ABSTRACT

Majority of enterprises of various industries rarely utilize the vast internally and externally generated data available in the business for productive and improved performance of the sectors. This has been due to the paucity of reliable intelligent systems to enable such sectors to fully manipulate these vast heterogeneous data. The concept of Business Intelligence comes handy to resolve the problem involved in decision making as well as in taking actions based on facts and evidence-based knowledge insight particularly in the health sector. Being an intelligent tool, it needed an effective and enhanced data integration technique to handle the vast heterogeneous data across the nation’s health centres, hence this research. The aim of the study was to develop a hybrid model for enhanced Business Intelligence process (HMEBIP). It combined ontology-based and virtual data integration (OBDI and VDI) techniques to enhance the data integration process in Business Intelligence (BI) environment. The objectives were to: provide a database for storing and tracking disease outbreak and control for resolving its historical data in real-time; provide an integrated patient medical record for accessibility across health centres in the country; use the combined data integration techniques and case-based reasoning (CBR) to boost the intelligence expertise of the Business Intelligence process as well as for resolving latencies, redundancy, and interoperability issues; and to provide the medical experts with the facilities for making accurate, intelligent, fact and evidence-based knowledge insight decisions on patients’ matters. The hybrid model was developed with Java Script, Hypertext Pre-Processor (PhP), and My Structured Query Language (My-Sql) programming languages using object-oriented analysis and design methodology (OOADM) and the model was tested with the health sector domain that deals with disease control procedure. The model was verified and validated using confusion matrix which was used to carry out the performance evaluation by comparing the result attained when only either of the two data integration techniques; ontology-based and virtual data integration (OBDI and VDI – data virtualization) was exclusively used to enhance a Business Intelligence (BI) process. The results obtained show that the hybrid model had a higher enhanced Business Intelligence (BI) process performance of 95% as against 75% and 65% for the OBDI and VDI respectively. This shows that the hybrid model is successful as it outperformed the existing model with 20% performance level.

CHAPTER ONE

INTRODUCTION

1.1.      Background of the Study

With the growth in the use of computer systems for a number of functions in businesses, there is the challenge of processing and analysing huge amounts of data and turning them into profits. This has led to vendors upgrading their Business Intelligence (BI) products, which are sets of tools and technologies designed to efficiently extract useful information from oceans of data (Sixto, 2002). The process of gathering and utilizing gathered knowledge and information for decision making is becoming central for organizations, rather than in the past relying solely on past experience, inituition or knowledge of the decision maker. Today data is seen as one of the most if not the most important asset in modern organizations, used to support different activities, most important of them presumably being to support decision making (Pekka, 2017).

In recent times, Business Intelligence has gained momentum in real-world practice, and it has evolved as an important research subject of information systems within the decision support domain (Liu, 2014). Recent growing competitive pressure in business has led to increased needs for real-time analytics termed Operational Business Intelligence or Real-Time Business Intelligence. This is essentially true with respect to health industry which is quite dynamic in nature with new disease discoveries that would require varying treatment and prevention procedures based on clinical analysis of individual patients (customers) as well as administrative management decision based on government policies on health.

The health sector is one of the most dynamic sectors of the economy of any nation, hence it is a major priority in ensuring healthy citizens of a nation. The use of intelligent techniques provides an effective computational methods and robust environment for Business Intelligence (BI) in health sector domain. Presently, health systems are faced with challenges due to demographic changes, technological advances in medicine and the limited possibilities to increase health funding requiring more intensive search for effectiveness of the systems. Business Intelligence (BI) as a key technology used to build systems that integrates analytical data from different transactional systems is referred to decision making, information analysis, knowledge management and human computer interaction (Celina and Kornelia, 2012).

As it is well known, health industry is very dependent on information. But very few technologies are in real-time that  take data and convert them into information has  being

developed. These data are devoid of context and are only slightly more than useless. So far, only Business Intelligence (BI) technology is able to focus on key indicators easily and quickly to provide valuable information for health sector. With the health sector, swimming in an ever- deeper pool of data, it needs a system that would be responsible for collecting, providing and analyzing the most relevant data, so that its organizations can be able to use these data in practice, thereby being rich in data as well as in information (Celina and Kornelia, 2012). This is where the research developed hybrid model for an enhanced Business Intelligence (BI) process comes handy.

