Vagan TerziyanUniversity of Jyväskylä | JYU · Faculty of Information Technology
Vagan Terziyan
Prof. (Distributed Systems)
About
181
Publications
24,323
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
2,283
Citations
Introduction
Vagan Terziyan currently works at the Faculty of Information Technology, University of Jyväskylä (Finland). Vagan does research in Artificial Intelligence, Semantic Web, Machine Learning and Knowledge Discovery, Multi-Agent Systems. Their current projects are 'Semantic keyword-based search on structured data sources (KEYSTONE)', Wearable Robots, Cognitive Computing and Collective Intelligence
Additional affiliations
May 2003 - present
September 2001 - present
September 2001 - present
Publications
Publications (181)
Smart manufacturing uses emerging deep learning models, and particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), for different industrial diagnostics tasks, e.g., classification, detection, recognition, prediction, synthetic data generation, security, etc., on the basis of image data. In spite of being effic...
In Artificial Intelligence (AI) in general and in Machine Learning (ML) in particular, which are important and integral components of modern Industry 4.0, we often deal with uncertainty, e.g., lack of complete information about the objects we are classifying, recognizing, diagnosing, etc. Traditionally, uncertainty is considered to be a problem esp...
Smart manufacturing is being shaped nowadays by two different paradigms: Industry 4.0 proclaims transition to digitalization and automation of processes while emerging Industry 5.0 emphasizes human centricity. This turn can be explained by unprecedented challenges being faced recently by societies, such as, global climate change, pandemics, hybrid...
Current advances in machine (deep) learning and the exponential growth of data collected by and shared between smart manufacturing processes give a unique opportunity to get extra value from that data. The use of public machine learning services actualizes the issue of data privacy. Ordinary encryption protects the data but could make it useless fo...
Convolutional Neural Network is one of the famous members of the deep learning family of neural network architectures, which is used for many purposes, including image classification. In spite of the wide adoption, such networks are known to be highly tuned to the training data (samples representing a particular problem), and they are poorly reusab...
Industry 4.0 and Smart Manufacturing are associated with the Cyber-Physical-Social Systems populated and controlled by the Collective Intelligence (human and artificial). They are an important component of Critical Infrastructure and they are essential for the functioning of a society and economy. Hybrid Threats nowadays target critical infrastruct...
This study uses a design science research methodology to develop and evaluate the Pi-Mind agent, an information technology artefact that acts as a responsible, resilient, ubiquitous cognitive clone – or a digital copy – and an autonomous representative of a human decision-maker. Pi-Mind agents can learn the decision-making capabilities of their “do...
Biologicalization (biological transformation) is an emerging trend in Industry 4.0 affecting digitization of manufacturing and related processes. It brings up the next generation of manufacturing technology and systems that extensively use biological and bio-inspired principles, materials, functions, structures and resources. This research is a con...
Artificial Intelligence (AI) is known to be a driving force behind the Industry 4.0. Nowadays the current hype on development and industrial adoption of the AI systems is mostly associated with the deep learning, i.e., with the abilities of the AI to perform various specific cognitive activities better than humans do. However, what about the Artifi...
Artificial Intelligence is an important asset of Industry 4.0. Current discoveries within machine learning and particularly in deep learning enable qualitative change within the industrial processes, applications, systems and products. However, there is an important challenge related to explainability of (and, therefore, trust to) the decisions mad...
Smart manufacturing often requires digital clones of physical objects (twins) and human decision-makers (“cognitive clones”). The latter requires use of machine learning to capture hidden personalized decision models from humans. Machine learning nowadays is a subject of various adversarial attacks (poisoning, evasion, etc.) on the training and tes...
Smart manufacturing needs digital clones of physical objects (digital twins) and human decision-makers (cognitive clones). The latter requires use of machine learning to capture hidden personalised decision models from humans. Machine learning nowadays is a subject of various adversarial attacks (poisoning, evasion, etc.). Responsible use of machin...
Machine learning is a good tool to simulate human cognitive skills as it is about mapping perceived information to various labels or action choices, aiming at optimal behavior policies for a human or an artificial agent operating in the environment. Regarding autonomous systems, objects and situations are perceived by some receptors as divided betw...
