IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Ship Identification on Satellite Image Using Convolutional Neural Network and Random Forest
Get PDFShip identification on satellite imagery can be used for fisheries management, monitoring of smuggling activities, ship traffic services, and naval warfare. However, high-resolution satellite imagery also makes the segmentation of the ship difficult in the background, so that to handle it requires reliable features so that it can be identified adequately between large vessels, small vessels and not ships. The Convolutional Neural Network (CNN) method, which has the advantage of being able to extract features automatically and produce reliable features that facilitate ship identification. This study combines CNN ZFNet architecture with the Random Forest method. The training was conducted with the aim of knowing the accuracy of the ZFNet layers to produce the best features, which are characterized by high accuracy, combined with the Random Forest method. Testing the combination of this method is done with two parameters, namely batch size and a number of trees. The test results identify large vessels with an accuracy of 87.5% and small vessels with an accuracy of not up to 50%
System Security Awareness Planning Model Using The Octave Method Approach
Get PDFAwareness of the security of information systems is an important thing to note. In this study, we will discuss planning models of awareness about information system security using Octave models or methods. The analytical method used is qualitative descriptive analysis. The results of the study show that the Octave model can increase awareness about the importance of security in an information system and companies that implement it will be able to improve their performance in the future
The K-Means Clustering Algorithm With Semantic Similarity To Estimate The Cost of Hospitalization
Get PDF The cost of hospitalization from a patient can be estimated by performing a cluster of patient. One of the algorithms that is widely used for clustering is K-means. K-means algorithm, based on distance still has weaknesses in terms of measuring the proximity of meaning or semantics between data. To overcome this problem, semantic similarity can be used to measure the similarity between objects in clustering, so that, semantic proximity can be calculated. This study aims to conduct clustering of patient data by paying attention to the similarity of the patient’s disease. ICD code is used as a guide in determining a patient’s disease. The K-means method is combined with semantic similarity to measure the proximity of the patient’s ICD code. The method used to measure the semantic similarity between data, in this study, is the semantic similarity of Girardi, Leacock & Chodorow, Rada, and Jaccard Similarity. Cluster quality measurement uses the silhouette coefficient method. Based on the experimental results, the method of measuring semantic similarity data is capable to produce better quality clustering results than without semantic similarity. The best accuracy is 91.78% for the three semantic similarity methods, whereas without semantic similarity the best accuracy is 84.93%
DSS for "E-Private" Using a Combination of AHP and SAW Methods
Get PDFPrivate tutoring was non-formal education and it was needed to help student in learning.There were already tutoring system developed where the selection of private tutors was done by filtering peocess. However, filtering process was not suitable with needs and desires of students.Besides the filtering process, to support the solution in making decisions on the selection of private tutors on the E-Privat system it also used the Decision Suport System (DSS) concept, namely a combination of AHP and SAW methods. AHP method was used to find the weights in each criterion, and the ranking calculation with the SAW method.E-Privat aimed to help parents / students in choosing private tutors that suit the needs and desires of students by involving multi-criteria and various alternative. This system was also developed to help private tutors to get the opportunity to fill out private lessons. The testing process results showed that the system had been successful and suitable for used. There were 5 testing processes : (1)black box testing, (2)white box testing, (3)accuracy test which showed a percentage of 87%, and (4)user's response test whichused the SUS method showed a percentage 92.08% with best imaginable category
Classification of Sambas Traditional Fabric “Kain Lunggi” Using Texture Feature
Get PDFTraditional fabric is a cultural heritage that has to be preserved. Kain Lunggi is Sambas traditional fabric that saw a decline in its crafter. To introduce Kain Lunggi in a broader national and global society in order to preserve it, a digital image processing based system to perform Kain Lunggi pattern recognition need to be built. Feature extraction is an important part of digital image processing. The visual feature that does not represent the character of an object will affect the accuracy of a recognition system. The purposes of this research are to perform feature selection on sets of feature to determine the best feature that can increase recognition accuracy. This research conducted in several steps which are image acquisition of Kain Lunggi pattern, preprocessing to reduce image noise, feature extraction to obtain image features, and feature selection. GLCM is implemented as a feature extraction method. Feature extraction result will be used in a feature selection process using CFS (Correlation-based Feature Selection) methods. Selected features from CFS process are Angular Second Moment, Contrast, and Correlation. Selected features evaluation is conducted by calculating classification accuracy with the KNN method. Classification accuracy prior to feature extraction is 85.18% with K values K=1 ; meanwhile, the accuracy increases to 88.89% after feature selection. The highest accuracy improvement of 20.74% in KNN occurred when using K value K= 4
Classification of Human Weight Based on Image
Get PDFClassification of human weight can be determined by body mass index. The body mass index can be calculated by dividing the height by the square of the body weight. According to researchers, this is less practical, so it needs to make a tool that can be used to determine ideal body weight more practically. One way is to use an Android smartphone camera. The camera is used to capture the image of the human body. Then the image is processed by using digital image processing and by using certain algorithms, so it may conclude the person's ideal weight category. The data used in this study are human photos, body weight and height. There are four stages to determine the weight and height based on the image. First, performing an analysis of the calculation of the derived formulas. Second, analyzing the edge detection algorithm. Third, conducting unit convertion, and fourth, proposing several algorithms to calculate the height and weight used to determine the ideal body weight. The results of the evaluation show that Algorithm C (measuring the width of an object starting with the height of the image adjusting half of the height of the object in the image) is the best algorithm with deviation value of 1.85% of the height and 8.87% of the weight, while the system accuracy rate in determining the ideal body weight has reached 78.7%.
