Transformation Technique Research Articles

Exploring laboratory-based spectroscopy for estimating NPK content in the hutton soils of Syferkuil Farmlands, South Africa

This study seeks to identify the key wavelengths and spectral transformation techniques that may be used to accurately estimate soil nitrogen, phosphorus, and potassium (NPK) concentration in the Hutton soils. For this purpose, the reflectance spectra of 74 soil samples were measured in the laboratory, and the chemical properties of the soil were analysed. Pearson correlation (r), stepwise multiple linear regression (SMLR), and Partial Least Square Regression were used to model the relationships between the selected variables under study. The study findings revealed that moderate to weak correlations (r = −0.2 − 0.6) exist between wavelengths (400 − 2500 nm) and soil NPK content. Important wavelengths for accurately predicting Soil NPK content were found within visible (400 nm − 729nm), near-infrared (805 nm − 1200nm) and mid-infrared region (1375 nm to 2462 nm). The PLSR model coupled with different spectral transformations was found to be the optimal model for estimating soil NPK (RPD > 2). The introduction of the first and second derivate spectral transformation approach markedly improved all the models investigated in this study. The results retrieved from the study provide a high-accuracy prediction of soil nutrient contents, which is critical for soil fertility management and sustainable food production.

A study on the application of neural style transformation technique in personalized art creation

Abstract In this paper, using the loss function of image stylization, combined with the development of image stylization based on deep learning, the proposed convolutional neural network in the style of image conversion fitting and overfitting response. Based on this, the multi-scale feature fusion method is chosen to train the style conversion network, with the help of deep feature extraction of the image for style conversion, reconstruct the multi-scale feature fusion image, and send it to the decoder for deep coding to realize the style conversion. To evaluate the effectiveness of the proposed multi-scale feature fusion style conversion algorithm, the content loss and style loss parameters of the algorithm are analyzed using the lightweight encoder and VGG encoder, respectively. Calculate the number of algorithmic model parameters and the amount of computation. Analyze the change in the iteration number of the personalized art style conversion process and select the performance evaluation index to evaluate the results of the personalized art style image conversion process. In the process of personalized art style conversion, the multi-scale feature fusion algorithm network proposed in this paper can basically reconstruct the original image after 1000 iterations. Personalized style image reconstruction has a PSNR of 25.26 dB when the number of iterations is 1000. With the deepening of training, the reconstruction effect becomes better and better, and the advantages of personalized art style image conversion applications are significant.

Theoretical Advancement of Xi Jinping’s Socialist Thought with Chinese Characteristics in the New Era under the Construction of Knowledge Map

Abstract This paper discusses the theory and practice of constructing knowledge graph under the guidance of Xi Jinping’s socialist thought with Chinese characteristics in the new era. The study first adopts the Transformer technique based on the BERT model for effectively extracting entity relationships. Then, the article proposes an entity alignment method based on Neural Tensor Network, which enhances the semantic and structural information utilization of entity embedding vectors through optimized NTN and joint knowledge representation learning. In addition, the study employs a knowledge graph link prediction method that combines semantics and paths to fill in missing relations, and applies probabilistic soft logic to solve the inference problem of non-deterministic knowledge. Ultimately, the effectiveness of the constructed knowledge graph is demonstrated through empirical analysis of Xi Jinping’s theoretical dataset of socialist thought with Chinese characteristics in the new era. The results show that the method is more effective in dealing with polysemous words and participle errors than traditional methods, improving the data structuring level. For example, the accuracy of entity alignment is significantly better than the baseline algorithm on different datasets, e.g., on the DBP-WE dataset, its Hits@1, Hits@10 and MRR values are higher than those of the baseline by 4.01-29.49, 1.99-31.05, and 0.036-0.289, respectively. The method of this paper is remarkably effective in improving the performance of the entity alignment task, which is helpful in understanding and applying the Xi Jinping’s thought of socialism with Chinese characteristics in the new era provides new theoretical perspectives and practical methods.

