I Gusti Bagus Baskara Nugraha

Environmental and disaster sensing using cloud computing infrastructure

The remote monitoring system is growing very rapidly due to the growth of supporting technologies as well. Problem that may occur in remote monitoring such as the number of objects to be monitored and how fast, how much data to be transmitted to the data center to be processed properly. This study proposes using a cloud computing infrastructure as processing center in the remote sensing data. This study focuses on the situation for sensing on the environment condition and disaster early detection. Where those two things, it has become an important issue, especially in big cities big cities that have many residents. This study proposes to build the conceptual and also prototype model in a comprehensive manner from the remote terminal unit until development method for data retrieval. We also propose using FTR-HTTP method to guarantee the delivery from remote client to server.

Home energy management system: A framework through context awareness

The motivation to manage energy usage at residential home in Indonesia is influenced by economics environment condition and technical reasons. Economically, it offers reduction of government subsidies and electricity bill. The environment condition aspect enables reduction of CO2 level. We consider the room controllable with interface control based on web. The room has a Zigbee hub, a lamp and sensors. The zigbee hubs report the power consumption information to the cloud server through home gateway. This paper purpose a system built on cloud platform based on context awareness. This system will accommodate the integration of services through sharing information platform either for the occupants or the electricity providers. Context awareness approach will provide intelligence on monitoring and controlling services based on user context and environment.

Building crawler engine on cloud computing infrastructure

This paper is aimed to create implementation crawler engine or search engine using cloud computing infrastructure. This approach use virtual machines on a cloud computing infrastructure to run service engine crawlers and also for application servers. Based on our initial experiments, this research has successfully built crawler engine that runs on Virtual Machine (VM) of cloud computing infrastructure. The use of Virtual Machine (VM) on this architecture will help to ease setup or installation, maintenance or VM terminating that has been running with some particular service crawler engine as needed. With this infrastructure, the increasing or decreasing in capacity and capability of multiple engine crawlers could set easily and more efficiently.

Mobile health monitoring and consultation to support hypertension treatment

Hypertension is a disease that can lead to heart attack and blood vessel disease. Maintain blood pressure on normal conditions can reduce the risk of hypertension and heart disease. Conventionally, patients can consult the hypertensive condition by visiting hospital then take measurements of blood pressure, doctor will diagnose the condition of a patients blood pressure, then give advice on what should be done by the patient. This paper will describe the monitoring and consultation system for hypertension treatment using smartphone devices that are integrated with medical sensor device.

Road traffic information for daily drive with level of traffic condition

Traffic jam is a big problem in road transportation. It makes everyone who is trapped reduce their productivity. Nobody wants to meet those situations. So, person hopes obtain information of traffic in their daily drive. All road users in Indonesia get road traffic information at various ways. It depends on the media which is used. There are traffic news from television, radio, social media (e.g. Twitter), etc. Nowadays, there are many mobile applications which give information about road traffic (traffic jam, traffic accident, etc.). In this paper, BlackBerry 10 mobile application has designed to provide better information in traffic monitoring system with level of traffic condition.

Web application for Jigsaw-based cooperative learning

This paper describes an applications for supporting the cooperative learning by applying the Jigsaw method. Cooperative learning is the process which people gather in groups to teach each other what they know and understand. One of the famous method of cooperative learning is Jigsaw. But, using Jigsaw method need much time, hard to divide students into some groups and evaluation the learning process is not easy. We build a system that allows to help teachers support the cooperative learning process. In this paper we propose the cooperative learning tool that can help the teacher to grouping the students automatically, and help the teacher to evaluate the learning process.

Video analysis tools for cloud-based motion detection

We present a fast moving object detection application by extending the functionality of open source tools that are available freely on the Internet. This application can be placed on a cloud infrastructure and performs fast processing so that the costs needed to use the cloud resources can be minimized.

Dam water level prediction system utilizing Artificial Neural Network Back Propagation: Case study: Ciliwung watershed, Katulampa Dam

Flooding is a natural disaster that happens annually in Jakarta because the capacity insufficiency of the canals in accommodating the overflowing river water especially under the rainy season. Hydrologists and meteorologists have tried to predict the rainfall, as it was the expected root cause of the overflow. However, there were no models available for real time water level prediction from rainfall area nearby, especially with respect to Indonesian environment characteristics. Current flood prediction system only last for 6-24 hour based on outskirts dam water level using projected time from the sluicegate to the city canals. Therefore, when there is a predicted disaster to happen, the subsequent evacuation has to be done in a short time period. Artificial Neural Network Back Propagation is one of the common methods in solving continuous data modeling and has supported multiple early warning systems in some countries. Based on the geomorphology of Ciliwung watershed, runoff drainage and land seeping variable needs to be included as one of the training attributes. Available node model has linked rainfall from nearby area to Katulampa Dam, and the model has been further developed with RMSE of 9.2142 and r (correlation coefficient) accounted for 0.8799. The result has improved the prediction capacity of the previous node model by 1%, and can be used for actual early warning system in the future. This model used batch learning for its training method but it can be upgraded to online learning where weights from the model could be readjusted automatically through continuous learning.