Automated Plant Care For Smart Gardens Using IoT

Adarsh Shivam Dr. Nidhi Sharma*

Lovely Professional University Lovely Professional University

Jalandhar, Punjab Jalandhar, Punjab

[email protected] [email protected]

Kashish Verma Krishna Upadhyay

Lovely Professional University Lovely Professional University

Jalandhar, Punjab Jalandhar, Punjab

[email protected] [email protected]

Pratham Singh Ujjwal shivhare

Lovely Professional University Lovely Professional University

Jalandhar, Punjab Jalandhar, Punjab

[email protected] [email protected]

Abstract—The integration of IoT in agriculture and I. INTRODUCTION

home gardening has revolutionized plant care by Gardening, once a predominantly manual activity, has
enabling real-time monitoring, automated watering, evolved significantly with the advent of emerging
environmental sensing, and predictive nutrient
management. Traditional methods often lead to
inefficiencies such as overwatering, under-fertilization, technologies such as the Internet of Things (IoT) and
and lack of real-time insights. This study presents an Artificial Intelligence (AI). Traditional gardening methods
IoT-based Smart Garden System utilizing soil moisture often suffer from inefficiencies, including inconsistent
sensors for precise watering, rain and wind sensors for watering, improper nutrient distribution, and a lack of real-
adaptive irrigation, smoke detectors for fire prevention, time environmental monitoring, which result in suboptimal
and Wi-Fi-enabled microcontrollers for real-time data plant growth and inefficient resource utilization [1]. Many
transmission. AI-driven nutrient management, weather urban gardeners, particularly beginners, struggle with
prediction algorithms, and smart home integration challenges such as overwatering, under-fertilization, and
further enhance automation and plant care. A mixed- unpredictable weather conditions, leading to poor plant
method research approach, including field experiments health and excessive resource consumption [3].
and user surveys, was used to evaluate the system across The global smart gardening industry has seen rapid
various environments (indoor, outdoor, greenhouse). expansion due to increasing demand for automated plant
Results show a 40% reduction in manual effort, 35% care solutions. Research indicates that IoT-based plant
optimization in water usage, and 30% improvement in monitoring and AI-driven irrigation systems are being
plant health. This research contributes to smart widely adopted, especially in urban settings where users
agriculture and urban gardening by demonstrating seek efficient and intelligent gardening solutions [2].
IoT’s potential in enhancing efficiency, reducing Furthermore, AI-driven irrigation scheduling has
resource wastage, and promoting sustainability, with demonstrated the potential to reduce water wastage by up to
future work focused on expanding AI capabilities, 30% in controlled environments, emphasizing the
improving home automation interoperability, and effectiveness of data-driven automation in precision
assessing long-term plant health impacts. agriculture [4]. These advancements highlight the growing
Keywords—IoT, Smart Gardening, Automated Plant Care, need to integrate smart technologies for optimized plant care
Real-time Monitoring, Smart Home Integration, and resource management.
Sustainable Agriculture
Despite these technological advancements, current smart Compared to traditional irrigation systems, studies show that
gardening solutions often lack a fully integrated approach smart and automated irrigation systems can steer to
that combines real-time environmental monitoring, significant conservation of water, with an estimated 35%
automated plant care, and seamless smart home integration. less water waste [3]. Furthermore, AI-based nutrient
Existing systems typically focus on individual aspects such analysis and automated irrigation models can improve plant
as soil moisture detection or automated irrigation, without health by 30% [5]. Additionally, this system can reduce the
considering external environmental factors like wind speed, need of manual labor needed for plant care by 40% at least,
rainfall, and smoke detection, which are critical for plant which makes it beneficial for individuals with limited
health and safety. gardening time [2].
A study by Rahim et al. found that 80% of plant health issues The indoor gardeners who often with plant maintenance,
in urban gardening stem from poorly managed watering urban agriculture farmers seek for automated solution for
schedules and imbalanced nutrient distribution, small-scale farming, and home automation hobbyist for
underscoring the need for an intelligent, sensor-driven those who are interested in integrating plant maintenance
system [5]. There are automated irrigation systems out into their home automation system all stand to gain from this
