An academic institute is a system of systems that consist of departments, administration, and external resources as subsystems. These subsystems can be further divided into smaller active subsystems of students, faculties, external industries, placement unit. For active and dynamic subsystems, predicting its behavior for any action is undeterministic. The complex and uncertain operating environment of an institute makes the decision making process dificult using the regular qualitative analysis based approach. This paper presents a digital twin based approach to enable data-driven quantitative analysis to the decision-making process that can provide feedback to the academic institute on various decision options before taking an actual decision. Our approach has used an artificial intelligence concept called Bayesian Network to develop the digital twin of the department to help department-level stakeholders to take qualitative, data-driven, and simulated verified results that help in taking departmental-level decisions. The Digital twin takes input from the department data, and current situational data, that is fed to the department's Bayesian Network and thus provides feedback to the department regarding various decision options available.
Before the advancement of the Industry 4.0 revolution, Artificial intelligence, and advanced data analytics manufacturing, smart city, healthcare and enterprises sectors were solely dependent on qualitative analytics, quality discussions, high authority people’s intuition and field studies to take decisions for attaining goals. However now in this digital era, every sector involves a high level of uncertainty, easy to get influenced by the outside environment and requires smart functioning thus there is a need for every sector to act fast as well as precise in the decision-making process to hold a stand in the market. This section first describes what is Digital Twin and how it being used in various sector. We will discuss some past work on using digital twin in decision making process for enterprises and then we will learn why qualitative approach for decision making is not suited for academic institute and will lay foundation for Bayesian Networks based Digital Twin model for evidence based decision making process.
Digital Twin is a virtual/digital representation of a physical entity with its complete behavior, and operating environment in which both, the physical entity and its digital model is fully https://github.com/PoonamM29 (P. Maheshwari) integrated in real-time with the bi-directional flow of data, and various actions efect. The digital model continuously takes data/action’s efect from the physical entity, user inputs update its domain knowledge adapts to operational changes, performs simulations on the inputs received, and thus provides feedback or forecast to the physical entity. Figure 1 shows the block diagram of Digital Twin that depicts physical entity and digital model connected and communicating data and information to each other. Internet of Things and sensors[1] have provided a large volume of raw data to every sector. This raw data when processed with Artificial Intelligence, data analytics, and data storage[2] facilities, can be made useful for the sectors to gather information and quality insights that can help in data-driven decision-making process. This advancement in technology[3] has paved way for the Digital Twin technology to be widely used in manufacturing, Smart city, Healthcare, and Enterprise sectors. [4]. Digital Twin was first used in the Aerospace industry[4]. In the manufacturing sector, with the technology advancement, real-time data can be sensed and sent from the machines to the digital twin, which then uses data analytic tools to help in the predictive maintenance of machines[5]. Manufacturing processes can also be monitored and using digital twin simulation results processes can be made more reliable, to get maximum production[6]. In the healthcare sector[7], the digital twin concept is paving way for robotic surgery, and patient monitoring. The digital twin of a human being is the fullest use of this concept in the healthcare sector. Cities are known to be a complex eco-system of systems. Few digital twin experiments have been implemented on a city subsystems including transportation[8], and farms[9][10]. A digital twin of city infrastructures like buildings, trafic signals, water lines, and power grids and its simulation results, are useful in visualizing and analyzing in improving livability, and sustainability. One can use the digital twin to monitor and maintain a city’s infrastructure. The transportation system is also implementing digital twin technology to avoid accidental hazards, trafic jams, and emergency route/service help.
In recent years, research is done to apply the Digital Twin methodology in the enterprise sector[11]. Paper[12] illustrate how using modeling, simulation and reinforcement learning an enterprise can be made adaptive. Currently, decision-making for an enterprise solely depends on a qualitative approach like discussions among senior organization members and experts’ intuitions. No or little quantitative data-driven approach is utilized in making future decisions. Thus, sometimes a decision’s outcome is not in favor of the enterprise’s goals. Therefore, for the enterprise, one of the major challenges in today’s world is to have a decision-making process that is more data-driven, can be rigorously analyzed for various what-if/if-what situations before implementation in actuality, can encompass the uncertainty and dynamic behavior involved in the working environment, and provide some real simulation based feedback to the enterprise. Previously some work on the organisational decision making is done using actor-agent based simulations[13]. This work involves prior knowledge of the behavior of the enterprise and its subsystems for modeling the digital twin.
