Normalized Mean Square Error Research Articles

Investigation of scatter energy window width and count levels for deep learning-based attenuation map estimation in cardiac SPECT/CT imaging

Objective.Deep learning (DL) is becoming increasingly important in generating attenuation maps for accurate attenuation correction (AC) in cardiac perfusion SPECT imaging. Typically, DL models take inputs from initial reconstructed SPECT images, which are performed on the photopeak window and often also on scatter windows. While prior studies have demonstrated improvements in DL performance when scatter window images are incorporated into the DL input, the comprehensive analysis of the impact of employing different scatter windows remains unassessed. Additionally, existing research mainly focuses on applying DL to SPECT scans obtained at clinical standard count levels. This study aimed to assess utilities of DL from two aspects: (1) investigating the impact when different scatter windows were used as input to DL, and (2) evaluating the performance of DL when applied on SPECT scans acquired at a reduced count level.Approach.We utilized 1517 subjects, with 386 subjects for testing and the remaining 1131 for training and validation.Main results.The results showed that as scatter window width increased from 4% to 30%, a slight improvement was observed in DL estimated attenuation maps. The application of DL models to quarter-count (¼-count) SPECT scans, compared to full-count scans, showed a slight reduction in performance. Nonetheless, discrepancies across different scatter window configurations and between count levels were minimal, with all normalized mean square error (NMSE) values remaining within 2.1% when comparing the different DL attenuation maps to the reference CT maps. For attenuation corrected SPECT slices using DL estimated maps, NMSE values were within 0.5% when compared to CT correction.Significance.This study, leveraging an extensive clinical dataset, showed that the performance of DL seemed to be consistent across the use of varied scatter window settings. Moreover, our investigation into reduced count studies indicated that DL could provide accurate AC even at a ¼-count level.

Use of bore-epoxy anchorage system with CFRP laminates for shear strengthening of RC beams: An experimental and analytical investigation

Shear strengthening of reinforced concrete (RC) beams with externally bonded reinforcement (EBR) using carbon fiber reinforced polymer (CFRP) plates and sheets have become a widely accepted practice. To avoid the associated premature debonding failure, this study presents an experimental and analytical investigation on the use of bore-epoxy as an anchorage system for CFRP plates and sheets bonded on both sides of shear deficient RC beams of rectangular cross-sections. Nine (9) RC beams were prepared and strengthened with CFRP plates and sheets as EBR with bore-epoxy anchorage system considering different bore diameters and tested under four point bending. The results indicate that RC beams strengthened with bore-epoxy anchorage system have high shear strength as compared with the unstrengthened control beam and those strenghtended with the conventional EBR approach (without boring). The increase in the shear strength over the control beam was found to be up to 67 % and 121 % for cases of CFRP plates and sheets, respectively. Moreover, the increase of shear strength in comparison with the conventional EBR method ranged from 9.33 % to 20.36 % for CFRP plates and from 12.97 % to 36.10 % for CFRP sheets. Consistently, the contribution of bore-epoxy on the shear strength increased with the increase of bore diameter. Consequently, the existing formulas in the ACI440.2 R for predicting the shear strength of FRP strengthened RC beams were modified to incorporate the improvement made by the proposed bore-epoxy approach. The revised models predicted the experimental shear strength of RC beams, strengthened with bore-epoxy, with a good level of accuracy with average mean absolute percentage error (MAPE) = 6.07 %, 14.71 %, normalized mean square error (NMSE) = 0.097, 0.16, and coefficient of determination R2 = 0.912, 0.974 for plates and sheets, respectively.

ICe: interior cevian initialization for enhanced reconstruction methods

This paper introduces two novel self-induced basis strategies, interior cevian initialization for orthogonal matching pursuit (ICe) and its l2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l_2$$\\end{document}-sense optimized version, optimized interior cevian initialization (OICe). These methods address the complexity and convergence issues of the previously proposed self-inspired bases (SIBS) approach. Both algorithms enhance sparse image representation by generating adaptive auxiliary atoms tailored to the image, thereby improving reconstruction quality and computational efficiency. Experimental results show that ICe achieves up to a 35.6% improvement in Normalized Mean Squared Error (NMSE) and a 16.4% increase in Structural Similarity Index (SSIM) compared to conventional OMP. OICe, as the l2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$l_2$$\\end{document}-sense optimized version of ICe, delivers even greater performance, with improvements of up to 40% in NMSE and 18.5% in SSIM. Additionally, both ICe and OICe significantly reduce bits per pixel (BPP) for image encoding, outperforming SIBS when paired with state-of-the-art dictionaries such as KSVD, MOD, RBDL, and ODL. These results highlight the effectiveness of ICe and OICe in addressing key challenges in sparse representation, offering enhanced accuracy and efficiency across a variety of applications.

