A Comprehensive Framework for Smart Agriculture: Integrating

IoT, Edge Computing, and AI for Scalable, Transparent, and

Adaptive Crop Management

Durgalakshmi B.

, Umapathi S.

, M. Priya

, M. Soma Sabitha

, Ilakkiya E.

and M. Uday Raj Kumar

Department of Artificial Intelligence and Data science, Tagore institute of Engineering and Technology, Deviyakurichi,

Tamil Nadu, Salem, India

Department of Computer Science and Engineering, Tagore institute of Engineering and Technology, Deviyakurichi, Salem,

Tamil Nadu, India

Department of Electrical and Electronics Engineering, J.J. College of Engineering and Technology, Tiruchirappalli, Tamil

Nadu, India

Department of Computer Science and Engineering, MLR Institute of Technology, Hyderabad, Telangana, India

Department of CSE, New Prince Bhavani Shri College of Engineering and Technology, Chennai, Tamil Nadu, India

Department of ECE, Ballari Institute of Technology and Management, Ballari, Karnataka, India

Keywords: Smart Agriculture, IoT, Edge Computing, Crop Management, Adaptive Systems.

Abstract: Smart farming is an emerging concept that is rapidly transforming due to the development of the Internet of

Things, edge computing and AI, and providing revolutionary solutions for real time crop monitoring and

decision making. This article introduces a unified and adaptive framework that combines IoT-based sensing,

edge-level analytics, knowledge-driven analytics and AI-driven analytics, aiming to achieve the premises of

scalability, transparency and responsiveness in intelligent agriculture. Leveraging the latest breakthroughs

from 2021 to 2025, the work investigates the ways in which edge intelligence and distributed architecture

solve the key challenges, including data latency, connectivity outages and context-aware decision support.

The proposed architecture focuses on the practical implementation in a broad range of agricultural systems,

comprising classical and soilless farms, taking into consideration issues related to the integration, constraints

of infrastructure, and system interoperability. We seek to narrow the chasm between prototype ideas and

practical applications in precision agriculture by critically reviewing existing models and adding a new

architectural approach.

1 INTRODUCTION

Increasing global needs for sustainability in food

production have spurred a technological revolution

in the agriculture industry, from historical farming

techniques to smart, data-driven solutions. As farms

are becoming increasingly information-intensive,

using digital tools to observe, analyse and optimize

processes, smart agriculture has become a key area

where advanced technologies such as IoT are

combined to tackle challenges related to climate

variability, resource limitation, and labour crimps.

Driving this change is the Internet of Things (IoT) and

edge computing, making it possible for data-driven

decision making to happen in real time, closer to the

farm.

Internet of things devices, like environmental

sensors, and actuators, and drones allow us to

constantly monitor environmental health, crops, and

weather. Nevertheless, the amount of data produced

is so large that centralized cloud infrastructures

become swamped and latency, bandwidth,

restrictions in processing these data as well as data

privacy become a problem. To address some of these

issues, edge computing has emerged as a way of

processing data closer to the source to avoid

communication latencies and to make quicker,

context-dependent decisions.

AI enriches this ecosystem with predictive

analysis, anomaly detection and intelligent

350

B., D., S., U., Priya, M., Sabitha, M. S., E., I. and Kumar, M. U. R.

A Comprehensive Framework for Smart Agriculture: Integrating IoT, Edge Computing, and AI for Scalable, Transparent, and Adaptive Crop Management.

DOI: 10.5220/0013865600004919

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 1, pages

350-356

ISBN: 978-989-758-777-1

automation to convert raw data into actionable

knowledge. However, in spite of these many

improvements, many of the proposed systems are

either still stuck in the realm of experiments or are

non-scalable and are not interoperable to support

wide-spread usage. Furthermore, infrastructure-level

heterogeneity, high-cost implementation, and

fragmented architectures are still critical barriers to

the smooth integration of technologies on the fields.

This study attempts to fill this gap by proposing a

unified, scalable, and adaptive framework for smart

agriculture that integrate the potentialities of IoT,

edge computing, and AI. Combining recent literature

and knowledge of implementation, important steps

are provided in order to develop strong agricultural

systems that facilitate efficient and informed crop

management in different crop systems.

