Research on Human Performance Evaluation Model Based on Neural Network and Data Mining Algorithm

DOI: https://doi.org/10.21203/rs.3.rs-19197/v2

Abstract

In order to effectively evaluate personnel performance, a distributed data mining algorithm for spatial networks based on BP neural wireless network is proposed. In the cloud computing environment, an excavator is used to construct multiple input multiple output spatial network data, analyze the data structure, and perform redundant data compression of massive data through time-frequency feature extraction. Combined with adaptive matching filtering method, the characteristics of the data are matched. The spatial frequency feature extraction method is used to locate the features of the multiple-input multiple-output spatial network data. In order to improve the accuracy of data mining, the BP neural network is used to classify and identify the extracted data features to achieve the optimization of data mining. A wireless sensor network is a wireless network composed of a large number of stationary or moving sensors in a self-organizing and multi-hop manner. It cooperatively senses, collects, processes, and transmits the information of the perceived objects in the geographical area covered by the network, and finally puts these The information is sent to the owner of the network. This algorithm improves the accuracy of personnel performance evaluation, and simultaneously establishes a hierarchical analysis and quantitative evaluation model for the performance of government managers, and adjusts the results of hierarchical statistical analysis on government administrators as needed. The performance evaluation and optimization of government administrators were introduced. The empirical analysis results show that the method has higher accuracy for government managers' performance evaluation, higher efficiency of big data processing and better integration.

Introduction

The number of administrative departments of the government continues to merge with the reform of the government system and the development of the economy. No matter whether the scale of government administration is large or small, it is necessary to manage the performance of administrative staff. There are some difficulties in this part of the management. The administrative department of government is a non-profit organization. Under the situation of the reform of government system and mechanism, its business scale is expanding constantly. The staff in the administration include office, financial and other aspects. Administrators, like staff in other departments, put the goals and interests of the executive branch at the top of their work. The performance management of administrative staff plays an important role in the development of administrative staff as well as the whole government administration[1]. Fuzzy normal form neural network partly covers the basic knowledge of neural computation and fuzzy neural computation, and the realization of the algorithm can identify the essence of the relationship between fuzzy system and neural network.The work of administrative staff is complicated, flexible and difficult to quantify. Administrative staff provide more temporary services to other departments, such as manpower, finance and so on. These temporary services are not easy to judge in quantitative management. The work of administrative personnel is complex, and often receive other tasks in the work[2]. Fuzzy normal form system can provide big data support for medical health and reliable data source for decision-makers. In this paper, prov-s, safety data origin model based on W3CPROV, is proposed to study various labeled objects in the safety origin relation graph and define the range of related objects.Compared with the task of the production department, the work of the administrative staff is not restricted and directed by the production plan, and there is often sudden work in the daily work. This kind of sudden work can account for a large part of the total work of administrative personnel. The administrative personnel's work is too dynamic, the examination will encounter problems of one kind or another[3].

The administrative staff's work content is more complex, mainly for the other departments of the government administrative department to provide services and help, and it also has the function of supervision and coordination[4]. The performance assessment of the administrative staff is not enough, the quantitative process and the quantitative results are not clear and accurate. In the performance assessment of the administrative staff, the evaluation index is not flexible and does not take into account the differences between the administrative staff. Although the use of the unified assessment can save the cost for the government administration, it will strike the enthusiasm of the administrative staff[5]. Therefore, it needs to be studied. This paper proposes an effective performance evaluation model for government administrators. This paper puts forward the performance evaluation model of government administrators based on an analytic hierarchy process, and combines the results of descriptive statistical average analysis to test the sample regression of the large data of the performance evaluation of the government administrators and adopt the adaptive fuzzy scheduler. The law carries out the classification and recognition of the performance data of the government administrators[6]. According to the results of the performance information fusion of the government administrative personnel, the hierarchical analysis is carried out, the quantitative evaluation model of the performance of the administrative personnel of the government is established, and the regression analysis and adaptation of the administrative personnel management of the government are carried out by the F statistics analysis method. The adjustment, based on the hierarchical statistical analysis results of adaptive adjustment of government administrative personnel, combined with the AHP method, to achieve the performance evaluation of government administrative personnel optimization. Finally, the empirical analysis of the performance test is taken, it shows the superiority of this model in improving the ability of the performance evaluation of administrative personnel of the government[7,8].

The rest of this paper is organized as follows. Section 2 discusses statistical analysis model and constraint parameter analysis of the performance evaluation of government administrators, followed by optimization of performance evaluation model for government administrators in Section 3. Empirical analysis and test is discussed in Section 4. Section 5 concludes the paper with summary and future research directions.

Statistical Analysis Model And Constraint Parameter Analysis Of The Performance Evaluation Of Government Administrators

Due to technical limitations, the statistical analysis section is only available as a download in the supplementary files.

Methods

Due to technical limitations, the Methods section is only available as a download in the supplementary files.

Experiment

The experiment adopts Matlab 7, the method of sampling the data of government administrative personnel's performance evaluation modeling adopts the method of social investigation and descriptive statistical analysis. The software of data analysis is SPSS 19.0. the basic statistical results of the personnel are shown in Table 4. Figure 2 is the distribution diagram of network nodes.

According to the results of the regression analysis of performance evaluation in Table 5, the performance evaluation of government administrators is carried out. The distribution of the evaluation curve is shown in Figure 4, taking the satisfaction degree of the masses and administrative behavior as the parameter.

The analysis shows that the performance evaluation of government administrators by using this model is accurate and confidence level is better.

In order to further verify the effectiveness of the performance evaluation model of this paper, compared with the quantitative evaluation method, the relative evaluation method and the scale evaluation method, as shown in Figure 5.

 

 

The experiment adopts Matlab 7, the method of sampling the data of government administrative personnel's performance evaluation modeling adopts the method of social investigation and descriptive statistical analysis. The software of data analysis is SPSS 19.0. the basic statistical results of the personnel are shown in Table 4. Figure 2 is the distribution diagram of network nodes.

According to the results of the regression analysis of performance evaluation in Table 5, the performance evaluation of government administrators is carried out. The distribution of the evaluation curve is shown in Figure 4, taking the satisfaction degree of the masses and administrative behavior as the parameter.

The analysis shows that the performance evaluation of government administrators by using this model is accurate and confidence level is better.

In order to further verify the effectiveness of the performance evaluation model of this paper, compared with the quantitative evaluation method, the relative evaluation method and the scale evaluation method, as shown in Figure 5.

Results And Discussion

In this paper, a performance evaluation model of government administrators based on AHP is proposed. Combined with the results of descriptive statistical average analysis, the sample regression test of big data performance evaluation of government administrators is carried out, and the adaptive fuzzy scheduling method is used to classify and identify the performance big data of government administrators. According to the results of the performance information fusion of government administrators, the hierarchical analysis and the quantitative evaluation model of the performance of government administrators are established. The F statistic analysis method is used for the regression analysis and adaptive adjustment of the government administrative personnel management, and the adaptive adjustment for the government administrative personnel is carried out according to the results of the hierarchical statistical analysis, and combined with the AHP method, the performance evaluation and optimization of government administrators is realized. The results of empirical analysis show that the performance evaluation of government administrators by using this method has higher accuracy, higher efficiency of big data processing and better integration. This method has a good application value in the performance evaluation of government managers.

Declarations

Availability of data and material

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Competing interests

declares that he has no conflict of interest.

* Research involving human participants and/or animals

Ethical approval: This article does not contain any studies with human participants or animals performed by any of the authors.

* Informed consent

All authors agree to submit this version and claim that no part of this manuscript has been published or submitted elsewhere.

Funding

None

Authors' contributions

Wei Liang wrote the entire article.Tingyi Li is responsible for the experimental simulation

Acknowledgements

None

Abbreviations

 (AHP ) Analytic Hierarchy Process

References

[1] J. F. Zheng, J. Zhang, K. Y. Zhu, Gust front statistical characteristics and automatic identification algorithm for CINRAD. Acta Meteorologica Sinica 28(4), 607-623(2014).

[2] Y. Hwang, T. Y. Yu, V. Lakshmanan, Neuro-fuzzy gust front detection algorithm with S-band polarimetric radar. IEEE Transactions on Geoscience and Remote Sensing 55(3), 1618-1628(2017).

[3] E. Shi, Q. Li, D. Q. Gu, Z. M. Zhao, Weather radar echo extrapolation method based on convolutional neural networks. Journal of Computer Applications 38(3), 661-665(2018).

[4] T. D. Fletcher, H. Andrieu, P. Hamel, Understanding, management and modelling of urban hydrology and its consequences for receiving waters, a state of the art. Advances in Water Resources 51(1), 261-279(2013).

[5] J. Y. Xue, X. Y. Ni, On the Reform of College English Teaching under the trend of Educational Informatization. Integration of Information Technology and Teaching practice 45(12), 43-45(2015).