Furthermore, in the 21^st century, the increased use of computing technology is driving a revolutionary change in the way business and decisions making is done. Despite its importance, many decisions in commercial and non-profit organizations are still based on intuition and experience rather than on automated and evidence-based fact processes (Ing.Dita, 2016). Business in all sectors of the economy; education, healthcare, science, state administration, research, and government, requires information to be able to run effectively and successfully. This has led to the demand by modern organization in expressing the need for an effective business information system that would enable them collect, preserve, process and find information when needed. The major characteristics facing the modern world today is vast uncertainties and rapid changes. So due to these, business managers are forced to look for instruments and mechanisms that will facilitate management decisions and create good conditions for business success. Again, this is where Business Intelligence (BI) comes handy as a mechanism to achieve the desires of business managers (Benjamin, 2013).

Business Intelligence (BI) can be seen to provide answers from what happened, to how, to why using a wide variety of analytical methods and tools to provide answers to organizational current questions and problems. With this trend, it is important for Business Intelligence (BI) professionals or management professionals working in Information Technology (IT) and business to stay informed about changes happening in the Business Intelligence (BI) industry, which is behind the organizations’ ability to make the correct intelligent business decisions (Pekka, 2017).

With the challenges in the health sector, which is growing at a high speed, then comes the need for an evolution in computing technology that meets the needs of an effective personalized medicine and specific treatments, diagnosis and disease prevention procedures according to patients’ individual characteristics. This leads to the demand to create more value in the health

sector in terms of efficient, reliable and accurate intelligent delivery of healthcare by its business executive’s users when taking decisions (Mihaela and Manole, 2015). Using this information technology (IT) evolution means to analysis proper data at the right moment. This has being a long-term challenge for health sector generally.

Business Intelligence (BI) as a specialized tool that is a routine component of management practice in other sectors such as finance and manufacturing is yet to reach its full potential in the health sector because its availability (with respect to BI) is limited and factors such as data quality, complexity, data integration and access to data have been identified as barriers (Loewen, 2017). The deployment of Business Intelligence (BI) leads to support for better decision-making, with its ability to handle large variety of data. It can help identify and develop new business opportunities and insights, with this when implemented by business enterprises with effective strategy; it will consequently enhance such enterprise’s competitive advantage, thereby leading to sustainable and profitable growth. Also, the technologies of Business Intelligence (BI) provide historical, current and predictive views of business operations with common functions such as querying, reporting, online analytical processing (OLAP), data mining, data integration, text mining, and business analytics (Liu, 2014).

The concept of Business Intelligence (BI) is defined as “the set of strategies, processes, applications, data, products, technologies and technical architectures which are used to support the collection, analysis, presentation and dissemination of business information” (Delic and Stanier, 2016; Elaheh and Mohammed, 2017). It is the result of natural evolution in terms of decision support systems (DSS) and Enterprise Systems (ESs), systems that aimed at replacing humans in the decision making process or at least at offering solutions to the issues they are concerned of. Its’ process implies actions based on the decisions made (manually or automated). The latencies involved include the time it takes to initiate an action and the time it takes to execute and monitor the action. It is different from Management Information System (MIS), Decision Support System (DSS), Executive Information System (EIS) and Enterprise System (ES)) because it describes a set of concepts and methods that improves business decision making by using fact-based support system. It is a data-driven type of Decision Support System (DSS), which involves the update of data, and supports process-oriented organization. Also, it is used to solve sophisticated complex information needs, it has wider thematic range, it is multivariate in analysis, and it involves semi-structured data as well as multidimensional data, which originate from different sources.