Universal Remaining Useful Life Prediction for OECTs under Different Aging Conditions

Abstract It is significantly important to predict remaining useful life (RUL) of organic electrochemical transistors (OECTs) for next-generation offshore electronics with stable and reliable performance. Most existing RUL prediction models are not suitable for OECT RUL prediction tasks as they are based on the premise that components have the same aging conditions. In fact, aging conditions of different OECTs often exist discrepancy, leading to performance degradation of RUL prediction models. Although a few methods addressed this issue via transfer learning methods, they still suffer from the challenge in terms of an obvious discrepancy of aging data distribution caused by different aging conditions. To address this issue, we developed a novel universal RUL prediction model for OECTs, called adaptive transformer-based network (ATFN), to reduce the obvious discrepancy among different aging data. First, a transformer-based feature extractor is used to capture the temporal and spatial aging features from some aging precursors. Then, a multi-scale feature alignment metric is adopted to align the aging features of OECTs by reducing discrepancy at different feature scales. Last, an adversarial manner is developed to obtain aging-condition-invariant features for further feature alignment. Extensive experiments are conducted on a real-world OECTs cycling stability aging tests dataset. The average MSE of our method is reduced by two orders of magnitude compared to the one of baseline, which indicates that our method achieves great progress for universal RUL prediction of OECTs under different aging conditions.

Channel reconstruction through improvised deep learning architecture for high-speed networks

Efficient acquisition of channel state information (CSI) is quite complicated process but immensely essential to exploit probable benefits of massive multiple input multiple output (MIMO) systems. Therefore, a deep learningbased model is utilized to estimate channel feedback in a massive MIMO system. The proposed improvised deep learning-based channel estimation (IDLCE) model enhances channel reconstruction efficiency by using multiple convolutional layers and residual blocks. The proposed IDLCE model utilizes encoder network to compress CSI matrices where decoder network is used to downlink reconstruct CSI matrices. Here, an additional quantization block is incorporated to improve feedback reconstruction accuracy by reducing channel errors. A COST 2,100 model is adopted to analyse performance efficiency for both indoor and outdoor scenarios. Further, deep learning-based model is used to train thousands of parameter and correlation coefficients much faster and to minimize computational complexity. The proposed IDLCE model evaluate performance in terms of normalized mean square error (NMSE), correlation efficiency and reconstruction accuracy and compared against varied state-of-art-channel estimation techniques. Excellent performance results are obtained with large improvement in channel reconstruction accuracy

Foundry fabricated compact slow-light Mach-Zehnder modulator and photodetector for on-chip analog photonic computing

This work presents a scaling pathway of on-chip analog photonic computing using foundry-fabricated silicon electro-optic (EO) slow-light Mach-Zehnder modulators (SL-MZMs) and compact Ge photodetectors (PDs) to construct a computing unit. Two SL-MZMs with phase shifter (PS) lengths of 500 μm and 150 μm are studied in this work. The bit resolution, nonlinearity, clock frequency, and power consumption of the photonic computing link, including an RF amplifier, on-chip SL-MZM, and a PD, are thoroughly investigated. The computing link using the SL-MZM with 500 μm has demonstrated a low normalized mean square error (NMSE) of 0.0305 at 8-bit resolution under 3.2 GHz clock frequency. Under the setting of 6-bit resolution at a clock frequency of 800 MHz, high computing accuracy was achieved with a measured NMSE of 0.0018 using the SL-MZM with 150 μm PS length. Using the Google Speed Commands dataset to run a voice keyword spotting task, we determine that 6-bit resolution operating at 3.2 GHz achieves the optimal power-accuracy trade-off. We show a 20× improvement in energy efficiency and a 3.35× improvement in area efficiency compared to NVIDIA V100 GPU [“Volta: Performance and programmability,” IEEE Micro 38(2), 42 (2018)10.1109/MM.2018.022071134 ]. These results show that our compact SL-MZMs and PDs promise to scale up photonic computing for practical machine-learning applications.