[6] B. F. Zheng, X. F. Gu, Walk through the "Cloud" end of practical Education Information--On the Application of Cloud platform in English Teaching. Education and Teaching Forum 12(03), 263-265(2016).

[7] S. Wei,WYNTER L., (2012). A New One-level Convex Optimization Approach for Estimating Origin–destination Demand .Transportation Research Part B: Methodological, 46(10), pp.1535–1555.

[8] C. S. Rao,K. C. K. Reddy, D. S. Rao, Power control technique for efficient call admission control in advanced Wireless Networks.International Journal on Computer Science and Engineering 4(6), 962-973(2012).

[9]H. Y. Shi, W. L. Wang, N. M. Kwok, Game theory for Wireless Sensor Networks: a survey.Sensors 12(7), 9055-9097(2012).

[10] G. P. Zhang, P. Liu, E. J. Ding, Energy efficient resource allocation in non-cooperative multi-cell OFDMA systems.Journal of Systems Engineering and Electronics 22(1), 175-182(2011).

[11] B. Ma, X. Z. Xie, H. P. Psho, An efficient proactive spectrum handover mechanism in cognitive radio networks. Wireless Personal Communications 79(3), 1-23(2014).

[12] Y. G. Ji, Y. T. Li, C. Shi, Aspect rating prediction based on heterogeneous network and topic model. Journal of Computer Applications 37(11), 3201-3206(2017).

[13] H. J. Sun, H. Zhang, J. J. Wu, Correlated scale-free network with community: modeling and transportation dynamics .Nonlinear Dynamics 69(4), 2097-2104(2012).

[14] A. Q. Bi, S. T. Wang, Transfer Affinity Propagation Clustering Algorithm Based on Kullback-Leiber Distance 38(8), 2076-2084(2016).

[15] X. L. Xiong, L. X. Yang, Y. Z. Ma, Z. B. Zhuang, Alerting algorithm of low-level wind shear based on fuzzy C-means. Journal of Computer Applications 38(3), 655-660(2018).

[16] H. Bo, L. C. Shu, M. M. Yu, Performance evaluation of the Taiwan railway administration. Annals of Operations Research 259(1-2),119-156(2017).

[17] S. Mutereko, F. Ruffin, Public Administration Dilemmas: An Analysis of Teachers’ Perceptions of the Effects of Performance Evaluation in Post-Colonial South Africa. International Journal of Public Administration 41(1), 1-12(2016).

[18] A. J. Million, Indispensable Institutions: Making a Case for Public Libraries as Local E‐Government Service Administrators. Bulletin of the Association for Information Science & Technology 42(2),11-16(2016).

[19] J. H. Li, Y. Lei, Research on the optimization design of public sector performance evaluation based on analytic hierarchy process. Agro Food Industry Hi Tech 28(1),1627-1631(2017).

[20] X. Fan, Research on validity evaluation framework of college internal control based on AHP and FCE. Revista De La Facultad De Ingenieria 32(3), 440-447(2017).

[21] Xie Z., Lin R., Wang J., Hu W. and Miao L.Vicarious Learning: How Entrepreneurs Enhance a Firm’s International Competitiveness Through Learning From Interlocking Director Network Partners. Front. Psychol. Doi: 10.3389/fpsyg.2020.00689(2020).

[22]Y. H. Chang, P. C. Shao, H. J. Chen, Performance evaluation of airport safety management systems in Taiwan. Safety Science 75(5), 72-86(2015).

[23]W. Su, L. Zhao, S. Deng, Developing a performance evaluation model of Organic Rankine Cycle for working fluids based on the group contribution method. Energy Conversion & Management 132, 307-315(2017).

[24]G. Szárnyas, B. Izsó, I. Ráth, The Train Benchmark: cross-technology performance evaluation of continuous model queries. Software & Systems Modeling, 1-29(2017).

[25]M. Shao, Y. Song, B. Wu, The Supplier Selection of the Marine Rescue Equipment Based on the Analytic Hierarchy Process (AHP)-Limited Diversity Factors Method. Polar Biology 20(20), 259-272(2018).

[26]J. Zhang, X. U. Xiu, Ming D, A condition assessment method of power transformers based on fuzzy analytic hierarchy process. Power System Protection & Control 3(75),75-81(2016).

[27]C. Qin, Y. Zhang, Evaluation of the Safety of Mine Road Based on Fuzzy Analytic Hierarchy Process. Journal of Transportation Technologies 07(1), 70-82(2017).

