Search results for "Algoritmi"

Modeling and Mitigating Errors in Belief Propagation for Distributed Detection

2021

We study the behavior of the belief-propagation (BP) algorithm affected by erroneous data exchange in a wireless sensor network (WSN). The WSN conducts a distributed multidimensional hypothesis test over binary random variables. The joint statistical behavior of the sensor observations is modeled by a Markov random field whose parameters are used to build the BP messages exchanged between the sensing nodes. Through linearization of the BP message-update rule, we analyze the behavior of the resulting erroneous decision variables and derive closed-form relationships that describe the impact of stochastic errors on the performance of the BP algorithm. We then develop a decentralized distribute…

Algorithmic issues in computational intelligence optimization: from design to implementation, from implementation to design

2016

The vertiginous technological growth of the last decades has generated a variety of powerful and complex systems. By embedding within modern hardware devices sophisticated software, they allow the solution of complicated tasks. As side effect, the availability of these heterogeneous technologies results into new difficult optimization problems to be faced by researchers in the field. In order to overcome the most common algorithmic issues, occurring in such a variety of possible scenarios, this research has gone through cherry-picked case-studies. A first research study moved from implementation to design considerations. Implementation limitations, such as memory constraints and real-time r…

Informācijas burbuļu nozīme studentu informacionālajā telpā

2021

Bakalaura darbs par informācijas burbuļa nozīmi studentu informacionālajā telpā tika izstrādāts, lai noskaidrotu, kā informācijas burbuļi ietekmē studentu informacionālo telpu, un meklētu iemeslus, kāpēc ir tik vienkārši ieslīgt filtru burbulī. Svarīgs pētījuma jautājums uz, kuru bija jāatrod atbilde bija kādas ir līdzības un atšķirības starp filtru un informācijas burbuļiem. Pētījumā tika izmantotas divas teorijas – sociālā konstruktīvisma un tīmekļa vārtu sargāšanas teorija. Pētījuma rezultātā var secināt, ka informācijas burbulis ir studentu dzīves daļa ar, ko ir jāmācās sadzīvot, un studenti to dara labprāt, bet viņiem ir nepieciešams profesionāļu atbalsts, lai labāk saprastu, kā sadzīv…

Hybrid evolutionary multi-objective optimization with enhanced convergence and diversity

2011

Impact of Artificial Intelligence on Management

2019

This study focuses on the impact of advancing Artificial Intelligence systems on management during the next decade. Much of the attention around Artificial Intelligence and work revolves around the replacement versus augmentation debate. According to previous literature, rather than simply replacing tasks, machine learning tools can complement human decision making. Based on semi-structured expert interviews, this study provides tentative evidence that this may be true for managers on the highest level of organisations, but perhaps less so for operational and middle managers who may find a larger number of their tasks replaced. As routine tasks of supervision and administration can be autom…

Taylorism on steroids or enabling autonomy? A systematic review of algorithmic management

2023

AbstractThe use of algorithmic management systems is rapidly changing organizational models and practices, as millions of workers in multiple sectors worldwide are managed by computer software. Despite receiving increasing academic interest, little summarizing literature exist on the ways algorithmic systems are used in management. This article aims to fill this gap by systematically reviewing and qualitatively analyzing 172 articles on the topic. Our research contributes to the existent algorithmic management literature in three ways. First, we provide a descriptive overview of algorithmic management as a field of research. Second, we identify and synthesize the discussion on the key conce…

Empīriskās ticamības funkcijas izmantošana klasteru analīzē

2019

Bakalaura darbā apskatīta klasteru analīze ar empīriskās ticamības funkciju. Tās rezultāti salīdzināti ar pazīstamāko klasteru analīžu rezultātiem: hierarhisko klasterizāciju, k-vidējo klasterizāciju un uz modeļa balstīto Gausa jaukto modeļu klasterizāciju. Tika aplūkotas klasterizācijas metodes simulētiem un reāliem datu piemēriem, lai novērtētu, kurš algoritms veiksmīgāk veic datu klasterizāciju. Simulēto datu gadījumā Rand indekss rezultātus salīdzina ar sākotnējo datu grupām. Darba mērķis ir noskaidrot, kādas priekšrocības ir klasterizējot datus ar empīriskās ticamības funkciju. Gūtie rezultāti liecina, ka novērojumiem, kuros ir izlēcēji, klasteru analīze ar empīrisko ticamības funkciju…

Knowledge discovery using diffusion maps

2013

Big high-dimensional data analysis with diffusion maps

2013

High-dimensional Big Data processing with dictionary learning and diffusion maps

2015

Algorithms for modern Big Data analysis deal with both massive amount of sam- ples and a large number of features (high-dimension). One way to cope with these challenges is to assume and discover the existence of localization in the data by uncovering its intrinsic geometry. This approach suggests that different data segments can be analyzed separately and then unified in order to gain an understanding of the whole phenomenon. Methods that utilize efficiently local- ized data are attractive for high-dimensional big data analysis, because they can be parallelized, and thus the computational resources, which are needed for their utilization, are realistic and affordable. These methods can explo…