Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics

R. Sujatha, S. L. Aarthy, R. Vettriselvan, R. Sujatha, S. L. Aarthy, R. Vettriselvan

• Publisher: CRC Press
• Year: 2021
• Print ISBN: 9780367466633
• eBook ISBN: 9781000454543
• Edition: 1
• Topic: Computer Science
• Subtopic: Computer Science General
• Index: Computer Science

Data science revolves around two giants: Big Data analytics and Deep Learning. It is becoming challenging to handle and retrieve useful information due to how fast data is expanding. This book presents the technologies and tools to simplify and streamline the formation of Big Data as well as Deep Learning systems.

This book discusses how Big Data and Deep Learning hold the potential to significantly increase data understanding and decision-making. It also covers numerous applications in healthcare, education, communication, media, and entertainment. Integrating Deep Learning Algorithms to Overcome Challenges in Big Data Analytics offers innovative platforms for integrating Big Data and Deep Learning and presents issues related to adequate data storage, semantic indexing, data tagging, and fast information retrieval.

FEATURES

• 
  
  

• Provides insight into the skill set that leverages one's strength to act as a good data analyst

• 
  
  

• Discusses how Big Data and Deep Learning hold the potential to significantly increase data understanding and help in decision-making

• 
  
  

• Covers numerous potential applications in healthcare, education, communication, media, and entertainment

• 
  
  

• Offers innovative platforms for integrating Big Data and Deep Learning

• 
  
  

• Presents issues related to adequate data storage, semantic indexing, data tagging, and fast information retrieval from Big Data

This book is aimed at industry professionals, academics, research scholars, system modelers, and simulation experts.

1 A Study on Big Data and Artificial Intelligence Techniques in Agricultural Sector

D. Helen and C. Padmapriya

DOI: 10.1201/9781003038450-1

CONTENTS

1.1 Introduction

1.1.1 The Life Cycle of Agriculture

1.2 The Role of Big Data in the Agricultural Sector

1.2.1 Overall Characteristics of Big Data Applicable to the Agricultural Sector

1.2.2 The Processing Steps of Big Data in Agriculture

1.3 Some Cases of the Use of Big Data on Farm

1.3.1 To Evade Food Scarcity of the Growing Population

1.3.2 Managing Pesticides and Farm Equipment

1.3.3 Supply Chain Management

1.3.4 Yield Prediction and Risk Management

1.4 Challenges Faced by Farmers versus AI Solutions

1.4.1 Forecasting Weather Conditions

1.4.2 Decision-Making

1.4.3 Diagnosing Defects in Soil and Weed Detection

1.4.4 Nutrition Treatment

1.5 AI Techniques in Agricultural Sector

1.5.1 Machine Learning

1.5.1.1 Supervised Learning

1.5.1.2 Unsupervised Learning

1.5.2 Neural Networks

1.5.2.1 Working Process of Neural Network

1.5.3 The Expert System

1.5.3.1 Components of the Expert System

1.5.3.2 The Working Process of the Expert System

1.5.4 The Decision Tree

1.5.4.1 Working Steps of the Decision Tree

1.5.5 Support Vector Machine

1.5.6 Random Forest

1.5.6.1 Working Steps of an RF

1.6 Application of AI in Agriculture

1.6.1 Image Recognition

1.6.2 Disease Detection

1.6.3 Field Management

1.6.4 Driverless Tractor

1.6.5 Weather Forecasting

1.6.6 AI Agricultural Bots

1.6.7 Reduction of Pesticide Usage

1.7 Advantages of Using AI in Agriculture

1.8 Conclusion

References

1.1 Introduction

Agriculture plays a vital role in the overall development of a country’s economy. Agriculture is the major source of livelihood (Guruprasad et al., 2019). To ensure the financial development of a country, it is necessary to monitor and estimate crop production (Shah & Shah, 2019). The main aim of the country is to increase crop yield using minimal resources (Kumar et al., 2015). The yield prediction is most important for universal food production. The accurate crop prediction and the timely report reinforce the overall food security. The crop yield prediction helps the government in planning for manufacturing, supply, and utilization of the food. The major issue for agricultural development is an accurate yield prediction for the number of crops involved in the production.

Big Data and Artificial Intelligence (AI) is an emerging technology in the agricultural sector, which automates the agricultural process. In the agricultural field, AI techniques are applied in three major areas: (1) Artificial Robots, which harvest crops faster and in high volume; (2) Deep Learning and Computer Vision techniques, which monitor the health of crops and soil; and (3) Predictive Analysis Method, which predicts environmental changes such as temperature, rainfall, etc.

