JRSSEM 2022, Vol. 01, No. 7, 922 – 930

E-ISSN: 2807 - 6311, P-ISSN: 2807 - 6494

DOI : 0.36418/jrssem.v1i7.113

DESIGN AND BUILD SMART AGRICULTURE USING

COGNITIVE INTERNET OF THINGS (C IOT)

Aries Dwi Indriyanti*

Informatics Engineering Department, of Engineering Faculty, Surabaya State University

e-mail: ariesdwi@unesa.ac.id

*Correspondence: arie[email protected].id

Submitted: 30 January 2022, Revised: 10 February 2022, Accepted: 20 February 2022

Abstract. In Indonesia, agriculture is required to be able to develop growth in the region and be

able to produce agricultural products that have high competitiveness while also empowering the

community. IoT, or commonly known as the Internet of Things (Internet of Things), allows us to

connect to various things. For example, we can use a smart farm. This research leads to the

implementation of a plant sprayer that uses the Cognitive internet of things that can be integrated

into farmers and factories whose raw material uses corn. This irrigation system uses a NodeMCU

microcontroller, automatic discharge using a DC water pump, a soil moisture sensor using a

capacitive soil moisture v.2 sensor. The system used uses fuzzy logic algorithms as data processing.

The sensor data shows the 70% soil moisture value displayed on the smartphone so that the system

will water or not automatically until the soil moisture value is as needed. Soil moisture in this system

is in 3 criteria, namely dry, normal, and wet. Watering produced by this system with an average

time duration of 8 seconds. This farming system is designed to increase productivity and predict

problems in agriculture. This analysis illustrates that the Cognitive internet of things has great

potential in agricultural technology because it can increase and facilitate corn production for

farmers.

Keywords: cognitive internet of things; algoritma fuzzy logic; soil moisture sensor.

Aries Dwi Indriyanti                                                                                                              | 923 
DOI : 0.36418/jrssem.v1i7.113 
INTRODUCTION 
 
Technological  developments  in  the 
current era of globalization have an impact 
on  all  aspects  of  life.  For  example,  the 
impact  that  arises  on  work  in  agriculture 
(Wandi  &  Husni,  2019).  An  important 
aspect of plant growth in agriculture is the 
watering  process,  because  plants  need 
nutrients contained in the soil. In order for 
watering to  remain  in  the  best  condition, 
monitoring must be carried out so that the 
plants being treated do not show too much 
or lack of water, which can cause plants to 
die  (Afif,  Kastono,  &  Yudono,  2014). 
Watering  plants  is  influenced  by  various 
factors,  namely  air  temperature  and  soil 
humidity.  Especially  in  corn  farming. 
Because soil moisture is an element that is 
very  influential  on  plant  growth  (Yan, 
Marschner, Cao, Zuo, & Qin, 2015); (Leghari 
et al., 2016). 
In a dry climate, corn plants can grow 
better.  Corn  sensitivity  to  foggy  weather, 
rainfall  and  rainfall  intensity.  This  plant 
most  requires  (at  least)  70%  sunlight 
radiation), 50-70% relative humidity, and an 
air temperature of 25-320 ° C. The increase 
in  population  causes  an  increase  in  the 
demand  for  corn.  The  Central  Statistics 
Agency (BPS) and the Directorate General 
of Horticulture (DJH) stated that from 2017 
to 2020 Indonesia's onion production has 
always  increased  from  1 470 155  tons, 
1 503 438 tons, 1 580 247 tons, to 1 815 445 
tons.  
Based  on  these  problems,  a  smart 
farming is  needed  which is  an  innovation 
from  modern  IOT-based  agriculture  and 
also  android  (Dewi,  Ulinuha,  Mustofa, 
Kurniawan,  &  Rakhmadi,  2021).  Irrigation 
care  or  watering  using  a  smart  farm,  a 
system  is  needed  that  can  provide 
automatic decision making in the form of 
decision  data  when  watering  is  needed.  , 
when  watering  is  not  needed,  and  how 
much water is needed for irrigation. Plant 
watering systems using mobile applications 
with  Internet  of  Things  (IOT) 
communication methods can help farmers 
monitor  and  water  plants  (Wasista, 
Saraswati, & Susanto, 2019). So if there is 
an automatic watering system it will really 
help  watering  evenly  as  needed  (Fauziah, 
Susila, & Sulistyono, 2016).  
This  system  can  be  authorized  via  an 
IoT-based communication link, so that data 
monitoring  and  irrigation  scheduling  can 
be  done  via  an  Android  smartphone 
(Kumar,  Surendra,  Mohan,  Valliappan,  & 
Kirthika, 2017). A system that uses Internet 
of Things technology uses wireless sensors 
to  process  data  obtained  by  sensors  and 
turns  it  into  information  (Tzounis, 
Katsoulas,  Bartzanas,  &  Kittas,  2017).  As 
well as a decision support system for plant 
care  or  watering  using  input  from  soil 
moisture on a microcontroller machine by 
using  fuzzy  logic  method  (Muslihudin, 
Renvillia, Taufiq, Andoyo, & Susanto, 2018). 
The  IoT  concept  is  divided  into  3  layers, 
namely  the  network  layer  (data 
transmission),  the  perception  layer 
(sensing),  and  the  application  layer  (data 
storage).  Modern  agriculture  is  becoming 
more industrialized (Kremen, Iles, & Bacon, 
2012). 
These  combinations  called  Cognitive 
Internet of Things (C IoT) are a combination 
of  cognitive  computing  technology  and 
data  collected  from  connected  devices 
(Sassi, Jedidi, & Fourati, 2019). This has led 