It supports decision making at all levels of management structure. For the strategic level, it makes it possible to set objectives precisely and follow realization of such established objectives. It allows for performing different comparative reports such as on historical results, profitability of particular offers, and effectiveness of distribution channels along with carrying out simulations of development or forecasting future results on the basis of some assumptions (Celina and Ewa, 2004). At tactical level, it provides some basis for decision making within marketing, sales, finance, and capital management. It allows for optimizing future actions and for modifying organizational, financial or technological aspects of company performance appropriately in order to help enterprises realize their strategic objectives more effectively. In operational level, it is used to perform ad-hoc analyzes and answer questions related to departments’ on-going operations, up-to-date financial standing, sales and co-operation with suppliers, and customers. While at the technical level, it offers an integrated set of tools, technologies and software products that are used to collect heterogenic data from dispersed sources in order to integrate and analyze data to make it commonly available (Celina and Ewa, 2007).

The research adopted the definition of Business Intelligence (BI) according to Sanja, et al., (2016) that states “Business Intelligence (BI) is that technology which enables organizations to make more informed, intelligent business decisions as well as to adapt to a changeable environment and to survive in the business world, while cooperating with patients, customers, suppliers, competitors and clients of various sector depending on domain area applied”. It further states that modern Business Intelligence (BI) involves the integration of intelligence methodologies and information technology that are applied to the business world (Sanja, et al., 2016).

Worthy of note is that, Business Intelligence (BI) and Big Data are helping in the fight against the spread of epidemics, and researchers are using both technologies to find a cure for diseases such as cancer. It is believed that in the future, companies of various sectors would be forced to rely on Business Intelligence (BI) systems completely to keep up with the competition that is increasing on a daily basis. In modern economy, knowledge has become the most important business resource and modern business has become dependent on the concept of Business Intelligence (BI) as a process of gathering significant external and internal data and their conversion into useful information for business decision making. It is a field of building information that is conclusive, fact-based and actionable. So it expose the importance of data and information kept by various organization, which can be used to help in accurate and

efficient decision-making based on the facts rather than human reasonings (Tanko and Musiliudeen, 2012). Also, the value of real-time Business Intelligence (BI) rests in its’ capability to reduce the three types of latency: Data latency (the time between business events and when the operational data is captured), Analysis latency (the time to analyze the data and when the findings are available for use), and Decision latency (the time to act upon the data). So, real-time Business Intelligence (BI) can enhance the agility of an organization to significantly increase the responsiveness to varying customer needs and ever-changing market situations (Liu, 2014).

With the concept of intelligent agents in conjunction with case-based reasoning (CBR) they offer a potential of increased production quality, flexibility, reliability and fast delivery times in health sector as well as other sectors such as manufacturing, production, electricity, transportation, banking and finance. Information from heterogeneous sources such as from the evolution of sensor and internet technologies, are becoming available for utilization, but the data received are frequently continuous and subject to more complex properties such as being dynamic, sequential unstructured, uncertain and imprecise. So with software agent (intelligent agent), solutions that can support the creation, processing and utilizing of these knowledge as defined in organizations would be achievable. Worthy of note is that intelligent techniques provide an effective computational methods and robust environment for Business Intelligence in the health sector domain. This is important because much of the data storage in all kinds of system used in the health sector organizations resides in proprietary silos thereby making access to such data difficult (Celina and Kornelia, 2012).

Case-based reasoning (CBR) implies an approach to model the way humans think as well as to build intelligent systems. It is an artificial intelligence (AI) technology that can be used to develop intelligent systems such as Expert system and Business Intelligence system. It is a technique suited for intelligent automated problem solving model designing. The intelligence provided by case-based reasoning (CBR) technique aids decision making in clinical areas of health sector such as in diagnosis, treatment, healing, monitoring and disease control.

