Resource Allocation Index Research Articles

Network link prediction via deep learning method: A comparative analysis with traditional methods

In the domain of data-centric networks, Link Prediction (LP) is instrumental in discerning potential or absent connections among entities within complex networks. By employing graph data structures, LP techniques enable a detailed analysis of entity interactions across varied sectors, contributing significantly to overcoming challenges in data filtering and integrity restoration, primarily when the network does not provide embedded data. Although LP methods are widely applicable, especially in recommender systems, their efficacy in current social networks needs to be thoroughly investigated. This study introduces an innovative LP approach using Deep Neural Networks (DNNs). We compare our method against a comprehensive set of established techniques, including traditional score-based methods, classical baselines, and recent deep learning approaches like Graph Neural Networks (GNNs). Our DNN-based solution incorporates a robust feature extraction process and a binary classifier, optimized for accurate prediction of missing links within networks. We performed extensive experimental evaluations on diverse datasets, including co-authorship networks, e-commerce, and social media networks. The study encompasses a comparative analysis with traditional LP techniques, namely Common Neighbors, Resource Allocation Index, Jaccard’s Coefficient, and Adamic/Adar Index, as well as other selected baseline and deep-learning methods. Our findings demonstrate that the DNN-based approach significantly enhances predictive accuracy, outperforming the conventional baseline methods in link prediction.

Ensemble decision of local similarity indices on the biological network for disease related gene prediction.

Link prediction (LP) is a task for the identification of potential, missing and spurious links in complex networks. Protein-protein interaction (PPI) networks are important for understanding the underlying biological mechanisms of diseases. Many complex networks have been constructed using LP methods; however, there are a limited number of studies that focus on disease-related gene predictions and evaluate these genes using various evaluation criteria. The main objective of the study is to investigate the effect of a simple ensemble method in disease related gene predictions. Local similarity indices (LSIs) based disease related gene predictions were integrated by a simple ensemble decision method, simple majority voting (SMV), on the PPI network to detect accurate disease related genes. Human PPI network was utilized to discover potential disease related genes using four LSIs for the gene prediction. LSIs discovered potential links between disease related genes, which were obtained from OMIM database for gastric, colorectal, breast, prostate and lung cancers. LSIs based disease related genes were ranked due to their LSI scores in descending order for retrieving the top 10, 50 and 100 disease related genes. SMV integrated four LSIs based predictions to obtain SMV based the top 10, 50 and 100 disease related genes. The performance of LSIs based and SMV based genes were evaluated separately by employing overlap analyses, which were performed with GeneCard disease-gene relation dataset and Gene Ontology (GO) terms. The GO-terms were used for biological assessment for the inferred gene lists by LSIs and SMV on all cancer types. Adamic-Adar (AA), Resource Allocation Index (RAI), and SMV based gene lists are generally achieved good performance results on all cancers in both overlap analyses. SMV also outperformed on breast cancer data. The increment in the selection of the number of the top ranked disease related genes also enhanced the performance results of SMV.

Analysis of Regional Differences in Teacher Resources in Secondary Vocational Schools in the Context of Beijing-Tianjin-Hebei Synergy

Under the background of beijing-Tianjin-Hebei coordinated development, the allocation of secondary vocational education resources has been deeply affected.Firstly, based on the relevant data of teachers' educational resources in Beijing, Tianjin and Hebei secondary vocational Firstly, based on the relevant data of teachers' educational resources in Beijing, Tianjin and Hebei secondary vocational schools in 2020, this paper defines each index of resource allocation in Beijing, Tianjin and Hebei secondary vocational schools. Secondly, the coefficient of variation method is used to calculate and analyze the related factors that affect the educational resources of secondary vocational schools. Finally, optimization strategies are proposed for the unbalanced resource allocation of teachers in Beijing-Tianjin-Hebei secondary In addition, the Joint Committee also recommends that the Government of the Republic of China (RDC), in cooperation with the Ministry of Education of the Republic of China and the Ministry of Education of the People's Republic of China (MEC), should consider the possibility of establishing a new system of education for teachers. reference for the establishment of modern vocational education system and optimization of resource allocation in first-class vocational education in The aim of this study is to provide a comprehensive overview of the development of vocational education in the Beijing-Tianjin-Hebei region.