924 | Design and Build Smart Agriculture Using Cognitive Internet of Things (C IoT)

to the development of ubiquitous

computing, which has led to

heterogeneous infrastructure challenges

(Sassi et al., 2019). Through an objective

context, the Internet of Things solves the

challenges represented in context

awareness by producing intelligent systems

that meet user needs as shown in Figure 1.

Figure 1. C IoT Architecture (Sassi et al., 2019)

Based on this explanation, it is

necessary to develop a smart agriculture

model that is integrated with factories

made from corn using the Cognitive

Internet of Things (IoT) network formed in

cloud computing using data mining (Fuzzy

logic). This makes it easier for corn farmers

to monitor the condition of corn plants and

carry out watering automatically so that

they can improve agriculture and are

integrated with factories made from corn

(Grigorova, 2019).

METHODS

The method used is a type of applied

research (applied research). The

implementation of the work is carried out

by designing software and hardware

designs as well as implementing cognitive

internet of things (C IOT) based tools.

Applied research is usually used by

companies, agents or individuals who aim

to find solutions to a current problem that

is being faced by society or

industrial/business organizations (Costa,

Soares, & de Sousa, 2020). The stages of

this research are as follows:

Figure 2. General Stages of Research

Inisialisasi Sistem Pemrosesan data

pada arduino

Pengiriman data ke

Node MCU

Upload pada web

server

Data terintegrasi

pada petani dengan

smart phone

Data terintegrasi

pada Pabrik Bahan

baku jagung

Aries Dwi Indriyanti | 925

DOI : 0.36418/jrssem.v1i7.113

This system starts by initializing the

system and then checking the soil moisture

with sensor data which is processed using

Arduino, then Arduino data is sent to the

MCU Node and then uploaded to the web

server, so the sensor data will be displayed

on the farmer's smartphone via the

internet. data from agriculture is also

integrated in factories made from corn.

Flowchart Sistem

The flowchart of this system describes

the process of running the application as

shown in Figure 3.

Gambar 3. Flowchart Sistem Smart Agriculture Mennggunakan Internet Of Things (IOT).

The system starts from the next

initialization if the PH is greater than 1000

the data will be displayed on the smart

phone which is processed using a fuzzy

logic algorithm then the plant watering

driver is activated so that the Water Pump

automatically activates and performs

watering after the soil moisture content is

less than 500 then watering stops.

Diagram Blok

Based on the block diagram on the

system design are as follows:

Figure 4. System block diagram

926 | Design and Build Smart Agriculture Using Cognitive Internet of Things (C IoT)

Algoritma Fuzzy Logic

Fuzzy Logic Algorithm is a process to

get a clear input value. Each appropriate

fuzzy set can determine the degree of

membership. After the membership value is

obtained, the minimum operation or

maximum operation is then used to

perform the process of calculating the truth

value of each existing premise. If the

premise of a rule has a non-zero degree of

truth, it can be said that the rule is said to

be triggered (Arhami, 2005). Suppose min

is operated as follows:

v1 = mln ( µ1(µ), µ3(µ)) => terpicu (fired) ; V2

= mln ( µ1(a), µ4(a)) => terpicu (fired)

v1 = mln ( µ2(a), µ3(a)) => terpicu (fired) ; v1

= mln ( µ2(a), µ4(a)) => terpicu (fired)

Figure 4. Fuzzification process for two linguistic variables

Figure 5. The process of forming a "Very Good" fuzzy set

RESULTS AND DISCUSSION

Implementasi Hardware

The Smart Farm system consists of an

internet-based soil moisture control and

monitoring subsystem. Internet of Things

(IoT) and Android.