We have taken academic institute’s department as an enterprise for which various decisions are being taken by the administration of the department, stakeholders, and faculty. To understand the department’s dynamic behavior, uncertainty, and input-output variables, let us take one example. The department sets a goal to raise funds. For this example, extra funds raised is an output variable. To achieve this goal, the department decides to start a few online executive programs, which can be considered as an input variable for this case. Introducing several online executive programs will raise extra funds however introducing beyond a certain number of online executive programs will afect faculty time management for research work that will in turn impact research quality and research papers submitted by the department. Similarly, it can also afect the department’s regular academic courses and thus other qualitative variables associated with academics like department’s perception to outside world, placements statistics and student satisfaction. One decision may have positive impact on some goals and can lead to a negative impact on other goals. The above example depicts how various variables are dependent and provide uncertainty.
Thus, it is a need for modern institute to have a data-driven approach for decision-making and before the implementation of a decision what-if/if-what analysis results can be obtained and evaluated. For multiple dependency and uncertainty, the Bayesian Network[14] based model provides probabilistic reasoning for the decision-making process. In this approach, Bayesian Network is created with input-output variables as nodes, dependency among these variables is depicted using a directed acyclic graph, and using past and current data Bayesian Network learns the values of its variables and dependency behavior i.e. positively or negatively dependent. Once the Bayesian Network is created then various what-if/if-what analyses could be done using AI inferences. This is a data-driven approach to the decision-making of an enterprise.
Consider an educational institute’s subsystem department that aims to achieve more research paper publications then previous year publications. To achieve this goal institute has to take few decisions. Few such decisions could be like faculty spending more time to research work, more number of research scholar, more number of hours spent by scholars on research work, more international conferences supported by the department, and more high end research equipment. If the institute takes the decision of faculty spending more time on research work then it would directly afect teaching hours of a faculty and will thus hamper the academic area of the institute, and other administration related work of the faculty. Similarly, if the institute decides to have more number of conferences/international travel then it will afect the institute’s ifnances to support other goals, funds for high end equipment and many other quantitative as well as qualitative factors of the institute. The above example again helps to shows how department’s defining variables are dependent to each other with high level of uncertainty and have dynamic behavior and working environment[13].
To define the problem statement mathematically, 1, 2, 3, .. are diferent dependent or independent events/variables of a department. Multiple events occur at the same time and thus afects other events. So, given the department data for these events, a model is needed to learn from this data and create a complete numeric probabilistic reasoning model for the case when all events occurs at the same time. Thus, problem statement for the paper is to develop a mathematical model that can give compute ( 1, 2, .. ) by self learning from the data provided and subsequently helps in providing feedback for various what-if/if-what analysis to the department. For this Bayesian network based digital twin is being designed and developed which is discussed in the next section.
In this section, we present a brief about Bayesian Networks. Then we depicts how Department can be modeled using Bayesian Network.
Bayesian Networks[14] represents probabilistic graph based model of an uncertain domain. In this, all the random variables are considered as nodes of the graph. Directed link between two nodes defines dependency among them (Parent-child). Joint probability is a way of calculating the likelihood of all the variables occurring together. Joint probability distribution of Bayesian network is given as, =1 ( 1, 2, .. ) = ∏ ( | (
)) ( ) = ∑ ( 1, 2, .. ) =1,≠ 1
) ( ) =1,≠, ∑ ( | ) = (
( 1, 2, .. ) (, , ) = (|, ) () () Here represents random variables.
