Fast Learning Algorithm Research Articles

LKLPDA: A Low-Rank Fast Kernel Learning Approach for Predicting piRNA-Disease Associations.

Piwi-interacting RNAs (piRNAs) are increasingly recognized as potential biomarkers for various diseases. Investig-ating the complex relationship between piRNAs and diseases through computational methods can reduce the costs and risks associated with biological experiments. Fast kernel learning (FKL) is a classical method for multi-source data fusion that is widely employed in association prediction research. However, biological networks are noisy due to the limitations of measurement technology and inherent natural variation, which can hamper the effectiveness of the network-based ideal kernel. The conventional FKL method does not address this issue. In this study, we propose a low-rank fast kernel learning (LRFKL) algorithm, which consists of low-rank representation (LRR) and the FKL algorithm. The LRFKL algorithm is designed to mitigate the effects of noise on the network-based ideal kernel. Using LRFKL, we propose a novel approach for predicting piRNA-disease associations called LKLPDA. Specifically, we first compute the similarity matrices for piRNAs and diseases. Then we use the LRFKL to fuse the similarity matrices for piRNAs and diseases separately. Finally, the LKLPDA employs AutoGluon-Tabular for predictive analysis. Computational results show that LKLPDA effectively predicts piRNA-disease associations with higher accuracy compared to previous methods. In addition, case studies confirm the reliability of the model in predicting piRNA-disease associations. Availability and implementation: The LKLPDA software and data are freely available at https://github.com/Shiqzz/LKLPDA-master.git.

Weak Target Detection Based on Full-Polarization Scattering Features under Sea Clutter Background

Aiming at the low observable target detection under sea clutter backgrounds, this paper emphasizes the exploration of distinguishable full-polarization features between target and sea clutter echoes. To overcome the shortcomings of the existing polarization feature-based methods, the full-polarization features of sea clutter are modeled and analyzed in detail by using Van Zyl polarization decomposition. Then, three polarimetric features (the relative surface scattering energy, the relative dihedral scattering energy and the relative diffuse scattering energy) are extracted from the fully polarimetric radar sea clutter echoes, which improve the feature differences between sea clutter and targets. And a tri-polarimetric feature detector with constant false alarm rate (CFAR) is constructed based on the fast convex hull learning algorithm. The experimental results on the real measured IPIX radar datasets prove that the proposed full-polarization feature detector obtains more competitive detection performance and lower computational complexity than the several existing feature-based detectors.

Interactive molecular causal networks of hypertension using a fast machine learning algorithm MRdualPC

BackgroundUnderstanding the complex interactions between genes and their causal effects on diseases is crucial for developing targeted treatments and gaining insight into biological mechanisms. However, the analysis of molecular networks, especially in the context of high-dimensional data, presents significant challenges.MethodsThis study introduces MRdualPC, a computationally tractable algorithm based on the MRPC approach, to infer large-scale causal molecular networks. We apply MRdualPC to investigate the upstream causal transcriptomics influencing hypertension using a comprehensive dataset of kidney genome and transcriptome data.ResultsOur algorithm proves to be 100 times faster than MRPC on average in identifying transcriptomics drivers of hypertension. Through clustering, we identify 63 modules with causal driver genes, including 17 modules with extensive causal networks. Notably, we find that genes within one of the causal networks are associated with the electron transport chain and oxidative phosphorylation, previously linked to hypertension. Moreover, the identified causal ancestor genes show an over-representation of blood pressure-related genes.ConclusionsMRdualPC has the potential for broader applications beyond gene expression data, including multi-omics integration. While there are limitations, such as the need for clustering in large gene expression datasets, our study represents a significant advancement in building causal molecular networks, offering researchers a valuable tool for analyzing big data and investigating complex diseases.

A deep neural network based reverse radio spectrogram search algorithm

Abstract Modern radio astronomy instruments generate vast amounts of data, and the increasingly challenging radio frequency interference (RFI) environment necessitates ever-more sophisticated RFI rejection algorithms. The ‘needle in a haystack’ nature of searches for transients and technosignatures requires us to develop methods that can determine whether a signal of interest has unique properties, or is a part of some larger set of pernicious RFI. In the past, this vetting has required onerous manual inspection of very large numbers of signals. In this paper, we present a fast and modular deep learning algorithm to search for lookalike signals of interest in radio spectrogram data. First, we trained a β-variational autoencoder on signals returned by an energy detection algorithm. We then adapted a positional embedding layer from classical transformer architecture to a embed additional metadata, which we demonstrate using a frequency-based embedding. Next we used the encoder component of the β-variational autoencoder to extract features from small (∼715 Hz, with a resolution of 2.79 Hz per frequency bin) windows in the radio spectrogram. We used our algorithm to conduct a search for a given query (encoded signal of interest) on a set of signals (encoded features of searched items) to produce the top candidates with similar features. We successfully demonstrate that the algorithm retrieves signals with similar appearance, given only the original radio spectrogram data. This algorithm can be used to improve the efficiency of vetting signals of interest in technosignature searches, but could also be applied to a wider variety of searches for ‘lookalike’ signals in large astronomical data sets.

