IJOER: August 2021

Engineering Journal: published its volume-7, Issue-8, August 2021 with AD Publications

Credit Card Fraud Detection using SMOTE and Ensemble Methods

Abstract We focused on the study of using math modeling and machine learning to do big data analysis, therefore to detect Credit card fraud, which is one of the serious issues in real life. In order to detect credit card fraud, after reviewed many recent research, we chose the most popular models among credit card fraud detection, which are Random Forest (RF), and ANN with multi-layers (DNN). We evaluated the accuracy and recall of these models in detecting credit card fraud with or without SMOTE, and found out that there is no significant improvement in the accuracy of these models with or without SMOTE training, but RF with SOMTE has a little bit vantage than others. There is a significant improvement in recall of these three models with SMOTE training. Especially, with SMOTE training, ANN or DNN is of better performance in the recall than RF. Therefore, we combine RF and DNN to generate a hybrid model so that it produces better stability in accuracy and recall. The study discovered that neural network models have greater potential for finding abnormal data in the big data stream. This has important guiding significance for what mathematical model that credit card companies use to monitor the cash flow and remind customers of the possible risk of credit card fraud.

Click here to Download Full Paper

Assessment of Some Heavy Metals as Contaminants in Petroleum Contaminated Soils of Eleme, Port Harcourt Nigeria

Abstract Samples from petroleum contaminated soil of Eleme, Port Harcourt and from non petroleum contaminated soil, Awka, Nigeria serving as control were analyzed for heavy metals. The results of the analysis showed that the metals concentrations in mg/kg were Ni <0.05- 2.05, Cr 0.005- 0.37, Cd <0.005- 0.008, Zn 0.14 – 2.87 Pb <0.02- 0.19 Fe 12.32-29.11, Mn < 0.008- 0.036, Se <0.001, as <0.001, and V <0.001. Majority of the metal concentrations were above those of the control. Though the values obtained did not exceed soil quality standards stipulated in the Environmental Management Regulations, 2007, the toxic metals could accumulate to a threatening level over a period of time. Food poisoning, occupational hazards and various disorders emanate from heavy load of toxic metals in our environment.

Environmental pollution may result from industrial and commercial activities when substances resulting from these activities enter the environment and attain levels which may cause discomfort and / or harm to man and his environment (Udosen et al, 1990). From the point of view of environmental pollution, metals may be broadly classified into three categories namely, non-toxic but accessible, toxic but non-accessible and toxic and accessible .It is the third category that has attracted more attention from the point of view of environmental pollution and public health (Dara, 2008).

Moriber (1974) reported that the consumption of waste water from a mine which produced cadmium, zinc and lead resulted in rickets-like disease called itai-itia.

Keywords— Heavy Metals as Contaminants, Petroleum Contaminated Soils, Port Harcourt, soil quality, toxic metals.

Click here to Download Full Paper
Translate »