Article Per Year (5 Year)
p-Index From 2019 - 2024
2.083
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Ilmiah Informatika Komputer Jurnal Ilmiah Teknologi dan Rekayasa Majalah Ilmiah Matematika Komputer Perfecting a Video Game with Game Metrics PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika InComTech: Jurnal Telekomunikasi dan Komputer J I M P - Jurnal Informatika Merdeka Pasuruan
Tubagus Maulana Kusuma
Gunadarma University
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mathematics

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
IMAGE ARTIFACTS AND NO-REFERENCE FEATURE EXTRACTIONS: A REVIEW Kusuma, Tubagus Maulana
Majalah Ilmiah Matematika Komputer 2007: MAJALAH MATEMATIKA KOMPUTER EDISI APRIL
Publisher : Majalah Ilmiah Matematika Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1064.227 KB)

Abstract

Image attributes, such as shape, orientation, size, texture, gradient, luminance, brightness, andcontrast can be easily recognized by human visual system. All these attributes contribute to thecharacteristics of an image or image features, which reveal uniqueness of the image. Once theimages get corrupted due to compression or transmission, the unexpected artificial features, whichare not existing in the origi"al images are introduced. The characteristics of these unexpectedfeatures known as artifact characteristics vary from one artifact to another By knowing the originalimage features, un-expected features can be detected. There are a number of feature extractiontechniques that can be used to extract image features, in order to observe the presence of artifacts.These techniques can be generally classified into two categories, as spatial domain based andtransform domain based. This paper presents a review of the existing spatial domain artifactextraction techniques using no-reference (withoul comparison to original image) as they arecomputationally inexpensive and suitable for in-service quality monitoring.Keywords: Artifact, feature extraction, error, blocking, blur, ringing, masking, lost blocks.
LINK ADAPTATION UTILISING PERCEPTUAL IMAGE QUALITY METRICS BASED ON REGION OF INTEREST Kusuma, Tubagus Maulana; Zepernick, Hans-Jurgen
Jurnal Ilmiah Informatika Komputer Vol 12, No 1 (2007)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

An implicit link adaptation technique based on hybrid automatic repeat request (H-ARQ) using a soft-combining algorithm is considered for transmission of Joint Photographic Experts Group 2000 (JPEG2000) images over wireless channels. Adaptation is carried out using an objective perceptual quality metric that takes into account the human perception. Retransmissions based on Region of Interest (ROI) are used to efficiently utilize the bandwidth. Numerical results shows that the use of the proposed reduced-reference hybrid image quality metric (RR-HIQM) and ROI in link adaptation provides robust link performance while meeting saticfactory quality constraints.Keywords : link adaptation, objective perceptual image quality metric, JPEG2000, region of interest
ANALISIS SENSITIVITAS VIDEO MPEG-4 BERDASARKAN STRUKTUR FRAME PADA TRANSMISI DVB-T Prayogo, Sandy Suryo; Kusuma, Tubagus Maulana
Jurnal Ilmiah Informatika Komputer Vol 25, No 2 (2020)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2020.v25i2.2691

