, it has been widely utilized as a beamforming device in numerous communication systems. Since the basic Rotman lens design incorporates multiple input, output, and dummy ports, in this study, and for the first time, we utilized a Rotman lens as a sensor. The main idea was to gather abundant information from available Rotman lens ports to obtain better sensing performance. The realized lens is optimized to work in the millimeter wave (mmW) band from 27 to 29 GHz with a focus on a central frequency of 28 GHz. The design has a footprint of 140 × 103 × 0.8 mm3. The polarity correlator was used to characterize the material under investigation.

Modulation format identification of optical signals: an approach based on singular value decomposition of Stokes space projections.

In this paper, two Stokes space (SS) analysis schemes for modulation format identification (MFI) are proposed. These schemes are based on singular value decomposition (SVD) and Radon transform (RT) for feature extraction. The singular values (SVs) are extracted from the SS projections for different modulation formats to discriminate between them. The SS projections are obtained at different optical signal-to-noise ratios (OSNRs) ranging from 11 to 30 dB for seven dual-polarized modulation formats. The first scheme depends on the SVDs of the SS projections on three planes, while the second scheme depends on the SVDs of the RTs of the SS projections. Different classifiers including support vector machine (SVM), decision tree (DT), and K-nearest neighbor (KNN) for MFI based on the obtained features are used. Both simulation and experimental setups are arranged and tested for proof of concept of the proposed schemes for the MFI task. Complexity reduction is studied for the SVD scheme by applying the decimation of the projections by two and four to achieve an acceptable classification rate, while reducing the computation time. Also, the effect of the variation of phase noise (PN) and state of polarization (SoP) on the accuracy of the MFI is considered at all OSNRs. The two proposed schemes are capable of identifying the polarization multiplexed modulation formats blindly with high accuracy levels up to 98%, even at low OSNR values of 12 dB, high PN levels up to 10 MHz, and SoP up to 45°.

Identifying structured light modes in a desert environment using machine learning algorithms.

The unique orthogonal shapes of structured light beams have attracted researchers to use as information carriers. Structured light-based free space optical communication is subject to atmospheric propagation effects such as rain, fog, and rain, which complicate the mode demultiplexing process using conventional technology. In this context, we experimentally investigate the detection of Laguerre Gaussian and Hermite Gaussian beams under dust storm conditions using machine learning algorithms. Different algorithms are employed to detect various structured light encoding schemes including the use of a convolutional neural network (CNN), support vector machine, and k-nearest neighbor. We report an identification accuracy of 99% under a visibility level of 9 m. The CNN approach is further used to estimate the visibility range of a dusty communication channel.

QuPWM: Feature Extraction Method for Epileptic Spike Classification.

Epilepsy is a neurological disorder ranked as the second most serious neurological disease known to humanity, after stroke. Inter-ictal spiking is an abnormal neuronal discharge after an epileptic seizure. This abnormal activity can originate from one or more cranial lobes, often travels from one lobe to another, and interferes with normal activity from the affected lobe. The common practice for Inter-ictal spike detection of brain signals is via visual scanning of the recordings, which is a subjective and a very time-consuming task. Motivated by that, this article focuses on using machine learning for epileptic spikes classification in magnetoencephalography (MEG) signals. First, we used the Position Weight Matrix (PWM) method combined with a uniform quantizer to generate useful features from time domain and frequency domain through a Fast Fourier Transform (FFT) of the framed raw MEG signals. Second, the extracted features are fed to standard classifiers for inter-ictel spikes classification. The proposed technique shows great potential in spike classification and reducing the feature vector size. Specifically, the proposed technique achieved average sensitivity up to 87% and specificity up to 97% using 5-folds cross-validation applied to a balanced dataset. These samples are extracted from nine epileptic subjects using a sliding frame of size 95 samples-points with a step-size of 8 sample-points.

Feature Generation and Dimensionality Reduction using the Discrete Spectrum of the Schrödinger Operator for Epileptic Spikes Detection.

Epilepsy is a neurological disorder classified as the second most serious neurological disease known to humanity, after stroke. Magnetoencephalography (MEG) is performed to localize the epileptogenic zone in the brain. However, the detection of epileptic spikes requires the visual assessment of long MEG recordings. This task is time-consuming and might lead to wrong decisions. Therefore, the introduction of effective machine learning algorithms for the quick and accurate epileptic spikes detection from MEG recordings would improve the clinical diagnosis of the disease. The efficiency of machine learning based algorithms requires a good characterization of the signal by extracting pertinent features. In this paper, we propose new sets of features for MEG signals. These features are based on a Semi-Classical Signal Analysis (SCSA) method, which allows a good characterization of peak shaped signals. Moreover, this method improves the spike detection accuracy and reduces the feature vector size. We could achieve up to 93.68% and 95.08% in average sensitivity and specificity, respectively. We used the 5-folds cross-validation applied to a balanced dataset of 3104 frames, extracted from eight healthy and eight epileptic subjects with a frame size of 100 samples with a step size of 2 samples, using Random Forest (RF) classifier.

Epileptic Seizure Prediction Using CSP and LDA for Scalp EEG Signals.

This paper presents a patient-specific epileptic seizure predication method relying on the common spatial pattern- (CSP-) based feature extraction of scalp electroencephalogram (sEEG) signals. Multichannel EEG signals are traced and segmented into overlapping segments for both preictal and interictal intervals. The features extracted using CSP are used for training a linear discriminant analysis classifier, which is then employed in the testing phase. A leave-one-out cross-validation strategy is adopted in the experiments. The experimental results for seizure prediction obtained from the records of 24 patients from the CHB-MIT database reveal that the proposed predictor can achieve an average sensitivity of 0.89, an average false prediction rate of 0.39, and an average prediction time of 68.71 minutes using a 120-minute prediction horizon.

Epileptic MEG Spike Detection Using Statistical Features and Genetic Programming with KNN.

Epilepsy is a neurological disorder that affects millions of people worldwide. Monitoring the brain activities and identifying the seizure source which starts with spike detection are important steps for epilepsy treatment. Magnetoencephalography (MEG) is an emerging epileptic diagnostic tool with high-density sensors; this makes manual analysis a challenging task due to the vast amount of MEG data. This paper explores the use of eight statistical features and genetic programing (GP) with the K-nearest neighbor (KNN) for interictal spike detection. The proposed method is comprised of three stages: preprocessing, genetic programming-based feature generation, and classification. The effectiveness of the proposed approach has been evaluated using real MEG data obtained from 28 epileptic patients. It has achieved a 91.75% average sensitivity and 92.99% average specificity.