Claim Missing Document
Check
Articles

Found 39 Documents
Search

LOCAL THRESHOLDING BERDASARKAN BENTUK UNTUK BINERISASI CITRA DOKUMEN Fanani, Aris; Prima, Putra; Hidayat, M. Mahaputra
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 10, No 1, Januari 2012
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (508.65 KB) | DOI: 10.12962/j24068535.v10i1.a27

Abstract

Pada binerisasi dokumen, variasi intensitas lokal sering muncul dan merupakan akibat dari berbagai faktor seperti pencahayaan yang tidak merata, noise, dan tekstur dari kertas. Salah satu cara untuk mengatasi permasalahan tersebut adalah dengan metode local thresholding berdasarkan informasi bentuk. Akan tetapi proses komputasi yang lama diperlukan pada metode local thresholding citra dokumen yang memanfaatkan informasi bentuk. Hal ini disebabkan, setiap local window akan ditentukan nilai threshold -nya berdasarkan informasi bentuk. Paper ini mengusulkan penggabungan metode global thresholding dan lo cal thresholding berdasarkan bentuk. Sehingga didapatkan kualitas thresholding yang lebih baik dengan proses komputasi yang lebih cepat. Pada local window yang memiliki intensitas rendah akan dilakukan proses thresholding secara global, sedangkan local window yang memiliki intensitas tinggi dilakukan local thresholding berdasarkan bentuk. Dari hasil uji coba didapatkan kualitas thresholding yang lebih baik dengan proses komputasi yang lebih cepat. Rata-rata keakuratan thresholding yang dicapai adalah 96,42%.
DETEKSI JARAK PANDANG AMAN SEBAGAI ACUAN UNTUK KESELAMATAN PENERBANGAN DENGAN MENGGUNAKAN METODE BACKPROPAGATION Hakim, Moch Rizki Kurniawan; Fanani, Aris
Jurnal RESISTOR (Rekayasa Sistem Komputer) Vol 1 No 2 (2018): Jurnal RESISTOR Edisi Oktober 2018
Publisher : LPPM STMIK STIKOM Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (613.145 KB) | DOI: 10.31598/jurnalresistor.v1i2.304

Abstract

Delay is a term used when the flight schedule late while depart or arrive. Delay causes due to bad weather, technical problems on the plane, uncompleted crew, and others. Delay is procedure to avoid unexpected condition for example is accidents. Bad weather is the the one of delay reason difficult to estimated or detected because relativity variable of each hour. Bad weather can be detected by the air visibility. According to the official standart of transportation the minimum distance of visibility is 5 kilometers. While distance less than for flight safety, can be categorized as danger. Therefore, the porpose of this research is to know early when the flight has to be delayed or not. Therefore to detect a weather condition can be use backpropagation method which can be identified through several factors such as wind speed, humidity, and temperature in the air. Based on this research using 720 data, obtained a high accuracy of 95.71%, recall of 97.81%, and precision of 94.98%. With learning rate of 0.1 and hidden layer as much as 100, which shows that the detection of visibility has a very good performance. Therefore the model can be used for the detection of the visibility of the safe.
Analisa Pengaruh Variasi Penambahan Massa Nilon pada Preparasi Membran Nilon Terhadap Karakteristik Fisik Membran Fanani, Aris; Nugroho, Wahyunanto Agung; Hendrawan, Yusuf
Jurnal Keteknikan Pertanian Tropis dan Biosistem Vol 2, No 3 (2014)
Publisher : Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (288.58 KB)