Abstract

DVB merupakan standar transmisi televisi digital yang paling banyak digunakan saat ini. Unsur terpenting dari suatu proses transmisi adalah kualitas gambar dari video yang diterima setelah melalui proses transimisi tersebut. Banyak faktor yang dapat mempengaruhi kualitas dari suatu gambar, salah satunya adalah struktur frame dari video. Pada tulisan ini dilakukan pengujian sensitifitas video MPEG-4 berdasarkan struktur frame pada transmisi DVB-T. Pengujian dilakukan menggunakan simulasi matlab dan simulink. Digunakan juga ffmpeg untuk menyediakan format dan pengaturan video akan disimulasikan. Variabel yang diubah dari video adalah bitrate dan juga group-of-pictures (GOP), sedangkan variabel yang diubah dari transmisi DVB-T adalah signal-to-noise-ratio (SNR) pada kanal AWGN di antara pengirim (Tx) dan penerima (Rx). Hasil yang diperoleh dari percobaan berupa kualitas rata-rata gambar pada video yang diukur menggunakan metode pengukuran structural-similarity-index (SSIM). Dilakukan juga pengukuran terhadap jumlah bit-error-rate BER pada bitstream DVB-T. Percobaan yang dilakukan dapat menunjukkan seberapa besar sensitifitas bitrate dan GOP dari video pada transmisi DVB-T dengan kesimpulan semakin besar bitrate maka akan semakin buruk nilai kualitas gambarnya, dan semakin kecil nilai GOP maka akan semakin baik nilai kualitasnya.  Penilitian diharapkan dapat dikembangkan menggunakan deep learning untuk memperoleh frame struktur yang tepat di kondisi-kondisi tertentu dalam proses transmisi televisi digital.
RANCANG BANGUN AGROBOT-II: ROBOT EDUKASI PENANAM BENIH TANAMAN PADI DENGAN KENDALI JARAK JAUH Prayogo, Sandy Suryo; Permadi, Yogi; Kusuma, Tubagus Maulana
Jurnal Ilmiah Teknologi dan Rekayasa Vol 25, No 2 (2020)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2020.v25i2.2676

Abstract

Pertanian konvensional yang mengalami penurunan baik dari jumlah petani dan hasil panennya berdampak pada penurunan ketersediaan pangan. Untuk mengatasi permasalahan tersebut, maka teknologi otomasi di bidang pertanian perlu dikembangkan, terutama untuk menarik minat generasi muda terhadap bidang pertanian. Oleh sebab itu, pada penelitian ini dirancang dan dibangun sebuah robot pertanian untuk keperluan edukasi dalam hal otomasi tanam dan panen tanaman padi yang diberi nama Agrobot-II. Robot ini dikendalikan dari jarak jauh dari perangkat telepon cerdas ataupun perangkat tablet berbasis Android untuk melakukan proses tanam dan panen tanaman padi yang juga dilengkapi dengan kamera sebagai alat bantu penglihatan bagi pengoperasi robot. Robot dibangun dengan menggunakan platform pengendali mikro (microcontroller) Arduino yang terhubung melalui komunikasi nirkabel bluetooth kepada sistem kendalinya, serta komunikasi nirkabel WiFi untuk menghubungkan pengendali dengan kamera pada robot. Hasil pengujian terhadap fungsi robot telah berhasil dilakukan, yaitu dari proses tanam, pencabutan gulma, dan panen. Selain itu, pengujian terhadap jarak kendali maksimum menggunakan komunikasi bluetooth yaitu pada jarak 16 meter telah berfungsi dengan baik tanpa adanya delay. Selanjutnya jarak maksimum kamera dapat tetap melakukan streaming ke perangkat Android yaitu pada jarak 15 meter, dimana terjadi delay setelah melewati jarak 8 meter. Tingkat keberhasilan rata-rata penanaman padi yaitu 90% dan rata-rata keberhasilan melakukan panen adalah 70% dari gabungan dua jenis skema, yaitu manual dan otomatis.
ROBOT EDUKASI PERTANIAN AGROBOT-I: RANCANGAN ELEKTRONIKA DAN SISTEM PENGGERAK Permadi, Yogi; Prayogo, Sandy Suryo; Kusuma, Tubagus Maulana
Jurnal Ilmiah Informatika Komputer Vol 26, No 1 (2021)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2021.v26i1.2696

