Diana Purwitasari

Batik Motif Classification Using Color-Texture-Based Feature Extraction and Backpropagation Neural Network

Batik is an Indonesians traditional cloth which has been recognized as one of the world cultural heritage. Currently, there are hundreds of different batik motif which can be classified into 7 groups, i.e. Parang, Ceplok, Lereng, Megamendung, Semen, Lunglungan, and Buketan. This research develops a software to automatically identify motifs of batik image using color-texture-based feature extraction and backpropagation neural network. Color and texture features of batik image is extracted using combination of Color Co-occurence Matrix, Different Between Pixels of Scan Pattern, and Color Histogram for K-Means methods. The extracted features vectors are furthermore classified into motifs using Backpropagation Neural Network. The experiment shows that the software can recognize batik motifs quite well, with rate of Tanimoto Distance 0,37.

Pencarian Question-Answer Menggunakan Convolutional Neural Network Pada Topik Agama Berbahasa Indonesia

Community-based question answering (CQA) is formed to help people who search information that they need through a community. One condition that may occurs in CQA is when people cannot obtain the information that they need, thus they will post a new question. This condition can cause CQA archive increased because of duplicated questions. Therefore, it becomes important problems to find semantically similar questions from CQA archive towards a new question. In this study, we use convolutional neural network methods for semantic modeling of sentence to obtain words that they represent the content of documents and new question. The result for the process of finding the same question semantically to a new question (query) from the question-answer documents archive using the convolutional neural network method, obtained the mean average precision value is 0,422. Whereas by using vector space model, as a comparison, obtained mean average precision value is 0,282. Index Terms—community-based question answering, convolutional neural network, question retrieval

Keynote Speaker II: Biomedical Engineering Research in the Social Network Analysis Era: Stance Classification for Analysis of Hoax Medical News in Social Media

Abstract Biomedical engineering research trend can be healthcare models with unobtrusive smart systems for monitoring vital signs and physical activity. Detecting infant facial cry because of inability to communicate pain, recognizing facial emotion to understand dysfunction mechanisms through micro expression or transform captured human expression with motion device into three-dimensional objects are some of the applied systems. Nowadays, collaborated with biomedical research, mining and analyzing social network can improve public and private health care sectors as well such as research health news shared on social media about pharmaceutical drugs, pandemics, or viral outbreaks. Due to the vast amount of shared news, there is an urgency to select and filter information to prevent the spread of hoax or fake news. We explored in depth some steps to classify hoaxes written as news articles. This discussion also encourages on how technologies of social network analysis could be used to make new kinds improvement in health care sectors. Then close with a description of limitless future possibilities of biomedical engineering research in social media.

Feature extraction using statistical moments of wavelet transform for iris recognition

Iris is unique for each person, so that it can be used as one alternative solution for human identification. In this study, an iris recognition system is developed to automatically identify a person by using eye image data. Firstly, iris area of eye image is detected using Canny Edge Detection and Hough Transform methods. Secondly, texture feature of iris image is extracted using statistical moments of Wavelet Transform. Furthermore, the texture feature representation is recognized using Support Vector Machine classifier method. Experiment on CASIA eye image dataset gives good recognition rate, that is 93.5%.

K-medoids algorithm on Indonesian Twitter feeds for clustering trending issue as important terms in news summarization

News summary could be a solution for information access need. However, it is challenging because of the number of news is growth rapidly. The information integration of several news has some difficulties because sentences that compose news summary could be come from various issues. Short text or Twitter Feeds called tweets could be used to recognize those issues. More weight value are given to the issue terms. Hence, the issue terms will exists within the news summary. This paper focuses on the usage of K-Medoids algorithm for tweet clustering. The data in this study is Twitter feeds in Indonesian. The result experiment shows the effect of re-tweet occurrences and also its influence in the summary result.