there, but most do not consider the weather ahead of time, or system. The system in question looks for revolutionize
the needs of the plant itself, causing inefficiencies and contemporary plant maintenance through intelligent
underperforming plants [6]. A comprehensive smart automation and data-driven decision making by overcoming
gardening system that combines environmental sensors, AI- the limitations of traditional gardening.
driven irrigation, and home automation features is required II. LITERATURE REVIEW
to address these issues. The goal of this research is to
Real-time tracking, predictive computing in agriculture, and
develop an IoT-enabled Smart Garden System that combines
autonomous control systems for plants have all been possible
AI-based nutrient management, automated plant irrigation,
by the Internet of Things (IoT) and Artificial Intelligence
and real-time environmental monitoring. The following are
(AI) [1]. This section helps us in examines existing research
the particular goals of this research:
on smart and automated gardening systems and categorizes
• Developing a real-time environmental monitoring it into the following areas:
system that precisely assesses plant conditions by
• Automated Gardening Systems based on IoT
utilizing sensors for rain, wind, smoke, and soil
moisture. • AI-guided Water and Nutrient Management
• Enhancing water efficiency by automating • Integration of Smart Homes with Gardening Using
irrigation of plants according to soil moisture and IoT.
weather forecasts. • Environmental Regulation Through Adaptive
Processes
• Applying AI-based nutrient management practices
to enhance plant health and maximize fertilization The importance of real-time feedback to environmental
schedules. Integrating the smart gardening system change and wastage of water are the few of the problems
with home automation platforms to provide remote solved by each of these categories in designing automated
control, insights, and real-time alerts capabilities. plant maintenance solutions for individuals with limited
• Employing experimental analysis to identify time.
whether the suggested system enhances gardening A. IoT-Based Smart Gardening Systems
efficiency, plant health, and resource use.
The use of IoT in gardening has notably improved the
With the help of an intelligent, multi-purpose IoT-based efficiency of irrigation control and the monitoring of the
automated plant care system, this research extensively adds plants. To enable the automation of plant care, IoT gardening
value to the world of precision agriculture and home systems normally consist of sensors, actuators, and cloud-
automation, which will definitely help extend our based analytics [2].
knowledge and improve plant monitoring. While all
Key Components of IoT-Based Smart Gardening
previous studies have focused on the advantages of
automated irrigation and nutrient management, there are The Key Components of IoT-Based Smart Gardening The
very few studies that have only provided effective importance of different sensors in IoT-based plant care has
unification of predictive AI with smart home automation been discussed in several pieces of research:
capabilities [7]. By offering this as an extensive solution that • Soil Moisture Sensors: These sensors regulate
not only enhances plant care and maintenance but also watering and keep track of soil humidity levels [3].
improves resource efficiency, the proposed system aims to • Temperature and humidity sensors: These sensors
address the existing challenges in the field of agriculture. help ensure that plants develop well during growth
[4].
 • Wind Speed Sensors: These sensors measure high The Real-time tracking, automated notifications , and voice-
winds to protect fragile plants [5]. enabled control are all enabled when smart devices are
• Rain Sensors: By optimizing irrigation schedules integrated with IoT-based plant care systems. Various
accordingly, they avoid overwatering [6]. different studies suggest that IoT and AI-powered gardening
systems can easily integrate with home automation
According to a study by Astutiningtyas et al. [3] an IoT-
platforms easily. [7].
based automated irrigation system for small gardens saved
35% more water in comparison to conventional manual Real-Time Alerts and Mobile Notifications
watering practices. Automated gardening systems also come with mobile apps
Wireless Communication and Cloud Integration that provide real-time reports on the wellness of plant, soil
water content, and environmental stressors [2]. User
For real-time transmission of sensor data, IoT gardening
engagement rose by 40% at least as a result of smart
systems utilize wireless communication protocols such as
gardening apps, as given by Rahim et al.'s study [5], leading
Wi-Fi, Bluetooth, LoRa, and Zigbee [7]. Mobile apps allow
to enhanced survival rates of the plants.
users to monitor and control plant care remotely due to cloud
integration [1]. Voice-Activated Gardening Control

