Moch. Hariadi
Teknik Elektro Institut Teknologi Sepuluh November Surabaya, Indonesia

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

RANCANG BANGUN RESPON DUA AGEN OTONOM DALAM AUGMENTED REALITY MENGGUNAKAN METODE LOGIKA FUZZY Widinugroho, Dani; Hariadi, Moch.
Semantik Vol 1, No 1 (2011): Prosiding Semantik 2011
Publisher : Semantik

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (820.735 KB)

Abstract

Perkembangan penelitian kecerdasan buatan dapat dimanfaatkan untuk melakukan penelitian mengenai kecerdasan dalam permainan termasuk dalam augmented reality (AR). Respon dua agen otonom akan disimulasikan dengan menggunakan pendekatan metode logika fuzzy. Penelitian ini tentang bagaimana membangun respon dua agen otonom sehingga mampu merespon gerakan satu dengan lainnya menggunakan logika fuzzy. Dalam penelitian ini akan ditetapkan dua perilaku agen otonom. Pertama adalah perilaku mengejar yang diterapkan pada agen pertama. Dan kedua adalah perilaku menghindar yang akan diterapkan pada agen kedua.Untuk membangun respon kedua agen otonom menggunakan logika fuzzy metode Mamdani. Agen pertama mempunyai dua variabel input yaitu jarak dan kekuatan sertasatu output berupa ketangkasan agen pertama. Didapat 9 aturan fuzzy untuk agen pertama dengan harapan keberhasilan 0,9 %. Agen kedua mempunyai dua variabel input yaitu ketangkasan agen pertama dan kewaspadaan agen kedua, serta satu output berupa ketangkasan agen kedua ketika menghindari agen pertama. Didapat 6 aturan fuzzy untuk agen kedua dengan kemungkinan keberhasilan 0,6%.Kata kunci : agen otonom, respon agen, logika fuzzy, augmented reality (AR).
ADAPTIVE THRESHOLD UNTUK ALPHA MATTING MENGGUNAKAN ALGORITMA OTSU Basuki, R. Suko; Hariadi, Moch.
Semantik Vol 2, No 1 (2012): Prosiding Semantik 2012
Publisher : Semantik

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (250.371 KB)

Abstract

Image matting merupakan proses ekstraksi objek foreground dari keseluruhan image. Hal ini memainkan peranan penting dalam proses image editing. Dalam paper ini algoritma Otsu digunakan untuk menghasilkan nilai threshold yang selanjutnya diberikan sebagai nilai alpha dalam “pulling matte”. Hasil objek foreground yang dipisahkan selanjutnya diukur kualitasnya dengan menggunakan MSE (Mean Squared Error). Proses pengukuran dilakukan dengan mencari perbedaan diantara objek foreground yang terdapat pada image masukan dengan objek foreground hasil matting.Kata kunci : Adaptive Threshold, Alpha Matting, Otsu
Segmentation of Moving Objects Based on Minkowski Distance Using K-means Clustering Hariadi, Moch.; Mulyanto, Eko; Purnomo, Mauridhi H.; Soeleman, Moch Arief
Kursor In Press Vol 8 no 3
Publisher : University of Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v0i0.1241

Abstract

Segmentation of moving objects is one of the challenging research areas for video surveillance application. The success of object changing position for segmentation is when the moving object completely separate the foreground from its background of frame. It depends on many factors, including the use of suitable clustering method to differentiate the pixels of the foreground and background. This paper propose to use k-means as clustering method for moving object segmentation. The method is evaluated on several distance measures. Several steps are performed to conduct the moving object segmentation, such as frame subtraction, median filtering, and noise removal. These steps are proposed to improve the achievement of moving object segmentation. The performance are evaluated by using Mean of Square Error and Peak Signal to Noise Error. The value of both measurement are 135.02 and 25.52. The experimental result shows that the moving object segmentation performs the best result on Minkowski distance.
IDENTIFIKASI SINYAL ELEKTRODE ENCHEPALO GRAPH UNTUK MENGGERAKKAN KURSOR MENGGUNAKAN TEKNIK SAMPLING DAN JARINGAN SYARAF TIRUAN Hariadi, Moch.; Purnomo, Mauridhi Hery; -, Hindarto
Kursor Vol 6, No 3 (2012)
Publisher : University of Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v6i1.101