According to the Total Probability rule, if the probability of an event is unknown then using
marginalization over all other events in the joint probability distribution one can calculate
marginal probability of an event. Mathematically, to calculate ( ) total probability law states,
(
Similarly, using joint distribution and total probability law, conditional probability can be calculated as, ( 1
) Here,
is a normalization constant.
Thus with full join probability distribution we can infer probability distribution of any variable under any conditional circumstances or no evidences given situation. depends on two independent events and .
Joint probability of the figure 2 Bayesian network is given as,
To infer probability of event , equation (
So far we have understood that for a domain that involves a high level of uncertainty, and consists of highly interrelated variables the probabilistic reasoning approach serve the best for the decision-making process. Figure 3 depicts a block diagram of the abstract level modeling of the department using the Bayesian Network. In the department model, nodes of the network are input and output variables of the department. For the model to learn, here, synthetic logical data is fed. Once, the model learns from the data we can provide input numerical values to the model via input variables. Input variables of a department are selected after discussion with the department’s higher authorities. These variables define or characterize a department. Then the model using joint, total, and conditional probability, technically termed as inferences, provides numerical valued outputs. Thus, by providing diferent sets of input variables, the model can be utilized for rigorous what-if/if-what scenarios and provides data-driven feedback for each set of input variables. The concerned authority can choose or alter the set of input variables that is most likely to produce output variables helping in achieving the goals.
A department has various quantitative as well as qualitative output variables. For the model, the most interesting and important output variables for the department’s growth are chosen. Few important qualitative variables are satisfaction level, and Research Skills that can be used to characterize the department. Using the proposed approach, the qualitative variables can be analyzed numerically. Table 1 contains important department’s input variables and table 2 contains important department’s output variables.
Using the input and output variables let us understand how Bayesian Network of the department is created. In general, Bayesian networks, for the department’s model, are created using the empirical understanding of the department, discussion among higher authorities, and logical dependencies of diferent variables on an output variable. An output variable of interest can be directly influenced by input variables and other output variables. There are also indirect logical dependencies on input variables that influence variable of interest via other output variables. For precise results from the Bayesian Probabilistic approach, instead of creating a whole Bayesian network of the department, this methodology has created Bayesian networks using variables that are closely related/ or afecting each other. In the subsequent networks, rectangle shaped node is an input variable and oval shaped node is an output variable. A short acronym of the variable is mentioned on top of its node.
The figure 4 Bayesian network depicts the output variable Placement statistics and student satisfaction are dependent on inputs like number of faculty members, research labs, etc and other output variables like student’s self study hours, student’s free time, college support for international conferences, etc. All inputs and outputs have positive impact on the Placement statistics and student satisfaction output. Equation (7) is the Joint Probability of the complete network.
The figure 5 Bayesian network depicts how the output variables Research Skills and Research Papers per faculty are dependent on other input variables like number of research labs, research students count, etc and output variables like research hour by student and faculty, number of academic visitors, etc. All inputs and outputs have positive impact on the Research skills and Research Paper output. Equation (8) is the Joint Probability of the complete network. ( ) = ( | , , , , , , )∗ (| , , , , , ) ∗ ( ) ∗ ( )∗
( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ () ∗ ( )
The figure 6 Bayesian network depicts how the output variables Faculty Time and Student Time are dependent on other input and other output variables. Here inputs Diploma program and Executive program have positive impact on Faculty teaching hour and at the same time have negative impact on Faculty Research hour. Similarly, more number of conferences and Academic visitors have negative impact on self study hour but at the same time have positive impact on student research hours. Here, one independent variable afects in a trade-of manner to two diferent time output. One of the hidden aspect of this approach is that through the learning data, network itself learns positive or negative co-relation between dependent variables. Equation (9) is the joint probability of faculty time management network and (10) is the Joint Probability of the student time management network. ( ) = ( | , , ) ∗ ( | , , )∗
( | , , ) ∗ ( ) ∗ ( ) ∗ ( )
The figure 7 Bayesian network depicts how the output variables International Travel Support and conferences by the department are dependent on other input and other output variables. All the funding inputs have positive impact and expenses input have negative impact on both of the output. Equation (11) is the Joint Probability of the complete network. ( ) = ( |, , , , , ) ∗ ( |, , , , , )∗ () ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) (11) (8) (9) (10)
The figure 8 Bayesian network depicts how Faculty Satisfaction is dependent on other input and other output variables. All the inputs have positive impact except too many programs as it may lead to less satisfaction due to less time on other important work. Equation (12) is the Joint Probability of the complete network. ( ) = ( | , , , , , , , , )∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) ∗ ( ) (12)
The Bayesian Networks are fed with the data tables that work as prior knowledge to the networks. For a Bayesian Network, the corresponding data table includes columns referring to each node of the network and rows have categorized values as shown in table 3. For example, for a variable number of research projects, a value of 0 signifies below an average count of projects under the department. Using learning or estimation algorithms like Maximum likelihood estimation the network learns the conditional probability of all the nodes. Using AI inferences, for example, Variable Elimination, the above conditional probability is used to infer posterior probabilities and thus do if-what/what-if analysis.
