{"title":"Single-output recurrent neural networks for sentence binary classification","authors":"A. Wicaksono, M. Adriani","doi":"10.1109/ICACSIS.2016.7872723","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872723","url":null,"abstract":"We report several experiments on using Recurrent Neural Networks (RNNs) for sentence binary classification task. In terms of sentence classification, RNNs have an important advantage compared to well-known traditional machine learning models (e.g. SVM and Maximum Entropy), in which it can naturally take into account neighboring information between contiguous words. In addition, to perform binary classification task, we employed Single-Output RNNs (SORNNs) which only consists of a single output layer located in the last time step. The output layer itself is a vector consisting of two units (since we perform binary classification), in which each unit corresponds to a single label. Our results showed that SORNN achieved better performance than other traditional machine learning models, such as SVM, Maximum Entropy, and Naive Bayes, which have been widely used for sentence classification.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130221191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Combination of relief feature selection and fuzzy K-nearest neighbor for plant species identification","authors":"A. Ambarwari, Y. Herdiyeni, Taufik Djatna","doi":"10.1109/ICACSIS.2016.7872767","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872767","url":null,"abstract":"Plant species identification is a digitally challenging object for a better classification such as in taxonomy resources problem. Feature selection as a preprocessing technique in data mining help to identify the prominent attributes of herbal leave with higher dimensioned data set. For this purpose, Relief Feature Selection algorithm was utilized for the improvement of Fuzzy K-Nearest Neighbor (Fuzzy K-NN) classification on shape, texture, and margins on the leaves. Best result was obtained on 73.48% of accuracy rate for 363 observation data. The trend of accuracy rate was directly imposed by the number of features. However, most of this combination was better than conventional K-NN alone.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121123984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"DBpedia entities expansion in automatically building dataset for Indonesian NER","authors":"Ika Alfina, R. Manurung, M. I. Fanany","doi":"10.1109/ICACSIS.2016.7872784","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872784","url":null,"abstract":"Named Entity Recognition (NER) plays a significant role in Information Extraction (IE). In English, the NER systems have achieved excellent performance, but for the Indonesian language, the systems still need a lot of improvement. To create a reliable NER system using machine learning approach, a massive dataset to train the classifier is a must. Several studies have proposed methods in automatically building dataset for Indonesian NER using Indonesian Wikipedia articles as the source of the dataset and DBpedia as the reference in determining entity types automatically. The objective of our research is to improve the quality of the automatically tagged dataset. We proposed a new method in using DBpedia as the referenced named entities. We have created some rules in expanding DBpedia entities corpus for category person, place, and organization. The resulting training dataset is trained using Stanford NER tool to build an Indonesian NER classifier. The evaluation shows that our method improves recall significantly but has lower precision compared to the previous research.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123396790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
W. R. Fitriani, A. Putra, Dipta Tanaya, H. N. Rochman, Elin Cahyaningsih, D. I. Sensuse
{"title":"Assessing knowledge management implementation readiness in Faculty of Computer Science, Universitas Indonesia","authors":"W. R. Fitriani, A. Putra, Dipta Tanaya, H. N. Rochman, Elin Cahyaningsih, D. I. Sensuse","doi":"10.1109/ICACSIS.2016.7872743","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872743","url":null,"abstract":"Knowledge is a very important resources in today's modern economy. Therefore managing knowledge is considered as a very crucial organizational capability. This paper attempts to analyze the readiness of knowledge management (KM) in Faculty of Computer Science, Universitas Indonesia. 45 staff of faculty were selected by stratified random sampling for data gathering by questionnaire. Then, one way ANOVA was used to analyze the data. The findings of this study indicates that in organizational culture, IT infrastructure and individual acceptance factors, organization is ready, but need a few improvement to implement KM. The organizational structure factor is not ready, hence it still needs some work to be able to implement KM. Regarding employees' intention to be involved in KM, this study showed that organization is ready, but need a few improvement to implement KM.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115682391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Numerical methods for initialization in fodder composition optimization","authors":"V. N. Wijayaningrum, Fitri Utaminingrum","doi":"10.1109/ICACSIS.2016.7872730","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872730","url":null,"abstract":"Determining the fodder composition is one of the important things to be done in animal raising because it may affect production. The process of determining the fodder composition is difficult to do because there are many things that must be considered at the same time, for example, the necessity to fulfill the nutrient needs while minimizing the total cost of the feed ingredients used. Evolutionary algorithms are often used to optimize the composition of animal feed with a random initial value. In this study, the use of numerical methods such as Cramer's Rule, Gauss-Elimination and Gauss-Jordan method is used as a solution for determining the initial value in evolutionary algorithms. The initial value which calculated using these three methods is the coefficient values that describe the amount of feed ingredients used in mixing fodder. The results showed that Cramer's Rule is better than Gauss-Elimination and Gauss-Jordan method with the difference in value of 7 × 10−13.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127315180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Wearable computing with computer input just by sight for health care","authors":"K. Arai","doi":"10.1109/ICACSIS.2016.7872715","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872715","url":null,"abstract":"Wearable computing with computer input just by sight for health care is proposed. Wearable computing with Input-Output Devices based on Eye-Based Human Computer Interaction: EBHCI which allows location based web services including navigation, location/attitude/health condition monitoring is proposed. Through implementation of the proposed wearable computing system, all the functionality is confirmed. It is also found that the system does work well. It can be used easily and also is not expensive. Experimental results for EBHCI show excellent performance in terms of key-in accuracy as well as input speed. It is accessible to internet, obviously, and has search engine capability. Also, one of the applications of health care, physical and psychological status monitoring is discussed.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121955185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. F. Syafiandini, Ito Wasito, S. Yazid, Aries Fitriawan, Mukhlis Amien