Information retrieval (IR) is known facilitator of changes ongoing in human society and vice versa. This is due to the fact that IR is a key component of the digital ecosystems, where both information providers and information consumers collaboratively address their problems with the use of technologies. Organization and design of such ecosystems d...
Various processes in academic organizations include the decision points where selecting people through their assessment and ranking is performed, and the impact of wrong or right choices can be very high. How do we simultaneously ensure that these selection decisions are well balanced, fair, and unbiased by satisfying the key stakeholders' wishes?...
Operating with ignorance is an important concern of geographical information science when the objective is to discover knowledge from the imperfect spatial data. Data mining (driven by knowledge discovery tools) is about processing available (observed, known, and understood) samples of data aiming to build a model (e.g., a classifier) to handle dat...
Industry 4.0 and highly automated critical infrastructure can be seen as cyber‐physicalsocial systems controlled bythe Collective Intelligence. Suchsystems are essentialfor the functioningofthesocietyandeconomy.Ononehand,theyhaveflexibleinfrastructureof heterogeneous systems and assets. On the other hand, they are social systems, which include coll...
Industry 4.0 is largely data-driven nowadays. Owners of the data, on the one hand, want to get added value from the data by using remote artificial intelligence tools as services, on the other hand, they concern on privacy of their data within external premises. Ideal solution for this challenge would be such anonymization of the data, which makes...
Industry 4.0 systems are extensively using artificial intelligence (AI) to enable smartness, automation and flexibility within variety of processes. Due to the importance of the systems, they are potential targets for attackers trying to take control over the critical processes. Attackers use various vulnerabilities of such systems including specif...
There can be many reasons for anyone to make a digital copy (clone) of own decision-making behavior. This enables virtual presence of a professional decision-maker simultaneously in many places and processes of Industry 4.0. Such clone can be used as one’s responsible representative when the human is not available. Pi-Mind (“Patented Intelligence”)...
There are no doubts that artificial and human intelligence enhance and complement each other. They are stronger together as a team of Collective (Collaborative) Intelligence. Both require training for personal development and high performance. However, the approaches to training (human vs. machine learning) are traditionally very different. If one...
Operating with ignorance is an important concern of the Machine Learning research, especially when the objective is to discover knowledge from the imperfect data. Data mining (driven by appropriate knowledge discovery tools) is about processing available (observed, known and understood) samples of data aiming to build a model (e.g., a classifier) t...
The environments, in which we all live, are known to be complex and unpredictable. The complete discovery of these environments aiming to take full control over them is a “mission-impossible”, however, still in our common agenda. People intend to make their living spaces smarter utilizing innovations from the Internet of Things and Artificial Intel...
Industry 4.0 is a trend related to smart factories, which are cyber-physical spaces populated and controlled by the collective intelligence for the autonomous and highly flexible manufacturing purposes. Artificial Intelligence (AI) embedded into various planning, production, and management processes in Industry 4.0 must take the initiative and resp...
Search is not only an instrument to find intended information. Ability to search is a basic cognitive skill helping people to explore the world. It is largely based on personal intuition and creativity. However, due to the emerged big data challenge, people require new forms of training to develop or improve this ability. Current developments withi...
Choice of a distance metric is a key for the success in many machine learning and data processing tasks. The distance between two data samples traditionally depends on the values of their attributes (coordinates) in a data space. Some metrics also take into account the distribution of samples within the space (e.g. local densities) aiming to improv...
Evolving Knowledge Ecosystems were proposed to approach the Big Data challenge, following the hypothesis that knowledge evolves in a way similar to biological systems. Therefore, the inner working of the knowledge ecosystem can be spotted from natural evolution. An evolving knowledge ecosystem consists of Knowledge Organisms, which form a represent...
In this paper we address an exploratory search challenge by presenting a new (structure-driven) collaborative filtering technique. The aim is to increase search effectiveness by predicting implicit seeker’s intents at an early stage of the search process. This is achieved by uncovering behavioral patterns within large datasets of preserved collecti...
