JUTI: Jurnal Ilmiah Teknologi Informasi
Not a member yet
407 research outputs found
Sort by
SISTEM AGEN CERDAS BERBASIS WEB UNTUK KOMPUTASI INFORMASI KINERJA DARI PELAKSANAAN PROYEK-PROYEK PERUSAHAAN
Get PDFIn this paper are presented the development of a model of intelligent software agents to support web-based computing of project performance information that being executed by the company. The project performance is calculated by using earned value management method. We have developed a prototype of the intelligent agent software based on Jadex agent framework. Based on some simple data simulations of enterprise projects, our agents have showed capabilities in calculating the performance value of projects and displaying into barchart or S-graph
PROTOTIPE KANTIN TANPA UANG BERBASIS KARTU PINTAR
Get PDFThis paper presents a desktop application prototype that uses smart cards for payment mode without cash transaction at a canteen. Smart cards, used for authentication, are also designed to have information of cash balance and some personal data of card holders. Application developed is still a prototype that has not connected into the banking system to refill the balance into the smart card. This prototype is a desktop application. Features that have been successfully developed and run well in these applications include food settings, user settings, and reports sales per period
PENGGUNAAN TEKNIK FEATURE WEIGHTING UNTUK PEMBERSIHAN NOISE PADA HALAMAN SITUS BERITA BERBAHASA INDONESIA
Get PDFA web page usually consists of information in every page blocks displayed. In some cases, news content displayed in a news website are not entirely relevant or are unrelated to the main content such as navigation panel, copyright, user guide, links, news summary, various advertisement etc. Information blocks irrelevant to the main content is known as web pages noise. This research applies feature weighting technique to improve classification results by detecting a noise in pages of a website. Using feature weighting technique the web is first modelled with Document Object Model(DOM) tree and Compressed Structure Tree(CST) to obtain the general structure and compare the information blocks in awebsite.Information obtained is used to measure and evaluate the importance level of each node created by Compressed Structureed Tree(CST). Based on the tree created and the importance level of each node, this method assign weights on each individual word (feature) in each content block. The weights will be used in web mining process
APLIKASI INPUT METHOD EDITOR (IME) JEPANG BERBASIS WEB
Get PDFJapanese language uses thousands of characters for its writing system. A system called Input Method is used to enable the inputs of those characters using a standard keyboard. Some Input Method applications were already developed, from the desktop application to the web-based application. Unfortunately, those applications are not flawless. In this research, an application using the Input Method system has been developed to cover the weaknesses of those applications that already developed before. This Input Method application system uses standard web technology. Such as JavaScript on the client side. PHP on the server side. MeCab: Yet Another Part-of-Speech and Morphological Analyze dictionary is used for its dictionary. The core algorithm uses Longest Match Method for word searching
PENGEMBANGAN MODEL ARSITEKTUR ENTERPRISE UNTUK PERGURUAN TINGGI
Get PDFSalah satu tujuan dari penerapan arsitektur enterprise adalah menciptakan keselarasan antara bisnis dan teknologi informasi bagi kebutuhan organisasi. Penerapan arsitektur enterprise tidak terlepas dari bagaimana sebuah organisasi merencanakan dan merancang arsitektur enterprise tersebut. Tahapan dalam pengembangan model arsitektur enterprise sangatlah penting dan akan berlanjut pada tahapan berikutnya yaitu rencana implementasi. Penelitian ini membangun sebuah arsitektur enterprise yang nantinya bisa dijadikan oleh organisasi untuk mencapai tujuan strategisnya. Model arsitektur ini dapat dijadikan sebagai model dasar bagi institusi perguruan tinggi didalam pengembangan arsitektur enterprise
AN INTRODUCTION TO KNOWLEDGE-GROWING SYSTEM: A NOVEL FIELD IN ARTIFICIAL INTELLIGENCE
No full textThe essential matter of Artificial Intelligence (AI) is how to build an entity that mimics human intelligence in the way of learning of a phenomenon in a real life to gain knowledge of it and uses the knowledge to solve problems related to it. Based on the findings of intelligenct characteristic displayed by the human brain in growing and generating new knowledge by fusing information perceived by sensory organs, we develop brain-inspired Knowledge-Growing System (KGS) that is, a system that is capable of growing its knowledge along with the accretion of information as the time passes. The essential matter of KGS is knowledge-growing method which is based on a new algorithm called Observation Multi-time A3S (OMA3S) information-inferencing fusion method. In this paper we deliver the development of KGS along with some examples of KGS application to a real-life problem. Based on the state-of-the-art of AI and approaches to construct OMA3S method as KG method as well as validations to assess the system performance, we state that brain-inspired KGS is a novel field in AI
