Jurnal Teknologi Informasi Cyberku
Jurnal Teknologi Informasi - Jurnal CyberKU is an open access journal, published by Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro. The journal is intended to be dedicated to the development of Information Technology related to Intelligent System, and Business Intelligence. Topics of interest include, but are not limited to: Artificial Intelligence, Machine Learning, Data Mining, Image Processing, Computer Vision, Text Processing, Signal Processing, Speech Recognition, Software Engineering, Decision Support System, IT Governance, eBusiness, Game Technology, Multimedia, eLearning, Computational Education, Computational Engineering, Mobile Computing, Internet of Things.
Articles
67 Documents
<![CDATA[KLASIFIKASI STATUS KESEJAHTERAAN RUMAH TANGGA KELUARGA BINAAN SOSIAL MENGGUNAKAN ALGORITMA NAIVE BAYES BERBASIS SELEKSI ATRIBUT CHI SQUARED ]]>
<![CDATA[Erfan Karyadiputra]]>;
<![CDATA[Edi Noersasongko]]>;
<![CDATA[Aris Marjuni]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (99.635 KB)
<![CDATA[Kemiskinan merupakan salah satu permasalahan yang sering dihadapi dalam upaya peningkatan kesejahteraan di hampir semua negara. Tersedianya data kemiskinan yang akurat dan berkesinambungan merupakan salah satu instrumen penting untuk mengevaluasi kebijakan pemerintah dalam mengentaskankemiskinan dengan memfokuskan perhatian pada pendistribusian bantuan sesuai rumah tangga sasaran (RTS). Penelitian terkait klasifikasi kesejahteraan rumah tangga sering menggunakan variabel target/kelas berupa kategori miskin dan tidak miskin. Kategori tersebut jika dilihat dari aspek pendistribusian bantuan masih bersifat umum, hal tersebut karena kategori rumah tangga miskin tersebut dapat diklasifikasikan lagi kedalam status kesejahteraan rumah tangga sesuai rumah tangga sasaran (RTS) sehingga dalam pendistribusian bantuan dapat disesuaikan dengan status kesejahteraan rumah tangga sasaran (RTS). Oleh sebab itu diperlukan variabel target/kelas baru yang sesuai RTS Keluarga Binaan Sosial yaitu sangat miskin dan miskin.Dalam penelitian ini akan dilakukan pengujian menggunakan algoritma Naive Bayes berbasis seleksi atribut Chi Squared untuk mengklasifikasi status kesejahteraan rumah tangga miskin yaitu rumah tangga sangat miskin (RTSM) dan rumah tangga miskin (RTM). Hasil pengujian yang didapatkan adalah algoritma Naive Bayes menghasilkan akurasi sebesar 85.80% dan nilai AUC sebesar 0.930. kemudian Naive Bayes setelah menerapkan seleksi atribut menggunakan Chi Squared dengan nilai k sebanyak 13 atribut dapat meningkatkan akurasi menjadi 86.78% dan nilai AUC sebesar 0.944.]]>
<![CDATA[KLASIFIKASI NAMA OBAT TULISAN TANGAN DOKTER DENGAN METODE GLCM DAN BACKPROPAGATION NEURAL NETWORK ]]>
<![CDATA[Arrahman Arrahman]]>;
<![CDATA[Purwanto Purwanto]]>;
<![CDATA[Pulung Nurtantio]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (449.801 KB)
<![CDATA[Pharmaceutical personnel in the work in general is always associated with the reading prescription, where the required accuracy, speed, and accuracy in reading prescription to avoid medication errors. This research show how to classify the doctor's handwriting drug name. Research conducted by the image processing prescription taken by scanner. Then the image manually cropped to take 200 drug names. Refining the drug name image has done twice with median filter and wiener filter, then dilation and erosion , feature extraction with GLCM (Grey-Level Co-occurance matrix) methods to obtain data sets that will be classified by the software RapidMiner. From the test we find that Backpropagation Neural Network had more accurate than Naive Bayes and C 4.5.]]>
<![CDATA[PEMISAHAN VOICE DAN UNVOICE MENGGUNAKAN TEKNIK OVERLAPING BLOCK, ZERO CROSSING RATE, DAN SHORT TIME ENERGY DALAM PENGENALAN SUARA ]]>
<![CDATA[Ade Yusupa]]>;
<![CDATA[Abdul Syukur]]>;
<![CDATA[Ricardus Anggi Pramunendar]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (501.69 KB)
<![CDATA[Dalam proses speech recognition, speech syntesis dan speech enhancement, signal suara yang diinputkan tidak dapat langsung dikenali atau diindentifikasi sebagai gelombang signal voice atau unvoice. Proses analisis ucapan dalam menetapkan voice dan unvoice biasanya dilakukan dengan ekstrasi dari speech signal atau signal suara. Dalam penelitian ini, kami melakukan dan membandingkan 3 akurasi metode yakni: penentuan manual dengan software Adobe Audition dibandingkan pada tool matlab dengan metode separation of voice and unvoice using non overlapping block, zero-crossing rate and energy of a speech signal, dan juga membandingkan dengan metode peneliti yaitu penggabungan teknik overlapping blocks, zero crossing rate dan short time energy dalam menentukan voice dan unvoice untuk memisahkan bagian unvoice dan voice ucapan dari sinyal suara. Dengan ada perbedaan pada overlapping block dan non-overlapping block. Kami mengevaluasi hasil dari semua metode tersebut bahwa teknik yang digunakan peneliti dengan overlapping blocks, zero crossing rate dan short time energy terbukti lebih efektif dalam pemisahan voice dan unvoice.]]>
