Fadlisyah Fadlisyah
Universitas Malikussaleh

Published : 16 Documents
Articles

Found 16 Documents
Search

COMPARISON OF SIMPLE ALGORITHM DATA (SORTING) CONTROL METHODS ON SELECTION AND BUBBLE SORT Bustami, Bustami; Fadlisyah, Fadlisyah; Alfyansyah, Gusti
TECHSI - Jurnal Teknik Informatika Vol 11, No 2 (2019)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v11i2.1601

Abstract

In the data there is a sorting process which is sorting data with certain rules, so that it will be arranged in the algorithm. Algorithms are steps that will solve a problem in the data, algorithms have a variety of settlement methods, one of which is the sorting method. Data sorting (Sorting) contains different types such as Bubble Sort, Insertion Sort, Merge Sort, Quick Sort, Selection Sort, and Shell Sort. The following will explain how to process the data sequencing of each method using a simple algorithm, especially in the Selection Sort method, and Bubble Sort. Keywords: Algorithm,  Bubble Sort, Selection Sort
IMPLEMENTATION OF LINEAR CONGRUENT METHOD (LCM) ALGORITHM AS A TRAFFICER FOR FAHMIL QUR’AN Alfyansyah, Gusti; Bustami, Bustami; Fadlisyah, Fadlisyah
TECHSI - Jurnal Teknik Informatika Vol 11, No 1 (2019)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/techsi.v11i1.1603

Abstract

Fahmil Qur'an is one of the branches of the Musabaqah Tilawatil Qur'an (MTQ) race. In the Fahmil Quran race, the participants will be given a package of questions - questions that will be tested by the participants' ability to work together when answering questions given by the jury. And the package of questions that are available is printed poorly, allowing the jury to misrepresent the participants. To avoid repetition in giving questions to participants, a system will be built that is able to randomize the questions automatically. Randomizing the question uses a linear congruent method algorithm. In this research there is a system flowchart and manual calculation of the linear congruent method algorithm.
KLASIFIKASI SENJATA API MELALUI SUARA MENGGUNAKAN TRANSFORMASI WAVELET Fadlisyah, Fadlisyah; Syahrial, Syahrial
TECHSI - Jurnal Teknik Informatika Vol 6, No 2 (2014)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (341.376 KB) | DOI: 10.29103/techsi.v6i2.173

Abstract

Classification of guns through sound using Wavelet Transform is a branch of sound processing can be used to identify several types of gunfire. This study uses wavelet transformation for the recognition and classification of firearms training through the noise using Wavelet Transform. The system was then tested by simulating it on the training data and test data to generate the percentage of recognition and classification of the sound of gunfire. Experiments done with several changes in parameter values to obtain the best percentage of recognition and classification. The results of this study in the form of gunfire were classified in accordance with the known brand guns from the calculation of energy using Wavelet Transformation.
PENGENALAN AYAT AL-QURAN SURAH AL-MAIDAH 51-57 MELALUI SUARA MENGGUNAKAN ALGORITMA GOERTZEL Fadlisyah, Fadlisyah; Bustami, Bustami; Rizal, Rizal; Fajriana, Fajriana; Munandar, Aris
TECHSI - Jurnal Teknik Informatika Vol 10, No 1 (2018)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (522.827 KB) | DOI: 10.29103/techsi.v10i1.604

