Dunja Mladenić

Dunja Mladenić
Jožef Stefan Institute | IJS

About

415
Publications
105,603
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,352
Citations

Publications

Publications (415)
Preprint
We propose using a two-layered deployment of machine learning models to prevent adversarial attacks. The first layer determines whether the data was tampered, while the second layer solves a domain-specific problem. We explore three sets of features and three dataset variations to train machine learning models. Our results show clustering algorithm...
Preprint
In this research, we develop machine learning models to predict future sensor readings of a waste-to-fuel plant, which would enable proactive control of the plant's operations. We developed models that predict sensor readings for 30 and 60 minutes into the future. The models were trained using historical data, and predictions were made based on sen...
Preprint
Quality control is a crucial activity performed by manufacturing enterprises to ensure that their products meet quality standards and avoid potential damage to the brand's reputation. The decreased cost of sensors and connectivity enabled increasing digitalization of manufacturing. In addition, artificial intelligence enables higher degrees of auto...
Preprint
This paper presents an Artificial Intelligence approach to mining context and emotions related to olfactory cultural heritage narratives, in particular to fairy tales. We provide an overview of the role of smell and emotions in literature, as well as highlight the importance of olfactory experience and emotions from psychology and linguistic perspe...
Article
Full-text available
This paper presents an Artificial Intelligence approach to mining context and emotions related to olfactory cultural heritage narratives, particularly to fairy tales. We provide an overview of the role of smell and emotions in literature, as well as highlight the importance of olfactory experience and emotions from psychology and linguistic perspec...
Article
Full-text available
The cultural heritage domain in general and silk textiles, in particular, are characterized by large, rich and heterogeneous data sets. Silk heritage vocabulary comes from multiple sources that have been mixed up across time and space. This has led to the use of different terminology in specialized organizations in order to describe their artefacts...
Article
Full-text available
Artificial intelligence models are increasingly used in manufacturing to inform decision making. Responsible decision making requires accurate forecasts and an understanding of the models’ behavior. Furthermore, the insights into the models’ rationale can be enriched with domain knowledge. This research builds explanations considering feature ranki...
Preprint
Full-text available
Artificial Intelligence models are increasingly used in manufacturing to inform decision-making. Responsible decision-making requires accurate forecasts and an understanding of the models' behavior. Furthermore, the insights into models' rationale can be enriched with domain knowledge. This research builds explanations considering feature rankings...
Article
Full-text available
Modern cross-lingual document retrieval models are capable of finding documents relevant to the query. However, they do not have the capabilities for explaining why the document is relevant. This paper proposes a novel learning-to-rank model named LM-EMD that uses the multilingual BERT language model and Earth Mover’s Distance (EMD) to measure the...
Article
Full-text available
News reporting, on events that occur in our society, can have different styles and structures, as well as different dynamics of news spreading over time. News publishers have the potential to spread their news and reach out to a large number of readers worldwide. In this paper we would like to understand how well they are doing it and which kind of...
Article
The purpose of this study is to analyse COVID-19 related news published across different geographical places, in order to gain insights in reporting differences. The COVID-19 pandemic had a major outbreak in January 2020 and was followed by different preventive measures, lockdown, and finally by the process of vaccination. To date, more comprehensi...
Article
Quality control is a crucial activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria. The decreased cost of sensors and connectivity enabled an increasing digitalization of manufacturing and pr...
Article
Full-text available
Refineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predic...
Article
Full-text available
This research work describes an architecture for building a system that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in a manufacturing demand forecasting use case and can be extended to other domains. In addition, the system provides the means for knowle...
Article
Full-text available
Actionable Cognitive Twins are the next generation Digital Twins enhanced with cognitive capabilities through a knowledge graph and artificial intelligence models that provide insights and decision-making options to the users. The knowledge graph describes the domain-specific knowledge regarding entities and interrelationships related to a manufact...
Preprint
Full-text available
The cultural heritage domain in general and silk textiles, in particular, are characterized by large, rich and heterogeneous data sets. Silk heritage vocabulary comes from multiple sources that have been mixed up across time and space. This has led to the use of different terminology in specialized organizations in order to describe their artefacts...