<![CDATA[APLIKASI PENCARIAN LOKASI FASILITAS PELAYANAN UMUM TERDEKAT MENGGUNAKAN METODE ARTIFICIAL BEE COLONY DI KOTA BENGKULU BERBASIS WEBVIEW ANDROID ]]>
<![CDATA[Eno Rahmandha]]>;
<![CDATA[Rusdi Efendi]]>;
<![CDATA[Diyah Puspitaningrum]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (602.477 KB)
<![CDATA[Public services are growing as concomitants of the Bengkulu’s population growth. That fact makes it hard to find a certain public service in Bengkulu city. Another reason is we need to find a nearby public service to do daily tasks. The purpose of tis research are: (1) to show a nearby public service’s location.(2) To implement Artificial Bee Colony method in Bengkulu City’s Public Services Finder using Webview Android. The results are: (1) This research managed to implement public services finder in to map;(2) The result of algorithm relevancy test using abc base is quite high, 81% relevant, Meanwhile for standard abcis 2.91%. (3) The best parameter setting is using bees (CS) {30,50}. Maximum limit (L) {300,500,600} and maximum iteration (MCN) {30,50}.(4) The best bees setting are (CS) 30, maximum limit (L) 1000 maximum iteration 50. Artificial Bee Colony linier relevancy using employed bees and defined iterations meanwhile maximum limit parameter is not taking effect on the algorithm.]]>
<![CDATA[PENERAPAN LEARNING TECHNOLOGY SYSTEM ARCHITECTURE (LTSA) PADA MULTIMEDIA PEMBELAJARAN PERAKITAN PC ]]>
<![CDATA[Stefanus Santosa]]>;
<![CDATA[April Firman Daru]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (431.126 KB)
<![CDATA[Conventional learning systems still dominate the learning process at various universities. In general, learning in college lecture reflects patterns that tend in the same direction. Students the opportunity to conduct personal understanding through looping and less enrichment accommodated properly. This research tried to solved the problem. Hence, it is important to develop a teaching medium based on Learning Technology Systems Architecture (LTSA) with multimedia tutorial approach. From the test results of learning can be stated that the learning method PC assembly using multimedia-based teaching tools can support the learning that is interactive, engaging, efficient, effective, and meaningful. In addition test results also showed a significant difference compared to conventional teaching methods . Students using conventional learning systems only obtained an average score of 49.6, while students use learning system using learning tools of animation and visualization obtain an average value of 80 , 09. This suggests that the use of teaching aids by using multimedia (text, audio, video and animation) more easily understood by the students so deserves its place as a major strategy in the laboratory learning.]]>
<![CDATA[PENGENALAN POLA HURUF HIJAIYAH TULISAN TANGAN MENGGUNAKAN FUZZY FEATURE EXTRACTION DAN JARINGAN SYARAF TIRUAN BACKPROPAGATION ]]>
<![CDATA[Helsi Tia Vermala]]>;
<![CDATA[Diyah Puspitaningrum]]>;
<![CDATA[Yudi Setiawan]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 2 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 2 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (288.743 KB)
<![CDATA[This research to build a pattern recognition hijaiyah letters handwriting application. In this offline pattern recognition research, a digital handwriting input is captured by a scanner. In this research we try to recognize digital handwriting based on feature classification using Backpropagation Neural Network and Fuzzy Feature Extraction method for feature extraction. This application is built using Matlab language programming and designed using Data Flow Diagram (DFD). Meanwhile the system development life cycle method that used is Waterfall. Experiments were performed on a single Hijaiyah letters isolated from 900 samples gave results of generalization ability of artificial neural networks for 96.11% and the ability to generalize the ability of Neural Network memorization for 98.33%.]]>
<![CDATA[PERILAKU SMART NPC BERBASIS KOORDINASI MULTI AGENT MENGGUNAKAN FUZZY COORDINATOR ]]>
<![CDATA[Tri Daryatni]]>;
<![CDATA[Mochamad Hariadi]]>;
<![CDATA[Ahmad Zainul Fanani]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (390.73 KB)
