Four special sessions have been accepted by DSAA’2020:

1. Data Science for Cyber Physical Systems
2. Environmental and Geo-spatial Data Analytics (EnGeoData)
3. Fake News, Bots and Trolls
4. Privacy, Security and Trust in Computational Intelligence

Aims and scope:
Special Session on Data Science for Cyber Physical Systems (DSCPS) aims to bridge research in the data mining and engineering community (both industry and research) by providing an open and interactive forum for researchers who are interested in data mining and CPS. To discuss the methodologies and technical foundations of data mining, machine learning, artificial intelligence, and other knowledge discovery approaches for mining and analyzing various types of CPS data. The overall objective is to facilitate specialized tasks in safety, security, and resilience of CPS. Participants of diverse background in either data mining, electrical and computer engineering, and software engineering can benefit from this Special Session.

Special Session on Data Science for Cyber Physical Systems (DSCPS) is the 1st Special Session focusing on original research on concepts, tools, and techniques from computer science, control theory, and applied mathematics for the analysis and control of cyber physical systems, with an emphasis on safety and security. By drawing on strategies from data mining, analysis, computation and control, the mining for cyber physical systems is applicable to both man-made cyber-physical systems (ranging from small robots to global infrastructure networks) and natural systems (ranging from biochemical networks to physiological models). Papers in the Special Session are expected to range over a wide spectrum of topics from theoretical results to practical considerations, and from academic research to industrial adoption.

Topics of Interest:
Topics of interest include, but are not limited to:

• Mining for Analysis, verification, validation, and testing.
• Mining for Design, synthesis, planning, and control.
• Programming and specification language.
• Security, privacy, and resilience for cyber-physical systems with focus on computation and control.
• Safe autonomy, Artificial intelligence and Machine learning in cyber-physical systems.
• Applications and industrial case studies in: automotive, transportation, autonomous systems, avionics, energy and power, robotics, medical devices, manufacturing, systems and synthetic biology, models for the life sciences, and other related areas.

Organizers:

• Apurva Narayan, The University of British Columbia, Canada
• Kapil Mathur, Microsoft, USA

Contact: apurva.narayan@ubc.ca.

Aims and scope:
Environmental and geo-spatial data is currently obtained by crowdsourcing and public administrations in the context of open data policies. Mining EnGeo data can provide significant insights and potentials to several domains such as public health, medicine, agriculture, among others. In public health, EnGeo data analysis can help detect, control, and monitor diseases caused by social phenomena (e.g., urbanization, globalization, trade, etc.), and by environmental factors (e.g., outdoor/indoor air pollution, water, sanitation, etc.). In the context on changing environment, “One Health” approaches focus on interconnection between people, animals, plants, and their shared environment. In this domain, ingestion and mining environmental and geo-spatial data is crucial for early detection, warning and assessment of threats for (re-)emergence of infectious diseases. In agriculture, the use of digital tools, methods, and technologies increases the amount of produced data, which can also be leveraged to identify variations in the field (e.g. crops, soil conditions, water
quality), and to deal with them using alternative strategies.
The analysis of EnGeo data is thus associated with two major challenges:

• The integration of heterogenous data and formats due to the high variability of data types such as structured, semantic, spatial and temporal.
• The selection of the appropriate knowledge discovery process according to different fields.

The main objective of this special session is to provide high quality research facing both challenges previously mentioned with theoretical or experimental approaches.

Topics of Interest:
Topics of interest include, but are not limited to:

• Pre and post processing of environmental data.
• Geographical information retrieval.
• Spatial data mining, data warehousing, and spatial data lake.
• Knowledge discovery use-cases applied to environmental data.
• Spatial text mining.
• Spatial ontology.
• Spatial recommendation and personalization.
• Visual analytics for geospatial data.
• Dedicated applications:
  • Spatio-temporal analytics platform.
  • Agricultural decision support systems.
  • Urban traffic systems.
  • Trajectory analysis.
  • Land-use and urban policies.
  • Land-use and urban planning analysis.
  • Spatio-temporal analysis in ecology and agriculture.
  • Disease surveillance systems (One Health).
• Technically supported by ACM SIGKDD and ASA.

Acknowledgements:
This session is supported by the MOOD project and the French National Research Agency under the Investments for the Future Program, referred to as ANR-16-CONV-0004 (#DigitAg). The MOOD project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 874850.

