7th International Conference on Green Computing and Engineering Technologies (ICGCET®)

22 Sep - 23 Sep 2021

Universidad Nacional Federico Villarreal, Lima, Peru

Digital transformation in industrial fishing

Pedro Lezama1, Ciro Rodriguez2,, Joe Mendoza3, Jorge Mayhuasca4,
, Iván Petrlik5,

1,2,3,4,5
National University Federico Villarreal, Lima Perú
1
[email protected], [email protected], [email protected],
4
[email protected], [email protected]

Abstract

The objectives of this research work were to determine the degree of improvement in the
efficiency of digital transformation, effectiveness in fishing extraction and performance and
benchmark in the implementation of digital transformation in fishing extraction processes. A
proposal of a digital transformation model was shown and the results were the product of the
comparative analysis of the last 4 years of fishing, due to the changes between fishing seasons.

Keywords—M-Learning, model, methodological strategies, learning

1. Introduction

a) Description of Problem
The FAO in its latest report stresses that "society is faced with the enormous task of providing food
and livelihoods for a population that will exceed 9 billion people by the middle of the 21st century, while
at the same time solving the problem of the disproportionate effects of climate change and deterioration
in the state of the environment as a resource base". [1].
Fish is the largest segment of the food market. "fish consumption accounts for 16% of the total
amount of animal protein consumed in the world." [1] This assessment of the global fish market is
provided by Jürgen Vogele, director of the World Bank's Agriculture and Ecological Services Department.
Industrial fishing despite COVID 19, contributed 1.5% of GDP in 2020, Fishing industries manage
their processes using SAP as the main ERP, however, the extraction process is controlled through
customized developments (web and mobile applications), having a delay in data integration, and therefore
in decision making.
These industries also do not have an end to end management of the extraction process, they only
focus on complying with the quotas granted by PRODUCE (Peruvian fishing regulator), sometimes
causing overfishing and threatening fish stocks, especially anchoveta.

1
International Journal of xxxxxx
Vol. x, No. x, xxxxx, 20xx

b) Adapting to technological change

Emerging technologies, leveraging the ubiquity of cell phones and tablets, cloud computing,
blockchain, have the potential to contribute to data collection. Automating and empowering data
processing and analysis, employing business intelligence and analytics tools facilitate the communication
of results to relevant stakeholders [2].
Technology can also be used to expand the distribution and accessibility of data to decision makers,
enabling them to optimize fishing based on the best available information and transforming unidirectional
flows of information (fleet to manager) into a collaborative and mutually beneficial cycle of data
collection, synthesis and sharing.
Adapting organizations from siloed organizational approaches to process-oriented, indicator-based
management, agile and value-oriented approaches are objectives that have not yet been fully implemented
in fishing companies.
The digital transformation allows a gradual change in fishing companies, allowing an effective use
of new technologies and their progressive adaptation in the organization.

c) Objectives

• Determine the degree of improvement in operational efficiency (vessel use, fuel use, cycle time)
by implementing digital transformation in harvesting processes.
• Determine the degree of improvement in harvesting efficiency (quota advancement, fish quality,
quota compliance per fishing trip and per season) by implementing digital transformation in
harvesting processes
• Determine the degree of improvement in performance and benchmark (top 6 industrial fishing
companies) by implementing digital transformation in harvesting processes.

2. Materials and methods

In the research "Opportunities to improve fisheries management through innovative technology and
advanced data systems" provides an overview of the current status and challenges of technologically
advanced data systems in the fisheries extraction process, and proposes a solution to guide greater use of
technology, with the aim of improving fisheries performance [3].

2
 7th International Conference on Green Computing and Engineering Technologies (ICGCET®)
22 Sep - 23 Sep 2021
Universidad Nacional Federico Villarreal, Lima, Peru

Conceptual diagram of fishery-dependent data collection systems using traditional systems (top)
Fig. 1.
and the use of high technology (bottom).