Abstract

Suara merupakan sarana utama komunikasi antara manusia. Pengolahan suara merupakan konsep yang sangat penting untuk semua jenis sistem yang membutuhkan interaksi manusia dalam kegiatan sehari-hari. Pengolahan suara dapat dikategorikan menjadi empat jenis: Isolated Words, Connected Word, Continuos Speech, Spontaneous Speech. Untuk mentransformasikan sinyal suara menjadi sinyal frekuensi suara dalam format WAV diperlukan suatu transformasi yang dapat meminimalkan masalah, yaitu transformasi Algoritma Goertzel dengan bantuan software Borland Delphi 7 dalam mengenali bacaan ayat Al-Qur’an. Hasil penelitian menunjukkan bahwa transformasi Algoritma Goertzel dapat diterapkan atau diimplementasikan dalam pengenalan suara ini dan memiliki true identification yang berbeda. Persentase true identification untuk transformasi Algoritma Goertzel ini yaitu antara 40% sampai 90%. Kata kunci : Pengolahan Suara, Algoritma Goertzel.
PERBANDINGAN UNJUK KERJA TRANSFORMASI WAVELET, MELLIN DAN DISCRETE SINE TRANSFORM (DST) UNTUK PENGENALANAYAT AL-QUR’AN PADA SURAT YASIIN 1- 10 MELALUI SUARA Fadlisyah, Fadlisyah; Muhathir, Muhathir
TECHSI - Jurnal Teknik Informatika Vol 7, No 2 (2015)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (435.91 KB) | DOI: 10.29103/techsi.v7i2.193

Abstract

Suara merupakan sarana utama komunikasi antara manusia. Pengolahan suara merupakan konsep yang sangat penting untuk semua jenis sistem yang membutuhkan interaksi manusia dalam kegiatan sehari-hari. Pengolahan suara dapat dikategorikan menjadi empat jenis: Isolated Words, Connected Words, Continuous Speech, Spontaneous Speech. Untuk mentransformasikan sinyal suara menjadi sinyal frekuensi suara dalam format WAV diperlukan suatu transformasi yang dapat meminimalkan masalah, yaitu transfromasi Wavelet, Mellin, Discrete Sine Transform (DST) dengan bantuan software Borland Delphi 7 dalam mengenali bacaan ayat Al-Quran. Hasil penelitian menunjukkan bahwa penbandingan unjuk kerja transformasi Wavelet, Mellin dan Discrete Sine Transform (DST) masing-masing memiliki true detection yang berbeda. Persentase true detection untuk transformasi Wavelet berkisar antara 25% hingga 85%, transformasi Mellin berkisar dari 30% hingga 92%, sedangkan transformasi Discrete Sine Transform (DST) tingkat true detection berkisar 25% hingga 87%.
SISTEM PENDETEKSIAN WAJAH PADA VIDEO MENGGUNAKAN JARINGAN ADAPTIVE LINEAR NEURON (ADALINE) Fadlisyah, Fadlisyah
TECHSI - Jurnal Teknik Informatika Vol 5, No 1 (2013)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (321.058 KB) | DOI: 10.29103/techsi.v5i1.146

Abstract

Face detection is an important first step to many advanced computer vision, biometrics recognition and multimedia applications, such as face tracking, face recognition, and video surveillance. In this paper, a faster face detection system is proposed using Adaptive Linear Neuron (ADALINE). System is constructed from the enhanced image by applying sobel operator, and then use the resulted image ’s vector to Widrow-Hoff learning’s scheme. The performance of the proposed method is evaluated by two performances parameter, detection rate and false positive rate. The result shows that performance of detection rate is range from 65% to 90%. To enhance the quality of system performance, a combination of either : video complexity test, skin color segmentation, or statistical test, should be apllied to future research.
SISTEM SKETSA GENERATIF PEMODELAN RAMBUT MANUSIA Fachrurrazi, Sayed; Fadlisyah, Fadlisyah
TECHSI - Jurnal Teknik Informatika Vol 4, No 1 (2012)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (632.512 KB) | DOI: 10.29103/techsi.v4i1.105