Rahim et al.'s [5] comparative analysis concluded that LoRa- Smart home devices such as Google Assistant and Amazon
based gardening systems provided improved range for Alexa now support a wide range of IoT-based gardening
bigger agricultural uses, whereas Wi-Fi-based gardening systems [6]. With voice commands, users can easily be able
systems performed better for residential urban settings. to adjust irrigation levels, monitor schedules of the water,
and receive information about the plant care.
B. AI-Driven Nutrient Prediction and Water Management
D. Environmental Monitoring and Adaptive Control
Data-driven fertilizer management and predictive irrigation
models are now achievable due to recent breakthroughs in Factors such as temperature, humidity, wind speed, and
artificial intelligence and machine learning. For optimizing pollution levels have a direct effect on the growth of
fertilization schedules, AI-based gardening systems utilize plant[4]. IoT-based systems with adaptive control features
past data regarding plant growth, soil health, and weather can react to environmental changes in real time.
forecasts [2]. Smoke and Fire Hazard Detection
AI-Based Nutrient Prediction Plant growth is determined directly by temperature,
In order to identify the most optimal nutrient blend for humidity, wind speed, and the levels of pollution [1].Internet
plants, AI models read data from sensors in real-time [4]. As of Things-based systems with adaptive control functionality
an example, Pendyala et al.'s AI system [6] utilized machine are able to immediately respond to any changes in the
learning algorithms for forecasting nutrient shortages, and environment.
consequently, reduced the amount of wastage of fertilizer by Wind and Rain Adaptation Systems
28%.
Greenhouses and indoor plant spaces are gravely threatened
AI Nutrient Prediction Formula: by fire risks. The importance of smoke detectors in
N_optimal = f(S_moisture, T_temp, pH, N, P, K) Where: intelligent gardens was highlighted in a study by Kasar et al.
● N_optimal = Recommended nutrient supply [5], which helped reduce plant losses due to fire by 25%.

