Search results

1 – 10 of 26
Article
Publication date: 7 July 2020

Jiaming Liu, Liuan Wang, Linan Zhang, Zeming Zhang and Sicheng Zhang

The primary objective of this study was to recognize critical indicators in predicting blood glucose (BG) through data-driven methods and to compare the prediction…

Abstract

Purpose

The primary objective of this study was to recognize critical indicators in predicting blood glucose (BG) through data-driven methods and to compare the prediction performance of four tree-based ensemble models, i.e. bagging with tree regressors (bagging-decision tree [Bagging-DT]), AdaBoost with tree regressors (Adaboost-DT), random forest (RF) and gradient boosting decision tree (GBDT).

Design/methodology/approach

This study proposed a majority voting feature selection method by combining lasso regression with the Akaike information criterion (AIC) (LR-AIC), lasso regression with the Bayesian information criterion (BIC) (LR-BIC) and RF to select indicators with excellent predictive performance from initial 38 indicators in 5,642 samples. The selected features were deployed to build the tree-based ensemble models. The 10-fold cross-validation (CV) method was used to evaluate the performance of each ensemble model.

Findings

The results of feature selection indicated that age, corpuscular hemoglobin concentration (CHC), red blood cell volume distribution width (RBCVDW), red blood cell volume and leucocyte count are five most important clinical/physical indicators in BG prediction. Furthermore, this study also found that the GBDT ensemble model combined with the proposed majority voting feature selection method is better than other three models with respect to prediction performance and stability.

Practical implications

This study proposed a novel BG prediction framework for better predictive analytics in health care.

Social implications

This study incorporated medical background and machine learning technology to reduce diabetes morbidity and formulate precise medical schemes.

Originality/value

The majority voting feature selection method combined with the GBDT ensemble model provides an effective decision-making tool for predicting BG and detecting diabetes risk in advance.

Article
Publication date: 19 June 2017

Jiaming Liu, Chong Wu and Tianyi Su

The purpose of this paper is to discuss the role of reference effect on newsvendor’s decision behavior in a market with strategic customers and work out the newsvendor’s…

Abstract

Purpose

The purpose of this paper is to discuss the role of reference effect on newsvendor’s decision behavior in a market with strategic customers and work out the newsvendor’s optimal pricing policy and ordering quantity.

Design/methodology/approach

This study utilizes the prospect theory and strategic customer framework to analyze the decision-making behavior on the newsvendor’s optimal pricing policy and ordering quantity. The paper further presents an extension of newsvendor model and provides the model’s properties. The paper finally analyzes the results with various parameters on the model and reports on the insights generated by the model.

Findings

The paper indicates that the ordering quantity is not altered with the changing proportion of strategic customers and myopic customers, but the ordering quantity and the pricing strategy are influenced in terms of newsvendor’s reference effect, loss aversion, product cost, and salvage price.

Practical implications

The research findings have important implications for decision makers. Previous researches have studied the incomplete rationality newsvendor’s decision-making behavior mainly by analyzing the vendor’s risk preferences or loss aversion, but the effect of reference point also plays an important role in analyzing the decision-maker’s behavior. The paper provides the optimal pricing policy and ordering quantity with the reference effect considering the strategic customers behavior. This model is also a valid complementarity to behavioral operations management research area.

Originality/value

The paper examines the role of reference effect in newsvendor problem with the strategic customers and analyzes the impact of parameters such as loss aversion on the newsvendor’s decision behavior.

Details

Management Decision, vol. 55 no. 5
Type: Research Article
ISSN: 0025-1747

Keywords

Article
Publication date: 5 August 2019

Yongli Li, Sihan Li, Chuang Wei and Jiaming Liu

Due to the unintentional or even the intentional mistakes arising from a survey, the purpose of this paper is to present a data-driven method for detecting students…

Abstract

Purpose

Due to the unintentional or even the intentional mistakes arising from a survey, the purpose of this paper is to present a data-driven method for detecting students’ friendship network based on their daily behaviour data. Based on the detected friendship network, this paper further aims to explore how the considered network effects (i.e. friend numbers (FNs), structural holes (SHs) and friendship homophily) influence students’ GPA ranking.

Design/methodology/approach

The authors collected the campus smart card data of 8,917 sophomores registered in one Chinese university during one academic year, uncovered the inner relationship between the daily behaviour data with the friendship to infer the friendship network among students, and further adopted the ordered probit regression model to test the relationship between network effects with GPA rankings by controlling several influencing variables.

Findings

The data-driven approach of detecting friendship network is demonstrated to be useful and the empirical analysis illustrates that the relationship between GPA ranking and FN presents an inverted “U-shape”, richness in SHs positively affects GPA ranking, and making more friends within the same department will benefit promoting GPA ranking.

Originality/value

The proposed approach can be regarded as a new information technology for detecting friendship network from the real behaviour data, which is potential to be widely used in many scopes. Moreover, the findings from the designed empirical analysis also shed light on how to improve GPA rankings from the angle of network effect and further guide how many friends should be made in order to achieve the highest GPA level, which contributes to the existing literature.

Details

Information Technology & People, vol. 33 no. 2
Type: Research Article
ISSN: 0959-3845

Keywords

Open Access
Article
Publication date: 29 July 2022

Jiaming Wu and Xiaobo Qu

This paper aims to review the studies on intersection control with connected and automated vehicles (CAVs).

Abstract

Purpose

This paper aims to review the studies on intersection control with connected and automated vehicles (CAVs).

Design/methodology/approach

The most seminal and recent research in this area is reviewed. This study specifically focuses on two categories: CAV trajectory planning and joint intersection and CAV control.

Findings

It is found that there is a lack of widely recognized benchmarks in this area, which hinders the validation and demonstration of new studies.

Originality/value

In this review, the authors focus on the methodological approaches taken to empower intersection control with CAVs. The authors hope the present review could shed light on the state-of-the-art methods, research gaps and future research directions.

Details

Journal of Intelligent and Connected Vehicles, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 2399-9802

Keywords

Article
Publication date: 4 February 2022

Lin Yang, Jiaming Lou, Junuo Zhou, Xianbo Zhao and Zhou Jiang

With multiple-related organizations, worldwide infections, deep economic recession and public disorder, and large consumption amount of anti-epidemic resources, the…

Abstract

Purpose

With multiple-related organizations, worldwide infections, deep economic recession and public disorder, and large consumption amount of anti-epidemic resources, the coronavirus disease 2019 (COVID-19) has been defined as a public health emergency of international concern (PHEIC). Nowadays, Wuhan has recovered from the pandemic disaster and reentered normalization. The purposes of this study are to (1) summarize organization collaboration patterns, successful experience and latent defects under across-stage evolution of Wuhan's cooperation governance mode against the pandemic, and on the basis, (2) reveal how the COVID-19 development trends and organizations' collaborative behaviors affected each other.

Design/methodology/approach

Detailed content analysis of online news reports covering COVID-19 prevention and control measures on the website of Wuhan Municipal Government was adopted to identify organizations and their mutual collaborative interrelationships. Four complex network (CN) models of organization collaboration representing the outbreak, preliminary control, recession and normalization stages, respectively, were established then. Time-span-based dynamic parameter analyses of the proposed networks, comprising network cohesiveness analysis and node centrality analysis, were undertaken to indicate changes of global and local characteristics in networks.

Findings

First, the definite collaborative status of Wuhan Headquarters for Pandemic Prevention and Control (WHPPC) has persisted throughout the period. Medical institutions and some other administrations were the most crucial participants collaborating with the WHPPC. Construction-industry organizations altered pandemic development trends twice to make the situation controllable. Media, large-scale enterprises, etc. set about underscoring themselves contributions since the third stage. Grassroots cadres and healthcare force, small and medium-sized enterprises (SMEs), financial institutions, etc. were essential collaborated objects. Second, four evolution mechanisms of organization collaboration responding to the COVID-19 in Wuhan has been proposed.

Research limitations/implications

First, universality of Wuhan-style governance experience may be affected. Second, the stage-dividing process may not be the most appropriate. Then, data source was single and link characteristics were not considered when modeling.

Practical implications

This study may offer beneficial action guidelines to governmental agencies, the society force, media, construction-industry organizations and the market in other countries or regions suffering from COVID-19. Other organizations involved could also learn from the concluded organizations' contributions and four evolution mechanisms to find improvement directions.

Originality/value

This study adds to the current theoretical knowledge body by verifying the feasibility and effectiveness of investigating cooperation governance in public emergencies from the perspectives of analyzing the across-stage organization collaboration CNs.

Details

Engineering, Construction and Architectural Management, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0969-9988

Keywords

Open Access
Article
Publication date: 16 March 2022

Liang Xu, Sheng Jin, Bolin Li and Jiaming Wu

This study aims to make full use of the advantages of connected and autonomous vehicles (CAVs) and dedicated CAV lanes to ensure all CAVs can pass intersections without stopping.

Abstract

Purpose

This study aims to make full use of the advantages of connected and autonomous vehicles (CAVs) and dedicated CAV lanes to ensure all CAVs can pass intersections without stopping.

Design/methodology/approach

The authors developed a signal coordination model for arteries with dedicated CAV lanes by using mixed integer linear programming. CAV non-stop constraints are proposed to adapt to the characteristics of CAVs. As it is a continuous problem, various situations that CAVs arrive at intersections are analyzed. The rules are discovered to simplify the problem by discretization method.

Findings

A case study is conducted via SUMO traffic simulation program. The results show that the efficiency of CAVs can be improved significantly both in high-volume scenario and medium-volume scenario with the plan optimized by the model proposed in this paper. At the same time, the progression efficiency of regular vehicles is not affected significantly. It is indicated that full-scale benefits of dedicated CAV lanes can only be achieved with signal coordination plans considering CAV characteristics.

Originality/value

To the best of the authors’ knowledge, this is the first research that develops a signal coordination model for arteries with dedicated CAV lanes.

Details

Journal of Intelligent and Connected Vehicles, vol. 5 no. 2
Type: Research Article
ISSN: 2399-9802

Keywords

Article
Publication date: 24 May 2018

Jiaming Han, Zhong Yang, Guoxiong Hu, Ting Fang and Hao Xu

This paper aims to propose a robust and efficient method for vanishing point detection in unstructured road scenes.

Abstract

Purpose

This paper aims to propose a robust and efficient method for vanishing point detection in unstructured road scenes.

Design/methodology/approach

The proposed method includes two main stages: drivable region estimation and vanishing point detection. In drivable region estimation stage, the road image is segmented into a set of patches; then the drivable region is estimated by the patch-wise manifold ranking. In vanishing point detection stage, the LSD method is used to extract the straight lines; then a series of principles are proposed to remove the noise lines. Finally, the vanishing point is detected by a novel voting strategy.

Findings

The proposed method is validated on various unstructured road images collected from the real world. It is more robust and more efficient than the state-of-the-art method and the other three recent methods. Experimental results demonstrate that the detected vanishing point is practical for vision-sensor-based navigation in complex unstructured road scenes.

Originality/value

This paper proposes a patch-wise manifold ranking method to estimate the drivable region that contains most of the informative clues for vanishing point detection. Based on the removal of the noise lines through a series of principles, a novel voting strategy is proposed to detect the vanishing point.

Details

Sensor Review, vol. 39 no. 1
Type: Research Article
ISSN: 0260-2288

Keywords

Open Access
Article
Publication date: 11 April 2022

Liang Wang, Jiaming Wu, Xiaopeng Li, Zhaohui Wu and Lin Zhu

This paper aims to address the longitudinal control problem for person-following robots (PFRs) for the implementation of this technology.