Embedding-based link predictions to explore latent comorbidity of chronic diseases.

Comorbidity is a term used to describe when a patient simultaneously has more than one chronic disease. Comorbidity is a significant health issue that affects people worldwide. This study aims to use machine learning and graph theory to predict the comorbidity of chronic diseases. A patient-disease bipartite graph is constructed based on the administrative claim data. The bipartite graph projection approach was used to create the comorbidity network. For the link prediction task, three graph machine learning embedding-based models (node2vec, graph neural networks and hand-crafted approach) with different variants were used on the comorbidity network to compare their performance. This study also considered three commonly used similarity-based link prediction approaches (Jaccard coefficient, Adamic-Adar index and Resource allocation index) for performance comparison. The results showed that the embedding-based hand-crafted features technique achieved outstanding performance compared with the remaining similarity-based and embedding-based models. Especially, the hand-crafted technique with the extreme gradient boosting classifier achieved the highest accuracy (91.67%), followed by the same technique with the Logistic regression classifier (90.26%). For this shallow embedding method, the Jaccard coefficient and the degree centrality of the original chronic disease were the most important features for comorbidity prediction. The proposed framework can be used to predict the comorbidity of chronic disease at an early stage of hospital admission. Thus, the prediction outcome could be valuable for medical practice, giving healthcare providers more control over their services and lowering expenses.

Spatial Heterogeneity Analysis of Resource Allocation Efficiency of Sports Venues in China from the Perspective of Polarization Theory

There are not many analyses of the degree of variation in the efficiency of the allocation of sports venues in China. The results show that the allocation efficiency of sports venues in China is very high. The results show that the efficiency of the allocation of sports venues in China generally shows a fluctuating upward trend, with the average efficiency value increasing from 0.7 in 2013 to 0.9 in 2014, and there are significant differences at the three regional levels of East, Central, and West China and at the level of each province and autonomous region. The efficiency of the allocation of sports venue resources in the three regions shows a geographical pattern of “eastern region > western region > central region.” The regional disparity in the efficiency of the allocation of sports venue resources in China gradually increases during the period under study, with the opening and closing values of the kernel density curve for 2013–2017, showing an overall “. The nuclear density curve in 2017 shows an obvious bimodal curve distribution. Compared with other years, it can be clearly seen that there are fewer areas with low values and more areas with high values. The polarization of the efficiency of China's sports venue resource allocation and layout has been revealed, and the core density curve is shown as a whole. It can be seen from the sports venue resource allocation index that during the study year, the changes and fluctuations of each major region were different, and the national Er index showed a trend of “Λ.” The shape of the national Er index is “Λ,” while the eastern, central, and western regions are in the shape of “N,” declining slowly and remaining stable, respectively. The ER index fluctuates the most in the eastern region. Hence, the change in the ER index in eastern China plays a dominant role in the polarization of the overall resource allocation efficiency of sports venues in China.

Auditor characteristics and the financial reporting quality: the moderating role of the client business strategy

PurposeThis study examines whether and how a client's business strategy can affect the relationship between auditor characteristics and financial reporting quality.Design/methodology/approachIn this study, auditor industry specialization and tenure were used as proxies for auditor characteristics. The client business strategy was measured using the resource allocation index method. Finally, discretionary accruals are used to assess financial reporting quality. This study includes 1,450 firm-year observations and 145 companies listed on the Tehran Stock Exchange (TSE) over a ten-year period from 2011 to 2020. The research hypotheses were analyzed using a multivariate regression model and panel data.FindingsThe results show that auditor industry specialization increases financial reporting quality. This relationship improves when the client's business strategy deviates from the industry–normal strategy. The research findings state that auditor tenure has a positive association with financial reporting quality, and this relationship is strengthened when the company's business strategy deviates from the normal industry strategy.Practical implicationsThe findings of this study provide important evidence for investors, firm management, and auditing firms. Investors must consider the auditor characteristics when selecting companies listed on the TSE. Managers of Iranian companies are advised to consider the auditor's characteristics when choosing an audit firm to increase financial reporting quality. Audit firms should evaluate their business strategies in audit planning to increase the quality of financial reporting.Originality/valueTo the best of the authors’ knowledge, this is the first empirical study to examine the relationship between auditor characteristics and the financial reporting quality in the emerging capital market by considering the clients' business strategy.