Abstract

Teknologi filtrasi membran merupakan salah satu teknologi filtrasi yang menggunakan media penyaring dari membran. Seiring perkembangan zaman, telah disintesis membran yang berbahan nilon. Nilon bersifat semikristalin, kuat dan tahan terhadap suhu tinggi. Dalam penelitian ini, tujuan utamanya adalah mengetahui karakteristik fisik membran membran nilon. Dalam penelitian ini metode yang dipakai adalah metode inversi fasa. Perlakuan yang digunakan dalam penelitian ini adalah perbedaan massa nilon pada sintesis membran nilon yaitu 10 g, 15 g, 20 g,25 g, dan 30 g. Sedangkan parameter yang akan diamati adalah sifat fisik yang meliputi kuat tekan, kuat tarik, dan ukuran pori dari membran yang dihasilkan. Hasil penelitian menunjukkan bahwa semakin banyak penambahan massa nilon  (semakin tinggi konsentrasi larutan nilon-HCl), maka kuat tekan dan kuat tarik membran yang didapatkan semakin besar. Nilai kuat tekan terbesar yang dihasilkan pada penelitian ini terjadi pada massa nilon 30 gram dengan konsentrasi 60% (b/v) yaitu 3.83 Kg/cm2 dan nilai kuat tekan terkecil pada penelitian ini terjadi pada massa nilon 10 gram dengan konsentrasi 20% (b/v)  yaitu 0.73 Kg/cm2. Nilai kuat tarik terbesar yang dihasilkan dari pengujian ini terjadi pada massa nilon 30 gram dengan konsentrasi 60% (b/v)  yaitu 9.22 Kg/cm2 dan nilai kuat tarik terkecil pada pengujian ini terjadi pada massa nilon 10 gram dengan konsentrasi 20% (b/v)  yaitu 2.16 Kg/cm2. Berdasarkan analisa SEM, membran nilon yang dihasilkan termasuk dalam golongan membran mikrofiltrasi. . Kata Kunci : inversi fasa,  kuat tekan, kuat tarik
Implementasi Kriptografi pada Teks Menggunakan Metode Block Chiper Mif'atul Mahmudah; Aris Fanani; Moh Hafiyusholeh
Prosiding SI MaNIs (Seminar Nasional Integrasi Matematika dan Nilai-Nilai Islami) Vol 2 No 1 (2018): Prosiding SI MaNIs (Seminar Nasional Integrasi Matematika dan Nilai Islami)
Publisher : Mathematics Department

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1063.44 KB)

Abstract

Berkembangnya teknologi dan komunikasi memudahkan kriptanalis untuk melakukan penyadapan, untuk menghindari hal tersebut perlu dilakukan pengamanan terhadap informasi yang dikirim, salah satu ilmu yang digunakan dalam mengamankan data adalah kriptografi dengan metode block chipper, dimana algoritma block chipper yang digunakan dalam penelitian iniadlah algoritma tanam padi dan bajak sawah, algoritma tersebut dipilih karena memiliki kecepatan enkripsi dan dekripsi lebih cepat dibandingkan dengan metode AES (Advanced Encryption Standard). Proses pembangkitan kunci dimulai dengan merubah kunci yang telah ditentukan yaitu “muslimah” kedalam bentuk biner, selanjutnya pemasukan dan pengambilan bit dengan pola bajak sawah. Proses enkripsi dimulai dengan merubah plainteks “mahmudah” kedalam bentuk biner, selanjutnya pemasukan dan pengambilan bit dilakukan dengan pola tanam padi, hasil dari pengambilan plainteks dan pembangkitan kunci kemudian di XoRkan, diproses sampai delapan putaran, sehingga dihasilkan enkripsi“EOTZb”. Proses dekripsi yaitu chipperteks di XoR kan dengan kunci yang telah dibangkitkan. Hasil XoR dimasukan kedalam bit menggunakan pola pengambilan plainteks dan diambil dengan pola pemasukan plainteks, setelah itu hasilnya di XoR kan dengan kunci yang telah dibangkitkan. Proses tersebut diulang sampai delapan kali putaran, menghasilkan dekripsi yaitu “mahmudah”.
Geometric Feature Extraction of Batik Image Using Cardinal Spline Curve Representation Aris Fanani; Anny Yuniarti; Nanik Suciati
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 12, No 2: June 2014
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v12i2.54

Abstract

Batik is an Indonesian national heritage which has been recognized as a world cultural heritage (world heritage). Batik is widely used as clothing material. The advancement of technology allowed the material optimization in clothing design. Geometrical information of batik image is required in a modul for optimizing clothing design with batik as raw material. Geometric feature extraction of batik image is used to help computer to recognize batik's pattern or motif. This research proposes a method for geometric feature extraction of batik image by using cardinal spline curve representation. The method for geometric feature extraction is divided into 2 processes, i.e., feature extraction for Klowongan and feature extraction for Isen-Isen. Klowongan represents pattern of batik image, whereas Isen-Isen is content patterns of Klowongan. Feature extraction of Klowongan is performed by deleting collinear points from object boundaries until the dominant points are obtained. The dominant points are then used as control points. Feature extraction of Isen-Isen is performed by saving coordinate of every connected components which are also used as control points. Geometry feature of batik image is represented as a set of control points of klowongan and isen-isen. Batik image can be reconstructed by drawing cardinal spline curve using a set of control points in the geometric representation. The experiment shows that the reconstructed images is visually similar with the original batik image.
Regression model focused on query for multi documents summarization based on significance of the sentence position Aris Fanani; Yuniar Farida; Putra Prima Arhandi; M. Mahaputra Hidayat; Abdul Muhid; Billy Montolalu
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 6: December 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i6.12494

