eChapters

Early and accurate detection of plant diseases is essential for protecting crop productivity and reducing agricultural losses. This chapter explores artificial intelligence-based plant disease detection using image processing and deep learning. It introduces major plant diseases and the fundamentals of image processing before examining deep learning approaches for identifying disease symptoms from plant images. AI models can automate disease recognition and support timely interventions in smart agricultural systems. The chapter presents a proposed methodology and discusses results and analysis, practical applications and limitations. It also considers challenges associated with data quality, environmental conditions and model performance, followed by future directions for developing more accurate, scalable and intelligent plant disease diagnostic systems

Linear models have been extensively used in animal breeding. This chapter explains the basics of linear models including description; fixed, random and mixed models; model diagnostics and covariates. The concept of linear models in animal breeding is explained with representation and actual examples of use in different types of livestock.

Introduction to Linear Models

A model can be defined as a physical, mathematical or otherwise logical representation of a system, entity, phenomenon, or process. Linear models are a way of describing response variables in terms of a linear combination of the predictor variable. They provide a framework for a large set of models whose common goal is to explain or predict a quantitative dependent variable by a set of independent variables that can be categorical or quantitative.

Introduction

Importance of basic statistics in everyday life cannot be stressed enough. Inclusion of basic statistics in high school curriculum is uncommon but proves highly beneficial to supplement certain careers in future. This field may be the most widely used of all and most people don’t even know they are using it. Many of today’s brightest business minds use this study to create charts and graph that allow them to stress a certain aspect of the business they are dealing with. Market research agencies, News rooms, marketing divisions of large corporations, NGOs, accounting firms etc. are full of people who specialize in basic statistics.

Statistics is concerned with the describing, interpreting and analyzing data. It is, therefore, an essential element in any improvement process. Statistics is often categorized into descriptive and inferential statistics. It uses analytical methods which provide the math to model and predict variation. It uses graphical methods to help making numbers visible for communication purposes.

Descriptive Statistics

• Descriptive statistics summarizes or describes characteristics of a data set.

• They help to make sense of large numbers of individual responses, to communicate the essence of those responses to others

• Helps exploring and making conclusions about the data in order to make rational decisions.

• Includes calculating things such as the average of the data, its spread and the shape it produces.

• Are displayed as tables, charts, percentages, frequency, distributions and reported as measures of central tendency

• Determine if the sample is normally distributed (bell curve) as most statistical tests require the sample to have normal distribution

• Determine if the sample can be compared to the larger population

Difference between Descriptive and Inferential Statistics

Nowadays, statistics is playing a major role in the field of research; that helps in the collection, analysis and presentation of data in a measurable form. It is quite hard to identify, whether the research relies on descriptive statistics or inferential statistics, as people usually, lacks knowledge about these two branches of statistics. As the name suggests, descriptive statistics is one which describes the population. On the other end, Inferential statistics is used to make the generalisation about the population based on the samples.

The branch of statistics which describes the data is called descriptive statistics. After collection, the data are presented in form of tables, diagrams or graphs. This facilitates the further analysis of data. The most basic form of data analysis is descriptive analysis of data collected and presented for the study. The descriptive statistics summarises the data and helps to find the representative value of the entire data set and the variation of the other values in the data set around the representative value. The descriptive statistics includes the measures of central tendency or averages, measures of dispersion or scatteredness, measures of skewness and the measures of kurtosis. Before going to discuss the R codes for various measures of descriptive analysis, we would first discuss in brief about these measure. This will help in better understanding of the R codes.

Measures of central tendency or averages: They are the representative values of the data series. They give an idea about the concentration of the values in the central part of the distribution of the data. There are five types of averages. They are 1. Arithmetic Mean (A.M.) 2. Geometric mean (G.M.) 3. Harmonic Mean (H.M.) 4. Median 5. Mode.

Healthcare represents one of the most promising yet sensitive application domains for Large Language Models. LLMs can process extensive medical literature, electronic health records, clinical narratives and other forms of biomedical information to support diagnosis, research and patient care. This chapter explores the growing role of LLMs in healthcare, beginning with their development from general language models toward specialized biomedical and clinical systems. It examines applications in disease diagnosis, clinical decision support, medical documentation, literature analysis, drug discovery and personalized medicine. LLMs can assist with differential diagnosis, symptom extraction, medical question answering, clinical trial matching and interpretation of medical information. In drug discovery, they can analyze scientific publications, patents and clinical evidence to identify potential drug candidates, targets and opportunities for drug repositioning. Personalized medicine applications involve integrating genetic, lifestyle and treatment-response information to support patient-specific therapeutic decisions. At the same time, the chapter emphasizes major concerns involving patient privacy, hallucination, explainability, regulatory compliance and human oversight. The discussion highlights the importance of responsible integration of LLMs with clinical expertise and established healthcare practices

16.1 OOP in python

Object-oriented programming (OOP) is a programming language model which organized object and data.

