Citation impact prediction for scientific papers using stepwise regression analysis

Mapping the relationship between traffic accidents, road network configuration, and urban land use

Understanding the nature of traffic accidents in relation to urban access networks is crucial for building safer and more resilient cities. This paper examines the issue of traffic accidents through the lenses of urban configurational theory and urban land use. Three data layers were used in the study, including space syntax analysis conducted in Depthmap X, geotagged traffic accidents collected by the police department, and geotagged land-use data. The method involved superimposing these data layers and exploring potential correlations using a geographic information system (GIS). The findings indicate significant correlations between the spatial frequency of traffic accidents and the choice measure (at 2500 m), local integration, and active land use. The findings of this study can help inform planners and policymakers about the best location to implement safety measures to reduce the risk of traffic accidents in urban access networks.

Impact of physical and mental fatigue on construction workers' unsafe behavior based on physiological measurement

INTRODUCTION

Construction worker fatigue is an important factor leading to unsafe behavior, a major cause of construction accidents. Uncovering the impact mechanism of fatigue on workers' unsafe behavior can prevent construction accidents. However, it is difficult to effectively measure workers' fatigue onsite and analyze the impact of worker fatigue on their unsafe behavior.

METHOD

This research analyzes the relationship between the physical and mental fatigue of construction workers and their unsafe behavior via physiological measurement based on a simulated experiment on handling tasks.

RESULTS

It is found that: (a) both physical fatigue and mental fatigue have negative effects on workers' cognitive ability and motion ability, and the negative effects are more serious under the combination of the two types of fatigue; (b) mental fatigue can easily change workers' risk propensity, making them more willing to face risks, and in a state of the two types of fatigue, they are more likely to make choices with less pay and higher risk; (c) the number of signal identification errors is positively correlated with LF (low frequency)/HF (high frequency), and negatively correlated with the standard deviation of normal-to-normal intervals (SDNN), while the number of footstep control errors is negatively correlated with the time elapsed between two successive R waves (RR interval) and skin temperature (SKT).

PRACTICAL APPLICATIONS

These findings can enrich construction safety management theory from a perspective of quantified fatigue and facilitate safety management practices on construction sites, thus contributing to the body of knowledge and practices of construction safety management.

A modified LSTM network to predict the citation counts of papers

Quantifiable predictability in the citation counts of articles is significant in scientometrics and informetrics. Many metrics based on the citation counts can evaluate the scientific impact of research articles and journals. Utilising time series models, an article’s citation counts up to the yth year after publication can be predicted by those up to the previous years. However, the typically used models cannot predict the fat tail of the actual citation distributions. Thus, based on cumulative advantage of the citation behaviour, we propose a method to predict the accumulated citation counts, by using a random number sampled from a power-law distribution to modify the results given by a recurrent neural network (RNN), long short-term memory. Extensive experiments on the data set including 17 journals in information science verified the effectiveness of our method by the good fittings on distributions and evolutionary trends of the citation counts of articles. Our method has the potential to be extended to predict other popular assessment measures such as impact factor and h-index for journals.

A Machine Learning Model to Predict Citation Counts of Scientific Papers in Otology Field

One of the most widely used measures of scientific impact is the number of citations. However, due to its heavy-tailed distribution, citations are fundamentally difficult to predict but can be improved. This study was aimed at investigating the factors and parts influencing the citation number of a scientific paper in the otology field. Therefore, this work proposes a new solution that utilizes machine learning and natural language processing to process English text and provides a paper citation as the predicted results. Different algorithms are implemented in this solution, such as linear regression, boosted decision tree, decision forest, and neural networks. The application of neural network regression revealed that papers' abstracts have more influence on the citation numbers of otological articles. This new solution has been developed in visual programming using Microsoft Azure machine learning at the back end and Programming Without Coding Technology at the front end. We recommend using machine learning models to improve the abstracts of research articles to get more citations.