This section demonstrates the experimental findings of the Bayesian Network based model and how to do inferences from them. For these simulations, python language is used. Please note for this work, collecting data from manual records of the institute, and the department was a practical challenge. However an organisation using enterprise resource planning system can collect data and fed it to the Bayesian Network based model. Thus, below simulations have used synthetic data that are created with a logic of positive/negative dependency on each other variables.
First Simulation is done by giving no inputs to the network that means no condition for input variables and simply learning from the data and thus giving joint probabilities of the output variables. Table 4 showing probability distribution for 3 categories.
From this simulation case 1, concerned authority can interpret that without taking any actions the institute will continue to attain below pointers for its output variables:• Average number of seminars, and workshops. • With decent support for international travel, department might be more inclined towards research side with good research skills and publications. • Though this scenario might be too busy for students and faculty. • Placements might be below average with mixed satisfaction from the faculty and the students.
For the second case Table 5 is provided as the input variables to the network. Please note these values will work as condition or action taken by the authority and inference will be read as probability of a variable given these conditions.
In this simulation, input is given in a COVID-19 situation with less expenses, more research funds and projects, average staf, average new programs.
Table 6 is the observations for the output variables for the simulation case 2. Below points can be inferred by the concerned authority if actions are taken in accordance to table 5 inputs:• Quite good number of seminars, workshops. • With much support for international travel, department might be totally inclined towards research side with very good research skills and publications.
• Though this scenario might be too busy for students and faculty as max time will be spent on research work. It might observe a balance with student time distribution between studies and research work. • Placements might be average with quite good satisfaction from the faculty and the students.
For the third case table 7 is provided as the input variables to the network. Please note these values will work as condition given or actions taken by the authority and inference will be read as probability of a variable given these conditions.
In this simulation, input is given as more expenses, less overall funds and projects, less staf and students, introducing new programs.
Table 8 is the observations for the output variables for the simulation case 3. Below points can be inferred by the concerned authority if actions are taken in accordance to table 7 inputs:• Average number of seminars, workshops. • With complete support for international travel, department might be totally inclined towards research side with very good research skills and publications • Though this scenario depicts less research time by the faculty and more research study by students. Faculty teaching hour are more than average in this case. • Placements might be below average with quite good satisfaction from the faculty and the students.
Decision makers can use these simulations for various if what/what-if scenarios. A learned Bayesian Network can be subjected to various combinations of input variables and the model using AI inference methods will provide a posterior probability of the output variable of interest. If the output variables value aligns with the goals then decision makers have an evidence based action to take in order to attain the required goals. An institute with accessible data can utilize this method for evidence based decision making process.
