Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Optical single-sideband (SSB) transmission enhances spectral efficiency and mitigates transmission reach limitations caused by chromatic dispersion (CD), making it ideal for cost-effective data-center interconnects. This paper proposes and demonstrates deep neural network (DNN)-enabled optical performance monitoring (OPM) for optical SSB transmissions. By extracting features dependent on both carrier-to-signal power ratio (CSPR) and optical signal-to-noise ratio (OSNR) from amplitude histograms (AHs) generated by an AC-coupled photodetector (PD) and an analog-to-digital converter (ADC), a low-complexity dual-task DNN (DT-DNN) is employed to jointly estimate CSPR and OSNR with high accuracy. Numerical results show that for a 50 GBaud 16-QAM SSB signal, the root mean square error (RMSE) values for CSPR estimation (2-11 dB range) and OSNR estimation (14-23 dB range) are 0.14 dB and 0.29 dB, respectively, under back-to-back (B2B) transmission. After transmission over 80 km of standard single-mode fiber (SSMF), the corresponding RMSE values increase to 0.17 dB and 0.33 dB, respectively. Experimental validation using a 25 GBaud 16-QAM SSB signal over 40 km of SSMF yields RMSE values for CSPR and OSNR estimation of less than 0.26 dB and 0.80 dB, respectively. The proposed technique shows great potential for real-time OPM in high-speed optical SSB transmission systems.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1364/OE.554252 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Humans exercising in the heat: A review on sweat models and a comparison to recent experimental datasets.
Temperature (Austin)
June 2025
Department of Mechanical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
Sweating is a vital thermoregulatory mechanism in humans for maintaining thermal balance during exercise and exposure to hot environments. The development of models that predict sweat rate based on body temperature has been ongoing for over half a century. Here, we compared predicted water loss rates (WLR) from these models to actual observations collected during 780 participant-exposures in three independent laboratory-based experiments.
View Article and Find Full Text PDFAutomatic specific absorption rate (SAR) prediction for hyperthermia treatment planning using deep learning method.
Int J Hyperthermia
December 2025
Department of Radiation Oncology Physics, University of Maryland, Baltimore, MD, USA.
Objective: To develop a deep learning method for fast and accurate prediction of Specific Absorption Rate (SAR) distributions in the human head to support real-time hyperthermia treatment planning (HTP) of brain cancer patients.
Approach: We propose an encoder-decoder neural network with cross-attention blocks to predict SAR maps from brain electrical properties, tumor 3D isocenter coordinates and microwave antenna phase settings. A dataset of 201 simulations was generated using finite-element modeling by varying tissue properties, tumor positions, and antenna phases within a human head model equipped with a three-ring phased-array applicator.
Refractive Outcomes Using Simulated Keratometry Versus Keratometry From an Optical Biometer.
Am J Ophthalmol
September 2025
Dean McGee Eye Institute, University of Oklahoma, Oklahoma City, Oklahoma, USA. Electronic address:
Purpose: To compare refractive prediction accuracy using simulated keratometry (SimK) measurements obtained from a Scheimpflug tomographer (Pentacam AXL, Oculus) versus keratometry (K) measurements obtained from an optical biometer utilizing telecentric keratometry (IOLMaster 700 (IOLM700), Carl Zeiss Meditec AG) applied to modern IOL power calculation formulas.
Design: Retrospective accuracy and validity analysis METHODS: Setting: Private practice center STUDY POPULATION: Five hundred eighty-nine eyes with preoperative SimK and K measurements undergoing phacoemulsification and implantation of monofocal IOL (Clareon SY60WF IOL, Alcon Laboratories, Inc.).
Half-life prediction of central nervous system (CNS) small molecules in humans using gradient tree boosting.
Future Med Chem
September 2025
Computational Science & Artificial Intelligence, Xenon Pharmaceuticals Inc, Burnaby, BC, Canada.
Aims: To develop a machine learning (ML) model for early-stage prediction of human half-life of oral central nervous system (CNS) drugs and to establish a curated dataset, including key and data, to support future modeling efforts.
Materials & Methods: Human and rat half-life, plasma protein binding (PPB), and liver microsomal clearance (LM) data for 76 diverse CNS drugs and candidates were obtained from public sources or evaluated at WuXi AppTec. Gradient tree boosting (GTB) models were constructed using ChemAxon's Trainer Engine.
Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging.
Eur Spine J
September 2025
Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Purpose: This study aims to address the limitations of radiographic imaging and single-task learning models in adolescent idiopathic scoliosis assessment by developing a noninvasive, radiation-free diagnostic framework.
Methods: A multi-task deep learning model was trained using structured back surface data acquired via fringe projection three-dimensional imaging. The model was designed to simultaneously predict the Cobb angle, curve type (thoracic, lumbar, mixed, none), and curve direction (left, right, none) by learning shared morphological features.