16.1.1 What is Encapsulation

If same variable is reapet in two different palce then which problem is solved using encapsulation it means one variable is making private otherwise program generate error.

16.1.2 Abstraction

Abstraction in Python is the process of hiding the real implementation of an application from the user and emphasizing only on usage of it. For example, consider you have bought a new electronic gadget. Along with the gadget, you get a user guide, instructing how to use the application, but this user guide has no info regarding the internal working of the gadget.

Another example is, when you use TV remote, you do not know how pressing a key in the remote changes the channel internally on the TV. You just know that pressing + volume key will increase the volume.

Introduction 
The evolution of governance reforms in India must be situated within the broader global and domestic transitions in public administration. Inheriting its foundational structures from British colonial rule, India retained key institutional frameworks post-Independence in 1947, including the Parliament, Executive, Judiciary, and systems of law and order and revenue administration. Although these institutions provided a degree of continuity and stability, they gradually became mired in procedural rigidity, excessive centralization, and legal formalism. Mathur (2013) notes that the performance of the three core organs of governance, the legislature, executive, and judiciary, has drawn increasing public concern, particularly in their responsiveness to the rising aspirations of Indian citizens. In the early decades post-independence, India adopted a centralized, commandand- control model of economic and administrative governance. State officials wielded considerable discretion over the allocation of licenses, quotas, and permits, while the private sector remained underdeveloped and tightly regulated. This framework, while aligned with the nation-building ethos of the time, ultimately led to inefficiencies, corruption, and citizen disenchantment. The 1990s marked a watershed moment in India’s governance trajectory. With a balance-of-payments crisis and external pressures from international financial institutions such as the IMF and World Bank, India adopted neoliberal economic reforms centered on liberalization, privatization, and globalization (Ramesh Singh, 2013). These reforms fundamentally altered the state’s role from a direct provider of goods and services to a facilitator and regulator. A new governance discourse emerged, emphasizing accountability, transparency, efficiency, and citizen participation. This also marked the diffusion of New Public Management (NPM) ideas, which advocated for performance-based administration, managerial autonomy, and partnership with non-state actors. Simultaneously, the Tenth Five-Year Plan (2002–2007) explicitly identified governance as a key determinant of development outcomes, underscoring that economic growth could not be sustained without reforming the institutions

Introduction 
The transformation of governance through digital means represents one of the most consequential shifts in contemporary public administration. Digital governance or e-governance entails strategically applying information and communication technologies (ICTs) to enhance the accessibility, efficiency, transparency, and responsiveness of government functions and public service delivery. In India, this digital shift has accelerated over the past two decades, driven by imperatives to modernise the state apparatus, promote inclusive development, and meet the rising expectations of a digitally literate citizenry. A complex interplay of demographic diversity, federal administrative structures, and asymmetries in socio-economic development shapes India’s trajectory toward digital governance. The proliferation of mobile devices, growth in internet penetration, and public investments in digital infrastructure have enabled a gradual shift from paper-based systems to platform-based governance. Concurrently, global paradigms such as open government, digital inclusion, and citizen-centric innovation, captured in international indices like the UN E-Government Development Index and the World Bank’s GovTech Maturity Index, have influenced national aspirations and strategy formulation. However, these technological and global catalysts can only be transformative when embedded within a coherent legal and policy framework that ensures institutional legitimacy, citizen trust, and systemic accountability. In this regard, digital governance’s legal and policy foundations are critical for establishing enabling conditions for its practical and equitable implementation. As highlighted by Sachdeva (2002), the transition to digital modes of governance requires not only the removal of outdated regulatory provisions but also enacting new laws on digital authentication, electronic records, data protection, cybercrime, and privacy. Additionally, procedural simplification through single-window systems, interoperability standards, and e-payment protocols is essential to reduce administrative friction and promote

Clinical decision support systems assist healthcare professionals in diagnosis, treatment planning and patient management. This chapter introduces intelligent clinical decision support systems and explains how computational intelligence overcomes the limitations of conventional rule-based approaches. It examines artificial neural networks, fuzzy logic, evolutionary algorithms, swarm intelligence and deep-learning models. A computational architecture integrating clinical data, learning algorithms, fuzzy inference and optimization is presented. Applications in heart-disease diagnosis, diabetes-risk prediction and medical-image analysis illustrate the practical value of these systems. The chapter also addresses interpretability, interoperability, data quality, privacy, legal responsibilities, real-time processing and the challenges involved in deploying intelligent decision-support tools in clinical environments.