{"title":"Multimodal Deep Boltzmann Machines for feature selection on gene expression data","authors":"A. F. Syafiandini, Ito Wasito, S. Yazid, Aries Fitriawan, Mukhlis Amien","doi":"10.1109/ICACSIS.2016.7872733","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872733","url":null,"abstract":"In this paper, multimodal Deep Boltzmann Machines (DBM) is employed to learn important genes (biomarkers) on gene expression data from human carcinoma colorectal. The learning process involves gene expression data and several patient phenotypes such as lymph node and distant metastasis occurrence. The proposed framework in this paper uses multimodal DBM to train records with metastasis occurrence. Later, the trained model is tested using records with no metastasis occurrence. After that, Mean Squared Error (MSE) is measured from the reconstructed and the original gene expression data. Genes are ranked based on the MSE value. The first gene has the highest MSE value. After that, k-means clustering is performed using various number of genes. Features that give the highest purity index are considered as the important genes. The important genes obtained from the proposed framework and two sample t-test are being compared. From the accuracy of metastasis classification, the proposed framework gives higher results compared to the top genes from two sample t-test.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115159627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The evaluation of information technology governance and the prioritization of process improvement using control objectives for information and related technology version 5: Case study on the ministry of foreign affairs","authors":"E. Erlangga, Y. G. Sucahyo, M. K. Hammi","doi":"10.1109/ICACSIS.2016.7872761","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872761","url":null,"abstract":"According to 2015 Performance Reports, the Ministry of Foreign Affairs' Key Performance Indicator (KPI): Percentage of Information Technology Master Plan Implementation performance falls into the poor category. Through root cause analysis, it is identified that the KPI's poor performance is caused by the evaluation of information technology (IT) governance has never been performed. By performing such evaluation, the organzation's status of IT governance can be determined, and then based on the status constructs the recommendations for improvement. COBIT 5 framework was used in this study as a frame of reference for assessing the capability level of the Ministry of Foreign Affairs' IT governance, prioritizing and constructing the recommendations for process improvement. The assessment of process capability using Process Assessment Model (PAM) generates an average rating of 0.7, where 1 process is at level 2 (managed), 15 processes are at level 1 (performed), and 21 processes are still at level 0 (incomplete). Prioritization using pain points yields 15 prioritized processes for immediate improvement. The recommendations for improvement are constructed using the provided COBIT 5's guidance, in the form of activities and best practices for each IT process.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128951402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Knowledge home","authors":"Ramjee Prasad","doi":"10.1109/icacsis.2016.7872717","DOIUrl":"https://doi.org/10.1109/icacsis.2016.7872717","url":null,"abstract":"A novel concept, termed as Knowledge Home, is introduced in this paper. The Knowledge Home encompasses a virtual Home with the ability of identifying different human senses and feelings and transmitting them through wireless communication technology. Modern communication technologies are helping humankind to achieve a high level of quality of life. Earlier, Human Bond Communication (HBC) was introduced to the community as a new concept of transmitting five humankind senses. This paper proposes to combine the achieved Knowledge from the HBC transmission with the ability of transmission of different human feelings and make a Knowledge Home. The Knowledge Home is a virtual center, where people can communicate with their five senses namely, optic (seeing), auditory (hearing), olfactory (smelling), gustatory (tasting) and tactile (touching) and should be able to transmit their feelings such as optimism, love, submission, awe, disappointment, remorse, contempt and aggression. The output of the Knowledge Home is to have a safe, reliable, pleasant, and conversant environment to live in and to communicate. This idea could advance human kind to the dream place where one has thought of it from the first day of existence.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121014416","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. A. Sari, Sigit Adinugroho, R. V. Ginardi, N. Suciati
{"title":"Enhancing tomato clustering evaluation using color correction with improved linear regression in preprocessing phase","authors":"Y. A. Sari, Sigit Adinugroho, R. V. Ginardi, N. Suciati","doi":"10.1109/ICACSIS.2016.7872731","DOIUrl":"https://doi.org/10.1109/ICACSIS.2016.7872731","url":null,"abstract":"Color inconsistency poses many difficulties when capturing the same object using different image capture devices. Color is one of main parts in image preprocessing and therefore color correction is needed to calibrate images in order to produce consistent color values. In this paper, we propose a new color correction method by employing combined linear regression with stepwise model to enhance the quality of tomatoes ripeness clustering. Macbeth ColorChecker is needed as a reference image while a test image to be corrected is captured by an Android smartphone camera. There are 12 color levels to be compared between reference and test image. However, only a number of color levels are selected by k-means clustering. The selected color levels are utilized to build a linear regression algorithm with stepwise model. The result confirms that color correction and color constancy increase the clustering performance by 10% up to 40% for all possible configurations.","PeriodicalId":267924,"journal":{"name":"2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121205338","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}