eChapters

As we know there are different branches of artificial Intelligence and machine Learning of one of them which has become a most advance and widely used branch of artificial Intelligence in every field of this generation whether it may be either electronics, civil, mechanics, Bioengineering, medical or agriculture etc., In this chapter we will study about machine learning and its types with the most common algorithms of machine learning which are being mostly used in different scenarios and their implementation using python language has been discussed in the implementation part of this book. Here we will also see where machine learning can be used.

i. Introduction

Machine learning is a subset of Artificial Intelligence and one of the most important part of artificial Intelligence. It is a field of Computer science which is totally differs from traditional computational approaches. In traditional approaches, a set of instruction is explicitly provided to the algorithm to solve any problem. Whereas in Machine Learning is a domain of an AI which uses a statistical analysis and can enables a system to always learn from its data without any external inputs in order to give an essential output. Due to this machine learning makes computers in advance to make model which provide decision based on input data.

Machine Learning involves a lot of algorithms which usually based on their requirements and functionalities to use where and when. To make a machine learning model we always require the data on which model can be made. Machine learning uses the algorithm which continuously learns from the data available as training data. A machine learning model is generated after the training of algorithm from the data. After the training completes, when trained model is provided with other real-life data then you can get an essential outcome. For example, in figure 3.1 Machine learning Model we use a predictive algorithm and make a model by providing it with some data, and later on we can receive prediction’s based on real data as input.

Introduction

Agriculture has played an important role in the global economy in recent years. The further growth of the population is leading to a gradual decrease in the area of the agricultural land and further growing stresses on the farm system. Agricultural food production methods are rising in demand for successful and healthy. Innovative sensoring and motive technologies and advanced information and communications systems and Artificial Intelligence must supplement conventional agricultural management methods to speed up farm productivity growth more accurately, thereby promoting the production of high-quality and high-performance agriculture. Computer vision monitoring systems have become valuable tools in farm operations over the past decades, and their use has increased significantly.

What is Computer Vision?

Computer vision can be characterized as a field of AI for extracting information from digital images. The type of data obtained from an image may be different from recognition, navigational space measurements or applications of increased reality.

The applications of computer vision can also be described. Computer vision builds algorithms that recognize and use the quality of pictures for other purposes.

In this chapter we will cover all the basics libraries and some frameworks of machine learning, deep learning and computer vision. We will discuss all about their use with an example and instruction which will states the commands to install to those libraries for building any project in our system. So let’s begin

What is a Library?

Library is an aggregate of features and methods that allow you to take many actions without getting your own code written.

For instance, the libraries that you have to know are if you work with data, numpy, scipy, pandas, etc. They have very simple data processing functions that save you time for small tricks.

In this Chapter the precision farming/ Agriculture is discussed along with its steps of implementation. It also includes how artificial Intelligence plays role to perform precision farming/ agriculture in various way along with its scope, limitation and challenges.

Introduction

The primary source of livelihood is agriculture in India, where two thirds of India’s population, services and the private sector account for the remainder. Agricultural land accounts for about 43 percent of the geographical area of India. In earlier days, India was largely dependent in terms of food imports, but over the years, the country’s production of grain and seeds was self-sufficient, and this effort led to the formation of the Green Revolution. In fact, there was strong effort to achieve food self-sufficiency. This trend has continued up to now and continuous improvements have occurred. Precision agriculture or precision farming means the right thing to do, in the right way, on the right place and at the right time. Precision agriculture is expected to suit the agro-climate activities to improve application precision. Farming land has declined a bit in the last 40 years but the number of farmers has increased. According to the 2010–11 Agriculture Census, a total of 138.35 million operating holdings were estimated (single farmers) and 159,59 million hectares were covered by operations.

Precision agriculture is a management technique that collects, processes and analyzes temporary, spatial and individual data and integrates this with other information in order to support management decisions based on an estimated variability to enhance efficiency of use of agricultural production resources, productivity, quality, profitability and sustainability. Precision Agriculture manages every input of crop production (fertilizer, specifically found calestone, herbicide, seeds, insecticide, etc. Reduce waste, boost income and maintain efficiency Place. Precision Agriculture adapts soil and crop management carefully to suit the different field conditions.

Deep learning enables automated analysis of agricultural images for crop classification, disease detection, weed identification, yield prediction and soil monitoring. This chapter examines Convolutional Neural Networks, Recurrent Neural Networks and Vision Transformers applied to imagery collected by satellites, drones and ground-based sensors. These models automatically identify patterns and features that conventional methods may overlook. Integration with precision agriculture can improve decision-making, increase crop productivity and reduce resource waste. Challenges include shortages of annotated datasets, limited interpretability and high computational requirements. Transfer learning, data augmentation, edge computing and real-time processing are discussed as approaches for enabling practical deployment in remote and resource-constrained agricultural environments.