Sediment imaging and factorized Haar wavelet transformation techniques for characterizing particle size distributions of granular soils

The particle size distribution (PSD) significantly influences various mechanical behaviors of granular soils. Advances in automation and camera technology allow for a rapid, green, and accurate PSD determination. This study develops a new sediment imaging system, mainly consisting of a sediment column filled with water and a line-scan camera driven by programmable logic controller, which can automatically capture high-resolution soil segregation images. The soil particles settle through the sediment column and segregate by size, which is scanned to generate sediment images. Naturally, the coarsest particles settle at the bottom of the image, while the finest particles are located at the top. Therefore, the analysis of the sediment image enables the determination of PSD. The higher sediment column, despite of poor operationality, yields better particle segregation quality and thus the more accurate PSD result. This study proposed a factorized Haar wavelet transformation (FHWT) algorithm that can account for less perfect segregation of particles by size, enabling to shorten the height of sediment column. The proposed hardware and FHWT are evaluated by six natural sands with different colors, internal textures, and geological origins. An excellent match between image-based PSDs and sieving-based PSDs are observed. Based on FHWT, four sediment columns with different heights of 2.1 m, 1.5 m, 1.0 m, 0.5 m are tested. The results indicate that columns higher than 1.0 m yield acceptable particle segregation results. Furthermore, the proposed FHWT is also adaptable to process high-resolution images captured by advanced cameras.

Role of Molecular tools in unravelling the cryptic characteristics of termites

Termites, as cryptic organisms, pose significant challenges to traditional methods of species identification and behavior analysis due to their morphological similarities, hidden habitats, and complex social structures. Molecular tools have emerged as transformative techniques for unraveling the cryptic characteristics of termites, aiding in taxonomy, phylogenetics, and population genetics. This research paper explores the pivotal role of molecular approaches, such as DNA barcoding, mitochondrial markers, and genome sequencing, in uncovering termite species diversity and evolutionary relationships. Molecular tools not only enhance the identification of cryptic species but also provide insight into caste differentiation, social behavior, and colony structure. Advanced techniques like transcriptomics and genomics have shed light on termite physiological adaptations, such as cellulose digestion and symbiosis with gut microbes, which are critical for their ecological roles. Additionally, molecular diagnostics offer innovative solutions for termite pest management by identifying genetic markers linked to pesticide resistance and targeting specific species for control measures. This paper reviews key molecular methodologies applied to termites, discusses case studies, and explores future directions in termite research, emphasizing the significance of these tools in understanding termite biology and ecological impact.

A modified round to flat beam transformation lattice for angular dispersion induced microbunching technique

The angular dispersion induced microbunching (ADM) technique has been proposed to generate high brightness coherent radiation in storage rings by taking advantage of it’s very low vertical emittance. To apply a similar scheme in the linac, it is necessary to reduce the vertical emittance of the electron beam. Generally, angular-momentum-dominated round beams can be generated by immersing the cathode into the axial solenoid magnetic field. The angular momentum can be then removed by skew quadrupoles downstream of the solenoid, resulting in a flat beam with low vertical emittance. In this paper, we propose a possible scheme that holds the possibility to improve the performance of round to flat beam transformation technique by chromatic correction. In this scheme, a chicane is used to introduce the transverse dispersion and sextupoles are employed to correct the chromatic effect. Three-dimensional numerical simulations have been carried out and the results show that a flat beam with transverse emittance ratio of ∼840 can be generated for a bunch charge of 0.5 nC.

Performance evaluation of DSTATCOM using retransformation of Clarke transformation technique for supply and load perturbations

Performance evaluation of DSTATCOM using retransformation of Clarke transformation technique for supply and load perturbations

