Power Map Research Articles

Towards harmonization of SO(3)-equivariance and expressiveness: a hybrid deep learning framework for electronic-structure Hamiltonian prediction

Abstract Deep learning for predicting the electronic-structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks remains unsolved. To navigate the harmonization between SO(3)-equivariance and expressiveness, we propose HarmoSE, a deep learning method synergizing two distinct categories of neural mechanisms as a two-stage encoding and regression framework. The first stage corresponds to group theory-based neural mechanisms with inherent SO(3)-equivariant properties prior to the parameter learning process, while the second stage is characterized by a non-linear 3D graph Transformer network we propose, featuring high capability on non-linear expressiveness. Their combination lies in the point that, the first stage predicts baseline Hamiltonians with abundant SO(3)-equivariant features extracted, assisting the second stage in empirical learning of equivariance; and in turn, the second stage refines the first stage’s output as a fine-grained prediction of Hamiltonians using powerful non-linear neural mappings, compensating for the intrinsic weakness on non-linear expressiveness capability of mechanisms in the first stage. Our method enables precise, generalizable predictions while capturing SO(3)-equivariance under rotational transformations, and achieves state-of-the-art performance in Hamiltonian prediction tasks under multiple mean absolute error (MAE) metrics, such as the average MAE across all samples and matrix elements, the MAE for challenging samples, the MAE for different Hamiltonian blocks, and the MAE for the challenging blocks. It also demonstrates significant improvements in accuracy for downstream quantities, such as occupied orbital energy and the electronic wavefunction, as measured by MAE and cosine similarity, respectively.

First test beam of the DMAPS-based proton tracker at the pMBRT facility at the Curie Institute

Objective.Proton radiotherapy's efficacy relies on an accurate relative stopping power (RSP) map of the patient to optimise the treatment plan and minimize uncertainties. Currently, a conversion of a Hounsfield Units map obtained by a common x-ray computed tomography (CT) is used to compute the RSP. This conversion is one of the main limiting factors for proton radiotherapy. To bypass this conversion a direct RSP map could be obtained by performing a proton CT (pCT). The focal point of this article is to present a proof of concept of the potential of fast pixel technologies for proton tracking at clinical facilities.Approach.A two-layer tracker based on the TJ-Monopix1, a depleted monolithic active pixel sensor (DMAPS) chip initially designed for the ATLAS, was tested at the proton minibeam radiotherapy beamline at the Curie Institute. The chips were subjected to 100 MeV protons passing through the single slit collimator (0.4×20mm2) with fluxes up to1.3×107p s-1 cm-2. The performance of the proton tracker was evaluated with GEANT4 simulations.Main results.The beam profile and dispersion in air were characterized by an opening of 0.031 mm cm-1, and aσx=0.172mm at the position of the slit. The results of the proton tracking show how the TJ-Monopix1 chip can effectively track protons in a clinical environment, achieving a tracking purity close to 70%, and a position resolution below 0.5 mm; confirming the chip's ability to handle high proton fluxes with a competitive performance.Significance.This work suggests that DMAPS technologies can be a cost-effective alternative for proton imaging. Additionally, the study identifies areas where further optimization of chip design is required to fully leverage these technologies for clinical ion imaging applications.

A review of load forecasting technology based on artificial intelligence

Abstract. Driven by the "dual carbon" goals and the construction of new-type power systems, the importance of power load forecasting technology has become increasingly prominent. Accurate power load forecasting can not only ensure the safe and stable operation of the power system, but also promote the efficient use of clean energy and reduce carbon emissions. Traditional power load forecasting methods have become insufficient in dealing with the complexity and nonlinear growth of power systems, and the development of artificial intelligence technology has brought new possibilities for power load forecasting. Power load forecasting methods based on machine learning and deep learning have gradually become a hot topic of research due to their powerful nonlinear mapping capabilities and advantages in processing big data. These methods not only perform well in short-term forecasting, but also show potential in medium- and long-term forecasting. This paper discusses the application of different artificial intelligence technologies in power load forecasting by sorting out the development status of related technologies, and provides a reference direction for future research.