Introduction

Accuracy and uncertainty analysis is an important step in preparation of surface map through geostatistical techniques or digital soil mapping approach. It is because that we rely on a map based on how much accurate it is and the degree of uncertainty associated with the estimates while the map was prepared. Any stakeholder for a soil map especially policy makers is interested in accuracy and uncertainty of the map before taking suitable land management decisions involving soil map as an input. Again the level of accuracy and uncertainty depends on the properties for which the map has been developed. If the property of interest is sensitive to environment or human consumption, then the accuracy level should be very high while the uncertainty level should be very low e.g. heavy metal concentration in soil, quality parameters of water etc.

Introduction

Soil is one of the vital resource, and is the basis of the existence of mankind. Management of this resource including its conservation and utilization is of crucial importance. It is a base on which all life depends. In the recent past, with burgeoning populations and the national goals of seeking self-sufficiency in food and fibre production, this resource base is slowly being stripped. While natural systems often adapt to stress in a remarkable fashion, some relationships - once destroyed - can never be restored. Soil resources can be assessed and monitored through its spectral signatures gathered through remote sensing.

The term ‘remote sensing’ is commonly restricted to methods that employ electromagnetic energy (such as lights, heat, micro wave) as means of detecting and measuring target characteristics. Sensors acquire data as various earth surface features reflect or e mit electromagnetic energy (EM energy). Remote sensing is the technology that is now the principal method (tool) by which the earth’s surface and atmosphere (as targets or objects of surveillance) are being observed, measured, and interpreted from vantage points. Remote sensing of the earth traditionally has used reflected energy in the visible and infrared, and emitted energy in the thermal infrared and microwave regions to gather radiation that can be analyzed numerically or used to generate images whose tonal variations represent different intensities of photons associated with a range of wavelengths that are received at the sensor.

Introduction

Over the past few decades, soil resources have witnessed many changes driven by demographic pressure and climate change. It is necessary to have up to date soil information to monitor the state of soils health with time. Soil resource inventory provides information about the potentialities and limitation of soils for its proper utilization. Soil survey offers an accurate and scientific inventory of different soils, their properties and extent. An in-depth knowledge of the type of soils and their spatial distribution is a prerequisite for developing rational land use planning. Remote sensing is the science of obtaining information about the earth’s surface without actually being in contact with it. On the other hand, proximal sensing refers to remotely sensed measurements that are taken at the field or laboratory level. Both these processes involve an interaction between incident radiation and the targets of interest. Fundamentally, remote sensing data products are a representation of the functional response of objects to energy sources. These are typically spectra, which are acquired as a discrete series of reflectance measurements taken at different wavelength intervals, or bands. In the shorter wavelengths of the electromagnetic spectrum (visible part), features can be detected by virtue of reflected solar energy, while in the longer wavelengths (microwave, thermal parts), sensing of emitted energy works. Conventional soil sampling, and subsequent laboratory analysis are generally time consuming and costly. In this context, remote sensing plays a crucial role for studying soil resources. The term remote sensing is generally used for airborne and space borne acquisitions, whereas proximal sensing refers to ground-based laboratory and field measurements. Advances in the quantitative disciplines like remote sensing and proximal sensing have laid the foundations for a spatial exploration of soil-system dynamics within a landscape context (Pennock and Veldkamp 2006).

4.1 Introduction

The objective of this chapter is to design a mobile app for agricultural field automation with Blynk app. Mobile app is designed to control the water management in field as per requirement. The complete system comprises of two sections sensor node and mobile app. Sensor node comprises of Node MCU, Power supply, LCD, Relay board, soil sensor and Ultrasonic sensor. The system is designed to establish control and communication with specific agricultural field to take sensory data from soil and ultrasonic level sensor and control the PUMP IN motor and PUMP OUT motor with the help of mobile app.Fig.4.1 shows a block diagram for a system to control specific agricultural field with mobile app and IoT modem.

7.1 Introduction

This chapter describes the development of data logger of agricultural field parameter monitoring system with MATLAB. The system comprises of Arduino, water level sensor, humidity sensor, light sensor, soil moisture sensor, temperature sensor, smoke detector, power supply, PC with MATLAB. The system is designed to monitor the environment and agriculture field parameters. The field device is designed to collect all physical parameters and same is communicated serially to MATLAB with I/O package. Fig.7.1 shows block diagram of the system. Table.7.1 shows the component list required to develop the system.