Modified Generalized Chen Distribution, Estimation and Application using Econometrics Data

In this study, a variant of the generalized Chen (GC) distribution with parameters α, β, γ, δ, and λ, termed the Modified Generalized Chen (MGC) distribution, was introduced. The study evaluated several Chen distribution variants theoretically, focusing on the MGC distribution. Variants considered include the Generalized Chen (GC), Half-Cauchy Chen (HCC), New Extended Chen (NEC), and Exponentially Generalized Modified Chen (EGMC) distributions. The objectives of the study was to derive the probability density function (PDF) and cumulative density function (CDF) of the MGC distribution, determine its statistical properties and reliability characteristics, compare these properties and characteristics to existing distributions, and empirically evaluate its performance. The study developed unique expressions for the PDF, CDF, survival function, and hazard function of the MGC distribution. By evaluating PDFs and performance measures such as the Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and mean square error (MSE) across various datasets, the MGC distribution consistently demonstrated superiority over other variants. The MGC distribution offers improved model fit, predictive accuracy, and interpretability without sacrificing simplicity. The dataset employed in this study was the secondary data, encompassing economic indicators from 1981 to 2021 and public health expenditure data for Nigeria and Ghana from 1995 to 2014. Statistical analyses revealed that on the average, the MGC distribution outperforms others, with superior average AIC (-509.95), BIC (-510.49), and MSE (499.89) measures across the datasets considered in the study. This superior performance indicates better fit and accuracy in predicting economic and public health outcomes, offering valuable insights for policymakers and researchers. The study underscores the importance of adopting flexible and interpretable distribution models like the MGC distribution to enhance empirical analyses, inform policy decisions, and advance knowledge in econometrics and related disciplines.

Overview of Tensor-Based Cooperative MIMO Communication Systems—Part 2: Semi-Blind Receivers

Cooperative MIMO communication systems play an important role in the development of future sixth-generation (6G) wireless systems incorporating new technologies such as massive MIMO relay systems, dual-polarized antenna arrays, millimeter-wave communications, and, more recently, communications assisted using intelligent reflecting surfaces (IRSs), and unmanned aerial vehicles (UAVs). In a companion paper, we provided an overview of cooperative communication systems from a tensor modeling perspective. The objective of the present paper is to provide a comprehensive tutorial on semi-blind receivers for MIMO one-way two-hop relay systems, allowing the joint estimation of transmitted symbols and individual communication channels with only a few pilot symbols. After a reminder of some tensor prerequisites, we present an overview of tensor models, with a detailed, unified, and original description of two classes of tensor decomposition frequently used in the design of relay systems, namely nested CPD/PARAFAC and nested Tucker decomposition (TD). Some new variants of nested models are introduced. Uniqueness and identifiability conditions, depending on the algorithm used to estimate the parameters of these models, are established. Two families of algorithms are presented: iterative algorithms based on alternating least squares (ALS) and closed-form solutions using Khatri–Rao and Kronecker factorization methods, which consist of SVD-based rank-one matrix or tensor approximations. In a second part of the paper, the overview of cooperative communication systems is completed before presenting several two-hop relay systems using different codings and configurations in terms of relaying protocol (AF/DF) and channel modeling. The aim of this presentation is firstly to show how these choices lead to different nested tensor models for the signals received at destination. Then, by capitalizing on these models and their correspondence with the generic models studied in the first part, we derive semi-blind receivers to jointly estimate the transmitted symbols and the individual communication channels for each relay system considered. In a third part, extensive Monte Carlo simulation results are presented to compare the performance of relay systems and associated semi-blind receivers in terms of the symbol error rate (SER) and channel estimate normalized mean-square error (NMSE). Their computation time is also compared. Finally, some perspectives are drawn for future research work.

