Reduction Algorithm Research Articles

Noise & mottle suppression methods for cumulative Cherenkov images of radiation therapy delivery

Purpose.Cherenkov imaging during radiotherapy provides a real time visualization of beam delivery on patient tissue, which can be used dynamically for incident detection or to review a summary of the delivered surface signal for treatment verification. Very few photons form the images, and one limitation is that the noise level per frame can be quite high, and mottle in the cumulative processed images can cause mild overall noise. This work focused on removing or suppressing noise via image postprocessing.Approach.Images were analyzed for peak-signal-to-noise and spatial frequencies present, and several established noise/mottle reduction algorithms were chosen based upon these observations. These included total variation minimization (TV-L1), non-local means filter (NLM), block-matching 3D (BM3D), alpha (adaptive) trimmed mean (ATM), and bilateral filtering. Each were applied to images acquired using a BeamSite camera (DoseOptics) imaged signal from 6x photons from a TrueBeam linac delivering dose at 600 MU min-1incident on an anthropomorphic phantom and tissue slab phantom in various configurations and beam angles. The standard denoised images were tested for PSNR, noise power spectrum (NPS) and image sharpness.Results.The average peak-signal-to-noise ratio (PSNR) increase was 17.4% for TV-L1. NLM denoising increased the average PSNR by 19.1%, BM3D processing increased it by12.1% and the bilateral filter increased the average PSNR by 19.0%. Lastly, the ATM filter resulted in the lowest average PSNR increase of 10.9%. Of all of these, the NLM and bilateral filters produced improved edge sharpness with, generally, the lowest NPS curve.Conclusion.For cumulative image Cherenkov data, NLM and the bilateral filter yielded optimal denoising with the TV-L1 algorithm giving comparable results. Single video frame Cherenkov images exhibit much higher noise levels compared to cumulative images. Noise suppression algorithms for these frame rates will likely be a different processing pipeline involving these filters incorporated with machine learning.

Unsupervised learning analysis on the proteomes of Zika virus

Background The Zika virus (ZIKV), which is transmitted by mosquito vectors to nonhuman primates and humans, causes devastating outbreaks in the poorest tropical regions of the world. Molecular epidemiology, supported by clustering phylogenetic gold standard studies using sequence data, has provided valuable information for tracking and controlling the spread of ZIKV. Unsupervised learning (UL), a form of machine learning algorithm, can be applied on the datasets without the need of known information for training. Methods In this work, unsupervised Random Forest (URF), followed by the application of dimensional reduction algorithms such as principal component analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), t-distributed stochastic neighbor embedding (t-SNE), and autoencoders were used to uncover hidden patterns from polymorphic amino acid sites extracted on the proteome ZIKV multi-alignments, without the need of an underlying evolutionary model. Results The four UL algorithms revealed specific host and geographical clustering patterns for ZIKV. Among the four dimensionality reduction (DR) algorithms, the performance was better for UMAP. The four algorithms allowed the identification of imported viruses for specific geographical clusters. The UL dimension coordinates showed a significant correlation with phylogenetic tree branch lengths and significant phylogenetic dependence in Abouheif’s Cmean and Pagel’s Lambda tests (p value < 0.01) that showed comparable performance with the phylogenetic method. This analytical strategy was generalizable to an external large dengue type 2 dataset. Conclusion These UL algorithms could be practical evolutionary analytical techniques to track the dispersal of viral pathogens.

Application of Machine Learning Techniques in Calibration and Data Reduction of Multi-Hole Probes

Abstract This work presents procedures to implement machine learning methods in the existing algorithms for multi-hole probe calibrations and data reduction. It is shown here, that utilizing artificial neural networks (ANNs) can reduce the amount of calibration data that needs to be acquired in order to obtain a specific calibration uncertainty, by more than 50% while simultaneously reducing data reduction times significantly. ANNs were used instead of the surface fitting methods, where first, the directional calibration coefficients related to the flow angles are calculated based on the pressure measurements, and then the flow angles are used as a set of the input parameters for the following ANNs to define Mach number and static and total pressure iteratively. In a second approach, novel calibration coefficients were used to directly relate the pressure measurements from five-hole probe to the quantities of interest thus, eliminating the need for iterative algorithms used in the conventional surface fitting methods. The advantageous features of this method are an average increase of less than 1% in the calibration uncertainty for flow angles and significant reduction of the data reduction times (few seconds). In addition, we confirmed the methodology to avoid over-fitting and under-fitting.