Organizers:

• Juan Antonio Lossio-Ventura, Stanford University, USA
• David McMeekin, Curtin University, Australia
• Mathieu Roche, CIRAD, TETIS, France
• Maguelonne Teisseire, INRAE, TETIS, France

Contact: engeodata@teledetection.fr.

The timetable of this session can be found in: https://www.sites.google.com/view/fake-news-bots-trolls/program
Aims and scope:
Fake news has become one of the main threats to our society. Although fake news is not a new phenomenon, the exponential growth of social media has offered an easy platform for its fast and wide propagation. The threat is even greater when fake news dissemination has a political or an ideological purpose, as it happens during electoral campaigns or during extreme events able to endanger political regimes, such as epidemics. Bots are commonly related to fake news spreading. They can artificially inflate the popularity of an opinion or a political candidate, as well as undermine the reputation of a targeted politician and hinder an opposing view, by repeatedly spamming contents produced by disinformation outlets. Other actors of misbehaviour in social media are trolls that offend people, dominate online discussions, and in general try to manipulate people’s opinion by triggering hate and anger, with the aim of interfering with the regular public debate.

In this special session we would like the research community to share how the above problems need to be addressed from several interdisciplinary perspectives. Special emphasis will be on how news broadcasting corporations fact check claims by politicians, public figures, advocacy groups and institutions engaged in the public debate; how crowd signals in social media can be used to flag fake news; how online user activity fingerprints can be leveraged in order to detect a malicious use of social networks; how pieces of disinformation spread on social networks; how fake news broadcasters cooperate to conduct misinformation campaigns; how to design a semi-automated system that could trace and/or verify news shared online, helping journalists to identify disinformation.

Topics of Interest:
Topics of interest include, but are not limited to:

• Computational approaches to the following tasks:
  • Detection of fake news spreaders.
  • Detection of bots and trolls.
  • Identification of information generated by bots and trolls.
  • Patterns in fake news propagation.
  • Credibility assessment of online information and information sources.
  • Detection of polarization in online communities.
  • Multimodal fake news detection.
  • Eary detection of fake news.
  • Fake news prevention, filtering and containment.
  • Analysis/detection of multi-platform fake news spreading.
• Others:
  • Measurements and analysis of fake news impact.
  • Resources for journalists for fake news detection.

Organizers:

• Barrón-Cedeño Alberto, DIT, Università di Bologna, Italy
• Giachanou Anastasia, Universitat Politècnica de València, Spain
• Koltsova Olessia, National Research University Higher School of Economics, Russia
• Paolo Rosso, Universitat Politècnica de València, Spain
• Semeraro Alfonso, Università degli Studi di Torino, Italy
• Xiuzhen Jenny Zhang, RMIT University, Australia

Programme committee:

• Aiello Luca, Bells Labs, London, UK
• Carman Mark, Politecnico di Milano, Italy
• Ciampaglia Giovanni Luca, University of South Florida, US
• De Domenico Manlio, Bruno Kessler Foundation, Italy
• Ferres Leo, Universidad de Deserrollo, Santiago de Chile, Chile
• Ghanem Bilal, Universitat Politècnica de València, Spain
• Gil Hermenegildo, Universitat Politècnica de València, Spain
• Koltsov Sergei, National Research University Higher School of Economics, Russia
• Montes y Gómez Manuel, INAOE Puebla, Mexico
• Nakov Preslav, Qatar Computing Research Institute, Qatar
• Panchenko Alexander, Skoltech University, Russia
• Paolotti Daniela, ISI Foundation, Turin, Italy
• Ponzetto Simone Paolo, Univesität Mannheim, Germany
• Rangel Francisco, Symanto, Germany
• Rubin Victoria, University of Western Ontario, Canada
• Schifanella Rossano, Università degli Studi di Torino, Italy
• Sidorov Grigori, National Polytechnic Institute, Mexico
• Stratu Strelet Doina, Universitat Politècnica de València, Spain
• Tambuscio Marcella, Austraian Academy of Science, Austria

Contact: prosso@dsic.upv.es.