Abstract

This paper describe the application of backpropagation neural networks as classification and sampling technique (ST) for the extraction of features from the signal wave Electro Encephalo Graph (EEG). This research aims to develop a system that can recognize the EEG signal that is used to move the cursor. The data used is the EEG data which is IIIA dataset of BCI competition III (BCI Competition III 2003). This data contains data from three subjects: K3b, K6b and L1b. In this study, EEG signal data separated by the imagination of movement to the left, right, leg movements and tongue movements. Decision making has been carried out in two stages. In the first stage, TS is used to extract features from EEG signal data. This feature is as basic inputs in back propagation neural networks as a process of learning. This research used Back Propagation (20-20-10-5-1) and 90 data files EEG signal for the training process. During the identification process into four classes of EEG signal data files data files plus 60 into 150 EEG signal so that the EEG signal data file. The results obtained for the classification of these signals is 80% of the 150 files examined data signal to the process of mapping.
ANIMASI GERAKAN EXAGGERATION PUKULAN TINJU BERBASIS PENDEKATAN KURVA BEZIER Primasetya, Aidil; Sumpeno, Surya; Hariadi, Moch.
SENTIA 2015 Vol 7, No 2 (2015)
Publisher : SENTIA 2015

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (664.384 KB)

Abstract

Pukulan dapat digunakan sebagai objek gerak yang ditangkap dengan motion capture (mocap). Gerakan tersebut banyak di temukan pada olahraga tinju. Data mocap berisi informasi titik-titik koordinat yang mewakili rangka manusia. Titik-titik koordinat tersebut ketika disusun berdasarkan perubahan waktu akan membentuk lintasan gerakan. Exaggeration merupakan salah satu prinsip animasi 2D yang melebih-lebihkan gerakan atau ekspresi wajah. Prinsip ini tidak dapat secara langsung diaplikasikan ke dalam animasi 3D berbasis mocap. Karena membutuhkan pengambilan data yang berulang-ulang. Pada penelitian ini, data mocap dimodifikasi dengan menggunakan rotasi matriks. Modifikasi ini menghasilkan data mocap baru. Animasi gerakan pada data tersebut terlihat  exaggeration  dan  tidak  alami.  Untuk  mengembalikan  kealamian  gerakan  tersebut  maka  digunakan metode  interpolasi  yaitu  kurva  linear  bezier  dan  kurva  kuadratik  bezier.  Hasil  percobaan  menunjukkan perbedaan lintasan gerakan pada animasi gerakan exaggeration pukulan tinju menggunakan matriks rotasi yang diinterpolasi dengan kurva linear bezier dan kurva quadratik bezier.
APLIKASI MODIFIED IMPROVED PARTICLE SWARM OPTIMIZATION (MPSO) UNTUK SKENARIO DINAMIK PADA GAME MATEMATIKA ., Minarto; N, Supeno Mardi S.; Hariadi, Moch.
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2012
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Dalam sebuah game sangat penting untuk menjaga player untuk tidak bosan, salah satu cara untuk itu adalah membuat skenario yang sesuai dengan kemampuan player. Jika terlalu sulit maka player akan cenderung malas dan bila terlalu mudah player akan menjadi bosan dan kurang tertantang. Sehingga diperlukan Skenario yang dinamis dan bisa menyesuaikan dengan kemampuan player dan munculnya bisa secara acak. Software WinGen versi 3 (Han & Hambleton, 2010) akan digunakan untuk menjadi generator bilangan acak untuk kemunculan soal dengan memberikan variasi pada pemilihan skenario yang dibuat untuk mensimulasikan skenario secara dinamik (dalam kasus ini, yang dibuat pada skenario Game Kantin untuk pembelajaran matematika ). Particle Swarm Optimization (PSO) yang dimodifikasi digunakan untuk mengoptimasi klastering terhadap soal dengan memperhitungkan nilai terbaik dari semua data, untuk pengacakan soal yang diharapkan muncul. Pada skenario yang berbentuk soal Jika di uji dengan nilai parameter c1=3 dan c2=1,maka kecenderungan soal yang muncul adalah soal mudah, sedangkan jika nilai c1=5 dan c2=1, kecenderungan soal yang muncul adalah soal sedang dan untuk nilai c1=7 dan c2=1, kecenderungan soal yang muncul adalah soal sulit.
