50 research outputs found
Pengenalan Nomor Polisi Kendaraan pada Data Video Menggunakan Convolutional Neural Network
No full textMachine learning telah menjadi bagian dari kehidupan sehari-hari bagi banyak orang. Salah satu pengaplikasian machine learning adalah pengenalan nomor polisi kendaraan. Pengenalan nomor polisi kendaraan mengkategorikan citra karakter-karakter yang ada. Banyak perusahaan, badan riset dan universitas yang terus mengembangkan machine learning agar mendapat hasil yang lebih akurat dan cepat. Dari situlah lahir algoritma deep learning, yang merupakan bagian dari machine learning. Convolutional Neural Network (CNN) adalah salah satu deep neural network yang cocok digunakan untuk mengolah data yang berbentuk 2 dimensi, seperti gambar dan video. Pada tugas akhir ini, penulis mengusulkan penggunaan CNN untuk melakukan pengenalan karakter plat nomor pada data video. Tujuannya adalah untuk membangun sistem yang dapat mengenali karakter pada citra plat nomor. Data pelatihan dan uji merupakan data yang diambil secara mandiri oleh penulis. Data latih merupakan karakter-karakter dari citra plat nomor yang telah dilakukan proses cropping. Praproses terhadap data antara lain dilakukan perubahan kanal citra menjadi grayscale, padding, perubahan resolusi gambar menjadi 32x32 piksel, dilakukan proses morfologi, dan dilakukan proses augmentasi data berupa rotasi dan perbesaran ukuran gambar. Hasil uji coba optimal didapatkan dari arsitektur CNN dengan optimizer Adam, ukuran kernel 4x4 pada Convolution Layer ketiga, dan lokalisasi YOLO dengan nilai akurasi 89,53%
====================================================================================================================================
Machine learning has become a part of the daily life of people around the world. One of the application of machine learning is automatic plate number recognition. Automatic plate number recognition categorize characters found on the plate itself. Many companies, researchers and universities keep improving the machine learning to get a better and faster result. And from those improvements, deep learning algorithm is born. Convolutional Neural Network (CNN) is one of the deep neural network that suitable to process 2 dimentional data like image and video. In this undergraduate thesis, author suggest the use of CNN to classify characters from the plate number. The purpose of this undergraduate thesis is to build a system that can regognize characters on plate number. The datasets itself are taken by the author from author’s surrounding neighborhood vehicles while the data test also taken by the author surrounding neighborhood vehicles. The data train are characters, cropped from plate number that taken by the author. Some preprocessing include are image grayscaling, image padding, resizing to 32x32 size, morphological operation, and data augmentation to increase the variety of the dataset. Final optimal result got from the testing from CNN architecture with Adam optimizer, kernel size 4x4 on the third Convolution Layer and YOLO localization are 89,53% for testing accuracy
Noise Considerations for Propulsion System Evaluation
No full textThe laws and regulations regarding the radiated noise and the on-board noise of the ship are expected to be stricter in the future. There is a big concern in this field, especially for the underwater noise. The radiated noise from the ship is harming the life of the underwater mammals while the on-board noise is threatening the health of the on-board crew. One of the main contributors to the noise generated by a vessel is the propulsion system. It is true that the noise reduction can be achieved by doing the corrective action in the later design stage, such as installing mounting and noise absorption material. Nevertheless, the decision in early-design stage often gives the highest impact on the noise generated by the propulsion system where the level of uncertainty is high. This thesis has two main goals; to determine the design choices of propulsion systems which affect the noise excitation, and to develop an evaluation methodology to assess a certain power configuration from the perspective of generated noise. First, the aspects of the propulsion system that affect its noise are determined. Those are transmission types, number of engines, number of shafts and number of compartments. The loading point is also included as one of the parameters. Although it is not a design choice, it has a significant role in the noise generated by the propulsion system. Second, the selection of the significant noise source in the propulsion system needs to be done. There is much equipment inside a propulsion plant, but not all of them give sufficient contribution to the overall noise level. Based on the literature review, the equipment that is considered as the main noise sources are the diesel engine, the diesel generator set, the reduction gear and the electric motor. A noise model from SNAME is implemented in this project to predict the airborne and structure-borne noise source levels of the equipment and the transmission losses to the receiver location. An engine room-sizing model is developed in this project since the transmission loss is a function of the compartment dimensions. Furthermore, the room dimensions depend on the equipment dimensions. Therefore, it is necessary to develop a model to predict the size of the equipment too. Afterwards, the evaluation methodology is established to quantify the effect of a certain design choice towards the noise of a propulsion system. The effects of varying ship requirements are also investigated to see the behaviour of the model with a different input. These requirements are the ship installed power, the ship propulsion power and the ship auxiliary power This project provides a general guideline for the marine engineer to evaluate the propulsion system based on the noise considerations in the early design phase. The evaluation methodology proves to be applicable to a wide range of propulsion plant type. It is possible to extend the application of this method for a ship with prime mover other than the diesel engine and the electric motor. Marine Technology | Ship Design, Production and Operation
Effect of maleic anhydride treatment on the mechanical properties of sansevieria fiber/vinyl ester composites
No full textEarly pictures of global climate change impact to the coastal area (North West of Demak Central Java Indonesia)
No full textDeformation analysis in the East Nusa Tenggara and Banda Islands based on GPS observation from 2010-2015
No full textSIFAT INKLUSI DAN PERUMUMAN KETAKSAMAAN HÖLDER PADA RUANG BARISAN ORLICZ
Get PDFRuang Orlicz adalah perumuman dari ruang Lebesgue yang dikenalkan oleh Z. W. Birnbaum dan W. Orlicz pada tahun 1931. Terdapat dua versi ruang Orlicz, yaitu ruang Orlicz kontinu dan ruang barisan Orlicz. Topik utama penelitian ini adalah mengenai ruang barisan Orlicz. Pada penelitian ini, penulis memperlihatkan syarat cukup dan perlu sifat inklusi dan keberlakuan ketaksamaan Hölder pada ruang barisan Orlicz. Lebih jauh lagi, penulis memperoleh syarat cukup dan perlu perumuman ketaksamaan Hölder pada ruang barisan Orlicz. Salah satu cara yang digunakan untuk membuktikan hal tersebut adalah dengan menggunakan norma dari barisan karakteristik pada Z.