● S_moisture = Soil moisture content Table 1: Comparison of Traditional Manual vs. Smart
Gardening Approaches
● T_temp = Temperature
Features Traditional Smart
● pH = Soil acidity
Gardening Gardening(IoT)
● N, P, K = Essential nutrient levels (Nitrogen,
Phosphorous, Potassium) Water Manual Watering, AI-Based
Efficiency risk of irrigation,
AI-Optimized Watering Schedules
over/underwaterin optimized for
With the observation of soil moisture trends, weather, and g moisture levels
plant evapotranspiration rates, AI-powered irrigation
Nutrient Guesswork-based AI-driven, real-
systems can predict when plants require water[5]. A study
Management fertilization time
by Astutiningtyas et al. [3] found that AI-guided irrigation
optimization
reduced water wastage by 30% compared to traditional
irrigation. Weather No real-time Automated
Adaption adaption responses to rain
C. Smart Home Integration in Gardening
and wind
 Enviromental No hazard Smoke, fire, and sensor, rain
Safety detection wind-speed sensor, smoke
monitoring detector (MQ-2),
water pump &
User Control Requires physical Mobile apps,
relay
presence remote control,
voice commands Network Layer ESP32/ESP8266 Transmits sensor
Summary of Literature Gaps & Research Contributions (Data microcontroller, data to cloud-
Transmission & Wi-Fi module, based platforms
While many studies have explored IoT-based gardening, AI- Cloud MQTT protocol, for remote
guided irrigation, and smart home integration, still no Processing) Firebase/AWS access
combined system has been proposed that can integrates all IoT
these functionalities in one[1].
Application Mobile/web Displays real-
This research addresses gaps by: Layer (User application, AI- time plant health
• Coming up with a real-time IoT plant monitoring Interface & AI based irrigation data, sends
system. Analytics) control, smart alerts, and
home integration enables remote
• Enacting AI-based irrigation and fertilizer
irrigation control
management practices.
• Adding smart home automation for the user's C. Software and Data Processing: The system uses AI-
convenience. driven decisions to improve irrigation, predict the need of
• Applying experimental validation to ascertain the nutrient, and adjust according to the environmental changes.
real-world effect of automated plant care.
1. AI-Driven Nutrient Prediction Model
III. METHODOLOGY
a. The AI model utilizes sensor data and
The IoT-based Smart Gardening System is designed,
weather forecasts to predict optimal
deployed, and tested in this section. The core elements of the
fertilizer requirements.
methodology are the following:
b. Formula:
A. System Design and Architecture: There are primary
layers to the system proposed for design:
1. Perception Layer: Comprising IoT sensors and
actuators, including soil moisture, temperature, c. The model adjusts nutrient dynamically
wind, smoke, and rain sensors, for real-time data based on the real-time data and
collection. information.
2. Network Layer: Wireless communication 2. IoT-Based Automated Irrigation Algorithm
through Wi-Fi (ESP8266/ESP32) or LoRa a. The irrigation system follows a
modules to transmit sensor data to cloud-based threshold-based decision model:
servers.
3. Application Layer: A mobile/web-based
application for real-time monitoring, AI-driven
irrigation control, and nutrient prediction. b. This logic prevents overwatering and
B. Hardware Components: For collecting information in adapts schedules based on real-time
real time, the system combines sensors and actuators with rainfall data.
the ESP8266/ESP32 microcontroller. D. The experimental environment involved different
Table 2: System Architecture of the Smart Gardening gardening systems and settings where the system was
System deployed and tested.
Layer Components Functionality 1. Indoor Plant Setup: Controlled environment
with potted plants.
Perception Soil moisture Collects real- 2. Outdoor Home Garden: Exposed to natural
Layer sensor, time
weather variations.
(Hardware temperature & environmental
Sensors & humidity sensor data & 3. Greenhouse Setup: Temperature and humidity-
Actuators) (DHT11/DHT22 automates regulated environment.
), wind speed irrigation
To test the variations between automated and traditional For the avoidance of over-watering and under-watering, the
plant maintenance, each setup was monitored for four weeks system was created to conserve water and eliminate wastage
and to collect data too. of water.
E. Data collection and analysis: Data collection and Figure1 presents a analysis of weekly water consumption
evaluation criteria analysis involve: over a four-week period of time.
● Water Consumption Efficiency: Reduction in
water usage (Liters/Week).
● Plant Health Index: Leaf color, growth rate, and
soil moisture stability.
● User Engagement: Mobile app usage and
feedback surveys.
Table 3: Comparison of Water Consumption (Manual vs.
System for Smart Gardening)
Metric Manual Smart Improveme
Gardenin Gardening nt (%)
g System
Observations:
● The smart system reduced water usage by an
Leaf Color 6.2 8.5 37%
average of 34.5%.
Index (0-10
Scale) ● Automated irrigation responded dynamically to
soil moisture levels.
Growth 2.1 cm 3.2 cm 52% ● Manual watering led to inconsistencies in water
Rate application.
(cm/week) B.Plant Health Improvement
To assess plant health, the study measured leaf color, growth
Soil ±20% ±5% 75% rate, and soil moisture stability.
Moisture
Fluctuation Table 4: Plant Growth & Health Comparison (Manual vs.
Smart Gardening)
Observations:
Environme Manual Smart Effectiveness
• The Automated Gardening System lowered water ntal Factor Response System
wastage by 34.5% on average. Response
• Traditional watering, however, produced different
consumption levels depending on user. Rain Manual Automated 100%
adjustment irrigation
• Based on real-time weather and soil moisture data, pause
the automated irrigation system simplified the
scheduling of irrigation easily. High Wind No Alert & 85%
IV. FINDINGS Speed protection plant cover
activation
The experimental analysis of the IoT based Smart
Gardening System is presented in this section and compared
Smoke No early Real-time 95%
with conventional manual gardening methodologies. The Detection warning fire alerts
scoring subsystems revolve around water efficiency,
beneficial development in plant health, adaptability to the Observations:
environment and overall satisfaction by the user ● AI-driven nutrient recommendations enhanced
Here you compare the outcomes of the IoT based Smart plant growth.
Gardening System with those of the traditional manual ● Soil moisture levels remained stable, preventing
gardening approaches. The key taglines are water plant stress.
efficiency, improvement in plant health, flexibility to
● Manual watering caused inconsistent growth
environmental conditions, and user satisfaction are the
patterns.
concerns of the evaluation criteria.
C.Environmental Adaptability
A. Water Efficiency Analysis
The system was tested across three environments: indoor ● The automation reduced manual effort and time
plants, outdoor gardens, and greenhouse setups. spent on plant care.
Table 5: Environmental Adaptability Test Results ● Real-time insights increased user confidence in
plant maintenance.
Advantage Traditional Smart
Gardening Gardening (IoT- V. DISCUSSION
based) This section interprets the findings from the IoT-based
Smart Gardening System, discusses its advantages over
Water Usage High wastage Optimized, traditional gardening, and highlights challenges,
34.5% reduction limitations, and future improvements.
Plant Growth Slower due to 52% A.Interpretation of Key Findings
Rate inconsistent improvement The results indicate that IoT-driven smart gardening
watering significantly enhances efficiency, plant health, and
environmental adaptability.
Nutrient Manual, risk of AI-based
Application under/over- precision Water Efficiency
fertilization
● The system reduced water consumption by
Environmental No automated Adjusts to rain, 34.5%, aligning with findings from
Response adaptation wind, and smoke Astutiningtyas et al. [3], who reported a 30%
levels reduction in water waste using automated
irrigation.
User Effort High (manual Reduced by 40% ● Soil moisture sensors effectively prevented
intervention)
overwatering, a major issue in manual gardening,
Remote Not possible Mobile app as noted by Rahim et al. [5].
Monitoring control Plant Health Improvements