Research on the Most Efficient Use of Wind Energy Resources in the Context of Carbon Neutrality: Overview Based on Evolutionary Algorithm

An evolutionary algorithm-based optimal allocation method of wind resources under the background of carbon neutralization is proposed in order to better achieve the goal of energy conservation and emission reduction under the background of carbon neutralization, aiming at the current unreasonable allocation of wind resources. The evaluation model of balanced wind resource allocation is designed, and the evaluation index of optimal wind resource allocation is constructed using the evolutionary algorithm. The optimal allocation path of wind energy resources is chosen to achieve the goal of reasonable wind energy resource allocation. Finally, simulation experiments show that using an evolutionary algorithm to solve the problem of poor energy allocation and achieve the research goal, the optimal allocation method of wind energy resources under the background of carbon neutralization can effectively solve the problem of poor energy allocation.

SCL-WTNS: A new link prediction algorithm based on strength of community link and weighted two-level neighborhood similarity

Link prediction is a significant and fundamental research issue in the field of network science. Numerous similarity-based algorithms have been widely applied due to low computational cost and high prediction accuracy. The topological features of networks like community structure are beneficial to link prediction. In this paper, we first introduce a Weighted Two-level Neighborhood Similarity (WTNS) index that integrates the resource allocation index and local path index. Then we define the Strength of Community Link (SCL) as a quantitative index to evaluate the close relationship among communities. Based on this, the connection likelihood between two nodes can be calculated and a new link prediction algorithm called SCL-WTNS is presented. The proposed algorithm has been compared with nine popular similarity methods on 12 real-world networks to verify the performance. SCL-WTNS is also compared with two groups of community-based link prediction methods. Experiments indicate that the proposed algorithm is better than comparison algorithms both in prediction accuracy and stability.

Bi-layer network analytics: A methodology for characterizing emerging general-purpose technologies

• A methodology of bi-layer network analytics for characterizing emerging general purpose technologies. • Three technological characteristics describing a technology's generality and emergence. • Topological indicators quantifying technological characteristics through topological features. • An approach of link prediction with a weighted index of resource allocation. • Emerging general purpose technologies in information science. Despite the tremendous contributions bibliometrics has made to profiling technological landscapes and identifying emerging topics, reliable methods for predicting potential technological changes are still elusive. To fill this gap, we propose a methodology based on bi-layer network analytics that characterizes emerging general-purpose technologies. The framework incorporates three novel indicators that quantify a technology's technical potential and social impacts, not just in one specific technological area but in a wide range of domains. Missing links in the network are extrapolated through a refined link prediction method, and a weighted resource allocation index ranks both current technologies and their predicted evolutions to reveal candidate innovations for further empirical and/or expert analysis. A case study on information science incorporating quanlitative and qualitative validations demonstrates the methodology to be feasible and reliable. Researchers and policymakers in information science and bibliometrics should find valuable decision support from the empirical insights presented.