Artificial intelligence prediction of the mechanical properties of banana peel-ash and bagasse blended geopolymer concrete

This research explores the application of Artificial Intelligence (AI) techniques to assess the mechanical properties of geopolymer concrete made from a blend of Banana Peel-Ash (BPA) and Sugarcane Bagasse Ash (SCBA), using a sodium silicate (Na2SiO3) to sodium hydroxide (NaOH) ratio ranging from 1.5 to 3. Utilizing three AI methodologies—Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Gene Expression Programming (GEP)—the study aims to enhance prediction accuracy for the mechanical properties of geopolymer concrete based on 104 datasets. By optimizing mix designs through varying proportions of BPA and SCBA, alkaline activator molarity, and aggregate-to-binder ratios, the research identified combinations that significantly enhance mechanical properties, demonstrating notable international relevance as it contributes to global efforts in sustainable construction by effectively utilizing industrial by-products. The experimental results demonstrated that increasing the molarity of the alkaline activator from 4 to 10 M significantly enhanced both the compressive and flexural strengths of the geopolymer concrete. Specifically, a mixture containing 52.5% SCBA and 47.5% BPA at a 10 M molarity achieved a maximum compressive strength of 33.17 MPa after 20 h of curing. In contrast, a mixture composed of 95% SCBA and 5% BPA at a 4 M molarity exhibited a substantially lower compressive strength of only 21.27 MPa. Additionally, the highest recorded flexural strength of 9.95 MPa (77.25% SCBA and 22.5 BPA) was observed at the 10 M molarity, while the flexural strength at 4 M was lowest, at 4.12 MPa (95% SCBA and 5% BPA). Microstructural analysis through Scanning Electron Microscopy with Energy-Dispersive X-ray Spectroscopy (ED-SEM) revealed insights into the pore structure and elemental composition of the concrete, while Thermogravimetric Analysis (TGA) provided data on the material’s thermal stability and decomposition characteristics. Performance analysis of the AI models showed that the ANN model had an average MSE of 1.338, RMSE of 1.157, MAE of 3.104, and R2 of 0.989, while the ANFIS model outperformed with an MSE of 0.345, RMSE of 0.587, MAE of 1.409, and R2 of 0.998. The GEP model demonstrated an MSE of 1.233, RMSE of 1.110, MAE of 1.828, and R2 of 0.992, confirming that ANFIS is the most accurate model for predicting the mechanical and rheological properties of geopolymer concrete. This study highlights the potential of integrating AI with experimental data to optimize the formulation and performance of geopolymer concrete, advancing sustainable construction practices by effectively utilizing industrial by-products.

Prediction of optical chaos using a multi-stage extreme learning machine with data uncertainty

In this paper, we study the problem of predicting optical chaos for semiconductor lasers, where data uncertainty can severely degrade the performance of chaos prediction. We hereby propose a multi-stage extreme learning machine (MSELM) based approach for the continuous prediction of optical chaos, which handles data uncertainty effectively. Rather than relying on pilot signals for conventional reservoir learning, the proposed approach enables the use of predicted optical intensity as virtual training samples for the MSELM model learning, which leads to enhanced prediction performance and low overhead. To address the data uncertainty in virtual training, total least square (TLS) is employed for the update of the proposed MSELM’s parameters with simple updating rule and low complexity. Simulation results demonstrate that the proposed MSELM can execute the continuous optical chaos predictions effectively. The chaotic time series can be continuously predicted for a time period in excess of 4 ns with a normalized mean squared error (NMSE) lower than 0.012. It also demands much fewer training samples than state-of-the-art learning-based methods. In addition, the simulation results show that with the help of TLS, the length of prediction is improved significantly as the uncertainty is handled properly. Finally, we verify the prediction ability of the multi-stage ELM under various laser parameters, and make the median boxplot of the predicted results, which shows that the proposed MSELM continues to produce accurate and continuous predictions on time-varying optical chaos.

Deep learning-based approach for acquisition time reduction in ventilation SPECT in patients after lung transplantation.