Childhood Environmental Instability and Social-Emotional Outcomes in Emerging Adults

Adverse childhood experiences (ACEs) can negatively affect social-emotional functioning. The association between individual and cumulative ACEs and social-emotional domains of self-esteem, loneliness, and negotiation in intimate partner relationships has not been explored in low-risk emerging adults, a gap this study aims to fill. An online survey was administered to undergraduate emerging adults, ages 18 to 25 years (M_age = 19.73, SD = 1.83; N = 436; 20.60% Hispanic; 63.80% female). The ACEs Survey, Child Abuse Potential Inventory, and Conflict Tactics Scale-2nd Edition were used. Three multivariate ordinary least squares regressions were run, each including predictors significant in bivariate analyses and outcomes of self-esteem, loneliness, and negotiation for each regression. Emotional abuse, B = -.20, p < .01; emotional neglect, B = -.21, p < .001; and substance using family member, B = -.12, p < .05, were negatively associated with self-esteem; emotional neglect, B = .11, p < .01, and cumulative ACEs, B = .16, p < .01, were positively associated with loneliness; and incarcerated family member was positively associated with negotiation, B = .12, p < .05. Overall, these findings suggest that individual ACEs associated with environmental instability (e.g., emotional abuse) are strong predictors of social-emotional outcomes, relative to ACEs associated with more direct physical harm (e.g., sexual abuse).

Leadership and supply chain management: a systematic literature review

Purpose

This study aims to analyze the state of knowledge on the relationship between leadership and the firm’s supply chain. The study identifies and examines the existing literature, unveils research gaps and suggests future research directions.

Design/methodology/approach

Adopting a systematic review process, a total of 110 articles published in top-ranked academic journals (A* and A category as per ABDC-2019 list) were analyzed. Descriptive, cluster, thematic and regression analyses of citations were performed to garner insights.

Findings

The review outcome shows an upward trend of articles studying the influence of leadership in the supply chain. With the highest number of articles, developed countries and manufacturing companies have been the research contexts of the research studies. Clustering reveals eight significant areas where the leader’s involvement in the supply chain is discussed, with several sub-themes emerging within each cluster. Finally, the regression analysis of citations shows that only the journal’s quality matters the most in receiving the highest citation for the articles.

Research limitations/implications

As this study considered only A* and A-ranked journals of the ABDC-2019 list, there is a risk of excluding some relevant articles.

Originality/value

While the current literature deliberates on recent trends in the supply chain, such as the application of Industry 4.0 practices, this review revolves around the classical theme of leadership and demonstrates its importance in the supply chain. The study is among the first to conduct a bibliometric analysis of articles deliberating on leadership and supply chain issues by grouping the articles into clusters and themes. In the end, the clusters and themes were conceptualized into the “House of Supply Chain Leadership,” of which leadership forms the foundation.

Selecting informative bands for partial least squares regressions improves their goodness-of-fits to estimate leaf photosynthetic parameters from hyperspectral data

The plant photosynthetic capacity determines the photosynthetic rates of the terrestrial biosphere. Timely approaches to obtain the spatiotemporal variations of the photosynthetic parameters are urgently needed to grasp the gas exchange rhythms of the terrestrial biosphere. While partial least squares regression (PLSR) is a promising way to predict the photosynthetic parameters maximum carboxylation rate (V_cmax) and maximum electron transport rate (J_max) rapidly and non-destructively from hyperspectral data, the approach, however, faces a high risk of overfitting and remains a high hurdle for applications. In this study, we propose to incorporate proper band selection techniques for PLSR analysis to refine the goodness-of-fit (GoF) in estimating V_cmax and J_max. Different band selection procedures coupled with different hyperspectral forms (reflectance, apparent absorption, as well as derivatives) were examined. Our results demonstrate that the GoFs of PLSR models could be greatly improved by combining proper band selection methods (especially the iterative stepwise elimination approach) rather than using full bands as commonly done with PLSR. The results also show that the 1st order derivative spectra had a balance between accuracy (R² = 0.80 for V_cmax, and 0.94 for J_max) and denoising (when a Gaussian noise was added to each leaf reflectance spectrum at each wavelength with a standard deviation of 1%) on retrieving photosynthetic parameters from hyperspectral data. Our results clearly illustrate the advantage of using the band selection approach for PLSR dimensionality reduction and model optimization, highlighting the superiority of using derivative spectra for V_cmax and J_max estimations, which should provide valuable insights for retrieving photosynthetic parameters from hyperspectral remotely sensed data.