Attentional templates are protected from retroactive interference during visual search: Converging evidence from event-related potentials

Attentional templates are stored representations of target features that guide visual search. Target features may remain fixed or change on every trial, requiring sustained or transient templates, respectively. In separate blocks of trials, two sustained templates guide visual search as efficiently as two transient templates. In mixed blocks, however, the transient template interferes with the sustained template, impairing its efficiency in guiding visual search. Here, we hypothesized that the priority of the sustained template would increase when threatened by interference, eventually restoring efficient guidance of visual search. Participants memorized two possible target colors before the onset of the search display. At encoding, we assessed attentional selection of the two possible target colors with the N2pc. During subsequent maintenance, we measured the CDA as an index of resource allocation in working memory. In Experiment 1, the CDA was smaller with sustained than transient templates in separate blocks, but similar in mixed blocks. Thus, the sustained template received more working memory resources when maintained concurrently with an interfering transient template, suggesting that it was prioritized. In Experiment 2, the priority of the sustained template was further increased as it guided visual search in 80% of cases. The N2pc to possible target colors matching the sustained template was enhanced both at encoding and during visual search, thus eliminating interference from the transient template. Therefore, sustained templates are not necessarily less efficient than transient templates. Rather, prioritization through attentional selection at encoding and resource allocation during maintenance may restore efficient guidance of visual search.

P300 amplitude during a monetary incentive delay task predicts future therapy completion in individuals with major depressive disorder

IntroductionTreatment effectiveness for major depressive disorder (MDD) is often affected by client non-adherence, dropout, and non-response. Identification of client characteristics predicting successful treatment completion and/or response (i.e., symptom reduction) may be an important tool to increase intervention effectiveness. It is unclear whether neural attenuations in reward processing associated with MDD predict behavioral treatment outcome. MethodsThis study aimed to determine whether blunted neural responses to reward at baseline differentiate MDD (n = 60; 41 with comorbid anxiety) and healthy control (HC; n = 40) groups; and predict MDD completion of and response to 7–10 sessions of behavior therapy. Participants completed a monetary incentive delay (MID) task. The N200, P300, contingent negative variation (CNV) event related potentials (ERPs) and behavioral responses (reaction time [RT], correct hits) were quantified and extracted for cross-sectional group analyses. ERPs and behavioral responses demonstrating group differences were then used to predict therapy completion and response within MDD. ResultsMDD exhibited faster RT and smaller P300 amplitudes than HC across conditions. Within the MDD group, treatment completers (n = 37) exhibited larger P300 amplitudes than non-completers (n = 21). Limitations: This study comprises secondary analyses of EEG data; thus task parameters are not optimized to examine feedback ERPs from the paradigm. We did not examine heterogenous presentations of MDD; however, severity and comorbidity did not influence findings. ConclusionsPrevious studies suggest that P300 is an index of motivational salience and stimulus resource allocation. In sum, individuals who deploy greater neural resources to task demands are more likely to persevere in behavioral therapy.

Evaluating the resource allocation index as a potential fMRI-based biomarker for substance use disorder

BackgroundThere is a lack of neuroscience-based biomarkers for the diagnosis, treatment and monitoring of individuals with substance use disorders (SUD). The resource allocation index (RAI), a measure of the interrelationship between salience, executive control and default-mode brain networks (SN, ECN, and DMN), has been proposed as one such biomarker. However, the RAI has yet to be extensively tested in SUD samples. MethodsThe present analysis compared RAI scores between individuals with stimulant and/or opioid use disorders (SUD; n = 139, abstinent 4–365 days) and healthy controls (HC; n = 56) who had completed resting-state functional magnetic resonance imaging (fMRI) scans within the context of the Tulsa 1000 cohort. First, we used independent component analysis (ICA) to identify the SN, ECN, and DMN and extract their time series data. Second, we used multiple permutations of automatically identified networks to compute RAI as reported in the fMRI literature. ResultsFirst, the RAI as a metric depended substantially on the approach that was used to define the network components. Second, regardless of the selection of networks, after controlling for multiple testing there was no difference in RAI scores between SUD and HC. Third, the RAI was not associated with any substance use-related self-report measures. ConclusionTaken together, these findings do not provide evidence that RAI can be used as an fMRI-derived biomarker for the severity or diagnosis of individuals with SUD.