Study on Audit Risk Model Based on Data Mining Algorithm

With the widespread application of modern information technologies such as big data, enterprises have generated a large amount of data in their daily operations. The traditional audit methods have drawbacks such as high cost and high consumption, and can no longer meet the needs of audit work in the digital era. Therefore, it is urgent to adopt audit methods suitable for the digital era to improve audit quality and reduce enterprise Audit risk. For professional auditors in enterprises, it is very important to utilize emerging technologies such as data mining algorithms. The audited enterprise may tamper with its financial statements, and identifying high-quality audit data from massive amounts of data is a huge challenge. Compared to traditional audit methods, data mining algorithms can significantly improve the efficiency and accuracy of audit work. For example, the BP neural network, with its powerful nonlinear mapping ability, can capture complex relationships in data; Support vector machines classify data by finding the optimal hyperplane in high-dimensional space and have good generalization ability; random forest reduces overfitting and improves prediction accuracy by integrating multiple decision trees; Association rule algorithms can discover interesting relationships between data items, helping auditors identify potential fraudulent behavior or abnormal transactions. Therefore, the purpose of this study is to accurately evaluate and reduce the audit risk of enterprises, and to build an audit risk model using computer data mining algorithms. This provides necessary reference and guidance for auditors to conduct data analysis and mine valuable data during the audit process of enterprises, thereby improving audit efficiency.

A comprehensive framework for 5G indoor localization

Localization inside legacy private 5G networks is a daunting task that involves solving the problem of indoor localization using commercial off-the-shelf proprietary hardware. While some previous work has focused on experimental analysis, none has undertaken to develop a realistic solution based on commercial equipment. In this study, we present the first comprehensive and concrete 5G framework that combines fingerprinting with the 3GPP Enhanced Cell ID (E-CID) approach. Our methodology consists of a machine-learning model to deduce the user’s position by comparing the signal strength received from the User Equipment (UE) with a reference radio power map. To achieve this, the 3GPP protocols and functions are improved to provide open, centralized, and universal localization functions. A new reference map paradigm named Optical Radio Power Estimation using Light Analysis (ORPELA) is introduced. Real-world experiments prove that it is reproducible and more accurate than state-of-the-art radio-planning software. Machine-learning models are then designed, trained, and optimized for an ultra-challenging radio context. Finally, a large-scale experimental campaign encompassing a wide range of cases, including line-of-sight or mobility, is being conducted to demonstrate expected location performance within realistic 5G private networks.

High-Precision Photonics-Assisted Two-Step Microwave Frequency Measurement Combining Time and Power Mapping Method.

Photonics-assisted methods for microwave frequency measurement (MFM) show great potential for overcoming electronic bottlenecks and offer promising applications in radar and communication due to their wide bandwidth and immunity to electromagnetic interference. In common photonics-assisted MFM methods, the frequency-to-time mapping (FTTM) method has the capability to measure various types of signals, but with a trade-off between measurement error, measurement range, and real-time performance, while the frequency-to-power mapping (FTPM) method offers low measurement error but faces great difficulty in measuring signal types other than single-tone signals. In this paper, a two-step high-precision MFM method based on the combination of FTTM and FTPM is proposed, which balances real-time performance with measurement precision and resolution compared with other similar works based on the FTTM method. By utilizing high-speed optical sweeping and an optical filter based on stimulated Brillouin scattering (SBS), FTTM is accomplished, enabling the rough identification of multiple different signals. Next, based on the results from the previous step, more precise measurement results can be calculated from several additional sampling points according to the FTPM principle. The demonstration system can perform optical sweeping at a speed of 20 GHz/μs in the measurement range of 1-18 GHz, with a measurement error of less than 10 MHz and a frequency resolution of 40 MHz.

Photonic scheme for simultaneous measurement of Doppler- frequency-shift and Angle-of-arrival based on optical frequency shift heterodyne and power mapping

Photonic scheme for simultaneous measurement of Doppler- frequency-shift and Angle-of-arrival based on optical frequency shift heterodyne and power mapping

Powerful mapping of cis-genetic effects on gene expression across diverse populations reveals novel disease-critical genes.