Aims and scope:
The enormous computation, communication and storage capabilities of the state-of-the-art computing paradigms such as cloud computing, Internet of Things (IoTs) and edge computing, have enabled a variety of large-scale applications and services that generate big data. The main and ultimate goal of the collection and storage of the big data is to extract the intelligence and insights for our decision-makings. Traditional computational intelligence algorithms need to be significantly revised or new computational intelligence algorithms have to be designed in order to make use of the scalable and distributed computing infrastructure mentioned above for big data analytics. However, the characteristics of such infrastructural platforms like ubiquitous access and multi-tenant pose unprecedented security threats on the computational intelligence algorithms and frameworks, render users more vulnerable to privacy leakage when extracting rich information from big data, and challenge the trust management of the numerous computing services and diverse data sources for computational intelligence. Hence, it is high time to investigate the privacy, security and trust issues in computation intelligence in the era of cloud/edge computing and big data. This special session aims at providing a forum for researchers, practitioners and developers from different background areas such as computational intelligence, data privacy and security, trust management, cloud computing, edge computing, Internet of Things, big data analytics, machine learning and data mining, knowledge discovery to exchange the latest experience, research ideas and synergic research and development on fundamental issues and applications about privacy, security and trust issues in computational intelligence. This special session invites authors to submit original manuscripts that demonstrate and explore current advances in all related areas mentioned above.

Topics of Interest:
Topics of interest include, but are not limited to:

• New challenges brought by IoT/edge/cloud to computational intelligence.
• New theories and modelling for privacy, security and trust.
• Privacy, security and trust in deep/reinforcement learning models.
• Privacy-preserving big data mining/publishing.
• Secure and scalable machine learning.
• Privacy, security and trust issues in Smart-X technologies.
• Computational intelligence for information security and privacy.
• Security and trust management for computational intelligence frameworks.
• Secure hardware design and implementation for computational intelligence.
• Real-world applications of computational intelligence for privacy, security and trust.
• Information hiding and encryption.
• Security and privacy issues, trends, and challenges in cloud/edge and IoT.

Organizers:

• Xuyun Zhang, xuyun.zhang@mq.edu.au, Macquarie University, Australia
• Guanfeng Liu, guanfeng.liu@mq.edu.au, Macquarie University, Australia
• Chi Yang, yangchi-hust@hust.edu.cn, Huazhong University of Science and Technology, China

Programme committee:

• Chunjie Zhou, Ludong University, China
• Chao Chen, Swinburne University of Technology, Australia
• Deepak Puthal, Newcastle University, UK
• Dieter Gollmann, Hamburg University of Technology, Germany
• Dongseong Kim, University of Queensland, Australia
• Francesco Palmieri, University of Salerno, Italy
• Gaofeng Zhang, Hefei University of Technology, China
• Hadis Karimipour, University of Guelph, Canada
• Hao Wang, Norwegian University of Science and Technology, Norway
• Haolong Xiang, University of Auckland, New Zealand
• Hongsheng Hu, University of Auckland, New Zealand
• Javier Parra-Arnau, Universitat Rovira i Virgili, Spain
• Jinguang Han, Queen’s University Belfast, U.K.
• Junwen Lu, Xiamen University of Technology, China
• Kar-Ann Toh, Yonsei University, South Korea
• Lam Kwok Yan, Nanyang Technological University, Singapore
• Liangfu Lv, Tianjin University, China
• Lianyong Qi, Qufu Normal University, China
• Lingjuan Lyu, National University of Singapore, Singapore
• Luigi Catuogno, University of Salerno, Italy
• Lutful Karim, Seneca College of Applied Arts and Technology, Canada
• Meng Liu, Shandong University, China
• Mingzhong Wang, University of the Sunshine Coast, Australia
• Mohammed EI-Abd, American University of Kuwait, KW
• Nathan Clarke, University of Plymouth, UK
• Saeid Hosseini, Sohar University, Oman
• Shunmei Meng, Nanjing University of Science and Technology, China
• Silvio Barra, University of Salerno, Italy
• Vincenzo Moscato, University of Naples, Italy
• Weizhi Meng, Technical University of Denmark, Denmark
• Wenjuan Li, Hong Kong Polytechnic University, HongKong
• Wenmin Lin, Hangzhou Normal University, China
• Xiao Liu, Deakin University, Australia
• Xiaochun Cheng, Middlesex University, U.K.
• Xiaolong Xu, Nanjing University of Information Science and Technology, China
• Xuan Zhao, Nanjing University, China
• Yanwei Xu, Tianjin University, China
• Yifeng Zheng, CSIRO, Australia
• Yirui Wu, Hohai University, China
• Zhiyuan Tan, Edinburgh Napier University, U.K.

Contact: xuyun.zhang@mq.edu.au.