cover
Contact Name
Stefanus Santosa
Contact Email
cyberku@pasca.dinus.ac.id
Phone
+6281225200216
Journal Mail Official
cyberku@pasca.dinus.ac.id
Editorial Address
Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro, Gedung G Lt. 2, Jl. Imam Bonjol 205, Semarang, 50131, INDONESIA - email: cyberku@pasca.dinus.ac.id
Location
Kota semarang,
Jawa tengah
INDONESIA
Jurnal Teknologi Informasi Cyberku
ISSN : 19073380     EISSN : 27472183     DOI : -
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
Simulasi Crowd Evacuation Menggunakan Kombinasi Social Force Model dan Attractive Potential Field Evi Rokhayati; Mochamad Hariadi; Ahmad Zainul Fanani
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 1 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 1 2018
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (952.857 KB)

Abstract

Natural disasters claimed many victims. To prevent this, one is to understand the problem of evacuation crowd behavior. Evacuation research in dangerous condition of the people or the crowd is a research to understand how human behavior in facing danger as individuals in a group or crowd. Evacuation research is almost impossible to be experimented in a real life, but it can be simulated. Evacuation simulation can help to understand more about the evacuation. For example, by understanding the evacuation, it could be used for the development of buildings and facilities safer and more comfortable or to make good standard evacuation procedures. Formerly research evacuation simulations in the crowd are based on the miSFM (mutual information Social Force Model) where the individual or agent in the crowd will conduct the evacuation simulation by using social force models and get feedbacks of mutual information such as location, rate, direction and density of agent, so there’s no effect of "faster is slower" but this model still has the disadvantage that doesn’t regulate the density in crucial areas, such as in the exit. This study proposes a force social combination model with attractive potential field or SPM-PF to solve the density, so the effect of "faster is slower" can be reduced and the evacuation could be faster. Based on the results of the tests taken place on environment with one door room showed that the average of SFM-PF algorithm is faster 13.01 seconds or 44.67% than the miSFM algorithm in the application of evacuation simulation.Keyword: crowd behavior, simulation evacuation, social force model, atrractive potential field
METODE SAMPLE BOOSTRAPING PADA K-NEAREST NEIGHBOR UNTUK KLASIFIKASI STATUS DESA Eko Siswanto; Suprapedi Suprapedi; Purwanto Purwanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 1 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 1 2018
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (442.069 KB)

Abstract

The Ministry of Rural Area, Remote Area Development and Transmigration divides village itself into five villages, such as, Independent Village, Advance Village, Developing Village, Remote Village and Very Extremely Remote Village. The data are based on Village Potency (Podes) in 2014 by the Ministry of Rural Area, Remote Area Development and Transmigration. It is necessary to know that the data of The Ministry of Rural Area, Remote Area Development and Transmigration can be used to predict the relationship between village development indicators and the status of villages. In this case, it means whether the indicators, which are built, can influence the status of villages or not and whether they can make the status of villages become better than before. k-Nearest Neighbor (k-NN) algorithm is a method which is used to classify toward new object based on k as the nearest neighbor. k-Nearest Neighbor (k-NN) algorithm has the strength as the effective and simple algorithm and it has been used by many problem classifications. However, it has weakness if it is used for the big dataset. It can happen because it needs higher computation time. In this research, Bootstrapping Sample method is proposed to increase the optimalization of computation accuracy and time on Boostraping Sample method. Based on this research, by using the integration of k-Nearest Neighbor (k-NN) algorithm with Bootstrapping Sample method on IPD dataset on Jepara in 2014, apparently it can increase the accuracy until 5.41 % (91.89%-97.30%) than using standard k-NN algorithm. The last, from the result of this research it can be inferred that by using the integration of K-Nearest Neighbor (k-NN) algorithm with Boostraping Sample method shows the better accuracy than using standard k-NN algorithm
KLASIFIKASI DATA TIME SERIES ARUS LALU LINTAS JANGKA PENDEK MENGGUNAKAN ALGORITMA ADABOOST DENGAN RANDOM FOREST Ahmad Rofiqul Muslikh; Heru Agus Santoso; Aris Marjuni
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 1 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 1 2018
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (584.878 KB)

Abstract

Data traffic in Indonesia is used for management control traffic flow, while the data on get results from the survey will be undertaken directly localized, the survey will be undertaken are less effective, and the data obtained from the survey results were used as a reference in control traffic flow, and therefore to obtain the data traffic flow more effective in need of a new approach that can classified and predict the data in the can with higher accuracy, so that density and congestion can be predicted earlier. In this study used the approach of using Adaboost and Random Forest algorithms to classification and predict the survey data that are time series, the results of testing for prediction using Adaboost with Random Forest With Confusion Matrix as a measuring accuracy rate of 87,8%, and the rate of error in getting at 0 , 0629. On the results using Adaboost with a Random Forest approach proved to be more efficient in predicting the survey data rather than simply relying on the original data to predict traffic flow
KLASIFIKASI PESAN SMS MENGGUNAKAN ALGORITMA NAIVE BAYES DENGAN SELEKSI FITUR GENETIC ALGORITHM Indah Munitasri; Stefanus Santosa; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 1 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 1 2018
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (469.055 KB)