Modification of Stemming Algorithm Using A Non Deterministic Approach To Indonesian Text
Get PDF Natural Language Processing is part of Artificial Intelegence that focus on language processing. One of stage in Natural Language Processing is Preprocessing. Preprocessing is the stage to prepare data before it is processed. There are many types of proccess in preprocessing, one of them is stemming. Stemming is process to find the root word from regular word. Errors when determining root words can cause misinformation. In addition, stemming process does not always produce one root word because there are several words in Indonesian that have two possibilities as root word or affixes word, e.g.the word “beruang”.To handle these problems, this study proposes a stemmer with more accurate word results by employing a non deterministic algorithm which gives more than one word candidate result. All rules are checked and the word results are kept in a candidate list. In case there are several word candidates were found, then one result will be chosen.This stemmer has been tested to 15.934 word and results in an accurate level of 93%. Therefore the stemmer can be used to detect words with more than one root word
Adaptive Moment Estimation On Deep Belief Network For Rupiah Currency Forecasting
Get PDFOne approach that is often used in forecasting is artificial neural networks (ANN), but ANNs have problems in determining the initial weight value between connections, a long time to reach convergent, and minimum local problems.Deep Belief Network (DBN) model is proposed to improve ANN's ability to forecast exchange rates. DBN is composed of a Restricted Boltzmann Machine (RBM) stack. The DBN structure is optimally determined through experiments. The Adam method is applied to accelerate learning in DBN because it is able to achieve good results quickly compared to other stochastic optimization methods such as Stochastic Gradient Descent (SGD) by maintaining the level of learning for each parameter.Tests are carried out on USD / IDR daily exchange rate data and four evaluation criteria are adopted to evaluate the performance of the proposed method. The DBN-Adam model produces RMSE 59.0635004, MAE 46.406739, MAPE 0.34652. DBN-Adam is also able to reach the point of convergence quickly, where this result is able to outperform the DBN-SGD model
Digitalization On Students Scoring System of SMPN 18 Bekasi
Get PDF Information technology has been supporting the development of school services in the world. But there are still many schools does not using the information technology at all - specially in Indonesia, for example at SMPN 18 Bekasi. As usually like another school they only using Ms. Word and Ms. Excel applications. That is make many differences output in format scoring and mistakes while filling score on the students report format. The application of academic information system in this research have developed using PHP, HTML and MySQL as programming language. It named SIADHEL, means Eighteen Academic Information System (Sistem Informasi Akademik Delapan Belas) . The aims of this project is to provide a good tools for students or their parents to receive the exactly, fast and accurate informations of their students scoring. Teachers can use an integrated and accurate tools as facility to provide data for the Principal to make new policies. This application could be opened by every browser platform, so it will make easier for the users to access the program wherever and anytime
Application of Load Balancing with the Nth Method on Multiple Gateway Internet Networks
No full textThe Performance of a Network Is Necessary by the Office of the Special Jayapura Regent in matters related to networking. One of the technological problems to increase connections in the network is to use three ISPs and become microtik as a balanced load. Each ISP uses load sharing that can be divided evenly in each section. Wireless networks that are connected to distributed systems make load balancing techniques that can be received from a system. Load balancing can be applied to HTTP servers, proxies, databases, and gateways. This research implements a proxy with load balancing method on an internet network that has three gateway lines through a router. Expected to be expected to be expected to be expected to load three ISP. The results of the research on the application of load balancing with the method on several internet gateways in the Jayapura District Regent Office is an inconsistency in bandwidth for each client before the implementation of the Nth method and using the Nth method with ten active clients can used when bandwidth on some clients is not much different and more evenly distributed than without load load balancing Nth