Abstract

In this paper, we present a generative sketch model for human hair analysis and synthesis. We treat hair images as2D piecewise smooth vector (flow) fields and, thus, our representation is view-based in contrast to the physically-based 3D hair models in graphics. The generative model has three levels. The bottom level is the high-frequency band of the hair image. The middle level is a piecewise smooth vector field for the hair orientation, gradient strength, and growth directions. The top level is an attribute sketch graph for representing the discontinuities in the vector field.Asketch graph typically has a number of sketch curves which are divided into 11 types of directed primitives. Each primitive is a small window (say 5 _ 7 pixels) where the orientations and growth directions are defined in parametric forms, for example, hair boundaries, occluding lines between hair strands, dividing lines on top of the hair, etc. In addition to the three level representation, we model the shading effects, i.e., the low-frequency band of the hair image, by a linear superposition of some Gaussian image bases andwe encode the hair color by a color map. The inference algorithm is divided into two stages: 1) We compute the undirected orientation field and sketch graph from an input image and 2) we compute the hair growth direction for the sketch curves and the orientation field using a Swendsen-Wang cut algorithm. Both steps maximize a joint Bayesian posterior probability. The generative model provides a straightforward way for synthesizing realistic hair images and stylistic drawings (rendering) from a sketch graph and a few Gaussian bases. The latter can be either inferred from a real hair image or input(edited) manually using a simple sketching interface. We test our algorithm on a large data set of hair images with diverse hair styles.
MULTIMODAL FACIAL GENDER DAN IDENTIFIKASI ETNIK Jalaluddin, Jalaluddin; Fadlisyah, Fadlisyah
TECHSI - Jurnal Teknik Informatika Vol 4, No 1 (2012)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (547.24 KB) | DOI: 10.29103/techsi.v4i1.106

Abstract

Human faces provide demographic information, such as gender and ethnicity. Different modalities of human faces, e.g., range and intensity, provide different cues for gender and ethnicity identifications. In this paper we exploit the range information of human faces for ethnicity identification using a support vector machine. An integration scheme is also proposed for ethnicity and gender identifications by combining the registered range and intensity images. The experiments are conducted on a database containing 1240 facial scans of 376 subjects. It is demonstrated that the range modality provides competitive discriminative power on ethnicity and gender identifications to the intensity modality. For both gender and ethnicity identifications, the proposed integration scheme outperforms each individual modality.
MODEL GENERATIF WAJAH BERPOTENSI “FITNAH” MENGGUNAKAN JARINGAN SYARAF TIRUAN ADALINE Fadlisyah, Fadlisyah; Bustami, Bustami
TECHSI - Jurnal Teknik Informatika Vol 8, No 1 (2016)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (199.077 KB) | DOI: 10.29103/techsi.v8i1.120

Abstract

Wajah merupakan perwakilan informasi dari sifat atau karakter seseorang, dan satu-satunya fitur yang dapat secara langsung digunakan untuk menilai seseorang berdasarkan database statistik wajah. Salah satu informasi yang dapat digali dari wajah adalah potensi seseorang dalam melakukan prilaku fitnah, untuk itu paper ini bertujuan mengajukan sebuah model generatif pemodelan wajah eigen yang dibangun dari berbagai wajah yang berpotensi melakukan fitnah. Perangkat komputasi yang sesuai digunakan pada lingkungan waktu-nyata adalah jaringan ADALINE, dan hasil unjuk kerja sistem mampu menggenaratif dan mengenali wajah berpotensi fitnah hingga mencapai 90%. Penelitian disarankan tidak terbatas hanya penggunaan komputasi yang terbatas pada wajah, tetapi juga menekankan interaksi wajah terhadap background wajah ataupun interaksi wajah terhadap cahaya. 
KUALITAS UNJUK KERJA PENDETEKSIAN CITRA IRIS DENGAN WAVELET 2D Fadlisyah, Fadlisyah
TECHSI - Jurnal Teknik Informatika Vol 7, No 1 (2015)
Publisher : Teknik Informatika Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (325.861 KB) | DOI: 10.29103/techsi.v7i1.176

Abstract

The performance of an iris recognition system can be undermined by poor quality images and result in high false reject rates (FRR) and failure to enroll (FTE) rates. In this paper, a wavelet-based quality measure for iris images is proposed. The merit of the this approach lies in its ability to deliver good spatial adaptivity and determine local quality measures for different regions of an iris image. Our experiments demonstrate that the proposed quality index can reliably predict the matching performance of an iris recognition system. By incorporating local quality measures in the matching algorithm, we also observe a relative matching performance improvement of about 20% and 10% at the equal error rate (EER), respectively, on the CASIA and WVU iris databases.