Annals of Operations Research

Liu, Yan; Zhang, Wei; Pan, Shuwen; Li, Yanjun; Wang, Xuejie; Chen, Zhuo; Samuel, R. Dinesh Jackson

doi: 10.1007/s10479-021-04383-8pmid: N/A

Intelligent Transportation System (ITS) relies on communication and computer-aided technologies for reliable driving and roadside assistance. The vehicle recognizes input from the driving environment through parking and dashboard video recorders. Based on the input, decisions on driving direction, object detection, etc., are made with ease. This article introduces Modular Input Processing Scheme (MIPS) for roadside object detection and decision-making in ITS. The scheme operates over the different input segments and features for identifying the object pattern. In the identification process, the object’s estimated distance and velocity is computed. Therefore, the textural and physical features of the objects are identified for smart detection and driving decisions. The feature analysis is aided by classification learning for adaptable and non-adaptable feature differentiation. The proposed scheme also relies on stored and iterated features for in-distance identifications. The classification improves the detection accuracy in less time, reducing complexity and cumulative analysis. Thus the proposed scheme’s performance is verified using accuracy, detection time, and computation complexity.

P C D, Kalaivaani; V E, Sathishkumar; Hatamleh, Wesam Atef; Haouam, Kamel Dine; Venkatesh, B.; Sweidan, Dirar

doi: 10.1007/s10479-021-04384-7pmid: N/A

Online advertising has expanded to a hundred-dollar billion industry in recent years, with sales growing at faster rate in every year. Prediction of the click-through rate (CTR) is an important role in recommended systems and online ads. Click through rating (CTR) is the newest evolution in the advertising and marketing digital world. It is essential for any online advertising company in real time to display the appropriate ads to the right users in the correct context. A huge amount of research work proposed considers each ad separately and does not takes in the relationship with other ads that may have an impact on Click Through Rate. A Factorization machine, a more generalized predictor like support vector machines (SVM) is not able to estimate reliable parameters under sparsity. The main drawback is that the primary features and existing algorithms considers the large weighted parameters. KGCN (Knowledge graph-based convolution network) overcomes the drawback and works on alternating graphs which creates additional clustering and node comparison with high latency and performance. A new framework DeepLight Weight is proposed to resolve the high server latency and high usage of memory issues in online advertising. This work presents a framework to improve the CTR predictions with an objective to accelerate the model inference, prune redundant parameters and the dense embedding vectors. Field Weighed Factorization machine helps to organize the data features with high structure to improve the accuracy. For clearing latency issues, structural pruning makes the algorithm work with dense matrices by combining and executing the individual matrix values or neural nodes.

Cui, Runyan; Zhang, Min; Zhang, Shaoyun; Zhang, Songtao

doi: 10.1007/s10479-021-04385-6pmid: N/A

Uncertainty and lead time (LT) make supply chain (SC) system present dynamic characteristics. In order to maintain low cost and stability in the operation of dynamic SC system, a cost optimization strategy (COS) and a robust control strategy (RCS) are investigated. A cost model of LT reduction is set up through the method of piecewise accumulation, and then a COS is designed by the comparison between the LT reduction cost and the shortage cost. By considering production LTs and uncertainties of the external demand and internal parameter for dynamic SC system, an inventory state transition equation and a system cost transition equation are developed. Based on the fuzzy control theory, a RCS is designed to reduce the interference of uncertainties and LTs to the normal operation of the dynamic SC system. Simulation results show that the COS and the RCS can make the dynamic SC system run stably at low cost under disturbance factors.

Yixin, Liu; Miao, Zhang

doi: 10.1007/s10479-021-04398-1pmid: N/A

In order to study the financial management of the Guangdong-Hong Kong-Macao Greater Bay Area, this paper builds a financial analysis model based on the LS-SVM algorithm and analyzes the implementation process of the LS-SVM algorithm and its modeling process. Moreover, this paper conducts research on CUDA-based GPU high-performance computing methods, designs and implements the LS-SVM algorithm on the CUDA-based GPU platform, and compares and analyzes the performance before and after optimization. In addition, this paper combines the improved algorithm to construct the financial analysis model and verifies the effect of the method proposed in this paper through actual data analysis. The research results prove the effectiveness of this method. The Hausman test achieves the probability of 0.1005 and 9.60182558 chi-square statistics.

Zhao, Jinmei; Sun, Lijuan

doi: 10.1007/s10479-021-04399-0pmid: N/A

Artificial intelligence (AI) in the workplace is revolutionising the way businesses operate. AI is being integrated into company operations with the goal of saving money, increasing efficiency, producing insights, and opening up new markets. In order to improve the effect of financial control of enterprise groups, this paper applies artificial intelligence technology to enterprise group management, and based on traditional data mining algorithms, this paper improves the data mining algorithm according to the actual needs of enterprise group management data. Starting from the needs of enterprise group management, this paper uses modern information technology as the support and takes several major elements of financial control system of enterprise groups as the breakthrough point to discuss the solution of financial control of enterprise groups under the network environment, and gives some reference significance optimization procedures. In addition, this paper constructs a financial control platform of enterprise groups and analyzes its data operation process. Finally, this paper verifies and evaluates the system performance through simulation tests. The experimental research results show that the financial control platform of enterprise groups based on artificial intelligence and big data constructed in this paper has good practical effects.

