Computing and Informatics (E-Journal - Institute of Informatics, SAS, Bratislava)
Not a member yet
1506 research outputs found
Sort by
LDA-Based Topic Strength Analysis
Get PDFTopic strength is an important hotspot in topic research. The evolution of topic strength not only indicates emerging new topics, but also helps us to determine whether a topic will produce some fluctuation of topic strength over time. Thus, topic strength analysis can provide significant findings in public opinion monitoring and user personalization. In this paper, we present an LDA-based topic strength analysis approach. We take topic quality into our topic strength consideration by combining local LDA and global LDA. For empirical studies, we use three data sets in real applications: film critic data of "A Chinese Odyssey" in Douban Movies, corruption news data in Sina News, and public paper data. Compared to existing approaches, experimental results show that our proposed approach can obtain better results of topic strength analysis in detecting the time of event topic occurrences and distinguishing different types of topics, and it can be used to monitor the occurrences of public opinions and the changes of public concerns
Heuristic Algorithms for Energy and Performance Dynamic Optimization in Cloud Computing
Get PDFCloud computing becomes increasingly popular for hosting all kinds of applications not only due to their ability to support dynamic provisioning of virtualized resources to handle workload fluctuations but also because of the usage based on pricing. This results in the adoption of data centers which store, process and present the data in a seamless, efficient and easy way. Furthermore, it also consumes an enormous amount of electrical energy, then leads to high using cost and carbon dioxide emission. Therefore, we need a Green computing solution that can not only minimize the using costs and reduce the environment impact but also improve the performance. Dynamic consolidation of Virtual Machines (VMs), using live migration of the VMs and switching idle servers to sleep mode or shutdown, optimizes the energy consumption. We propose an adaptive underloading detection method of hosts, VMs migration selecting method and heuristic algorithm for dynamic consolidation of VMs based on the analysis of the historical data. Through extensive simulation based on random data and real workload data, we show that our method and algorithm observably reduce energy consumption and allow the system to meet the Service Level Agreements (SLAs)
Adaptive Aggregation of Flow Records
Get PDFThis paper explores the problem of processing the immense volume of measurement data arising during network traffic monitoring. Due to the ever-increasing demands of current networks, observing accurate information about every single flow is virtually infeasible. In many cases the existing methods for the reduction of flow records are still not sufficient enough. Since the accurate knowledge of flows termed as "heavy-hitters" suffices to fulfill most of the monitoring purposes, we decided to aggregate the flow records pertaining to non-heavy-hitters. However, due to the ever-changing nature of traffic, their identification is a challenge. To overcome this challenge, our proposed approach - the adaptive aggregation of flow records - automatically adjusts its operation to the actual traffic load and to the monitoring requirements. Preliminary experiments in existing network topologies showed that adaptive aggregation efficiently reduces the number of flow records, while a significant proportion of traffic details is preserved
Regularized Surface and Point Landmarks Based Efficient Non-Rigid Medical Image Registration
Get PDFMedical image registration is one of the fundamental tasks in medical image processing. It has various applications in field of image guided surgery (IGS) and computer assisted diagnosis (CAD). A set of non-linear methods have been already developed for inter-subject and intra-subject 3D medical image registration. However, efficient registration in terms of accuracy and speed is one of the most demanded of today surgical navigation (SN) systems. This paper is a result of a series of experiments which utilizes Fast Radial Basis Function (RBF) technique to register one or more medical images non-rigidly. Initially, a set of curves are extracted using a combined watershed and active contours algorithm and then tiled and converted to a regular surface using a global parameterization algorithm. It is shown that the registration accuracy improves when higher number of salient features (i.e. anatomical point landmarks and surfaces) are used and it also has no impact on the speed of the algorithm. The results show that the target registration error is less than 2 mm and has sub-second performance on intra-subject registration of MR image real datasets. It is observed that the Fast RBF algorithm is relatively insensitive to the increasing number of point landmarks used as compared with the competing feature based algorithms
Sentiment and Authority Analysis in Conversational Content
Get PDFThis paper deals with mining conversational content from the social media. It focused on two issues: opinion and emotion classification and identification of authoritative reviewers. The paper also describes applications representing the results obtained in the given areas. Authority identification can be used by organizations to search for experts in their specific areas to employ them. The opinion and emotion analysis can be useful for providing decision-making support