Eye-Tracking System with Low-End Hardware: Development and Evaluation

Eye-tracking systems have emerged as valuable tools in various research fields, including psychology, medicine, marketing, car safety, and advertising. However, the high costs of the necessary specialized hardware prevent the widespread adoption of these systems. Appearance-based gaze estimation techniques offer a cost-effective alternative that can rely solely on RGB cameras, albeit with reduced accuracy. Therefore, the aim of our work was to present a real-time eye-tracking system with low-end hardware that leverages appearance-based techniques while overcoming their drawbacks to make reliable gaze data accessible to more users. Our system employs fast and light machine learning algorithms from an external library called MediaPipe to identify 3D facial landmarks. Additionally, it uses a series of widely recognized computer vision techniques, like morphological transformations, to effectively track eye movements. The precision and accuracy of the developed system in recognizing saccades and fixations when the eye movements are mainly horizontal were tested through a quantitative comparison with the EyeLink 1000 Plus, a professional eye tracker. Based on the encouraging registered results, we think that it is possible to adopt the presented system as a tool to quickly retrieve reliable gaze information.

Fast sparse Bayesian learning-based seismic resolution enhancement

Seismic high resolution processing plays a crucial role in seismic interpretation and reservoir characterization. However, the low and high frequency of seismic signal are lost owing to the effects of earth filtering and diffraction. The missing of low-frequency increases the energy of wavelet side lobe, which not only enhances the interference with adjacent events, but also lead to side lobe artifacts. High frequency attenuation is more serious, which significantly reduces the seismic resolution. In addition, the current resolution enhancement methods are difficult to achieve desirable result in noise contaminated environment. A novel resolution enhancement method that extends high and low frequencies simultaneously and improves the signal-to-noise ratio (SNR) under the framework of sparse decomposition theory is proposed. Firstly, an over-complete dictionary is constructed using non-zero phase Ricker wavelet and then the effective seismic signal is extracted by sparse decomposition using the fast sparse Bayesian learning (FSBL) algorithm. Secondly, the effective frequency range of the seismic signal is determined through a series of atoms obtained by sparse decomposition. Then, a desired broadband spectrum can be identified depending on this range. By approximating the broadband spectrum of seismic data, the weak high-frequency information can be extended. Furthermore, a correction term is introduced in frequency domain to suppress the side lobes of atoms. The side lobes are well suppressed without distorting the main lobe, meanwhile, both the low and high frequencies are extended. Finally, the validity of this method is verified by synthetic and field data. The results show that this method has better performance than the ordinary deconvolution and spectral whitening methods in processing high resolution data.

A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning

Microstructural analyses of porous media have considerable research value when studying of macroscopic properties,and the accurate reconstruction of a digital microstructure model is an important component of this research. Computational reconstruction algorithms for microstructures have attracted much attention due to their low cost and excellent performance. However, achieving faster and more efficient reconstruction remains a challenge for computational reconstruction algorithms. The bottleneck lies in the computational reconstruction algorithms themselves, which are either too slow (traditional reconstruction algorithms) or not flexible to the training process (deep learning reconstruction algorithms). To address these limitations, we propose a fast and flexible deep learning algorithm using a neural network based on an improved simulated annealing framework (ISAF-NN). The proposed algorithm adopts structural information of the reference image to guide the network design, and uses the description function to extract feature distribution of the reference image as the objective function to complete the network optimization. Benefit from the network structure is simple and flexible, the proposed algorithm can complete training and reconstruction in a short time. By adjusting the input size, the algorithm can also achieve arbitrary sized reconstruction. The proposed algorithm is experimentally applied to several materials to verify its effectiveness and generalizability.

