In this paper, we present a management tool for tracking KPIs in business processes. This tool ca... more In this paper, we present a management tool for tracking KPIs in business processes. This tool can be used by executives from a Smart Factory in a strategic manner for defining performance targets by using Smart Production dimensions. The tool uses a standard BPMN notation that suits the operational-driven scenarios of Smart Production. This paper introduces a tool that allows attaching and tracking of KPIs to the single tasks and activities of a business process modeled in BPMN. It describes its functionality and its possible applicability for Smart Factory use case where also business processes, systems, and humans interact within an intelligent manufacturing procedure.
2019 17th International Conference on Emerging eLearning Technologies and Applications (ICETA), 2019
E-learning represents novel learning way, which increase teaching flexibility and availability of... more E-learning represents novel learning way, which increase teaching flexibility and availability of learning resources. This paper explores the evaluation of student success at e-learning platform. Authors used multi-method approach for data analysis (i.e. Social Network Analysis, K-means Clustering and Linear Regression). This approach presents novelty in the field of e-learning, which provides more detailed analysis that enable more relevant results. The research was conducted with student group at the University of Novi Sad, Faculty of Technical Sciences, Serbia. Results indicate that digital resources at the e-learning platform make strong effects on student success. Moreover, results indicate that students with the similar grades belongs to the same clusters.
Abstract. In recent history, the term ontology has been used as if conveyed a great deal of weigh... more Abstract. In recent history, the term ontology has been used as if conveyed a great deal of weight and importance when, in many cases, the term has been used incorrectly. This diffusion of meaning is often the path by which a perfectly acceptable and well-defined word becomes a buzzword, reduced in meaning and a warning to readers that poor science is ahead. Frequently, a hyped buzzword will lead the reader to form expectations that are never fulfilled. This research work provides a critical reflec-tion on ontologies, their frequent misuse in research and business applications, and concerns aspects why ontologies have not been successful in large-scale business applications until now. When a definition that changes over time, as is the case for on-tologies, this may be indicative of a lack of understanding in the field, or an inability to effectively communicate and share a common understanding. Whatever the reason is for this case, introducing numerous definitions for one concept, ...
Recommender systems are machine learning based algorithms that found application in various busin... more Recommender systems are machine learning based algorithms that found application in various business scenarios, e.g., video on demand or music streaming like Netflix and YouTube, products sales recommendation such as Amazon, or content recommendation such as Facebook or Twitter. Besides successful utilization by multinational companies, the recommender systems found application in small business like supermarket, cinema, restaurants, retail stores, etc. In this chapter detailed overview about the algorithms behind the recommender systems was described with focus of the application using the ML.NET open source framework for training, building, and evaluating machine learning models. Furthermore, the methodology and use case scenario for the restaurant recommendation using ML.NET were developed to provide full life-cycle management of the modern cloud based recommended system.
In this paper, which focuses on the exogenous risks, a prototype is developed, which presents the... more In this paper, which focuses on the exogenous risks, a prototype is developed, which presents the users a world map with the country-specific risk factors. These risk factors, which have a massive impact on the supply chain of a company, are based on live data sources from the Internet, in order to provide up-to-date risk assessments. The prototype allows to place and link the individual company sites or suppliers in the world map. The resulting supply chains can be analyzed based on the exogenous risk factors such as weather and natural catastrophes, as well as war situations and terrorist warnings. Through a detail view, as well as through the comparability of several supply chains, based on an aggregation of the risks, the prototype provides users with the vulnerability of the supply chain as a measure of the risk exposure of the company.
SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We des... more SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We designed and developed SentiProMo for supporting social business processes management to enhance the business process management (BPM) lifecycle. In particular, we socially improve the BPM lifecycle in the process analysis stage by capturing and processing stakeholder's opinions regarding the tasks within a business process. By taking a social information systems perspective, SentiProMo transforms these opinions with sentiment analysis and classifies them into positive and negative feedback. The aim is to support the business analysts for redesigning a business process by considering the sentiment-analyzed opinions for designing the to-be process. We illustrate the current SentiProMo's capabilities with a simple process.
Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems, 2021
In this paper we propose a novel approach of empowering the design of business processes in manuf... more In this paper we propose a novel approach of empowering the design of business processes in manufacturing and broader by using sentiment analysis on comments collected during the design phase of business processes. For this purpose we trained and tested our Sentiment Analysis Module (SAM) to prioritize and classify the stakeholder comments as a part of software tool for BPMN based modeling and annotation. The preliminary result with evaluation test case seem to be promising regarding effective ranking and classifying the improvement proposals on BPMN design of manufacturing processes. However, there is still pleanty of space for improvements in trainings data segment and in extending the tool with social BPMN functionality.
Immer mehr Daten sind heute in immer höherer Geschwindigkeit und in unterschiedlichster Beschaffe... more Immer mehr Daten sind heute in immer höherer Geschwindigkeit und in unterschiedlichster Beschaffenheit verfügbar. Das Phänomen Big Data ist zugleich Mythos und Hype – und es wird doch vieles in unserer Welt grundlegend verändern. Doch was verbirgt sich hinter diesem Konzept, wie können Daten „zum Sprechen gebracht“ werden, um neue Anwendungsmöglichkeiten zu eröffnen? Dieser Beitrag will einen konzeptionellen Einblick in die Big Data Welt vermitteln.
Linked Data offers an entity-based infrastructure to resolve indirect relations between resources... more Linked Data offers an entity-based infrastructure to resolve indirect relations between resources, expressed as chains of links. If we could benchmark how effective retrieving chains of links from these sources is, we can motivate why they are a reliable addition for exploratory search interfaces. A vast number of applications could reap the benefits from encouraging insights in this field. Especially all kinds of knowledge discovery tasks related for instance to adhoc decision support and digital assistance systems. In this paper, we explain a benchmark model for evaluating the effectiveness of associating chains of links with keyword-based queries. We illustrate the benchmark model with an example case using academic library and conference metadata where we measured precision involving targeted expert users and directed it towards search effectiveness. This kind of typical semantic search engine evaluation focusing on information retrieval metrics such as precision is typically bi...
In this work we introduce necessary steps and planned actions for implementation of analytical ap... more In this work we introduce necessary steps and planned actions for implementation of analytical application with purpose on analyzing and visualizing information gathered by tracking user behavior and actions in our educational system called Personal Learning Environment (PLE). Furthermore we present a novel Semantic Web driven approach, for modeling of learning and activity based context using eligible domain specific ontologies, as well as for retrieving modeled data depending on the value of interests demonstrated by learner himself. We intend on closing the learning analytic cycle [Clo12] for PLE and for that purpose we are defining the requirements and implementation steps of analytic dashboard which shall give us necessary knowledge for improvement.
International Journal on Semantic Web and Information Systems, 2017
When researchers formulate search queries to find relevant content on the Web, those queries typi... more When researchers formulate search queries to find relevant content on the Web, those queries typically consist of keywords that can only be matched in the content or its metadata. The Web of Data extends this functionality by bringing structure and giving well-defined meaning to the content and it enables humans and machines to work together using controlled vocabularies. Due the high degree of mismatches between the structure of the content and the vocabularies in different sources, searching over multiple heterogeneous repositories of structured data is considered challenging. Therefore, the authors present a semantic search engine for researchers facilitating search in research related Linked Data. To facilitate high-precision interactive search, they annotated and interlinked structured research data with ontologies from various repositories in an effective semantic model. Furthermore, the authors' system is adaptive as researchers can synchronize using new social media acco...
Proceedings of the 23rd International Conference on World Wide Web, 2014
ABSTRACT Resources for research are not always easy to explore, and rarely come with strong suppo... more ABSTRACT Resources for research are not always easy to explore, and rarely come with strong support for identifying, linking and selecting those that can be of interest to scholars. In this work we introduce a model that uses state-of-the-art semantic technologies to interlink structured research data and data from Web collaboration tools, social media and Linked Open Data. We use this model to build a platform that connects scholars, using their profiles as a starting point to explore novel and relevant content for their research. Scholars can easily adapt to evolving trends by synchronizing new social media accounts or collaboration tools and integrate then with new datasets. We evaluate our approach by a scenario of personalized exploration of research repositories where we analyze real world scholar profiles and compare them to a reference profile.
In this paper, we present a management tool for tracking KPIs in business processes. This tool ca... more In this paper, we present a management tool for tracking KPIs in business processes. This tool can be used by executives from a Smart Factory in a strategic manner for defining performance targets by using Smart Production dimensions. The tool uses a standard BPMN notation that suits the operational-driven scenarios of Smart Production. This paper introduces a tool that allows attaching and tracking of KPIs to the single tasks and activities of a business process modeled in BPMN. It describes its functionality and its possible applicability for Smart Factory use case where also business processes, systems, and humans interact within an intelligent manufacturing procedure.