1.1 Problem Statement

Agriculture is experiencing an intense digitalisation

but the convergence of emerging technologies, such

as Internet of Things (IoT), edge computing and

artificial intelligence (AI), into an integrated smart

agriculture system is still constrained by many

technical and operational challenges. Despite the

increasing evidence of the potential of these

technologies to disrupt crop monitoring, resource

management and yield estimation practices, their

application in actual farming practices is still

scattered, in many cases limited to one-shots or

specific-purpose solutions. The vast majority of

existing systems use centralized, cloud-based

architectures that are not surrogate to the dynamic and

distributed conditions found in agricultural settings

such as rural and remote environments where reliable

connectivity is scarce or not available.

Model processing overly centralized is high

latency, real time response is poor and there are also

data privacy and ownership issues. Furthermore,

there is no standard or holistic solution to

interoperate different sensor networks, platforms, and

data format to establish a seamless decision-making

system. Smallholder and mid-scale farmers (who

produce most of the world’s food) face additional

challenges such as prohibitive costs of setting up

solutions, technical complexity and lack of access to

dependable infrastructure, further increasing the

digital gap in agriculture.

Furthermore, though artificial intelligence, with

superior analytics and predictive capabilities, has

been used in agriculture for various purposes, a large

portion of the AI models are not specifically designed

to run on edge devices that have limited resources on

the edge. Thus, there is a significant discrepancy

between the theoretical potential of smart, real-time

and scalable agricultural systems compared to their

real-world implementation. Missing still is a flexible

and adaptive framework mixing low-latency edge

processing, resilient IoT data collection, and smart

analytics addressing the requirements of the varied

farming environments.

This work tackles the pressing requirement of a

unified, scalable and context aware framework that

leverages efficiently the IoT, edge computing and AI

towards a seamless farming management. By

crossing current technology silos and targeting in-

field deployment scenarios, this research offers the

potential to address critical performance,

deployability and accessibility limitations that are

hindering this transformation — and to implement the

first steps toward agricultural solutions that are robust

and smart.

2 LITERATURE SURVEY

Content Smart agriculture in recent years, the smart

agriculture field seems to have been developed with

the organic integration of IoT technologies, edge

computing, and AI technologies for the complex

demands of modern farming systems. Investigations

are using different system architectures and

application domains for increased crop yield, real-

time monitoring and automated decision marking.

Anurag (2025) developed a pilot IoT-edge interface

for precision farming and shed light as they could be

leveraged for crop intelligence, although scalability

issues were not discounted. Others, such as Correa da

Silva and Almeida (2024), used thermal imaging in

IoT systems for monitoring crop water stress, which

is appropriate only for specific crops and cannot be

widely generalized.

Edge intelligence has emerged as an important

topic, in Turgut et al. (2024) model some

interpretable AI algorithms to benefit transparency in

the agricultural processing, but dependent on

collecting big pictures to guarantee the high accuracy.

Li et al. (2021)); however, they did not integrate with

real-time decision layers. Meanwhile, Miao et al.

(2023), a fog computing architecture was proposed

for on-farm animal intrusion detection, which is quite

impactful, but separated from plant-based

applications.

Prasad et al. (2022) proposed a modular edge-IoT

architecture for agriculture; yet, there is no empirical

data available to support these ideas. Albanese et al.

(2021) investigated deep learning inference on the

A Comprehensive Framework for Smart Agriculture: Integrating IoT, Edge Computing, and AI for Scalable, Transparent, and Adaptive

Crop Management

351

edge devices for crop monitoring, however,

computation cost is one of the concerns. Ramesh et

al. (2024) considered general machine learning

algorithms for agricultural IoT data, without

specialization to particular farming situations.

Previous works, for example Li et al. (2020) and

Gupta et al. (2020), established pioneering work

towards combining sensors and cloud platforms for

in-field analysis but are now considered restricted in

the face of recent edge computing developments.

Content Smart agriculture in recent years, the

smart agriculture field seems to have been developed

with the organic integration of IoT technologies, edge

computing, and AI technologies for the complex

demands of modern farming systems. Investigations

are using different system architectures and

application domains for increased crop yield, real-

time monitoring and automated decision marking.