Article
The paper proposes a novel architecture for explainable artificial intelligence based on semantic technologies and artificial intelligence. We tailor the architecture for the domain of demand forecasting and validate it on a real-world case study. The explanations provided result from knowledge fusion regarding concepts describing features relevant...
Preprint
Full-text available
Refineries execute a series of interlinked processes, where the product of one unit serves as the input to another process. Potential failures within these processes affect the quality of the end products, operational efficiency, and revenue of the entire refinery. In this context, implementation of a real-time cognitive module, referring to predic...
Preprint
Full-text available
Quality control is a key activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria. The decreased cost of sensors and connectivity enabled an increasing digitalization of manufacturing and provid...
Article
Full-text available
In this work we study how company co-occurrence in news events can be used to discover business links between them. We develop a methodology that is able to process raw textual data, embed it into a numerical form, and extract a meaningful network of connections. Each news event is considered as a node on the graph and we define the similarity betw...
Article
Full-text available
While increasing empirical evidence suggests that global time series forecasting models can achieve better forecasting performance than local ones, there is a research void regarding when and why the global models fail to provide a good forecast. This paper uses anomaly detection algorithms and explainable artificial intelligence (XAI) to answer wh...
Preprint
Full-text available
This research work describes an architecture for building a system that guide a user from a forecast generated by a machine learning model through a sequence of decision-making steps. The system is demonstrated in manufacturing demand forecasting use case and can be extended to other domains. In addition, the system provides means for knowledge acq...
Preprint
Full-text available
Since the start of the COVID-19 pandemic, much research has been published highlighting how artificial intelligence models can be used to diagnose a COVID-19 infection based on medical images. Given the scarcity of published images, heterogeneous sources, formats, and labels, generative models can be a promising solution for data augmentation. We p...
Preprint
Full-text available
Quality control is a key activity performed by manufacturing enterprises to ensure products meet quality standards and avoid potential damage to the brand's reputation. The decreased cost of sensors and connectivity enabled an increasing digitalization of manufacturing. In addition, artificial intelligence enables higher degrees of automation, redu...
Chapter
There is a lack of a single architecture specification that addresses the needs of trusted and secure Artificial Intelligence systems with humans in the loop, such as human-centered manufacturing systems at the core of the evolution towards Industry 5.0. To realize this, we propose an architecture that integrates forecasts, Explainable Artificial I...
Chapter
Smart assistants in manufacturing can guide and aid on decision-making while also provide means to collect additional insights and information available to the users. A general approach for building a smart assistant that provides users with machine learning forecasts and a sequence of decision-making options is presented in this work. The system p...
Preprint
Full-text available
While increasing empirical evidence suggests that global time series forecasting models can achieve better forecasting performance than local ones, there is a research void regarding when and why the global models fail to provide a good forecast. This paper uses anomaly detection algorithms and Explainable Artificial Intelligence (XAI) to answer wh...
Article
Full-text available
Demand forecasting is a crucial component of demand management, directly impacting manufacturing companies’ planning, revenues, and actors through the supply chain. We evaluate 21 baseline, statistical, and machine learning algorithms to forecast smooth and erratic demand on a real-world use case scenario. The products’ data were obtained from a Eu...
Preprint
Full-text available
The increasing digitalization of the manufacturing domain requires adequate knowledge modeling to capture relevant information. Ontologies and Knowledge Graphs provide means to model and relate a wide range of concepts, problems, and configurations. Both can be used to generate new knowledge through deductive inference and identify missing knowledg...
Preprint
Full-text available
The implementation of Artificial Intelligence (AI) systems in the manufacturing domain enables higher production efficiency, outstanding performance, and safer operations, leveraging powerful tools such as deep learning and reinforcement learning techniques. Despite the high accuracy of these models, they are mostly considered black boxes: they are...
Chapter
Full-text available
The increasing adoption of artificial intelligence requires accurate forecasts and means to understand the reasoning of artificial intelligence models behind such a forecast. Explainable Artificial Intelligence (XAI) aims to provide cues for why a model issued a certain prediction. Such cues are of utmost importance to decision-making since they pr...
