Št. zadetkov: 113
Izvirni znanstveni članek
Oznake:
prevoz tovora;kontejnerski transport;napovedovanje transportnih zahtev;razporejanje;umetna inteligenca;strojno učenje;intermodalni transport;freight demand forecasting;container transportation demand forecasting;vertical federated learning;privacy-preserving methods;sample and feature selection;machine learning;homomorphic encryption;resource allocation and scheduling;
In response to the growing demand for accurate freight forecasting in sea-rail intermodal transportation, particularly under the constraints of stringent data protection regulations, we introduce a privacy-preserving, AI-based framework that focuses on the micro-level identification of container tra ...
Leto:
2025
Vir:
Digitalna knjižnica Univerze v Mariboru (DKUM)
Izvirni znanstveni članek
Oznake:
bulk cargo terminal;scheduling;optimisation;Markov decision process (MDP) model;deep reinforcement learning;prioritised experience replay and softmax strategy-based dueling;double deep Q-network;
The cornerstone of port production operations is ship handling, necessitating judicious allocation of diverse production resources to enhance the efficiency of loading and unloading operations. This paper introduces an optimisation method based on deep reinforcement learning to schedule berths and y ...
Leto:
2023
Vir:
Digitalna knjižnica Univerze v Mariboru (DKUM)
Izvirni znanstveni članek
Oznake:
distribution;vehicle routing;optimization;path optimization;end-of-line;large-scale neighbourhood search algorithm;
Logistics is an important guarantee for economic and social development. Among the various aspects of logistics, the urban logistics end distribution link, which involves the direct connection between distribution personnel and customers, has a direct impact on customers' sense of experience and sat ...
Leto:
2022
Vir:
Digitalna knjižnica Univerze v Mariboru (DKUM)
Izvirni znanstveni članek
Oznake:
transportation;last mile;Adaptive Large Neighborhood Search (ALNS);market demand;logistics;distribution;optimization;heuristic algorithms;
Based on the current situation and problems of transportation "last mile" transportation distribution, this paper establishes a path optimization model based on user distribution methods from the perspective of market preference for transportation distribution methods, designs an Adaptive Large Neig ...
Leto:
2022
Vir:
Digitalna knjižnica Univerze v Mariboru (DKUM)
Izvirni znanstveni članek
Oznake:
backfill;centrifugal simulation;osmotic pressure;mechanical properties;
Leto:
2025
Vir:
Inštitut za kovinske materiale in tehnologije (IMT)
Video in druga učna gradiva
Oznake:
computer science;artificial intelligence
Planning as satisfiability is a principal approach to planning
with many eminent advantages. The existing planning
as satisfiability techniques usually use encodings
compiled from the STRIPS formalism. We introduce a
novel SAT encoding scheme based on the SAS+ formalism.
It exploits the structural i ...
Leto:
2010
Vir:
videolectures.net
Video in druga učna gradiva
Oznake:
computer science;machine learning;markov processes
Leto:
2008
Vir:
videolectures.net
Video in druga učna gradiva
Oznake:
computer science;machine learning
Permutations arise in a variety of real-world problems, such as voting, ranking, and data association. Representing uncertainty over permutations, however, is difficult since there are n! permutations, and unlike many problems, they cannot be represented effectively by graphical models due to the mu ...
Leto:
2008
Vir:
videolectures.net
Video in druga učna gradiva
Oznake:
computer science;machine learning
In this paper we introduce our attempts to incorporate the participant role information in multiparty meetings for document modeling using the hierarchical Dirichlet process. The
perplexity and automatic speech recognition results demonstrate that the participant role information is a promising pri ...
Leto:
2008
Vir:
videolectures.net
Video in druga učna gradiva
Oznake:
computer science;machine learning;statistical learning
This paper investigates a new learning formulation called structured sparsity, which is a natural extension of the standard sparsity
concept in statistical learning and compressive sensing. By allowing arbitrary structures on the feature set,this concept generalizes the
group sparsity idea. A gene ...
Leto:
2009
Vir:
videolectures.net