Articles
Evaluasi Performa Support Vector Machine Classifier Terhadap Penyakit Mental
Furqan, Mhd;
Kurniawan, Rakhmat;
HP, Kiki Iranda
JSINBIS (Jurnal Sistem Informasi Bisnis) Vol 10, No 2 (2020): Volume 10 Nomor 2 Tahun 2020
Publisher : Universitas Diponegoro
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.21456/vol10iss2pp203-210
Expression of genes found in the brains of autism, bipolar, and schizophrenia patients identified as overlapping. The overlap is a state in which the values of genes are similar. This paper aims to determine the best performance of support vector machines algorithm in classifying autism, bipolar, and schizophrenia based on the expression of genes using genome-wide association studies data. Using three support vector machine kernels, this study evaluates the performance of gaussian, laplacian, and sigmoid for genome-wide association studies datasets. The datasets were obtained from Psychiatric Genomics Consortium publications, where 660 data were taken with each disorder consisting of 220 data. This study proposes an optimal kernel for one-against-one and one-against-all multiclass support vector machine, and the performance is evaluated using accuracy. The study results show that the Gaussian kernel has the best accuracy performance compared to other support vector machines kernels in classifying genome-wide association studies data of autism, bipolar, and schizophrenia as early diagnosis.
Diagnosis of Victims of Bullying Behaviour Using Bayes Method
Hasugian, Abdul Halim;
Furqan, Mhd.;
Khairunnisa, K
IJISTECH (International Journal of Information System & Technology) Vol 3, No 2 (2020): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (889.527 KB)
|
DOI: 10.30645/ijistech.v3i2.61
Victims of bullying behavior in the first high school students are still going on and unresolved. Victims of bullying behavior that is not easily visible to the naked eye and the lack of knowledge about bullying are problems in resolving the problem. This research is to create an expert system that can diagnose victims of bullying behavior based on the symptoms suffered by the victims of bullying to address the problems faced during this time. The Bayes method describes the relationship between the probability of A with event B has occurred. The probability of event B on the condition of event A has occurred. The occurrence of an event based on the influence gained from the observation result, Like bullying symptoms that occur in victims of bullying behavior, the Bayes method will calculate the probability and generated types of bullying experienced by students based on the knowledge that is in the can of an expert and made into an application.
Augmented Reality Using Brute Force Algorithm for Introduction to Prayer Movement Based
Furqan, Mhd;
Ikhsan, Muhammad;
Nasution, Irma Yunita
Scientific Journal of Informatics Vol 8, No 2 (2021): November 2021
Publisher : Universitas Negeri Semarang
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.15294/sji.v8i2.29472
Proposed: Prayer is compulsory to worship for Muslims around the world. Prayer is a mandatory commandment from Allah SWT. However, the companions and the Madzhab of Islam have a different opinion but remain Saheeh as long as it does not stray away from the teachings of the Prophet and Al-Quran. This prayer movement consists of the prayer movement of the Madzhab, Imam Shafi'i, Imam Hanafi, Imam Hambali, and Imam Maliki. The Marker used 9 pieces with pictures of each movement. One marker has several shapes of the movements that are several object targets are listed in it. Methods: The Brute Force algorithm used is to match the String value. The Brute Force algorithm can recognize well any String value that is matched to the marker and data from the database. This algorithm is applied to Augmented Reality technology. This app is built using Augmented Reality technology that combines real-world and virtual worlds. Results: This technology is well recognized applied from the Brute Force algorithm, which can validate the match result String value between the database and marker. Novelty: This technology uses the camera to find suitable markers in order to display 3D objects if the marker and the database match. So that this built system can facilitate many circles in learning the prayer movements based on the prayer movement version of islamic high priest.