Zhang, Lifen; Zhou, Qiang; Zhang, Yuan; Liao, Xinyu

doi: 10.1007/s10479-021-04400-wpmid: N/A

Based on the fractal self-similarity theory, this paper puts forward the service level analysis method of container terminal’s logistics system. Based on the detailed study of container terminal’s logistics system, firstly, the self-similarity characteristics of container terminal’ logistics system are extracted to verify the applicability of fractal theory to container terminal’s logistics system. Secondly, the simulation analysis model is established, which measures the service level of container terminal’s logistics system from nine indicators, such as annual throughput, average service time of the ships, average ship-time efficiency, average utilization rate of berths, average daily occupancy rate of container yard, etc. The simulation model is applied to a container terminal, and the results show that the model can not only evaluate the overall service level of the container terminal, but also analyze the influence of different storage time and ship inter-arrival time on the service level of the terminal, so as to provide the basis for the terminal operation decision. The constructed model is a useful tool for assessing the validity of ideas about the functional interrelationships between the dry port's primary parameters, as well as the system's long-term viability.

Li, Cheng; Ji, Jie

doi: 10.1007/s10479-021-04404-6pmid: N/A

The improvement of green economic efficiency can impose significant influence on the new development of China’s economy. In this paper, the green economic efficiency of various provinces and cities in China during 1996–2018 is calculated by non-radial directional distance function. Then, the influence of different types of manufacturing agglomerations on green economic efficiency is studied by spatial static model and spatial dynamic model, and the short-term and long-term effects, direct and indirect effects as well as total effects are further analyzed. As the research results show, labor-intensive industrial agglomeration has an inhibiting effect on the green economic efficiency of local and surrounding regions, with long-term effect greater than short-term effect. Capital-intensive industrial agglomeration has more short-term negative effects on local green economic efficiency, with weak long-term effect and no significant influence on the green economic efficiency of surrounding regions. However, technology-intensive industrial agglomeration has a significant effect on improving the green economic efficiency of both local and surrounding regions.

Khan, Hashim; Aamir, Alamzeb; Jan, Sharif Ullah; Nassani, Abdelmohsen A.; Haffar, Mohamed

doi: 10.1007/s10479-021-04408-2pmid: N/A

The current study aims to identify the impact of shared leadership on project team processes such as coordination, goal commitment, and knowledge sharing in the context of Saudi Arabia. To serve this aim, a survey is conducted of 168 project team members working in various project teams. For analysis of the data, the latest editions of both AMOS and SPSS were used. The findings exhibited that the shared leadership directly affected all the three factors which in-turn directly affected the team performance; though, the shared leadership had no direct impact on the team performance. Moreover, based on the results, this study provides implications for team members and leaders to focus on coordinating activities, commitment to goals, and share the knowledge effectively in order to affect the team processes for better performance. The study adds to the area of shared leadership and team performances with these novel insights by introducing the significant role of these factors.

Li, Hongge; Manickam, Adhiyaman; Samuel, R. Dinesh Jackson

doi: 10.1007/s10479-021-04409-1pmid: N/A

In this research, players are investigated physically for the actual analysis to improve the recognition of motion effects based on image recognition technology. In this paper, the incorporation of the status of image recognition science has been tested on the athletes through image processing using artificial intelligence technology (IPAIT). Furthermore, the segmentation of gradient procedure has been validated using image segmentation techniques with big data assistance. In AIT, enhancing the traditional method of a grayscale image and obtaining the reconstructed image segmentation algorithm has been designed and developed. Furthermore, big data-assisted Gaussian background and IPAIT modeling are used to identify the target for the feature extraction of the human body and use morphological operators to deal with noise. The simulation findings demonstrate that the proposed IPAIT model enhances the recognition ratio of 98.8%, a performance ratio of 97.7%, and increases the accuracy ratio by 95.9% compared to other existing models.

Zhang, Yu; Ramanathan, L.; Maheswari, M.

doi: 10.1007/s10479-021-04412-6pmid: N/A

The main job of the e-business professional is to produce appropriate and trustworthy financial data. The solid internal controlling systems and the ethics and integrity of administration and staff depend significantly on the accuracy and relevancy of financial reports. This article demonstrates how Artificial Intelligence interacts with internal controlling systems creatively to assist managers in creating quality financial data by minimizing the risk of loss. A risk analysis approach for e-business is proposed in this article. Even though various kinds of research suggested in accountancy utilizing artificial intelligence, none of these proved explicitly how data risks were reduced via AI technology. The analysis benefits organizations save considerable expenses and losses by providing reliable financial data, helping managers decide effectively, and enhancing firms' efficiency. This article offers a concept of utilizing artificial intelligence to automate the removal of the vulnerability of internal monitoring systems by all types of businesses. It decreases the risk control, identification, and reporting quality through managing the risk of information reporting by offering the highest risk prediction accuracy of 89% and the precision ratio of 91% compared to the existing models.