Articles
            
            
            
            
            
                            
                    
                        Tactical Planning in Space Game using Goal-Oriented Action Planning 
                    
                    Restuadi Studiawan; 
Mochamad Hariadi; 
Surya Sumpeno                    
                     JAREE (Journal on Advanced Research in Electrical Engineering) Vol 2, No 1 (2018): April 
                    
                    Publisher : Department of Electrical Engineering ITS and FORTEI 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                                                    
                            | 
                                DOI: 10.12962/j25796216.v2.i1.32                            
                                            
                    
                        
                            
                            
                                
Along with improvement of modern electronic games, necessity of an intelligent agent that easily build is needed. One of electronic games that need good intelligent agent is real-time tactics. In this game type, good action planning is necessary to provide best experience to the player. On this paper, we try to find out whether if Goal-Oriented Action Planning (GOAP) is robust enough to be used at tactical game. By using GOAP, tactic dynamism still can be provided with reasonable amount of runtime.Keywords: Artificial intelligence, Games, Goal-Oriented Action Planning, Planning, Unity3D
                            
                         
                     
                 
                
                            
                    
                        Clustering Data National Examinations based on Social Media Using K-Means Methods 
                    
                    Chandra Eko Wahyudi Utomo; 
Mochamad Hariadi; 
Surya Sumpeno                    
                     JAREE (Journal on Advanced Research in Electrical Engineering) Vol 4, No 2 (2020): October 
                    
                    Publisher : Department of Electrical Engineering ITS and FORTEI 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                                                    
                            | 
                                DOI: 10.12962/j25796216.v4.i2.152                            
                                            
                    
                        
                            
                            
                                
The development of social media as a source of data is now increasingly interesting to study. The social media studied in this research is Twitter. Twitter as one of the top-ranked social media among social media accessed by the people of Indonesia. People's behavior can be learned by collecting and processing data, one of which is people's sentiments or opinions about national examinations in Indonesia. Twitter user behavior in the form of their comments about the national exam in Indonesia. This study aims to analyze the public sentiments of social media users about the National Examination in Indonesia. Data is retrieved by crawling data via the Twitter API. The data needs to be preprocessed first and feature extracted using TF-IDF. However, because the text data on Twitter is unstructured and very diverse data (variety), the grouping stage must be done first. Grouping technique using K-Means Clustering on Spark. Spark clustering techniques are used to overcome the grouping of data on very large and complex amounts of data. From the clustering process using Spark it was found that the grouping process resulted in 3 clusters where elbow detection was found in the third cluster of the number of clusters between 2 and 50. The results of clustering in the form of 3 large groups were further processed (with classification techniques) to get a positive or negative sentiment comparison of social media user comments about the national exam. Furthermore, these results become recommendations and new knowledge about community behavior regarding Social Media-based National Exams.Keywords: clustering, K-Means, national exam, sentiment analysis, social media.
                            
                         
                     
                 
                
                            
                    
                        Penerapan Logika Fuzzy untuk Pembentukan Sutradara Otonom dalam hal Pencahayaan pada Machinima 
                    
                    Andreas; 
Mauridhi H. Purnomo; 
Mochamad Hariadi                    
                     Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 9 No 1: Februari 2020 
                    
                    Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                    |
                            
                            
                                Full PDF (1486.123 KB)
                            
                                                                                    
                            | 
                                DOI: 10.22146/jnteti.v9i1.147                            
                                            
                    
                        
                            
                            
                                
Lighting is one of the most important things in the world of cinematography. There are several parameters that must be considered to produce good lighting. There are so many permutations in the lighting arrangement. It causes complexity of the process and there is no simple way to do the calculation. This complexity is compounded by the fact that each director has their own style in lighting arrangements in the film production process. This paper refers to the tabulation of the results of interviews with three movie directors and then the similarities of the three were taken. In this study, a fuzzy logic structure was built with five parameters of lighting arrangement, namely: the situation of the set, the camera's point of view, the installed light intensity, the position and direction of the camera, and the emotions of the character. This research was conducted using 20 animated movie scenes that were built using Unity. The assessment of the output is done manually by several animated film designers. As a result, the designers assess that 80% of the lighting arrangement has been as expected.
                            