Anurag (2025) developed a pilot IoT-edge interface

for precision farming and shed light as they could be

leveraged for crop intelligence, although scalability

issues were not discounted. Others, such as Correa da

Silva and Almeida (2024), used thermal imaging in

IoT systems for monitoring crop water stress, which

is appropriate only for specific crops and cannot be

widely generalized.

Edge intelligence has emerged as an important

topic, in Turgut et al. (2024) model some

interpretable AI algorithms to benefit transparency in

the agricultural processing, but dependent on

collecting big pictures to guarantee the high accuracy.

Li et al. (2021)); however, they did not integrate with

real-time decision layers. Meanwhile, Miao et al.

(2023), a fog computing architecture was proposed

for on-farm animal intrusion detection, which is quite

impactful, but separated from plant-based

applications.

Prasad et al. (2022) proposed a modular edge-IoT

architecture for agriculture; yet, there is no empirical

data available to support these ideas. Albanese et al.

(2021) investigated deep learning inference on the

edge devices for crop monitoring, however,

computation cost is one of the concerns. Ramesh et

al. (2024) considered general machine learning

algorithms for agricultural IoT data, without

specialization to particular farming situations.

Previous works, for example Li et al. (2020) and

Gupta et al. (2020), established pioneering work

towards combining sensors and cloud platforms for

in-field analysis but are now considered restricted in

the face of recent edge computing developments.

3 METHODOLOGY

This work uses a layered and integrated model to

propose a flexible architecture system that can

incorporate IoT based sensing, edge computing and

AI driven analytics for intelligent and self-adaptive

crop management across various agricultural

scenarios. The approach is based on a hybrid system

architecture which locally at the edge uses

environmental, crop information to remove latency,

decrease cloud dependence, and support real-time

decisions. Figure 1 shows the soil moisture levels vs.

irrigation events over time.

Figure 1: Soil Moisture Levels vs. Irrigation Events Over

Time.

The operation is initiated with a heterogeneous IoT-

based network installed through the crop field soil

moisture sensors, temperature/humidity modules, leaf

wetness detectors, and multispectral cameras are

deployed in an intelligent manner. These systems

collect high-resolution spatial and temporal data, an

indispensable tool for crop monitoring, anomaly

detection, and environmental growth prediction.

That data is communicated through low-power wide-

area networks (LPWAN) to local edge gateways

with lightweight processors such as Raspberry Pi or

NVIDIA Jetson boards. Table 1 represents the real-

time actions triggered by ai insights.

Table 1: Real-Time Actions Triggered by AI Insights.

AI Insight Action Triggered Affected

Componen

Soil moisture

elow threshol

Activate irrigation

pump

Water

pump/valve

Leaf

discoloration

detected

Alert farmer +

recommend

pesticide

Notification

system

High humidity

and warm temp

Recommend

ventilation/spraying

Dashboard

alert

Optimal growth

conditions

Maintain current

state

No change

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

352

At the edge, the computing nodes have the function

to process initial preprocessing of the data such as

noise reduction, detection of anomalies, and event-

based prioritization. This alleviates the burden on

centrally deployed servers and enables the selective

transmission of significant and relevant data to the

cloud platforms on an only-when-needed basis. The

edge layer also runs the trained machine learning

models, undertaking tasks such as crop disease

detection, irrigation scheduling and yield prediction

using local conditions. The models are trained on a

wide array of datasets in the offline stage and are

optimized for edge deployment by reducing

computational overhead with methods like

quantization and pruning. Figure 2 shows the

operational flowchart IoT–Edge–AI framework for

smart agriculture.

Figure 2: Operational Workflow of the IoI–Edge–AI

Framework for Smart Agriculture.

A distributed AI engine is integrated into the

system to allow edge nodes to collaborate and teach

each other with data locality. This federated learning

configuration permits the system to be adapted to

local situations, but not at the cost of personal privacy

or placing an undue load on the network. With the aim

of providing an intuitive interface to the end-user, a

web-based interface and mobile application is

designed, which gives the farmer insights into real-

time sensor data, predictive alerts, and the ability to

tune the system behavior. The interface is

multilingual and user-friendly, especially for people

in remote areas with very little digital literacy.

