Search Results (156)

We propose a probabilistic shaping (PS) scheme based on a single-layer lookup table (LUT) that employs only one LUT for symbol mapping while achieving favorable system performance. This scheme reduces the average power of the signal by adjusting the symbol distribution using a specialized LUT architecture and a flexible shaping proportion. The simulation results indicate that the proposed PS scheme delivers performance comparable to that of the conventional constant-composition distribution-matching-based probabilistic shaping (CCDM-PS) algorithm. Specifically, it reduces the bit error rate (BER) from 1.2376 $\times {10}^{-4}$ to 6.3256 $\times {10}^{-5}$, corresponding to a 48.89% improvement. The radial basis function neural network (RBFNN) effectively compensates for nonlinear distortions and further enhances transmission performance due to its simple architecture and strong capacity for nonlinear learning. In this work, we combine lookup-table-based probabilistic shaping (LUT-PS) with RBFNN-based nonlinear equalization for the first time, completing the transmission of 16-QAM OFDM signals over a photonic terahertz-over-fiber system operating at 400 GHz. Simulation results show that the proposed approach reduces the BER by 81.45% and achieves a maximum Q-factor improvement of up to 23 dB. Full article

Leveraging the human brain as a paradigm of energy-efficient computation, considerable attention has been paid to photonic neurons and neural networks to achieve higher computing efficiency and lower energy consumption. This study experimentally demonstrates on-chip silicon photonic neurons and neural networks based on thermally tunable microring resonators (MRRs) implement weighting and nonlinear operations. The weight component consists of eight cascaded MRRs thermally tuned within wavelength division multiplexing (WDM) architecture. The nonlinear response depends on the MRR’s nonlinear transmission spectrum, which is analogous to the rectified linear unit (ReLU) function. The matrix multiplication and recognition task of digits 2, 3, and 5 represented by seven-segment digital tube are successfully completed by using the photonic neural networks constructed by the photonic neurons based on the on-chip thermally tunable MRR as the nonlinear units. The power consumption of the nonlinear unit was about 5.65 mW, with an extinction ratio of about 25 dB between different digits. The proposed photonic neural network is CMOS-compatible, which makes it easy to construct scalable and large-scale multilayer neural networks. These findings reveal that there is great potential for highly integrated and scalable neuromorphic photonic chips. Full article

High demand for 6G wireless has made photonics-aided D-band (110–170 GHz) communication a research priority. Photonics-aided technology integrates optical and wireless communications to boost spectral efficiency and transmission distance. This study presents a Radio-over-Fiber (RoF) communication system utilizing photonics-aided technology for 4600 m long-distance D-band transmission. We successfully show the transmission of a 50 Gbps (25 Gbaud) QPSK signal utilizing a 128.75 GHz carrier frequency. Notwithstanding these encouraging outcomes, RoF systems encounter considerable obstacles, including pronounced nonlinear distortions and phase noise related to laser linewidth. Numerous factors can induce nonlinear impairments, including high-power amplifiers (PAs) in wireless channels, the operational mechanisms of optoelectronic devices (such as electrical amplifiers, modulators, and photodiodes), and elevated optical power levels during fiber transmission. Phase noise (PN) is generated by laser linewidth. Despite the notable advantages of classical Volterra series and deep neural network (DNN) methods in alleviating nonlinear distortion, they display considerable performance limitations in adjusting for phase noise. To address these problems, we propose a novel post-processing approach utilizing a two-dimensional convolutional neural network (2D-CNN). This methodology allows for the extraction of intricate features from data preprocessed using traditional Digital Signal Processing (DSP) techniques, enabling concurrent compensation for phase noise and nonlinear distortions. The 4600 m long-distance D-band transmission experiment demonstrated that the proposed 2D-CNN post-processing method achieved a Bit Error Rate (BER) of 5.3 × 10⁻³ at 8 dBm optical power, satisfying the soft-decision forward error correction (SD-FEC) criterion of 1.56 × 10⁻² with a 15% overhead. The 2D-CNN outperformed Volterra series and deep neural network approaches in long-haul D-band RoF systems by compensating for phase noise and nonlinear distortions via spatiotemporal feature integration, hierarchical feature extraction, and nonlinear modelling. Full article