While disease-associated variants identified by genome-wide association studies (GWAS) most likely regulate gene expression levels, linking variants to target genes is critical to determining the functional mechanisms of these variants. Genetic effects on gene expression have been extensively characterized by expression quantitative trait loci (eQTL) studies, yet data from non-European populations is limited. This restricts our understanding of disease to genes whose regulatory variants are common in European populations. While previous work has leveraged data from multiple populations to improve GWAS power and polygenic risk score (PRS) accuracy, multi-ancestry data has not yet been used to better estimate cis-genetic effects on gene expression. Here, we present a new method, Multi-Ancestry Gene Expression Prediction Regularized Optimization (MAGEPRO), which constructs robust genetic models of gene expression in understudied populations or cell types by fitting a regularized linear combination of eQTL summary data across diverse cohorts. In simulations, our tool generates more accurate models of gene expression than widely-used LASSO and the state-of-the-art multi-ancestry PRS method, PRS-CSx, adapted to gene expression prediction. We attribute this improvement to MAGEPRO's ability to more accurately estimate causal eQTL effect sizes (p < 3.98 × 10-4, two-sided paired t-test). With real data, we applied MAGEPRO to 8 eQTL cohorts representing 3 ancestries (average n = 355) and consistently outperformed each of 6 competing methods in gene expression prediction tasks. Integration with GWAS summary statistics across 66 complex traits (representing 22 phenotypes and 3 ancestries) resulted in 2,331 new gene-trait associations, many of which replicate across multiple ancestries, including PHTF1 linked to white blood cell count, a gene which is overexpressed in leukemia patients. MAGEPRO also identified biologically plausible novel findings, such as PIGB, an essential component of GPI biosynthesis, associated with heart failure, which has been previously evidenced by clinical outcome data. Overall, MAGEPRO is a powerful tool to enhance inference of gene regulatory effects in underpowered datasets and has improved our understanding of population-specific and shared genetic effects on complex traits.

Future workplace reimagination: A multiscenario analysis on entrepreneurial small and medium internationalisers

AbstractThis paper aims to encounter the scholarly demand for comprehensive identification and investigation of the factors that highlight the sense of the “workplace of the future.” Besides, this study sheds in‐depth qualitative and quantitative insights into analysing such drivers in international entrepreneurial small and medium enterprises of emerging economies like Iran. A mixed method of systematic literature review and hesitant triangular fuzzy Delphi was initially employed to identify and finalise the significant factors. Afterwards, the causal level‐based relationship network and the finalised factors' power map were accomplished for three distinct scenarios (i.e., the pessimistic, probable and optimistic conditions). To this end, a novel integration of hesitant triangular fuzzy sets and interpretive structural modelling‐matrix‐based multiplication applied to a classification was designed and applied. As a result, future workplace concerns were systematically reviewed. From the initial list of 34 factors, eight were selected from the perspective of three panels of experts (15 international entrepreneurs) as the most crucial for international small and medium enterprises due to implementing the hesitant triangular fuzzy sets. Furthermore, the selected factors were categorised and levelled according to the novel interpretive structural modelling‐matrix‐based multiplication applied to a classification method developed in this article. Accordingly, for each scenario studied, from low to high uncertainty and indeterminacy, a separate conceptual model illustrating the relationship among the factors propelling the reimagining of the future of the workplace was presented.

Enhancing the accuracy of wind power projections under climate change using geospatial machine learning models

This paper presents a geospatial artificial intelligence (GeoAI) approach for generating wind power projection maps employing various Machine Learning (ML) models. These models include Artificial Neural Network (ANN), Decision Tree (DT), Gaussian Process Regression (GPR), and Support Vector Regression (SVR), which collectively aim to provide insightful wind power forecasts under the effects of climate change. The framework considers different influential parameters affecting wind speed, including pressure gradient, temperature gradient, humidity, and topography. The study’s geographic focus is Cork City, Ireland. The investigation covers a historical period from 2000 to 2014 and extends to encompass two future climate scenarios, between 2015 and 2050. A comprehensive set of statistical skill scores is computed to gauge the models’ performance. The study’s findings underscore the efficacy of the ML models in generating dependable estimates of wind power fluctuations. Notably, the SVR model emerges as the frontrunner in performance across most pixels examined. Despite the inherent complexity of wind power dynamics, this research highlights that the SVR model can produce accurate wind power maps, even when operating with limited input data. The results emphasize the importance of considering influential factors in wind speed projections. This approach opens up promising avenues for improving the management of renewable energy resources.