One of the processes of designing Business Intelligence system is by providing the means for integrating data into information framework. With Ontology which helps in realizing reasoning, data integration in Business Intelligence can be implemented. Using Business Intelligence with Ontology-based and Virtual Data Integration technique, the development of semantic interoperability by integrating data warehouse (DW), Online Analytical Processing

(OLAP), data mining (DM) alongside structural interaction together is achievable. This type of integration will enhance Business Intelligence process to be more intelligent, business- oriented, adaptive and automatic, in the integration of Business Intelligence system in the real world. While, with virtual data integration (data virtualization), Business Intelligence (BI) data integration process would be enhanced in ways that, it would become easier to change systems, new reports can be developed and existing reports can be adapted easily and quickly. This agility is an important aspect for users of Business Intelligence systems. In essence, the enhanced Business Intelligence (BI) Integration process, aims at providing systematic analyzes and decision support by combining queries, reporting and analysis tools (Rick, 2012).

In summary, enhancing Business Intelligence (BI) with the hybridization of Ontology-based and Virtual Data Integration (VDI) techniques as well as intelligence technique using case- based reasoning (CBR) would give rise to a seamless transition from a practical work space into the virtual business-oriented analysis world that business persons expect. The collection of user-friendly supports will help users to modify, update, create or re-arrange ontological items and functionalities at different granularities on-demand, which is beneficial to business persons in a business-oriented rather than technology-centred interaction. It also results in run-time capabilities which will help business analyst to adapt to changing or new environment flexibly and adaptively in a user-friendly manner.

The Ontology-based aspect does the seamless transition, while the Virtual data integration technique does the hiding of the technical jargons. Also, the intelligence from case-based reasoning (CBR) technique would enhance the level of intelligence, accuracy and the speed rate for the delivery of decision on real-time basis. Thereby reducing cost of processing, increases availability, reduce time of processing and/or accessing data and it brings about adaptively, flexibility, intelligence and agility. The hybrid enhanced Business Intelligence (BI) process was developed to assist especially modern days’ managers at all levels (operational, tactical or strategic) to make correct, and timely management decisions. So it would greatly improve and support the process of making decisions in organizations, particularly in the health sector.

Hence, the research “development of a hybrid model for enhanced Business Intelligence (BI) process (HMEBIP)” is geared towards hybridizing two data integration techniques; Ontology- based (OBDI) and Virtual Data Integration (VDI – data virtualization) using case-based reasoning (CBR) intelligence approach in developing an expert system Business Intelligence

(BI) process for effective disease control procedure in the health sector. This would bring about a better-performance model of the data integration process in Business Intelligence (BI) technology; which is a key process for the delivery of effective decision making in Business Intelligence (BI) applications, thereby improving the value and increasing the quality of Business Intelligence (BI) used in the health sector in particular for decision-making by physicians and health management (managers) as well as other sectors in general. It further tried to address the fact that hybridization of the two data integration techniques is feasible, as research question was asked “if it is possible to hybrid both types of data integration techniques in a Business Intelligence (BI) system model”.

1.2              Statement of the Problem

Traditional Business Intelligence process is faced with the challenge of handling data integration in a BI environment; especially in the capability in producing analytics that would be meaningful from the heterogeneous data; the level of data completeness, cleansing, and intelligence, as well as the issue of real-time and up-to-date data accessibility and manipulative capabilities.

The possibility for the integration of Business Intelligence (BI) technology with already existing electronic medical record (EMR) and electronic health record (EHR) for the purpose of assisting health providers in knowledge discovery process thereby maximizing intelligent fact and evidence-based decision making practice among the medical practitioners in the health sector.

The research motivated question was coined from Ana-Ramona and Razvan (2011) that state “if the hybrid of both data integration techniques in a Business Intelligence domain is obtainable and if it would yield a better advantage compared to when each techniques is used individually?” was considered.

1.3              Aim and Objectives of the Study

Aim: The aim of the study is to develop a hybrid model for enhanced Business Intelligence (BI) process (HMEBIP).

Objective:     The objective of the study includes:

1. Capturing a database for storing and tracking disease outbreak and control in order to resolve the disease registry historical data issue in real-time.

• Provide an integrated patient medical record that would be accessible from any healthcare center across the country.
  • The use ontology-based, data virtualization techniques and case-based reasoning (CBR) technology to resolve the issue of latencies, redundancy, interoperability and intelligence.
  • Using ontology-based and virtualized data integration access, to provide a reliable and scalable data access framework for handling complex data sources.
  • Assist the medical experts in the health sector in achieving fact and evidence-based knowledge insight decision of the disease control procedure to be applied to patients’ treatment.

1.4.            Significance of the Study

The benefits and significance of the research study include but not limited to the following;

Decision making and the intelligence expertise service for quality delivery of disease control procedure and patients’ medical records was improved with high level of accuracy and relevance in real-time for the health sector.

It brings about the importance of fact and evidence-based knowledge insight in health care practise generally. It also improved the analyzing of data in the health sector in order to transform it into relevant information, intelligent knowledge insight and then profitable action.

Information presentation was made easy by using an easy to understand user graphical interface. It reduces the issue of latencies such as data, analyzes and action latency in the existing model. Also, it analyzes clinical data based on structured, semi-structured and unstructured information or data.

It would assist medical researcher and practitioners with up-to-date clinical and medical information in carrying out research process. This helped track and manage population health more efficiently as well as significantly improve patients care across the health sector. And it enhances the ability to deliver preventive and predictive disease control in health care.

It simplified access to data, makes it to be of standard and be retrieved real-time from their original sources. Also, it increase business efficiency, agility, increase sales, provide better customer targeting, reduce customer service costs, identify fraud and generally increase profits while reducing costs.

With Ontology involved, it leads to seamless transition from a practical workspace into the virtual business oriented analysis world that business persons expect as well as reduce the technology-centred interaction of Business Intelligence process.

With the hybrid data integration technique, the quality of data distribution improved among independent data sources, thereby reducing structural, syntactic and semantic heterogeneity and interoperability as well as redundancy. This brings about increased availability and degree of completeness and result in run-time capabilities which helps business analyst to adapt to changing or new environment flexibly and adaptively in a user-friendly manner.

With the reduction in cost and time of processing, quicker results was retrieved from the data sources. Also, with the study, resources are encapsulated in such a way that all technical details become hidden and the application works with a simpler interface.

The study resolved to a great extent the complexities involved with bringing together all data related to a patient record that are spread out over multiple and heterogeneous data sources, formats and location (Intra-hospital wise). It also brings about order, efficiency and consistency to informational Information Technology (IT) so that users can manage their affairs with a single version of the facts.

The study helps to control the resources and the information flow of businesses, which exist in and around the organization. It would make a large contribution to the required intelligence and knowledge of organizations’ management by identifying and processing data in order to explain hidden meanings (Saeed, et al., 2012).

Furthermore, the study brought about the abstracting of information related to technical aspect of shared data such as location, storage structure, access language, application programming interfaces, and so on. Also, the virtualization of data sources connection process (databases, web content and various application environments) would be made logically accessible from a single point, as if they were in one place so that a user can query data or report against it. More so, with the virtual data integration technique as part of the study, the issue of data security, data quality and data management requirements for queries optimization, caching, and so on, which are capabilities of data virtualization is feasible.

In summary, the study would bring about increase value through increased use, quality, merging, sharing of data, decoupling as well as on-demand transformation is achieved. Hence, the research study for the development of a hybrid model for enhanced Business Intelligence

process (HMEBIP) with the hybridization of Ontology-based and Virtual Data Integration technique using case-based reasoning (CBR) to improve its intelligence expertise service for quality delivery of disease control procedure and patients medical records in health sector, is quite significant in the world of today as the process of decision making is changing and the biggest change is that organization have to react faster, which means decisions have to be made faster with high level of accuracy, intelligence and relevance, since there is very less time available to make (sometimes crucial) decisions.

1.5.            Scope of the Study

The scope of the research is the development of a hybrid model of ontology-based and virtual data Integration (OBDI and VDI) techniques for enhanced Business Intelligence process. It uses case-based reasoning (CBR) to improve the model’s intelligence process quality. And it was tested in the health sector domain.