Aspects of time, change, evolution, temporal reasoning and decision-making remain in the focus of metadata and ontology engineering because many related challenges are yet to be fully addressed. In this paper, we present ontology ALLEN+ as a tool to reason with imperfect temporal information. We created a rule-set (SWRL on top of OWL) capable of te...
Evolving Knowledge Ecosystems were proposed recently to approach the Big Data challenge, following the hypothesis that knowledge evolves in a way similar to biological systems. Therefore, the inner working of the knowledge ecosystem can be spotted from natural evolution. An evolving knowledge ecosystem consists of Knowledge Organisms, which form a...
Education is recognized as a fundamental enabler of human development. The adoption of information and communications technologies (ICTs) by education (especially in developing countries) contributes to educational system reforms, in addition to the traditional advantages, such as social openness and accessibility. Yet the academic community has no...
The domain of Emotional Business Intelligence (EBI) aims to support business-relevant emotional and emotionaware decisions in addition to rational decision making. EBI originates from three root domains: Emotional Business, Emotional Intelligence and Business Intelligence (BI). In this paper we emphasize emotional empowerment of the traditional BI...
This report is dedicated to considerations and perspectives for the strategy of using unmanned aerial vehicles and Cloud Computing in emergency situations in a Smart City environment. The aim is to provide inspiring insights in this highly complex problem from a technological and a tactical point of view. This specific case can be seen as a member...
Emotions are known to be an important driver in human behaviour and decision-making. In the business world, there is a growing belief that emotions are not an obstacle but rather an enabler for a successful business. Business intelligence (by providing analytical processing and convenient presentation of a business data) traditionally supports rati...
This paper deals with the challenges related to self-management and evolution of massive knowledge collections. We can assume that a self-managed knowledge graph needs a kind of a hybrid of: an explicit declarative self-knowledge (as knowledge about own properties and capabilities) and an explicit procedural self-knowledge (as knowledge on how to u...
It is widely agreed that “a picture is worth a thousand words” . When it comes to Big Data computing a good picture may be worth of petabytes, saving weeks of data analysts’ work. An adequate and timely representation of knowledge dissolved in and carried by the petabytes of data may be even more effective than a good picture. Indeed, data emerge r...
Nowadays, we make a separation between the real/physical world and the Internet. It is time for these two be
blended and provide ubiquitous access and interoperability online. We are approaching Internet of Things - a forthcoming technological revolution that will radically change our environment and enable innovative applications and services. To...
Today, we make a separation between the real/physical world and the Internet. It is time for these two be blended and provide ubiquitous access and interoperability online. We are approaching Internet of Things -a forthcoming technological revolution that will radically change our environment and enable innovative applications and services. To make...
This paper presents the concept of "Executable Knowledge", which is based on Linked Data and in addition to traditional subject-predicate-object semantic triplet model it contains also subject-predicate-query triplets. Actual values for such "executable" properties are supposed to be queried or/and computed whenever requested "on-the-fly" from/by s...
The Semantic Web is a proposal from the World Wide Web Consortium aimed at solving problems like data integration and application interoperability. To reach these goals several languages for the representation of semantic data have been proposed. One of the essential concepts behind semantic data is that the data is according to a certain ontology....
This paper deals with an interface between expert knowledge and group of experts from whom this knowledge has been acquired and who are going to be users of it. Method is based on deriving the most supported opinion of th e group of experts acting as knowledge sources with further applying of it as an interface to each of experts acting as user. Kn...
Current Web grows rapidly to several directions (from the Web of Documents to the Webs of Humans, Things, Services, Knowledge, Intelligence, etc.). Consequently the recent and future Web-based applications, systems and frameworks (like, e.g., Social and Ubiquitous Computing, SOA and Cloud Computing, etc.) should take into account challenges related...
Enabling interoperability between a large number of heterogeneous entities (devices, software, humans, abstractions, etc.), while ensuring predictability and safety of their operation, is difficult without an extra layer of intelligence that will ensure the orchestration of these various actors according to well-defined goals, taking into account c...
