Search

Big data is growing fast following Big data has the characteristics of high volume, speed, and variety (3v) and continues to grow exponentially following the development of the world's use of information and communication technology. The main problem with big data is the data deluge. The need for technology and large data storage and processing methods to keep pace with the exponential data growth rate is potentially limitless, giving rise to the problem of exponentially increasing technology requirements as well. The weakness of previous big data analysis approaches (batch and online real time processing) is that it requires high technology (large storage, memory and processing). This paper proposes a new approach in big-data analysis by separating the basic knowledge (BK) construction process from original data with a much smaller volume (volume reduction), then analyzing it into final knowledge, thus requiring smaller/simpler analysis technology. The proposals include formulating the definition and representation of BK, developing methods for constructing BK from source data, and analyzing BK into final knowledge. We propose a BK construction method based on a knowledge extraction technique using BIRCH clustering algorithm for instance reduction, and handling high-dimensional problems by parallelizing the dimension calculation process to calculate the distance between instances. We use the Adjusted Rand Index (ARI) to measure the similarity of the final knowledge of the baseline and proposed methods. First, the BIRCH baseline was modified by parallelizing the calculations has succeeded in increasing speed from 17% to 25%. Next, the parallel BIRCH (PBIRCH) baseline was broken into BK construction and BK analysis, has succeeded in reducing volume by 96% or more and increasing speed by 43.50%, with similar final knowledge results (ARI=1). Based on these results, we conclude that the BK construction method and analysis from BK into final knowledge for highdimensional big data have significantly reduced volume and speed up the analytical process without reducing the quality of the final knowledge. [ABSTRACT FROM AUTHOR]

Application of the recommender system on the online platform turns out to produce a large volume of data and at an unexpected rate, making it more realistic to study the recommender system under streaming settings. Many studies have tried to develop a streaming recommender system, one of which is Stream-centered Probabilistic Matrix Factorization (SPMF). In SPMF, model will be updated continuously every time a data stream window enters the system using the data managed in reservoir plus the data in data stream window. This study focuses on developing a reservoir sampling technique in SPMF method, namely uniform random sampling, which can result in model ranking errors due to the loss of observational data from memory. To reduce this consequence, sample is selected based on the matrix factorization score, which is considered to represent the popularity of item. In addition, this research also developed a parallelization technique for the updating of the SPMF algorithm for the purpose of increasing scalability. Based on the experiments conducted on E-commerce dataset, the proposed method is proven to have better recommendation quality than the baseline method and reaches at least 84% quality of BPR-MF with a reduction of the dataset up to 78% and computation time 60 times faster. Parallel computing can also increase computation speed by 23% by using 4 workers. [ABSTRACT FROM AUTHOR]

Ontology alignment is a collection of correspondences or mappings between entities from two ontologies being matched. Alignment is an essential data resource that used as a reference to build interlinking on Linked Data. Since it is produced by an ontology matching system, the good quality of alignment determines the good performance of the ontology matching system. The coherence of alignment is one of the success criteria of the ontology matching system so that some systems implement the alignment repair feature in it. This feature restores the incoherent to coherent by removing some mappings in alignment. Research of alignment incoherence stated that the repair process should have a minimum impact on alignment by minimizing the number of removed mappings and/or minimizing the confidence value of removed mappings. The study discussed in this paper is alignment repair to restore coherent conditions with two minimization focus of diagnosis. In a repair system, the process of finding and removing a mapping to produce conflict-free alignment is called the diagnosis. We have been proven that conflict-free alignment is coherent alignment. The proposed repair system implements a dynamic weighting heuristic to guide the search for minimum removed mapping with two minimization focus, in order to produce conflict-free alignment. Experiment on 8 alignments shows that the current system which removes more mapping will produce conflict-free alignment, but does not support minimal impact. Conversely, the current system that removes minimal mapping does not support conflict-free alignment. The proposed system excels at producing conflict-free alignment with minimal impact. [ABSTRACT FROM AUTHOR]

Most trajectory pattern mining techniques assume that the data to be analyzed contain complete and evenly distributed spatial and temporal information. However in reality, collected data may contain noise, missing or incomplete information, and uneven spatial resolution. In trajectory pattern mining methods, trajectory patterns are extracted by splitting spatial workspace into uniformly tiny sized squares, followed by determining popular cells which contain many data points. Finally, a sequential pattern mining technique, e.g. MiSTA, is used to extract trajectory pattern. This research proposes non-uniform partitioning to handle uneven spatial distribution as modification towards the uniform spatial workspace division process. The proposed approach, named multistage spatial partitioning is developed based on point-region quadtree concept. The new partitioning method is conducted for preprocessing before applying MiSTA. As the result, using multistage spatial partition, MiSTA succeeds in uncovering more detailed and broader coverage patterns compared to uniform partitioning approach through a series of experiments. [ABSTRACT FROM AUTHOR]

The development of electronic media in the world, such as e-learning, communication through the internet, and information system automation, is growing very fast. While the media is mostly developed for people without disability, a question about how this electronic media being used and utilized by people with disability still remains. People with disability, either mentally or physically, with either single (deaf, blind) or multiple handicapped (mentally deaf, mentally blind) have special needs in order to let them work/utilize this electronic media. A proposed model of integrating a multiple-handicapped person information management system has been developed [1]. The former focuses on managing all management aspects of rehabilitation, dormitory, school and workshop such that the activity and the improvement of multiple handicapped individual record can be monitored easily. It emerges some interested point about how this EMHaS Information System being prepare to implement. While these disabled person who have specific characteristics and behaviors became part of the user and they have some difficulties to use the normal electronic devices some preparation activities have taken place. In this paper we discuss on how Enterprise Architecture Planning (EAP) methodology can support the Multiple Handicapped Education Information System development has taken place. Furthermore another study on how Individual Education Program (IEP) in Multiple Handicapped Education Information System can be applied is also explored. The paper also describe a particular design of man-computer interface for improving disabled persons mental and physical ability. A prototype of handicapped interface device has been designed and implemented in rehabilitation institute Bale Endah, Jawa Barat. As a case study the education EMHaS model has been developed based on the Indonesia Multiple Handicapped environment which is run by Bhakti Mitra Utama Foundation (BMUF). It is expected that this integrated information system could helps caregivers and managers to manage and monitor disabled persons daily activity in the school and dormitory area more easily and more comprehensively. Another expectation that this result could be count as one system that is really suitable to implement not only in this multiple handicapped foundation (BMUF) but also in all such multipled handicapped foundation or institutes in Indonesia. [ABSTRACT FROM AUTHOR]