Accurate Ranking Research Articles

Identifying critical nodes in complex networks based on distance Laplacian energy

Identifying critical nodes in complex networks is a fundamental problem, it plays a crucial role in stabilizing the performance of the network structure and propagating information. Majority of the existing studies are built by directly considering the topology of the network. In this paper, a new vertex centrality called distance Laplacian centrality (DLC) is proposed for critical nodes identification from the perspective of graph energy. This method incorporates the vertex’s transfer degree, considers the position of nodes in the network from a global perspective, and measures the importance of a node using the relative variation of the distance Laplacian energy responding to the deletion of the node from the network. To validate the performance and applicability of the proposed method, this paper compares DLC with other methods through susceptible-infected-recovered (SIR) model on different real networks. The experimental results demonstrate that DLC has better performance in terms of influence, distinguishing ability relevance and ranking accuracy, and can effectively recognize critical nodes in complex networks.

Toward Accurate Two-Photon Absorption Spectrum Simulations: Exploring the Landscape beyond the Generalized Gradient Approximation.

In this Letter, we present a pioneering analysis of the density functional approximations (DFAs) beyond the generalized gradient approximation (GGA) for predicting two-photon absorption (2PA) strengths of a set of push-pull π-conjugated molecules. In more detail, we have employed a variety of meta-generalized gradient approximation (meta-GGA) functionals, including SCAN, MN15, and M06-2X, to assess their accuracy in describing the 2PA properties of a chosen set of 48 organic molecules. Analytic quadratic response theory is employed for these functionals, and their performance is compared against the previously studied DFAs and reference data obtained at the coupled-cluster CC2 level combined with the resolution-of-identity approximation (RI-CC2). A detailed analysis of the meta-GGA functional performance is provided, demonstrating that they improve upon their predecessors in capturing the key electronic features of the π-conjugated two-photon absorbers. In particular, the Minnesota functional MN15 shows very promising results as it delivers pleasingly accurate chemical rankings for two-photon transition strengths and excited-state dipole moments.

Social Recommender System Based on CNN Incorporating Tagging and Contextual Features

The Internet's rapid growth has led to information overload, necessitating recommender systems for personalized suggestions. While content-based and collaborative filtering have been successful, data sparsity remains a challenge. To address this, this article presents a novel social recommender system based on convolutional neural networks (SRSCNN). This approach integrates deep learning and contextual information to overcome data sparsity. The SRSCNN model incorporates user and item factors obtained from a neural network architecture, utilizing features from item titles and tags through a CNN. The authors conducted extensive experiments with the MovieLens 10M dataset, demonstrating that the SRSCNN approach outperforms state-of-the-art baselines. This improvement is evident in both rating prediction and ranking accuracy across recommendation lists of varying lengths.

Personalized product ranking system for enhanced user experience

Businesses looking to engage and satisfy their online audience must prioritize the user experience in the quickly changing digital landscape. In order to address this challenge, this project proposes and implements a sophisticated algorithmic solution designed to produce extremely accurate and user-centric product rankings. This represents a groundbreaking approach. The system attempts to predict and present the most relevant product suggestions by meticulously considering a wide range of factors such as user preferences, historical interactions, product popularity trends, and user similarity metrics. Our methodology is distinguished by the use of a dynamic simulation environment in which user profiles, product categories, and interaction pat- terns are manipulated to replicate authentic real-world scenarios. The dynamic framework facilitates the comprehensive testing and optimization of customized ranking algorithms, guaranteeing their flexibility in response to changing user preferences and behaviors. The project’s effectiveness is evaluated using precise evaluation metrics that offer quantitative information about how well the system understands and responds to each unique user’s preference, ultimately resulting in a more fulfilling and rich online shopping or content consumption experience.

Motion Capture Sensor-Based Pose Estimation for Dance Canonical Movements

Abstract Motion capture technology, a developing technique for the quantification of human movement, is progressively revealing its unique significance within the realm of dance. This study introduces a motion capture approach using Kinect sensors to estimate normative dance postures. The sensors capture depth data, allowing for real-time, precise recording of a dancer’s posture. We propose a new method of similarity matching between feature planes to enhance the analysis of human movement postures. Evaluation trials have shown that this method, which focuses on feature plane similarity matching, yields more accurate assessments of movement complexity than traditional 3D model matching techniques. The feature plane matching-based similarity technique achieved the highest pairwise ranking precision, at 80.25%, using the Urban Dance Motion Quality Evaluation dataset. Additionally, it recorded the highest average bilateral ranking accuracy of 78.68% on the BEST dataset. This method has been proven to enhance the stability and efficiency of human posture analysis through its application of feature plane matching.

