Wahidah Husain

Data Mining for Medical Systems: A Review

Data mining is a growing area of research that intersects with many disciplines such as Artificial Intelligence (AI), databases, statistics, visualization, and high-performance and parallel computing. The goal of data mining is to turn data that are facts, numbers, or text which can be processed by a computer into knowledge. Nowadays, the reliance of health care on data is increasing. Therefore, this paper aims to allow the readers to understand about data mining and its importance in

Application of data mining techniques in a personalized diet recommendation system for cancer patients

Cancer is one of the top fatal diseases in the world. When cancer patients undergo treatment, they need a different diet to help them withstand the side-effects of treatment, as well as to provide sufficient nutrition to boost the recovery cycle. Most of the dietician systems currently in the market are more in the advice area rather than recommending specific diet menus for users. These systems usually provide advice in a general form, for example: “Cancer patients should eat foods with high protein”. Such recommendations are insufficient to assist cancer patients with the physical preparation necessary to withstand the side effects of treatment, or with ensuring they take adequate nutrients for their body. We propose a Personalized Diet Recommendation System for Cancer Patients to help patients manage their daily food intake. The proposed system integrates the data mining techniques of Case-based Reasoning, Rule-based Reasoning and Genetic Algorithm. Case-based Reasoning is used to suggest a set of diet plans taken from the cases existing in the system, whereas Rule-based Reasoning is used to filter out irrelevant cases from the system and select the most appropriate case to be suggested to the patient. The Genetic Algorithm technique ensures that the diet menus suggested are customized according to each patients personal health conditions. The output of the diet plan system is in the form of a list of specific nutritional values to be taken daily, and a menu recommendation suggesting actual dishes for the patient.

Recommender System for Personalised Wellness Therapy

rising costs and risks in health care have shifted the preference of individuals from health treatment to disease prevention. This prevention treatment is known as wellness. In recent years, the Internet has become a popular place for wellness-conscious users to search for wellness-related information and solutions. As the user community becomes more wellness conscious, service improvement is needed to help users find relevant personalised wellness solutions. Due to rapid development in the wellness market, users value convenient access to wellness services. Most wellness websites reflect common health informatics approaches; these amount to more than 70,000 sites worldwide. Thus, the wellness industry should improve its Internet services in order to provide better and more convenient customer service. This paper discusses the development of a wellness recommender system that would help users find and adapt suitable personalised wellness therapy treatments based on their individual needs. This paper introduces new approaches that enhance the convenience and quality of wellness information delivery on the Internet. The wellness recommendation task is performed using an Artificial Intelligence technique of hybrid case-based reasoning (HCBR). HCBR solves users’ current wellness problems by applying solutions from similar cases in the past. From the evaluation results for our prototype wellness recommendation system, we conclude that wellness consultants are using consistent wellness knowledge to recommend solutions for sample wellness cases generated through an online consultation form. Thus, the proposed model can be integrated into wellness websites to enable users to search for suitable personalized wellness therapy treatment based on their health condition.

A framework for childhood obesity classifications and predictions using NBtree

Obesity is a common issue nowadays. The numbers of obese people are increasing every year. There are evidences that childhood obesity persists into adulthood. Predicting obesity at an early age is both useful and important because preventive measures and proper interventions can be applied if the children indicated a high risk of obesity. However, the prediction of childhood obesity is a difficult task. Many ways and techniques such as assessment of body composition, data mining techniques, and logistic regression have been applied to predict childhood obesity, but only a few managed to produce accurate results. The numbers of efforts on childhood obesity prediction need to be increased and the techniques used should be improvised. The initial stage of this study involves collecting data from primary sources: parents, children and caretaker. Then, we identify risk factors such as parental obesity and education, children lifestyle and habits, and environment influences, and proposes a framework of childhood obesity prediction using NBtree.

A Survey on Data Integration in Bioinformatics

The need for data integration is widely acknowledged in bioinformatics. There are several huge biological databanks now available across the world in different formats. To characterize or apply data mapping between several data sources requires integration of all related data fields. The problem of integration may be addressed using a variety of approaches; some are widely used and some are less so, having failed to achieve the basic requirements of data integration. In this paper, we discuss three techniques for data integration: the federated database system approach, the data warehousing approach and the link-driven approach. While each approach has its strengths and weaknesses, it is important to identify which approach is best suited to a given user’s needs. We also discuss some database systems which use these three different approaches to solving the problem of data integration.

Mobile game approach to prevent childhood obesity using persuasive technology

Obesity is a condition in which the body has excess fat. Childhood obesity has become an important public health issue because affects every aspect of the life of a child. More specifically, the condition leads to poor health and negative social perceptions. Many risk factors are linked to obesity. The varying aspects of the problem and its serious implications for future health and well-being of children are enormous. The most effective solution can be achieved via programs geared to prevent such diseases. Children spend an average of more than three hours daily in front of the television, an hour at the computer, and 30 minutes playing video games, which opens major opportunities for us to propose a mobile game approach to prevent childhood obesity (MACO) using persuasive technology. MACO is a game-based persuasive mobile technology designed to inspire children to apply healthy eating habits as well as to begin and continue being physically active. This technology also introduces fun activities to motivate children to exercise more and encourage them to choose healthier food in appropriate amounts. A study on persuasive technologies application and childhood obesity prevention is conducted to determine the best persuasive technology application for MACO. The study proposes a framework and develops a system prototype.

MyHealthCentral.com: Integrating knowledge based system in personalized diet plan and menu construction

The rising awareness on weight gain has resulted in the creation of MyHealthCentral.com, a health portal that provides a complete weight management solution for users. There are various websites and web application which provide weight management application to its users but most of them are for generic users. Therefore, a personalized weight management solution would be a great way in helping users to manage their weight in a better way. The unique innovation of this portal is the capability to recommend personalized diet plan and menu construction to its users. The solutions to recommend a personalized diet plan and menu construction is to apply a knowledge-based approach that allows fast and dependable decision making process. A knowledge based framework is proposed to solve the recommendation tasks for personalized diet plan and menu construction.

Protecting privacy of children in social networking sites with rule-based privacy tool

With the growing use of social networking sites (SNS) such as Facebook, MySpace and Twitter, privacy issues have become a major concern especially for children nowadays. There is no doubt that this new form of communication is gaining popularity nowadays. SNS offer many benefits such as reconnecting long lost friends and communicating with each other by just sitting in front of the screen. However, it raises many ethical and social issues and privacy is one of them. Users are often exposed to various threats and violations because they do not know how to protect their personal information from being revealed to strangers. Hence, a system is needed to assist children in managing and controlling their privacy settings. The privacy management system proposed in this study is based on a rule-based expert system which is used to emulate human intelligence by using rules and conditions. The rules, which are the main component in a rule-based system, are used to determine the suitable privacy settings for children. The privacy settings are based on the recommendation obtained from a questionnaire given to the parents who have a Facebook account and are aware of how to manage and protect their privacy

Mediator-Based architecture for integrated access to biological databases

The amount of biological information accessible via the internet is growing at a tremendous rate. The biologists often encounter problems in accessing huge amount of widely spread data due to disparate formats, remotely dispersed and varying implementation on different platforms and data models. Besides that, the custom browsing and querying mechanism implemented in different data sources requires the users to uniquely query each individual database. Instead of having different custom interfaces to these public bioinformatics databases, an intuitive common integrated data access method is proposed to provide uniform transparent access to disparate biological databases. The proposed mediator-based architecture consists of three conceptual layers namely Query Formulation, Query Transformation and Query Execution.

A proposed framework for enhancing a Supply Chain Management System to support flood disaster relief operations

The big floods that hit Malaysia in December 2014 to January 2015 affected more than 200,000 people and caused 21 fatalities. Shortage of food supply, clean water, and problems caused by unreliable communication continued to affect flood victims even after the flood water had receded. As aid is crucial, the correct management of the supply chain is important to allow a correct and relevant assistance to the needy population. Thus, the Supply Chain Management (SCM) system, which includes inventory management system, automatic matching of supply and demand, consumption trend analysis and data visualization is critical so that the delivery of humanitarian aid can be executed on time, which in turn reduces the impact of the disaster. Lack of either one of these components can lead to problems of forecasting the needs of the flood victims and causes unnecessary delays in decision making. The main objective of this paper is to propose a framework for SCM to support flood disaster relief operation and describe the different phases within the supply chain of food aid in a humanitarian crisis. This proposed framework is to enhance the existing SCM system so that the three phases involved in a flood disaster, which are pre-disaster, during disaster and post-disaster can be managed in a more systematic way. Based on the proposed framework, a supply chain management system can be developed to include inventory management system for monitoring, managing and distributing goods; matching of supply and demand for overcoming demand uncertainty; and data visualization for quick decision making.