Yustinus Eko Soelistio

Yustinus Eko Soelistio

Albeit many HCI / emotion recognition studies use facial expressive images, few scrutinize the accuracies of the people (experimenters and participants) in perceiving the expressions representing the intended emotions. The misinterpretation of the expression will put bias in the data and introduce questions on the validity of the studies. The possibility of misinterpretation of the expressions will be the focus of the experiment conducted in this study. The experiment will evaluate the ability of people in taking the perspective of others in spite of their current emotions and gender, and whether the expressions can be universally perceived. This study find that it is relatively safe to use facial expressive images for research as long as the emotions are exclusively within the six basic emotions.

Richard Adiguna, Yustinus Eko Soelistio

Although many studies suggest high performance hand detection methods, those methods are likely to be overfitting. Fortunately, the Convolution Neural Network (CNN) based approach provides a better way that is less sensitive to translation and hand poses. However the CNN approach is complex and can increase computational time, which at the end reduce its effectiveness on a system where the speed is essential.In this study we propose a shallow CNN network which is fast, and insensitive to translation and hand poses. It is tested on two different domains of hand datasets, and performs in relatively comparable performance and faster than the other state-of-the-art hand CNN-based hand detection method. Our evaluation shows that the proposed shallow CNN network performs at 93.9% accuracy and reaches much faster speed than its competitors.

Novita Belinda Wunarso, Yustinus Eko Soelistio

Even though speech-emotion recognition (SER) has been receiving much attention as research topic, there are still some disputes about which vocal features can identify certain emotion. Emotion expression is also known to be differed according to the cultural backgrounds that make it important to study SER specific to the culture where the language belongs to. Furthermore, only a few studies addresses the SER in Indonesian which what this study attempts to explore. In this study, we extract simple features from 3420 voice data gathered from 38 participants. The features are compared by means of linear mixed effect model which shows that people who are in emotional and non-emotional state can be differentiated by their speech duration. Using SVM and speech duration as input feature, we achieve 76.84% average accuracy in classifying emotional and non-emotional speech.

Elvyna Tunggawan, Yustinus Eko Soelistio

This paper describes a Naive-Bayesian predictive model for 2016 U.S. Presidential Election based on Twitter data. We use 33,708 tweets gathered since December 16, 2015 until February 29, 2016. We introduce a simpler data preprocessing method to label the data and train the model. The model achieves 95.8% accuracy on 10-fold cross validation and predicts Ted Cruz and Bernie Sanders as Republican and Democratic nominee respectively. It achieves a comparable result to those in its competitor methods.

Yustinus Eko Soelistio, Martinus Raditia Sigit Surendra

Text mining can be applied to many fields. One of the application is using text mining in digital newspaper to do politic sentiment analysis. In this paper sentiment analysis is applied to get information from digital news articles about its positive or negative sentiment regarding particular politician. This paper suggests a simple model to analyze digital newspaper sentiment polarity using naive Bayes classifier method. The model uses a set of initial data to begin with which will be updated when new information appears. The model showed promising result when tested and can be implemented to some other sentiment analysis problems.

Ardy Wibowo Haryanto, Adhi Kusnadi, Yustinus Eko Soelistio

Warehouse is one of the important aspects of a company. Therefore, it is necessary to improve Warehouse Management System (WMS) to have a simple function that can determine the layout of the storage goods. In this paper we propose an improved warehouse layout method based on ant colony algorithm and backtracking algorithm. The method works on two steps. First, it generates a solutions parameter tree from backtracking algorithm. Then second, it deducts the solutions parameter by using a combination of ant colony algorithm and backtracking algorithm. This method was tested by measuring the time needed to build the tree and to fill up the space using two scenarios. The method needs 0.294 to 33.15 seconds to construct the tree and 3.23 seconds (best case) to 61.41 minutes (worst case) to fill up the warehouse. This method is proved to be an attractive alternative solution for warehouse layout system.

Yustinus Eko Soelistio, Eric Postma, Alfons Maes

We propose an improved eye center localization method based on the Hough transform, called Circle-based Eye Center Localization (CECL) that is simple, robust, and achieves accuracy on a par with typically more complex state-of-the-art methods. The CECL method relies on color and shape cues that distinguish the iris from other facial structures. The accuracy of the CECL method is demonstrated through a comparison with 15 state-of-the-art eye center localization methods against five error thresholds, as reported in the literature. The CECL method achieved an accuracy of 80.8% to 99.4% and ranked first for 2 of the 5 thresholds. It is concluded that the CECL method offers an attractive alternative to existing methods for automatic eye center localization.