Subsampling and space-filling metrics to test ensemble size for robustness analysis with a demonstration in the Colorado River Basin

Decision Making Under Deep Uncertainty often uses prohibitively large scenario ensembles to calculate robustness and rank policies’ performance. This paper contributes a framework using subsampling algorithms and space-filling metrics to determine how smaller ensemble sizes impact the accuracy of robustness rankings. Subsampling methods create smaller scenario ensembles of varying sizes. We evaluate ranking sensitivity to the ensemble size and calculate accuracy relative to a baseline ranking. Then, metrics of scenario set quality predict ranking accuracy. Notably, the metrics and subsampling methods do not require additional model simulations. We demonstrate the framework with a case study of shortage policies for Lake Mead in the Colorado River Basin (CRB). Results suggest that fewer scenarios than previous studies can accurately rank Lake Mead policies, and results depend on the type of objective and robustness metric. Smaller ensembles could reduce the computational burden of robustness analyses in the ongoing CRB policy renegotiation.

Extraction of evolutionary factors in smart manufacturing systems with heterogeneous product preferences and trust levels

Smart products, as an increasingly significant part of smart manufacturing systems, have brought users extreme experiences. To provide a significantly better user experience and succeed amidst intense market competition, smart products undergo continuous and iterative evolution guided by diverse user requirements. However, users' requirements are heterogeneous, ever-changing, and misleading owing to the heterogeneous familiarity and deceptive interactions, leading to an erroneous identification of product evolutionary factors and inferior subsequent evolution. In existing works, the heterogeneous preferences and trust levels of users are considered superficially, and the extracted product evolutionary factors fail to adequately fulfill users' requirements. To address this issue, a reliable extraction method for evolutionary factors of smart products with heterogeneous product preferences and trust levels is proposed. First, the fuzzy similarity measure is introduced and a group classification method based on this measure is designed to filter out users without reference value. Second, the trust score induced order weighted averaging (TS-IOWA) operator is employed to obtain the comprehensive trust level of an individual user. Third, the dual trust aggregating operator is improved by two corrective factors being incorporated with the Einstein product and the Einstein sum to overcome the deficiency: an over-reduction of trust level and an over-expansion of distrust level, and then employed to aggregate multiple trust/distrust values and sort the evolutionary factors. Finally, two case studies on the App rating system and the evolution of smart wristbands are provided to verify the effectiveness of this proposed method. Throughout the analysis, the ranking accuracy of users' trust levels has increased by 25%, and the matching ratio between the extraction results and user requirements has increased from 57.14% to 85.7% with an improvement of 50%. The results demonstrate that the proposed method is capable of obtaining more credible evolutionary factors of smart products.

Guided optimization of ToxPi model weights using a Semi-Automated approach

The Toxicological Prioritization Index (ToxPi) is a visual analysis and decision support tool for dimension reduction and visualization of high throughput, multi-dimensional feature data. ToxPi was originally developed for assessing the relative toxicity of multiple chemicals or stressors by synthesizing complex toxicological data to provide a single comprehensive view of the potential health effects. It continues to be used for profiling chemicals and has since been applied to other types of “sample” entities, including geospatial (e.g. county-level Covid-19 risk and sites of historical PFAS exposure) and other profiling applications. For any set of features (data collected on a set of sample entities), ToxPi integrates the data into a set of weighted slices that provide a visual profile and a score metric for comparison. This scoring system is highly dependent on user-provided feature weights, yet users often lack knowledge of how to define these feature weights. Common methods for predicting feature weights are generally unusable due to inappropriate statistical assumptions and lack of global distributional expectation. However, users often have an inherent understanding of expected results for a small subset of samples. For example, in chemical toxicity, prior knowledge can often place subsets of chemicals into categories of low, moderate or high toxicity (reference chemicals). Ordinal regression can be used to predict weights based on these response levels that are applicable to the entire feature set, analogous to using positive and negative controls to contextualize an empirical distribution. We propose a semi-supervised method utilizing ordinal regression to predict a set of feature weights that produces the best fit for the known response (“reference”) data and subsequently fine-tunes the weights via a customized genetic algorithm. We conduct a simulation study to show when this method can improve the results of ordinal regression, allowing for accurate feature weight prediction and sample ranking in scenarios with minimal response data. To ground-truth the guided weight optimization, we test this method on published data to build a ToxPi model for comparison against expert-knowledge-driven weight assignments.