A High-Accuracy-Light-AI Data-Driven Diagnosis Method for Open-Circuit Faults in Single-Phase PWM Rectifiers

Data-driven solutions like artificial intelligence (AI) are more upright and effectual for fault diagnosis in the power converter system. To decrease computing load and improve the diagnosis speed of the intelligent algorithm, a high-accuracy-light-AI data-driven open-circuit diagnosis method is proposed to diagnose single or multiple IGBT open-circuit faults in the single-phase pulse width modulation (PWM) rectifiers. Firstly, the fault characteristics of three fault scenarios are analyzed to seek the most critical features and provide prior knowledge for developing the intelligent diagnostic algorithm. Then, a fast-learning algorithm named random vector function link network (RVFL) is utilized to extract the mapping knowledge between the well-selected features and fault modes. To balance the testing accuracy and calculation time of the diagnostic algorithm, the RVFL parameters are tuned to decrease the computing burden. After that, a decision-making framework is designed for identifying the faults in real-time. Finally, the effectiveness of the proposed fault diagnosis method is thoroughly verified by extensive experimental tests. A substantial comparison to state-of-the-art techniques shows the proposed scheme’s superiority in diagnostic accuracy, computing time, and diagnosis time.

MetaHEP: Meta learning for fast shower simulation of high energy physics experiments

For High Energy Physics (HEP) experiments, such as the Large Hadron Collider (LHC) experiments, the calorimeter is a key detector to measure the energy of particles. Incident particles interact with the material of the calorimeter, creating cascades of secondary particles, so-called showers. A detailed description of the showering process relies on simulation methods that precisely describe all particle interactions with matter. Constrained by the need for precision, the simulation of calorimeters is inherently slow and constitutes a bottleneck for HEP analysis. Furthermore, with the upcoming high luminosity upgrade of the LHC and a much-increased data production rate, the amount of required simulated events will increase. Several research directions have recently investigated the use of Machine Learning based models to accelerate particular calorimeter response simulation. These models typically require a large amount of data and time for training, and the result is a simulation tuned specifically to this configuration. Meta-learning has emerged recently as a fast learning algorithm using small training datasets. In this paper, we use a meta-learning approach that “learns to learn” to generate showers from multiple calorimeter geometries, using a first-order gradient-based algorithm. We present MetaHEP, the first application of the meta-learning approach to accelerate shower simulation using very high granular data and using one of the calorimeters proposed for the Future Circular Collider (FCC), a next-generation of high-performance particle colliders.

Functional extreme learning machine.

Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. However, the ELM also has some shortcomings, such as structure selection, overfitting and low generalization performance. This article a new functional neuron (FN) model is proposed, we takes functional neurons as the basic unit, and uses functional equation solving theory to guide the modeling process of FELM, a new functional extreme learning machine (FELM) model theory is proposed. The FELM implements learning by adjusting the coefficients of the basis function in neurons. At the same time, a simple, iterative-free and high-precision fast parameter learning algorithm is proposed. The standard data sets UCI and StatLib are selected for regression problems, and compared with the ELM, support vector machine (SVM) and other algorithms, the experimental results show that the FELM achieves better performance.

High-Speed Maneuvering Target Inverse Synthetic Aperture Radar Imaging and Motion Parameter Estimation Based on Fast Spare Bayesian Learning and Minimum Entropy

High-speed maneuvering target inverse synthetic aperture radar (ISAR) imaging is always a hot topic in signal processing. High-speed maneuvering targets often have high-order maneuvering characteristics, such as translational and rotational characteristics, which destroy the signal structure of stationary targets and make basic imaging processing methods such as range-Doppler (RD) algorithm no longer suitable. In this paper, a high-resolution imaging method for high-speed maneuvering targets is proposed, which uses the fast sparse Bayesian learning (SBL) algorithm and the minimum entropy algorithm for ISAR high-resolution imaging and motion parameter estimation, respectively. Because SBL makes full use of the characteristics of the target and the environment, it can obtain an ISAR high-resolution image of the maneuvering target. However, the high computational complexity caused by matrix inversion and some matrix operations in SBL iteration limit the practical application of SBL in ISAR imaging. In view of the special structure of the matrix required to be inverted, we propose a fast SBL algorithm, which uses a new decomposition method to obtain the decomposition formula of the inverse matrix. Based on the decomposition factors, the multiplication operation involving the inverse matrix can be quickly calculated using fast Fourier transform (FFT), which greatly improves the computational efficiency. Image entropy represents the sharpness and focusing degree of an image, and so the minimum entropy algorithm can estimate the motion parameters of maneuvering targets more accurately. We combine the minimum entropy algorithm with the fast SBL algorithm to realize phase error correction and high-resolution imaging, which has better noise sensitivity and can obtain the best focusing degree image. Finally, simulation results prove the effectiveness of this algorithm.