Introduction

Soil is a dynamic natural body, characterized by high degree of spatial variability due to combined effect of physical, chemical or biological processes that operate with different intensities at different scales (Goovaerts 1998). Reports have shown that there is large variability in soil properties, crop yield, disease, weed etc., not only in large-sized fields (Godwin and Miller 2003,Vrindts et al. 2005), but also in small-sized fields (Bhattacharya et al. 2008). Therefore, knowledge of hydro-physical properties of soils is crucial for management practices for all kinds of agricultural practices for efficient utilization of input resources. Plant growth and development is highly related to soil hydro-physical properties, which not only depend on soil intrinsic textural and chemical characteristics (Hamza and Anderson 2005) but also on soil management.

Soil physical properties which change with the variation in soil structure include bulk density, total porosity, pore geometry (size distribution, shape, continuity and tortuosity), penetration resistance and aggregate stability, consequently affecting soil hydraulic properties such as water retention characteristics, plant available water capacity, infiltration capacity and saturated hydraulic conductivity. These soil properties are dependent on seasonal climatic conditions, management practices, crop development and biological activity (Reynolds et al. 2007). The hydro-physical properties of soils, i.e., water retention and water permeability in both saturated and unsaturated zones not only shape soil water balance but also decide the conditions for plant growth, development and yield. They also determine water availability for the plant root system and the transfer of water with chemical compounds dissolved in it into deeper layers.

Introduction

The life support systems of a country and socioeconomic development of its people largely depend on soils. The soils are the most valuable natural resources for the society. It caters the basic needs of mankind by producing food, fibre and timber. It is therefore essential to know the distribution and extent of different soils and their qualities, potentialities and constraints for sustainable utilization of this valuable natural resource (Shyampura and Sehgal 1995). Information on distribution, potential and constraints of major forest soils are essential to design most appropriate soil management systems in order to increase productivity of forests as forests also offer excellent potential for poverty reduction and rural economic growth in India. However, unlike agriculture lands forest soils usually draw less attention and are ignored in spite of the fact that they nourish the lungs of the Earth. Soil quality is the most important factor in forest management decisions. Soils will determine productivity of a particular forest and management strategy. Knowing about forest soils can serve as a basis for forest management decisions, including land acquisition, species selection for planting, site preparation requirements, watershed development, fertilization prescriptions, stand density/ composition, and harvest timing, as well as decisions affecting land ownership and use.

Introduction

High degree of spatial variability in soil properties is observed at different scales. This variability is generally originated from the combined effect of physical, chemical or biological processes operating with different intensities at different scales (Goovaerts 1998). Knowledge of this spatial variationof soil properties is important in several land management applications e.g. variable rate application of nutrient and water in agricultural production system, land suitability classifications, modeling water balance components at landscape scales, precision farming etc. The concept of ‘management zone’ was also evolved in response to this large variability with the main purpose in efficient utilization of agricultural inputs with respect to spatial variation of soils and its properties (Franzluebbers et al. 1996, Atherton et al. 1999, Malhi et al. 2001). Therefore, an appropriate understanding of spatial variation of soil properties is essential. The most important way to gather knowledge in this aspect is to prepare soil maps through spatial interpolation of point-based measurements of soil properties. Here, a case study is discussed where soil water retention at two critical levels e.g. field capacity (FC) and permanent wilting point (PWP) was spatially characterized through geostatistical approaches. Because these two soil moisture contents guide farmers to apply right amount of irrigation water at right time. The study was carried out at the experimental farm of ICAR-Indian Agricultural Research Institute, New Delhi, India (28°37′-28°39′ N, 77°8′ 30″-77°10′30″ E, 217-241 m above mean sea level). A detailed discussion of the study is available in Santra et al. (2008)

Introduction

Globally, the SOC pool of 1,550 Pg (1 Pg = 1015 g) to 1-m depth is about three times that of biotic and twice that of atmospheric pools (Post et al. 1982, Watson et al. 2000). In arid and semi-arid ecosystems, SOC contents show high degree of spatial variability due to patchiness of vegetation (Wiesmeier et al. 2009). The arid ecosystem might play a key role in mitigation of climate change effects through sequestering carbon in soils (United Nations 2011). Therefore, a suitable land use system having high C sequestration potential for arid ecosystem needs to be identified and promoted. However, the prevailing conditions of arid ecosystems normally does not support dense vegetation. Therefore, low carbon stock is expected in both above-ground vegetation and below-ground soil. Fruit trees are an integral part of arid farming system and played a significant role to improve the nutritional security and employment opportunity of farmers but also have potential role to increase carbon storage both in biomass and soil. To quickly assess the soil carbon restoration programmes, it is important to know how much soil carbon is stored in an agricultural farm through adoption of different land management practices. Therefore, reliable estimates of SOC pools are essential to establish the soil carbon sequestration programmes at different landscape scales.

Now we have to learn how to enter numbers and text, how to edit any erroneous entry and then how to do simple calculations. Open empty excel spread sheet by clicking on the start menu in the window tool bars, click on Programs and then click on the Excel menu item.

