| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju


1 - 10 / 31
Na začetekNa prejšnjo stran1234Na naslednjo stranNa konec
Sustainable operations of last mile logistics based on machine learning processes
Jerko Oršič, Borut Jereb, Matevž Obrecht, 2022, izvirni znanstveni članek

Opis: The last-mile logistics is regarded as one of the least efficient, most expensive, and polluting part of the entire supply chain and has a significant impact and consequences on sustainable delivery operations. The leading business model in e-commerce called Attended Home Delivery is the most expensive and demanding when a short delivery window is mutually agreed upon with the customer, decreasing possible optimizing flexibility. On the other hand, last-mile logistics is changing as decisions should be made in real time. This paper is focused on the proposed solution of sustainability opportunities in Attended Home Delivery, where we use a new approach to achieve more sustainable deliveries with machine learning forecasts based on real-time data, different dynamic route planning algorithms, tracking logistics events, fleet capacities and other relevant data. The developed model proposes to influence customers to choose a more sustainable delivery time window with important sustainability benefits based on machine learning to predict accurate time windows with real-time data influence. At the same time, better utilization of vehicles, less congestion, and fewer failures at home delivery are achieved. More sustainable routes are selected in the preplanning process due to predicted traffic or other circumstances. Increasing time slots from 2 to 4 h makes it possible to improve travel distance by about 5.5% and decrease cost by 11% if we assume that only 20% of customers agree to larger time slots.
Ključne besede: supply chain management, real-time, home delivery, business modeling, e-commerce, time window
Objavljeno v DKUM: 19.02.2024; Ogledov: 148; Prenosov: 19
.pdf Celotno besedilo (1,54 MB)
Gradivo ima več datotek! Več...

Orchestrating Digital Wallets for On- and Off-Chain Decentralized Identity Management
Vid Keršič, Urban Vidovic, Andraz Vrecko, Martin Domajnko, Muhamed Turkanović, 2023, izvirni znanstveni članek

Opis: Digital identity is becoming one of the core elements during the digitalization age, when more and more processes and interactions are taking place in the digital sphere. Therefore, current identity management approaches will define how these interactions will look in the future, but different fields and communities often approach management with their own solutions and tools, despite their similarities. This includes decentralized digital identities, where the identity is managed with asymmetric cryptographic keys, and no centralized entity oversees the whole identity system. This paper focuses on managing on- and off-chain decentralized digital identities, with the former being used for blockchain networks and the latter for self-sovereignty and privacy. While both types of decentralized identity build on the same cryptographic and identity primitives, there is no single wallet that handles both. Therefore, this paper proposes an orchestration solution for both wallet types, which enables their convergence to a single universal wallet and validates it with a real-life decentralized identity use case.
Ključne besede: blockchain networks, current identity management approaches, decentralized digital identities, digital identity, digital sphere, digitalization age, on-and-off-chain decentralized identity management, orchestrating digital wallets, real-life decentralized identity, same cryptographic identity
Objavljeno v DKUM: 06.12.2023; Ogledov: 326; Prenosov: 17
.pdf Celotno besedilo (3,25 MB)
Gradivo ima več datotek! Več...

Estimation of real driving emissions based on data from OBD
Matej Fike, Andrej Predin, 2022, objavljeni povzetek znanstvenega prispevka na konferenci

Ključne besede: vehicle, diesel engine, exhaust emission levels, real driving emissions
Objavljeno v DKUM: 30.10.2023; Ogledov: 295; Prenosov: 5
.pdf Celotno besedilo (14,78 MB)
Gradivo ima več datotek! Več...

Scoping review on the multimodal classification of depression and experimental study on existing multimodal models
Umut Arioz, Urška Smrke, Nejc Plohl, Izidor Mlakar, 2022, pregledni znanstveni članek

Opis: Depression is a prevalent comorbidity in patients with severe physical disorders, such as cancer, stroke, and coronary diseases. Although it can significantly impact the course of the primary disease, the signs of depression are often underestimated and overlooked. The aim of this paper was to review algorithms for the automatic, uniform, and multimodal classification of signs of depression from human conversations and to evaluate their accuracy. For the scoping review, the PRISMA guidelines for scoping reviews were followed. In the scoping review, the search yielded 1095 papers, out of which 20 papers (8.26%) included more than two modalities, and 3 of those papers provided codes. Within the scope of this review, supported vector machine (SVM), random forest (RF), and long short-term memory network (LSTM; with gated and non-gated recurrent units) models, as well as different combinations of features, were identified as the most widely researched techniques. We tested the models using the DAIC-WOZ dataset (original training dataset) and using the SymptomMedia dataset to further assess their reliability and dependency on the nature of the training datasets. The best performance was obtained by the LSTM with gated recurrent units (F1-score of 0.64 for the DAIC-WOZ dataset). However, with a drop to an F1-score of 0.56 for the SymptomMedia dataset, the method also appears to be the most data-dependent.
Ključne besede: multimodal depression classification, scoping review, real-world data, mental health
Objavljeno v DKUM: 11.08.2023; Ogledov: 421; Prenosov: 44
.pdf Celotno besedilo (1,43 MB)
Gradivo ima več datotek! Več...