Abstract

Document summarization is needed to get the information effectively and efficiently. One method used to obtain the document summarization by applying machine learning techniques. This paper proposes the application of regression models to query-focused multi-document summarization based on the significance of the sentence position. The method used is the Support Vector Regression (SVR) which estimates the weight of the sentence on a set of documents to be made as a summary based on sentence feature which has been defined previously. A series of evaluations performed on a data set of DUC 2005. From the test results obtained summary which has an average precision and recall values of 0.0580 and 0.0590 for measurements using ROUGE-2, ROUGE 0.0997 and 0.1019 for measurements using the proposed regression-SU4. Model can perform measurements of the significance of the position of the sentence in the document well.
WATERMARKING CITRA DIGITAL MENGGUNAKAN METODE DISCRETE COSINE TRANSFORM Aris Fanani; Nurissaidah Ulinnuha
Jurnal Matematika MANTIK Vol. 1 No. 2 (2016): Mathematics and Applied Mathematics
Publisher : Mathematics Department, Faculty of Science and Technology, UIN Sunan Ampel Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (441.653 KB)

Abstract

Pada paper ini, mengusulkan penyisipan watermark pada citra grayscale dan RGB dengan cara modulating relative size pada blok koefisien DCT. Watermark disisipkan pada blok-blok frekuensi menengah. Modulating relative size pada blok koefisien DCT diterapkan dengan menambahkan atau mengurangi blok-blok koefisien DCT. Dari uji coba yang dilakukan metode yang diusulkan menghasilkan watermark yang tahan terhadap berbagai serangan, serta kualitas yang baik dari citra yang disisipi watermark
APLIKASI GRAPH COLORING PADA PENJADWALAN PERKULIAHAN DI FAKULTAS SAINS DAN TEKNOLOGI UIN SUNAN AMPEL SURABAYA Devi Saidatuz Zaenab; Deasy Alfiah Adyanti; Aris Fanani; Nurissaidah Ulinnuha
Jurnal Matematika MANTIK Vol. 2 No. 1 (2016): Mathematics and Applied Mathematics
Publisher : Mathematics Department, Faculty of Science and Technology, UIN Sunan Ampel Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (379.359 KB)

Abstract

In the academic environment there are various problems, one of problem is scheduling of courses at the university level. These problems are affected by the allocation of time (Conformity of SKS with each course), the availability of classrooms, and many study program. In the study preparation lecture schedules in this time, the parameters used, among others: second semester students in each Study Program, Number of Study Program, availability of classrooms, Lectures, number of credits a day of each study program at the Faculty of Science and Technology. This research is aimed as an alternative in formulating scheduling system when the faculty there is an imbalance between the lecture hall, many Study Program, and the number of credits taken each Study Program. Based on the analysis of Graph Coloring and Edge Coloring at case of scheduling Study Program Faculty of Science and Technology State Islamic University Sunan Ampel Surabaya, which has 6 Programs and 5 lecture room with three simulated combinations of input data, obtained scheduling unchanged (consistent) and results scheduling does not overlap / collision, both in the lecture room, and the time of the lecture.
Prediction of Sea Surface Current Velocity and Direction Using LSTM Irkhana Indaka Zulfa; Dian Candra Rini Novitasari; Fajar Setiawan; Aris Fanani; Moh. Hafiyusholeh
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 11, No 1 (2021): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.63669

Abstract

 Labuan Bajo is considered to have an important role as a transportation route for traders and tourists. Therefore, it is necessary to have a further understanding of the condition of the waters in Labuan Bajo, one of them is sea currents. The purpose of this research is to predict sea surface flow velocity and direction using LSTM. There are many prediction methods, one of them is Long short-term memory (LSTM). The fundamental of LSTM is to process information from the previous memory by going through three gates, that is forget gate, input gate, and output gate so the output will be the input in the next process. Based on trials with several parameters namely Hidden Layer, Learning Rate, Batch Size, and Learning rate drop period, it achieved the smallest MAPE values of U and V components of 14.15% and 8.43% with 50 hidden layers, 32 Batch size and 150 Learn rate drop.  
Predicting Velocity and Direction of Ocean Surface Currents using Elman Recurrent Neural Network Method Eka Alifia Kusnanti; Dian C. Rini Novitasari; Fajar Setiawan; Aris Fanani; Mohammad Hafiyusholeh; Ghaluh Indah Permata Sari
Journal of Information Systems Engineering and Business Intelligence Vol. 8 No. 1 (2022): April
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.8.1.21-30

