Agricultural Irrigation Recommendation and Alert (AIRA) system using optimization and machine learning in Hadoop for sustainable agriculture

Veerachamy, Ramachandran; Ramalakshmi, R.

doi:10.1007/s11356-021-13248-3

“…Sensors and actuators have been developed for various applications of WSNs, including agriculture. Smart applications and methodologies for irrigation, soil fertilization, pest control, and disease forecasting have attracted important attention among researchers in the field of precision agriculture [14][15][16][17][18][19][20][21][22][23][24].…”

Section: Evolution Of Irrigationmentioning

confidence: 99%

“…Many factors are dependent on the type of irrigation optimization that is performed [15][16][17]. Furthermore, all of the factors differ based on the geography, crop, soil type, irrigation methodology, and the amount of rainfall [18,19].…”

Section: Factors To Be Considered For Effective Irrigationmentioning

confidence: 99%

Exploiting IoT and Its Enabled Technologies for Irrigation Needs in Agriculture

Veerachamy

¹

,

Ramalakshmi

²

,

Kavin

³

et al. 2022

Water

Self Cite

View full text Add to dashboard Cite

The increase in population growth and demand is rapidly depleting natural resources. Irrigation plays a vital role in the productivity and growth of agriculture, consuming no less than 75% of fresh water utilization globally. Irrigation, being the largest consumer of water across the globe, needs refinements in its process, and because it is implemented by individuals (farmers), the use of water for irrigation is not effective. To enhance irrigation management, farmers need to keep track of information such as soil type, climatic conditions, available water resources, soil pH, soil nutrients, and soil moisture to make decisions that resolve or prevent agricultural complexity. Irrigation, a data-driven technology, requires the integration of emerging technologies and modern methodologies to provide solutions to the complex problems faced by agriculture. The paper is an overview of IoT-enabled modern technologies through which irrigation management can be elevated. This paper presents the evolution of irrigation and IoT, factors to be considered for effective irrigation, the need for effective irrigation optimization, and how dynamic irrigation optimization would help reduce water use. The paper also discusses the different IoT architecture and deployment models, sensors, and controllers used in the agriculture field, available cloud platforms for IoT, prominent tools or software used for irrigation scheduling and water need prediction, and machine learning and neural network models for irrigation. Convergence of the tools, technologies and approaches helps in the development of better irrigation management applications. Access to real-time data, such as weather, plant and soil data, must be enhanced for the development of effective irrigation management applications.

show abstract

“…In this paper, we opt for HD as being invariant to noise, outliers and data scale, since the nature of this metric prevents each feature from having a distance greater than one, regardless of the scale of the features in the targeted dataset. Furthermore, HD had been shown to outperform a wide range of machine learning similarity measures, including the most common ones like ED and MD [184,185,186,187,188].…”

Section: Minority Majoritymentioning

confidence: 99%

Stop Oversampling for Class Imbalance Learning: A Critical Review

Hassanat

¹

,

Tarawneh

²

,

Altarawneh

³

2022

Preprint

4

0

View full text Add to dashboard Cite

For the last two decades, oversampling has been employed to overcome the challenge of learning from imbalanced datasets. Many approaches to solving this challenge have been offered in the literature. Oversampling, on the other hand, is a concern. That is, models trained on fictitious data may fail spectacularly when put to real-world problems. The fundamental difficulty with oversampling approaches is that, given a real-life population, the synthesized samples may not truly belong to the minority class. As a result, training a classifier on these samples while pretending they represent minority may result in incorrect predictions when the model is used in the real world. We analyzed a large number of oversampling methods in this paper and devised a new oversampling evaluation system based on hiding a number of majority examples and comparing them to those generated by the oversampling process. Based on our evaluation system, we ranked all these methods based on their incorrectly generated examples for comparison. Our experiments using more than 70 oversampling methods and three imbalanced real-world datasets reveal that all oversampling methods studied generate minority samples that are most likely to be majority. Given data and methods in hand, we argue that oversampling in its current forms and methodologies is unreliable for learning from class imbalanced data and should be avoided in real-world applications.

show abstract

“…In this paper, we opt for HD as being invariant to noise, outliers and data scale, since the nature of this metric prevents each feature from having a distance greater than one, regardless of the scale of the features in the targeted dataset. Furthermore, HD had been shown to outperform a wide range of machine learning similarity measures, including the most common ones like ED and MD [184,185,186,187,188].…”

Section: Minority Majoritymentioning

confidence: 99%

Stop Oversampling for Class Imbalance Learning: A Critical Review

Hassanat¹,

Tarawneh²,

Altarawneh³

2022

Preprint

0

View full text Add to dashboard Cite

For the last two decades, oversampling has been employed to overcome the challenge of learning from imbalanced datasets. Many approaches to solving this challenge have been offered in the literature. Oversampling, on the other hand, is a concern. That is, models trained on fictitious data may fail spectacularly when put to real-world problems. The fundamental difficulty with oversampling approaches is that, given a real-life population, the synthesized samples may not truly belong to the minority class. As a result, training a classifier on these samples while pretending they represent minority may result in incorrect predictions when the model is used in the real world. We analyzed a large number of oversampling methods in this paper and devised a new oversampling evaluation system based on hiding a number of majority examples and comparing them to those generated by the oversampling process. Based on our evaluation system, we ranked all these methods based on their incorrectly generated examples for comparison. Our experiments using more than 70 oversampling methods and three imbalanced real-world datasets reveal that all oversampling methods studied generate minority samples that are most likely to be majority. Given data and methods in hand, we argue that oversampling in its current forms and methodologies is unreliable for learning from class imbalanced data and should be avoided in real-world applications.

show abstract

Agricultural Irrigation Recommendation and Alert (AIRA) system using optimization and machine learning in Hadoop for sustainable agriculture

Cited by 27 publications

References 40 publications

Exploiting IoT and Its Enabled Technologies for Irrigation Needs in Agriculture

Exploiting IoT and Its Enabled Technologies for Irrigation Needs in Agriculture

Stop Oversampling for Class Imbalance Learning: A Critical Review

Stop Oversampling for Class Imbalance Learning: A Critical Review

Contact Info

Product

Resources

About