A Systematic Decision-Making Approach for Quality Function Deployment Based on Hesitant Fuzzy Linguistic Term Sets

As a powerful tool for improving customer satisfaction, quality function deployment (QFD) can convert customer requirements (CRs) into engineering characteristics (ECs) during product development and design. Aiming to address the deficiencies of traditional QFD in expert evaluation, CRs’ weight determination and ECs’ importance ranking, this paper proposes an enhanced QFD model that integrates hesitant fuzzy binary semantic variables, the Best–Worst Method (BWM), and the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS). The objective is to determine the prioritization of product engineering characteristics. Indeed, hesitant fuzzy linguistic term sets (HFLTS) have found extensive application in decision-making problems. Compared to other fuzzy language methods, HFLTS offers greater convenience and flexibility in addressing decision-makers’ hesitations and uncertainties. Initially, the combination of hesitant fuzzy linguistic term sets with interval binary tuple language variables is employed to articulate the uncertainty in the assessment information provided by QFD team members. Subsequently, the improved BWM and TOPSIS methods based on HFLTS are used to improve the accuracy of the importance ranking of engineering characteristics by determining the weights of CRs and prioritizing ECs in two stages. Finally, the feasibility and effectiveness of the proposed method are validated through an illustrative example.

A Bayesian multi-model inference methodology for imprecise moment-independent global sensitivity analysis of rock structures

Traditional global sensitivity analysis (GSA) neglects the epistemic uncertainties associated with the probabilistic characteristics (i.e. type of distribution type and its parameters) of input rock properties emanating due to the small size of datasets while mapping the relative importance of properties to the model response. This paper proposes an augmented Bayesian multi-model inference (BMMI) coupled with GSA methodology (BMMI-GSA) to address this issue by estimating the imprecision in the moment-independent sensitivity indices of rock structures arising from the small size of input data. The methodology employs BMMI to quantify the epistemic uncertainties associated with model type and parameters of input properties. The estimated uncertainties are propagated in estimating imprecision in moment-independent Borgonovo's indices by employing a reweighting approach on candidate probabilistic models. The proposed methodology is showcased for a rock slope prone to stress-controlled failure in the Himalayan region of India. The proposed methodology was superior to the conventional GSA (neglects all epistemic uncertainties) and Bayesian coupled GSA (B-GSA) (neglects model uncertainty) due to its capability to incorporate the uncertainties in both model type and parameters of properties. Imprecise Borgonovo's indices estimated via proposed methodology provide the confidence intervals of the sensitivity indices instead of their fixed-point estimates, which makes the user more informed in the data collection efforts. Analyses performed with the varying sample sizes suggested that the uncertainties in sensitivity indices reduce significantly with the increasing sample sizes. The accurate importance ranking of properties was only possible via samples of large sizes. Further, the impact of the prior knowledge in terms of prior ranges and distributions was significant; hence, any related assumption should be made carefully.

PSV-2 Difference in Sire Pta Evaluated By Taiwan Dhi and the Original Countries

Abstract Taiwan is located in a region with a tropical/subtropical oceanic climate characterized by high temperatures and humidity, which significantly affects the milk production, health, and reproduction of dairy cows. Most dairy herds in Taiwan have utilized semen of superior foreign sires from countries in temperate climate, mainly from USA and Canada. However, the performance of daughters in Taiwan of those foreign sires may differ from those in temperate countries. Therefore, the objective of this study was to evaluate the performance of foreign sire semen in Taiwan's dairy herds, and to compare the PTAs of those sires in both Taiwan and their original countries. Data and pedigree from the Dairy Herd Improvement program (DHI) were collected between 2009 and 2021. In total, 108,348 lactation records from 54,269 cows and 76,024 animals in the pedigree were obtained from 120 herds. Traits to evaluate include milk yield (MY), milk fat percentage (MF%), milk fat yield (MFY), milk protein percentage (MP%), and milk protein yield (MPY) standardized to 305d-2X yield. The herd-year-season and lactation were considered as fixed effects in the model with additive genetic effect and permanent environmental effect as random effects. In addition, an extra fixed effect, physical situation of lactation (PSL), was included to account for abnormal physiology or subclinical mastitis in those dairy cows. The ASReml program was used to estimate the variance and covariance components as well as heritability and correlation with multiple-trait animal models. Not only the accuracy of predicted transmitting ability (PTATW) ≥ 75% of those superior foreign sires using DHI data and their PTAs obtained from the original countries (PTAInt) were compared, but also the rank correlation between PTATW and PTAInt was also calculated. The results indicated that only when the accuracy of PTATW increased to 90%, a moderate correlation was observed. Moreover, PTATW and PTAInt of all the sires with an accuracy of PTATW ≥ 75% were tracked to the lactation performance of their daughters in Taiwan using regression analysis. The results showed that selecting sires with an increase of 1 kg in PTATW and in PTAInt would increase the average production of their daughters in Taiwan's dairy herds by 1.620 kg and 0.213 kg in milk yield, 1.328 kg and 1.201 kg in fat yield, and 1.493 kg and 0.550 kg in protein yield, respectively. Therefore, selecting offspring through PTATW of sires is much more efficient, and increasing the number of daughters for each sire and their DHI records would improve the accuracy of PTATW prediction and ranking, making it an important indicator for selecting progeny in Taiwan dairy herds.