Optimizing Optical Potentials With Physics-Inspired Learning Algorithms

We present our experimental and theoretical framework, which combines a broadband superluminescent diode with fast learning algorithms to provide speed and accuracy improvements for the optimization of on-dimensional optical dipole potentials, here generated with a digital micromirror device. To characterize the setup and potential speckle patterns arising from coherence, we compare the superluminescent diode to a single-mode laser by investigating interference properties. We employ machine-learning tools to train a physics-inspired model acting as a digital twin of the optical system predicting the behavior of the optical apparatus including all its imperfections. Implementing an iterative algorithm based on iterative learning control we optimize optical potentials an order of magnitude faster than heuristic optimization methods. We compare iterative model-based ``offline'' optimization and experimental feedback-based ``online'' optimization. Our methods provide a route to fast optimization of optical potentials, which is relevant for the dynamical manipulation of ultracold gases.

Probability-Based Diagnostic Imaging of Fatigue Damage in Carbon Fiber Composites Using Sparse Representation of Lamb Waves

Carbon fiber composites are commonly used in aerospace and other fields due to their excellent properties, and fatigue damage will occur in the process of service. Damage imaging can be performed using damage probability imaging methods to obtain the fatigue damage condition of carbon fiber composites. At present, the damage factor commonly used in the damage probability imaging algorithm has low contrast and poor anti-noise performance, which leads to artifacts in the imaging and misjudgment of the damaged area. Therefore, this paper proposes a fatigue damage probability imaging method for carbon fiber composite materials based on the sparse representation of Lamb wave signals. Based on constructing the Lamb wave dictionary, a fast block sparse Bayesian learning algorithm is used to represent the Lamb wave signals sparsely, and the definition of Lamb wave sparse representing the damage factor calculates the damage probability of the monitoring area and then images the fatigue damage of the carbon fiber composite materials. The imaging research was carried out using the fatigue monitoring experiment data of NASA’s carbon fiber composite materials. The results show that the proposed damage factor can clearly distinguish the damaged area from the undamaged area and has strong noise immunity. Compared with the energy damage factor and the cross-correlation damage factor, the error percentages are reduced by at least 58.63%, 28.11%, and 8.43% for signal-to-noise ratios of 6 dB, 3 dB, and 0.1 dB, respectively, after adding noise to the signal. The results can more accurately reflect the real location and area of fatigue damage in carbon fiber composites.

Accelerating probabilistic tensor canonical polyadic decomposition with nonnegative factors: An inexact BCD Approach

Recently, Bayesian modeling and variational inference (VI) were leveraged to enable the nonnegative factor matrix learning with automatic rank determination in tensor canonical polyadic decomposition (CPD), which has found various applications in big data analytics. However, since VI inherently performs block coordinate descent (BCD) steps over the functional space, it generally does not allow integration with modern large-scale optimization methods, making the scalability a critical issue. In this paper, it is revealed that the expectations of the variables updated by the VI algorithm is equivalent to the block minimization steps of a deterministic optimization problem. This equivalence further enables the adoption of inexact BCD method for devising a fast nonnegative factor matrix learning algorithm with automatic tensor rank determination. Numerical results using synthetic data and real-world applications show that the performance of the proposed algorithm is comparable with that of the VI-based algorithm, but with computation times reduced significantly.

Meta-learning for multiple detector geometry modeling

The simulation of the passage of particles through the detectors of High Energy Physics (HEP) experiments is a core component of any physics analysis. A detailed and accurate simulation of the detector response using the Geant4 toolkit is a time and CPU consuming process. With the upcoming high luminosity LHC upgrade, with more complex events and a much increased trigger rate, the amount of required simulated events will increase. Several research directions investigated the use of Machine Learning based models to accelerate particular detector response simulation. This results in a specifically tuned simulation and generally these models require a large amount of data for training. Meta learning has emerged recently as fast learning algorithm using small training datasets. In this paper, we propose a meta-learning model that “learns to learn” to generate electromagnetic showers using a first-order gradient based algorithm. This model is trained on multiple detector geometries and can rapidly adapt to a new geometry using few training samples.

Accurate and fast machine learning algorithm for systems outage prediction

Cyber-attacks (CAs) on electrical networks in presents of renewable energies, particularly solar energy, have become more complex and sophisticated over the past few years by making severe system outages. In light of increased automation in solar-based energy industries, a holistic cyber-physical infrastructure must be considered to predict the effect of CAs on electrical networks and the ways to enhance its resilience. The present study examines the resilience characteristics at the equipment area of the diverse control methods and their effect on the outage severity of the smart grid using digital twins (DT) simulation technology. The paper presents a machine learning based metric for measuring the resilience of cyber-physical features that considers device-level characteristics, vulnerabilities, and system models. Resiliency refers to a system's capability of providing energy even during severe contingencies and relates to the ability to resist, forecast, and recover. An example based on the newest CA against Ukraine has been provided and simulated on DT environment. A case study is proposed to illustrate how cyber-physical resilience metrics can be applied to improve operators' situational awareness and provide more proactive or corrective control measures for improving resilience.