Reconfigurable spin-wave properties in two-dimensional magnonic crystals formed of diamond and triangular shaped nanomagnets

Two-dimensional ferromagnetic nanodot structures exhibit intriguing magnetization dynamics and hold promise for future magnonic devices. In this study, we present a comparative experimental investigation into the reconfigurable magnetization dynamics of non-ellipsoidal diamond and triangular-shaped nanodot structures, employing broadband ferromagnetic resonance spectroscopy. Our findings reveal substantial variations in the spin wave (SW) spectra of these structures under different bias field strengths (H) and angles (φ). Notably, the diamond nanodot structure exhibits a variation from nearly symmetric W-shaped dispersion to a skewed dispersion and subsequent transition to a discontinuous dispersion with subtle variation in bias field angle. On the other hand, in the triangular nanodot array a SW mode anti-crossing appears at φ = 15° which is starkly modified with the increase in φ to 30°. By analyzing the static magnetic configurations, we unveil the nature of the SW spectra in these two shapes. We reinforce our observations with simulated spatial power and phase maps. This study underscores the critical impact of dot shape and inversion symmetry on SW dynamical response, highlighting the significance of selecting appropriate structures and bias field strength and orientation for required functionalities. The remarkable tunability demonstrated by the magnonic crystals underscores their potential suitability for future magnonic devices.

Real-Time Millimeter-Wave Imaging With Linear Frequency Modulation Radar and Scattered Power Mapping

Real-Time Millimeter-Wave Imaging With Linear Frequency Modulation Radar and Scattered Power Mapping

A direct comparison of multi-energy x-ray and proton CT for imaging and relative stopping power estimation of plastic and ex-vivo phantoms

Objective.Proton therapy administers a highly conformal dose to the tumour region, necessitating accurate prediction of the patient's 3D map of proton relative stopping power (RSP) compared to water. This remains challenging due to inaccuracies inherent in single-energy computed tomography (SECT) calibration. Recent advancements in spectral x-ray CT (xCT) and proton CT (pCT) have shown improved RSP estimation compared to traditional SECT methods. This study aims to provide the first comparison of the imaging and RSP estimation performance among dual-energy CT (DECT) and photon-counting CT (PCCT) scanners, and a pCT system prototype.Approach.Two phantoms were scanned with the three systems for their performance characterisation: a plastic phantom, filled with water and containing four plastic inserts and a wood insert, and a heterogeneous biological phantom, containing a formalin-stabilised bovine specimen. RSP maps were generated by converting CT numbers to RSP using a calibration based on low- and high-energy xCT images, while pCT utilised a distance-driven filtered back projection algorithm for RSP reconstruction. Spatial resolution, noise, and RSP accuracy were compared across the resulting images.Main results.All three systems exhibited similar spatial resolution of around 0.54 lp/mm for the plastic phantom. The PCCT images were less noisy than the DECT images at the same dose level. The lowest mean absolute percentage error (MAPE) of RSP,(0.28±0.07)%, was obtained with the pCT system, compared to MAPE values of(0.51±0.08)%and(0.80±0.08)%for the DECT- and PCCT-based methods, respectively. For the biological phantom, the xCT-based methods resulted in higher RSP values in most of the voxels compared to pCT.Significance.The pCT system yielded the most accurate estimation of RSP values for the plastic materials, and was thus used to benchmark the xCT calibration performance on the biological phantom. This study underlined the potential benefits and constraints of utilising such a novelex-vivophantom for inter-centre surveys in future.

Functional Design Analysis of Two Current Extended-Depth-of-Focus Intraocular Lenses.