Biomarker detection using corrected degree of domesticity in hybrid social network feature selection for improving classifier performance

BackgroundDimension reduction, especially feature selection, is an important step in improving classification performance for high-dimensional data. Particularly in cancer research, when reducing the number of features, i.e., genes, it is important to select the most informative features/potential biomarkers that could affect the diagnostic accuracy. Therefore, researchers continuously try to explore more efficient ways to reduce the large number of features/genes to a small but informative subset before the classification task. Hybrid methods have been extensively investigated for this purpose, and research to find the optimal approach is ongoing. Social network analysis is used as a part of a hybrid method, although there are several issues that have arisen when using social network tools, such as using a single environment for computing, constructing an adjacency matrix or computing network measures. Therefore, in our study, we apply a hybrid feature selection method consisting of several machine learning algorithms in addition to social network analysis with our proposed network metric, called the corrected degree of domesticity, in a single environment, R, to improve the support vector machine classifier’s performance. In addition, we evaluate and compare the performances of several combinations used in the different steps of the method with a simulation experiment.ResultsThe proposed method improves the classifier’s performance compared to using the whole feature set in all the cases we investigate. Additionally, in terms of the area under the receiver operating characteristic (ROC) curve, our approach improves classification performance compared to several approaches in the literature.ConclusionWhen using the corrected degree of domesticity as a network degree centrality measure, it is important to use our correction to compare nodes/features with no connection outside of their community since it provides a more accurate ranking among the features. Due to the nature of the hybrid method, which includes social network analysis, it is necessary to investigate possible combinations to provide an optimal solution for the microarray data used in the research.

Realized genomic selection across generations in a reciprocal recurrent selection breeding program of Eucalyptus hybrids.

Genomic selection (GS) experiments in forest trees have largely reported estimates of predictive abilities from cross-validation among individuals in the same breeding generation. In such conditions, no effects of recombination, selection, drift, and environmental changes are accounted for. Here, we assessed the effectively realized predictive ability (RPA) for volume growth at harvest age by GS across generations in an operational reciprocal recurrent selection (RRS) program of hybrid Eucalyptus. Genomic best linear unbiased prediction with additive (GBLUP_G), additive plus dominance (GBLUP_G+D), and additive single-step (HBLUP) models were trained with different combinations of growth data of hybrids and pure species individuals (N = 17,462) of the G1 generation, 1,944 of which were genotyped with ~16,000 SNPs from SNP arrays. The hybrid G2 progeny trial (HPT267) was the GS target, with 1,400 selection candidates, 197 of which were genotyped still at the seedling stage, and genomically predicted for their breeding and genotypic values at the operational harvest age (6 years). Seedlings were then grown to harvest and measured, and their pedigree-based breeding and genotypic values were compared to their originally predicted genomic counterparts. Genomic RPAs ≥0.80 were obtained as the genetic relatedness between G1 and G2 increased, especially when the direct parents of selection candidates were used in training. GBLUP_G+D reached RPAs ≥0.70 only when hybrid or pure species data of G1 were included in training. HBLUP was only marginally better than GBLUP. Correlations ≥0.80 were obtained between pedigree and genomic individual ranks. Rank coincidence of the top 2.5% selections was the highest for GBLUP_G (45% to 60%) compared to GBLUP_G+D. To advance the pure species RRS populations, GS models were best when trained on pure species than hybrid data, and HBLUP yielded ~20% higher predictive abilities than GBLUP, but was not better than ABLUP for ungenotyped trees. We demonstrate that genomic data effectively enable accurate ranking of eucalypt hybrid seedlings for their yet-to-be observed volume growth at harvest age. Our results support a two-stage GS approach involving family selection by average genomic breeding value, followed by within-top-families individual GS, significantly increasing selection intensity, optimizing genotyping costs, and accelerating RRS breeding.