AI techniques work efficiently in complex relationships between Input and Output variables (Jain et al., 2017). AI techniques depend on the semi-parametric and non-parametric structures, and the justification is based on accurate prediction (Breiman, 2001). Machine Learning, Artificial Neural Networks (Fortin et al., 2011; Liu et al., 2001), Regression Trees, and Support Vector Machines (Jaikla et al., 2008) are the popular AI techniques used for crop yield prediction.

1.1.1 The Life Cycle of Agriculture

Soil Preparation: This is the first stage of farming where farmers sow the seeds in the soil. This process involves breaking up huge soil clumps and removing wreckage such as sticks, rocks, and roots. Fertilizers and organic matter are added according to the type of crop.

Sowing: At this stage, climate conditions play an important role. The distance between two seeds and the depth for planting seeds is necessary while sowing the seeds.

Adding Manures and Fertilizers: Soil fertility is an important factor that helps farmers to grow nutritious and healthy crops. Fertilizers are chemical substances with the composition of nitrogen, phosphorus, and potassium that are added to the soil to increase crop productivity. Crop yield can be increased by adding manure and fertilizers.

Irrigation: Humidity and soil moisture can be maintained at this stage. Watering the crops plays an important role here. Underwatering and overwatering can damage the growth of crops.

Weeding: Weeds are the unwanted plants that grow along with the main crops. Weeding plays a necessary role in agriculture because the presence of weeds decreases crop yield, reduces crop quality, and increases production cost.

Harvesting: In this phase, ripe crops are collected from the fields. A lot of laborers are needed during this activity. Harvesting also includes post-harvest handling such as cleaning, sorting, packing, and cooling.

Threshing: This is the process of removing grains from the straw and chaff. This operation can be carried out manually or through machines. Threshing can be done by three methods that include rubbing, impact, and stripping.

Storage: Foodgrains obtained after harvesting should be dried to remove moisture. The products are stored in such a way as to guarantee food security. Grains are stored in silos. This phase also includes the packing and transportation of crops (Figure 1.1).

Figure 1.1 The life cycle of agriculture.

1.2 The Role of Big Data in the Agricultural Sector

Big Data plays a prominent role in the agricultural sector. Big Data is a combination of technology and analytics that can collect a huge amount of both structured and unstructured data. It compiles and processes these data effectively to assist in decision-making (Sonka, 2014). To process these large amounts of data, advanced tools are required. Real-time data analytics and automated processing are done with Big Data. In order to implement Big Data successfully, many techniques are used, such as predictive analytics, machine learning, time series analysis, classification and clustering, data mining, regression analytics, etc.

More advancement in the technology of Big Data can establish a smart agricultural system. Agriculture is rapidly moving from traditional methods to these modern tools and technology. A farming process would be simpler and better with the help of Big Data. Big Data can solve complex problems in agricultural systems. Massive data are collected through various kinds of control devices, drones, satellites, and sensors. These data are analyzed and used to plan for better crop production. Farmers can face critical problems regarding decision-making (Sonka, 2014). Using Big Data analytics, farmers can make predictions and appropriate decisions with the data drawn from the preceding years’ rainfall and climate conditions to avoid crop failure. Big Data not only creates smart farming but als...

Table of contents

• Cover
• Half Title
• Series Page
• Title Page
• Copyright Page
• Contents
• Preface
• Editors
• Contributors
• Chapter 1 A Study on Big Data and Artificial Intelligence Techniques in Agricultural Sector
• Chapter 2 Deep Learning Models for Object Detection in Self-Driven Cars
• Chapter 3 Deep Learning for Analyzing the Data on Object Detection and Recognition
• Chapter 4 Emerging Applications of Deep Learning
• Chapter 5 Emerging Trend and Research Issues in Deep Learning with Cloud Computing
• Chapter 6 An Investigation of Deep Learning
• Chapter 7 A Study and Comparative Analysis of Various Use Cases of NLP Using Sequential Transfer Learning Techniques
• Chapter 8 Deep Learning for Medical Dataset Classification Based on Convolutional Neural Networks
• Chapter 9 Deep Learning in Medical Image Classification
• Chapter 10 A Comparative Review of the Role of Deep Learning in Medical Image Processing
• Index