3. Proposal development

Next, we will show the conceptual diagram of the proposed digital transformation model based
on the improvement of the management process by indicators.

a. Digital transformation model proposal

Fig. 2. Proposal of the digital transformation model

b. Description of the digital transformation model

The following table shows the respective summary of the digital transformation model:

RE EXTERNAL RESPONSIBLE, It is the maximum

responsible for defining the terms of the fishing season.
Includes authority and veto right.
RI INTERNAL RESPONSIBLE, Responsible for defining
the daily strategy that the organization will employ in the
extraction of anchovy. (R)
MAC MONITORING ALERT AND CONTROL, He is the
maximum responsible in the control of the fulfillment of
the goals and alerts the casuistry found every day in the
different mobile devices, tablets, web applications and
blockchain. (A)

TABLA I. RESPONSIBILITIES DEFINED IN THE DIGITAL TRANSFORMATION MODEL

asks of the persons in charge

• RE is responsible for:

o Evaluating whether the sea state is conducive for fishing.

o Defining the date on which the two fishing seasons begin.

3
International Journal of xxxxxx
Vol. x, No. x, xxxxx, 20xx

o Defining the number of days of operation.

o Defining fishing quotas.

o Define the size of the fishery.

• RI is responsible for:

o Directing the evolutionary strategy of the daily fishing.

o Carrying out fishing plans.

o Carrying out fuel plans.

o Making the fishing chronogram.

o Define the sea route.

• MAC is responsible for:

o Monitoring fuel consumption.

o Monitoring the capacity of the vessel.

o Monitoring the quality of the catch.

o Alerting long unloading times.

o Alerting long waiting times to set sail. o Alerting long waiting times to set sail. o Alerting
long waiting times to set sail.

Detail of the tasks

Assessing the state of the sea

The Peruvian Ministry of Production carries out an evaluation of the state of the Peruvian sea and
defines the areas reserved for artisanal and industrial fishing.

Define season start date

The Ministry of Production defines the start date of the season after the exploration of the Peruvian
sea where it is verified that it is in conditions of exploitation. This procedure is carried out twice
a year, in the Peruvian sea there are two extraction seasons.

Define Quota and magnitude of fishing

The Ministry of Production defines the fishing magnitude after the evaluation of the Peruvian sea.
This magnitude allows the rational exploitation of these hydrobiological resources.

Define days of operation

The ministry of production defines the days of the season allowing the rational exploitation of
these hydrobiological resources.

Define evolutionary strategy

The organization defines a flexible evolutionary strategy for each fishing day because fishing is
volatile. It takes into consideration the three fishing plans, fuel plans, vessel conditions, trip

4
 7th International Conference on Green Computing and Engineering Technologies (ICGCET®)
22 Sep - 23 Sep 2021
Universidad Nacional Federico Villarreal, Lima, Peru

schedules, waiting times for unloading the catch, the time it takes to unload the catch, and the
time it takes to wait before setting sail.

Define Fishing Plans

The organization defines three fishing plans, which allows you to visualize each day the status as
the vessels report (favorable plan, intermediate plan, unfavorable plan).

Define Fuel Plans

The organization defines the fuel plans allowing you to make the plans flexible among the vessels
according to their daily consumption and how much they have fished during the season.

Make the trip schedule

The organization defines the trips that the boats will make according to the weather, sea
temperature and the fishing season they are in. To make the schedule more flexible due to
navigation setbacks, GPS data is taken from the boats.

Defining the maritime route

The organization defines the fishing route in the areas where the Ministry of Production allows
it, taking into account historical data and experience of the fleet when defining the route where
the anchoveta shoals are found.

Monitoring fuel consumption

The organization monitors the daily consumption of each vessel and the capacity of the vessel's
hold. It analyzes fuel consumption per ton fished and distributes the information on the maritime
route taken by the vessel so that the evolutionary fishing strategy can be redefined.

Monitor the vessel's hold capacity.