Elementary effects for models with dimensional inputs of arbitrary type and range: Scaling and trajectory generation.

The Elementary Effects method is a global sensitivity analysis approach for identifying (un)important parameters in a model. However, it has almost exclusively been used where inputs are dimensionless and take values on [0, 1]. Here, we consider models with dimensional inputs, inputs taking values on arbitrary intervals or discrete inputs. In such cases scaling effects by a function of the input range is essential for correct ranking results. We propose two alternative dimensionless sensitivity indices by normalizing the scaled mean or median of absolute effects. Testing these indices with 9 trajectory generation methods on 4 test functions (including the Penman-Monteith equation for evapotranspiration) reveals that: i) scaled elementary effects are necessary to obtain correct parameter importance rankings; ii) small step-size methods typically produce more accurate rankings; iii) it is beneficial to compute and compare both sensitivity indices; and iv) spread and discrepancy of the simulation points are poor proxies for trajectory generation method performance.

Multi-object detection for crowded road scene based on ML-AFP of YOLOv5

Aiming at the problem of multi-object detection such as target occlusion and tiny targets in road scenes, this paper proposes an improved YOLOv5 multi-object detection model based on ML-AFP (multi-level aggregation feature perception) mechanism. Since tiny targets such as non-motor vehicle and pedestrians are not easily detected, this paper adds a micro target detection layer and a double head mechanism to improve the detection ability of tiny targets. Varifocal loss is used to achieve a more accurate ranking in the process of non-maximum suppression to solve the problem of target occlusion, and this paper also proposes a ML-AFP mechanism. The adaptive fusion of spatial feature information at different scales improves the expression ability of network model features, and improves the detection accuracy of the model as a whole. Our experimental results on multiple challenging datasets such as KITTI, BDD100K, and show that the accuracy, recall rate and mAP value of the proposed model are greatly improved, which solves the problem of multi-object detection in crowded road scenes.

Energy efficiency evaluation and optimization of active distribution networks with building integrated photovoltaic systems

With the rapid development of building integrated photovoltaic (BIPV) technology, rooftop PV grid-connected systems face challenges in operation. When the consumption rate of BIPV systems is low, power reverse increases distribution network losses and decreases power supply quality. Traditional energy efficiency evaluations for distribution networks do not consider the impact of low BIPV consumption rates on network losses. This paper establishes an energy efficiency evaluation model for distribution networks with BIPV systems based on adversarial interpretive structural modeling and proposes an energy efficiency indicator system applicable to distribution networks with BIPV systems. The method was applied to eight distribution networks with BIPV systems, achieving accurate energy efficiency level rankings. Through single-factor sensitivity analysis of the indicator system, the primary factors affecting distribution networks with BIPV systems energy efficiency were identified. A reactive power optimization model based on multi-objective particle swarm optimization algorithm was established. After optimization, network losses decreased by 153 kW, PV consumption rate increased by 73 %, and node voltage drift was significantly enhanced. Corresponding loss reduction strategies were proposed for other indicators. This paper provides valuable references for planning and renovating distribution networks with BIPV systems.

A hybrid influence method based on information entropy to identify the key nodes

Identifying the key nodes in complicated networks is an essential topic. A number of methods have been developed in recent years to solve this issue more effectively. Multi-attribute ranking is a widely used and efficient method to increase the accuracy of identifying the key nodes. Using k-shell iteration information and propagation threshold differences, we thoroughly analyze the node’s position attribute and the propagation attribute to offer a hybrid influence method based on information entropy. The two attributes will be weighted using the information entropy weighting method, and then the nodes’ influence ranking will be calculated. Correlation experiments in nine different networks were carried out based on the Susceptible–Infected–Recovered (SIR) model. Among these, we use the imprecision function, Kendall’s correlation coefficient, and the complementary cumulative distribution function to validate the suggested method. The experimental results demonstrate that our suggested method outperforms previous node ranking methods in terms of monotonicity, relevance, and accuracy and performs well to achieve a more accurate ranking of nodes in the network.