2019 17th International Conference on Emerging eLearning Technologies and Applications (ICETA), 2019
E-learning represents novel learning way, which increase teaching flexibility and availability of... more E-learning represents novel learning way, which increase teaching flexibility and availability of learning resources. This paper explores the evaluation of student success at e-learning platform. Authors used multi-method approach for data analysis (i.e. Social Network Analysis, K-means Clustering and Linear Regression). This approach presents novelty in the field of e-learning, which provides more detailed analysis that enable more relevant results. The research was conducted with student group at the University of Novi Sad, Faculty of Technical Sciences, Serbia. Results indicate that digital resources at the e-learning platform make strong effects on student success. Moreover, results indicate that students with the similar grades belongs to the same clusters.
Abstract. In recent history, the term ontology has been used as if conveyed a great deal of weigh... more Abstract. In recent history, the term ontology has been used as if conveyed a great deal of weight and importance when, in many cases, the term has been used incorrectly. This diffusion of meaning is often the path by which a perfectly acceptable and well-defined word becomes a buzzword, reduced in meaning and a warning to readers that poor science is ahead. Frequently, a hyped buzzword will lead the reader to form expectations that are never fulfilled. This research work provides a critical reflec-tion on ontologies, their frequent misuse in research and business applications, and concerns aspects why ontologies have not been successful in large-scale business applications until now. When a definition that changes over time, as is the case for on-tologies, this may be indicative of a lack of understanding in the field, or an inability to effectively communicate and share a common understanding. Whatever the reason is for this case, introducing numerous definitions for one concept, ...
Recommender systems are machine learning based algorithms that found application in various busin... more Recommender systems are machine learning based algorithms that found application in various business scenarios, e.g., video on demand or music streaming like Netflix and YouTube, products sales recommendation such as Amazon, or content recommendation such as Facebook or Twitter. Besides successful utilization by multinational companies, the recommender systems found application in small business like supermarket, cinema, restaurants, retail stores, etc. In this chapter detailed overview about the algorithms behind the recommender systems was described with focus of the application using the ML.NET open source framework for training, building, and evaluating machine learning models. Furthermore, the methodology and use case scenario for the restaurant recommendation using ML.NET were developed to provide full life-cycle management of the modern cloud based recommended system.
In this paper, which focuses on the exogenous risks, a prototype is developed, which presents the... more In this paper, which focuses on the exogenous risks, a prototype is developed, which presents the users a world map with the country-specific risk factors. These risk factors, which have a massive impact on the supply chain of a company, are based on live data sources from the Internet, in order to provide up-to-date risk assessments. The prototype allows to place and link the individual company sites or suppliers in the world map. The resulting supply chains can be analyzed based on the exogenous risk factors such as weather and natural catastrophes, as well as war situations and terrorist warnings. Through a detail view, as well as through the comparability of several supply chains, based on an aggregation of the risks, the prototype provides users with the vulnerability of the supply chain as a measure of the risk exposure of the company.
SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We des... more SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We designed and developed SentiProMo for supporting social business processes management to enhance the business process management (BPM) lifecycle. In particular, we socially improve the BPM lifecycle in the process analysis stage by capturing and processing stakeholder's opinions regarding the tasks within a business process. By taking a social information systems perspective, SentiProMo transforms these opinions with sentiment analysis and classifies them into positive and negative feedback. The aim is to support the business analysts for redesigning a business process by considering the sentiment-analyzed opinions for designing the to-be process. We illustrate the current SentiProMo's capabilities with a simple process.
Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems, 2021
In this paper we propose a novel approach of empowering the design of business processes in manuf... more In this paper we propose a novel approach of empowering the design of business processes in manufacturing and broader by using sentiment analysis on comments collected during the design phase of business processes. For this purpose we trained and tested our Sentiment Analysis Module (SAM) to prioritize and classify the stakeholder comments as a part of software tool for BPMN based modeling and annotation. The preliminary result with evaluation test case seem to be promising regarding effective ranking and classifying the improvement proposals on BPMN design of manufacturing processes. However, there is still pleanty of space for improvements in trainings data segment and in extending the tool with social BPMN functionality.