Introduction 
Digital governance in India has made remarkable strides over the past two decades, transitioning from isolated digitisation projects to an integrated, citizen-centric governance ecosystem. Enabled by policy reforms, technological innovation, and infrastructural development, digital governance has become a cornerstone of the country’s public service delivery, transparency, and accountability. However, the ambitious expansion of digital governance has also encountered systemic and structural challenges that continue to hinder its full realisation. These challenges are not merely technological but are deeply embedded in socio-political, administrative, and economic contexts that define the Indian public administration landscape. While the progress has been notable, the sustainability and inclusiveness of digital governance remain contingent on the country’s ability to address these entrenched constraints. Despite substantial advances, several persistent challenges threaten the transformative potential of digital governance in India. Chief among them is the digital divide across rural-urban, gender, economic, and social lines, which inhibits equitable access to digital services. According to the National Family Health Survey (NFHS-5, 2019–21), internet usage in rural areas remains alarmingly low, with only 33% of women and 57% of men reporting regular access. Infrastructural constraints, human resource limitations, weak system interoperability, cyber-security threats, and concerns about data protection and digital rights compound these disparities. The post-2015 period has witnessed transformative initiatives under the Digital India Programme, including the proliferation of platforms such as Aadhaar, DigiLocker, Unified Payments Interface (UPI), and MyGov, among others (MeitY, 2022). While these developments have significantly enhanced service accessibility and administrative efficiency, they have simultaneously revealed critical gaps in digital infrastructure, policy coherence, data governance, and institutional capacities. For instance, the rural-urban digital divide, disparities

Data-centric artificial intelligence has transformed medical imaging, clinical prediction and electronic health-record analysis, but purely data-driven models face limitations involving generalization, bias, privacy and interpretability. This chapter examines the transition toward knowledge-aware and hybrid healthcare systems that combine machine learning with clinical knowledge, ontologies and knowledge graphs. It discusses explainable AI, clinical reasoning and the integration of structured knowledge into intelligent decision support. Applications include acute-care support, precision medicine, genomic oncology and population-health management. Ethical issues, regulatory compliance, fairness and privacy-preserving technologies are also considered. Future directions include quantum computing, large language models, multimodal integration and equity-focused healthcare-system development.

Ice cream defects can result from formulation imbalance, poor ingredient quality, processing deviations, inadequate freezing or hardening, packaging problems, storage conditions, and cold-chain failures. This chapter provides a systematic framework for understanding, classifying, diagnosing, and correcting defects affecting flavour, body, texture, melting, colour, appearance, packaging, and storage stability. It emphasizes that a visible defect in the finished product may originate much earlier in the production or distribution chain. Examples include iciness caused by slow freezing or temperature abuse, weak body associated with formulation or overrun, and flavour problems originating from raw materials or microbial activity. Defect analysis therefore becomes an important tool for troubleshooting, quality improvement, training, and preventive action.

Early Warning Systems (EWS) have evolved from simple, rudimentary alert mechanisms into complex, multi-hazard, data-driven networks that play a critical role in disaster risk management and climate adaptation. In today’s rapidly changing climate, timely and accurate information is essential not only for saving lives but also for protecting livelihoods, reducing economic losses, and enhancing community resilience. The application of EWS varies significantly by region, geography, type of disaster, and across diverse sectors such as agriculture, aquaculture, horticulture, animal husbandry, fisheries, and allied sciences. Global initiatives - led by organizations such as the United Nations - aim to ensure that every person, particularly the most vulnerable, is equipped with lifesaving early warnings by 2027 (Fig.11.1). Complementary partnerships, such as that between the World Meteorological Organization (WMO) and the Food and Agriculture Organization (FAO), further strengthen these systems by integrating cutting edge forecasting with actionable advisories for critical sectors. A particularly groundbreaking effort is the United Nations’ Early Warnings for All (EW4ALL) initiative, launched in 2022 by UN Secretary General António Guterres, which seeks to provide comprehensive early warning coverage for hazardous weather, water, and climate events to every person on Earth. Underpinning these global efforts is Weather Intelligence - a transformative approach that harnesses advanced data analytics, real time monitoring, and machine learning techniques to refine forecasts and deliver precise, context specific alerts. By integrating diverse data streams and tailoring