Figure 6. Implementation of sensor installation with node MCU ESP8266

Aries Dwi Indriyanti | 927

Implementation On Smart Phone

This smart farm system uses the blynk

application. This application displays a

sensor graphic, an LCD in the description of

the soil and pump, the value of soil

moisture, and the on or off status of the

pump.

Figure 7. Smart Farm Application Display in Dry, Normal, and Wet Conditions

Testing on Smart Farm System

The smart farm system connected to

the MCU node is tested with several sensor

modules. The purpose of testing this sensor

is not to measure the accuracy of sensor

readings so that humidity readings are

obtained that are suitable for corn plants.

Table 1. Testing Soil Moisture Value

Waktu

Nilai PH tanah

Keterangan Kondisi Tanah

Kondisi Pompa

06.00

256

Basah

Off

07.00

258

Basah

Off

08.00

332

Basah

Off

09.00

356

Basah

Off

10.00

467

Normal

Off

11.00

680

Kering

12.00

354

Basah

Off

13.00

476

Normal

Off

14.00

480

Normal

Off

15.00

485

Normal

Off

16.00

687

Kering

17.00

332

Basah

Off

18.00

324

Basah

Off

19.00

325

Basah

Off

20.00

327

Basah

Off

21.00

328

Basah

Off

22.00

331

Basah

Off

928 | Design and Build Smart Agriculture Using Cognitive Internet of Things (C IoT)

Waktu

Nilai PH tanah

Keterangan Kondisi Tanah

Kondisi Pompa

23.00

240

Basah

Off

24.00

231

Basah

Off

01.00

210

Basah

Off

02.00

215

Basah

Off

03.00

220

Basah

Off

04.00

223

Basah

Off

05.00

234

Basah

Off

Graph 1. Soil Moisture Value Test

The results of the measurement of the

moisture oil sensor are used as the results

of actual temperature measurements. The

reading of the PH sensor module in order

to monitor plant PH levels has a very

important effect on plant growth. From the

test results in the morning there was a

decrease in the PH value of soil moisture

and its value increased by 70% during the

day. The output produced in this study is

the condition of soil moisture in 3 criteria,

namely dry, normal and wet. The results of

this study showed a soil moisture value of

70%. Watering in this study had an average

duration of 8 seconds.

CONCLUSIONS

This study proposes an automatic

watering control system using soil

conditions (humidity) using fuzzy logic. The

output produced in this study is the

condition of soil moisture in 3 criteria,

namely dry, normal and wet. The results of

this study indicate that the soil moisture

value is 70%. Watering in this study has an

average duration of 8 seconds.

Aries Dwi Indriyanti                                                                                                              | 929 
DOI : 0.36418/jrssem.v1i7.113 
REFERENCES 
 
Afif,  Taufik,  Kastono,  Dody,  &  Yudono, 
Prapto. (2014). Pengaruh macam pupuk 
kandang  terhadap  pertumbuhan  dan 
hasil  tiga  kultivar  kacang  hijau  (Vigna 
radiata L. Wilczek) di lahan pasir pantai 
Bugel,  Kulon  Progo.  Vegetalika,  3(3), 
78–88. 
https://doi.org/10.22146/veg.5160 
 
Costa,  Eric,  Soares,  António  Lucas,  &  de 
Sousa,  Jorge  Pinho.  (2020).  Industrial 
business  associations  improving  the 
internationalisation of SMEs with digital 
platforms:  A  design  science  research 
approach.  International  Journal  of 
Information  Management,  5(3),  120–
135. 
https://doi.org/10.1016/j.ijinfomgt.202
0.102070 
 
Dewi,  Imelda  Zahra  Tungga,  Ulinuha, 
Muhamad Faqih, Mustofa, Wahyu Ajis, 
Kurniawan,  Ade,  &  Rakhmadi,  Frida 
Agung.  (2021).  Smart  Farming:  Sistem 
Tanaman  Hidroponik  Terintegrasi  IoT 
MQTT  Panel  Berbasis  Android.  Jurnal 
Keteknikan  Pertanian  Tropis  Dan 
Biosistem, 9(1), 71–78. 
 