GraphPCA: a fast and interpretable dimension reduction algorithm for spatial transcriptomics data

The rapid advancement of spatial transcriptomics technologies has revolutionized our understanding of cell heterogeneity and intricate spatial structures within tissues and organs. However, the high dimensionality and noise in spatial transcriptomic data present significant challenges for downstream data analyses. Here, we develop GraphPCA, an interpretable and quasi-linear dimension reduction algorithm that leverages the strengths of graphical regularization and principal component analysis. Comprehensive evaluations on simulated and multi-resolution spatial transcriptomic datasets generated from various platforms demonstrate the capacity of GraphPCA to enhance downstream analysis tasks including spatial domain detection, denoising, and trajectory inference compared to other state-of-the-art methods.

RC Bridge Concrete Surface Cracks and Bug-Holes Detection Using Smartphone Images Based on Flood-Filling Noise Reduction Algorithm

Noise reduction is a key process in digital image detection technology for concrete cracks and bug-holes. In this study, the threshold range of the flood-filling noise reduction algorithm was investigated experimentally. Surface cracks and bug-holes in RC bridge concrete were detected using mobile terminal images based on the flood-filling noise reduction algorithm. The results showed that the error range was within 10% when threshold range Θ was confined in [60, 80] as the crack width was from 0.1 mm to 2 mm. It is suitable that the threshold range Θ was selected as 70 while the measured crack width range was 0.2 mm to 2 mm. However, by reducing the values of the threshold range Θ to 50, the miscalculation was obviously eliminated. The influences of reducing values of the threshold range on bug-holes of the equivalent diameter and area were not significant. It is suitable that the threshold range Θ was elected on 50 to detect bug-holes in the concrete surface. The threshold range can be selected as a suitable value for the detection of cracks and bug-holes in order to reduce noise.

Inner product reduction for fuzzy formal contexts

Formal concept analysis finds application across multiple domains, including knowledge representation, data mining, and decision analysis. Within this framework, the exploration of attribute reduction for fuzzy formal contexts represents a substantial area of research. We introduce a novel form of attribute reduction for fuzzy formal contexts named inner product reduction, and an algorithm for finding all inner product reducts is given by using the indiscernibility matrix, and a calculation example is given. Furthermore, for consistent fuzzy decision formal contexts, the definition and algorithm of inner product reduction are given. Finally, the concept and algorithm of inner product reduction are extended to general fuzzy decision formal contexts. Through experimental verification, the viability and efficacy of the inner product reduction algorithm for fuzzy formal contexts are verified.

Local fuzzy rough attribute reduction for large-scale mixed data with limited missing labels based on local fuzzy self information

The advent of the era of big data is accompanied by the generation of large-scale data of various types. Extracting the potential value and rules from such data has always been a challenge. Due to various external and internal factors, it is commonplace for large-scale data to exhibit the phenomenon of missing limited labels. In addressing a large-scale mixed information system with limited label missing (LSMDISLML), local neighborhood rough set model (LNRS-model) is typically employed. However, the identical neighborhood radius is often used by such model when confronted with numerical attributes, which could potentially attenuate the classification capability of the data. Local fuzzy rough set model (LFRS-model) can overcomes this point. This paper studies local fuzzy rough attribute reduction for large-scale mixed data with limited missing labels based on LFRS-model via local fuzzy self information and overlap degree function. First, leveraging the statistical distribution of data as a foundation, fuzzy relations on the entire sample set are established, which has the advantage of being able to use different fuzzy similarity radii to calculate similarity, thereby adapting to different data distributions. Subsequently, the samples with missing labels are discarded as they constitute a small proportion of the entire sample set and have little impact on overall performance of dataset. The limited computing resources and storage space are focused on the sample set with complete labels (denoted as target set). Thereafter, based on the target set, local fuzzy λ-upper and lower approximations are defined, and LFRS-model is constructed. This model not only reduces processing time and sources of error in large-scale data but also improves data quality and enhances the reliability of the experimental results. Then, local fuzzy λ-self information is introduced and used to design a local fuzzy rough attribute reduction algorithm in a LSMDISLML. Furthermore, a overlap degree function is introduced to evaluate and reorder the attributes based on their importance, prioritizing the elimination of redundant attributes with high overlap and low importance from the preordered attribute set. This strategy effectively improves the efficiency of obtaining the optimal subset. Finally, a series of experiments are carried out. The experiment results demonstrate that the designed algorithm exhibits excellent performance in classification tasks and outlier detection tasks, surpassing existing four algorithms.