ARTIFICIAL INTELLIGENCE BERBASIS PENGETAHUAN PEMAIN UNTUK REAL TIME TACTIC GAME MENGGUNAKAN KNOWLEDGE BASED ARTIFICIAL NEURAL NETWORKS Ibad, Muhammad Rofiul; Hariadi, Moch.
Sains & Matematika Vol 1, No 1 (2012): Oktober, Sains & Matematika
Publisher : Sains & Matematika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Solution for the complexity problem of Artificial Intelligence (AI) on Real Time Tactic (RTT) game as one of the real-world simulation game requiresefective control system.Control system is in the form of a representative agent as a human player in anticipating the changes of the game states. In this thesis, control agent is built by applying a Knowledge Based System (KBS) based on the knowledge base related to human player action for goal achievement of the game. The construction of KBS inference is divided into two phases, which isdetermination of the case inlinguistic format of human players from the numerical values of complex states in the game, and selection of the appropriate tactic when a series of cases occur.Existanceof knowledge that is not deterministic as the basis of the inference process, requires adaptability of the agent through weighting system of knowledge and learning. KBS is mapped to Knowledge Base Artificial Neural Networks (KBANN) using certainty factor (CF) based back propagation as learning method. Inference is limited to the process of achieving main goal through controlling of attack and defense. The design of AI system is implemented in RTT Game ?The Cursed? through the shared interfaces of SPRING AI Game Engine. Testing against other static AI shows the ability of adaptation to changes in circumstances and improved quality control of the game by 0.017745641. These results fit expectations of human players who expect an improvement of playing quality in each session through the selection of appropriate goal achievement action. 
Artificial Intelligence Berbasis Pengetahuan Pemain untuk Real Time Tactic Game Menggunakan Knowledge Based Artificial Neural Networks Ibad, Muhammad Rofiul; Hariadi, Moch.
Sains & Matematika Vol 1, No 1 (2012): Oktober, Sains & Matematika
Publisher : Sains & Matematika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Solution for the complexity problem of Artificial Intelligence (AI) on Real Time Tactic (RTT) game as one of the real-world simulation game requiresefective control system.Control system is in the form of a representative agent as a human player in anticipating the changes of the game states. In this thesis, control agent is built by applying a Knowledge Based System (KBS) based on the knowledge base related to human player action for goal achievement of the game. The construction of KBS inference is divided into two phases, which isdetermination of the case inlinguistic format of human players from the numerical values of complex states in the game, and selection of the appropriate tactic when a series of cases occur.Existanceof knowledge that is not deterministic as the basis of the inference process, requires adaptability of the agent through weighting system of knowledge and learning. KBS is mapped to Knowledge Base Artificial Neural Networks (KBANN) using certainty factor (CF) based back propagation as learning method. Inference is limited to the process of achieving main goal through controlling of attack and defense. The design of AI system is implemented in RTT Game “The Cursed” through the shared interfaces of SPRING AI Game Engine. Testing against other static AI shows the ability of adaptation to changes in circumstances and improved quality control of the game by 0.017745641. These results fit expectations of human players who expect an improvement of playing quality in each session through the selection of appropriate goal achievement action.