Immer mehr Daten sind heute in immer höherer Geschwindigkeit und in unterschiedlichster Beschaffe... more Immer mehr Daten sind heute in immer höherer Geschwindigkeit und in unterschiedlichster Beschaffenheit verfügbar. Das Phänomen Big Data ist zugleich Mythos und Hype – und es wird doch vieles in unserer Welt grundlegend verändern. Doch was verbirgt sich hinter diesem Konzept, wie können Daten „zum Sprechen gebracht“ werden, um neue Anwendungsmöglichkeiten zu eröffnen? Dieser Beitrag will einen konzeptionellen Einblick in die Big Data Welt vermitteln.
Linked Data offers an entity-based infrastructure to resolve indirect relations between resources... more Linked Data offers an entity-based infrastructure to resolve indirect relations between resources, expressed as chains of links. If we could benchmark how effective retrieving chains of links from these sources is, we can motivate why they are a reliable addition for exploratory search interfaces. A vast number of applications could reap the benefits from encouraging insights in this field. Especially all kinds of knowledge discovery tasks related for instance to adhoc decision support and digital assistance systems. In this paper, we explain a benchmark model for evaluating the effectiveness of associating chains of links with keyword-based queries. We illustrate the benchmark model with an example case using academic library and conference metadata where we measured precision involving targeted expert users and directed it towards search effectiveness. This kind of typical semantic search engine evaluation focusing on information retrieval metrics such as precision is typically bi...
In this work we introduce necessary steps and planned actions for implementation of analytical ap... more In this work we introduce necessary steps and planned actions for implementation of analytical application with purpose on analyzing and visualizing information gathered by tracking user behavior and actions in our educational system called Personal Learning Environment (PLE). Furthermore we present a novel Semantic Web driven approach, for modeling of learning and activity based context using eligible domain specific ontologies, as well as for retrieving modeled data depending on the value of interests demonstrated by learner himself. We intend on closing the learning analytic cycle [Clo12] for PLE and for that purpose we are defining the requirements and implementation steps of analytic dashboard which shall give us necessary knowledge for improvement.
International Journal on Semantic Web and Information Systems, 2017
When researchers formulate search queries to find relevant content on the Web, those queries typi... more When researchers formulate search queries to find relevant content on the Web, those queries typically consist of keywords that can only be matched in the content or its metadata. The Web of Data extends this functionality by bringing structure and giving well-defined meaning to the content and it enables humans and machines to work together using controlled vocabularies. Due the high degree of mismatches between the structure of the content and the vocabularies in different sources, searching over multiple heterogeneous repositories of structured data is considered challenging. Therefore, the authors present a semantic search engine for researchers facilitating search in research related Linked Data. To facilitate high-precision interactive search, they annotated and interlinked structured research data with ontologies from various repositories in an effective semantic model. Furthermore, the authors' system is adaptive as researchers can synchronize using new social media acco...
Proceedings of the 23rd International Conference on World Wide Web, 2014
ABSTRACT Resources for research are not always easy to explore, and rarely come with strong suppo... more ABSTRACT Resources for research are not always easy to explore, and rarely come with strong support for identifying, linking and selecting those that can be of interest to scholars. In this work we introduce a model that uses state-of-the-art semantic technologies to interlink structured research data and data from Web collaboration tools, social media and Linked Open Data. We use this model to build a platform that connects scholars, using their profiles as a starting point to explore novel and relevant content for their research. Scholars can easily adapt to evolving trends by synchronizing new social media accounts or collaboration tools and integrate then with new datasets. We evaluate our approach by a scenario of personalized exploration of research repositories where we analyze real world scholar profiles and compare them to a reference profile.
Del-Río-Ortega.A, Leopold.H, Santoro.S (eds). Business Process Management Workshops. BPM 2020. Lecture Notes in Business Information Processing. Springer, Cham , 2020
SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We des... more SentiProMo is a novel social business process modeling tool enabled by sentiment analysis. We designed and developed SentiProMo for supporting social business processes management to enhance the business process management (BPM) lifecycle. In particular, we socially improve the BPM lifecycle in the process analysis stage by capturing and processing stakeholder's opinions regarding the tasks within a business process. By taking a social information systems perspective, SentiProMo transforms these opinions with sentiment analysis and classifies them into positive and negative feedback. The aim is to support the business analysts for redesigning a business process by considering the sentiment-analyzed opinions for designing the to-be process. We illustrate the current SentiProMo's capabilities with a simple process.
Uploads
Papers by Selver Softic