191

Abstract

Purpose

This paper aims to address the longitudinal control problem for person-following robots (PFRs) for the implementation of this technology.

Design/methodology/approach

Nine representative car-following models are analyzed from PFRs application and the linear model and optimal velocity model/full velocity difference model are qualified and selected in the PFR control.

Findings

A lab PFR with the bar-laser-perception device is developed and tested in the field, and the results indicate that the proposed models perform well in normal person-following scenarios.

Originality/value

This study fills a gap in the research on PRFs longitudinal control and provides a useful and practical reference on PFRs longitudinal control for the related research.

Details

Journal of Intelligent and Connected Vehicles, vol. 5 no. 2
Type: Research Article
ISSN: 2399-9802

Keywords

Article
Publication date: 18 March 2020

Jiaming Zhang and Xiangrong Deng

This study aims to empirically analyze how interest rate liberalization affects bank liquidity creation, and investigate whether the relationship between them is linear.

Abstract

Purpose

This study aims to empirically analyze how interest rate liberalization affects bank liquidity creation, and investigate whether the relationship between them is linear.

Design/methodology/approach

Based on panel data on 145 banks in China over the period 1997–2015, this paper regresses the econometric model by conducting feasible generalized least square estimation.

Findings

The regression results show that, first, interest rate liberalization has a nonlinear impact on bank liquidity creation, and the relationship between them is inverted U-shaped. In other words, as interest rate liberalization progresses, bank liquidity creation increases first, and then decreases. Second, through the mediation effect tests, this study found that interest rate liberalization affects bank liquidity creation through bank risk-taking. That is, interest rate liberalization leads to changes in bank risk-taking, thus resulting in changes in bank liquidity creation.

Research limitations/implications

The effect of interest rate liberalization on bank liquidity creation is nonlinear, so promoting interest rate liberalization faces a trade-off because excessive bank liquidity creation may lead to asset price bubbles, while insufficient bank liquidity creation may inhibit economic growth.

Practical implications

Interest rate liberalization has a significant impact on bank liquidity creation; therefore, bank liquidity creation should be added to the objective function of the regulator that determines interest rate liberalization reform in China.

Social implications

Interest rate liberalization has a direct impact on bank risk-taking, so the consequences of interest rate liberalization should be included in the framework of macro-prudential supervision.

Originality/value

Interest rate liberalization is one of the most important financial reforms in China, yet its potential impact on firm-level bank liquidity is little explored. This paper attempts to fill the gap.

Book part
Publication date: 6 September 2021

Giacomo Del Chiappa, Marcello Atzeni and Enrico Panai

Set against the background of uncertainty and crisis generated by COVID-19, policymakers, destination marketers and tourism and hospitality managers are struggling in…

Abstract

Set against the background of uncertainty and crisis generated by COVID-19, policymakers, destination marketers and tourism and hospitality managers are struggling in trying to envision how, and till when, tourist behaviour will be changed and transformed by this pandemic and how tourists will select the accommodation where to stay during their holiday.

So far, a limited number of academic studies have been devoted to analyzing how travellers will select the accommodation for their holidays. This urges academicians to fill this gap with the aim to provide practitioners with fresh and insightful knowledge to support their decision-making in a tourism era where everyone seems to be shifting towards a ‘new normality’ of uncertain duration.

This study was therefore carried out to contribute to this debate by presenting and discussing findings of an empirical investigation applying a factor–cluster analysis on a sample of 225 French consumers/travellers to profile them based on accommodation selection criteria. Further, a series of chi-square tests was run to investigate whether significant differences exist among clusters based on their sociodemographic characteristics (i.e. gender, age, level of occupation, employment status) and travel-related variables (i.e. the preferred type of accommodation and the length of the holiday).

Findings contribute to deepening the scientific debate about how tourists' behaviour is being transformed in a tourism era affected by the COVID-19 pandemic. Meanwhile, our results will provide accommodation marketers with useful information to be used to effectively plan and implement their service design to meet tourists' expectations and needs.

1 – 10 of 26