Implementation of entropically secure encryption: Securing personal health data

AbstractEntropically secure encryption (ESE) offers unconditional security with shorter keys compared to the One‐Time Pad. Here, the first implementation of ESE for bulk encryption is presented. The main computational bottleneck for bulk ESE is a multiplication in a very large finite field. This involves multiplication of polynomials followed by modular reduction. A polynomial multiplication is implemented based on the gf2x library, with modifications that avoid inputs of vastly different length, thus improving speed. Additionally, a recently proposed efficient reduction algorithm that works for any polynomial degree is implemented. Two use cases are investigated: x‐ray images of patients and human genome data. Entropy estimation is conducted using compression methods whose results determine the key lengths required for ESE. The running times for all steps of the encryption are reported. The potential of ESE to be used in conjunction with quantum key distribution (QKD), in order to achieve full information‐theoretic security of QKD‐protected links for these use cases is discussed.

Research on Automatic Detection System of Drawing Defects based on Machine Vision

Background: For a long time, product packaging has been used as an instruction manual to connect consumers and factories. Product packaging is an important column in product image display and information presentation. However, missing prints, misprints, and surface stains during the manufacture of packaging bags will cause consumers to misunderstand product information. Based on machine vision, image processing technology, and Python language, this paper designs an automatic detection system for paper defects. Through the preprocessing of the image of the paper to be tested, after the paper area is extracted and compared with the standard template paper, the defective parts of the paper to be tested relative to the standard template paper can be quickly and accurately obtained. The system has a single drawing detection time of 2~3 seconds, and the measurement accuracy rate reaches 100%. The results show that the system has high measurement accuracy, high measurement precision, fast measurement speed, strong adaptability to the environment, and can meet the requirements of detecting defective paper. Objective: The purpose of this study is to develop an automatic detection system for packaging paper, which can detect all defective parts of defective paper compared with standard paper templates. This study aims to reduce the misprints or stains that may occur when producing high-volume bags. The system optimizes and controls the detection accuracy, detection time, detection accuracy and detection environment to ensure that the system can meet the real detection requirements. Method: First, the accompanying software of this system is used to import the standard template of the inspection paper and use the industrial camera to obtain the original image of the inspection drawing. Then, a series of necessary processing is performed on the image: grayscale, Gaussian filter, median filter, binarization, edge detection, contour detection, and the paper area covered with the image is extracted through inverse perspective transformation. Secondly, divide the picture into several blocks and measure the translation matrix of each block to achieve translation fine-tuning to achieve higher detection accuracy. Then, the defect mask is obtained by comparing it with the standard template, and the mask is fine-tuned and processed by the strong noise reduction algorithm. After median filtering, binarization, erosion, marking and other operations are performed to realize the final defect area finding and marking. Finally, all defective areas will be displayed in the designated area of the included software. Results: The detection accuracy rate of this system for the defect area reaches 100%, the minimum range of the recognition area reaches 1mm (2 pixels), the light intensity of the detection environment can adapt to 50 gray levels compared with the template, and the detection of a single drawing only takes 2 ~3 seconds, indicating the high detection efficiency of the system. A patent application for the system has already begun. Conclusion: The system has strong adaptability to the light intensity range of the testing environment, and the minimum testing area can meet the requirements of most production drawings. The accuracy of identifying the defect area of the testing drawings shows that the system can complete the testing task well when the testing environment is suitable.

Spcolor: Semantic prior guided exemplar-based image colorization

Exemplar-based image colorization aims to colorize a target grayscale image based on a color reference image, and the key is to establish accurate pixel-level semantic correspondence between these two images. Previous methods directly search for correspondence over the entire reference image, and this type of global matching is prone to mismatch. Intuitively, a reasonable correspondence should be established between objects which are semantically similar. Motivated by this, we introduce the idea of semantic prior and propose SPColor, a semantic prior guided exemplar-based image colorization framework. Several novel components are systematically designed in SPColor, including a semantic prior guided correspondence network (SPC), a category reduction algorithm (CRA), and a similarity masked perceptual loss (SMP loss). Different from previous methods, SPColor establishes the correspondence between the pixels in the same semantic class locally. In this way, improper correspondence between different semantic classes is explicitly excluded, and the mismatch is obviously alleviated. In addition, SPColor supports region-level class assignments before SPC in the pipeline. With this feature, a category manipulation process (CMP) is proposed as an interactive interface to control colorization, which can also produce more varied colorization results and improve the flexibility of reference selection. Experiments demonstrate that our model outperforms recent state-of-the-art methods both quantitatively and qualitatively on public dataset. Our code is available at https://github.com/viector/spcolor.

