Milos Jovanovic | University of Belgrade (original) (raw)
Uploads
Papers by Milos Jovanovic
arXiv (Cornell University), Jan 31, 2019
International Journal on Artificial Intelligence Tools, 2019
It is commonly understood that machine learning algorithms discover and extract knowledge based o... more It is commonly understood that machine learning algorithms discover and extract knowledge based on data at hand. However, a huge amount of knowledge is available which is in machine-readable format and ready for inclusion in machine learning algorithms and models. In this paper, we propose a framework that integrates domain knowledge in form of ontologies/hierarchies into logistic regression using stacked generalization. Namely, relations from ontology/hierarchy are used in stacking manner in order to obtain higher, more abstract concepts. Obtained concepts are further used for prediction. The problem we solved is unplanned 30-days hospital readmission, which is considered as one of the major problems in healthcare. Proposed framework yields better results compared to Ridge, Lasso, and Tree Lasso Logistic Regression. Results suggest that the proposed framework improves AUC by up to 9.5% on pediatric datasets and up to 4% on morbidly obese patients’ datasets and also improves AUPRC b...
arXiv (Cornell University), Nov 15, 2020
Analyzing human trajectories based on sensor data is a challenging research topic. It has been an... more Analyzing human trajectories based on sensor data is a challenging research topic. It has been analyzed from many aspects like clustering, process mining, and others. Still, less attention has been paid on analyzing this data based on hidden factors that drive the behavior of people. We, therefore, adapt the standard matrix factorization approach and reveal factors which are interpretable and soundly explain the behavior of a dynamic population. We analyze the motion of a skier population based on data from RFID-recorded ski entrances of skiers on ski lift gates. The approach is applicable to other similar settings, like shopping malls or road traffic. We further applied recommender systems algorithms for testing how well we can predict the distribution of ski lift usage (number of ski lift visits) based on hidden factors, but also on other benchmark algorithms. The matrix factorization algorithm showed to be the best recommender score predictor with an RMSE of 2.569 ± 0.049 and an ...
Engineering Applications of Artificial Intelligence, 2021
ABSTRACT WhiBo is a framework for defining, running and testing of machine-learning algorithms as... more ABSTRACT WhiBo is a framework for defining, running and testing of machine-learning algorithms as a composition of reusable components (i.e. white-box design approach). These components are extracted from well known algorithms as well as their partial improvements for solving specific sub-problems. WhiBo is intended for data mining practitioners, algorithm designers and machine-learning software developers. Currently the WhiBo framework consists of a reusable components (RC) repository, a RC-based generic decision tree algorithm, GUI for design of RC-based algorithms and an operator group for performance and significance testing of decision trees. Additionally, a generic partitioning clustering algorithm is included in WhiBo.
International Journal of Computational Intelligence Systems, 2012
IEEE Transactions on Education, 2013
ABSTRACT University students are usually taught data mining through black-box data mining algorit... more ABSTRACT University students are usually taught data mining through black-box data mining algorithms, which hide the algorithm's details from the user and optionally allow parameter adjustment. This minimizes the effort required to use these algorithms. On the other hand, white-box algorithms reveal the algorithm's structure, allowing users to assemble algorithms from algorithm building blocks. This paper provides a comparison between students' acceptance of both black-box and white-box decision tree algorithms. For these purposes, the technology acceptance model is used. The model is extended with perceived understanding and the influence it has on acceptance of decision tree algorithms. An experiment was conducted with 118 senior management students who were divided into two groups-one working with black-box, and the other with white-box algorithms-and their cognitive styles were analyzed. The results of how cognitive styles affect the perceived understanding of students when using decision tree algorithms with different levels of algorithm transparency are reported here.
Data & Knowledge Engineering, 2012
ABSTRACT We propose an architecture for the design of representative-based clustering algorithms ... more ABSTRACT We propose an architecture for the design of representative-based clustering algorithms based on reusable components. These components were derived from K-means-like algorithms and their extensions. With the suggested clustering design architecture, it is possible to reconstruct popular algorithms, but also to build new algorithms by exchanging components from original algorithms and their improvements. In this way, the design of a myriad of representative-based clustering algorithms and their fair comparison and evaluation are possible. In addition to the architecture, we show the usefulness of the proposed approach by providing experimental evaluation.
Computational Statistics, 2011
Artificial Intelligence Review, 2009
Clustering algorithms are well-established and widely used for solving data-mining tasks. Every c... more Clustering algorithms are well-established and widely used for solving data-mining tasks. Every clustering algorithm is composed of several solutions for specific sub-problems in the clustering process. These solutions are linked together in a clustering algorithm, and they define the process and the structure of the algorithm. Frequently, many of these solutions occur in more than one clustering algorithm. Mostly, new
… -časopis za teoriju i …, 2010
Poslovna inteligencija je aktivno područje istraivanja i primene. Iako je oblast mlada, nudi dos... more Poslovna inteligencija je aktivno područje istraivanja i primene. Iako je oblast mlada, nudi dosta reenja, prvenstveno namenjena boljem izvetavanju i analizi koji će podrati proces donoenja odluke, na svim nivoima odlučivanja. Kako je proces odlučivanja prisutan u svakoj oblasti ...