6.1 Entering Numbers

Numeric entries are constant, can be integers, decimal fractions, integer fractions and scientific nations which can be entered by typing the number in the active cell [cell which can be made active by clicking the mouse on the cell.

Introduction

The term ‘Fish Marketing’ is composed of two broad meaning term ‘Fish’ and ‘Marketing’. Before discussing the methodological issues of fish marketing data analysis, we must understand the broader meaning of it as both words are being used frequently with a précised meaning. Google dictionary explains fish as ‘A limbless cold-blooded vertebrate animal with gills and fins living wholly in water’. But ‘fish’ as a component of fish marketing or social science study, means a product and a variety of product, which has different time, space and form utilities for consumers.

The word ‘marketing’ is not merely buying and selling of fish, rather it connotes a series of activities involved in moving goods or services from point of production to the point of consumption. So ‘fish marketing’ is defined as physical and institutional set up to perform all activities involved in the flow of fish, fish products and services from the point of initial fish production until they are in the hands of ultimate customers.

It includes assembling, handling, storage, transport, processing, wholesaling, retailing and export of fish and fishery products as well as accompanying supporting services such as market information, establishment of grades and standards, community trade, financing and price risk management and the institutions involved in performing the above functions.

It is desired to have an efficient and well planned distribution networkso that fish and fishery products move from the place of landing or production to the place of consumption at cheapest cost with quality –intact, ensuring the maximum price realization to the farmers or fish producers. It is really challenging to the public agencies involved to meet the requirements of all three major players, viz., fishermen or fish farmers, consumers and traders.

It includes all activities involved in creation of time, place, form and possession utility. Philip Kotler explained marketing as the science and art of exploring, creating, and delivering value to satisfy the needs of a target market at a profit. ‘Fish marketing’ is different from marketing of other goods and services and even differs a bit from marketing of variousagricultural goods and services.

5.1 Introduction
One of the main methods for cost avoidance and prevention is value engineering/ value analysis. “Society of American Value Engineers (SAVE)” states that value Analysis is the systematic use of known procedures which determine the function of a product or service, define a monetary value for the function, and provide the essential function reliably at the lowest overall cost. If these are applied to a new product, it is called value engineering. By analysing the function of any product, material part, component, system, or service, it is possible to find extraneous expenditures connected with them and effectively remove them without compromising the product’s quality, functional dependability, or ability to provide services. The principles and steps of value analysis/ value engineering will supplement the effort of design thinking.
5.2 Symptoms for Introducing Value Analysis (VA)
If one or more of the following symptoms exist, starting a VA programme is expected to yield very positive effects.
i. Sales of the company’s products are declining.
ii. The prices of the products of the company are greater than those of the products of its rivals.

The rapid growth of Large Language Models has produced remarkable advances in artificial intelligence but has also increased computational requirements, energy consumption and environmental impact. This chapter examines the relationship between large-scale AI development, energy efficiency and sustainable computing. Modern AI models may contain billions or even trillions of parameters and require extensive datasets, powerful accelerators and energy-intensive data-centre infrastructure for training and inference. The chapter investigates the environmental consequences associated with model development, including energy consumption, carbon emissions, cooling requirements and resource utilization. It examines model-level optimization techniques such as pruning, quantization and knowledge distillation as methods for reducing computational demands. System-level approaches, including specialized hardware accelerators, energy-efficient data centres, improved cooling systems, renewable energy and intelligent workload scheduling, are also considered. The distinction between energy efficiency and broader sustainability is emphasized, with attention to metrics such as energy per inference, total energy consumption, carbon emissions and hardware lifecycle impacts. The chapter further highlights the importance of transparent sustainability reporting, green computing and governance policies. Sustainable AI development requires balancing model performance and innovation with responsible resource use and long-term environmental objectives

Abstract

An intellectual property infringement is the violation of an intellectual property right of the owner. Infringement is established based on the law governing appropriate IPR in the concerned country. Both civil and criminal remedies are available under the concerned law. The present paper introduces the patent infringement as per Indian Patent Act, 1970. It discusses various modes and types of infringements which can take place. It further discusses a procedure to formulate opinion about product infringing a granted patent. In the end some usual defenses against patent infringements have been discussed. Some case studies have also been presented along with the damages awarded for the patent infringement.

Abstract

The paper discusses patentability aspect of subject matter. Patentable subject matter must satisfy three basic criteria i.e. novelty, inventiveness and industrial applicability, though few subject matter satisfying all the three basic criteria stated above may still be not patentable in specific jurisdiction based on certain circumstances or as stated in the patent act of the specified jurisdiction. Therefore grant of a patent is subject to certain limitations mentioned in the section 3 and 4 of the Indian Patent Act for Indian jurisdiction. The aim of this paper is to study such limitations in detail.