Fusion-Embedding Siamese Network for Light Field Salient Object Detection

Light field salient object detection (SOD) has shown remarkable success and gained considerable attention from the computer vision community. Existing methods usually employ a single-/two-stream network to detect saliency. However, these methods can only handle up to two different modalities at a time, preventing them from being able to fully explore the rich information in multi-modal light field derived data. To address this, we propose the first joint multi-modal learning framework, called FES-Net, for light field SOD, which can take rich inputs not limited to two modalities. Specifically, we propose an attention-aware adaptation module to first transform the multi-modal inputs for use in our joint learning framework. The transformed inputs are then fed to a Siamese network along with multiple embedded feature fusion modules to extract informative multi-modal features. Finally, we predict saliency maps from the high-level extracted features using a saliency decoder module. Our joint multi-modal learning framework effectively resolves the limitations of existing methods, providing efficient and effective multi-modal learning that can fully explore the valuable information in light field data for accurate saliency detection. Furthermore, we improve the performance by introducing the Transformer as our backbone network. To the best of our knowledge, the improved version of our model, called FES-Trans, is the first attempt to address the challenging light field SOD with the powerful Transformer technique. Extensive experiments on benchmark datasets demonstrate that our models are superior light field SOD approaches and outperform cutting-edge models remarkably.

TGFuse: An Infrared and Visible Image Fusion Approach Based on Transformer and Generative Adversarial Network.

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion approaches, impeding balancing the entire image-level perception for complex scenario fusion. In this paper, therefore, we propose an infrared and visible image fusion algorithm based on the transformer module and adversarial learning. Inspired by the global interaction power, we use the transformer technique to learn the effective global fusion relations. In particular, shallow features extracted by CNN are interacted in the proposed transformer fusion module to refine the fusion relationship within the spatial scope and across channels simultaneously. Besides, adversarial learning is designed in the training process to improve the output discrimination via imposing competitive consistency from the inputs, reflecting the specific characteristics in infrared and visible images. The experimental performance demonstrates the effectiveness of the proposed modules, with superior improvement against the state-of-the-art, generalising a novel paradigm via transformer and adversarial learning in the fusion task.

Transformation from e-voting to e-cheque.

Although e-voting scheme and e-cheque scheme are two different applications, they have similarities in the scheme definitions and security properties. This inspires us to establish a relationship between the two schemes by formalising a generic transformation from e-voting to e-cheque scheme. Firstly, we define the scheme definitions and security models for both e-voting scheme and e-cheque scheme. Subsequently, we demonstrate a generic transformation framework from e-voting to e-cheque with asymptotic complexity of [Formula: see text] and design a formal proof to show that a secure e-voting scheme can be transformed into a secure e-cheque scheme. As a proof of concept, we apply our newly proposed transformation technique to the e-voting scheme proposed by Li et al. and obtain a concrete e-cheque scheme.

Some mathematical assumptions for accurate transformation parameters between WGS84 and Nord Sahara geodetic systems

Abstract The transformation of coordinates between different geodetic datums has been a common practice within the geospatial profession. Relating different geodetic datums mostly involves the use of conformal transformation techniques, which could produce results that are not very often satisfactory for certain geodetic, surveying, and mapping purposes. This has been attributed to the inability of the conformal models to resolve the lack (non-exhaustivity) and the heterogeneity of double points existing within the Algerian local geodetic networks. Indeed, the Algerian geodetic network is divided into two main zones completely different in accuracy and points exhaustivity. The North is better and well defined in precision; on the other hand, the South is poorly defined because of the lack of heterogeneity of the points. Mathematical algebraic methods give closed-form solutions to geodetic transformation problems, requiring a high-level computer programming background. In everyday usage, the closed-form solutions are much simpler and have a higher precision than earlier procedures. Thus, it can be predicted that these new solutions will find their place in practice. The present work deals with an important theoretical problem of geodesy: we are looking for a mathematical dependency between two spatial systems using common pairs of points whose coordinates are given in both systems. In geodesy and photogrammetry, the most often used procedure to move from one coordinate system to another is the 3D, seven-parameter similarity transformation (Bursa–Wolf, Molodensky–Badekas, and Helmert).

A NUMERICAL APPROACH FOR THE STUDY OF HEAT GENERATION IN THE PRESENCE OF THERMAL BOUNDARY LAYER FOR A FLAT PLATE

In this study, we investigate the laminar boundary layer flow in two dimensions, steadiness, and incompressibility around a moving vertical flat plate in a uniform free stream of fluid with a convective surface boundary condition. The similarity transformation technique has been applied to convert the governing nonlinear partial differential equation into two nonlinear ordinary differential equations. By combining the finite difference method with the shooting technique, the problem is solved numerically. We present a tabular and graphical representation of the variation in dimensionless temperature and fluid-solid interface characteristics for various values of the Prandtl number. As a special case of the problem, a comparison between the current result and the previously published result demonstrates a good agreement.