Metode High-Pass Filter Dan Fast Fourier Transform Untuk Perbaikan Citra Telapak Tangan
Mhd Furqan;
- Sriani;
Muhammad Akbar Ramadhan Tanjung
Techno.Com Vol 20, No 4 (2021): November 2021
Publisher : LPPM Universitas Dian Nuswantoro
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33633/tc.v20i4.5262
Telapak tangan sering digunakan sebagai sumber penelitian dibidang sistem biometrik karena mempunyai karakteristik seperti sidik jari. Selain itu, telapak tangan juga mudah didapatkan dan dapat diperoleh dari citra yang memiliki resolusi rendah. Namun, selain itu juga sebuah citra telapak tangan akan dapat mengalami penurunan terhadap kualitasnya. Untuk itu dilakukanlah sebuah tahap yang dikenal dengan perbaikan kualitas citra, dimana bidang ini merupakan tahap awal dari pengolahan citra digital. Dalam penelitian ini penggunaan metode dalam perbaikan citra difokuskan untuk menajamkan citra telapak tangan dengan menggunakan high pass filter dan filter fast fourier transform, dimana sebelumnya citra tersebut telah diolah dengan menggunakan histogram ekualisasi untuk meningkatkan kontras citra telapak tangan. Setelah dilakukan pengujian terhadap 30 sampel citra. Dengan menilai error pada MSE (Mean Square Error) dan PSNR (Peak Signal to Noise Ratio) dari citra hasil rekonstruksi, hasil pengujian menunjukkan bahwa penggunaan high pass filter dengan koefisien=1 menghasilkan citra yang lebih baik dimana nilai rata-rata MSE=7,064544(dB) dan PSNR=40,01314(dB) daripada menggunakan high-pass filter dengan koefisien=0. Sedangkan pada fast fourier transform dengan menggunakan Ideal High-Pass Filter (IHPF) mampu menghasilkan citra rekonstruksi yang lebih baik dengan rerata MSE=9,354056(dB) dan PSNR=38,537046(dB) dari pada menggunakan butterworth high-pass filter (BHPF) dan gaussian high-pass filter (GHPF)
Analisis Sentimen Menggunakan K-Nearest Neighbor Terhadap New Normal Masa Covid-19 Di Indonesia
Mhd Furqan;
Sriani Sriani;
Susan Mayang Sari
Techno.Com Vol 21, No 1 (2022): Februari 2022
Publisher : LPPM Universitas Dian Nuswantoro
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33633/tc.v21i1.5446
New normal diterapkan oleh pemerintah untuk mengembalikan masyarakat beraktivitas normal ditengah pandemi covid-19 dengan protokol kesehatan. Penerapan new normal menuai beragam komentar dari masyarakat dan masuk kedalam topik terpopuler di media sosial twitter. Analisis sentimen untuk memprediksi komentar ataupun opini masyarakat yang kecenderungan beropini positif maupun negatif. Preprocessing data menggunakan cleaning, case folding, normalisasi, stemming, filtering, dan tokenizing. Pada normalisasi kata bertujuan memperbaiki kesalahan penulisan kata (typo) berdasarkan KBBI dan TF-IDF sebagai metode pembobotan kata. Data yang digunakan terdiri dari 1000 tweet. Metode klasifikasi opini menggunakan metode K-Nearest Neighbor dan melakukan pengujian agar mendapatkan hasil akurasi yang paling terbaik serta mengevaluasi menggunakan confusion matrix. Hasil dari pelabelan untuk sentimen positif berjumlah 811 dan 189 untuk sentimen negatif. Klasifikasi K-NN dengan nilai k = 1 menghasilkan pengujian use training set dengan accuracy sebesar 100%, 92,60% untuk 10-fold cross-validation dan 94,50% untuk 80% percentage split.
Diagnosis of Victims of Bullying Behaviour Using Bayes Method
Abdul Halim Hasugian;
Mhd. Furqan;
K Khairunnisa
IJISTECH (International Journal of Information System and Technology) Vol 3, No 2 (2020): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v3i2.61
Victims of bullying behavior in the first high school students are still going on and unresolved. Victims of bullying behavior that is not easily visible to the naked eye and the lack of knowledge about bullying are problems in resolving the problem. This research is to create an expert system that can diagnose victims of bullying behavior based on the symptoms suffered by the victims of bullying to address the problems faced during this time. The Bayes method describes the relationship between the probability of A with event B has occurred. The probability of event B on the condition of event A has occurred. The occurrence of an event based on the influence gained from the observation result, Like bullying symptoms that occur in victims of bullying behavior, the Bayes method will calculate the probability and generated types of bullying experienced by students based on the knowledge that is in the can of an expert and made into an application.