In this paper, we propose a recurrent neural network numerical method with the finite element method for partial differential equations to study the band gap structure and Dirac points in two-dimensional photonic crystals. Electromagnetic wave propagation is governed by Maxwell’s equations. We transform the partial differential equations into large-scale generalized eigenvalue problems by spatially discretising them using the finite element method. Compared with traditional numerical computation methods, neural networks can perform high-speed parallel computation. Existing neural network-based eigenvalue solvers are typically restricted to computing extremal eigenvalues of real symmetric matrix pairs. To overcome this limitation, we develop a novel RNN-based numerical scheme tailored for solving the band structure problem in photonic crystals. We validate our method by computing the dispersion relations of photonic crystals with periodic dielectric columns, achieving excellent agreement with the plane-wave expansion method. In addition, we calculate the Dirac points at the center of the Brillouin zone, which is crucial for understanding the unique optical properties of photonic crystals. We determine the precise filling ratios at which these Dirac points appear, thus providing insight into the relationship between geometrical and material parameters and the appearance of Dirac points. Full article

Background/Objectives: 123I-FP-CIT dopamine transporter imaging is commonly used for the diagnosis of Parkinsonian syndromes in patients whose clinical presentation is atypical. Prolonged immobility, which can be difficult to maintain in this population, is required to perform SPECT acquisition. In this study we aimed to develop a Convolutional Neural Network (CNN) able to predict the outcome of the full examination based on the first acquired projection, and reliably detect normal patients. Methods: All 123I-FP-CIT SPECT performed in our center between June 2017 and February 2024 were included and split between a training and a validation set (70%/30%). An additional 100 SPECT were used as an independent test set. Examinations were labeled by two independent physicians. A VGG16-like CNN model was trained to assess the probability of examination abnormality from the first acquired projection (anterior and posterior view at 0°), taking age into consideration. A threshold maximizing sensitivity while maintaining good diagnostic accuracy was then determined. The model was validated in the independent testing set. Saliency maps were generated to visualize the most impactful areas in the classification. Results: A total of 982 123I-FP-CIT SPECT were retrieved and labelled (training set: 618; validation set: 264; independent testing set: 100). The trained model achieved a sensibility of 98.0% and a negative predictive value of 96.3% (one false negative) while maintaining an accuracy of 75.0%. The saliency maps confirmed that the regions with the greatest impact on the final classification corresponded to clinically relevant areas (basal ganglia and background noise). Conclusions: Our results suggest that this trained CNN could be used to exclude presynaptic dopaminergic loss with high reliability from the first acquired projection. It could be particularly useful in patients with compliance issues. Confirmation with images from other centers will be necessary. Full article

Recently, Fano resonance modulators and photonic crystal nanobeam cavities (PCNCs) have attracted more and more attention due to their superior performance, such as high modulation efficiency and high extinction ratio (ER). In this paper, a silicon Fano resonance Mach–Zehnder modulator (MZM) based on a single arm coupled with a PCNC is theoretically analyzed, designed, and numerically simulated. By optimizing the coupling length, lattice constant, coupling gap, and the number of holes in the mirror/taper region, the ER of our MZM can achieve 34 dB. When the applied voltage of the MZM is biased at 4.3 V and the non-return-to-zero on–off keying (NRZ-OOK) signal at a data rate of 10 Gbit/s is modulated, the sharpest asymmetric resonant peak and the most remarkable Fano line shape can be obtained around a wavelength of 1550.68 nm. Compared with the traditional nanobeam cavities, along with the varying radii, our PCNC design has holes with a fixed radius of 90 nm, which is suitable to be fabricated by a 180 nm passive silicon photonic multi-project wafer (MPW). Therefore, our compacted lab-on-chip, resonance-based silicon photonic MZM that is coupled with a PCNC has the advantages of superior performance and easy fabrication, which provide support for photonic integrated circuit designs and can be beneficial to various silicon photonic application fields, including photonic computing, photonic convolutional neural networks, and optical communications, in the future. Full article

The photon detection capability of quanta image sensors make them an optimal choice for low-light imaging. To address Possion noise in QIS reconstruction caused by spatio-temporal oversampling characteristic, a deep learning-based noise suppression reconstruction method is proposed in this paper. The proposed neural network integrates convolutional neural networks and Transformers. Its architecture combines the Anscombe transformation with serial and parallel modules to enhance denoising performance and adaptability across various scenarios. Experimental results demonstrate that the proposed method effectively suppresses noise in QIS image reconstruction. Compared with representative methods such as TD-BM3D, QIS-Net and DPIR, our approach achieves up to 1.2 dB improvement in PSNR, demonstrating superior reconstruction quality. Full article

Two-photon polymerization (TPP) is an effective and rapid method for prototyping diffractive neural networks (DNNs). However, DNNs’ accuracy can be diminished by phase aberrations resulting from substrate misalignment in fabrication. To address this, we introduce index-matched two-photon polymerization (IM-TPP) for fabricating DNNs. Numerical simulations show that DNNs’ accuracy on tilted substrates improved from 91.50% to 95.00%. Experimentally, the IM-TPP process enhances device accuracy by 3.00% (91.67% to 94.67%), closely matching the theoretical simulated accuracy of 95.03%. Additionally, the average accuracy of multiple batches of samples reached 94.86%. IM-TPP reduces the influence of tilt error, improves device performance and manufacturing repeatability, and provides a new method for rapid prototyping of high-precision optical computing elements. Full article

We simulate hadrons impinging on a homogeneous lead tungstate (${\mathrm{PbWO}}_4$) calorimeter using GEANT4 software to investigate how the resulting light yield and its temporal structure, as detected by an array of light-sensitive sensors, can be processed by a neuromorphic computing system. Our model encodes temporal photon distributions as spike trains and employs a fully connected spiking neural network to estimate the total deposited energy, as well as the position and spatial distribution of the light emissions within the sensitive material. The extracted primitives offer valuable topological information about the shower development in the material, achieved without requiring a segmentation of the active medium. A potential nanophotonic implementation using III-V semiconductor nanowires is discussed. It can be both fast and energy efficient. Full article

Brain-inspired neuromorphic computing is expected to overcome the von Neumann bottleneck by eliminating the memory wall between processing and memory units. Nevertheless, critical challenges persist in synaptic device implementation, particularly regarding nonlinear/asymmetric conductance modulation and multilevel conductance states, which substantially impede the realization of high-performance neuromorphic hardware. This study demonstrates a novel advancement in photonic–electronic modulated synaptic devices through the development of an amorphous indium–gallium–zinc oxide (a-IGZO) synaptic transistor. The device demonstrates biological synaptic functionalities, including excitatory/inhibitory post-synaptic currents (EPSCs/IPSCs) and spike-timing-dependent plasticity, while achieving excellent conductance modulation characteristics (nonlinearity of 0.0095/−0.0115 and asymmetric ratio of 0.247) and successfully implementing Pavlovian associative learning paradigms. Notably, systematic neural network simulations employing the experimental parameters reveal a 93.8% recognition accuracy on the MNIST handwritten digit dataset. The a-IGZO synaptic transistor with photonic–electronic co-modulation serves as a potential critical building block for constructing neuromorphic architectures with human-brain efficiency. Full article

Underwater optical imaging plays a crucial role in maritime safety, enabling reliable navigation, efficient search and rescue operations, precise target recognition, and robust military reconnaissance. However, conventional underwater imaging methods often suffer from severe backscattering noise, limited detection range, and reduced image clarity—challenges that are exacerbated in turbid waters. To address these issues, Underwater Laser Range-Gated Imaging has emerged as a promising solution. By selectively capturing photons within a controlled temporal gate, this technique effectively suppresses backscattering noise-enhancing image clarity, contrast, and detection range. Nevertheless, residual noise within the imaging slice can still degrade image quality, particularly in challenging underwater conditions. In this study, we propose an enhanced U-Net neural network designed to mitigate noise interference in underwater laser range-gated images, improving target recognition performance. Built upon the U-Net architecture with added residual connections, our network combines a VGG16-based perceptual loss with Mean Squared Error (MSE) as the loss function, effectively capturing high-level semantic features while preserving critical target details during reconstruction. Trained on a semi-synthetic grayscale dataset containing synthetically degraded images paired with their reference counterparts, the proposed approach demonstrates improved performance compared to several existing underwater image restoration methods in our experimental evaluations. Through comprehensive qualitative and quantitative evaluations, underwater target detection experiments, and real-world oceanic validations, our method demonstrates significant potential for advancing maritime safety and related applications. Full article

