64 research outputs found
Catatan Kuliah Umum Rapid Earthquake Magnitude Estimation Using Near Realtime GPS Data
No full textKuliah Umum Rapid Earthquake Magnitude Estimation Using Near Realtime GPS Data Prof. Yusaku Ohta Associate Professor Crustal Physics Laboratory, Research Center for Prediction of Earthquakes and Volcanic Eruptions Tohoku UniversityAcara bertempat di Auditorium BMKG, pada tanggal 9 Agustus 2016, berlangsung dari jam 09:00 WIB sampai dengan jam 13:00 WIB.Live at: http://media.bmkg.go.id/Live.bmkg?ID=2625949045519124http://www.bmkg.go.idVia Dr. Rahma Hanifa, Dr. Abdul Muhari, Himpunan Mahasiswa Oseanografi ITB, Carmadi Machbub, Ary Setijadi Prihatmanto, Egi Hidayat, Astri Novianty, Irwan Meilano, Irina Rafliana</p
New Methodology of Block Cipher Analysis Using Chaos Game
Get PDFBlock cipher analysis covers randomness analysis and cryptanalysis. This paper proposes a new method potentially used for randomness analysis and cryptanalysis. The method uses true random sequence concept as a reference for measuring randomness level of a random sequence. By using this concept, this paper defines bias which represents violation of a random sequence from true random sequence. In this paper, block cipher is treated as a mapping function of a discrete time dynamical system. The dynamical system framework is used to make the application of various analysis techniques developed in dynamical system field becomes possible. There are three main parts of the methodology presented in this paper: the dynamical system framework for block cipher analysis, a new chaos game scheme and an extended measure concept related to chaos game and fractal analysis. This paper also presents the general procedures of the proposed method, which includes: symbolic dynamic analysis of discr ete dynamical system whose block cipher as its mapping function, random sequence construction, the random sequence usage as input of a chaos game scheme, output measurement of chaos game scheme using extended measure concept, analysis the result of the measurement. The analysis process and of a specific real or sample block cipher and the analysis result are beyond the scope of this paper
Center of Mass based Walking Pattern Generator with Gravity Compensation for Walking Control on Bioloid Humanoid Robot
No full textKombinasi Deteksi Objek, Pengenalan Wajah dan Perilaku Anomali menggunakan State Machine untuk Kamera Pengawas
Get PDFABSTRAKSaat ini sistem kamera pengawas mengandalkan manusia dalam melakukan penerjemahan pada rekaman gambar yang terjadi. Perkembangan computer vision, machine learning, dan pengolahan citra dapat dimanfaatkan untuk membantu peran manusia dalam melakukan pengawasan. Penelitian ini merancang sistem kerja kamera yang terdiri dari tiga modul yaitu deteksi objek, pengenalan wajah, dan perilaku anomali. Deteksi objek memakai HOG-SVM, pengenalan wajah menggunakan CNN dengan arsitektur VGG-16 memanfaatkan transfer learning, dan perilaku anomali memakai spatiotemporal autoencoder berdasarkan threshold. Ketiga modul tersebut diuji menggunakan metrik akurasi, presisi, recall, dan f1-score. Ketiga modul diintegrasikan dengan state machine menjadi satu kesatuan sistem. Kinerja modul memiliki akurasi 88% untuk deteksi objek, 98% untuk pengenalan wajah, dan 78% untuk perilaku anomali. Hasil tampilan riil dapat diakses secara sederhana dan nirkabel melalui web.Kata kunci: HOG-SVM, CNN, VGG-16, spatiotemporal autoencoder, state machineABSTRACTNowadays, the surveillance camera system relies on human to interpret the recorded images. Computer vision, machine learning, and image processing can be utilized to assist the human role in supervising. This study designed a camera work system consisting of three main modules, namely object detection, face recognition, and anomaly behavior. Object detection used the HOG-SVM combination. Facial recognition used CNN with the VGG-16 architecture that utilized transfer learning. Anomalous behavior used spatiotemporal autoencoder based on threshold. Modules are tested using the metrics of accuracy, precision, recall, and f1-score. The three modules are integrated using a state machine into one system. The performance of the module had 88% accuracy for object detection, 98% for facial recognition, and 78% for anomalous behavior. Real time video recording can be accessed wireless via web-based.Keywords: HOG-SVM, CNN, VGG-16, spatiotemporal autoencoder, state machin
Human gesture imitation on NAO humanoid robot using kinect based on inverse kinematics method
No full text
Educational game design using the 7 steps for designing serious games method (Case study: Mathematical subject on comparison and scale material for 7th grade junior high school)
No full textDesign and implementation of walking pattern and trajectory compensator of NAO humanoid robot
No full text- …
