Publications ⋆ Kawa Nazemi

Publications


Show all
2023
3.
 Banissi, Ebad;  Siirtola, Harri;  Ursyn, Anna;  Pires, João Moura;  Datia, Nuno;  Nazemi, Kawa;  Kovalerchuk, Boris;  Andonie, Razvan;  Nakayama, Minoru;  Temperini, Marco;  Sciarrone, Filippo;  Nguyen, Quang Vinh;  Mabakane, Mabule Samuel;  Rusu, Adrian;  Cvek, Urska;  Trutschl, Marjan;  Mueller, Heimo;  Francese, Rita;  Boua-li, Fatma;  Venturini, Gilles (Ed.)
Proceedings of 2023 27th International Conference Information Visualisation Proceedings 
2023, ISBN: 979-8-3503-4161-4.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Data Analytics, Data Science, Visual analytics, Visual Knowledge Discovery
@proceedings{Banissi2023,

title = {Proceedings of 2023 27th International Conference Information Visualisation},

editor = {Ebad Banissi and Harri Siirtola and Anna Ursyn and João Moura Pires and Nuno Datia and Kawa Nazemi and Boris Kovalerchuk and Razvan Andonie and Minoru Nakayama and Marco Temperini and Filippo Sciarrone and Quang Vinh Nguyen and Mabule Samuel Mabakane and Adrian Rusu and Urska Cvek and Marjan Trutschl and Heimo Mueller and Rita Francese and Fatma Boua-li and Gilles Venturini},

doi = {10.1109/IV60283.2023.00001},

isbn = {979-8-3503-4161-4},

year  = {2023},

date = {2023-11-01},

urldate = {2023-11-01},

issue = {IV2023},

abstract = {Do aspects of our lives depend on and are driven by data, information, knowledge, user experience, and cultural influences in the current information era? Does the infrastructure of any information-dependent society rely on the quality of data, information, and analysis of such entities from past and present and projected future activities and, most importantly, how it is intended to be applied? Information Visualization, Analytics, Machine Learning, Artificial Intelligence, and Application domains are state-of-the-art developments that effectively enhance understanding of these well-established drivers. Several key interdependent variables are emerging that are becoming the focus of scientific activities, such as Information and Data Science. Aspects tightly tie raw data (origin, autonomous capture, classification, incompleteness, impurity, filtering) and data scale to knowledge acquisition. Its dependencies on the application domain and its evolution steer the next generation of research activities. From raw data to knowledge, processing the relationship between these phases has added new impetus to understanding and communicating these. The tradition of use and communication by visualization is deep-rooted. It helps us investigate new meanings for the humanities, history of art, design, human factors, and user experience, leading to knowledge discoveries and hypothesis analysis. Modern-day computer-aided analytics and visualization have added momentum in developing tools that exploit metaphor-driven techniques within many applied domains to simply storytelling through data. The methods are developed beyond visualization to simplify the complexities, reveal ambiguity, and work with incompleteness. The next phase of this evolving field is to understand uncertainty, risk analysis, and tapping into unknowns; this uncertainty is built into all stages of the processes, from raw data to the knowledge acquisition stage. But there is a new twist: fast-developing generative AI with ever-increasing access to data outsmarting humans in decision-making. A new evolutionary step in the human journey, no doubt.},

keywords = {Artificial Intelligence, Data Analytics, Data Science, Visual analytics, Visual Knowledge Discovery},