Fauziah,  Rahmi,  Susila,  Anas  D.,  & 
Sulistyono,  Eko.  (2016).  Budidaya 
bawang merah (Allium ascalonicum L.) 
pada lahan kering menggunakan irigasi 
sprinkler  pada  berbagai  volume  dan 
frekuensi. Jurnal Hortikultura Indonesia, 
7(1),  1–8. 
https://doi.org/10.29244/jhi.7.1.1-8 
 
Grigorova,  V.  (2019).  Strategic  marketing 
decisions  of  industrial  business 
organizations.  Экономический 
Вестник Донбасса, 4(4), 132–137. 
 
Kremen,  Claire,  Iles,  Alastair,  &  Bacon, 
Christopher. (2012). Diversified farming 
systems:  an  agroecological,  systems-
based alternative to modern industrial 
agriculture. Ecology and Society, 4(4). 
 
Kumar,  Anusha,  Surendra,  Aremandla, 
Mohan, Harine, Valliappan, K. Muthu, & 
Kirthika,  N.  (2017).  Internet  of  things 
based smart irrigation using regression 
algorithm.  2017  International 
Conference  on  Intelligent  Computing, 
Instrumentation  and  Control 
Technologies  (ICICICT),  1652–1657. 
IEEE. 10.1109/ICICICT1.2017.8342819 
 
Leghari,  Shah  Jahan,  Wahocho,  Niaz 
Ahmed,  Laghari,  Ghulam  Mustafa, 
HafeezLaghari,  Abdul, 
MustafaBhabhan,  Ghulam, 
HussainTalpur,  Khalid,  Bhutto,  Tofique 
Ahmed, Wahocho, Safdar Ali, & Lashari, 
Ayaz  Ahmed.  (2016).  Role  of  nitrogen 
for  plant  growth  and  development:  A 
review.  Advances  in  Environmental 
Biology, 10(9), 209–219. 
 
Muslihudin,  Muhamad,  Renvillia,  Willy, 
Taufiq,  Taufiq,  Andoyo,  Andreas,  & 
Susanto,  Fery.  (2018).  Implementasi 
Aplikasi Rumah Pintar Berbasis Android 
Dengan Arduino Microcontroller. Jurnal 
Keteknikan  Dan  Sains  (JUTEKS),  1(1), 
23–31.  http://orcid.org/0000-0001-
6673-9244 
 
Sassi,  Mohamed  Saifeddine  Hadj,  Jedidi, 
Faiza  Ghozzi,  &  Fourati,  Lamia  Chaari. 
(2019). A new architecture for cognitive 
internet  of  things  and  big  data. 
Procedia  Computer  Science,  5(9),  534–
543. 
https://doi.org/10.1016/j.procs.2019.09
.208 
 
Tzounis,  Antonis,  Katsoulas,  Nikolaos, 
Bartzanas,  Thomas,  &  Kittas, 
Constantinos. (2017). Internet of Things 
in  agriculture,  recent  advances  and 

930 | Design and Build Smart Agriculture Using Cognitive Internet of Things (C IoT) 
 
future  challenges.  Biosystems 
Engineering,  164,  31–48. 
https://doi.org/10.1016/j.biosystemsen
g.2017.09.007 
 
Wandi,  Ir  Sis,  &  Husni,  Nyayyu  Latifah. 
(2019). Penyiram Otomatis Berdasarkan 
Sensor  Kelembaban  Tanah.  TEKNIKA, 
13(2), 137–142. 
 
Wasista,  Sigit,  Saraswati,  Delima  Ayu,  & 
Susanto, Eko. (2019). Aplikasi Internet of 
Things  (IOT)  dengan  Arduino  dan 
Android “Membangun Smart Home Dan 
Smart  Robot  Berbasis  Arduino  Dan 
Android.” Deepublish. 
 
Yan, Nan, Marschner, Petra, Cao, Wenhong, 
Zuo,  Changqing,  &  Qin,  Wei.  (2015). 
Influence of salinity and water content 
on  soil  microorganisms.  International 
Soil  and  Water  Conservation  Research, 
3(4),  316–323. 
https://doi.org/10.1016/j.iswcr.2015.11.
003 
 
 
 
 
 
 
 
 
© 2022 by the authors. Submitted  
for possible open access publication  
under  the  terms  and  conditions  of  the  Creative 
Commons  Attribution  (CC  BY  SA)  license 
(https://creativecommons.org/licenses/by-sa/4.0/). 
 