Optical Microscopy Images Enhancement Using YCbCr Color Space Based on Nonlinear Mapping

Improving medical images captured by the optical microscope plays an essential role in many medical, radiological, and other applications in the medical field. In this study, the microscope image was improved based on the color conversion (Ycbcr) and the transformation nonlinear mapping, where the lighting component (Y) was processed based on the nonlinear transformation and fuzzy technique, and the color component was improved using (CLAHE) algorithm. The proposed algorithm was compared with several modern algorithms based on non-referenced quality measures. Analyzing the proposed results has obtained the best quality measures with high values of EN (7.0701), AG (14.6901), and MSD (55.8363).

Enhancing adversarial robustness with randomized interlayer processing

Adversarial training, coupled with loss regularization techniques (such as MART and TRADES), is the current most effective method for consistently achieving adversarial robustness on various known datasets. However, without extra training data, the robustness gains of adversarial training are limited. To overcome this limitation, several alternative defenses were proposed as potential extensions to adversarial training, the most notable being the recent denoising diffusion models to generate additional training data. In this work, we propose a different candidate defense that combines both adversarial retraining and input transformation techniques, but instead, applies the transformations between the architecture layers without the need for extra training data. Namely, our interlayer processing technique introduces bit-depth reduction, originally an input pre-processing technique, between the layers of the model to reduce the space for an adversary to exploit. Together with adversarial training and randomization in the forward pass, interlayer processing leads to higher robustness gains. Our experiments show that our defense improves over standard loss regularization techniques by 1.56% and 7.92% for the ResNet-18 model on the CIFAR-10 and SVHN datasets, respectively. Additional experiments on ResNet-34 architecture led to improvements of 1.96% and 10.42% on CIFAR-100 and SVHN, respectively.

Well-Posedness of Backward Stochastic Differential Equations with Jumps and Irregular Coefficients

In this paper, we focus on investigating the well-posedness of backward stochastic differential equations with jumps (BSDEJs) driven by irregular coefficients. We establish new results regarding the existence and uniqueness of solutions for a specific class of singular BSDEJs. Unlike previous studies, our approach considers terminal data that are square-integrable, eliminating the need for them to be necessarily bounded. The generators in our study encompass a standard drift, a signed measure across the entire real line, and the local time of the unknown process. This broadens the scope to include BSDEJs with quadratic growth in the Brownian component and exponential growth concerning the jump noise. The key methodology involves establishing Krylov-type estimates for a subset of solutions to irregular BSDEJs and subsequently proving the Tanaka-Krylov formula. Additionally, we employ a space transformation technique to simplify the initial BSDEJs, leading to a standard form without singular terms. We also provide various examples and special cases, shedding light on BSDEJs with irregular drift coefficients and contributing to new findings in the field.

Explicit scheme based on integral transforms for estimation of source terms in diffusion problems in heterogeneous media

The estimation of source terms present in differential equations has various applications, ranging from structural assessment, industrial process monitoring, equipment failure detection, environmental pollution source detection to identification applications in medicine. Significant progress has been made in recent years in methodologies capable of estimating this parameter. This work employs a methodology based on an explicit formulation of the integral transformation to characterize the unknown source term, reconstructing it through the expansion in known eigenfunctions of the Sturm-Liouville eigenvalue problem. To achieve this, a linear model is considered in a heterogeneous medium with known and spatially varying physical properties and two heat sources, with both temporal and spatial dependencies, and only spatial dependence. The eigenvalue problem contains information about the heterogeneous properties and is solved using the generalized integral transformation technique. Additionally, an initial interpolation of the sensor data is proposed for each observation time, making the inverse problem computationally lighter. The solutions of the inverse problem exhibit optimal performance, even with noisy input data and sources with abrupt discontinuities. The temperatures recovered by the direct problem considering the recovered source closely match synthetic experimental data, showing errors less than 1%, ensuring the robustness and reliability of the technique for the proposed application.