Алгоритм оценивания публикационной активности преподавателей вузов, направленный на улучшение научно-педагогической деятельности

Purpose: To create a more effective algorithm for evaluating the publication activity of lecturers in comparison with the existing algorithms for the formation of the Hirsch index and ghp-index. Methods: The algorithm includes a mathematical description of all published works of the lecturer and their citations. The results of the scientific activity of the lecturer are reflected using the matrix form of recording statistical source data, consisting of citations for each published work of the author. The sequence of citations of publications in the matrix is determined by the non-increasing nature of citations in subsequent publications compared to the previous ones. The constructed matrix of the distribution of citations S by published works is rebuilt into a block matrix, which includes the following block matrices: H is the base matrix defining the Hirsch index; G is the matrix of significant publications located above the Hirsch matrix; P is the matrix of less-cited works of the lecturer; O is the zero matrix. The formed matrices have allowed the introduction of the following indices using Euclidean norms: h — Hirsch index, g — index of significant publications and p — index of intensive work. In turn, these indices have allowed to determine the following as Euclidean norms: gh — the index of basic significant publications, hp — the index of intensive work of a lecturer and a comprehensive ghp-index that takes into account all the published works of a lecturer and all their citations. The ghp-index has been improved by introducing weighting coefficients for its constituent indices. Results: The ratings of a team of 20 lecturers has been formed using a sample from the RSCI with the help of the Hirsch index and the A-ghp index. It is shown that the proposed algorithm is more effective in comparison with the Hirsch index and other introduced indexes. Practical significance: The conducted research has allowed to substantiate the possibility of using an improved comprehensive index to distribute the incentives of a team of lecturers in a differentiated and fair manner according to their rating. The algorithm aims to improve the scientific and methodological activities of lecturers by providing fair and accurate ranking of the members of their collectives.

CAGM: A communicability-based adaptive gravity model for influential nodes identification in complex networks

Identifying influential nodes is a very hot and challenging issue in the field of complex system and network. A great deal of algorithms have been developed to address the influential nodes identification problem, but most of previous studies are compromising between result accuracy and time cost. In this work, we propose a communicability-based adaptive gravity model (CAGM) for influential nodes identification. The key idea of CAGM algorithm is that the importance of each node is evaluated by comprehensively considering the influence probability and influence intensity information of neighbor nodes located in its influence radius. More specifically, the communicability network matrix is introduced to depict the influence probability between each pair of nodes. By integrating k-shell, degree and distance information, the influence radius of each node can be determined uniquely so as to portray the inherent heterogeneity of nodes in complex networks. To verify the effectiveness and applicability of CAGM, several groups of simulated experiments on twelve real and artificial datasets are concluded. Experimental results show that CAGM performs better than eight popular algorithms in terms of top-10 nodes, discrimination ability, imprecision function and ranking accuracy.

Linear diophantine multi-fuzzy aggregation operators and its application in digital transformation

Digital transformation is the significant phenomena in contemporary global environment. All the conventional fuzzy sets are extended by the Linear Diophantine Fuzzy Set (LDFS). LDFS is the most viable adaptable method for decision makers to choose their grade values as it includes reference parameters. The foremost vision is to promote the resilient integration of Linear Diophantine Multi-Fuzzy Set (LDMFS) as a model for constructing decisions in order to identify the appropriate standards for digital transformation. Aggregation Operators are crucial in fuzzy systems for fusing information. To aggregate the LDMF, a number of operators have been devised, such as the Linear Diophantine Multi-Fuzzy Weighted Geometric Operator (LDMFWGO), Linear Diophantine Multi-Fuzzy Ordered Weighted Geometric Operator (LDMFOWGO), Linear Diophantine Multi-Fuzzy Weighted Averaging Operator (LDMFWGO) and Linear Diophantine Multi-Fuzzy Ordered Weighted Averaging Operator (LDMFOWAO). By integrating preferred aggregating operations, a novel method for MCDM with LDMF data is studied. The best option from the current alternatives can be determined using these operators. Moreover, a comparison of LDMF operators is made. Additionally, the idea of a scoring function for LDF is designed to examine the rank of viable alternaties. Additionally, a novel approach to solving LDMF sets is suggested. The annals on organisational digital transformation is presented as the final section to test the supremacy of the theory. Accurate rankings for digital transformation are provided by the outcome. To exhibit the robustness of the MCDM methodology, a prompt comparative analysis is established between the suggested concept and the currently used approaches.