Parallel Tiled Code Generation with Loop Permutation within Tiles
Get PDFAn approach of generation of tiled code with an arbitrary order of loops within tiles is presented. It is based on the transitive closure of the program dependence graph and derived via a combination of the Polyhedral and Iteration Space Slicing frameworks. The approach is explained by means of a working example. Details of an implementation of the approach in the TRACO compiler are outlined. Increasing tiled program performance due to loop permutation within tiles is illustrated on real-life programs from the NAS Parallel Benchmark suite. An analysis of speed-up and scalability of parallel tiled code with loop permutation is presented
EXTRA: EXpertise-Boosted Model for Trust-Based Recommendation System Based on Supervised Random Walk
Get PDFThe quality of recommendations based on any class of recommender systems may become poor if no or low quality data has been provided by users. This is a situation known as it Cold Start problem, which typically happens when a new user registers to the system and no preference data is available for that user. Trust-Aware Recommendation Systems can be considered as a solution for the cold start problem. In these systems, the trust between users plays an import role for making recommendations. However, most of the Trust-Aware RSs consider trust as a context independent phenomenon which means if user a trusts user b to the degree k then user a trusts user b to the degree k in all the concepts. However, in reality, trust is context dependent and user a can trust user b in context X but not in Y. Moreover, most of the trust-aware RSs do not consider an expertise concept for users and all the users are considered as same in the recommendation process. In this paper we proposed a novel approach for detecting expert users just based on their ratings (unlike previous systems which consider the separate profile and extra information for each user to find an expert). In this model a supervised random walk is exploited to search the trust network for finding experts. Empirical experiments on the Epinions dataset shows that EXTRA can outperform previous models in terms of accuracy and coverage
Meta-Programming and Policy-Based Design as a Technique of Architecting Modular and Efficient DSP Algorithm Implementations
Get PDFMeta-programming paradigm and policy-based design are less known programming techniques in Digital Signal Processing (DSP) community, used to coding in pure C or assembly language. Major software components, like C++ STL, have proven usefulness of such paradigms in providing top performance of highly optimised native code, along with abstraction and modularity necessary in complex software projects. This paper describes composition of DSP code using these techniques, bringing as an example implementation of Feedback Delay Network (FDN) artificial reverberation algorithm. The proposed approach was proven to be practical, especially in case of prototyping computationally intense algorithms. To provide further performance insight, we discuss the techniques in context of other optimisation methods, like Single Instruction Multiple Data (SIMD) instruction sets usage and exploitation of superscalar architecture capabilities
Use of Self-Healing Techniques for Highly-Available Distributed Monitoring
Get PDFThe paper addresses the self-healing aspects of the monitoring systems. Nowadays, when the complex distributed systems are concerned, the monitoring system should become "intelligent" - as the first step it can guide the user what should be monitored. The next level of the "intelligence" can be described by the term "self-healing". The goal is to provide the capability that a decision made automatically by the monitoring system should force the system under monitoring to behave more stable, reliable and predictable. In the paper a new monitoring system is presented: AgeMon is an agent based, distributed monitoring system with strictly defined roles which can be performed by the agents. In the paper we discuss self-healing in the context of monitoring. When the self-healing of the monitoring system is concerned, a good example is the case where it is possible to lose the monitoring data due to the storage problems. AgeMon can handle such problems and automatically elects substitute persistence agents to store the data
Granular Partition and Concept Lattice Division Based on Quotient Space
Get PDFIn this paper, we investigate the relationship between the concept lattice and quotient space by granularity. A new framework of knowledge representation - granular quotient space - is constructed and it demonstrates that concept lattice classing is linked to quotient space. The covering of the formal context is firstly given based on this granule, then the granular concept lattice model and its construction are discussed on the sub-context which is formed by the granular classification set. We analyze knowledge reduction and give the description of granular entropy techniques, including some novel formulas. Lastly, a concept lattice constructing algorithm is proposed based on multi-granular feature selection in quotient space. Examples and experiments show that the algorithm can obtain a minimal reduct and is much more efficient than classical incremental concept formation methods