Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Telematika

Comparison of Inverse Kinematics and Forward Kinematics Methods on Walk Cycle Animation Characters Afifah Nur Aini; Ema Utami; Suwanto Raharjo
Telematika Vol 14, No 1: February (2021)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v14i1.888

Abstract

The 3D animation industry is currently growing rapidly, but the process of animating 3D characters is not always fast, because it is often constrained at the animation stage due to the complexity or irregularity of the function of each rig on the 3D character object, therefore it takes a proper rig creation stage to support the animation process that is more efficient in terms of process and time. Kinematics in animation is used for reference when an object is moving. The animation uses a Kinematics approach to display natural results. This research aims to study the level of effectiveness in terms of the time span required to drive the 3D Walk cycle animation using the attached Kinematics & Advanced Kinematics methods. The animation reference used was a standard human Walk cycle with the extent for each part of the body to be animated such as head animation, hand animation, foot animation, and bed animation to complete a walking compilation of animated Walk cycle. The execution of each part is carried out by the inverse kinematics method and then proceed with the advanced kinematics method. Based on the results of the implementation in each section of the walk cycle by comparing the two methods, Inverse Kinematics is an effective method for animating the legs and the head. While the Forward Kinematics method is more effective in animating the hands, body parts, and finishing movement. The results of the comparison show that the level of time effectiveness in human character 3D animation movements using the inverse kinematics method compared to forward kinematics are 31.18% in body animation, 40.46% in foot animation, 13.94% in hand animation, 2.04% in head animation motion, and 7.61% for finishing walk cycle movement.
Stacked LSTM-GRU Model for Traffic Anomalies Detection Alsyaibani, Omar Muhammad Altoumi; Utami, Ema; Raharjo, Suwanto; Hartanto, Anggit Dwi
Telematika Vol 15, No 2: August (2022)
Publisher : Universitas Amikom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35671/telematika.v15i2.1855