Provisional security of creditors in cross-border civil and commercial matters
Neža Pogorelčnik Vogrinc, 2020, izvirni znanstveni članek

Opis: Provisional measures can be of utmost importance to creditors especially in relationships with a cross-border element. The Regulation 1215/2012 is the legal source that provides rules regarding the jurisdiction to issue a provisional measure but also offers imperfect provisions regarding the recognition and enforcement of foreign provisional measures issued in other Member States of the European Union. Due to the inadequate regulation, CJEU case law has played an important role, but nevertheless the article finds and opens new questions that have not yet been answered.
Ključne besede: Regulation 44/2001, Regulation 1215/2012, provisional measure, jurisdiction, recognition, enforcement, arbitration clause, real connecting link
Objavljeno v DKUM: 15.01.2021; Ogledov: 731; Prenosov: 0

Notaries' escrow services in selling real estate in the Republic of Slovenia
Bojan Podgoršek, 2020, izvirni znanstveni članek

Opis: Notary's escrow is a legal relationship between the notary and the parties to the underlying legal transaction, which is generally a sales agreement. Notary's escrow is regulated with mandatory statutory rules commissioning public notaries and the rules of the mandate agreement. Mutual obligations of the parties to the underlying legal transaction in and of themselves do not influence the notary's obligations under a notary's escrow agreement unless they are included in the notary's escrow agreement as a constituent part thereof. Slovenian legislation stipulates the general conditions of notaries' operations. However, it does not stipulate specific conditions that must be fulfilled in order to place documents, funds and securities into escrow with a notary, nor does it stipulate the mandatory component elements of the escrow order. Therefore, The Slovenian regulation of notary's escrow should be supplemented.
Ključne besede: escrow services, notaries' escrow services, notary escrow of funds, notary escrow of documents, selling real estate, conditions of notary's escrow, risk of non-performance, legitimate interest for notary escrow
Objavljeno v DKUM: 15.01.2021; Ogledov: 873; Prenosov: 0

Simulations of VoIP applications in INET framework
Sebastijan Horvatić, 2017, magistrsko delo

Opis: This master's thesis describes the support for modelling Voice over Internet Protocol (VoIP) applications in the INET Framework. First, it briefly presents the VoIP technology and factors responsible for the VoIP quality of service. Next, the thesis moves on to discuss the OMNeT++ environment and the INET Framework, their installation and usage. Following this, it examines all of the INET packages and modules available for VoIP modelling, with all VoIP-related INET examples then shortly described and tested. By using INET, our own network and application models are created and simulated using different parameters. Comparisons of the simulation results are carried out and some of the best-found parameters for the VoIP communications are presented. At last, the calculation of jitter by using the obtained simulation results and Excel program is described, because jitter is not shown in the simulation results in INET.
Ključne besede: voice over internet protocol, performance analysis, simulation, real-time transport protocol, user datagram protocol
Objavljeno v DKUM: 18.08.2017; Ogledov: 1463; Prenosov: 135
.pdf Celotno besedilo (3,86 MB)

Re-examination of the purchasing power parity in Central and Eastern European economies
Ahmad Zubaidi Baharumshah, Jani Bekő, Darja Boršič, 2011, objavljeni znanstveni prispevek na konferenci

Opis: The empirical record on PPP tests for transition economies is far from being so opulent as it is for the developed market economies. This paper attempts to fill this gap by scrutinizing the theory of PPP on a sample of Central and Eastern European economies. The paper has two main advances with respect to previous PPP studies. First, it employs a monthly data base on real exchange rates for a panel of 12 Central and Eastern European economies by testing the theory separately with respect to US dollar and with respect to Euro. Second, we utilise a panel unit root test that involves the estimation of the ADF regression in a SUR framework. Since our study found support for the validity of PPP in some reforming European economies, special attention should be devoted to individual country-specific factors that cause PPP deviations.
Ključne besede: purchasing power parity, real exchange rates, stationarity test, exchange rate, currency, exchange rates, macroeconomics, parity, purchasing power of money, purchasing power
Objavljeno v DKUM: 21.07.2017; Ogledov: 1284; Prenosov: 170
.pdf Celotno besedilo (256,38 KB)
Gradivo ima več datotek! Več...

Maximal neighbor similarity reveals real communities in networks
Krista Rizman Žalik, 2015, izvirni znanstveni članek

Opis: An important problem in the analysis of network data is the detection of groups of densely interconnected nodes also called modules or communities. Community structure reveals functions and organizations of networks. Currently used algorithms for community detection in large-scale realworld networks are computationally expensive or require a priori information such as the number or sizes of communities or are not able to give the same resulting partition in multiple runs. In this paper we investigate a simple and fast algorithm that uses the network structure alone and requires neither optimization of pre-defined objective function nor information about number of communities. We propose a bottom up community detection algorithm in which starting from communities consisting of adjacent pairs of nodes and their maximal similar neighbors we find real communities. We show that the overall advantage of the proposed algorithm compared to the other community detection algorithms is its simple nature, low computational cost and its very high accuracy in detection communities of different sizes also in networks with blurred modularity structure consisting of poorly separated communities. All communities identified by the proposed method for facebook network and E-Coli transcriptional regulatory network have strong structural and functional coherence.
Ključne besede: networks, real communities, neighbor similarity
Objavljeno v DKUM: 23.06.2017; Ogledov: 1075; Prenosov: 380
.pdf Celotno besedilo (2,21 MB)
Gradivo ima več datotek! Več...

Iskanje izvedeno v 16.72 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici