Zunxin Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zunxin Zheng has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Fumin Zhu
College of Economics, Shenzhen University, Shenzhen, China
5 shared publications - Chen Zhang
College of Economics, Shenzhen University, Shenzhen, China
2 shared publications - Ahmed Farouk
College of Science and Engineering, Qatar Center for Quantum Computing, Hamad Bin Khalifa University, Doha, Qatar
1 shared publication Fumin Zhu
College of Economics, Shenzhen University, Shenzhen, 518060 China
1 shared publicationHonghong Yang
Northwestern Polytechinical University
1 shared publication- Lijun Ma
Shenzhen University
1 shared publication
Latest Publications
- 24 May 2024
- Published by Elsevier in The North American Journal of Economics and Finance
- Vol. 74
Pricing VIX options based on mean-reverting models driven by information
- 24 May 2024
- Published by Elsevier in The North American Journal of Economics and Finance
- Vol. 74
Pricing VIX options based on mean-reverting models driven by information
- 1 October 2021
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 95, 107373
Potential technologies and applications based on deep learning in the 6G networks
- 1 October 2021
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 95, 107373
Potential technologies and applications based on deep learning in the 6G networks
- 1 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 9747-9754
Click Fraud Detection of Online Advertising–LSH Based Tensor Recovery Mechanism
Online advertising utilizes the Internet technique to deliver marketing messages to promotional consumers. It is growing in recent years to facilitate the increasing demands of electronic commerce. Advertisers bid and pay for the advertisement whenever potential customers click it. The way of Pay-Per-Click (PPC) is vulnerable to malicious clicks that mimic real user behaviour to trick the platform into counting their clicks as legitimate. It causes massive financial losses on advertisers and also significantly reduces the credibility of online advertising platforms. The common strategies to detect fraud clicks are dynamically tailoring and interpreting data based on the machine learning model. These algorithms treat multi-dimensional data as an individual feature vector or matrix, making it different to explore intrinsic relations among a sequence of data. Million daily fraud clicks on various types further disperse the focus of models and result in relatively low efficiency for the current fraud prediction system. To tackle the fraud click problem, we introduce a tensor-based mechanism to predict fraud clicks. This paper considered reconstructing data into a high-rank tensor, implement tensor decomposition and transformation to explore hidden information under each data and explore the joined effect among a sequence of data. The proposed tensor transformation algorithm with locality-sensitive hashing (LSH) is tested by extensive experiments using real-world data. Compared with the state-of-art machine learning algorithms, our model can achieve significant performance in terms of accuracy and prediction-recall rate.
- 1 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (7) , 9747-9754
Click Fraud Detection of Online Advertising–LSH Based Tensor Recovery Mechanism
Online advertising utilizes the Internet technique to deliver marketing messages to promotional consumers. It is growing in recent years to facilitate the increasing demands of electronic commerce. Advertisers bid and pay for the advertisement whenever potential customers click it. The way of Pay-Per-Click (PPC) is vulnerable to malicious clicks that mimic real user behaviour to trick the platform into counting their clicks as legitimate. It causes massive financial losses on advertisers and also significantly reduces the credibility of online advertising platforms. The common strategies to detect fraud clicks are dynamically tailoring and interpreting data based on the machine learning model. These algorithms treat multi-dimensional data as an individual feature vector or matrix, making it different to explore intrinsic relations among a sequence of data. Million daily fraud clicks on various types further disperse the focus of models and result in relatively low efficiency for the current fraud prediction system. To tackle the fraud click problem, we introduce a tensor-based mechanism to predict fraud clicks. This paper considered reconstructing data into a high-rank tensor, implement tensor decomposition and transformation to explore hidden information under each data and explore the joined effect among a sequence of data. The proposed tensor transformation algorithm with locality-sensitive hashing (LSH) is tested by extensive experiments using real-world data. Compared with the state-of-art machine learning algorithms, our model can achieve significant performance in terms of accuracy and prediction-recall rate.
- 2 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (7) , 5211-5218
Practical Network Coding Technologies and Softwarization in Wireless Networks
Network coding is an elegant and novel technique to improve network throughput and performance. It is considered as a critical technology to facilitate ever-increasing demands of future wireless networks. It exploits the broadcast nature of wireless media and cooperatively codes packets from different senders to provide reliable, secure, and efficient transmissions. Current research focuses on either transmission delay, coding complexity, forwarding security, or end-to-end throughput. Network coding-aided solutions can recover lost packets without feedback, eliminate latency, reduce the routing cost on diverse paths, or optimize the capacity of unstable wireless networks. However, devices or smart sensors usually have limited computational capacity and some applications could not tolerate high decoding delay, which prevents network coding from being widely deployed in the real world. In recent years, many research methods consider simplifying decoding matrix or coding algorithm to alleviate the shortcoming of network coding and further satisfy the extreme demands of the future wireless network. This article summarizes complexity-optimized methods and explains the interaction effect of coding opportunities and decoding overhead. We propose a taxonomy of practical network coding methods and illustrate three practical directions on cutting computational complexity and enhancing progressive decoding. We also conclude the benefit and cost of current network coding algorithms along with the outline of future research.
- 2 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (7) , 5211-5218
Practical Network Coding Technologies and Softwarization in Wireless Networks
Network coding is an elegant and novel technique to improve network throughput and performance. It is considered as a critical technology to facilitate ever-increasing demands of future wireless networks. It exploits the broadcast nature of wireless media and cooperatively codes packets from different senders to provide reliable, secure, and efficient transmissions. Current research focuses on either transmission delay, coding complexity, forwarding security, or end-to-end throughput. Network coding-aided solutions can recover lost packets without feedback, eliminate latency, reduce the routing cost on diverse paths, or optimize the capacity of unstable wireless networks. However, devices or smart sensors usually have limited computational capacity and some applications could not tolerate high decoding delay, which prevents network coding from being widely deployed in the real world. In recent years, many research methods consider simplifying decoding matrix or coding algorithm to alleviate the shortcoming of network coding and further satisfy the extreme demands of the future wireless network. This article summarizes complexity-optimized methods and explains the interaction effect of coding opportunities and decoding overhead. We propose a taxonomy of practical network coding methods and illustrate three practical directions on cutting computational complexity and enhancing progressive decoding. We also conclude the benefit and cost of current network coding algorithms along with the outline of future research.
- Open Access
- 24 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 50278-50289
Sparse Trading, Information Transmission and Futures Prices Recovery (August 2018)
This paper proposes a sparse trading model of futures prices. The model considers that nearby futures contract with liquidity plays an important role in the price recovery, and allows that far futures contract with sparse trading uses the price of nearby futures contract as a source of information. Also, it is shown whether and how liquidity may well be an influential factor for futures prices in Chinese commodity futures markets. Empirical results show strong evidence for lead-lag information transmission for fuel oil, nature rubber, and soybean, which implies sparse trading effect on futures prices.
- 24 August 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 50278-50289
Open AccessSparse Trading, Information Transmission and Futures Prices Recovery (August 2018)
This paper proposes a sparse trading model of futures prices. The model considers that nearby futures contract with liquidity plays an important role in the price recovery, and allows that far futures contract with sparse trading uses the price of nearby futures contract as a source of information. Also, it is shown whether and how liquidity may well be an influential factor for futures prices in Chinese commodity futures markets. Empirical results show strong evidence for lead-lag information transmission for fuel oil, nature rubber, and soybean, which implies sparse trading effect on futures prices.
- Open Access
- 9 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 38959-38966
A Bayesian Learning Method for Financial Time-Series Analysis
This article develops a sequential Bayesian learning method to estimate the parameters and recover the state variables for generalized autoregressive conditional heteroscedasticity (GARCH) models, which are commonly used in the financial time-series analysis. This simulation-based method combines particle-filtering technology with a Markov chain Monte Carlo (MCMC) algorithm when the model is non-linear and the number of observed variables is relatively sparse. We compare the performance of the sequential Bayesian learning approach (SBLA) with the numerical maximum likelihood estimation (NMLE) in estimating models based on S&P 500 return rates. Our research concludes that the sequential parameter learning approach performs more robustly and accurately than the NMLE, as take into account the uncertainty of the model. We also carry out simulation studies to confirm that the sequential Bayesian learning method is extremely reliable for GARCH models.
- 9 July 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 38959-38966
Open AccessA Bayesian Learning Method for Financial Time-Series Analysis
This article develops a sequential Bayesian learning method to estimate the parameters and recover the state variables for generalized autoregressive conditional heteroscedasticity (GARCH) models, which are commonly used in the financial time-series analysis. This simulation-based method combines particle-filtering technology with a Markov chain Monte Carlo (MCMC) algorithm when the model is non-linear and the number of observed variables is relatively sparse. We compare the performance of the sequential Bayesian learning approach (SBLA) with the numerical maximum likelihood estimation (NMLE) in estimating models based on S&P 500 return rates. Our research concludes that the sequential parameter learning approach performs more robustly and accurately than the NMLE, as take into account the uncertainty of the model. We also carry out simulation studies to confirm that the sequential Bayesian learning method is extremely reliable for GARCH models.
- 1 July 2018
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 69, 422-434
Towards an improved heuristic genetic algorithm for static content delivery in cloud storage
- 1 July 2018
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 69, 422-434
Towards an improved heuristic genetic algorithm for static content delivery in cloud storage
- 27 February 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (4) , 4113-4131
Visual tracking via online discriminative multiple instance metric learning
- 27 February 2017
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (4) , 4113-4131
Visual tracking via online discriminative multiple instance metric learning
- Open Access
- 22 January 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-9
Customized Transportation, Equity Participation, and Cooperation Performance within Logistics Supply Chains
Customized transportation has received growing concerns by researchers and practitioners in recent years. Despite the fact that one consignor often holds partial ownership of its carrier within a supply chain, the existing interpretations behind them remain relatively unexplored. Based on the game models, we find that a simple take-or-pay contract is not likely to solve the low-efficient customized production problem, and equity participation mechanism plus simple contract may improve the cooperation performance of customized transportation. In the case of the owner-managed carrier, only when purchasing at par can it be ensured to obtain the socially optimal customization investment, but when purchasing at premium or discount, the optimal partial ownership selected by consignor cannot motivate the carrier to make the most efficient customization investment. With the optimal solutions, we also provide a theoretic foundation for calculating the optimal partial ownership and for interpreting why the interfirm share-holding ratios of the member-firms within the familial-type logistic supply chains are much larger than the ratios within the public-type logistic supply chains. Finally, our results show that the familial-type logistic supply chains may choose more efficient customized production level than public-type logistic supply chains.
- 22 January 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-9
Open AccessCustomized Transportation, Equity Participation, and Cooperation Performance within Logistics Supply Chains
Customized transportation has received growing concerns by researchers and practitioners in recent years. Despite the fact that one consignor often holds partial ownership of its carrier within a supply chain, the existing interpretations behind them remain relatively unexplored. Based on the game models, we find that a simple take-or-pay contract is not likely to solve the low-efficient customized production problem, and equity participation mechanism plus simple contract may improve the cooperation performance of customized transportation. In the case of the owner-managed carrier, only when purchasing at par can it be ensured to obtain the socially optimal customization investment, but when purchasing at premium or discount, the optimal partial ownership selected by consignor cannot motivate the carrier to make the most efficient customization investment. With the optimal solutions, we also provide a theoretic foundation for calculating the optimal partial ownership and for interpreting why the interfirm share-holding ratios of the member-firms within the familial-type logistic supply chains are much larger than the ratios within the public-type logistic supply chains. Finally, our results show that the familial-type logistic supply chains may choose more efficient customized production level than public-type logistic supply chains.