pubstate = {published},

tppubtype = {proceedings}

}

Close
Do aspects of our lives depend on and are driven by data, information, knowledge, user experience, and cultural influences in the current information era? Does the infrastructure of any information-dependent society rely on the quality of data, information, and analysis of such entities from past and present and projected future activities and, most importantly, how it is intended to be applied? Information Visualization, Analytics, Machine Learning, Artificial Intelligence, and Application domains are state-of-the-art developments that effectively enhance understanding of these well-established drivers. Several key interdependent variables are emerging that are becoming the focus of scientific activities, such as Information and Data Science. Aspects tightly tie raw data (origin, autonomous capture, classification, incompleteness, impurity, filtering) and data scale to knowledge acquisition. Its dependencies on the application domain and its evolution steer the next generation of research activities. From raw data to knowledge, processing the relationship between these phases has added new impetus to understanding and communicating these. The tradition of use and communication by visualization is deep-rooted. It helps us investigate new meanings for the humanities, history of art, design, human factors, and user experience, leading to knowledge discoveries and hypothesis analysis. Modern-day computer-aided analytics and visualization have added momentum in developing tools that exploit metaphor-driven techniques within many applied domains to simply storytelling through data. The methods are developed beyond visualization to simplify the complexities, reveal ambiguity, and work with incompleteness. The next phase of this evolving field is to understand uncertainty, risk analysis, and tapping into unknowns; this uncertainty is built into all stages of the processes, from raw data to the knowledge acquisition stage. But there is a new twist: fast-developing generative AI with ever-increasing access to data outsmarting humans in decision-making. A new evolutionary step in the human journey, no doubt.
Close
doi:10.1109/IV60283.2023.00001
Close
2022
2.
 Kaupp, Lukas;  Nazemi, Kawa;  Humm, Bernhard
Context-Aware Diagnosis in Smart Manufacturing: TAOISM, An Industry 4.0-Ready Visual Analytics Model Book Chapter 
In:  Kovalerchuk, Boris;  Nazemi, Kawa;  Andonie, Răzvan;  Datia, Nuno;  Banissi, Ebad (Ed.): Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery, pp. 403–436, Springer International Publishing, Cham, 2022, ISBN: 978-3-030-93119-3.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Machine Leanring, Machine learning, mobility indicators for visual analytics, smart factory, Smart manufacturing, Visual Analytical Reasoning, Visual analytics, Visual Knowledge Discovery
@inbook{Kaupp2022,

title = {Context-Aware Diagnosis in Smart Manufacturing: TAOISM, An Industry 4.0-Ready Visual Analytics Model},

author = {Lukas Kaupp and Kawa Nazemi and Bernhard Humm},

editor = {Boris Kovalerchuk and Kawa Nazemi and Răzvan Andonie and Nuno Datia and Ebad Banissi},

url = {https://doi.org/10.1007/978-3-030-93119-3_16},

doi = {10.1007/978-3-030-93119-3_16},

isbn = {978-3-030-93119-3},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery},

pages = {403--436},

publisher = {Springer International Publishing},

address = {Cham},

abstract = {The integration of cyber-physical systems accelerates Industry 4.0. Smart factories become more and more complex, with novel connections, relationships, and dependencies. Consequently, complexity also rises with the vast amount of data. While acquiring data from all the involved systems and protocols remains challenging, the assessment and reasoning of information are complex for tasks like fault detection and diagnosis. Furthermore, through the risen complexity of smart manufacturing, the diagnosis process relies even more on the current situation, the context. Current Visual Analytics models prevail only a vague definition of context. This chapter presents an updated and extended version of the TAOISM Visual Analytics model based on our previous work. The model defines the context in smart manufacturing that enables context-aware diagnosis and analysis. Additionally, we extend our model in contrast to our previous work with context hierarchies, an applied use case on open-source data, transformation strategies, an algorithm to acquire context information automatically and present a concept of context-based information aggregation as well as a test of context-aware diagnosis with latest advances in neural networks. We fuse methodologies, algorithms, and specifications of both vital research fields, Visual Analytics and Smart Manufacturing, together with our previous findings to build a living Visual Analytics model open for future research.},

keywords = {Artificial Intelligence, Machine Leanring, Machine learning, mobility indicators for visual analytics, smart factory, Smart manufacturing, Visual Analytical Reasoning, Visual analytics, Visual Knowledge Discovery},