The organization monitors the free space of the vessel's hold, if the quantity fished is appropriate
the RSW (refrigeration) is used due to the higher fuel consumption, but also ensures the quality
of the anchoveta. Likewise, the sensors in the hold calculate the tons caught.

Monitoring the quality of the catch

The organization monitors the quality in which the anchoveta arrives at the port, dividing it into
standard, prime and super prime. When a vessel arrives and fills more than 60% of its hold, it
is decided to use the cold system (RSW) to maintain the highest quality.

Monitoring of fishing zones

The vessels have sensors, GPS and satellite communication, allowing to know the areas with
schools of anchoveta, this allows to alert better fishing areas than those drawn at the beginning
of the season in the schedule of trips, to comply with the fishing plan.

Alerting of waiting time for unloading

The organization monitors the waiting times for unloading in the ports and can divert the
unloading in another port if it is not favorable.

Alerting of unloading times

5
International Journal of xxxxxx
Vol. x, No. x, xxxxx, 20xx

The organization monitors vessel unloading times, sensors in the port unloading area send an
alert to the vessel when unloading is completed and the actual tons unloaded at the port is
declared.

Alerting waiting times for departure

The organization monitors the time it takes for vessels to depart after anchovies have been
unloaded.

Relationships of tasks and responsibilities

Process Tasks RI MAC
Define fishing plans in three tonnage scenarios R/A I
Define fuel consumption plans R/A I
Define the maritime fishing route R/A I
Make the fishing trip schedule R/A I
Monitor fuel consumption I R/A
Monitor vessel's hold capacity I R/A
Monitor the quality of the catch I R/A
Monitor fishing zones I R/A
Alerting long unloading times I R/A
Alerting long waiting times to set sail I R/A
Alerting long waiting times for unloading I R/A

TABLA II. PROCESS TASKS AND THEIR RELATIONSHIP TO RESPONSIBILITIES

4. Results
a) Fishing extraction results for the last 4 years

The analysis is a comparison of the result of the last 4 years of fishing, due to the changes in the weather
between the first and second fishing season, the analysis is divided in two: Season-I and Season-II of the
last 4 years.

Progress of tons fished

Fig. 3. Tons fished advances

6
 7th International Conference on Green Computing and Engineering Technologies (ICGCET®)
22 Sep - 23 Sep 2021
Universidad Nacional Federico Villarreal, Lima, Peru

According to Fig. 3, the following was observed:

• In the last 4 years, the goal was reached with the exception of 2017, which only reached
80.9%, narrowly missing the minimum established of 80%. The traffic light for the
years 2019, 2018 and 2017 is the comparison with the year 2020 and the average of the
3 years, which is in compliance with what was established.
• In the year 2020 it is observed how the target of 407,813TN (tons) was met and
exceeded.
• The bar graph shows the amount of tons fished. Each year is different due to the quota
assigned by the Peruvian Ministry of Production.

Fuel consumption

Fig. 4. Fuel consumption

Fuel consumption GL/TN

Fig. 5. Fuel consumption GL/TN

According to Fig. 4 and Fig. 5, the following was observed:

7
International Journal of xxxxxx
Vol. x, No. x, xxxxx, 20xx

• Fuel consumption in 2020 is 1.845 million gallons, which is below the consumption of previous
years; however, fuel consumption is linked to the quota that the company must fish, which can
be seen in the advance graph of tons fished.

Advancement of vessel performance

Fig. 6. Advancement of vessel performance

According to Fig. 6, the following was observed:

• Increasing performance in 2020 compared to previous years.

Analysis by vessel size

The last 5 years of the fishing season-I are observed.

Fig. 7. Report of the last 5 years of the fishing season-I

According to Fig. .7, the results of the digital transformation are seen in 2020, we visualize a slight
reduction in cycle time.

8
 7th International Conference on Green Computing and Engineering Technologies (ICGCET®)
22 Sep - 23 Sep 2021
Universidad Nacional Federico Villarreal, Lima, Peru

Tons fished for the season - II

Fig. 8. Season progress - II in tons of fish caught.

