Technology Reports of Kansai University (ISSN: 04532198) is a monthly peer-reviewed and open-access international Journal. It was first built in 1959 and officially in 1975 till now by kansai university, japan. The journal covers all sort of engineering topic, mathematics and physics. Technology Reports of Kansai University (TRKU) was closed access journal until 2017. After that TRKU became open access journal. TRKU is a scopus indexed journal and directly run by faculty of engineering, kansai university.
Technology Reports of Kansai University (ISSN: 04532198) is a peer-reviewed journal. The journal covers all sort of engineering topic as well as mathematics and physics. the journal's scopes are
in the following fields but not limited to:
This research intends to obtain the discharge modeling for supporting water balance in the Konto Hulu sub-watershed-Indonesia, Based on the water balance, it can be investigated the water supply as well as the water demand. The methodology consist of discharge modeling by using F.J. Mock method that is based on rainfall data and some others one. The observed discharge data from the Automatic Water Level Recorder is used as the control of model validation. The potency of water supply is known from the dependable discharge due to the probability of 80% and the results is 22.41 m3/s that is proportional with 706.622 million m3 per-year, The water demand in incoming 25 years on scenario-1 (based on the growth rate) is 95.085 million m3 per-year, however on scenario-2 (based on the increasing estimation of domestic, non-domestic, and industry) is about 93.418 million m3 per-year. The result of water balance shows that the potency of water supply can fulfill the whole water demand or it shows the condition of water surplus reaches until 25% in 2017-2042
Breast cancer detection is one of imbalanced classification problem in machine learning. The breast cancer dataset consists of significantly more class of non-cancerous observations than the cancerous observations. The classification of imbalanced dataset is a problem to machine learning algorithm due to the fact that the standard machine learning algorithms assume the class in the dataset are balanced or equal. The imbalance of the classes in breast cancer dataset makes the detection of breast cancer more difficult with the existing standard machine learning algorithms. This is because the algorithms are biased prediction due to the class imbalance in the dataset. In this research, a solution to imbalanced classification problem is proposed by proposing a weighted decision tree model for breast cancer detection. Finally, the performance of the proposed model is tested and result reveals an accuracy of 94.03% is achieved. Moreover, experimental test on the breast cancer dataset shows that better performance is achieved by the proposed model as compared to the standard decision tree model