[28]R. Fatchurrahman, H. Putra, I. Joyokusumo, Light sensor selection of Wi-MoLS (wireless modern light sensor) based on analytic hierarchy process (AHP)// Industrial, Mechanical, Electrical, and Chemical Engineering. IEEE, 152-155(2017).

[29]M. Abdel-Basset, M. Mai, Y. Zhou, Multi-criteria group decision making based on neutrosophic analytic hierarchy process. Journal of Intelligent & Fuzzy Systems 33(6), 4055-4066(2017).

[30]C. Xu,A novel recommendation method based on social network using matrix factorization 

technique. Information processing & management 54(3), 463-474(2018).

[31]W. X. Xin, J. G. Hou, L. Y. Ming, Quantitative characterization of vertical heterogeneity of mouth bar based on the analytic hierarchy process and the fuzzy mathematics:A case study of Guan 195 fault block of Wangguantun Oilfield. Natural Gas Geoscience 28(12), 1914-1924(2017).

[32]Z. Huang, J. Tang, G. Shan, J. Ni, Y. Chen and C. Wang. An Efficient Passenger-Hunting Recommendation Framework with Multi-Task Deep Learning. IEEE Internet of Things Journal (2019).

[33]Y. Wang, E. Zio, X. Wei, D. Zhang, B. Wu, A resilience perspective on water transport systems: The case of Eastern Star. International Journal of Disaster Risk Reduction 33, 343-354(2019).

[34]M. Zhang, D. Zhang, F. Goerlandt, X. Yan, P. Kujala, Use of HFACS and fault tree model for collision risk factors analysis of icebreaker assistance in ice-covered waters. Safety science 111(4), 128-143(2019).

Tables

Table 1 Performance evaluation indicators for government managers

 

Primary indicator

Secondary index

Performance evaluation indicators for government managers

Ability

Working attitude 

Conscientiousness

Event handling capability

Innovation ability 

Other capabilities

Organizational management capacity

Capacity for policy analysis

Moral character

Political morality

 Professional ethics 

Ethics and morality

Psychological morality

Autonomy

performance 

Achievements in scientific research 

Daily performance

Winning rate

Diligence

Attendance situation

Load

Work efficiency

Degree of diligence


Table 2 Judgment matrix -








1.0000

1.0321

1.4555

1.2365

1.0000

0.2365


0.6321

1.2236

1.0000

1.0000

1.2568

0.3214


0.6540

1.0000

1.2635

1.3654

1.0000

1.0000


0.8565

0.4526

0.4569

0.7569

1.9635

0.1652


1.0000

0.3251

0.1358

0.5236

1.2365

0.1356

The of the weight coefficient of the judgment matrix is less than 0.1, which satisfies the consistency detection.


Table 3 Judgment matrix -








1.0000

1.0355

1.1351

1.1656

1.0000

0.2235


0.3651

1.2236

1.0000

1.0000

1.0356

0.3261


0.6666

1.0000

1.2635

1.3546

1.0000

1.0000


1.23565

0.4657

0.4566

0.6526

1.1386

0.1352


1.0103

0.3246

0.1324

0.3103

1.1356

1.5686

The of the weight coefficient of the judgment matrix is less than 0.1, which satisfies the consistency detection.


Table 4  Basic information of government administrators

Statistical characteristics

Quantity

Effective percentage

Cumulative percentage

Career

Administration

123

42.76

48.45

Technology

43

14.87

61.56

Rear services

57

38.75

53.23

Working time

Less 1 year 

86

29.44

26.22

1-3 years

83

41.53

65.34

More than 3 years

55

30.54

42.21

Sex

Male

123

71.31

71.21

Female

55

28.54

32.21

Educational background

College and below

32

19.65

19.23

Undergraduate course

82

70.92

70.43

Master's degree or above

43

18.21

43.33

Age

Under 30

54

72.24

72.45

30-40 

43

23.35

92.45

Over 40 years of age

58

4.65

54.33


Table 5. Regression model coefficient table for performance evaluation 

Factors

Standardization coefficient

Collinear statistics

Coefficient

Standard error

Tolerance

Variance inflation factor

Constant

3.432

0.054

-

-

F3(x1)

0.354

0.043

0.545

1.543

F4(x2)

0.532

0.021

0.656

1.212

F6(x 3)

0.345

0.023

0.653

1.554

F7(x 4)

0.233

0.045

0.932

1.432