Abstract

Berkurang peminat generasi muda terhadap pertanian konvensional berdampak pada penurunan ketersediaan pangan, untuk mengatasi permasalahan tersebut, maka teknologi otomasi dibidang pertanian perlu dikembangkan selain untuk mempermudah juga untuk meningkatkat minat generasi penerus pertanian di Indonesia. Pada penelitian ini dirancang dan dibangun sebuah prototipe robot pertanian untuk keperluan edukasi dan penelitian dalam hal otomasi tanam dan panen tanaman padi yang diberi nama Agrobot-I. Robot ini dapat bergerak medan tanah lahan pertanian untuk melakukan proses tanam, perawatan tanaman dari gangguan gulma dan proses panen tanaman padi yang dilengkapi dengan mekanik gripper yang menyerupai lengan sebagai alat bantu untuk melakukan ketiga pekerjaan tersebut. Robot yang memiliki tujuan utama untuk sarana edukasi dan pengenalan terhadap aplikasi teknologi pada bidang pertanian ini diharapkan dapat memberikan gambaran proses pertanian yang sesungguhnya, meskipun hanya dalam bentuk simulasi di lingkungan buatan. Pengujian dilakukan terhadap fungsi masing-masing sistem penggerak yang dikendalikan menggunakan mikrokontroller Arduino dari pergerakan motor DC yang menggunakan sistem differensial drive. Pengujian terhadap lengan robot dari peneumatik untuk menaik turunkan lengan, pengujian cartesian untuk sb-x dan sb-y dari lengan, dan juga lengan itu sendiri yang menggunakan motor servo. Hasil pengujian terhadap fungsi robot secara keseluruhan telah berhasil dilakukan, yaitu dari proses tanam, pencabutan gulma, dan panen.
Adaptive power link adaptation on DVB-T system based on picture quality feedback Tubagus Maulana Kusuma; Randy Rahmanto; Emy Haryatmi
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 4: August 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (804.114 KB) | DOI: 10.11591/ijece.v9i4.pp3121-3129

Abstract

In digital television systems such as DVB-T, service provider has difficulties to observe the quality of picture reception in the viewers’ television. This is due to the unavailability of quality feedback sent from viewers’ devices to the service provider. Therefore, this research proposes link adaptation method in DVB-T system based on image quality measurement at recipient side, so that service provider may adjust the transmission power in real-time to improve the image quality. Quality metric used in this research is human perception- based no-reference image quality metric, which does not need the presence of the reference frame. The quality assessment is focused on the severeness of blocking artifact, which is the dominant artifacts in MPEG video. The numerical results have shown that power adaptation could maintain good picture quality as well as transmission power efficiency at the same time on the digital television transmission system. The proposed scheme is also suitable for other DVB system as well as various digital television system standards.
Automated hierarchical classification of scanned documents using convolutional neural network and regular expression Rifiana Arief; Achmad Benny Mutiara; Tubagus Maulana Kusuma; Hustinawaty Hustinawaty
International Journal of Electrical and Computer Engineering (IJECE) Vol 12, No 1: February 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v12i1.pp1018-1029

Abstract

This research proposed automated hierarchical classification of scanned documents with characteristics content that have unstructured text and special patterns (specific and short strings) using convolutional neural network (CNN) and regular expression method (REM). The research data using digital correspondence documents with format PDF images from pusat data teknologi dan informasi (technology and information data center). The document hierarchy covers type of letter, type of manuscript letter, origin of letter and subject of letter. The research method consists of preprocessing, classification, and storage to database. Preprocessing covers extraction using Tesseract optical character recognition (OCR) and formation of word document vector with Word2Vec. Hierarchical classification uses CNN to classify 5 types of letters and regular expression to classify 4 types of manuscript letter, 15 origins of letter and 25 subjects of letter. The classified documents are stored in the Hive database in Hadoop big data architecture. The amount of data used is 5200 documents, consisting of 4000 for training, 1000 for testing and 200 for classification prediction documents. The trial result of 200 new documents is 188 documents correctly classified and 12 documents incorrectly classified. The accuracy of automated hierarchical classification is 94%. Next, the search of classified scanned documents based on content can be developed.
The Design and Performance Analysis of DTMB System Emy Haryatmi; Tubagus Maulana Kusuma; Busono Soerowirdjo; Purnawarman Musa
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 3: September 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v14i3.3830