To evaluate the differences between two extended depth-of-focus intraocular lenses, the Alcon IQ Vivity and the Bausch & Lomb LuxSmart and to compare them with a simple monofocal lens, the Alcon IQ, using a simulation-based approach. A mathematical lens model was created for each lens type based on a measured surface geometry. The lens model was then used in a raytracer to calculate a refractive power map of the lens and a ray propagation image for the focal zone. The simulations confirm the enhanced depth of focus of these two lenses. There are apparent differences between the models. For the Vivity, more light is directed into the far focus in low light conditions, whereas the LuxSmart behaves more pupil independent and prioritizes intermediate vision. The simulation-based approach was effective in evaluating and comparing the design aspects of these lenses. It can be positioned as a valuable third tool for lens characterization, complementing in vivo studies and in vitro measurements. With this approach not only focusing on the resulting optical performance, but the underlying functional mechanisms, it paves the way forward for a better adaptation to the individual needs and preferences of patients.

A Novel Automated System for Early Diabetic Retinopathy Detection and Severity Classification

ABSTRACTDiabetes is a common and serious global disease that damages blood vessels in the eye, leading to vision loss. Early and accurate diagnosis of this issue is crucial to reduce the risk of visual impairment. The typical deep learning (DL) methods for diabetic retinopathy (DR) grading are often time‐consuming, resulting in unsatisfactory detection performance due to inadequate representation of lesion features. To overcome these challenges, this research proposes a new automated mechanism for detecting and classifying DR, aiming to identify DR severities and different stages. To figure out and capture feature characteristics from DR samples, a conjugated attention mechanism and vision transformer are utilized within a collective net model, which automatically generates feature maps for diagnosing DR. These extracted feature maps are then fused through the feature fusion function in a fused attention net model, calculating attention weights to produce the most powerful feature map. Finally, the DR cases are identified and discriminated using the kernel extreme learning machine (KELM) model. For evaluating DR severity, our work utilizes four different benchmark datasets: APTOS 2019, MESSIDOR‐2 dataset, DiaRetDB1 V2.1, and DIARETDB0 datasets. To illuminate data noise and unwanted variations, two preprocessing steps are carried out, which include contrast enhancement and illumination correction. The experimental results evaluated using well‐known indicators demonstrate that the suggested method achieves a higher accuracy of 99.63% compared to other baseline methods. This research contributes to the development of powerful DR screening techniques that are less time‐consuming and capable of automatically identifying DR severity levels at a premature level.

Powerful QTL mapping and favorable allele mining in an all-in-one population: a case study of heading date.

The multiparent advanced generation intercross (MAGIC) population is characterized with great potentials in power and resolution of quantitative trait locus (QTL) mapping, but single nucleotide polymorphism (SNP)-based GWAS does not fully reach its potential. In this study, a MAGIC population of 1021 lines was developed from four Xian and four Geng varieties from five subgroups of rice. A total of 44000 genes showed functional polymorphisms among eight parents, including frameshift variations or premature stop codon variations, which provides the potential to map almost all genes of the MAGIC population. Principal component analysis results showed that the MAGIC population had a weak population structure. A high-density bin map of 24414 bins was constructed. Segregation distortion occurred in the regions possessing the genes underlying genetic incompatibility and gamete development. SNP-based association analysis and bin-based linkage analysis identified 25 significant loci and 47 QTLs for heading date, including 14 known heading date genes. The mapping resolution of genes is dependent on genetic effects with offset distances of <55kb for major effect genes and <123kb for moderate effect genes. Four causal variants and noncoding structure variants were identified to be associated with heading date. Three to four types of alleles with strong, intermediate, weak, and no genetic effects were identified from eight parents, providing flexibility for the improvement of rice heading date. In most cases, japonica rice carries weak alleles, and indica rice carries strong alleles and nonfunctional alleles. These results confirm that the MAGIC population provides the exceptional opportunity to detect QTLs, and its use is encouraged for mapping genes and mining favorable alleles for breeding.