                         
                     
                 
                
                            
                    
                        Analisis Kinerja LSTM dan GRU sebagai Model Generatif untuk Tari Remo 
                    
                    Lukman Zaman; 
Surya Sumpeno; 
Mochamad Hariadi                    
                     Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 8 No 2: Mei 2019 
                    
                    Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                    |
                            
                            
                                Full PDF (1418.245 KB)
                            
                                                                    
                    
                        
                            
                            
                                
Creating dance animations can be done manually or using a motion capture system. An intelligent system that able to generate a variety of dance movements should be helpful for this task. The recurrent neural network such as Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU) could be trained as a generative model. This model is able to memorize the training data set and reiterate its memory as the output with arbitrary length. This ability makes the model feasible for generating dance animation. Remo is a dance that comprises several repeating basic moves. A generative model with Remo moves as training data set should make the animation creating process for this dance simpler. Because the generative model for this kind of problem involves a probabilistic function in form of Mixture Density Models (MDN), the random effects of that function also affect the model performance. This paper uses LSTM and GRU as generative models for Remo dance moves and tests their performance. SGD, Adagrad, and Adam are also used as optimization algorithms and drop-out is used as the regulator to find out how these algorithms affect the training process. The experiment results show that LSTM outperforms GRU in term of the number of successful training. The trained models are able to create unlimited dance moves animation. The quality of the animations is assessed by using visual and dynamic time warping (DTW) method. The DTW method shows that on average, GRU results have 116% greater variance than LSTM’s.
                            
                         
                     
                 
                
                            
                    
                        Modifikasi Fitur dengan Differential Asymmetry untuk Meningkatkan Akurasi Klasifikasi EEG Motor Imagery 
                    
                    Yulianto Tejo Putranto; 
Tri Arief Sardjono; 
Mochamad Hariadi; 
Mauridhi Hery Purnomo                    
                     Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 8 No 1: Februari 2019 
                    
                    Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                    |
                            
                            
                                Full PDF (1090.653 KB)
                            
                                                                    
                    
                        
                            
                            
                                
Brain-Computer Interface (BCI) technology has enabled people with motor disabilities to interact with their environment. The electroencephalograph (EEG) signals related to a motor imagery movement were used as a control signal. In this paper, EEG motor imagery signals from the 2-class data have been processed into features and classified. The power and standard deviation of EEG signals, mean of absolute wavelet coefficients, and the average power of the wavelet coefficients were used as features. The purpose of this paper is to apply the differential asymmetry of these features as new features to improve the system accuracy. As a classifier, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Tree were used. The result shows that for dataset I the use of differential asymmetry as feature can increase the system accuracy up to 47.8%, from 52.20% to 100%, with Tree as a classifier. For dataset II, it can increase accuracy by 8.46%, from 54.42% to 62.48%.
                            
                         
                     
                 
                
                            
                    
                        Crowd evacuation navigation for evasive maneuver of brownian based dynamic obstacles using reciprocal velocity obstacles 
                    
                    Susi Juniastuti; 
Moch Fachri; 
Fresy Nugroho; 
Supeno Mardi Susiki Nugroho; 
Mochamad Hariadi                    
                     Bulletin of Electrical Engineering and Informatics Vol 11, No 4: August 2022 
                    
                    Publisher : Institute of Advanced Engineering and Science 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                                                    
                            | 
                                DOI: 10.11591/eei.v11i4.3806                            
                                            
                    
                        
                            
                            
                                
This paper presents an approach for evasive maneuver against dynamic obstacles in multi-agent navigation in a crowd evacuation scenario. Our proposed approach is based on reciprocal velocity obstacles (RVO) with a different manner to treat the obstacles. We treat all possible hindrances in velocity space reciprocally thus all collision cones generated by other agents and obstacles are treated in the same RVO manner with the key difference in the effort of avoidance. Our approach assumes that dynamic obstacles bear no awareness of navigation space unlike agents thus the avoidance effort lies on behalf of the mobile agents, creating unmutual effort in an evasive maneuver. We display our approach in an evacuation scenario where a crowd of agents must navigate through an evacuation area trespassing zone filled with dynamic obstacles. These dynamic obstacles consist of random motion built based on Brownian motion thus posses an immense challenge for the mobile agent in order to overcome this hindrance and safely navigate to their evacuation area. Our experimentation shows that 51.1% fewer collisions occurred which is denote safer navigation for agents in approaching their evacuation point.
                            