Chapter
Time is now and now is the time. Digitalization is spreading in our work and daily life. To take the best out of digitalization, we should be ready to use it consciously to shape our tomorrow. We are looking to understand the opportunities and challenges of the digital transformation and predict at least some of the consequences. Here we focus main...
Conference Paper
Full-text available
The increasing adoption of artificial intelligence requires accurate forecasts and means to understand the reasoning of artificial intelligence models behind such a forecast. Explainable Artificial Intelligence (XAI) aims to provide cues for why a model issued a certain prediction. Such cues are of utmost importance to decision-making since they pr...
Preprint
Full-text available
The increasing adoption of artificial intelligence requires accurate forecasts and means to understand the reasoning of artificial intelligence models behind such a forecast. Explainable Artificial Intelligence (XAI) aims to provide cues for why a model issued a certain prediction. Such cues are of utmost importance to decision-making since they pr...
Preprint
Full-text available
There is a lack of a single architecture specification that addresses the needs of trusted and secure Artificial Intelligence systems with humans in the loop, such as human-centered manufacturing systems at the core of the evolution towards Industry 5.0. To realize this, we propose an architecture that integrates forecasts, Explainable Artificial I...
Preprint
Full-text available
The paper proposes a novel architecture for explainable AI based on semantic technologies and AI. We tailor the architecture for the domain of demand forecasting and validate it on a real-world case study. The provided explanations combine concepts describing features relevant to a particular forecast, related media events, and metadata regarding e...
Preprint
Full-text available
A general approach for building a smart assistant that guides a user from a forecast generated by a machine learning model through a sequence of decision-making steps is presented. We develop a methodology to build such a system. The system is demonstrated on a demand forecasting use case in manufacturing. The methodology can be extended to several...
Preprint
Full-text available
Actionable Cognitive Twins are the next generation Digital Twins enhanced with cognitive capabilities through a knowledge graph and artificial intelligence models that provide insights and decision-making options to the users. The knowledge graph describes the domain-specific knowledge regarding entities and interrelationships related to a manufact...
Preprint
Full-text available
Demand forecasting is a crucial component of demand management. While shortening the forecasting horizon allows for more recent data and less uncertainty, this frequently means lower data aggregation levels and a more significant data sparsity. Sparse demand data usually results in lumpy or intermittent demand patterns, which have sparse and irregu...
Article
Motivation In the age of big data, the amount of scientific information available online dwarfs the ability of current tools to support researchers in locating and securing access to the necessary materials. Well-structured open data and the smart systems that make the appropriate use of it are invaluable and can help health researchers and profess...
Book
The 5-volume proceedings, LNAI 12457 until 12461 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2020, which was held during September 14-18, 2020. The conference was planned to take place in Ghent, Belgium, but had to change to an online format due to the COVID-19...
Book
The 5-volume proceedings, LNAI 12457 until 12461 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2020, which was held during September 14-18, 2020. The conference was planned to take place in Ghent, Belgium, but had to change to an online format due to the COVID-19...
Conference Paper
In recent years, a great amount of research has been done in predictive modeling in the domain of healthcare. Such research is facilitated by the existence of various biomedical vocabularies and standards which play a crucial role in understanding healthcare information. In addition, the Unified Medical Language System (UMLS) links together biomedi...
Article
Full-text available
The documentation, dissemination, and enhancement of Cultural Heritage is of great relevance. To that end, technological tools and interactive solutions (e.g., 3D models) have become increasingly popular. Historical silk fabrics are nearly flat objects, very fragile and with complex internal geometries, related to different weaving techniques and t...
Conference Paper
Full-text available
The availability of open educational resources is growing at an increasingly fast pace since its first promotion by UNESCO in 2002. Today, large variability of opportunities for free and online educational resources are available and accessible by everyone from all around the world who has access to the Internet. An Internet user may exploit number...