<![CDATA[Computer games are very popular today, not only children but also adults like to play games. Good computer game is a game that has the type of NPC (Non-Player Character) that similar to humans, and looks natural. To make the game more interesting requires proper coordination between the NPC and multi agent intelligent. Multi agent based Artificial intelligent game will feature a challenging and exciting, so that people who play games not only get a lesson and recreation but also will not feel quickly bored with the existing game. By using Fuzzy Coordinator will make coordination between the NPC and the Smart Agents stronger. Multi agent cooperation would control the health of each NPC. Agent will coordinate the NPC where the strong and the weak, where should resign or stay afloat, so the game will be a lot of challenges and not boring.]]>
<![CDATA[DETEKSI API MENGGUNAKAN BACKGROUND SUBSTRACTION DAN ARTIFICIAL NEURAL NETWORK UNTUK REAL TIME MONITORING ]]>
<![CDATA[Andi Kamaruddin]]>;
<![CDATA[Vincent Suhartono]]>;
<![CDATA[Ricardus Anggi Pramunendar]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (410.01 KB)
<![CDATA[The most important initial step in the detection and localization of the fire is to detect fire quickly and reliably. Video-based surveillance is one of the most promising solutions for automatic fire detection with the ability to monitor a large area and ease of reading an alarm to the operator through the monitorSupervision, unfortunately, the main drawback of video-based fire monitoring system that uses optic is a false alarm caused by an Error detection (Error detection), for it is then in this study using the feature extraction GLCM (Gray level Coocurance Matrix) as input spectral classification of Neural network to detect fire, the approach can reduce the Average Error detection with Error detection rate Average is 7%]]>
<![CDATA[PEMODELAN DESAIN CAMPURAN BETON DENGAN BACKPROPAGATION NEURAL NETWORKS ]]>
<![CDATA[Stefanus Santosa]]>;
<![CDATA[Basuki Setiyo Budi]]>;
<![CDATA[Karnawan Joko Setiyono]]>;
<![CDATA[Tjokro Hadi]]>;
<![CDATA[Triatmo Sugih Hardono]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (139.373 KB)
<![CDATA[Concrete is a mixture of materials that has complex characteristic so that it raises a variety of very complex models as well. The experts in concrete mixing believe that the formula to find compressive strength of a mixture is not good enough. Every mixture design only applies to one mixture only. Because of that, every mixture production who need even the slightiest diferrences in the base materials, will need a new mixture design. Concrete mixture modeling process is done manually with a variety of mixed composition and destructively testing has some drawbacks like expensive, unpredictable, and not environmental friendly. Besides of that, state of the art concrete mixture design modelling computation with Multilayer Perceptron Artificial Neural Network s (MLP) have RMSE = 5,27. Computational model developed in this study with the same data sets has more good performace than MLP model. From the results of experiments that have been carried out proved that the proposed model, Backpropagation Neural Network (BPNN), has lower error rate than MLP with RMSE = 4.18.]]>
<![CDATA[PREDIKSI KECEPATAN ANGIN MENGGUNAKAN MODEL ARTIFICIAL NEURAL NETWORK BERBASIS ADABOOST ]]>
<![CDATA[Abdul Syukur]]>;
<![CDATA[Catur Supriyanto]]>;
<![CDATA[Akhmad Khanif Zyen]]>
<![CDATA[ Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1 ]]>
Publisher : <![CDATA[Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (172.759 KB)
<![CDATA[Prediction is an attempt to predict the future by examining the past. This prediction consists of the bias estimation of the magnitude of future several variables, such as sales, on the basis of knowledge of the past, present, and experience. Adaboost is one of the optimization algorithm which can improve the accuracy of a predictive value. Previous research examines the exchange rate prediction of wind speed using back propagation Artificial Neural Network algorithm. The purpose of this study is intended to improve the accuracy of prediction of wind speed previously predicted using Artificial Neural Network Backpropagation algorithm then improved the prediction accuracy using adaboost algorithm during the process of training and added back propagation Artificial Neural Network algorithm in the learning process.The results showed that the prediction accuracy of the wind speed values previously predicted using Artificial Neural Network back propagation algorithm with an accuracy of prediction error at sample time per 10 minute predictions of 0.31576596 managed to reduce the value of the accuracy of the prediction error using adaboost algorithm during training and coupled Artificial Neural Network algorithm Backpropagation learning process with an accuracy of prediction error amounting to 0.15945762.]]>