Abstract

Various standard in digital television broadcasting system has been developed in the world, one of which is the Digital Terrestrial Multimedia Broadcasting, or abbreviated as DTMB that currently used by China and Hong Kong. DTMB has several standard configurations and parameters. In this research, DTMB system was designed and the results was validated through simulation using computer program, named Simulink. The parameters used in this research is the FEC with code rate of 0.4, 4QAM modulation, interleaver mode 1 and using a single carrier transmission mode. Stream format used in the simulation was MPEG2-TS as the input for DTMB system. Parameters selection was based on low implementation complexity, but with good results. Two important things in DTMB system is the existence of FEC and TDS-OFDM. FEC consists of cascaded BCH as the outer encoder/decoder (codec) and LDPC as the inner codec. The reason of using TDS-OFDM because it provides better picture quality when the receiver is in motion. The test results have shown that for static video, DTMB was able to receive video with identical quality compared to the original video, when the value of SNR=11dB and SNR=12dB for dynamic video. It is shown that after going through the process from LDPC to BCH, the number of bit errors decreased while the value of SNR increased.
Indonesian Music Classification on Folk and Dangdut Genre Based on Rolloff Spectral Feature Using Support Vector Machine (SVM) Algorithm Brizky Ramadhani Ismanto; Tubagus Maulana Kusuma; Dina Anggraini
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 15, No 1 (2021): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.54646

Abstract

Music Genre Classification is one of the interesting digital music processing topics. Genre is a category of artistry, in this case, especially music, to characterize and categorize music is now available in various forms and sources. One of the applications is in determining the music genre classification on folk songs and dangdut songs.The main problem in the classification music genre is to find a combination of features and classifiers that can provide the best result in classifying music files into music genres. So we need to develop methods and algorithms that can classify genres appropriately. This problem can be solved by using the Support Vector Machine (SVM). The genre classification process begins by selecting the song file that will be classified by the genre, then the preprocessing process, the collection features by utilizing feature extraction, and the last process is Support Vector Machine (SVM) classification process to produce genre types from selected song files. The final result of this research is to classify Indonesian folk music genre and dangdut music genre along with the 83.3% accuracy values that indicate the level of system relevance to the results of music genre classification and to provide genre labels on music files as to facilitate the management and search of music files.
Fingerprint Authenticity Classification Algorithm based-on Distance of Minutiae using Convolutional Neural Network Hariyanto Hariyanto; Sarifuddin Madenda; Sunny Arief Sudiro; Tubagus Maulana Kusuma
InComTech : Jurnal Telekomunikasi dan Komputer Vol 11, No 3 (2021)
Publisher : Department of Electrical Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/incomtech.v11i3.13770

Abstract

Fingerprint identification systems are vulnerable to attempted authentication fraud by creating fake fingerprints that mimic the live. This paper proposes method to detect whether a fingerprint is live fingerprint or fake fingerprint using Convolutional Neural Network (CNN). We construct a features database of distances among minutiaes of fingerprints, where the distance calculation is based-on Euclidean Distance. Furthermore, the distance features database that has been constructed is classified using the CNN. CNN is a deep learning method designed for machine learning processes so that computers recognize objects in an image and this method has capability classifying an object. The numerical results have shown that the best accuracy achieves 99.38% when the learning rate is 0.001 with the epoch of 100.
Co-Authors Achmad Benny Mutiara Brizky Ramadhani Ismanto Busono Soerowirdjo DHATU PARAGYA Dina Anggraini Emy Haryatmi Hans-Jurgen Zepernick Hariyanto Hariyanto Hustinawaty Hustinawaty, Hustinawaty Khairunnisa Fadhilla Ramdhania Muhammad Guruh Ajinugroho Musa, Purnawarman Paulus Sakti Laksono Permadi, Yogi Prayogo, Sandy Suryo Rakhmi Khalida Randy Rahmanto Rifiana Arief Sandy Suryo Prayogo Sarifuddin Madenda Sunny Arief Sudiro Suryarini Widodo YOGI PERMADI