Advancement of vessel performance

Fig. 9. Vessel performance report

Fuel consumption

Fig. 10. Fuel consumption report

9
International Journal of xxxxxx
Vol. x, No. x, xxxxx, 20xx

Fuel consumption GL/TN

Fig. 11. GL/TN Fuel Consumption Report

Analysis by vessel size

The last 5 years of the fishing season-II are observed.

Fig. 12. Analysis report by vessel size

Next, we are going to show the dictionary of key words regarding the fishing process:

Cycle time: It is the average time it takes for a vessel, waiting in port, unloading the catch and the time
it takes to set sail again.
Number of trips: The number of trips made by the vessels as a whole.
Hold capacity: The storage capacity of the vessels as a whole, expressed by the number of trips.
Fuel consumption Gl/h: It is the fuel consumption per hour of the vessels.
Fuel consumption Gl/TN: Fuel consumption per tons fished.

10
 7th International Conference on Green Computing and Engineering Technologies (ICGCET®)
22 Sep - 23 Sep 2021
Universidad Nacional Federico Villarreal, Lima, Peru

5. References

[1] FAO, 2018. El estado mundial de la pesca y la acuicultura”. Roma, Italia.

[2] Mnatsakanyan, A. G., & Kharin, A. G. (2021). Digitalization in the context of solving ecosystem problems
in the fishing industry. IOP Conference Series.Earth and Environmental Science, 689(1)
doi:http://dx.doi.org/10.1088/1755-1315/689/1/012008.
[3] Bradley, D., Merrifield, M., Miller, K. M., Lomonico, S., Wilson, J. R., & Gleason, M. G. (2019).
Opportunities to improve fisheries management through innovative technology and advanced data
systems. Fish and Fisheries, 20(3), 564-583. doi:http://dx.doi.org/10.1111/faf.12361
[4] B. Hitpass, “BPM: Business Process Management: Fundamentos y Conceptos de Implementación”.
Santiago : BHH Ltda.-Santiago de Chile, Cuarta Edición 2017.
[5] E. Igarza, “Efectos de la Aplicación del M-Learning en el Desempeño Académico de los Estudiantes del
Curso de Matemática de la Facultad de Ingeniería de Sistemas e Informática”. Universidad Nacional de
San Martín-Tarapoto, 2018.
[6] F. Luna, “Desarrollo web para dispositivos móviles: Herramientas para diseñar y programar WebApps”.
Buenos Aires, 2016.
[7] M. Trujillo, J. Correa “Planeación estratégica de tecnologías de informáticas y sistemas de información”.
Luis Fernando Escobar Velásquez. Primera edición. s.l. : Editorial Universidad de Caldas, 2007.
[8] Otero Escobar, Alma Delia. 2014. Modelo de aprendizaje móvil abierto para educación superior.
Veracruz : s.n., 2014. Tesis Doctoral.
[9] Ubalde, R., Rodriguez, C., Petrlik, I., Esenarro, D., Lezama, P. and Sotomayor, J., 2020. Quality model for peruvian
microenterprises of a software product factory. Test Engineering and Management, 83, pp.13434–13441, ISSN: 0193-
4120

[10] Rodriguez, C., Lezama, P. and Freddy, K. and Chavez, D., 2020. Bayesian model to determine genealogical links of
family descendants. Test Engineering and Management, 83, pp.17937–17946, ISSN: 0193.4120
[11] Falcón, J.C.B., Rodriguez, C.R. and Vargas, D.E., Real time facial expression recognition system based on deep learning.
International Journal of Recent Technology and Engineering (IJRTE), 8(2S11), p.4049, ISSN: 2277.3878.
[12] Levy, J., Pandey, B., Chowdhry, B. and Rodriguez, C., 2020. Prologue: Recent trends in computer science and
engineering (RTCSE). 3C Tecnología. Glosas De Innovación Aplicadas a La Pyme, 19– 25. Recuperado a partir de
https://ojs.3ciencias.com/index.php/3ctecnologia/article/view/991

11