Application of the Steepest Ascent Hill Climbing (SAHC) Algorithm for Mobile-based Shortest Route Search
Mhd Furqan;
A Armansyah;
Razzaq H. Nur Wijaya
IJISTECH (International Journal of Information System and Technology) Vol 4, No 1 (2020): November
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v4i1.88
This study aims at early to determine the application of algorithms Steepest Ascent Hill Climbing (SAHC) for finding the shortest route-based Mobile in Humbang Hasundutan. Based on the results of the application of algorithms Steepest Ascent Hill Climbing (Sahc) To search based Shortest These Mobile in Humbang Hasundutan. So it can be concluded that the search for the shortest route based on Mobile can be solved using the Steepest Ascent Hill Climbing algorithm. In the manual calculation process using the Steepest Ascent Hill Climbing algorithm at the node from Humbang, there is a heuristic value of 0.0896184808, at the node from which the three intersections are originated there is a heuristic value of 0.1693780561, at the node from which there is a heuristic value of 0.367474152, at the node from which the waterfall falls sibabo has a heuristic value of 0.3823982675. Then the result of the shortest route from Sipinsur Geosite (F) to Simolap Waterfall (B) is F èD èB (Sipinsur GeoSite - intersection 4 - Simolap Waterfall) the total distance is 51 km and the time is 1 hour 34 minutes. So that the test results of the Steepest Ascent Hill Climbing algorithm process with the system in accordance with the manual calculation process of the Steepest Ascent Hill Climbing algorithm.
Classification of Tomato Leaf Based on Gabor Filter Extraction And Support Vector Machine Algorithm
Mhd. Furqan;
A Armansyah;
Lely Sahrani
IJISTECH (International Journal of Information System and Technology) Vol 4, No 2 (2021): May
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30645/ijistech.v4i2.173
Tomato production in Indonesia is reduced because tomato leaves are stricken with disease. The main disease that often attacks tomato leaves is rotten leaves and bacterial patches or commonly called dry patches. Identification of tomato leaf disease is still done manually with human vision. The shortcomings of the method manually required a technology that is able to extract the texture of tomato leaf disease. One of them is by the process of extracting the texture of leaves with gabor filters, namely by using frequency and orientation parameters. Based on the results of the experiment obtained that the input parameter gabor filter with orientation of 90o with a combination of frequency 4 produces a fairly clear contrast. The process of extracting the texture of the leaf aims to get the magnitude value of the tomato leaf that will be used as inputs for the classification process. The svm algorithm grouped data that had the same characteristics into one class. Training data used 42 images and test data used 30 images, with the success rate of 83.33%.
Aplikasi Mobile Media Pembelajaran Dasar Algoritma dan Pemrograman Berbasis Android
Yusuf Ramadhan Nasution;
Mhd Furqan
Syntax : Journal of Software Engineering, Computer Science and Information Technology Vol 1, No 1 (2020): Juni 2020
Publisher : Universitas Dharmawangsa
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.46576/syntax.v1i1.791
This research is a type of development research. The product development model adopts a software development model consisting of (1) Analysis of software requirements, (2) design, (3) writing code and (4) testing. Data collection techniques are done by observation, interviews and questionnaires. The testing phase is carried out with product validation by experts, testing on the first user (lecturer) and testing on the end user (student).Keywords : Learning Media, Mobile Applications, Algorithms and Programming.
APPLICATION OF SPEED UP ROBUST FEATURES (SURF) AND FEATURES FROM ACCELERATED SEGMENT TEST (FAST) FOR INTRODUCTION OF PLACE
Mhd. Furqan;
Rakhmat Kurniawan;
Mey Hendra Putra Sirait
INFOKUM Vol. 9 No. 1,Desember (2020): Data Mining, Image Processing,artificial intelligence, networking
Publisher : Sean Institute
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (802.08 KB)
With the current technology that is starting to develop rapidly, it can match an image with another image. In recognizing an image, there needs to be a process that will be carried out in image matching, but current image matching is still comparing pixels between two images. To compare between images, the color and resolution and shape of the image pixels affect the recognition results in an image. Therefore, to deal with this problem, the algorithms that can be used in the work process of this program are the Speed Up Robust Features (SURF) algorithm and Features from Accelerated Segment Test (FAST). FAST is a method for determining the angle that is in an image while the SURF algorithm can describe the features that exist in an image so that image matching no longer matches between pixels but based on the descriptors that have been generated and the matched results will be listed on the database, using the SURF algorithm , there is no need to worry about the resolution, color, and shape of the image to be matched. Tests that were carried out were still successful with a precision value of 0.9, which means that the value of successful matching is 9% and with a recall value of 100% and a value that has reached 100% means that the number of points is similar to the number of points that have been matched