Cardiovascular disease (CVD) is a leading cause of death, accounting for over 30% of annual global fatalities. Ischemic heart disease, in turn, is a frontrunner of worldwide CVD mortality. With the burden of coronary disease rapidly growing, understanding the nuances of cardiac imaging and risk prognostication becomes paramount. Myocardial perfusion imaging (MPI) is a frequently utilized and well established testing modality due to its significant clinical impact in disease diagnosis and risk assessment. Recently, nuclear cardiology has witnessed major advancements, driven by innovations in novel imaging technologies and improved understanding of cardiovascular pathophysiology. Applications of artificial intelligence (AI) to MPI have enhanced diagnostic accuracy, risk stratification, and therapeutic decision-making in patients with coronary artery disease (CAD). AI techniques such as machine learning (ML) and deep learning (DL) neural networks offer new interpretations of immense data fields, acquired through cardiovascular imaging modalities such as nuclear medicine (NM). Recently, AI algorithms have been employed to enhance image reconstruction, reduce noise, and assist in the interpretation of complex datasets. The rise of AI in nuclear medicine (AI-NM) has proven itself groundbreaking in the efficiency of image acquisition, post-processing time, diagnostic ability, consistency, and even in risk-stratification and outcome prognostication. To that end, this narrative review will explore these latest advances in AI in nuclear medicine and its rapid transformation of the cardiac diagnostics landscape. This paper will examine the evolution of AI-NM, review novel AI techniques and applications in nuclear cardiac imaging, summarize recent AI-NM clinical trials, and explore the technical and clinical challenges in its implementation of artificial intelligence. Full article

Fourier Neural Operators (FNOs) have gained increasing attention for their effectiveness in extracting frequencydomain features and efficiently approximating functions, making them wellsuited for classification tasks. However, the absence of specialized photonic hardware has limited the acceleration of FNO inference. In this study, we introduce what we believe is the first photonic hardware framework dedicated to speeding up the Fourier layer of an FNO. Our approach employs a frequency domain convolutional photonic chip and a micro-ring array chip, achieving 5-bit quantization precision in the inference process. On the Radio ML 2016.10b dataset, our Fourier convolutional neural network achieves a peak identification accuracy of 95.50%, outperforming standard convolution-based networks. These findings highlight the transformative potential of co-designing software and hardware, demonstrating how photonic computing can deliver specialized acceleration for critical AI components and substantially improve inference efficiency. Ultimately, this work lays a foundation for integrating photonic technologies into next-generation AI accelerators, pointing to a promising direction for further research and development in optoelectronic hybrid computing. Full article

Photonic millimeter-wave communication systems are promising for high-capacity, high-speed wireless networks, and their production is driven by the growing demand from data-intensive applications. However, challenges such as inter-symbol interferences (ISIs), inter-band interferences (IBIs), symbol timing offsets (STOs), and nonlinearity impairments exist, especially in non-orthogonal multiband configurations. This paper proposes and demonstrates the neural network-based waveform-to-symbol converter (NNWSC) for a coordinated multi-input and single-output (MISO) photonic millimeter-wave system with multiband multiplexing. The NNWSC replaces conventional matched filtering, down-sampling, and equalization, simplifying the receiver and enhancing interference resilience. Additionally, it reduces computational complexity, improving operational feasibility. As a proof of concept, experiments are conducted in a 16QAM non-orthogonal multiband carrierless amplitude and phase (NM-CAP) modulation system with coordinated MISO configurations in a scenario where two base stations have 5 km and 10 km fiber links, respectively. Data were collected across various roll-off factors, sub-band spacings, and received optical power (ROP) levels. Based on the proposed method, a coordinated MISO photonic millimeter-wave (mmWave) communication system at 91.9 GHz is demonstrated at a transmission speed of 30 Gbps. The results show that the NNWSC-based receiver achieves significant bit error rate (BER) reductions compared to conventional receivers across all configurations. The tolerances to the STO of NNWSC are also studied. These findings highlight NNWSC integration as a promising solution for high-frequency, interference-prone environments, with potential improvements for low-SNR and dynamic STO scenarios. Full article

Upon the advent of the big data era, information processing hardware platforms have undergone explosive development, facilitating unprecedented computational capabilities while significantly reducing energy consumption. However, conventional electronic computing hardware, despite significant upgrades in architecture optimization and chip scaling, still faces fundamental limitations in speed and energy efficiency due to Joule heating, electromagnetic crosstalk, and capacitance. A new type of information processing hardware is urgently needed for emerging data-intensive applications such as face identification, target tracking, and autonomous driving. Recently, integrated photonics computing architecture, which possesses remarkable compactness, wide bandwidth, low latency, and inherent parallelism, has harvested great attention due to its enormous potential to accelerate parallel data processing, such as digital image convolution. In this study, an integrated photonic processor based on a Mach-Zehnder interferometer (MZI) network is proposed and demonstrated. The processor, being scalable and compatible with complementary metal oxide semiconductors, facilitates mass production and seamless integration with other silicon-based optoelectronic devices. An experimental verification for digital image convolution is also performed, and the result deviations between our processor and a commercial 64-bit computer are less than 2.3%. Full article