Ahmad Nadhir

Implementation of Town Watching and Development of Observatory for Community Education in Volcano Hazard Mitigation: study case at Kelud and Arjuno-Welirang volcanoes, East Java, Indonesia

A Town Watching has been implemented at Kelud volcano region and an Observatory is being developed at Arjuno-Welirang Volcano Hosted Geothermal area in order to improve community education for volcano hazard mitigation in East Java, Indonesia. From the results shown that the level of participants interest was good because more than 75% expressed interest in the Town Watching implementation and 70% participants stated that they understand about the material presented at the event. All of the participants stated that the Town Watching was necessary and they hope that it could be done periodically. Almost 95% participants satisfied and 90% participants expected that similar town watching should be done in the future. In addition, an observatory of volcano was being developed at Arjuno-Welirang volcano complex in strengthening education in the field of volcano hosted geothermal. The observatory can be developed as part of pilot project in community education in that field. In the future, it can be integrated with town watching as a unity in education and research in the field of volcano hazard mitigation.

Haar-like feature based real-time neuro car detection system

A real-time neuro car detection system based on the Haar-like feature is presented in this paper. The proposed system relies on an artificial neural network (ANN) to recognize the car object. ANN was trained using the Haar-like features extracted from the negative and positive car image data. The car objects vary with their sizes and trademarks. However, they have common features which can be assumed unique for the car. In this paper, the common features of the various car objects were transformed into the Haar-like features and then used to train ANN. The system was implemented on the embedded PC Raspberry Pi 3 using the camera SJCAM SJ4000. The research results show that the detection accuracy was influenced by many factors. The developed system resulted in the accuracy coefficient of up to 95% and the detection speed of about 700 ms per frame.