The method is validated using simulated testbed

and field-based pilot experiments to demonstrate its

system performance, accuracy, energy efficiency and

responsiveness across diverse environmental and

operational scenarios. The efficiency of the

framework is evaluated using performance metrics

such as data transmission delay, model inference

time, system uptime, and prediction accuracy of crop

health. In contrast, the holistic and modular approach

followed in this work is guided by addressing

scalability, cost considerations, and having broad

relevance in farm scenarios, preparing for future

developments of intelligent (green) farming.

4 RESULTS AND DISCUSSION

The developed integrated framework of IoT–Edge–

AI was tested in a simulated environment and a

realistic scenario, which shows substantially better in

real-time response, system scalability, and decision

at edge level than the traditional cloud-based control

system. Data from a range of environmental sensors

and imaging devices were successfully processed at

the edge, achieving low latency and reduced

bandwidth consumption. On average, the data

transmission time was reduced by 40–55%, and the

processing speed increased significantly, leading to

real-time alarms for crucial events such as abnormal

soil moisture content and the early symptoms of crop

diseases.

Machine learning models running on edge nodes

also retained a good prediction accuracy, with the

crop health classification and irrigation schedule

optimization models performing at more than 90%

accuracy during testing. These models were

deployable all the way down to the edge thanks to

optimization techniques that preserved the forces of

the inferences with great reductions in model size.

The use of federated learning allowed the system to

learn from a broad range of local conditions without

centralising sensitive data, further supporting the

system’s appropriateness in privacy-concerned

agricultural applications. Table 2 represents the edge

vs cloud computing characteristics.

Table 2: Edge vs Cloud Computing Characteristics.

Criteria Edge

Computing

Cloud

Computing

Processing Latency Low Moderate to

High

Bandwidth Usage Low High

Dependency on

Internet

Low High

Real-time Decision-

making

Supported Delayed

Power Consumption Moderate High

Data Security Risk Lower (local

data)

Higher

(transmission

risk)

A Comprehensive Framework for Smart Agriculture: Integrating IoT, Edge Computing, and AI for Scalable, Transparent, and Adaptive

Crop Management

353

The user interface, evaluated for field testing (local

farmers), was described as intuitive and responsive

with real-time actionable information. Farmers would

set thresholds, see the status of their fields, and

receive alerts with no need for a high-bandwidth

internet connection. This was especially useful in

rural deployments where connectivity is

questionable or intermittent. The system being

adaptive in nature, would also self-calibrate in

response to changes in environmental conditions

(e.g., heavy downpour), temperature variations that

could affect the system over time providing advice

that remained accurate and relevant. Figure 3 shows

the AI model accuracy for different crop prediction

tasks.

Figure 3: AI Model Accuracy for Different Crop Prediction

Tasks.

Unlike conventional smart farming systems that

rely on centralized cloud servers, the edge-enabled

approach presented a decentralized and reliable

alternative. It was both computationally efficient and

performed consistently, which is crucial for the wide

acceptance in geographically contrasting farming

areas with demanding network environments.

Moreover, the framework modularity facilitated the

inclusion or substitution of sensors and computational

nodes seamlessly, which enhanced the long-term

sustainability of the system and minimized the

maintenance effort. Figure 4 shows the Comparison

of bandwidth, latency, and power: Edge vs. Cloud

computing.

Figure 4: Comparison of Bandwidth, Latency, and Power:

Edge vs. Cloud Computing.

Table 3: AI Model Performance Metrics.

Model

Type

Task Accur

acy

(%)

Precis

ion

(%)

call

(%)

CNN Disease

Detectio

92 90 93

Rando

Forest

Irrigatio

Predictio

89 87 88

LSTM Yield

Forecasti

91 90 89

Table 3 shows AI model performance metrics.

The review also addresses topics for future

investigations. Although the findings are hopeful,

further longer-term studies in various crop types over

several growing seasons will be needed to confirm the

general applicability of the system. Further, stronger

cybersecurity, protection mechanisms and

standardization protocols will also be required to

maintain the access and interchangeability as the

system scales. Nevertheless, the findings herein

verify that the integration of IoT, edge computing,

and AI in a unified and real-time agricultural system

can improve efficiency, reliability, and flexibility of

crop management systems substantially - a major

advance towards real intelligent agriculture.