Target Defense Against Link-Prediction-Based Attacks via Evolutionary Perturbations

In social networks, by removing some target-sensitive links, privacy protection might be achieved. However, some hidden links can still be re-observed by link prediction methods on observable networks. In this paper, the conventional link prediction method named Resource Allocation Index (RA) is adopted for privacy attacks. Several defense methods are proposed, including heuristic and evolutionary approaches, to protect targeted links from RA attacks via evolutionary perturbations. This is the first time to study privacy protection on targeted links against link-prediction-based attacks. Some links are randomly selected from the network as targeted links for experimentation. The simulation results on six real-world networks demonstrate the superiority of the evolutionary perturbation approach for target defense against RA attacks. Moreover, transferring experiments show that, although the evolutionary perturbation approach is designed to against RA attacks, it is also effective against other link-prediction-based attacks.

Link Weight Prediction Using Supervised Learning Methods and Its Application to Yelp Layered Network

Real-world networks feature weights of interactions, where link weights often represent some physical attributes. In many situations, to recover the missing data or predict the network evolution, we need to predict link weights in a network. In this paper, we first proposed a series of new centrality indices for links in line graph. Then, utilizing these line graph indices, as well as a number of original graph indices, we designed three supervised learning methods to realize link weight prediction both in the networks of single layer and multiple layers, which perform much better than several recently proposed baseline methods. We found that the resource allocation index (RA) plays a more important role in the weight prediction than other topological properties, and the line graph indices are at least as important as the original graph indices in link weight prediction. In particular, the success application of our methods on Yelp layered network suggests that we can indeed predict the offline co-foraging behaviors of users just based on their online social interactions, which may open a new direction for link weight prediction algorithms, and meanwhile provide insights to design better restaurant recommendation systems.

Incorporating facial attractiveness in photos for online dating recommendation

Data sparsity has been a great challenge of data-driven applications. It is essential to explore the availability of other side information that can be utilized for alleviating this problem. This study proposes incorporating facial attractiveness embedded in user photos to boost recommendations in the context of online dating site, aiming at demonstrating the possibility of utilizing image features for increasing data richness. Specifically, subjective and objective grading methods are proposed to extract the facial attractiveness from user photos. A user network is then constructed, and a link prediction method is proposed to incorporate the extracted facial attractiveness in the recommendation process. Evaluation conducted on a real-world dataset shows that the proposed CNAF method is effective in increasing the prediction accuracy for the cold-start users. In particular, the prediction errors of the proposed CNAF method are on average 8.68%, 8.79%, and 8.71% lower than the systems using the Adamic–Adar index, resource allocation index, and preference attachment index respectively. The proposed CNAF method also maintains a high recommendation diversity.

Altered coupling of default-mode, executive-control and salience networks in Internet gaming disorder

BackgroundRecently, a triple-network model suggested the abnormal interactions between the executive-control network (ECN), default-mode network (DMN) and salience network (SN) are important characteristics of addiction, in which the SN plays a critical role in allocating attentional resources toward the ECN and DMN. Although increasing studies have reported dysfunctions in these brain networks in Internet gaming disorder (IGD), interactions between these networks, particularly in the context of the triple-network model, have not been investigated in IGD. Thus, we aimed to assess alterations in the inter-network interactions of these large-scale networks in IGD, and to associate the alterations with IGD-related behaviors. MethodsDMN, ECN and SN were identified using group-level independent component analysis (gICA) in 39 individuals with IGD and 34 age and gender matched healthy controls (HCs). Then alterations in the SN-ECN and SN-DMN connectivity, as well as in the modulation of ECN versus DMN by SN, using a resource allocation index (RAI) developed and validated previously in nicotine addiction, were assessed. Further, associations between these altered network coupling and clinical assessments were also examined. ResultsCompared with HCs, IGD had significantly increased SN-DMN connectivity and decreased RAI in right hemisphere (rRAI), and the rRAI in IGD was negatively associated with their scores of craving. ConclusionsThese findings suggest that the deficient modulation of ECN versus DMN by SN might provide a mechanistic framework to better understand the neural basis of IGD and might provide novel evidence for the triple-network model in IGD.