Poster
Full-text available
We present results of collaborative work bringing together semantic technologies, machine learning and cultural heritage to enable advanced search and visualization of textual descriptions of museum artifacts related to silk fabrics. Proposed is a multilingual txt analysis approach where the developed domain-specific multilingual thesaurus and doma...
Poster
Full-text available
We present results of collaborative work bringing together semantic technologies, machine learning and cultural heritage to enable advanced search and visualization of textual descriptions of museum artifacts related to silk fabrics. Proposed is a multilingual txt analysis approach where the developed domain-specific multilingual thesaurus and doma...
Conference Paper
Full-text available
In education we can find different open educational resource (OER) providers that are serving resources in different modalities , formats and languages. These providers can be the actual resource creators or re-distributors that redirect the user to the actual provider. In recent work, we developed a recommendation engine which provides content-bas...
Article
Full-text available
To achieve the full analytical potential of the streaming data from the internet of things, the interconnection of various data sources is needed. By definition, those sources are heterogeneous and their integration is not a trivial task. A common approach to exploit streaming sensor data potential is to use machine learning techniques for predicti...
Article
Full-text available
This paper proposes an approach for performing bilingual dictionary generation even when trained on widely available comparable bilingual corpora. We also show its capability to provide cross-lingual similarity estimates that correlate well with human judgments. We implement an approach using a nonlinear bilingual translation model that we train us...
Article
Full-text available
Rating of different services, products and experiences plays an important role in our digitally assisted day-to-day life. It helps us make decisions when we are indecisive, uninformed or inexperienced. Traditionally, ratings depend on the willingness of existing customers to provide them. This often leads to biased (due to the insufficient number o...
Article
Full-text available
Cross-language information retrieval aims at retrieving relevant documents in one language for a query set in another language. Here we propose a new approach to the problem of cross-language information retrieval based on factorization of a term-document matrix by an iterative method of Reduced k-means clustering. Method of Reduced k-means intende...
Conference Paper
Full-text available
In this study an algorithm for missing data imputation is presented. The algorithm uses measurements from neighboring sensors to estimate the missing values. Data-driven approach is used and methodology chooses the optimal available combination of modeling algorithm and available measurements to produce an estimate from the model with lowest error....
Presentation
Full-text available
One of the major goals of the SUNSEED European Project is to improve the observability of the distribution grid. The improved observability is one of the key challenges in the context of introducing smart grids. To avoid high investment costs into reinforced grid, the grid requires some smartness, where all decisions are based on the in-real-time e...
Conference Paper
Full-text available
In this study a thorough analysis is conducted concerning the prediction of groundwater levels of Ljubljana polje aquifer. Machine learning methodologies are implemented using strongly correlated physical parameters as input variables. The results show that data-driven modelling approaches can perform sufficiently well in predicting groundwater lev...
Article
Full-text available
Groundwater management is important for all urban systems. Thus, data needs to be available on request for various decision-makers and stakeholders. This article presents conceptual and implemented framework for collecting, analyzing and sharing of groundwater data for various purposes. It allows controlled access to data that is continuously colle...
Article
Full-text available
Background: Internet of Things (IoT), earth observation and big scientific experiments are sources of extensive amounts of sensor big-data today. With low measurement costs we are faced with large amounts of data. A standard approach in such cases is a stream mining approach, where we look at a particular measurement only once during the real-time...
Article
This paper presents an approach for the interactive visualization, exploration and interpretation of large multivariate time series. Interesting patterns in such datasets usually appear as periodic or recurrent behavior often caused by the interaction between variables. To identify such patterns, we summarize the data as conceptual states, modeling...
Article
Made possible by the availability of spatio-temporal data, collected by smart phones and other smart devices, understanding people’s mobility patterns has become one of the most promising location based services in the past few years, with various business-wise application possibilities. The simplest version of this problem is to predict where a us...
Conference Paper
Full-text available
Real-time classification of events in high energy physics is essential to deal with huge amounts of data, produced by proton-proton collisions in ATLAS detector at Large Hadron Collider in CERN. With this work we have implemented a triggering mechanism method for saving relevant data, based on machine learning. In comparison with the state of the a...