**4. Discussion**

The work proposed in this paper presents some methodological achievements in the field of beehive keeping control thanks to electronic data and remains in progress. It included the data chain from information obtained using IoT devices, workflows in the form as BPMN models, and triggering events for those models based on patterns detected in incoming data. The model-to-model approach is under development. The model transformation is not automatically done yet, but testing over pilot hives in France and Lebanon provided encouraging feedback. Moreover, the final implementation of the main key performance indicators is still under discussion.

In the context of driving and automating model transformation, authors identified several approaches, such as model driven development (MDD) within the framework for modeling simulation (MDD4MS) [34], the model driven service architecture (MDSEA [61]), the model driven interoperability for system engineering (MDISE [28]), and in this domain, "Beeomatics" [31], that can guide conceptual domain models to formal and executable models. The targeted formal models can be either used for simulation or execution of the models. As a result, the framework will integrate a transformation of BPMN models into execution and simulation models based on previous research in this domain to simulate and orchestrate/execute process models.

In any case, the interoperability will still be considered as crucial either for data or models since data can be heterogeneous, and process can integrate different data sources. The interoperability of processes will aim to make various processes work better together. These processes will clearly define in which order services (functions) are to be executed according to the business rules [62].

As a first perspective, models are required to clearly capture the decision to be taken. For instance, the Object Management Group offers several languages that are compliant and complement BPMN onto specific features. Thus, let us mention Decisional Model Notation (DMN—OMG 2015) [63], allowing to model and represent decision and business rules within an organization. This notation is usable with BPMN and intended to be usable by businesspeople and technical people as well. In the frame of the managemen<sup>t</sup> of a beekeeping exploitation, it will be interesting to build a set of business rules fully readable by business users and combine this kind of language with BPMN allowing to design, describe and automatize decision within a process. The DMN model will be used to pave the way and better formalize decisions in the target execution model. Moreover, the automatic model discovery and process mining will be considered as a path to capitalize on process models from historical data regarding domain practices.

Then, this work will integrate some tailored simulation code to run the dynamic animation of the BPMN model, in order to help users when facing risk in the hive. It will be proposed for a didactic purpose and decision support [64]. Considering simulation as another target model, the model-to-model transformation from BPMN as a conceptual modeling language to DEVS as a simulation model specification appears promising to run simulation and provide user decision support before choosing an action to perform. We propose to inscribe these works in open-source development frames.

The system provides recommendations for actions to be carried out to optimize the monitoring, management, and production of all apiaries. These recommendations are based on macroscopic events that originate from multiple sources of information constituting the data model, and from a behavioral model (BPMN) describing the activity of managemen<sup>t</sup> of the apiaries. The events considered by the model can be the result of an aggregation (multicriteria) of the data collected from apiaries and from environment (weight, humidity, temperature, weather data, geographical data, video of apiaries, ...), which may be the result of business experience or learning process or both.

In addition, and as part of the future work, the apiarist will be able to choose a predefined workflow which best fits his needs or build a new one from scratch. More, beekeepers will have the choice to work in a collaborative environment where they can share their experience with local and international apiarists. The flowering and vegetation maps will be established in a collaborative way by the beekeepers of each region who will provide their own observations. The server will transform the collected data into a cartographic representation. In fact, the collaboration environment will be considered as a win-win situation since the user can benefit himself and transfer his expertise and useful information to local or even international beekeepers as well.

This cooperation will strengthen and improve practices while the system will be designed in such a way to preserve privacy for all participants. Moreover, due to multiple data sources (e.g., relative humidity, relative temperature, weather, image, sounds, etc.) and rich database system, the simulation feature will enrich the apiarist's experience and help him to manage his stock by forecasting his needs for supplies and of course will give him an eye on the production and profit. The modeling and simulation will also enhance the system's performance as far as countermeasures to be taken, based on similar previous scenarios in the past.

For now, inputs are mostly composed of hives' weights. Other information, such as weather, ambient temperature, internal hive temperature and hygrometry, and flowering, coming from the web can be added to complement the source of inputs and provide greater insight and confidence regarding the patterns of events that trigger the process models. The functioning of used IoT and extracted data format are fully known at this stage to show the usability of the approach. In the end, the final proposed application will have to allow different IoTs to inject their own data into models. Generic and interoperability mechanisms will have to be provided to allow users to exploit their own IoT and data formats without interfacing effort.

Moreover, the gamification concept will be pushed to its extreme by allowing different apiarists to share their problems, post solutions, trade ideas, and interact one with another. In fact, a rich collaborative data base collection will enhance the system's performance regarding simulation and will improve the decision making by proposing more accurate response to problems occurring inside the hives. Such a system will promote cooperation within national and international beekeepers' communities which will contribute to growth in the field.