Observations: ● AI-driven nutrient management increased growth

rates by 52%, similar to studies by Pendyala et al.
● The system effectively adjusted irrigation
[6], where smart irrigation improved plant
schedules based on rainfall.
survival rates by 40%.
● Wind detection enabled proactive plant
● Soil moisture fluctuations decreased by 75%,
protection.
proving that real-time monitoring maintains
● Smoke sensors provided real-time fire alerts. stable conditions [1].
D. User Satisfaction & Engagement Environmental Adaptability
A survey among 30 users assessed their satisfaction with ● Avoiding over-watering, the system changed
manual vs. smart gardening. schedules of watering depending on rainfalls [7].
● Smoke and wind detection systems allowed for
early indications, enabling optimal protection of
the plants [2].
User Experience
● Due to automation, convenience, and the time
saved, user satisfaction scores rose by 58%.
● More importantly, the confidence of the users in
maintaining the plants increased by 45 percent
due to real-time indications that enabled them to
make informed decisions [4].
B.Challenges & Limitations
The Internet of Things-based system faces a number of
Figure 2 presents user satisfaction survey results
difficulties despite its successes:
Observations:
Sensor Accuracy & Calibration
● Users preferred the smart system for convenience
and efficiency.
 ● Soil moisture sensors need regular calibration A. Contributions to Smart Agriculture
because they can degrade over time [5]. The proposed system makes significant contributions to
● Wind speed sensors might also give false positives smart agriculture by:
during minor airflow changes. ● Implementing real-time IoT-based plant care with
Initial Setup Costs AI-driven automation.
● The initial expenses are higher due to the costs of ● Enhancing water efficiency through adaptive
sensors and cloud services [2]. irrigation techniques.
● However, the long-term savings from reduced ● Improving plant health with sensor-based nutrient
water and fertilizer usage can balance these costs. monitoring.
Internet Dependency ● Demonstrating smart home integration for managing
● The cloud-based processing relies on stable Wi- gardening remotely.
Fi connectivity. [6]. B. Limitations and Future Scope
● Implementing local storage fallback systems can Despite its effectiveness, the system has certain limitations,
improve reliability during network outages. including hardware dependencies, reliance on internet
AI Model Optimization connectivity, and the need for further optimization of AI
models for various plant species. Future enhancements could
● Nutrient prediction models need to be trained on
include:
various soil types, which may require
customization for different environments [1]. ● AI-powered detection of plant diseases using image
processing technology.
● Integrating real-time weather APIs could enhance
prediction accuracy even further. ● Solar-powered IoT nodes to improve energy
efficiency.
D. Future Improvements & Research Directions
● Integration of weather APIs for predictive irrigation
To improve the system further, the following enhancements
strategies.
are suggested:
Expanding this system to large-scale agricultural
Integration with Weather Forecast APIs
applications could significantly contribute to precision
● Improving AI models by accessing real-time farming and water conservation, positioning it as a scalable
weather forecasts (like the Google Weather API) and sustainable solution for the future.
for more effective irrigation planning.
VII. REFERNCES
Energy Efficiency Optimization
[1] R. N. Kasar, A. H. Bangar, and S. Raut, "A Review on
● Using solar-powered microcontrollers to create a IoT Smart Plant Care and Plant Monitoring System," Int. J.
self-sustaining system. Creative Res. Thoughts (IJCRT), vol. 24, no. 10, pp. 477–
Advanced AI-Based Disease Detection 484, 2023.
● Employing machine learning models to identify [2] V. Dhople, A. Chavan, N. Hadmode, and V. Godase,
plant diseases through leaf color analysis. "Smart Gardening System Using IoT," Int. J. Creative Res.
Thoughts (IJCRT), vol. 24, no. 4, pp. 580–590, 2023.
Customizable Smart Home Integration
[3] M. B. I. Astutiningtyas, M. M. Nugraheni, and S. Suyoto,