We aimed to evaluate the image quality and diagnostic performance of chronic lung allograft dysfunction (CLAD) with lung ventilation single-photon emission computed tomography (SPECT) images acquired briefly using a convolutional neural network (CNN) in patients after lung transplantation and to explore the feasibility of short acquisition times. We retrospectively identified 93 consecutive lung-transplant recipients who underwent ventilation SPECT/computed tomography (CT). We employed a CNN to distinguish the images acquired in full time from those acquired in a short time. The image quality was evaluated using the structural similarity index (SSIM) loss and normalized mean square error (NMSE). The correlation between functional volume/morphological volume (F/M) ratios of full-time SPECT images and predicted SPECT images was evaluated. Differences in the F/M ratio were evaluated using Bland-Altman plots, and the diagnostic performance was compared using the area under the curve (AUC). The learning curve, obtained using MSE, converged within 100 epochs. The NMSE was significantly lower (P < 0.001) and the SSIM was significantly higher (P < 0.001) for the CNN-predicted SPECT images compared to the short-time SPECT images. The F/M ratio of full-time SPECT images and predicted SPECT images showed a significant correlation (r = 0.955, P < 0.0001). The Bland-Altman plot revealed a bias of -7.90% in the F/M ratio. The AUC values were 0.942 for full-time SPECT images, 0.934 for predicted SPECT images and 0.872 for short-time SPECT images. Our findings suggest that a deep-learning-based approach can significantly curtail the acquisition time of ventilation SPECT, while preserving the image quality and diagnostic accuracy for CLAD.

Accelerated cardiac cine with spatio-coil regularized deep learning reconstruction.

To develop an iterative deep learning (DL) reconstruction with spatio-coil regularization and multichannel k-space data consistency for accelerated cine imaging. This study proposes a Spatio-Coil Regularized DL (SCR-DL) approach for iterative deep learning reconstruction incorporating multicoil information in data consistency and regularizer. SCR-DL uses shift-invariant convolutional kernels to interpolate missing k-space lines and reconstruct individual coil images, followed by a regularizer that operates simultaneously across spatial and coil dimensions using learned image priors. At 8-fold acceleration, SCR-DL was compared with Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA), sensitivity encoding (SENSE)-based DL and spatio-temporal regularized (STR)-DL reconstruction. In the retrospective undersampled cine, images were quantitatively evaluated using normalized mean square error (NMSE) and structural similarity index measure (SSIM). Additionally, agreement for left-ventricular ejection fraction and left-ventricular mass were assessed using prospectively accelerated cine images at 2-fold and 8-fold accelerations. The SCR-DL algorithm successfully reconstructed highly accelerated cine images. SCR-DL had significant improvements in NMSE (0.03 ± 0.02) and SSIM (91.4% ± 2.7%) compared with GRAPPA (NMSE: 0.09 ± 0.04, SSIM: 69.9% ± 11.1%; p < 0.001), SENSE-DL (NMSE: 0.07 ± 0.04, SSIM: 86.9% ± 3.2%; p < 0.001), and STR-DL (NMSE: 0.04 ± 0.03, SSIM: 90.0% ± 2.5%; p < 0.001) with retrospective undersampled cine. Despite the 3-fold reduction in scan time, there was no difference between left-ventricular ejection fraction (59.8 ± 4.5 vs. 60.8 ± 4.8, p = 0.46) or left-ventricular mass (73.6 ± 19.4 g vs. 73.2 ± 19.7 g, p = 0.95) between R = 2 and R = 8 prospectively accelerated cine images. SCR-DL enabled highly accelerated cardiac cine imaging, significantly reducing breath-hold time. Compared with GRAPPA or SENSE-DL, images reconstructed with SCR-DL showed superior NMSE and SSIM.

Massive MIMO uplink and downlink joint representation based on couple dictionary learning

AbstractThe challenge of jointly representing both the uplink (UL) and downlink (DL) in massive multiple input multiple output (MIMO) systems have been tackled. Considering the angular reciprocity, a couple dictionary learning (CDL) support to enhance performance and address high complexity has been introduced. This approach minimizes the number of pilots and improves accuracy. Currently, accuracy analysis of UL/DL representation primarily relies on simulation. To bridge this gap, a proportion factor (PF) operator is proposed for CDL to assess accuracy. Specifically, a qualitative analysis formula is provided for accuracy and an optimal upper bound is established. Through theoretical proof, it is demonstrated that the accuracy of CDL for representation is mainly influenced by the cross‐correlation between the pilot matrix and the dictionary matrix. Inspired by PF operator, an optimal couple dictionary learning (OCDL) algorithm using singular value decomposition (SVD) is introduced to obtain dictionary updating, aiming at high‐precision representation. By establishing normalized mean squared error (NMSE), successful representation ratio, bit error rate (BER), and constellation performance, an OCDL algorithm that outperforms existing methods is showcased and channel representation accuracy is enhanced significantly.