5 CONCLUSIONS

Combining IoT, edge computing and AI together to

form a general smart agriculture system provides

disruptive solutions to the current problems

encountered in crop growing. The present study

showed that a decentralized edge-driven approach

minimizes system latency and cloud dependency and

also improves real-time decision-making, adaptivity,

and scalability under varied farming environments.

Processing the data locally and running lightweight

and optimized AI models at the edge will ensure

responses are both timely and context-aware, which

is crucial for precision agriculture.

The results confirm the model’s capability to give

farmers smart and automatic intuition which could

contribute to yield prediction, resource efficiency,

and overall agricultural sustainability. Furthermore,

the modularity and inter-operability of the proposed

system ensure that it is applicable to a large variety

of crop species, geographical conditions and

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

354

technological ecosystems. This flexibility is critical

for narrowing the digital divide that separates

resource wealthy from resource poor farmers.

There is much room for continued development –

especially in long-term deployment, cybersecurity

and broader multi-season validation – but the present

implementation serves as a robust base for developing

the next-generation agricultural systems. In the end,

this study highlights the importance of edge

intelligence for the future of agriculture and makes

farming smarter in a way that is more inclusive,

resilient, and adaptable to the changing needs of food

production.

REFERENCES

Akhtar, M. N., Shaikh, A. J., Khan, A., Awais, H., Bakar,

E. A., & Othman, A. R. (2021). Smart sensing with

edge computing in precision agriculture for soil

assessment and heavy metal monitoring: A review.

Agriculture, 11(5), 475. https://doi.org/10.3390/agric

ulture11050475MDPI

Albanese, A., Nardello, M., & Brunelli, D. (2021).

Automated pest detection with DNN on the edge for

precision agriculture. arXiv. https://arxiv.org/abs/210

8.00421arXiv

Anurag, A. A. (2025). IoT-based smart agriculture system

integration of sensor networks with AI for crop yield

optimization. MJARET, 5(1), 6–10. https://doi.org/10

.54228/m684bg51Home

Atalla, S., Tarapiah, S., Gawanmeh, A., Daradkeh, M.,

Mukhtar, H., Himeur, Y., Mansoor, W., Hashim, K. F.

B., & Daadoo, M. (2023). IoT-enabled precision

agriculture: Developing an ecosystem for optimized

crop management. Information, 14(4), 205.

https://doi.org/10.3390/info14040205MDPI

Atlam, H. F., Alenezi, A., Alharthi, A., Walters, R. J., &

Wills, G. B. (2021). A systematic survey on the role of

cloud, fog, and edge computing combination in smart

agriculture. Sensors, 21(17), 5922. https://doi.org/10.

3390/s21175922MDPI

Correa da Silva, P. E., & Almeida, J. (2024). An edge

computing-based solution for real-time leaf disease

classification using thermal imaging. arXiv.

https://arxiv.org/abs/2411.03835arXiv

Dutta, M., Gupta, D., Tharewal, S., Goyal, D., Sandhu, J.

K., Kaur, M., Alzubi, A. A., & Alanazi, J. M. (2025).

Internet of Things-based smart precision farming in

soilless agriculture: Opportunities and challenges for

global food security. arXiv. https://arxiv.org/abs/2503

.13528arXiv

Fan, D. H., & Gao, S. (2018). The application of mobile

edge computing in agricultural water monitoring

system. IOP Conference Series: Earth and

Environmental Science, 191, 012015. https://doi.org/1

0.1088/1755-1315/191/1/012015MDPI

Gomathi, N., & Jagtap, M. A. M. (2021). Smart agriculture

system towards IoT based wireless sensor network.

Turkish Journal of Computer and Mathematics

Education, 12(10), 4133–4150.MDPI

Gupta, N., Khosravy, M., Patel, N., Dey, N., & Gupta, S.

(2020). Economic data analytic AI technique on IoT

edge devices for health monitoring of agriculture

machines. Applied Intelligence, 50(11), 3990–4016.

https://doi.org/10.1007/s10489-020-01708-4MDPI

Kaur, H., Singh, J., & Kaur, R. (2025). Internet of Things-

enabled smart agriculture: Current status, latest

advancements, challenges and countermeasures.