Abstract

This study aims to improve the accuracy of the intrusion detection system model. It focused on LSTM and GRU methods proposed by several previous studies. The bidirectional layer was also tested to see if it improves model performance. Dataset used in the study was CIC IDS 2017. The dataset was divided into 3 parts, for training, validation, and testing purposes. Validation data was used to evaluate model performance in every training iteration. It helped to make the model would not overfit the training data. Furthermore, Dropout layer and L2 regularization were also added to the model architecture. The training model was done in a binary classification approach with a learning rate of 0.0001. We found that the stacked method reached accuracy 98.1087% in 100 iteration training. This result is slightly higher than LSTM, GRU, Bidirectional LSTM, and Bidirectional GRU. The method which contains LSTM layer performed its best accuracy using Tanh activation. Differently, GRU and Bidirectional GRU performed the best performance with Lrelu and Prelu activation function, respectively. All models could reach the plateau in the first 20 iterations, while in the next 80 iterations the model performance still could be fluctuately improved. Even though the model already reached the plateau in 20 iteration training, it is still possible for the model to slowly improve by using a small learning rate and by implementing Dropout layer and L2 regularization. Fluctuation of model performance implies that the highest model performance was not always reached in the last training iteration. ModelCheckPoint could help to overcome the issue. In addition, the Bidirectional layer increased the complexity of the model which certainly increased training duration. The bidirectional layer improved the performance of the GRU method, but it did not improve the performance LSTM method.
Co-Authors -, Komarudin Abdul Malik Zuhdi Achmad Yusron Arif Ade Rizki Saputra Afifah Nur Aini Aflahah Apriliyani Ahmad irfa’i Alsyaibani, Omar Muhammad Altoumi Amalia Febryane Adhani Mazaya Amir Hamzah Amir Hamzah Amir Hamzah Amrullah, Yusuf Amri Andi Kriswantono Anggit Dwi Hartanto, Anggit Dwi Apolinarius Gusala Argaditia Mawadati Ari Sabela Anggraini Arief Setyanto Arief, Achmad Yusron Arif Nur Rohman Arif setiadi Arif, Achmad Yusron Aziz Nurwahidin Cahyono, Nova Tri Cahyono, Nova Tri Candra Kusuma Catur Iswahyudi Catur Iswahyudi Catur Iswahyudi Catur Iswayudi Danang Kastowo Dani Yulkarnain Dewo Pambudi Dimas Wiryatari Dodik Prakoso Eko Hery Suwandojo Dodik Prakoso Eko Hery Suwandojo Dzakiya, Nurul Edhy Sutanta (Jurusan Teknik Informatika IST AKPRIND Yogyakarta) Edi Winarko Eka Suteja Eko Darmanto Eko Haryanto Eko Haryanto Eko Pramono Eko Pramono Ema Utami Ema Utami (Jurusan Sistem Informasi STMIK AMIKOM Yogyakarta) Emy Setyaningsih Emy Setyaningsih Enggar Febriyanti Enie Yuliani Erfanti Fatkhiyah Erma Susanti Ermawati - Erna Kumalasari N Erna Kumalasari Nurnawati Eska Almuntaha Faisal Siregar Fuad Hasan Gardyas Bidari Adninda Gardyas Bidari Adninda Gatot Santoso Gatot Santoso Gunawan Wicahyono Hanafi Eko Kurniawan Hardianto Nugroho Hari Rachmadi Hartanto, Anggit Dwi Hendrik Satria Harefa Heri Sismoro Hilarion Yogi Ibnu Berliyanto G.A Ibnu Berliyanto G.A, Ibnu Berliyanto Imam Syafii Imam Syafii Imam Thoib Indarto Indarto Irwan Siswanto Jazi Eko Istiyanto (Program Magister Ilmu Komputer Sekolah Pascasarjana UGM) Joko Triyono Joko Triyono Joko Waluyo JULIANTO Julianto Jussac Maulana Masjhoer Khalil Sidik Khalil sidik Koco Anggoro Kurniati, Devi Kurniawan, Hanafi Eko Laksono Trisnantoro M Yusuf Ali Fiqri M. Abdul Alim Alami M. Ari pamungkas1 M. Rudiyanto Arief Maulana Wahid, Rindo Mazaya, Amalia Febryane Adhani Merlie Anita Miftah Farid Moh Erzal Arighi Damopolii Moh. Ishaq Yanuar Mohammad Sholeh Muh. Ibnu Habil Hanafi Muh. Ibnu Habil Hanafi, Muh. Ibnu Habil Muhamad Fatahillah Z Muhammad Arif Setyawan Muhammad Fahrizal Farid Muhammad Farid Ali Safii Muhammad Puguh Pamungkas Muhammad Rosyid Muhammad Saleh Jafri Muhammad Sholeh MUHAMMAD SHOLEH Munandar, Arief Mursyid Ardiansyah Mustofa Wisnu Dhamara1 Naniek Widyastuti Nansi, Maria Regina Nidia Lestari Nurcahyo, Azriel Christian Okid Parama Astirin Omar Muhammad Altoumi Alsyaibani Prabowo Budi Utomo Prita Haryani Prita Haryani Purnawan Purnawan - Purnawan Purnawan Purnawan Purnawan R. K. ST., MT., Rr. Yuliana Rahardyan Bisma Setya Putra Ramadhan, Hanan Fajar Rauf, Budi Wijaya Rendi Saputra Rio Ponco Negoro Muhammad Hakim Rizal Fakhruddin Lubis Rizki Pratama Rizqa Luviana Musyarofah Rizqi Aji Nugroho Robertus Desta Raka Siwi Robertus Desta Raka Siwi, Robertus Desta Rohmat Hidayat Rohmat Hidayat Rr Yuliana Rachmawati Kusumaningsih Rr. Yuliana Rachmawati Rr.Y. Rachmawati Kusumaningsih Rr.Yuliana Rachamawati, Rr.Yuliana Ryvan Sirait S.T., M.T, Muhammad Sholeh, Samuel Kristiyana Saryadi K T Soba Saryadi K T Soba, Saryadi K T Setya Putra, Rahardyan Bisma Siswanto - Slamet Hani, Slamet Sofyan Pariyasto Sri Hartati Stefanus Samuel Tampi Suparni Setyowati Rahayu Suraya - Suraya - Suraya ., Suraya Syafrizal S Ardiansyah Syahrudin, Erwin Tampi, Stefanus Samuel Thaariq, Muhammad Rizqy Ath Than Raymond Toto Rusianto Triyono, Joko Uning Lestari Uning Lestari Utami, Ema Utami Utamu, Ema Vian Ardiyansyah Saputro Vian Ardiyansyah Saputro Wahyu Hidayat Wahyudi, Doni Yoga Arjanggi Nofianto Yuki Syambudi Setiadi Yuli Purwanto Yuli Purwanto Yuliana Rachmawati Yulianto Mustaqim Zeppi Maulana Bhakti