Underwater Acoustic Channel Estimation Based on Sparse Bayesian Learning Algorithm

The channel estimation algorithm based on sparse Bayesian learning proposed in recent years shows better performance than the traditional channel estimation algorithm by effectively reducing the convergence error in the channel estimation process. However, the sparse Bayesian learning algorithm based on expectation maximization (EM-SBL) is difficult to meet the practical applications with low complexity and power consumption. In order to guarantee the long-term stable communication of underwater devices, this paper proposes the fast sparse Bayesian learning algorithm based on Fast Marginal Likelihood Maximization (FM-SBL) to estimate underwater acoustic channels with low power consumption and high performance. Simulation and sea trial results show the output BER after channel estimation of FM-SBL is similar to that of EM-SBL, better than LS, MP and OMP, and it has good robustness in fast and slow time-varying channels. In terms of running speed, the FM-SBL algorithm is 16.7% of EM-SBL algorithm, which greatly reduces the estimation time.

Synthetic Beam Scanning and Super-Resolution Coincidence Imaging Based on Randomly Excited Antenna Array

Nowadays, there is no good scheme for simultaneously achieving super-resolution imaging within a coherent beamwidth and beam scanning in microwave radar. In this paper, a synthetic beam scanning method based on a randomly excited antenna array, which possesses the ability of super-resolution coincidence imaging, is proposed. The beamwidth of the randomly excited array is comparable to that of the conventional phased array with the same size, and its steering angle can be adjusted by modulating the excitation signals. Firstly, the optimized covariance matrix of the proposed array to uniformly bunch the spatial radiation energy in a specific angle range is obtained by means of the sequential quadratic programming (SQP) algorithm. Accordingly, the partially correlated excitation signals restricted by the optimized covariance matrix are determined. Then, a secondary weighted modulation method is proposed to steer the main beam to the direction of interest. The excitation signals are weighted by the conjugated radiation fields in the direction of interest. Furthermore, the super-resolution ability of the proposed coincidence imaging system is analyzed based on the first-order statistical characteristics of the radiation fields. Simulations and experiments demonstrate that synthetic beam scanning can be realized by controlling the excitation signals. Besides, a 10 times super-resolution coincidence image can be reconstructed within a coherent beamwidth (3dB-beamwidth) when the signal-to-noise (SNR) is greater than 15 dB, assisted by the fast Bayesian learning (FBL) algorithm.

Clustering of massive datasets using an Adaptive and efficient K-Means approach

In today’s technology-driven and Internet-obsessed society, it can be challenging to go through huge amounts of information and find relevant knowledge for various educational contexts. Simple, fast, and adaptable machine learning algorithms make such tasks easier to complete. K-means is the most effective unsupervised learning technique for classifying data into meaningful groups. K-means groups data by shared characteristics. K-means clusters are determined by k. Unfortunately, standard k-means requires a lot of math. Scholars have suggested strategies to improve k-means grouping. This work recommends computing initial centroids and establishing a distance between data points that are unlikely to change their cluster in subsequent iterations and those that are extremely likely to do so to lessen the load of k-means clustering for very large data sets. This piece will find information digits whose cluster is statistically likely to alter in the following few cycles. After processing several datasets, it is compared to other K-Means methods

Digital twin application for attach detection and mitigation of PV-based smart systems using fast and accurate hybrid machine learning algorithm

Microgrids (MG) is originally designed to make Smart Grids more energy-efficient and reliable. The MG represents a complex cyber-physical system whose functioning is driven by the interaction of physical actions and computational elements, making it vulnerable to many forms of malicious cyber-attack. This study considers the effect of data integrity attack (DIA) on the performance of hybrid MGs, an important cyber threat to microgrids (MGs). Further, this paper develops a new process using sequential hypothesis testing (SHT) for detecting DIA on renewable energy resources and improving the security of information in hybrid MGs. By using a binary sample generated from the suggested approach, an analysis statistic is computed and afterward compared to 2 thresholds for deciding between the 3 options. On the measured energy production of renewable energy sources such as wind turbines, DIAs of various severity levels have been conducted for assessing the impact of DIAs on hybrid MG security. A standard IEEE test system has been used to evaluate the efficiency of the suggested process.