1.6.            Definition of Terms

1. Agent Technology: the use of agents to improve expertise of a system model.
2. Business Intelligence (BI): is a set of tools, process, practices and people that are used to take advantage of information to support decision making in the organization.
3. Business Intelligence System (BIS): A set of integrated tools, technologies and programmed products used to collect, integrate, analyze and make data.
4. Business Intelligence Process: is the key activities that must be in a Business Intelligence application; data accessibility, data integration, analysis and actionable knowledge discovery.
5. Case-Based Reasoning (CBR): broadly constructed is the process of solving new problems based on the solutions of similar past problems.
6. Clinical Data: is a staple resource for most health and medical research. Clinical data is either collected during the course of ongoing patient care or as part of a formal clinical trial program.
7. Clinical Data Registry: records information about the health status of patients and the health care they receive over varying periods of time. Clinical data registries typically focus on patients who share a common reason for needing health care.
8. Data Integration (DI): is the act of combining data residing at different sources, and providing the user with a unified view of these data. The problem of designing data integration system is important in current real world applications.

• Data Warehouse (DW): is defined as that which extracts current and historical data from multiple internal operational systems. This data is combined with data extracted from external sources and re-organized into a central database designed for management reporting and analysis purpose.
• Data Marts: is a subset of a central data warehouse, in which a summarized or highly focused portion of the organization’s data is placed in a separate database for a specific user’s population. It focuses on a single business area or line of business area.
• Data Mining: is more discovery driven as it provides insight into corporate data that cannot be obtained with online analytical processing (OLAP) or traditional database query. It also finds hidden patterns and relationships in large databases and inferring rules from them to predict future behaviour. These patterns and inferring rules are used to guide decision making and forecast the effect of these decisions.
• Disease Registries: are clinical information systems that track a narrow range of key data for certain chronic conditions such as Alzheimer’s disease, cancer, diabetes, heart disease, and asthma. Registries often provide critical information for managing patient conditions.
• EHR (Electronic Health Record): Is a repository of information regarding the health status of a subject of care in computer process-able form, stored and transmitted securely, and accessible by multiple authorised users.
• Expert System: are computer programs that exhibit intelligent behavior. They are concerned with the concepts and methods of symbolic inference, or reasoning, by a computer, and how the knowledge used to make those inferences will be represented.
• Hybridization: means that several methods (soft-computing) are crafted to complement one another resulting in a better-performance model.
• Intelligent System: is that system that employs its knowledge to become more self-aware. It is built on four fundamental elements; Data, Information, Knowledge and Wisdom.
• Ontology: is “a formal, explicit specification of a shared conceptualization”. Conceptualization refers to an abstract model of a phenomenon existing in the real world. This abstract model includes only relevant concepts of that phenomenon. Explicit means that the type of concepts used and the constraints on their use are explicitly defined. Formal means that ontology should be unambiguous and machine-readable. Shared refers to the fact that knowledge comprising an ontology is accepted and agreed on by a group of people, not just an individual.

1. On-line analytical processing (OLAP): Tools that allow us to analyze multidimensional data known as cubes. Cubes are data that are extracted from the data ware house and used by managers in decision-making situations.
2. Patient Registry: is an organized system that uses observational study methods to collect uniform data (clinical and other) to evaluate specified outcomes for a population defined by a particular disease, condition, or exposure, and that serves one or more predetermined scientific, clinical, or policy purposes.
3. Registry: is an organized system that uses observational study methods to collect uniform data (clinical and others) to evaluate specified outcomes for a population defined by a particular disease, condition, or exposure, and that serves one or more predetermined scientific, clinical, or policy purposes.
4. Virtualization: means that applications can use a resource without any concern for where it resides, what the technical interface is, how it has been implemented, which platform it uses and how much of it is available. Its solution encapsulates the resource in such a way that all those technical details become hidden and the application can work with a simpler interface.

₦5,000.00 – DOWNLOAD FULL PROJECT DOWNLOAD FULL PROJECT Added to cart

---

---

---

---

Related Project Topics :