Current economical situation in Finnish forest industry desperately calls for higher degree of efficiency in all stages of the production chain. The competitiveness of timber-based products directly and heavily depends on the raw material cost. At the same time, the successes of companies, that use timber, determine the volumes of the raw wood cons...
Next generation of integration systems will utilize different methods and techniques to achieve the vision of ubiquitous knowledge: Semantic Web and Web Services, Agent Technologies and Mobility. Nowadays, unlimited interoperability and collaboration are the important things for industry, business, education and research, health and wellness, and o...
Current Cloud Computing stack mainly targets three architectural layers: Infrastructure, Platform and Software. These can be considered as services for the respective layers above. The infrastructure layer is provided as a service for the platform layer and the platform layer is, in turn, a service for the Software layer. Agent platforms fit the "P...
A smart road environment is such a traffic environment that is equipped with all necessary facilities to enable seamless mobile service provisioning to the users. However, advanced sensors and network architectures deployed within the traffic environment are insufficient to make mobile service provisioning autonomous and proactive, thus minimizing...
Existing middleware platforms for multi-agent systems (MAS) do not provide general support for observation. On the other hand, observation is considered to be an important mechanism needed for realizing effective and efficient coordination of agents. This paper describes a framework called Agent Observable Environment (AOE) for observation-based in...
In open systems where the components, i.e. the agents and the resources, may be unknown at design time, or in dynamic and self-organizing systems evolving with time, there is a need to enable the agents to communicate their intentions with respect to future activities and resource utilization to resolve coordination issues dynamically. Ideally, we...
The volumes of data in information systems are growing drastically. The systems become increasingly complex in trying to handle heterogeneity of ubiquitous components, standards, data formats, etc. According to the vision of Autonomic Computing, the complexity can be handled by introducing self-manageable components able to "run themselves." Agent...
Some initiatives towards future Internet, e.g., GENI, DARPA's Active Networks, argue the need for programmability of the network components. Some other initiatives extend this with argumentation for declarative networking, where the behavior of a network component is specified using some high-level declarative language, with a software-based engine...
Industry pushes a new type of Internet characterized as the Internet of Things, which represents a fusion of the physical and digital worlds. The technology of the Internet of Things opens new horizons for industrial automation, that is, automated monitoring, control, maintenance planning, and so forth, of industrial resources and processes. Intern...
Now, when, according to recent Web evolution trends, a human becomes a very dynamic and proactive player in a large highly heterogeneous and distributed environment with a huge amount of different kind of data, services, devices, etc., it is quite necessary to provide a technology and tools for easy and handy human information access and manipulati...
Among traditional users of Web resources, industry has a growing set of smart industrial devices with embedded intelligence. Just like humans, they need online services (i.e., for condition monitoring, remote diagnostics, maintenance, etc.). In this paper, we present one possible implementation framework for such Web services. Such services should...
The paper summarizes research findings related to SmartResource project (2004-2007) funded by Tekes and industrial companies. The main objectives was research and development of the large-scale distributed environment for integration of smart devices, web services and humans based on combination of Semantic Web, agent technologies and service-orien...
As ubiquitous systems become increasingly complex, traditional solutions to manage and control them reach their limits and pose a need for self-manageability. Also, heterogeneity of the ubiquitous components, standards, data formats, etc, creates significant obstacles for interoperability in such complex systems. The promising technologies to tackl...
In this paper a recursive expansion of the set of ordinary arithmetical operations is investigated. The addition is considered to be a base of recursion. Next we have multiplication, rising to a power, and so on, up to the infinity. Algebra is considered based on the set of recursive operations. The variable arithmetical operation a + n b is define...
Although the flexibility of agent interactions has many advantages when it comes to engineering a complex system, the downside is that it leads to certain unpredictability of the run-time system. Literature sketches two major directions for search for a solution: social-level characterization of agent sys- tems and ontological approaches to inter-a...
Bayesian Networks are proven to be a comprehensive model to describe causal relationships among domain attributes with probabilistic measure of conditional dependency. However, depending on a context, many attributes of the model might not be relevant. If a Bayesian Network has been learned across multiple contexts then all uncovered conditional de...
