• The Complete Research Material is averagely 49 pages long and it is in Ms Word Format, it has 1-5 Chapters.
  • Major Attributes are Abstract, All Chapters, Figures, Appendix, References.
  • Study Level: BTech, BSc, BEng, BA, HND, ND or NCE.
  • Full Access Fee: ₦6,000

Get the complete project » Instant Download Active

CHAPTER ONE

1.0                          INTRODUCTION

1.1  Background of the Study

The urinary bladder is a hollow muscular organ in many animals, which collects and stores urine from the kidneys before disposal by urination. In the human, the bladder is a hollow muscular organ situated at the base of the pelvisUrine collects in the bladder, fed from the two ureters that are connected to the kidneys (Netter, 2014). Urine leaves the bladder via the urethra, a single muscular tube which ends in an opening the urinary meatus, where it exits the body (Patel, 2010). The typical human bladder can hold between 300 and 500 ml before the urge to empty occurs, but can hold considerably more (Patel, 2010).

 Inflammation of the urinary bladder also called cystitis which can occur due to infection from bacteria that ascend the urethra to the bladder or for unknown reasons, such as with acute cystitis. Symptoms include a frequent need to urinate, often accompanied by a burning sensation (VanDeVoorde, 2015). As bladder inflammation progresses, blood may be observed in the urine and the patient may suffer cramps after urination (VanDeVoorde, 2015. In young children, attempts to avoid the pain of cystitis can be a cause for daytime wetting (enuresis) (Flores-Mireles, Walker, Caparon and Hultgren, 2015). Treatment includes avoiding irritants, such as perfumed soaps, near the urethral opening; increased fluid intake; and, for infectious cystitis, antibiotics (Flores-Mireles, Walker, Caparon and Hultgren, 2015). Untreated bladder inflammation can lead to scarring and the formation of stones when urine is retained for long periods of time to avoid painful urination which can cause death (Flores-Mireles, Walker, Caparon and Hultgren, 2015).

The kidneys are two bean-shaped organs found on the left and right sides of the body in vertebrates. Unlike the heart or lungs they possess no overtly moving structures. They filter the blood in order to make urine, to release and retain water, and to remove waste and nitrogen (the excretory system) (Elbashier, 2016). They also control the ion concentrations and acid-base balance of the blood. Each kidney feeds urine into the bladder by means of a tube known as the ureter. In humans, they are roughly 11 centimetres (4.3 in) in length (Elbashier, 2016).

The kidneys regulate the balance of ions known as electrolytes in the blood, along with maintaining acid base homeostasis. They also move waste products out of the blood and into the urine, such as nitrogen-containing urea and ammonium. Kidneys also regulate fluid balance and blood pressure (Elbashier, 2016).

They are also responsible for the reabsorption of waterglucose and amino acid. The kidneys also produce hormones including calcitriol and erythropoietin. The kidneys also make an important enzymerenin, which affects blood pressure through negative feedback (Elbashier, 2016).

Inflammation of the kidneys also called Nephritis. Nephritis is often caused by infections, and toxins, but is most commonly caused by autoimmune disorders that affect the major organs like kidneys (Fu, Mao, Xu, Zhu and Liu, 2016). Nephritis can produce glomerular injury, by disturbing the glomerular structure with inflammatory cell proliferation. This can lead to reduced glomerular blood flow, leading to reduced urine output (oliguria) and retention of waste products (uremia). As a result, red blood cells may leak out of damaged glomeruli, causing blood to appear in the urine (hematuria) (Fu, Mao, Xu, Zhu and Liu, 2016).

Low renal blood flow activates the renin-angiotensin-aldosterone system (RAAS), causing fluid retention and mild hypertension. As the kidneys inflame, they begin to excrete needed protein from the affected individual's body into the urine stream. This condition is called proteinuria (Fu, Mao, Xu, Zhu and Liu, 2016).

Loss of necessary protein due to nephritis can result in several life-threatening symptoms. The most serious complication of nephritis can occur if there is significant loss of the proteins that keep blood from clotting excessively. Loss of these proteins can result in blood clots, causing sudden stroke (Fu, Mao, Xu, Zhu and Liu, 2016).

In the terminology of machine learning, classification is considered an instance of supervised learning, i.e. learning where a training set of correctly identified observations is available (Alpaydin, 2014). The corresponding unsupervised procedure is known as clustering, and involves grouping data into categories based on some measure of inherent similarity or distance (Alpaydin, 2014).

Often, the individual observations are analyzed into a set of quantifiable properties, known variously as explanatory variables or features. These properties may variously be categorical (e.g. "A", "B", "AB" or "O", for blood type), ordinal (e.g. "large", "medium" or "small"), integer-valued (e.g. the number of occurrences of a particular word in an email) or real-valued (e.g. a measurement ofblood pressure). Other classifiers work by comparing observations to previous observations by means of a similarity or distance function (Alpaydin, 2014).

An algorithm that implements classification, especially in a concrete implementation, is known as a classifier. The term "classifier" sometimes also refers to the mathematical function, implemented by a classification algorithm that maps input data to a category (Alpaydin, 2014).

In this work Support Vector Machine (SVM) will be used for classification of both acute inflammation of the bladder and acute inflammation of the kidneys from medical records of patients suffering from this ailment.

In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data used for classification and regression analysis (Mills, 2014). Given a set of training examples, each marked as belonging to one or the other of two categories, an SVM training algorithm builds a model that assigns new examples to one category or the other, making it a non-probabilistic binary linear classifier (Mills, 2014). An SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall (Mills, 2014).

In addition to performing linear classification, SVMs can efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping their inputs into high-dimensional feature spaces (Hwang, Jun and Yoon, (2014).

1.2  Statement of the Problem

According to world bank, estimates of the global burden of disease indicate that diseases of the kidney and urinary tract account for approximately 830,000 deaths and 18,467,000 disability-adjusted life years annually, ranking them 12th among causes of death (1.4 percent of all deaths) and 17th among causes of disability (1.0 percent of all disability-adjusted life years) (Appel, 2015). The main factor for the high value is the wrong diagnosis of the urinary system diseases which has related symptoms and this has necessitated the design of a urinary diseases diagnosis system.

1.3  Aim and Objectives of the Study

The aim of this study is to classify both acute inflammation of the bladder and acute inflammation of the kidneys using Support Vector Machine. The objectives are:

        i.            To pre-process the acute inflammation dataset to have normalized data.

      ii.            To train the network using the pre-processed dataset with Support Vector Machine (SVM).

    iii.            To evaluate the performance on the network.

1.4  Significance of the Study

This study would be of high importance to the medical practitioners and researchers whose aim is to perform classification of both acute inflammation of the bladder and acute inflammation of the kidneys using AI technique which have been very difficult due to the related symptoms of these two diseases.

1.5   Scope and Limitation of the Study

This study focused on classification of both acute inflammation of the bladder and acute inflammation of the kidneys using Support Vector Machine, respectively on acute inflammation Dataset. However, the study did not consider all various types of urinary system diseases.

1.6 Organization of the Study

This study is made up of five chapters. Chapter one covers the background of the study, statement of the problem, aim and objectives of the study, scope and limitation of the study and significance of the study. Chapter two reviews related literatures in relation to classification techniques. Chapter three contain the research methodology, analysis and limitation of available system. Chapter four covers the experimental result, analysis of data and discussion. Chapter five includes conclusion, summary and recommendation.


You either get what you want or your money back. T&C Apply





You can find more project topics easily, just search

Quick Project Topic Search