Abstract: Data mining, also referred to as knowledge extraction from databases, is one of the most important analytical methods for identifying the relationships between the various elements of the information collected in order to discover the useful knowledge and support of strategic decision-making and sustainable development systems in various industries. Mathematical modeling, quantitative analysis of data and new algorithms can identify new relationships between different data, which in turn leads to competitive advantage. Olive oil is one of the most important agricultural crops due to its digestive properties and economic status. However, olive oil production is a costly process which causes an expensive price of the final product. The most jobbery ways during olive oil production consist of mixing other oils such as maize, sunflower, Canola and corn into the olive oil. So, the aim of this study was to develop a dielectric-based system to Authenticate in olive oil using cylindrical capacitive sensor. For categorizing of fake olive oil by using frequency specification, Support vector machine, linear regression, Ensemble Trees and Gaussian was developed. A set of 16 samples of olive oil, sunflower, canola and corn oil which mixed with different ratio of Authentication, were used for calibration and evaluation of developed system.Abstract: Data mining, also referred to as knowledge extraction from databases, is one of the most important analytical methods for identifying the relationships between the various elements of the information collected in order to discover the useful knowledge and support of strategic decision-making and sustainable development systems in various industries...Show More
Abstract: The objective of the present study was to investigate the economic consequences of non-communicable diseases of adults at household level. According to the objective of the study the analysis was done using data collected from 808 adults of Bangladesh who were investigated by some doctors and nurses from and nearby their working places. Among these adults 49.6 percent were suffering from at least one of the non-communicable diseases. The most common non-communicable disease was diabetes. The percentage of exclusive diabetic patients among NCDs affected adults was 55.9 followed by diabetic-cum-heart (14.0%) and diabetic- cum- kidney (9.5%) patients. The percentage of admitted NCDs patients in hospital was 71.1 and they were treated for, on an average, 4.72 days incurring an opportunity loss of 37.75 working hours. The economic loss per month for treatment was Tk.3030.21. This economic loss was 4.04 percent of the monthly family income. The economic loss and the opportunity loss due to hospital admission was the economic burden to the individual household.Abstract: The objective of the present study was to investigate the economic consequences of non-communicable diseases of adults at household level. According to the objective of the study the analysis was done using data collected from 808 adults of Bangladesh who were investigated by some doctors and nurses from and nearby their working places. Among these...Show More
Abstract: Knowledge discovery, shortly known as Data mining plays a crucial role within the insurance sector. Serious troublesome cases such as fraudulent cases can be well managed in the insurance sector through data mining application. In this paper, we aim to put on surface the two forms of fraud that is softy and hard fraud, to give out the causes of such fraudulent acts and to state out different suggested data mining techniques that can be applied to the insurance data to detect fraud. Also, we aim to highlight other benefits that can be enjoyed from using data mining in the insurance sector. We conjectured and found that, application of data mining helps to quickly detect fraud, reduce operation cost and to improve profit margins and increased competitive advantages. We put forward that techniques such as association, clustering, classification and regression are good when detecting fraud from the insurance claims data and should be acquired and applied. We then recommended that, underwriters and insurance officials should contribute much in preventing fraudulent cases in the insurance sector. This is so because, prevention is better than cure. Above all, we concluded that, application of data mining techniques through sequential pattern mining can help much to predict any future and potential fraudulent cases. This is helpful on planning and to keep the insurers alert before the fraudulent risk occurs.Abstract: Knowledge discovery, shortly known as Data mining plays a crucial role within the insurance sector. Serious troublesome cases such as fraudulent cases can be well managed in the insurance sector through data mining application. In this paper, we aim to put on surface the two forms of fraud that is softy and hard fraud, to give out the causes of suc...Show More