Surya Sumpeno

Multi attribute decision making model using multi rough set: Case study classification of anger intensity of Javanese woman

Decision-making process typically involves multiple attributes. It is using a part or whole attributes to find the best decision from the alternatives. Some methods such as rough set are used to solve this problem but it has worse time complexity with respect to the numerous attributes. Hence, Multi Rough Set is proposed to improve the performance of rough set. In this study, this method used to classify the anger of Javanese womans which require numerous attributes but has limited number of object. We divided the information table into several groups which has similarity attribute and it is computed simultaneously. The decision of each group as result of rough set and then used fuzzy rule set to obtain the final result. Using leave one out cross validation obtained 79% more accurate than using single rough set for all attribute.

Developing modified PeGI indicators for e-Government Ranking method

e-Government Ranking of Indonesia (Pemeringkatan e-Government Indonesia - PeGI) is conducted in order to determine and evaluate the success of e-Government implementation nationally. However, the parameters that have been used by PeGI in evaluating government offices were too general. Some more detail exploration regarding the parameters for ranking the Government office is necessary to determine the level of PeGI in more detail and objective judgement. Due to that, this research was done to get more details indicators on PeGI ratings that can evaluate the success level of e-Government implementation in government office and also to minimize the improper assessment. In this study, the modified PeGI indicators were developed based on COBIT 5 standard. Questionnaire with detail indicators as a result of PeGI modification was used to re-rank some government offices sample. The result of ranking then being compared with the rank of current PeGI. This study resulted: 164 questions in the modified questionnaire, each on Policy Dimension (8 categories) 39 questions, Institutional Dimension (5 categories) 19 questions, Infrastructure Dimension (7 categories) 44 questions, Application Dimension (5 categories) 41 questions, and Planning Dimension (5 categories) 21 questions. In conclusion, we found that the final result of Modified PeGI ranking for Surabaya City Government was lower compared to normal PeGI ranking. Detail indicators can describe e-Government implementation in a more objective way.

Simulation multi behavior NPCs in fire evacuation using emotional behavior tree

Evacuation procedure in building fire has several points, and the main destination for occupants are going through the exit door of the building safely. In this research we learn how occupants behave with the emotion influence in a building fire. Emotions have important role to affect decision making because it can increase or decrease the rational value and aim at being realistic and naturally. The possibility to make NPCs behave naturally are implement multi behavior and handle all behavior using artificial intelligence (AI) technique. AI architecture have to support variant behavior and easily to reuse for complex character behaviors. Behavior trees (BTs) is the one of many AI techniques that more readable and scalable for action selection mechanism. So, we propose to implement Emotional Behavior Trees (EmoBTs) to handle dynamic behavior scenario that influenced by emotions. We already made the scenario for NPCs, that have emotion to decide which act would be selected. The experiment result compare how each NPCs are going to act by the emotions influence.

Synthesis of virtual character poses using Lagrange polynomial interpolation

In these times, affective virtual characters are often being involved as a major component in creative industries such as computer games and animation. Creating affective characters is not a simple job. One of technique used in creating the characters is the motion capture. Results using this technique are presented in motion capture data and can be processed further for many other functions, including creating variations of affective content. Motion capture data synthesis has been used widely to produce these variations by applying the interpolation method. In this study, Lagrange polynomial interpolation was applied to generate variations in pose.

Multi-Attribute Clustering of Student's Entrepreneurial Potential Mapping Based on Its Characteristics and the Affecting Factors: Preliminary Study on Indonesian Higher Education Database

Indonesian governments efforts to improve the growth of scientific-based young entrepreneurs from universities require the support of information in the form of entrepreneurial potential students. The clustering of entrepreneurial potential aims to classify student data based on their diverse characteristic. However, the problem is that the entrepreneurial potential of students is affected by many factors, where each factor has varied characteristics, both in terms of its value and weight. Regarding these affecting factors, Simple Multi-Attribute Rating Technique (SMART) is proposed as a solution to simplify the assessment of entrepreneurial potential per criteria. Therefore, the clustering process to the dataset has the concept of multi clustering attribute. The experimental results show that the multi-attribute clustering with the K-Means algorithm has better performance than normal clustering. It can decrease the value of Sum of Squared Errors (SSE) significantly by 90% and reduce the number of iterations by 30% so that the time in building model reduce by 1% and decrease the value of Incorrectly Cluster Instance (ICI) by 3%. Based on visualization, multi-attribute clustering results are also easier to interpret.