The cold chain is the lifeline of the ice cream industry because the product must remain continuously frozen from factory hardening until consumption. This chapter examines the complete cold-chain network, beginning with hardening and factory cold storage and extending through CFA or distributor cold rooms, refrigerated transport, retail freezers, and final consumer handling. It explains temperature requirements, monitoring systems, equipment selection, cold-room management, stock rotation, and quality assurance. Particular attention is given to Indian challenges such as power interruptions, inadequate freezer maintenance, poor retailer practices, and temperature abuse. The chapter demonstrates how disciplined cold-chain management protects texture, flavour, shape, overrun, shelf life, and ultimately consumer confidence

A greenfield ice cream project involves much more than installing production machinery. It requires integrated planning of the business model, market opportunity, capacity, product portfolio, plant layout, process technology, refrigeration, utilities, packaging, cold storage, quality systems, regulatory compliance, distribution, working capital, and future scalability. This chapter presents a practical framework for evaluating new ice cream manufacturing projects, with particular attention to a representative 1000 LPH facility. Different project scales and business models are considered along with major plant and machinery requirements. The chapter also highlights common project-planning mistakes and best practices. It helps entrepreneurs and investors assess technical feasibility, operational readiness, financial requirements, scalability, and long-term commercial viability.

Orthogonal designs provide an efficient framework for arranging treatments and sources of variation so that their effects can be estimated independently. This chapter introduces contrasts, orthogonal contrasts, and the concept of orthogonality in experimental design. Orthogonality helps prevent the effects of different factors from becoming entangled and facilitates systematic statistical analysis. The chapter discusses three basic experimental designs: Completely Randomized Design, Randomized Complete Block Design, and Latin Square Design. Their principles, applications, and suitability for forestry and agricultural experiments are explained. Examples involving seedlings, tree species, fertilizers, chemicals, wood pieces, and seeds demonstrate how appropriate design selection can reduce heterogeneity and improve experimental precision.

Effective crop monitoring is essential for maintaining plant health, optimizing farm operations, and improving agricultural productivity. This chapter explores the application of artificial intelligence for real-time crop monitoring and farm management. AI systems integrate information from sensors, satellites, drones, mobile devices, and other sources to assess crop conditions and identify emerging problems. Machine learning and deep learning techniques can analyse crop images, environmental parameters, growth patterns, and field conditions to provide actionable insights. The chapter examines real-time monitoring, image analysis, crop health assessment, anomaly detection, and decision-support applications. It also highlights the role of IoT and multimodal agricultural data in developing intelligent and responsive farming systems.

Plant diseases significantly reduce crop productivity, quality, and economic returns, making early and accurate detection essential for effective crop protection. This chapter examines the application of machine learning and computer vision for identifying diseases at an early stage. It discusses agricultural image acquisition using RGB, hyperspectral, and sensor-based technologies, followed by image preprocessing, segmentation, feature extraction, and classification. Machine learning algorithms such as support vector machines, random forests, and convolutional neural networks are considered for disease recognition. The chapter also explores the integration of AI with IoT and mobile technologies and presents practical applications while addressing challenges involving datasets, environmental variability, model generalization, and computational requirements.

Agriculture has progressed from labour-intensive traditional practices through mechanization and the Green Revolution to precision agriculture and Agriculture 5.0. This chapter traces that historical development and identifies limitations associated with conventional farming, including inefficient resource use, environmental degradation and weak adaptability. It explains how GPS-guided machinery, sensors and precision technologies prepared the foundation for intelligent systems. Artificial neural networks, deep learning and fuzzy logic now process data from IoT devices, UAVs and satellites to support automated irrigation, crop monitoring and soil analysis. The chapter emphasizes that integrating human knowledge with computational power is increasingly essential for global food security, sustainability and climate resilience.

Increasing crop productivity while reducing resource consumption is a central objective of modern agriculture. This chapter examines how artificial intelligence can support crop yield improvement through data-driven analysis, prediction, and decision-making. AI models can integrate information from soil, weather, crop growth, remote sensing, IoT sensors, and historical yield records to identify important factors influencing productivity. Machine learning and deep learning approaches can support yield forecasting, crop selection, fertilizer and water optimization, and precision management. The chapter also considers AI-enabled genomic selection, market intelligence, and intelligent farm management. Challenges such as data availability, implementation cost, connectivity, farmer training, and model reliability are discussed alongside future opportunities including edge AI and explainable AI.