An ARIMA-based study of bibliometric index prediction

Purpose

The purpose of this paper is to predict bibliometric indicators based on ARIMA models and to study the short-term trends of bibliometric indicators.

Design/methodology/approach

This paper establishes a non-stationary time series ARIMA (p, d, q) model for forecasting based on the bibliometric index data of 13 journals in the library intelligence category selected from the Chinese Social Sciences Citation Index (CSSCI) as the data source database for the period 1998–2018, and uses ACF and PACF methods for parameter estimation to predict the development trend of the bibliometric index in the next 5 years. The predicted model was also subjected to error analysis.

Findings

ARIMA models are feasible for predicting bibliometric indicators. The model predicted the trend of the four bibliometric indicators in the next 5 years, in which the number of publications showed a decreasing trend and the H-value, average citations and citations showed an increasing trend. Error analysis of the model data showed that the average absolute percentage error of the four bibliometric indicators was within 5%, indicating that the model predicted well.

Research limitations/implications

This study has some limitations. 13 Chinese journals were selected in the field of Library and Information Science as the research objects. However, the scope of research based on bibliometric indicators of Chinese journals is relatively small and cannot represent the evolution trend of the entire discipline. Therefore, in the future, the authors will select different fields and different sources for further research.

Originality/value

This study predicts the trend changes of bibliometric indicators in the next 5 years to understand the trend of bibliometric indicators, which is beneficial for further in-depth research. At the same time, it provides a new and effective method for predicting bibliometric indicators.

Effect of simulated tidal cycle on DOM, nitrogen and phosphorus release from sediment in Dagu River-Jiaozhou Bay estuary

Tide drives salt mixing processes, erosion, deposition, and nutrient circulation in sediments, which is critical to the estuarine systems. This study aims to investigate the effects of tidal cycle intensity on sediment dissolved organic matter (DOM), nitrogen and phosphorus release. In this study, the effects of tide are investigated by simulating different intensity of tidal disturbance with tidal simulator devices. The microbial community changes under different tidal cycle are disclosed to explain the mechanism of nutrient release. In addition, the short-term release of nitrogen and phosphorus under simulated tidal cycle is predicted by stepwise regression method. Results show that the higher the tidal cycle intensity, the stronger the DOM mineralization in sediments and diffusion into overlying water, leading to a sustained increase of fluorescence intensity in DOM. Besides, the tidal disturbance promotes the NH₄⁺-N and NO₃^--N release and the tidal disturbance is helpful for ammonification. While the greater the tidal intensity, the lower the NO₃^--N release. Content of released total phosphorus (TP) maintains at a low level and fluctuates over time under different simulated tidal intensity. In addition, tidal cycle greatly changes the microbial richness and diversity. Gammaproteobactere has the ability of denitrification and can reduce nitrate to nitrite. Besides, tidal environment greatly affects the abundance of Marinobacter which can enhance the N, P, and C migration transformation ability. The research on microbial community further explains the mechanism of nutrient release. The model of nitrogen and phosphorus release contributes to providing basic data for predicting the short-term release of nutrients under different simulated tidal intensity.

Impact of the reference list features on the number of citations

Many believe that the quality of a scientific publication is as good as the science it cites. However, quantifications of how features of reference lists affect citations remain sparse. We examined seven numerical characteristics of reference lists of 50,878 research articles published in 17 ecological journals between 1997 and 2017. Over this period, significant changes occurred in reference lists’ features. On average, more recent papers have longer reference lists and cite more high Impact Factor papers and fewer non-journal publications. We also show that highly cited articles across the ecological literature have longer reference lists, cite more recent and impactful references, and include more self-citations. Conversely, the proportion of ‘classic’ papers and non-journal publications cited, as well as the temporal span of the reference list, have no significant influence on articles’ citations. From this analysis, we distill a recipe for crafting impactful reference lists, at least in ecology.