Efficient incremental dynamic link prediction algorithms in social network

To enhance customers’ loyalty and experience, link prediction in social networks can help service providers to predict the friendship between users in the future, according to the network structure and personal information. However, most of prior studies consider link prediction in the static scenario while ignoring that the social network generally is updated over time. In this paper, to address this problem, we design two efficient incremental dynamic algorithms that can predict the relationship between users according to the updated social network structure. The first one, instead of using classic prediction index, creates a latent space for each node in the network, and adopts the incremental calculation to predict the future links according to the position of each node in the latent space. The second one is a dynamic improved algorithm based on the resource allocation index, which only recalculates updated part of the social network structure instead of the whole social network. Extensive experiments show that our first algorithm has high prediction accuracy while the second algorithm incurs low running time cost at the expense of less prediction accuracy.

Extended resource allocation index for link prediction of complex network

Recently, a number of similarity-based methods have been proposed to predict the missing links in complex network. Among these indices, the resource allocation index performs very well with lower time complexity. However, it ignores potential resources transferred by local paths between two endpoints. Motivated by the resource exchange taking places between endpoints, an extended resource allocation index is proposed. Empirical study on twelve real networks and three synthetic dynamic networks has shown that the index we proposed can achieve a good performance, compared with eight mainstream baselines.

Comparison of Local Information Indices Applied in Resting State Functional Brain Network Connectivity Prediction.

Anatomical distance has been widely used to predict functional connectivity because of the potential relationship between structural connectivity and functional connectivity. The basic implicit assumption of this method is “distance penalization.” But studies have shown that one-parameter model (anatomical distance) cannot account for the small-worldness, modularity, and degree distribution of normal human brain functional networks. Two local information indices–common neighbor (CN) and preferential attachment index (PA), are introduced into the prediction model as another parameter to emulate many key topological of brain functional networks in the previous study. In addition to these two indices, many other local information indices can be chosen for investigation. Different indices evaluate local similarity from different perspectives. Currently, we still have no idea about how to select local information indices to achieve higher predicted accuracy of functional connectivity. Here, seven local information indices are chosen, including CN, hub depressed index (HDI), hub promoted index (HPI), Leicht-Holme-Newman index (LHN-I), Sørensen index (SI), PA, and resource allocation index (RA). Statistical analyses were performed on eight network topological properties to evaluate the predictions. Analysis shows that different prediction models have different performances in terms of simulating topological properties and most of the predicted network properties are close to the real data. There are four topological properties whose average relative error is less than 5%, including characteristic path length, clustering coefficient, global efficiency, and local efficiency. CN model shows the most accurate predictions. Statistical analysis reveals that five properties within the CN-predicted network do not differ significantly from the real data (P > 0.05, false-discovery rate method corrected for seven comparisons). PA model shows the worst prediction performance which was first applied in models of growth networks. Our results suggest that PA is not suitable for predicting connectivity in a small-world network. Furthermore, in order to evaluate the predictions rapidly, prediction power was proposed as an evaluation metric. The current study compares the predictions of functional connectivity with seven local information indices and provides a reference of method selection for construction of prediction models.

Playing the role of weak clique property in link prediction: A friend recommendation model.

An important fact in studying link prediction is that the structural properties of networks have significant impacts on the performance of algorithms. Therefore, how to improve the performance of link prediction with the aid of structural properties of networks is an essential problem. By analyzing many real networks, we find a typical structural property: nodes are preferentially linked to the nodes with the weak clique structure (abbreviated as PWCS to simplify descriptions). Based on this PWCS phenomenon, we propose a local friend recommendation (FR) index to facilitate link prediction. Our experiments show that the performance of FR index is better than some famous local similarity indices, such as Common Neighbor (CN) index, Adamic-Adar (AA) index and Resource Allocation (RA) index. We then explain why PWCS can give rise to the better performance of FR index in link prediction. Finally, a mixed friend recommendation index (labelled MFR) is proposed by utilizing the PWCS phenomenon, which further improves the accuracy of link prediction.