A Green analytical method for simultaneous determination of dexamethasone sodium phosphate and prednisolone acetate in veterinary formulations using UV spectroscopy and dimension reduction algorithms

A Green analytical method for simultaneous determination of dexamethasone sodium phosphate and prednisolone acetate in veterinary formulations using UV spectroscopy and dimension reduction algorithms

A BACTERIA FORAGING ALGORITHM-BASED HYBRID A-LAW AND PTS PAPR REDUCTION METHOD FOR BEYOND 5G WAVEFORM

One of the most advanced waveforms available in the beyond-fifth-generation radio (B5GR) framework is nonorthogonal multiple access (NOMA). The power amplifier (PA) of the NOMA structure performs less efficiently when the signal is strong and the peak-to-average power ratio (PAPR) is high. This study applies a hybrid algorithm to the NOMA structure, combining fractal partial transmit sequence (PTS), A-law companding, and the bacterial foraging algorithm (BFA). Fractals are known for their self-repeating structures at different scales, allowing for efficient coverage and exploration of space. Fractals enhance the bacteria foraging algorithm (BFA) by improving search efficiency, enabling better exploration of complex, multi-dimensional optimization landscapes. Similarly, BFA balances exploring the search in promising areas. We utilized BFA to achieve optimal phase factors for the PTS algorithm and applied A-Law companding to the NOMA symbols to further enhance the structure’s performance. The intermediate computational complexity in the Rician and Rayleigh channels improves PAPR, bit error rate (BER), and power spectral density performance. Simulation results reveal that the performance of the proposed hybrid method is superior to that of existing PAPR reduction algorithms and substantially enhances the efficiency of NOMA.

A Heuristic Attribute-Reduction Algorithm Based on Conditional Entropy for Incomplete Information Systems

With the continuous expansion of databases, the extraction of information has been an urgent research topic in many fields. As an effective method to remove redundant attributes, attribute reduction demonstrates extraordinary ability in simplifying information systems. This paper applies a novel form of conditional entropy to investigate the attribute reduction in incomplete information systems. Firstly, a novel definition of conditional entropy is introduced based on tolerance relation. Additionally, in order to reduce time complexity, we propose a binsearch heuristic attribute-reduction algorithm with conditional entropy as heuristic knowledge. Furthermore, two examples are used to illustrate the feasibility and validity of the reduction algorithm.

Acoustic structure inverse design and optimization using deep learning

From ancient to modern times, acoustic structures have been employed to manage the spread of acoustic waves. Nevertheless, designing these structures traditionally remains a laborious and computationally intensive iterative process. Recognizing that complex acoustic systems can be effectively analyzed using the lumped-parameter method, we introduce a deep learning model that learns the correlation between the equivalent electrical parameters and the acoustic properties of these structures. As an illustration, we consider the design of multi-order Helmholtz resonators, showing experimentally that our model can predict structures with high precision that closely align with the specified design criteria. Furthermore, our model can seek multiple solutions in conjunction with dimensionality reduction algorithms and support evolutionary algorithms in optimization tasks. Compared to traditional numerical methods, our approach offers greater efficiency, flexibility, and universality. The designed acoustic structures hold broad potential for applications including speech enhancement, sound absorption, and insulation.

Low-dimensional projection of reactivity classes in chemical reaction dynamics using supervised dimensionality reduction.

Transition state theory (TST) provides a framework to estimate the rate of chemical reactions. Despite its great success with many reaction systems, the underlying assumptions such as local equilibrium and nonrecrossing do not necessarily hold in all cases. Although dynamical systems theory can provide the mathematical foundation of reaction tubes existing in phase space that enables us to predict the fate of reactions free from the assumptions of TST, numerical demonstrations for large systems have been yet one of the challenges. Here, we propose a dimensionality reduction algorithm to demonstrate structures in phase space (called reactive islands) that predict reactivity in systems with many degrees of freedom. The core of this method is the application of supervised principal component analysis, where a coordinate transformation is performed to preserve the dynamical information on reactivity (i.e., to which potential basin the system moves from a region of interest) as much as possible. The reactive island structures are expected to be reflected in the transformed, low-dimensional phase space. As an illustrative example, the algorithm is scrutinized using a modified Hénon-Heiles Hamiltonian system extended to many degrees of freedom, which has three channels leading to three different products from one stable potential basin. It is shown that our algorithm can predict the reactivity in the transformed, low-dimensional coordinate system better than a naïve coordinate system and that the reactivity distribution in the transformed low-dimensional space is considered to reflect the underlying reactive islands.

Method for Noise Reduction by Averaging the Filtering Results on Circular Displacements Using Wavelet Transform and Local Binary Pattern

Algorithms for noise reduction that use the translation invariant wavelet transform indirectly are spatially selective filtering algorithms in the wavelet domain. These algorithms use the undecimated wavelet transform to accurately determine the coefficients corresponding to the contours in the images, these being processed differently from the other wavelet coefficients. The use of the undecimated wavelet transform in image noise reduction applications leads not only to an improvement in terms of Mean Square Error (MSE), but also in terms of the content quality of the processed images. In the case of noise reduction procedures by truncation of wavelet coefficients, artifacts appear, especially in the approximation of singularities, due to some pseudo-Gibbs phenomena. These artifacts, which appear locally, are troublesome in the case of object recognition applications from images acquired in conditions of nonuniform illumination and low contrast. In this work we propose a method of feature extractor based on undecimated wavelet transform (UWT) and local binary pattern (LBP). The results obtained on images acquired from drones in adverse conditions show promising results in terms of accuracy. The authors show that the displacement-invariant wavelet transform is an very good method of compression and noise reduction in signals.

MD-HIT: Machine learning for material property prediction with dataset redundancy control

Materials datasets usually contain many redundant (highly similar) materials due to the tinkering approach historically used in material design. This redundancy skews the performance evaluation of machine learning (ML) models when using random splitting, leading to overestimated predictive performance and poor performance on out-of-distribution samples. This issue is well-known in bioinformatics for protein function prediction, where tools like CD-HIT are used to reduce redundancy by ensuring sequence similarity among samples greater than a given threshold. In this paper, we survey the overestimated ML performance in materials science for material property prediction and propose MD-HIT, a redundancy reduction algorithm for material datasets. Applying MD-HIT to composition- and structure-based formation energy and band gap prediction problems, we demonstrate that with redundancy control, the prediction performances of the ML models on test sets tend to have relatively lower performance compared to the model with high redundancy, but better reflect models’ true prediction capability.

Face Image Recognition by using some Dimension Reduction Algorithms and Logistic Regression

Face recognition is a common technique for artificial intelligence and image processing in which machine-learning algorithms automatically recognize a person's face through a huge image collection or even from a live video since there is difficulty in detecting data when using different shots for the same person in a facial recognition system, it takes time to determine person's membership. Furthermore, when working with high-dimensional data, where the 2D-pixel values of facial images, can be computationally challenging, the face recognition problem gets harder, so the current research compares the dimensionality reduction techniques like the principal component analysis algorithm PCA, an unsupervised learning algorithm that reduces dimensions by moving them from a high-dimensional area to a lower area without losing important information, and the two-dimensional principal component analysis algorithm 2DPCA to determine which technique is most effective for the process of detecting facial images, and this method will be compared with the logistic regression which is a statistical model for face recognition that has been used for classification tasks. Two different sets of data were used, the first group represented the ORL database, which was made up of 40 individuals, while the second group represented the real data, which was made up of 100 individuals from AL-Mamoon College, the results showed that the logistic regression model achieved the lowest MSE for ORL dataset and real data by achieving (0.0024414, 0.091936) respectively, followed by 2DPCA and PCA and all three techniques reached the highest accuracy rate of 100% for facial image recognition on real data. Paper type: Research paper

MEGS: Morphological Evaluation of Galactic Structur. Principal component analysis as a galaxy morphology model

Understanding the morphology of galaxies is a critical aspect of astrophysics research, providing insight into the formation, evolution, and physical properties of these vast cosmic structures. Various observational and computational methods have been developed to quantify galaxy morphology, and with the advent of large galaxy simulations, the need for automated and effective classification methods has become increasingly important. This paper investigates the use of principal component analysis (PCA) as an interpretable dimensionality reduction algorithm for galaxy morphology using the IllustrisTNG cosmological simulation dataset with the aim of developing a generative model for galaxies. We first generate a dataset of 2D images and 3D cubes of galaxies from the IllustrisTNG simulation, focusing on the mass, metallicity, and stellar age distribution of each galaxy. PCA is then applied to this data, transforming it into a lower-dimensional image space, where closeness of data points corresponds to morphological similarity. We find that PCA can effectively capture the key morphological features of galaxies, with a significant proportion of the variance in the data being explained by a small number of components. With our method we achieve a dimensionality reduction by a factor of $ for 2D images and $ for 3D cubes at a reconstruction accuracy below five percent. Our results illustrate the potential of PCA in compressing large cosmological simulations into an interpretable generative model for galaxies that can easily be used in various downstreaming tasks such as galaxy classification and analysis.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST’s capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.