Intelligent Data Analysis, 2011
Intelligent Data Analysis
arXiv (Cornell University), Jan 31, 2019
International Journal on Artificial Intelligence Tools, 2019
It is commonly understood that machine learning algorithms discover and extract knowledge based o... more It is commonly understood that machine learning algorithms discover and extract knowledge based on data at hand. However, a huge amount of knowledge is available which is in machine-readable format and ready for inclusion in machine learning algorithms and models. In this paper, we propose a framework that integrates domain knowledge in form of ontologies/hierarchies into logistic regression using stacked generalization. Namely, relations from ontology/hierarchy are used in stacking manner in order to obtain higher, more abstract concepts. Obtained concepts are further used for prediction. The problem we solved is unplanned 30-days hospital readmission, which is considered as one of the major problems in healthcare. Proposed framework yields better results compared to Ridge, Lasso, and Tree Lasso Logistic Regression. Results suggest that the proposed framework improves AUC by up to 9.5% on pediatric datasets and up to 4% on morbidly obese patients’ datasets and also improves AUPRC b...
arXiv (Cornell University), Nov 15, 2020
Analyzing human trajectories based on sensor data is a challenging research topic. It has been an... more Analyzing human trajectories based on sensor data is a challenging research topic. It has been analyzed from many aspects like clustering, process mining, and others. Still, less attention has been paid on analyzing this data based on hidden factors that drive the behavior of people. We, therefore, adapt the standard matrix factorization approach and reveal factors which are interpretable and soundly explain the behavior of a dynamic population. We analyze the motion of a skier population based on data from RFID-recorded ski entrances of skiers on ski lift gates. The approach is applicable to other similar settings, like shopping malls or road traffic. We further applied recommender systems algorithms for testing how well we can predict the distribution of ski lift usage (number of ski lift visits) based on hidden factors, but also on other benchmark algorithms. The matrix factorization algorithm showed to be the best recommender score predictor with an RMSE of 2.569 ± 0.049 and an ...
Engineering Applications of Artificial Intelligence, 2021
ABSTRACT WhiBo is a framework for defining, running and testing of machine-learning algorithms as... more ABSTRACT WhiBo is a framework for defining, running and testing of machine-learning algorithms as a composition of reusable components (i.e. white-box design approach). These components are extracted from well known algorithms as well as their partial improvements for solving specific sub-problems. WhiBo is intended for data mining practitioners, algorithm designers and machine-learning software developers. Currently the WhiBo framework consists of a reusable components (RC) repository, a RC-based generic decision tree algorithm, GUI for design of RC-based algorithms and an operator group for performance and significance testing of decision trees. Additionally, a generic partitioning clustering algorithm is included in WhiBo.
International Journal of Computational Intelligence Systems, 2012
IEEE Transactions on Education, 2013
ABSTRACT University students are usually taught data mining through black-box data mining algorit... more ABSTRACT University students are usually taught data mining through black-box data mining algorithms, which hide the algorithm's details from the user and optionally allow parameter adjustment. This minimizes the effort required to use these algorithms. On the other hand, white-box algorithms reveal the algorithm's structure, allowing users to assemble algorithms from algorithm building blocks. This paper provides a comparison between students' acceptance of both black-box and white-box decision tree algorithms. For these purposes, the technology acceptance model is used. The model is extended with perceived understanding and the influence it has on acceptance of decision tree algorithms. An experiment was conducted with 118 senior management students who were divided into two groups-one working with black-box, and the other with white-box algorithms-and their cognitive styles were analyzed. The results of how cognitive styles affect the perceived understanding of students when using decision tree algorithms with different levels of algorithm transparency are reported here.
Data & Knowledge Engineering, 2012
ABSTRACT We propose an architecture for the design of representative-based clustering algorithms ... more ABSTRACT We propose an architecture for the design of representative-based clustering algorithms based on reusable components. These components were derived from K-means-like algorithms and their extensions. With the suggested clustering design architecture, it is possible to reconstruct popular algorithms, but also to build new algorithms by exchanging components from original algorithms and their improvements. In this way, the design of a myriad of representative-based clustering algorithms and their fair comparison and evaluation are possible. In addition to the architecture, we show the usefulness of the proposed approach by providing experimental evaluation.
Computational Statistics, 2011
Artificial Intelligence Review, 2009
Clustering algorithms are well-established and widely used for solving data-mining tasks. Every c... more Clustering algorithms are well-established and widely used for solving data-mining tasks. Every clustering algorithm is composed of several solutions for specific sub-problems in the clustering process. These solutions are linked together in a clustering algorithm, and they define the process and the structure of the algorithm. Frequently, many of these solutions occur in more than one clustering algorithm. Mostly, new
… -časopis za teoriju i …, 2010
Poslovna inteligencija je aktivno područje istraivanja i primene. Iako je oblast mlada, nudi dos... more Poslovna inteligencija je aktivno područje istraivanja i primene. Iako je oblast mlada, nudi dosta reenja, prvenstveno namenjena boljem izvetavanju i analizi koji će podrati proces donoenja odluke, na svim nivoima odlučivanja. Kako je proces odlučivanja prisutan u svakoj oblasti ...
Intelligent Data Analysis, 2011
Intelligent Data Analysis