This paper has proposed a Bayesian Network based approach to model a department, and its variables. Through simulations, we can conclude that if valid data is provided to the network based model then the network variables learn themselves and can also learn positive/negative dependency among other variables. This approach does not require prior knowledge of the complex behavior of the system thus making an academic institute’s decision-making process more adaptive and data-driven. Using AI inference methods decision options can be analyzed for various what-if/if-what scenarios. For Bayesian Networks to provide valid results, correct and suficient data is required for proper learning. This approach can further be enhanced with the inclusion of events, dynamic behavior modeling of the system, and leveling up the model for a complete institute.
Thanks to Dr. Souvik Barat, Abhishek Yadav and Dushyanthi Mulpuru for the continuous and helpful guidance throughout the process of learning. [3] Aidan Fuller, Zhong Fan, Charles Day, Chris Barlow, Digital twin: Enabling technologies, challenges and open research, IEEE Access 8 (2020) 108952–108971. doi:10.1109/ACCESS. 2020.2998358. [4] Fei Tao, He Zhang, Ang Liu, A. Y. C. Nee, Digital twin in industry: State-of-the-art, IEEE Transactions on Industrial Informatics 15 (2019) 2405–2415. doi:10.1109/TII.2018. 2873186. [5] Zheng Liu, Norbert Meyendorf, Nezih Mrad, The role of data fusion in predictive maintenance using digital twin, in: 44th Annual Review of Progress in Quantitative Nondestructive Evaluation, Volume 37, volume 1949 of American Institute of Physics Conference Series, 2018, p. 020023. doi:10.1063/1.5031520. [6] Werner Kritzinger, Matthias Karner, Georg Traar, Jan Henjes, Wilfried Sihn, Digital twin in manufacturing: A categorical literature review and classification, IFACPapersOnLine 51 (2018) 1016–1022. URL: https://www.sciencedirect.com/science/article/ pii/S2405896318316021. doi:https://doi.org/10.1016/j.ifacol.2018.08.474, 16th IFAC Symposium on Information Control Problems in Manufacturing INCOM 2018. [7] Tolga Erol, Arif Mendi, Dilara Dogan, The digital twin revolution in healthcare, 2020, pp.
1–7. doi:10.1109/ISMSIT50672.2020.9255249. [8] Freddy Lécué, Robert Tucker, Simone Tallevi-Diotallevi, Rahul Nair, Yiannis Gkoufas, Giuseppe Liguori, Mauro Borioni, Alexandre Rademaker, Luciano Barbosa, Semantic trafic diagnosis with star-city: Architecture and lessons learned from deployment in dublin, bologna, miami and rio, in: SEMWEB, 2014. [9] Seng-Kyoun Jo, Dae-Heon Park, Hyeon Park, Sehan Kim, Smart livestock farms using digital twin: Feasibility study, 2018 International Conference on Information and Communication Technology Convergence (ICTC) (2018) 1461–1463. [10] Neda Mohammadi, John Eric Taylor, Smart city digital twins, 2017 IEEE Symposium Series on Computational Intelligence (SSCI) (2017) 1–5. [11] Souvik Barat, Vinay Kulkarni, Tony Clark, Balbir Barn, An actor-model based bottomup simulation — an experiment on indian demonetisation initiative, in: 2017 Winter Simulation Conference (WSC), 2017, pp. 860–871. doi:10.1109/WSC.2017.8247838. [12] Vinay Kulkarni, Souvik Barat, Tony Clark, Towards adaptive enterprises using digital twins, in: Proceedings of the Winter Simulation Conference, WSC ’19, IEEE Press, 2019, p. 60–74. [13] Souvik Barat, Actor based behavioural simulation as an aid for organisational decision making. phd thesis, middlesex university. [thesis], 2018. URL: https://eprints.mdx.ac.uk/id/ eprint/26456. [14] Donald Bren School of Information and Computer Sciences University of California, Irvine, Understanding bayesian networks, 2012. URL: https://www.ics.uci.edu/~rickl/courses/ cs-171/2012-wq-cs171/2012-wq-cs171-lecture-slides/2012wq171-17-BayesianNetworks. pdf.