pubstate = {published},

tppubtype = {inbook}

}

Close
The integration of cyber-physical systems accelerates Industry 4.0. Smart factories become more and more complex, with novel connections, relationships, and dependencies. Consequently, complexity also rises with the vast amount of data. While acquiring data from all the involved systems and protocols remains challenging, the assessment and reasoning of information are complex for tasks like fault detection and diagnosis. Furthermore, through the risen complexity of smart manufacturing, the diagnosis process relies even more on the current situation, the context. Current Visual Analytics models prevail only a vague definition of context. This chapter presents an updated and extended version of the TAOISM Visual Analytics model based on our previous work. The model defines the context in smart manufacturing that enables context-aware diagnosis and analysis. Additionally, we extend our model in contrast to our previous work with context hierarchies, an applied use case on open-source data, transformation strategies, an algorithm to acquire context information automatically and present a concept of context-based information aggregation as well as a test of context-aware diagnosis with latest advances in neural networks. We fuse methodologies, algorithms, and specifications of both vital research fields, Visual Analytics and Smart Manufacturing, together with our previous findings to build a living Visual Analytics model open for future research.
Close
https://doi.org/10.1007/978-3-030-93119-3_16
doi:10.1007/978-3-030-93119-3_16
Close
1.
 Kaupp, Lukas;  Nazemi, Kawa;  Humm, Bernhard
Context-Aware Diagnosis in Smart Manufacturing: TAOISM, An Industry 4.0-Ready Visual Analytics Model Book Chapter 
In:  Kovalerchuk, Boris;  Nazemi, Kawa;  Andonie, Răzvan;  Datia, Nuno;  Banissi, Ebad (Ed.): Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery, pp. 403–436, Springer International Publishing, Cham, 2022, ISBN: 978-3-030-93119-3.
Abstract | Links | BibTeX | Tags: Artificial Intelligence, Machine Leanring, Machine learning, mobility indicators for visual analytics, smart factory, Smart manufacturing, Visual Analytical Reasoning, Visual analytics, Visual Knowledge Discovery
@inbook{Kaupp2022b,

title = {Context-Aware Diagnosis in Smart Manufacturing: TAOISM, An Industry 4.0-Ready Visual Analytics Model},

author = {Lukas Kaupp and Kawa Nazemi and Bernhard Humm},

editor = {Boris Kovalerchuk and Kawa Nazemi and Răzvan Andonie and Nuno Datia and Ebad Banissi},

doi = {10.1007/978-3-030-93119-3_16},

isbn = {978-3-030-93119-3},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {Integrating Artificial Intelligence and Visualization for Visual Knowledge Discovery},

pages = {403–436},

publisher = {Springer International Publishing},

address = {Cham},

abstract = {The integration of cyber-physical systems accelerates Industry 4.0. Smart factories become more and more complex, with novel connections, relationships, and dependencies. Consequently, complexity also rises with the vast amount of data. While acquiring data from all the involved systems and protocols remains challenging, the assessment and reasoning of information are complex for tasks like fault detection and diagnosis. Furthermore, through the risen complexity of smart manufacturing, the diagnosis process relies even more on the current situation, the context. Current Visual Analytics models prevail only a vague definition of context. This chapter presents an updated and extended version of the TAOISM Visual Analytics model based on our previous work. The model defines the context in smart manufacturing that enables context-aware diagnosis and analysis. Additionally, we extend our model in contrast to our previous work with context hierarchies, an applied use case on open-source data, transformation strategies, an algorithm to acquire context information automatically and present a concept of context-based information aggregation as well as a test of context-aware diagnosis with latest advances in neural networks. We fuse methodologies, algorithms, and specifications of both vital research fields, Visual Analytics and Smart Manufacturing, together with our previous findings to build a living Visual Analytics model open for future research.},

keywords = {Artificial Intelligence, Machine Leanring, Machine learning, mobility indicators for visual analytics, smart factory, Smart manufacturing, Visual Analytical Reasoning, Visual analytics, Visual Knowledge Discovery},

pubstate = {published},

tppubtype = {inbook}

}

Close
The integration of cyber-physical systems accelerates Industry 4.0. Smart factories become more and more complex, with novel connections, relationships, and dependencies. Consequently, complexity also rises with the vast amount of data. While acquiring data from all the involved systems and protocols remains challenging, the assessment and reasoning of information are complex for tasks like fault detection and diagnosis. Furthermore, through the risen complexity of smart manufacturing, the diagnosis process relies even more on the current situation, the context. Current Visual Analytics models prevail only a vague definition of context. This chapter presents an updated and extended version of the TAOISM Visual Analytics model based on our previous work. The model defines the context in smart manufacturing that enables context-aware diagnosis and analysis. Additionally, we extend our model in contrast to our previous work with context hierarchies, an applied use case on open-source data, transformation strategies, an algorithm to acquire context information automatically and present a concept of context-based information aggregation as well as a test of context-aware diagnosis with latest advances in neural networks. We fuse methodologies, algorithms, and specifications of both vital research fields, Visual Analytics and Smart Manufacturing, together with our previous findings to build a living Visual Analytics model open for future research.
Close
doi:10.1007/978-3-030-93119-3_16
Close