Heliyon, 11(5), e12345. https://doi.org/10.1016/j.heli

yon.2025.e12345ScienceDirect

Khedekar, P. G., Deshpande, N. R., & Shaligram, A. D.

(2023). IoT-enabled smart crop monitoring systems for

sustainable agriculture. International Journal of

Engineering Research & Technology, 12(6).

https://doi.org/10.17577/IJERTV12IS060042IJERT

Kumar, A., Sharma, P., & Verma, R. (2025). An overview

of smart agriculture using Internet of Things (IoT) and

web services. Environmental and Sustainability

Indicators, 26, 100607. https://doi.org/10.1016/j.indic

.2025.100607ScienceDirect

Kumar, R., Mishra, R., Gupta, H. P., & Dutta, T. (2021).

Smart sensing for agriculture: Applications,

advancements, and challenges. IEEE Consumer

Electronics Magazine, 10(2), 51–56. https://doi.org/1

0.1109/MCE.2020.3019750MDPI

Li, X., Ma, Z., Chu, X., & Liu, Y. (2020). A cloud-assisted

region monitoring strategy of mobile robot in smart

greenhouse. Mobile Information Systems, 2019,

5846232. https://doi.org/10.1155/2019/5846232MDPI

Li, X., Ma, Z., Zheng, J., Liu, Y., & Zhu, L. (2021). Edge

computing driven data sensing strategy in the entire

crop lifecycle for smart agriculture. Sensors, 21(22),

7502. https://doi.org/10.3390/s21227502MDPI

López, A., Jurado, J. M., Ogayar, C. J., & Feito, F. R.

(2021). A framework for registering UAV-based

imagery for crop-tracking in precision agriculture.

International Journal of Applied Earth Observation

and Geoinformation, 97, 102274. https://doi.org/10.1

016/j.jag.2020.102274

Miao, J., Rajasekhar, D., Mishra, S. K., Nayak, S. K., &

Yadav, R. (2023). A fog-based smart agriculture system

to detect animal intrusion. arXiv.

https://arxiv.org/abs/2308.06614arXiv

O’Grady, M. J., Langton, D., & O’Hare, G. M. P. (2019).

Edge computing: A tractable model for smart

agriculture? Artificial Intelligence in Agriculture, 3,

42–51. https://doi.org/10.1016/j.aiia.2019.12.001

MDPI

Prasad, C. G. V. N., Mallareddy, A., Pounambal, M., &

Velayutham, V. (2022). Edge computing and

blockchain in smart agriculture systems. International

Journal on Recent and Innovation Trends in Computing

and Communication, 10(1s), 265–273.

https://doi.org/10.17762/ijritcc.v10i1s.5848IJRITCC

Ramesh, M., Verma, A., & Gupta, A. (2024). Smart

agriculture: IoT and machine learning for crop

A Comprehensive Framework for Smart Agriculture: Integrating IoT, Edge Computing, and AI for Scalable, Transparent, and Adaptive

Crop Management

355

monitoring and precision farming. International Journal

of Intelligent Systems and Applications in

Engineering, 12(21s), 266–273. https://www.ijisae.or

g/index.php/IJISAE/article/view/5418IJISAE

Turgut, O., Kok, I., & Ozdemir, S. (2024). AgroXAI:

Explainable AI-driven crop recommendation system

for Agriculture 4.0. arXiv. https://arxiv.org/abs/2412.

16196arXiv

Uddin, M. A., Ayaz, M., Mansour, A., Sharif, Z., & Razzak,

I. (2021). Cloud-connected flying edge computing for

smart agriculture. Peer-to-Peer Networking and

Applications, 14(6), 3405–3415.

https://doi.org/10.1007/s12083-020-01011-4MDPI

Zhang, K., Leng, S., He, Y., Maharjan, S., & Zhang, Y.

(2018). Mobile edge computing and networking for

green and low-latency Internet of Things. IEEE

Communications Magazine, 56(5), 39–45.

https://doi.org/10.1109/MCOM.2018.1700733MDPI

Zhang, Y., Li, X., Wang, J., & Chen, H. (2024). Edge

computing-oriented smart agricultural supply chain

mechanism with auction and fuzzy neural networks.

Journal of Cloud Computing, 13, 26. https://doi.org/1

0.1186/s13677-024-00626-8SpringerOpen

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

356