APLIKASI WEB CRAWLER UNTUK WEB CONTENT PADA MOBILE PHONE
Get PDFCrawling is the process behind a search engine, which served through the World Wide Web in a structured and with certain ethics. Applications that run the crawling process is called Web Crawler, also called web spider or web robot. The growth of mobile search services provider, followed by growth of a web crawler that can browse web pages in mobile content type. Crawler Web applications can be accessed by mobile devices and only web pages that type Mobile Content to be explored is the Web Crawler. Web Crawler duty is to collect a number of Mobile Content. A mobile application functions as a search application that will use the results from the Web Crawler. Crawler Web server consists of the Servlet, Mobile Content Filter and datastore. Servlet is a gateway connection between the client with the server. Datastore is the storage media crawling results. Mobile Content Filter selects a web page, only the appropriate web pages for mobile devices or with mobile content that will be forwarded
PEMBENTUKAN SET JALUR ALIRAN PROGRAM MENGGUNAKAN TEKNIK JUMLAH JALUR MINIMUM DAN TEKNIK JUMLAH PREDIKAT MINIMUM
Get PDFStructured testing is based on the control flow of programs. The analysis of the control flow of program is conducted on a reduced flowgraph, called a decision-to-decision graph (DDGraph). The relations of dominance and implication between arcs enable to immediate identification of a subset of DDGraph arcs. These arcs are called unconstrained arcs, which have a property that, when the unconstrained arcs are exercised, the traversal of all the other arcs are guaranteed. In order to find a path cover for given program flowgraph, there are two methods: minimum number of paths technique and less pred technique
PERAMALAN KONSUMSI LISTRIK JANGKA PENDEK DENGAN ARIMA MUSIMAN GANDA DAN ELMAN-RECURRENT NEURAL NETWORK
Get PDFNeural network (NN) is one of many method used to predict the electricity consumption per hour in many countries. NN method which is used in many previous studies is Feed-Forward Neural Network (FFNN) or Autoregressive Neural Network(AR-NN). AR-NN model is not able to capture and explain the effect of moving average (MA) order on a time series of data. This research was conducted with the purpose of reviewing the application of other types of NN, that is Elman-Recurrent Neural Network (Elman-RNN) which could explain MA order effect and compare the result of prediction accuracy with multiple seasonal ARIMA (Autoregressive Integrated Moving Average) models. As a case study, we used data electricity consumption per hour in Mengare Gresik. Result of analysis showed that the best of double seasonal Arima models suited to short-term forecasting in the case study data is ARIMA([1,2,3,4,6,7,9,10,14,21,33],1,8)(0,1,1)24 (1,1,0)168. This model produces a white noise residuals, but it does not have a normal distribution due to suspected outlier. Outlier detection in iterative produce 14 innovation outliers. There are 4 inputs of Elman-RNN network that were examined and tested for forecasting the data, the input according to lag Arima, input such as lag Arima plus 14 dummy outlier, inputs are the lag-multiples of 24 up to lag 480, and the inputs are lag 1 and lag multiples of 24+1. All of four network uses one hidden layer with tangent sigmoid activation function and one output with a linear function. The result of comparative forecast accuracy through value of MAPE out-sample showed that the fourth networks, namely Elman-RNN (22, 3, 1), is the best model for forecasting electricity consumption per hour in short term in Mengare Gresik
RANCANGAN DAN IMPLEMENTASI GALERI VIDEO DAN ANIMASI PADA SITUS LAPAN POLAR SATELLITE
Get PDFLapan Tubsat satellite has produced large number of videos or satellite images since the first launch from the Satish Dhawan Space Center, Sriharikota India, on January 10, 2007. LAPAN expect that the results of the satellite tracking needs a storage media that enables it to be more accessible and attractive to the public. Therefore, a facility is designed and implemented to meet the user requirements. The built of an interactive video gallery which is embedded with the site is the main focus of this paper. In addition, animations and video player are also implemented so that Lapan Polar Satellite Sites (SLPS) become more interactive and interesting to the site visitors