The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this letter, we propose an adaptive part-level model knowledge transfer approach for gender classification of facial images based on Fisher vector (FV). Specifically, we first decompose the whole face image into several parts and compute the dense FVs on each face part. An adaptive transfer learning model is then proposed to reduce the discrepancies between the training data and the testing data...
SemEval (Semantic Evaluation) is an annual workshop where attendees participate in a series of evaluations (competitions) of computational semantic analysis for natural language processing (NLP). The series evaluations include 10–20 tasks each year. In this paper we present our entry to the SemEval-2014 Task 7 on the Analysis of Clinical Text evaluation. The main aim of this task is to analyze large...
Performance of an application is a vital issue for user satisfaction. Performance bug refers to a specific kind of bugs that create lags and overheads in application execution. Often, it is difficult to localize and fix performance bugs due to insufficient developer knowledge regarding the characteristics of these bugs. Eliminating performance bugs manually from the application is time consuming and...
According to The Global Burden of Disease conducted by Murray in collaboration with WHO and the World Bank predicts that mental illnesses will occupy the second position after cardiovascular disease in 2020. One of the mental illnesses is Schizophrenia Psychosis disorder. This research uses Artificial Intellegence case-based reasoning (CBR) method for diagnosing types of Schizophrenia disorders. Each...
Self-healing is an interesting topic in SON (Self- Organizing Networks). In this paper, we investigate cell outage detection problem, and propose an improved TCM (Transductive confidence machines) based automatic cell outage detection algorithm. By incorporating a hypothesis test with the Neyman-Pearson criterion to improve the detection accuracy, the improved TCM can effectively detect cell outage...
Nonnegative matrix factorization (NMF)-based speech enhancement algorithm has been proven to provide satisfactory performance when the prior information about speaker and noise types are given. In most real-world scenarios, however, such prior information may not always be accessible. Therefore, an adaptation technique is favorable to adapt the NMF matrices to match the testing condition for a better...
Voice recognition process is started with voice feature extraction using Mel Frequency Cepstrum Coefficient (MFCC). The purpose of the MFCC method is to get the signal feature that correlate to the human voice. The converted signal from analog to digital is needed in the MFCC method. The digital signal has a time domain and it make the analysis harder. So, the domain time is converted to time domain...
One of the factors in a country's economy is the exchange value of the currency towards another currency. The exchange value of Rupiah towards Dollar (USA) can quickly change depending on the environmental conditions and has a huge impact for the Indonesian Government. In this research, Learning Vector Quantization (LVQ) and Unsupervised K Nearest Network (UNN) was implemented in predicting the currency...
Indoor localization remains a hot topic and receives tremendous research efforts during the last few decades. While most previous efforts focus on the designing issue, little effort has been paid to the impact of different environmental parameters on the system performance. To this end, we present an extensive empirical study with real-world experiments to provide sufficient data for analysis. By...
Electricity demand forecasting is a nonlinear and complex problem. It consists of three levels, including long-term forecast for new power plant planning, medium-term forecast for maintenance scheduling and inventory of fuel, and short-term forecast for daily operations. There are many statistical forecasting techniques applied to short term load forecasting, such as Stochastic Time series, Regression...
Applications and middleware in pervasive systems frequently rely on machine learning to provide adaptivity and customization that results in a seamless user experience despite operating in a dynamic environment. Machine learning algorithms have been shown to be vulnerable to covert, strategic attacks through the manipulation of training data. Machine learning algorithms in pervasive systems frequently...
The accuracy of part of speech (POS) tagging reported in medical natural language processing (NLP) literature is typically very high when training and testing data sets are from the same domain and have similar characteristics, but is lower when these differ. This presents a problem for clinical NLP, where it is difficult to obtain large corpora of training data suitable for localized tasks. We experimented...
This paper presents a method to detect and correct anomalies in embedded systems. The proposed method consists of three phases: 1) Training, 2) Anomaly detection, and 3) Anomaly Correction. In the training phase, the method constructs different clusters so that each cluster has a number of similar members, similarity values of the members for a cluster to each others are not less than a predefined...
This paper presents a method to detect and correct anomalies in embedded systems. The proposed method consists of three phases: 1) Training, 2) Anomaly detection, and 3) Anomaly Correction. In the training phase, the method constructs different clusters so that each cluster has a number of similar members, similarity values of the members for a cluster to each others are not less than a predefined...
Forecasting traffic flow is a popular research topic in Intelligent Transportation System. There have been several methods used for this forecasting, such as statistical methods, Bayesian Network, Neural Network Model, Hybrid ARIMA and ANN. Generalized Regression Neural Network (GRNN) is an interesting model to be used in forecasting traffic flow, as it can predict data with dynamic change and non-linear...
The Open Directory Project (ODP) is a large scale, high quality and publicly available web directory. Many studies and real-world applications build on an ODP-based classifier. However, existing approaches use traditional bag-of-words representation of text to develop an ODP-based classifier and words alone do not always provide atomic units of semantic meaning. In this paper, we propose a novel framework...
Data mining rely on large amount of data to make learning model and the quality of data is very important. One of the important problem under data quality is the presence of missing values. Missing values can occur in both at the time of training and at the time of testing. There are many methods proposed to deal with missing values in training data. Many of them resort to imputation techniques. However,...
The amount of studies on classification of human characteristics based on measured individual signals has increased rapidly. In wearable sensors based activity recognition a common policy is to report human independent recognition results using leave-one-person-out cross-validation scheme. This can be a suitable solution when feature or model parameter selection is not needed or it is done outside...
In this study a Software-based Artificial Intelligence (AI) System and Neural Network (NN) System were combined to achieve a highly responsive and a self-learning machine capable in predicting the dispatch time and scheduling of buses in Epifanio Delos Santos Avenue (EDSA) which is a congested road in Metro Manila. The AI system is a software-based program that can learn through data gathering and...
Named Entity Recognition or NER is one of the sub-research field of Information Extraction which can be used for machine translation, question answering, semantic web, etc. One of the biggest challenge of NER is the adversity to construct a manually labeled training data. In this work, we present a semi-supervised approach for Indonesian language NER which is capable of creating high quality training...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.