Integration of heterogeneous applications and data sources into an interoperable system is one of the most relevant challenges for many knowledge-based corporations nowadays. Development of a global environment that would support knowledge transfer from human experts to automated Web services, which are able to learn, is a very profit-promising and...
This paper describes how semantic web and agent technologies could be used in enhancing the electricity distribution systems. The paper starts by a brief overview of functioning of electricity distribution systems. The introduced approaches aim at improving functionality of electricity distribution network systems and assisting the experts by suppo...
Conventional approaches to manage and control security seem to have reached their limits in new complex environments. These environments are open, dynamic, heterogeneous, distributed, self-managing, collabor ative, international, nomadic, and ubiquitous. We are currently working on a middleware platform focused on the industrial needs, UBIWARE. UBI...
A lot of IT solutions exist for simplific ation and time saving of industrial experts' activi ties. However, due to large diversity of tools and case-by-case softwa re development strategy, big industrial companies a re looking for an efficient and viable information int egration solution. The companies have realized the need for an integrated envi...
Integration of heterogeneous applications and data sources into an interoperable system is one of the most relevant challenges for many knowledge-based corporations nowadays. Development of a global environment, which would support knowledge transfer from human experts to automated Web-services which are able to learn, is a very profit-promising an...
Among traditional users of Web resources, industry also has a growing set of smart industrial devices with embedded intelligence. Just as humans do, smart industrial devices need online services-for example, for condition monitoring, remote diagnostics, maintenance, and so on. In this chapter, we present one possible implementation framework for su...
This chapter presents the framework for agent-enabled dynamic composition of Semantic Web services. The approach and the framework have been developed in several research and development projects by ISRG and IOG. The core of the methodology is the new understanding of a Semantic Web service as a capability of an intelligent software agent supplied...
Among traditional users of Web resources, industry also has a growing set of smart industrial devices with embedded intelligence. Just as humans do, smart industrial devices need online services—for example, for condition monitoring, remote diagnostics, maintenance, and so on. In this chapter, we present one possible implementation framework for su...
The problem of service and resource matching is being actively discussed currently as a new challenging task for the next
generation of semantic discovery approaches for Web services and Web agents. A significant advantage is expected when using
an ontological approach to semantically describe and query services. A matchmaking problem arises when a...
Although UDDI does not provide support for semantic search, retrieval and storage, it is already accepted as an industrial
standard and a huge number of services already store their service specifications in UDDI. Objective of this paper is to analyze
possibilities and ways to use UDDI registry to allow utilization of meta-data encoded according to...
Bayesian Networks are proven to be a comprehensive model to describe causal relationships among domain attributes with probabilistic measure of appropriate conditional dependency. However, depending on task and context, many attributes of the model might not be relevant. If a network has been learned across multiple contexts then all uncovered cond...
Recent expectations from a new generation of Web strongly depend on a success of Semantic Web technology. Resource Description Framework (RDF) is a basis for explicit and machine readable representation of semantics of various Web resources and is enabling framework for interoperability of future Semantic Web-based applications. However it was alre...
Recent expectations regarding the new generation of Web strongly depend on the success of Semantic Web technology. Resource Description Framework (RDF) is a basis for an explicit and machine-readable representation of semantics of various Web resources and an enabling framework for interoperability of future Semantic Web-based applications. RDF is...
Integration of heterogeneous applications and data sources into an interoperable system is one of the most relevant challenges for many knowledge-based corporations nowadays. Development of a global environment that would support knowledge transfer from human experts to automated Web services, which are able to learn, is a very profit-promising and...
This research has been performed as a part of the SmartResource (“Proactive Self‐Maintained Resources in Semantic web”) project in Agora Center (University of Jyväskylä, Finland) and funded by TEKES and industrial consortium of following companies: Metso Automation, TeliaSonera, TietoEnator and Science Park. The authors are also grateful to Mr Joun...
Agent-oriented approach has proven to be very efficient in engineering complex distributed software environments with dynamically
changing conditions. The efficiency of underlying modelling framework for this domain is undoubtedly of a crucial importance.
Currently, a model-driven architecture has been the most popular and developed for purposes of...