● Expanding compatibility with platforms like
"Automatic Plants Watering System for Small Garden," Int.
Google Assistant, Amazon Alexa, and Apple
J. Interactive Mobile Technol. (iJIM), vol. 15, no. 2, pp.
HomeKit.
200–207, 2021.
VI. CONCLUSION
[4] M.-H. Song, "A Study on IoT-based Real-Time Plants
This study showcased how an IoT-based smart gardening Growth Monitoring for Smart Garden," Int. J. Internet,
system can effectively optimize water usage, enhance plant Broadcasting Commun., vol. 12, pp. 130–136, 2020.
health, and improve user experience. The system achieved a
[5] A. Rahim, N. Hafhizah, A. Zaki, M. Noor, and A. Shukri,
34.5% reduction in water consumption, a 52% boost in plant
"Smart App for Gardening Monitoring System Using IoT
growth, and a 58% increase in user engagement through real-
Technology," Int. J. Adv. Sci. Technol., vol. 29, pp. 7375–
time monitoring and AI-driven automation. Automated
7384, 2020.
responses to environmental changes ensured the protection
of plants, underscoring the potential of IoT and AI in [6] H. Pendyala, G. Rodda, A. Mamidi, M. Vangala, S.
promoting sustainable urban gardening and precision Bonala, and K. Korlapati, "IoT-Based Smart Agriculture
agriculture.
Monitoring System," Int. J. Sci. Eng. Res. (IJSER), vol. 9, based smart agriculture: Toward making the fields talk.
pp. 31–34, 2019. IEEE Access, 7, 129551-129583.
[7] K. Lakshmisudha, S. Hegde, N. Kale, and S. Iyer, "Smart [21] Boursianis, A. D., Papadopoulou, M. S., Gotsis, A.,
Precision-Based Agriculture Using Sensors," Int. J. Comput. Wan, S., Sarigiannidis, P., Nikolaidis, S., & Goudos, S. K.
Appl., vol. 146, no. 11, 2011. (2020). Smart irrigation system for precision agriculture—
[8] N. B. Arbain, S. Sulaiman, and M. D. Darrawi bin Sadli, The AREThOU5A IoT platform. IEEE Sensors Journal,
"An IoT-Based Smart Garden with Weather Station 21(16), 17539-17547.
System," in Proc. IEEE 9th Symp. Comput. Appl. Ind. [22] Khattab, A., Habib, S. E. D., Ismail, H., Zayan, S., &
Electron. (ISCAIE), Malaysia, 2019, pp. 38–43. Fahmy, Y. (2019). An IoT-based cognitive monitoring
[9] Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. system for early plant disease forecast.
(2013). Internet of Things (IoT): A vision, architectural Computers and Electronics in Agriculture, 166, 105028.
elements, and future directions. Future Generation
Computer Systems, 29(7), 1645-1660.
[10] Farooq, M. S., Riaz, S., Abid, A., Umer, T., & Zikria,
Y. B. (2020). Role of IoT Technology in Agriculture: A
Systematic Literature Review.
[11] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep
learning in agriculture: A survey. Computers and
Electronics in Agriculture, 147, 70-90.
[12] Zhang, X., Zhang, J., Li, L., Zhang, Y., & Yang, G.
(2017). Monitoring Citrus Soil Moisture and Nutrients
Using an IoT-Based System. Sensors, 17(3), 447.
[13] Kodali, R. K., Jain, V., & Karagwal, S. (2016). IoT
based smart greenhouse. 2016 IEEE Region 10
Humanitarian Technology Conference (R10-HTC).
[14] Patil, K. A., & Kale, N. R. (2016). A model for smart
agriculture using IoT. 2016 International Conference on
Global Trends in Signal Processing, Information Computing
and Communication (ICGTSPICC).
[15] Srivastava, A., & Das, D. K. (2020). A Comprehensive
Review on IoT-Based Smart Agriculture: Challenges and
Opportunities. Journal of Sensors, 2020.
[16] Mekala, M. S., & Viswanathan, P. (2017). A survey:
Smart agriculture IoT with cloud computing.
2017 International Conference on Microelectronic Devices,
Circuits and Systems (ICMDCS).
[17] Ray, P. P. (2017). Internet of Things for Smart
Agriculture: Technologies, Practices and Future Direction.
Journal of Ambient Intelligence and Smart Environments,
9(4), 395-420.
[18] Nukala, R., Panduru, K., Shields, A., Riordan, D.,
Doody, P., & Walsh, J. (2016). Internet of Things: A review
from ‘Farm to Fork’. 2016 27th Irish Signals and Systems
Conference (ISSC).
[19] Tzounis, A., Katsoulas, N., Bartzanas, T., & Kittas, C.
(2017). Internet of Things in agriculture, recent advances,
and future challenges. Biosystems Engineering, 164, 31-48.
[20] Ayaz, M., Ammad-Uddin, M., Sharif, Z., Mansour, A.,
& Aggoune, E. H. M. (2019). Internet-of-Things (IoT)-