Channel estimation via compressed sampling matching pursuit for hybrid MIMO architectures in millimeter wave communication

ABSTRACT In recent times, there are considerable research efforts in utilising millimetre wave cellular system for meeting rising mobile traffic volume and escalating data rate demand. In this regard, several analytical models have been developed for obtaining Channel State Information (CSI) for the design of combiner and precoder architectures for millimetre wave communication. One prominent method that has caught the attention of most researchers is the Orthogonal Matching Pursuit (OMP) which performs poorly in noisy condition. As a result, this work introduces Compressed Sampling Matching Pursuit (CoSAMP) as alternative to OMP for obtaining CSI for the design of hybrid combiner. A comparative analysis of all the cases examined reveals that CoSAMP surpasses OMP and Least Square (LS) across SNR range of −30 dB to −10 dB, recording lowest Normalized Mean Square Error (NMSE), highest Spectral Efficiency (SE) and bit rate. For instance at −20 dB, NMSE of CoSAMP exhibits 95% and 86% gain over LS and OMP, respectively while SE and bit rate of CoSAMP are better than OMP and LS by 21% and 91%, respectively. It is therefore seen that CoSAMP is a better technique for estimating CSI and for combiner design in such condition.

Channel Estimation for Deep Space Communications Under the Effect of Solar Scintillation

AbstractDuring probe‐to‐Earth superior conjunction, deep space communication channels will suffer from solar scintillation, leading to amplitude attenuation of received signals. This study aims to obtain the channel state information (CSI) on deep space channels affected by solar scintillation. Classical least squares (LS) and minimum mean squared error (MMSE) methods are adopted to perform channel estimation and compensate for the channel fading. Simulation results indicate that under the effect of solar scintillation, performing channel estimation technology can significantly improve bit error rate (BER) performance compared to systems without CSI, and the MMSE algorithm outperforms the LS for both BER and normalized mean squared error (NMSE). In addition, we also find that pilot density, geometric parameters, and the outer scale of solar wind turbulence has great influence on the estimation performance.

DGD-CNet: Denoising Gated Recurrent Unit with a Dropout-Based CSI Network for IRS-Aided Massive MIMO Systems.

For the deployment of Sixth Generation (6G) networks, integrating Massive Multiple-Input Multiple-Output (Massive MIMO) systems with Intelligent Reflecting Surfaces (IRS) is highly recommended due to its significant benefits in reducing communication losses for Non-Line-of-Sight (NLoS) conditions. However, the use of passive IRS presents challenges in channel estimation, mainly due to the significant feedback overhead required in Frequency Division Duplex (FDD)-based Massive MIMO systems. To address these challenges, this paper introduces a novel Denoising Gated Recurrent Unit with a Dropout-based Channel state information Network (DGD-CNet). The proposed DGD-CNet model is specifically designed for FDD-based IRS-aided Massive MIMO systems, aiming to reduce the feedback overhead while improving the channel estimation accuracy. By leveraging the Dropout (DO) technique with the Gated Recurrent Unit (GRU), the DGD-CNet model enhances the channel estimation accuracy and effectively captures both spatial structures and time correlation in time-varying channels. The results show that the proposed DGD-CNet model outperformed existing models in the literature, achieving at least a 26% improvement in Normalized Mean Square Error (NMSE), a 2% increase in correlation coefficient, and a 4% in system accuracy under Low-Compression Ratio (Low-CR) in indoor situations. Additionally, the proposed model demonstrates effectiveness across different CRs and in outdoor scenarios.