Nonfragile containment control of nonlinear multi‐agent systems via a disturbance observer‐based approach

AbstractIn this article, we consider the nonfragile containment control problem of nonlinear multi‐agent systems (MASs) with exogenous disturbance where the communication links among agents under consideration is directed. Firstly, based on relative output measurements between the agent and its neighbors, a disturbance observer‐based control protocol is proposed to solve the containment control problem of MASs with inherent nonlinear dynamics and exogenous disturbances. Secondly, because of the additional tuning of parameters in the real control systems, uncertainties in the designing of observer and controller gains always occur, and as a result, an output feedback controller with disturbance rejection is conceived and the containment control problem of nonlinear MASs with nonfragility is thoroughly investigated. Then, depending on matrix transformation and inequality technique, sufficient conditions of the designed controller gains exist, which is derived from the asymptotic stability analysis problem of some containment error dynamics of MASs. Finally, two simulation examples are exploited to illustrate the effectiveness of the proposed techniques.

Rolling bearing fault diagnosis method using time-frequency information integration and multi-scale TransFusion network

Advances in deep learning methods have demonstrated remarkable development in diagnosing faults of rotating machinery. The currently popular deep neural networks suffer from design flaws in their network structure, leading to issues of long-term dependencies in fault diagnosis models built upon conventional deep neural networks. Consequently, such models exhibit insufficient global perceptual capabilities towards fault features. Furthermore, how accurately pre-trained models can diagnose faults is hugely impacted by changes in bearings’ working conditions. To tackle the aforementioned issues, this study puts forth a multi-scale TransFusion (MSTF) model for diagnosing faults in rolling bearings under multiple operating conditions. Firstly, a time-frequency symmetric dot pattern transformation technique is designed to transform the original vibration signals into two-dimensional representations. This method can effectively highlight the distinctions between different fault types. Secondly, a multi-scale feature fusion module is established, which fully extracts low-level features from the time-frequency signals and reduces the complexity of the subsequent attention calculations. Meanwhile, relying on the advantages of the Transformer model in capturing global dependencies, the long-range periodic fault information is deeply mined. Finally, multi-head and multi-layer attention are visualized to enhance the interpretability of the model. After analyzing two case studies with both public and experimental datasets, the examination demonstrated that the developed model outperformed other state-of-the-art models. The diagnostic model developed in this study exhibits the ability to accurately diagnose bearing faults across multiple operating conditions while maintaining high robustness to signals contaminated with noise.

SERS probing of fungal HET-s fibrils formed at neutral and acidic pH conditions

Advances in precision medical diagnostics require accurate and sensitive characterization of pathogens. In particular, health conditions associated with protein misfolding require an identification of proteinaceous amyloid fibrils or their precursors. These pathogenic entities express specific molecular structures, which require ultra-sensitive, molecular-level detection methods. A potentially transformative technique termed nanoplasmonics employs electro-optical phenomena in the vicinity of specially engineered metal nanostructures. A signature application of nanoplasmonics exploits enhancement of inelastic scattering of light in specific locations near metallic nanostructures, known as surface-enhanced Raman scattering (SERS). We applied SERS complemented with confocal microscopy imaging for ultra-sensitive, non-invasive, and label-free characterization of the fungal prion HET-s (218–289) as a model for β-sheet rich amyloid structures. This characterization employed Au-coated dielectric supports as plasmonic substrates. After confirming the formation of HET-s fibrils at both pH 7.5 and 2.8 using negative staining transmission electron microscopy, we subjected the fibril-containing solutions to multimodal analysis using confocal microscopy and SERS. The SERS spectral fingerprints from all HET-s samples expressed vibrational markers for β-structure, unstructured backbone, and aromatic side-chains. However, relative intensities of major SERS bands were pronouncedly different for the two pH levels. We have analyzed potential origins of the most pronounced SERS bands and proposed hypothetical mechanistic models that could explain the observed SERS fingerprints from HET-s fibrils grown at pH 7.5 and 2.8.

A novel similarity measure between picture fuzzy sets based on transformation techniques and its applications in mobile multimedia healthcare

A novel similarity measure between picture fuzzy sets based on transformation techniques and its applications in mobile multimedia healthcare