STORET is one method to determine the river water quality into four classes (very good , good, medium and bad) based on the data of water for each attribute or feature. The success of the formation of pattern recognition model much depends on the quality of data. There are two issues as the concern of this research as follows: the data having disproportionate amount among the classes (imbalance class) and the finding of noise on its attribute. Therefore, this research integrates the SMOTE Technique and bootstrapping to handle the problem of imbalance class. While an experiment is conducted to eliminate the noise on the attribute by using some feature selection algorithms with filter approach (information gain, rule, derivation, correlation and chi square). This research has some stages as follows: data understanding, pre-processing, imbalance class, feature selection, classification and performance evaluation. Based on the result of testing using 10-fold cross validation, it shows that the use of the SMOTE-bootstrapping technique is able to increase the accurate value from 83.3% to be 98.8%. While the process of noise elimination on the data attribute is also able to increase the accuracy to be 99.5% (the use of feature subset produced by the information gain algorithm and the decision tree classification algorithm).
Abstract. Local wisdom as product of local knowledge has been giving a local context in science development. Local wisdom is important to connect scientific theories and local conditions; hence science could be accessed by common people. Using local wisdom as a model for learning science enables students to build contextual learning, hence learning science becomes more meaningful and becomes more accessible for students in a local community. Based on this consideration, therefore, this research developed a model for learning biology based on Turgo's local wisdom on managing biodiversity. For this purpose, Turgo's biodiversity was mapped, and any local values that are co-existing with the biodiversity were recorded. All of these informations were, then, used as a hypohetical model for developing materials for teaching biology in a senior high school adjacent to Turgo. This research employed a qualitative method. We combined questionnaries, interviews and observation to gather the data. We found that Turgo community has been practicing local wisdom on using traditional plants for many uses, including land management and practicing rituals and traditional ceremonies. There were local values that they embrace which enable them to manage the nature wisely. After being cross-referenced with literature regarding educational philoshophy, educational theories and teachings, and biology curriculum for Indonesia's senior high school, we concluded that Turgo's local wisdom on managing biodiversity can be recommended to be used as learning materials and sources for biological learning in schools.
Developing a practical tool in ecology that addresses the challenge of transferring the ecologicalconcept systematically has become an essential factor in achieving a better understanding of the teaching process. Three-layer Observation Framework (TlOF) is one of the best methods that can be adopted in designing practical work in ecology since its power in providing a step-by-step concept reconstruction. This research aimed to develop a sample of practical work in ecological teaching and learning based on the TlOF. This research followed the ADDIE method in developing the product with some modifications. The research focus was set to gain product’s appropriateness from validators and users. The developed product was tested in Biology Education Department at the State Islamic University of Sunan Kalijaga, Yogyakarta in order to collect responses for further product improvement. The results of the appropriateness test from three validators showed that the developed product is “very good” with an average score of 81.8. During the performed preliminary test by users, as high as 82.5 was achieved. It means that the developed product gained a good perception from the respondents. According to the results, TlOF-based mobile learning the practical tool is the potential to become an alternative media in improving practical work in term of encompassing ecological concepts.
In the coastal areas of Parangtritis and its surroundings have plant’s diversity which is still not much researched and documented. Documentation of the useful plants by local people (ethnobotany) is needed so that knowledge will be exist. This is due to the development of technology and science, the local knowledge about plant is increasingly degraded. This study aims to find out the knowledge and use of plants by local people. Data about plant’s diversity was carried out by analyzing vegetation in the coastal areas of Parangtritis and its surroundings which consisted of three locations namely Mangrove Forest of Baros, Parangkusumo Sand Dune, and Karst around Langse Cave. Data collection of ethnobotany was carried out by direct observation and semi-structured interviews with key informants. Snowball sampling technique was used to determine the key informants. The results of the study obtained 40 plant species from 27 families. Among 40 species, there were species that had a single function or others that had multiple function. It divided into 7 usability groups, namely fodder (22 species), medicine (11 species), timber (4 species), household plant (19 species), ritual (2 species), ornamental (6 species), and crafts (2 species).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.