                         
                     
                 
                
                            
                    
                        Inert and mobile agents navigation interaction using reciprocal velocity obstacles for collisions avoidance 
                    
                    Susi Juniastuti; 
Moch Fachri; 
Supeno Mardi Susiki Nugroho; 
Mochamad Hariadi                    
                     Indonesian Journal of Electrical Engineering and Computer Science Vol 26, No 2: May 2022 
                    
                    Publisher : Institute of Advanced Engineering and Science 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                                                    
                            | 
                                DOI: 10.11591/ijeecs.v26.i2.pp1116-1124                            
                                            
                    
                        
                            
                            
                                
Reciprocal velocity obstacles (RVO) is a method used for multiagents navigation that enables collision and oscillation-free avoidance against other mobile agents. Despite its ability in collision avoidance between agents, RVO has a hard time dealing with static obstacle avoidance. This problem has led to a tendency to use RVO only for agents avoidance and use other methods to handle static obstacles avoidance. In this paper, we present our new approach for interaction between mobile agents against static obstacles in the RVO based collision avoidance. We propose a concept called inert agents that interact as static obstacles. This inert agent is stand firm as static obstacles should be, while the inert agent also able to satisfy reactive collision avoidance nature of RVO to produce better avoidance result. We conduct an experiment to compare the performance of avoidance in a certain scenario. Our method shows better results when compared with generic static obstacles.
                            
                         
                     
                 
                
                            
                    
                        KOORDINASI NONPLAYER CHARACTER FOLLOWER MENGGUNAKAN ALGORITMA POTENTIAL FIELDS BERBASIS MULTIBEHAVIOUR 
                    
                    Latius Hermawan; 
Mochamad Hariadi; 
Ruri Suko Basuki                    
                     Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 13 No 1 (2017): Jurnal Teknologi Informasi CyberKU Vol. 13, no 1 
                    
                    Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                    |
                            
                            
                                Full PDF (656.045 KB)
                            
                                                                    
                    
                        
                            
                            
                                
Games have become popular among the people, as a form of entertainment, social support interaction between them . NPC behavior modeling is an important issue in realizing the intelligence of computer games . In NPC team - mate, AI needed to help regulate the behavior of team - mate who played alongside or under the command of a human player to assist players in achieving the goal. Potential fields is described as the iron particles are moving towards the object through the magnetic field created by the target object . This movement depends on the existing magnetic field , the particles will be drawn towards the goal , or just the opposite of the iron particles will be rejected by the magnetic field at the time met an obstacle . In this study , the data obtained by reading the references relating to the title to find out the problems faced in coordinating the team in the game . From the study , analyzed the needs of the games that will be made to the AI model that will be used for team coordination . Only then designed a game that can resolve the issue . After the game was made , the game will be tested by several methods , so it will look the difference . The expected outcome of this study is to model the NPC behavior Follower and adjust the position of the player in accordance with the AI have been made . So players will not quickly lose the game and can finish coordinate with the NPC Follower followed by adjusting the movement of NPC Follower to the players during the attacks , NPC Follower still within range radius of the player to protect the player
                            
                         
                     
                 
                
                            
                    
                        PERILAKU SMART NPC BERBASIS KOORDINASI MULTI AGENT MENGGUNAKAN FUZZY COORDINATOR 
                    
                    Tri Daryatni; 
Mochamad Hariadi; 
Ahmad Zainul Fanani                    
                     Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 12 No 1 (2016): Jurnal Teknologi Informasi CyberKU Vol. 12, no 1 
                    
                    Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro 
                    
                         Show Abstract
                        | 
                             Download Original
                        
                        | 
                            
                                Original Source
                            
                        
                        | 
                            
                                Check in Google Scholar
                            
                        
                                                    |
                            
                            
                                Full PDF (390.73 KB)
                            
                                                                    
                    
                        
                            
                            
                                
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.
                            
                         
                     
                 
                
                            
                    
                        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)
                            
                                                                    
                    
                        
                            
                            
                                
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