Abstract

Background: Ocean surface currents need to be monitored to minimize accidents at ship crossings. One way to predict ocean currents—and estimate the danger level of the sea—is by finding out the currents’ velocity and their future direction. Objective: This study aims to predict the velocity and direction of ocean surface currents. Methods: This research uses the Elman recurrent neural network (ERNN). This study used 3,750 long-term data and 72 short-term data. Results: The evaluation with Mean Absolute Percentage Error (MAPE) achieved the best results in short-term predictions. The best MAPE of the U currents (east to west) was 14.0279% with five inputs; the first and second hidden layers were 50 and 100, and the learning rate was 0.3. While the best MAPE of the V currents (north to south) was 3.1253% with five inputs, the first and second hidden layers were 20 and 50, and the learning rate was 0.1. The ocean surface currents’ prediction indicates that the current state is from east to south with a magnitude of around 169,5773°-175,7127° resulting in a MAPE of 0.0668%. Conclusion: ERNN is more effective than single exponential smoothing and RBFNN in ocean current prediction studies because it produces a smaller error value. In addition, the ERNN method is good for short-term ocean surface currents but is not optimal for long-term current predictions. Keywords: MAPE, ERNN, ocean currents, ocean currents’ velocity, ocean currents’ directions
Co-Authors Abdul Muhid Abdulloh Hamid Abdulloh Hamid Achmad Aditya Rochim Ahmad Hanif Asyhar Ahmad Zaenal Arifin Alfirdausy, Roudlotul Jannah Aliyyah, Izzatul Anang Kunaefi Anny Yuniarti Arifin, Ahmad Zaenal Belly Ubaidila Billy Montolalu Chalawatul Ais Deasy Alfiah Adyanti Devi Saidatuz Zaenab Diah Ayu Sulistiani Dian C. Rini Novitasari Dian C. Rini Novitasari Dian Puspita Sari Dian Yuliati Dwi Agustina Dwi Mutiara Jelita Dzaky, Ahmad Naufal Eka Alifia Kusnanti Emi Fatchurin Fajar Setiawan Fajar Setiawan Fatmah Fatmah Fatmah Fatmah Fauzan Setyarizqi Muharram Ganeshar B.D. Prasanda Ghaluh Indah Permata Sari Hakim, Moch Rizki Kurniawan Hani Khaulasari Hapsari, Nabilla Windy Himami, Fatikul Ika Mustika Iksan Inayah, Jauharotul Irkhana Indaka Zulfa Karin Wahyu Cahyaningrum laili, ummiy Fauziah Laili, Ummiy Fauziyah Latifatun Nadya Desinaini Lia Puspita Sari Lubab, Ahmad LULUK WULANDARI M Mahaputra Hidayat M. Imron Maghfiroh, Wardatul Maulana, Achmad Resnu Micha Annata Shinami Mif'atul Mahmudah Moch Rizki Kurniawan Hakim Moh. Hafiyusholeh Moh. Syaeful Bahar Mohammad Nasir Mohammad Nasir Mohammad Nasir Montolalu, Billy Nabiela Naily Nanik Suciati Nur Aulia, Shofinatul Wahdah Nurissaidah Ulinnuha Prasetijo, Dono Purwanti, Ida Putra Prima Putra Prima Putra Prima Arhandi, Putra Prima Putroue Keumala Intan Sari, Dian Candra Rini Novita Sari, Yana Vita Silvia Kartika Sari Siti Nurlela Sufriyah, Lailiyatus Susilo Ari Wardani Susilo Ari Wardani Tarisa Amalia Dwi Arisanti Ummiy Fauziah Laili Ummiy Fauziyah Laili Ummiy Fauziyah Laili Wahyunanto Agung Nugroho Wanda N.P. Sunaryo Wardani, Susilo Ari Wika Dianita Utami Wika Dianita Utami Wika Dianita Utami Yana Vita Sari Yuliati, Dian Yuniar Farida Yusuf Hendrawan Zaen, Nanida Jenahara Zainullah Zuhri Zumrotul Muallifah