An experimental investigation was conducted to explore the fundamental difference among the Mamdani fuzzy inference system (FIS), Takagi–Sugeno FIS, and the proposed flood forecasting model, known as hybrid neurofuzzy inference system (HN-FIS). The study aims finding which approach gives the best performance for forecasting flood vulnerability. Due to the importance of forecasting flood event vulnerability, the Mamdani FIS, Sugeno FIS, and proposed models are compared using trapezoidal-type membership functions (MFs). The fuzzy inference systems and proposed model were used to predict the data time series from 2008 to 2012 for 31 subdistricts in Bandung, West Java Province, Indonesia. Our research results showed that the proposed model has a flood vulnerability forecasting accuracy of more than 96% with the lowest errors compared to the existing models.
4 February 2022 in Journal of Eastern European and Central Asian Research (JEECAR)
This study aims at proposing a business strategy to maintain the agricultural sector in Garut Regency during the Covid-19 Pandemic. Regardless of the fact that all sectors need special strategies to survive during the COVID-19 pandemic, there are still limited studies focusing on entrepreneurship strategies in the agriculture sector. The method used in this research was descriptive-qualitative case study. Observations were made for a period of one year from October 2019 to October 2020 to observe the resilience of the agricultural sector in Garut district, Indonesia. During the COVID-19 pandemic, the agricultural sector of Garut Regency used a closed-loop strategy, namely by establishing cooperation between farmers and the industrial as well as retail sectors. To support this strategy, a supporting strategy that considers internal and external factors in the agricultural sector is needed. This study uses SWOT analysis to determine important aspects. Based on the identified factors, various strategies were obtained to strengthen the economic structure of farmers. As a result, farmers are expected to increase production and welfare as well as can become a momentum for strengthening national food independence. This research can be used as a reference for other researchers in their research and add insight.
7 September 2023 in Journal of Advanced Research in Applied Sciences and Engineering Technology
Educational games are currently widely used as supporting media in the teaching and learning process. One of the elementary school subjects that require supporting media is mathematics. In the process of making interactive mathematics educational games for elementary school students, game developers must make a design first. The appropriate design method for this research is the Digital Game-Based Learning-Instructional Design (DGBL-ID) method. The DGBL-ID method is a development method for making educational games that can be adapted to learning materials. The purpose of this research is to help game developers in making mathematical game applications that are adapted to the 2013 curriculum that is currently applied. The focus of this research is on the analysis and design stages contained in the DGBL-ID method. The results of this research are in the form of designing games-based interactive mathematics learning media that can be used as a guide for game developers in making interactive mathematics educational games. With this design, game developers can find out what educational games are needed by users according to the characteristics and objectives of learning mathematics.
26 September 2018 in IOP Conference Series: Materials Science and Engineering
The purpose of this study is to enhance the indoor localization Algorithms in wireless sensor. Localization is one of the critical techniques in wireless sensor networks (WSNs). The implementation of localization can be used to determine object's position in the environments that could be applied both indoor and outdoor with several algorithms to estimates distance such as range-based and range-free. In this paper, the purpose of this study was to comprehensive survey of algorithms to optimize the trade-off between localization performance for an indoor area. Additionally, we discuss the application where the location information is crucial to estimate. The results of these localization algorithms comparison depict that the DV-Hop algorithm is more outstanding to detect the object location an indoor due to hop among sensor nodes rather than other algorithms with maximal range location up to 20 m, while the shortest ranges localization is TOA and TDOA with 60 cm and 90 cm, respectively.
In this paper, we evaluated the experiment and analysis measurement accuracy to determine object location based on wireless sensor network (WSN). The algorithm estimates the position of sensor nodes employing received signal strength (RSS) from scattered nodes in the environment, in particular for the indoor building. Besides that, we considered another algorithm based on weight centroid localization (WCL). In particular testbed, we combined both RSS and WCL as hybrid localization in case of noncooperative scheme with considering that source nodes directly communicate only with anchor nodes. Our experimental result shows localization accuracy of more than 90% and obtained the estimation error reduction to 4% compared to existing algorithms.