Surface tension prediction of pure organic components: An artificial neural network approach

Surface tension is an important thermodynamic property of fluids that impact several processes in the engineering. Accurate estimations of this parameter are required to correctly apply and develop operations such as flow processes and oil recovery. The present study proposes the applying of artificial neural network (ANN)-based approach to accurately predict the surface tension for 75 groups of pure organic compounds, encompassing 1,666 different compounds and 21,444 data points. The performance of the model was evaluated using the mean squared error (MSE) and the coefficient of determination (R2), with K-Fold cross-validation ensuring robustness. The optimal model (ArcD) achieved an average MSE of 8.27x10−5 during cross-validation and 1.55x10−5 during training, with an R2 value of 0.9955. Although training time for this model was 8.89 times longer than the second-best model (ArcA), which had an R2 of 0.9928. Comparative analyses with existing literature models were also realized and revealed an absolute relative deviation (ARD) value of 2.49% to ArcD, 18.39% to Brock and Bird, 23.97% to Curl and Pitzer, and 18.62% to Zuo and Stenby equations, demonstrating the applicability and precision of the developed model. The results highlighted the reliability, accuracy and robustness of the developed ANN-based model, providing a significant advancement in the prediction of surface tension for a wide range of pure organic compounds.

Explainable Encoder-Prediction-Reconstruction Framework for the Prediction of Metasurface Absorption Spectra.

The correlation between metasurface structures and their corresponding absorption spectra is inherently complex due to intricate physical interactions. Additionally, the reliance on Maxwell's equations for simulating these relationships leads to extensive computational demands, significantly hindering rapid development in this area. Numerous researchers have employed artificial intelligence (AI) models to predict absorption spectra. However, these models often act as black boxes. Despite training high-performance models, it remains challenging to verify if they are fitting to rational patterns or merely guessing outcomes. To address these challenges, we introduce the Explainable Encoder-Prediction-Reconstruction (EEPR) framework, which separates the prediction process into feature extraction and spectra generation, facilitating a deeper understanding of the physical relationships between metasurface structures and spectra and unveiling the model's operations at the feature level. Our model achieves a 66.23% reduction in average Mean Square Error (MSE), with an MSE of 2.843 × 10-4 compared to the average MSE of 8.421×10-4 for mainstream networks. Additionally, our model operates approximately 500,000 times faster than traditional simulations based on Maxwell's equations, with a time of 3×10-3 seconds per sample, and demonstrates excellent generalization capabilities. By utilizing the EEPR framework, we achieve feature-level explainability and offer insights into the physical properties and their impact on metasurface structures, going beyond the pixel-level explanations provided by existing research. Additionally, we demonstrate the capability to adjust absorption by changing the metasurface at the feature level. These insights potentially empower designers to refine structures and enhance their trust in AI applications.

Physical reservoir computing with visible-light signals using dye-sensitized solar cells

Physical reservoir computing (PRC) with visible-light signals was demonstrated using dye-sensitized solar cells. The short-term memory required for PRC was confirmed using light pulse inputs. Waveform learning was demonstrated for nonlinear autoregressive moving-average time series level 2 (NARMA2) signals with normalized mean square error of 0.027. The relatively slow (milliseconds to seconds) and complex charge transfer dynamics in the TiO2 porous layer with redox reactions in the solution phase provided the characteristics required for PRC.

Inverse design of ultranarrow and high-efficiency color filters based on tandem convolutional neural networks

In this paper, an ultranarrow, high-efficiency color filter based on a two-dimensional grating nanostructure array is realized by a tandem inverse design network. The tandem inverse designed network is generated by connecting an inverse network with a pre-trained forward network. The tandem convolutional neural network successfully overcame the non-uniqueness problem of the training data. The performance of the networks is verified by a test set of 2592 data points, and the average MSE of the prediction results of the tandem network is 1.01 × 10−3. Extremely low error indicates that the tandem network can learn and capture the distribution characteristics of the transmission spectrum and give a reasonable design of the structural parameters. Finally, we obtained multiple inverse-designed transmissive color filters with ultranarrow linewidths and high efficiency, with central wavelengths between 480 nm and 630 nm. The linewidth and efficiency of each kind of color filter are less than 10.6 nm and higher than 60%. Narrow linewidths and wide wavelength tunability result in high color accuracy and a broad color gamut of the filters. The filters with two-dimensional metallic nanostructure array also show polarization-independent characteristics. Compared with the traditional method, this method can quickly and accurately design the structural parameters corresponding to the spectral response, which provides a new method for the nanostructure design.