Evaluation of Informative Bands Used in Different PLS Regressions for Estimating Leaf Biochemical Contents from Hyperspectral Reflectance

Partial least squares (PLS) regression models are widely applied in spectroscopy to estimate biochemical components through hyperspectral reflected information. To build PLS regression models based on informative spectral bands, rather than strongly collinear bands contained in the full spectrum, is essential for upholding the performance of models. Yet no consensus has ever been reached on how to select informative bands, even though many techniques have been proposed for estimating plant properties using the vast array of hyperspectral reflectance. In this study, we designed a series of virtual experiments by introducing a dummy variable (Cd) with convertible specific absorption coefficients (SAC) into the well-accepted leaf reflectance PROSPECT-4 model for evaluating popularly adopted informative bands selection techniques, including stepwise-PLS, genetic algorithms PLS (GA-PLS) and PLS with uninformative variable elimination (UVE-PLS). Such virtual experiments have clearly defined responsible wavelength regions related to the dummy input variable, providing objective criteria for model evaluation. Results indicated that although all three techniques examined may estimate leaf biochemical contents efficiently, in most cases the selected bands, unfortunately, did not exactly match known absorption features, casting doubts on their general applicability. The GA-PLS approach was comparatively more efficient at accurately locating the informative bands (with physical and biochemical mechanisms) for estimating leaf biochemical properties and is, therefore, recommended for further applications. Through this study, we have provided objective evaluations of the potential of PLS regressions, which should help to understand the pros and cons of PLS regression models for estimating vegetation biochemical parameters.

Quantitative association analysis between PM2.5 concentration and factors on industry, energy, agriculture, and transportation

Rapid urbanization is causing serious PM_2.5 (particulate matter ≤2.5 μm) pollution in China. However, the impacts of human activities (including industrial production, energy production, agriculture, and transportation) on PM_2.5 concentrations have not been thoroughly studied. In this study, we obtained a regression formula for PM_2.5 concentration based on more than 1 million PM_2.5 recorded values and data from meteorology, industrial production, energy production, agriculture, and transportation for 31 provinces of mainland China between January 2013 and May 2017. We used stepwise regression to process 49 factors that influence PM_2.5 concentration, and obtained the 10 primary influencing factors. Data of PM_2.5 concentration and 10 factors from June to December, 2017 was used to verify the robustness of the model. Excluding meteorological factors, production of natural gas, industrial boilers, and ore production have the highest association with PM_2.5 concentration, while nuclear power generation is the most positive factor in decreasing PM_2.5 concentration. Tianjin, Beijing, and Hebei provinces are the most vulnerable to high PM_2.5 concentrations caused by industrial production, energy production, agriculture, and transportation (IEAT).

Identifying "hot papers" and papers with "delayed recognition" in large-scale datasets by using dynamically normalized citation impact scores

"Hot papers" (HPs) are papers which received a boost of citations shortly after publication. Papers with "delayed recognition" (DRs) received scarcely impact over a long time period, before a considerable citation boost started. DRs have attracted a lot of attention in scientometrics and beyond. Based on a comprehensive dataset with more than 5,000,000 papers published between 1980 and 1990, we identified HPs and DRs. In contrast to many other studies on DRs, which are based on raw citation counts, we calculated dynamically field-normalized impact scores for the search of HPs and DRs. This study is intended to investigate the differences between HPs (n = 323) and DRs (n = 315). The investigation of the journals which have published HPs and DRs revealed that some journals (e.g. Physical Review Letters and PNAS) were able to publish significantly more HPs than other journals. This pattern did not appear in DRs. Many HPs and DRs have been published by authors from the USA; however, in contrast to other countries, authors from the USA have published statistically significantly more HPs than DRs. Whereas "Biochemistry & Molecular Biology," "Immunology," and "Cell Biology" have published significantly more HPs than DRs, the opposite result arrived for "Surgery" and "Orthopedics." The results of the analysis of certain properties of HPs and DRs (e.g. number of pages) suggest that the emergence of DRs is an unpredictable process.