Abstract

Short Message service (SMS)is mobile communication that interest advertiser for its effective deliveries with cheap operational cost compare to printed media. Some spam SMS do not need mailing list to reach their customers. But, spam SMS could create higher respons from emails spam. Spam SMS includes promotion,scamming,and fraud.To overcome this problem,anti-spam filtering are needed to detect spam and non-spam SMS. Some anti-spam filtering algoritm such as Decission Tree, Naïve Bayes (NB),Support Vector Machine (SVM),and Neural Network. This research used Naïve Bayes classifier or known as multinominal Naïve Bayes is a simplification from Bayes algoritm which is suitable for text or documents classification.This study will make additional Genetic Algorithms in the process of selecting attributes that will be used in the classification process with Naïve Bayes algorithm. Genetic Algorithms can be used as an attribute of the overall voter attributes obtained from the process of feature extraction. NB compared to NB and GA produced significant accuracy result, NB gained 89.39% accuracy rate, but GA gained 89.73% accuracy rate. So, there is an increase in 0.34 % after adding GA. NB and GA can be applied to the classification of SMS messages, because Naïve Bayes algorithm is an algorithm that does not consider the relationship between attributes to one another (independence). So, when there is a data set with hundreds of attributes, all of those attributes will be counted by Naïve Bayes, by adding a Genetic Algorithm as a feature selection, which determines the attributes that are relevant in order to optimize the classification accuracy. It is expected to apply feature selection using Particle Swarm Optimization (PSO) for the next research because there is no evolution in the operator, for example, mutation and crossover on Genetic Algorithms (GA,) and PSO is more flexible in maintaining the balance between global and local searches on its search space.
OPTIMASI PARTFICLE SWARM OPTIMIZATION (PSO) PADA ALGORITMA KLASIFIKASI NEURAL NETWORK (NN) DALAM PENENTUAN KELAYAKAN PEMBERIAN SERTIFIKASI GURU Kurnia Prayoga Wicaksono; M. Arif Soeleman; Ricardus Anggi Pramunendar
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 1 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 1 2018
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (229.675 KB)

Abstract

To improve the quality of national education, the government through the Ministry of Education. This is of course interesting for the community to be part of this program, many of whom choose to become teachers, though not from an education-based college. One of the factors that is the main attraction is the benefits that will be obtained for teachers who have passed the certification exam. Government through Master's law, the issuance of a regulated policy of preparedness can be the basis for establishing Master's eligibility as a professional, so that the profession is allowance. owever, conditions in the field, found some teachers who are not yet eligible to hold the certification, there are still many teachers under the standard Teacher Compotency Test. Therefore, built a system made using Artificial Neural Network optimized with Particle Swarm Otimation, to determine the feasibility of certification so that later this case does not happen again. In this study gives a general idea that certified teachers are not all worthy of the predicate. Artificial Neural Network is optimized with Particle Swarm Optimization algorithm, giving higher accuracy with 80.80% accuracy level compared with 79.65% neural network algorithm model.
FEATURE RECOGNITION BERBASIS CORNER DETECTION DENGAN METODE FAST, SURF, DAN FLANN TREE UNTUK IDENTIFIKASI LOGO PADA AUGMENTED REALITY MOBILE SYSTEM Rastri Prathivi; Vincent Suhartono; Guruh Fajar Shidik
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (360.371 KB)

Abstract

Logo is a graphical symbol that is the identity of an organization, institution, or company. Logo isgenerally used to introduce to the public the existence of an organization, institution, or company.Through the existence of an agency logo can be seen by the public. Feature recognition is one of theprocesses that exist within an augmented reality system. One of uses augmented reality is able torecognize the identity of the logo through a camera. The first step to make a process of feature recognitionis through the corner detection. Incorporation of several method such as FAST, SURF, and FLANN TREEfor the feature detection process based corner detection feature matching up process, will have the betterability to detect the presence of a logo. Additionally when running the feature extraction process there areseveral issues that arise as scale invariant feature and rotation invariant feature. In this study theresearch object in the form of logo to the priority to make the process of feature recognition. FAST, SURF,and FLANN TREE method will detection logo with scale invariant feature and rotation invariant featureconditions. Obtained from this study will demonstration the accuracy from FAST, SURF, and FLANNTREE methods to solve the scale invariant and rotation invariant feature problems
KLASIFIKASI CITRA TELUR FERTIL DAN INFERTIL DENGAN ANALISIS TEKSTUR GRAY LEVEL CO-OCCURRENCE MATRIX DAN SUPPORT VECTOR MACHINE Dewi Nurdiyah; Stefanus Santosa; Ricardus Anggi Pramunendar
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (278.132 KB)