Third-order smoothness metric to characterize progressive addition lenses

Although second-order surface analyses, mainly mean power and cylinder maps, are commonly used to characterize the progressive addition lens (PAL) surface, recently it has been suggested that third-order variations may also have relevancy in PAL optical and visual performance. This paper proposes a third-order smoothness metric, and its associated Riemannian distance, to further characterize PAL’s surface optical performance. These metrics can provide a complementary scoring tool to those classical ones, particularly, to analyze the transition zones between far, near, intermediate, and blending zones. A method to compute these metrics is provided. This third-order smoothness metric also enables a formal definition of the PAL principal curve, namely, the curve embedded in the PAL surface, that minimizes the line path integral joining the far and near reference points weighted by the third-order smoothness metric. Finally, the paper describes a comprehensive methodology to compute such principal curves using a level-set geodesic procedure. All these ideas are put into practice with several real PAL surfaces.

On the Pentanomial Power Mapping Classification of 8-bit to 8-bit S-Boxes

Substitution boxes, or S-boxes, are one of the most important mathematical primitives in modern symmetric cryptographic algorithms. Given their importance, in the past decades, they have been thoroughly analyzed and evaluated by the academic world. Thus, a lot of desirable characteristics a given S-box should possess have been found. This includes, as much as possible, higher nonlinearity and algebraic degrees as well as, as much as possible, lower values of differential uniformity, autocorrelation and sum of squares indicator values. In this work, we use power mappings over GF(28) to generate, enumerate and evaluate all bijective S-boxes yielded by pentanomials of the form f(x)=xa+xb+xc+xd+xe given 0&lt;a&lt;b&lt;c&lt;d&lt;e&lt;256. We find a total of 152,320 different bijective S-boxes, which are further classified into 41,458 different groups in terms of the aforementioned characteristics as well as the number of their fixed points. Having this data, an S-box designer can easily generate a bijective substitution S-box with parameters of their choice. By using pentanomials, we show how we can easily construct S-boxes with cryptographic properties similar to those found in some popular S-boxes like the Kuznyechik S-box proposed by the Russian Federation’s standardization agency as well as the Skipjack S-box proposed by the National Security Agency of the USA.

Continuous mapping of nuclear reactor core power using artificial neural network even in the presence of inactive detectors

Monitoring the radial power distribution during the operation of a pressurized light water reactor (PWR) is crucial for ensuring safe operating conditions and achieving high levels of fuel burnup. This paper introduces a methodology utilizing Artificial Neural Networks (ANN) for reconstructing the radial power distribution in the core of a Pressurized Water Reactor (PWR) with a hot full power of 1876 MWth, such as the Angra 1 reactor. This approach uses measurements from Self-Powered Neutron Detectors (SPND), simulated through the SERPENT code. The use of ANN demonstrated good accuracy in predicting the radial power distribution with an average relative error of 1.27%, considering 36 active detectors, with maximum relative error of 6.99%. Moreover, the proposed process demonstrated robust performance, even when measurements from one, two, or three SPND detectors were unavailable, resulting in errors of 1.24%, 1.13 %, and 1.09%, respectively. Therefore, the methodology ensures a reliable reconstruction of the radial power distribution, even when SPND detector measurements are unavailable, enabling the optimization of detector use and contributing to the increase of operational safety margins.

Solar photovoltaic power forecasting system with online manner based on adaptive mode decomposition and multi-objective optimization

Constructing an accurate and reliable solar photovoltaic (PV) power forecasting system is crucial for smart grid management and dispatch. However, due to the intermittent, non-stationary and random nature of solar energy, current methods cannot effectively capture the dynamic change patterns of PV data, resulting in a forecasting accuracy that cannot satisfy the requirement for stable operation of smart grids. To address this issue, in this paper, a new solar PV power forecasting system is proposed based on a new adaptive mode decomposition method that combines machine learning models. First an adaptive mode decomposition method is proposed for adaptively eliminating high-frequency information of PV data, mitigating the impact of high noise on the forecasting performance. Then the powerful mapping ability of machine learning model is utilized to construct a solar PV power generation combination forecasting system. The system adopts a multi-objective optimization strategy to determine the optimal weights of the combination model, which reduces the volatility of the forecasting results and enhances the stability of the forecasting system. Experimental results demonstrate that the proposed system achieves the best overall performance with online manner on 10 state-of-the-art baselines. Furthermore, the evaluation analysis by Diebold–Mariano test, improvement ratio and sensitivity analysis further show that the stability and accuracy of the proposed system outperforms the comparative baselines.