Gamification wisata di Museum Mpu Tantular berbasis Augmented Reality

Museum sebagai sumber informasi peradaban dan kebudayaan telah menyajikan informasi terkait koleksi benda museum. Namun penyajian informasi yang tersedia cenderung diabaikan karena kurangnya minat pengunjung untuk menge-tahui informasi terkait koleksi benda museum. Akibatnya adalah pengetahuan pengunjung terkait koleksi Museum Mpu Tantular tidak bertambah. Pada tugas akhir ini dibangun suatu media yang dapat berinteraksi dua arah sehingga informasi tersebut dapat tersampaikan dengan baik dan penyajian informasi terkait koleksi Museum Mpu Tantular lebih menarik dan interaktif. Hasil yang diperoleh adalah aplikasi permainan tour museum dengan memanfaatkan penerapan teknologi augmented reality pada gamification sehingga pengunjung terpacu untuk men-cari informasi terkait koleksi Museum Mpu Tantular. Sete-lah melakukan pengujian didapatkan hasil survei dari seluruh responden yang menyatakan bahwa aplikasi permainan tour museum dapat menambah pengetahuan terkait koleksi Museum Mpu Tantular. Dibuktikan oleh rata-rata jawaban benar yang mengalami kenaikan sebesar 27,87% dari sebelum dan sesudah mencoba aplikasi ini.

Real-time video quality assessment based on fuzzy inference system for analog television tracking antenna system

Real-Time VQA (Video Quality Assessment) is very important for the tracking antenna system on an analog television in the decision making related to the direction of the antenna. This paper proposes VQA system based on FIS (Fuzzy Inference System) that works in real-time to process information from analog signals on AV-Out television. The VQA system can be said to work well if the output results show that the perception of the system is almost close to the perception of the user in assessing the video clarity level. In this research, simulation is performed using MATLAB Toolbox and then implemented by using AVR AT Mega 32 A microcontroller. Result of trial shows that there is no significant difference between simulation and implementation with percentage difference of only 1.74%. Other trial results prove that the perception of VQA system that has been built almost approach the users perception in assessing the video clarity level. This is evident from the percentage of accuracy on VQA system that reaches 79% to 95%.

Background subtraction using spatial mixture of Gaussian model with dynamic shadow filtering

Many applications of computer vision, motion captures nowadays are an active research field. Supported by camera innovation in high definition technology and high-speed processing unit technology make higher degree on object detection standard. We can see it from the increasing number of new methods that have improvement in accuracy. In automatic vehicle surveillance area, Spatial Mixture Gaussian model becomes well-known moving based object detection via background subtraction technique in this decades. This method models particular pixel as mixture of Gaussians distribution with regard to pixels higher probability of occurrences and variance of each Gaussians in the mixture model. Although, this model has threshold to control the sensitivity of objects motion, it has problem with separating an object from its shadow. This is happening because the shadow attaches to the object. Since they always move in tandem, as the result, detected object area will merge and shadow and object will form into a single unity that is difficult to separate. In accordance with detection, occluded object because of a shadow will decrease detectors accuracy. Therefore, we need to remove shadow, in order to maintain detectors quality of accuracy. Challenge in doing so is there is exist dynamic illumination condition which resulting a nonuniform shadow pixel value. This can cause failure of threshold-based linear shadow casting technique. To solve above-mentioned problem, we need a shadow filter that can adapt to the illumination changes. In this experiment, we have successfully implemented an adaptive shadow filter based on DSD algorithm to improve background subtraction method. Our proposed method has a stable result in outdoor environment dataset and it is proven to be able applied to traffic surveillance video application.

Affective human pose classification from optical motion capture

In the animation movie production, there is a common tool namely motion capture (mocap) to capture the motion of actors. Using this technology, reconstruction of actors motion is being mapped to drive 3D character in the animation. In the reconstruction process of human motion, there were some significant parameters that affect the quality of the result such as subtle motion and high precision reconstruction. In order to get the best result, it requires some configurations such as camera disposition, camera configuration, and marker arrangement that should be placed in the proper position. Furthermore, after the capturing process, the result needs to be repaired due to misplaced or unable to define some markers. The result of this research is a Human Motion Database (HMDB), consist of poses which express basic emotion based on database from The Bodily Expressive Action Stimulus Test (BEAST). Basic emotions are anger, fear, happiness and sadness. The database result evaluated by conducting classification and validation of the data affective poses. Pose data is represented by rotation value of each joint in the skeleton. This value classified using machine learning to predict each pose to emotion classes. Classification result of the affective pose has the highest accuration score was fear class. Respectively the accuracy of class fear, anger, happiness and sadness are 96.87%, 95.62%, 94.37%, and 94.37%/

Establishment of Indonesian viseme sequences using hidden Markov model based on affection

Every language has different characteristics, one of which is how to pronounce the language. Pronunciation accompanied by emotional expression are increasingly making different characteristics. This research proposes the establishment of natural Indonesian viseme order influenced by the expression of emotion. This system converts the text input of an Indonesian sentence into a sequence Indonesian viseme to be influenced by the affection. Animation of mouth shape and lip movements are made to complement the visualization of natural speech, which is resulted from the establishment Indonesian viseme model. The method used in the natural Indonesian viseme sequence, is using statistical approach through Viterbi algorithm Hidden Markov Model.