Orlicz spaces are generalization of the Lebesgue spaces which was introduced by Z. W. Birnbaum and W. Orlicz in 1931. There are two versions of Orlicz spaces, namely continuous Orlicz spaces and Orlicz sequence spaces. The main topic of this study was about Orlicz sequence spaces. In this study, the author showed the sufficient and necessary conditions for inclusion properties and Hölder's inequality in Orlicz sequence spaces. Furthermore, the author obtained the sufficient and necessary conditions for generalization of Hölder's inequality in Orlicz sequence spaces. One of the keys to prove these results was by using the norm of the characteristic sequence in Z
PERANCANGAN PRODUK TAS KERJA RCD DENGAN METODE QUALITY FUNCTION DEPLOYMENT (QFD) DI CV RCD BANGIL
No full textJika membutuhkan abstrak atau isi jurnal silakan menghubungi author melalui email [email protected] atau [email protected]
GAP ANALISIS DAN IMPORTANCE PERFORMANCE ANALYSIS POTENSI WISATA UMBUL JOLOTUNDO KABUPATEN KLATEN
No full textJika membutuhkan abstrak atau isi jurnal silahkan menghubungi author melalui email [email protected], [email protected]Â
Settlement of Criminal Actions Not Appearing Without Permission Through Military Discipline Legal Mechanism in Order Unit and Personnel Development
No full textThe law that applies specifically to military personnel consists of formal and material Military Criminal Law, apart from that there is also military discipline law which is regulated by law. Military crimes can be divided into two, namely pure military crimes and mixed military crimes. One of the pure military crimes is the crime of not being present without permission. The crime of being present without permission is generally regulated in CHAPTER III Book II of the Military Criminal Code, but this crime is also regulated in the Military Discipline Law as a violation of military discipline. With these conflicting legal regulations, the author then raises this problem into a thesis. The problem formulation that the author presents is: How is military disciplinary law applied to the crime of not being present without permission and what are the consequences of resolving THTI crimes through military disciplinary legal mechanisms in the face of unit and personnel development? There are three possibilities for resolving THTI crimes through military disciplinary legal channels. . The research method in this thesis is normative juridical using military discipline law enforcement theory, unit and personnel development theory and legal certainty theory. The conclusion of this research is that the criminal act of not being present without permission can be resolved through military disciplinary law, namely a criminal act in the narrow sense, namely Article 85 1 and Article 86 1 of the KUHPM. Completion of legal discipline will of course have an impact on the development of the unit and personnel concerned in the form of postponement of rank or education
Potensi Manufacture of Biodegradable Plastics from Cassava Peel Strach and Garut Sweet Potato Strach with Melt Intercalation methods in supporting of SDG's
Get PDFThe background of this research began with initiation in Indonesian has been at an alarming level. According to the Indonesian Retail Entrepreneurs Association (APRINDO) in one year, it has reached 10.95 million pieces of plastic bag waste. Therefore, this research aims to accelerate the level of degradation by replacing synthetic polymeric materials into natural polymers, namely using starch because it is easily degraded, abundant. As a solution to the problem, the author invites Biodegradable Plastics from Starch Garut Sweet Potato and Cassava Peel Starch. The research method using the Melt Intercalation method is that no additional solvents are needed in making bioplastic films. As a base material Starch Garut Sweet Potato and Cassava Peel Starch which have high potential as the main ingredients for Biodegradable plastic. Therefore, by combining Starch Garut Sweet Potato and Cassava peel starch, it is hoped that it can minimize the buildup of plastic wast