Abstract

Fertility eggs test are steps that must be performed in an attempt to hatch eggs. Fertility testusually use egg candling. The purpose of observation is to choose eggs fertile (eggs containedembryos) and infertile eggs (eggs that are no embryos). And then fertilized egg will be entered intothe incubator for hatching eggs and infertile can be egg consumption. However, there are obstaclesin the process of sorting the eggs are less time efficient and inaccuracies of human vision todistinguish between fertile and infertile eggs. To overcome this problem, it can be used ComputerVision technology is having such a principle of human vision. It used to identify an object basedon certain characteristics, so that the object can be classified. The aim of this study to classifyimage fertile and infertile eggs with SVM (Support Vector Machine) algorithm based on inputfrom bloodspot texture analysis and blood vessels with GLCM (Gray Level Co-occurrenceMatrix). Eggs image studied are 6 day old eggs. It is expected that the proposed method is anappropriate method for classification image fertile and infertile eggs.
PENENTUAN THRESHOLD MENGGUNAKAN ALGORITMA SELF ORGANIZING MAPS (SOM) UNTUK SEGMENTASI REGION KARAKTER PADA PLAT NOMOR KENDARAAN Apriyanto Alhamad; Vincent Suhartono; Ricardus Anggi Pramunendar
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (784.538 KB)

Abstract

At this time the era of information technology , the use of automation and intelligent systems are becomingmore and more widespread. Transfortasi Intelligent Systems has received so much attention that manysystems are being developed and applied throughout the world. In a vehicle license plate recognitionsystem consists of several stages , namely pre-processing , license plate detection, the segmentation ofcharacters and the vehicle license plate character recognition . In previous studies determining thethreshold value using Otsu local method by dividing two variants of black and white . In a study usinglocal methods otsu susceptible to interference in the picture . In the study proposes a method of self -organizing map in determining the threshold value . Then from the results of the threshold determinationfollowed by segmenting the characters using the function bouding Box . From the experimental results ofthreshold determination method of self - organizing maps can increase the threshold value of 0.5241 andthe experimental test of character segmentation as measured using the function Means Square Error of6.93E +03 pixels , smaller than the test results of the local segmentation character Otsu method
GAME SCORING NON PLAYER CHARACTER MENGGUNAKAN AGEN CERDAS BERBASIS FUZZY MAMDANI Astrid Novita Putri; Mochamad Hariadi; Ruri Suko Basuki
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (582.34 KB)

Abstract

Game are activity most structure, one that ordinary is done in fun and also education tool and help todevelop practical skill, as training, education, simulation or psychological. On its developing currentGame have until 3D. In one Game, include in First Person Shutter necessary scoring one that intent tomotivate that player is more terpacu to solve Game until all through, on scoring Super Mario's GameBoss, Compass does count scoring haven't utilized Artifical Intelligent so so chanted, while player meetwith enemy (Non Player Character) really guns directly dead, so is so easy win. Therefore at needs acount scoring interesting so more terpacu in menyelasaikan problem Scoring accounting point for FirstPerson Shutter's Game .This modelling as interesting daring in one Game, since model scoring one thateffective gets to motivate that player is more terpacu in plays and keep player for back plays. Besidesmodel scoring can assign value that bound up with Game zoom.On Research hits scoring this Game willmake scoring bases some criterion which is health Point, Attack point, Defending point, And Dammagewhat do at miiliki zombie,then in this research do compare two method are methodic statistic and Fuzzy.Result of this research 90 % on testing's examination and on eventually gets to be concluded that fuzzy'smethod in trouble finish time more long time but will player more challenging to railroad
PENGELOMPOKAN ARSIP UNIVERSITAS MENGGUNAKAN ALGORITMA K-MEANS DENGAN FEATURE SELECTION CHI SQUARE Sitti Munifah; Abdul Syukur; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (159.986 KB)

Abstract

The information in every activity is very fundamental either in technical activities or in decision making.One of those is information in the form of data records or archives. Considering the importance of therole of an archive more actively in supporting the activities, then, it needs to manage the archive betterthrough the application of information and communication technology aspect, particularly on the processof archives storage. By using electronic media in archives management, then it can give easiness instoring the archives. Related to the things discussed and due to the increasing of document numbers in thetext form which quiet large on University archives chamber, it makes the document clustering important.The document clustering is a right way and has purpose of distributing the document into some groups,which have text similarity level, term wighting and distance similarity that used at the time of archivesstoring subjectively. The objective of this writing is to clustering of archives document in the archivesstoring system, increasing of clustering document performance through term weighting TF-IDF andselection feature method. The results showed that the use of selection feature method and K-MeansAlgorithm on clustering analysis, to process the archives storing seen that there was an increasing ofaccuracy level on Manhattan Distance which previously selection feature added as 61.39% with timetaken was as 69 seconds, become 73.86% on weighting TF-IDF through selection feature of Chi Squarewith time taken needed in the process was as 9 seconds