Suparna De is a Senior Research Fellow at the Institute for Communication Systems (ICS), University of Surrey, UK. She obtained her Ph.D. and MSc. (with distinction) degrees in Electronic Engineering from the University of Surrey in 2009 and 2005, respectively. Prior to this, she received her Master in Information Technology degree from the University of Delhi, India and a BSc. Physics (with honours) degree from St. Stephen's College, University of Delhi.
She is currently guest-editing a special issue on Frontiers in Cyber-Physical-Social Data Fusion in Smart Cities in the Smart Cities journal (submissions due: 27 December 2019).
She has approximately 2.5 years of industry experience; having worked as a software engineer at Hughes Software Systems, India on 3G protocol stack development and at Sofblue India on Bluetooth smart meters and protocol stack software development.
She serves on the editorial board of the International Journal of Distributed Sensor Networks journal and on the review boards of several technical journals (ACM Transactions on Computer-Human Interaction, ACM Computing Surveys, IEEE Transactions on Network and Service Management, IEEE Systems, Sensors, IEEE Sensors, Elsevier Future Generation Computer Systems) and on the technical program committee of several conferences, including IEEE Infocom workshops 2019.
Areas of specialism
Affiliations and memberships
My research interests relate to the application of machine learning and semantic-Web technologies to knowledge engineering and data analytics in large-scale Cyber-Physical-Social systems. Current activities include data fusion and pattern derivation from cyber-physical and social streams, large-scale discovery and reasoning methods, including design and development of architectures and algorithms for distributed computing, knowledge modelling, distributed data retrieval and Big data analysis in various Internet of Things (IoT) deployments. Current research interests include machine learning techniques including deep learning, semantic knowledge modelling and distributed reasoning approaches, Big Data, service computing and pervasive computing.
Indicators of esteem
Invited talks and lectures
- Panel member on the IoT-enabled Smart Cities round-table at Intertraffic, Amsterdam (March 2018)
- Invited guest lecture on 'A Data-driven Approach for Internet of Things Applications: Methods and Case Studies' (October 2017), University of Granada, as part of their SEFORI lecture series for doctoral candidates.
Journal Guest editorship:
- Guest-editor: Special Issue on Frontiers in Cyber-Physical-Social Data Fusion in Smart Cities, Smart Cities journal. Submissions due December 27 2019
- Guest-editor: Special Issue on Advances in Optimization or Designs for Energy Efficient Internet of Things: Technologies, Algorithms, and Communication Protocols in the EURASIP Journal on Wireless Communications and Networking. Submissions due March 1 2019.
- Guest-editorship of a special issue on Big Data and Knowledge Extraction for Cyber-Physical Systems of the International Journal of Distributed Sensor Networks, SI published December 2017
- Overseas Research Student Sponsorship for PhD research (October 2005 - September 2009): University of Surrey and MobileVCE Core 4 programme
- DFIDSSS Scholarship (September 2004 - September 2005): jointly funded by the University of Surrey and the British Commonwealth Scholarship Commission for MSc programme.
- Cable and Wireless Award (2005): University of Surrey, for the best overall performance from a student graduating with an MSc in Satellite Communication Engineering or Communications Networks and Software
- IET Certificate (2009) in recognition of significant contribution to IET On Campus at the University of Surrey
- K. Meera Memorial Scholarship (1999): St. Stephen’s College, University of Delhi, India, for the best overall performance by a BSc. (H) Physics student
- Science Meritorious Student Award (1998): University of Delhi, India
Data analytics for Cyber-Physical and Social Streams
This research theme focusses on deriving latent patterns in CPSS data streams by developing novel ML algorithms; as well as fusion of social network data with sensor data streams. Our work looks at analysing social network data to extract real-world event information and human movements, in conjunction with sensor data and open datasets, to achieve outcomes related to quantifying their influence on smart city dynamics, such as traffic flows, measured pollution levels, redefining inner-city boundaries etc.
- Exploring the Effectiveness of Service Decomposition in Fog Computing Architecture for the Internet of Things, IEEE Transactions on Sustainable Computing, March 2019
- A Survey on an Emerging Area: Deep Learning for Smart City Data, IEEE Transactions on Emerging Topics in Computational Intelligence, May 2019
- Data-driven Air Quality Characterisation for Urban Environments: a Case Study, IEEE Access, December 2018
- Missing Data Estimation in Mobile Sensing Environments, IEEE Access 6(1), October 2018
- Cyber–Physical–Social Frameworks for Urban Big Data Systems: A Survey. MDPI Applied Sciences, 2017, 7 (10) (slideshare)
- Real world city event extraction from Twitter data streams, Procedia Computer Science, 2016, 98, pp. 443-448 (dataset)
Large scale sensor and data discovery and ranking
This research theme focuses on scalable, distributed discovery mechanisms supporting the sensor-as-a-service paradigm. Based on the particular localization characteristics of IoT deployments, our work has developed novel methods using geospatial indexing techniques and semantic service technologies for both sensor and sensor data discovery.
- Designing the Sensing as a Service Ecosystem for the Internet of Things, IEEE Internet of Things Magazine,1(2), December 2018
- Spatial Indexing for Data Searching in Mobile Sensing Environments. Sensors 2017, 17(6), 1427
- Search Techniques for the Web of Things: A Taxonomy and Survey, Sensors 2016, 16(5), 600
- An Experimental Study on Geospatial Indexing for Sensor Service Discovery, Expert Systems with Applications, Elsevier, May 2015 (ontology, dataset)
- A Ranking Method for Sensor Services based on Estimation of Service Access Cost, Information Sciences, Elsevier, October 2015 (code and dataset)
- Enabling Query of Frequently Updated Data from Mobile Sensing Sources, The 13th IEEE International Conferences on Ubiquitous Computing and Communications (IUCC2014), December 2014.
Semantic Models for the Internet of Things
This research theme focusses on semantic models for the main abstractions and concepts that underlie the IoT domain. The developed ontologies enable fine-grained semantic annotations, and to create Linked sensor data for service and data discovery.
- SmartTags: IoT Product Passport for Circular Economy Based on Printed Sensors and Unique Item-Level Identifiers, Sensors 2019, 19(3), 586.
- Knowledge Representation in the Internet of Things: Semantic Modelling and its Applications. Automatika – Journal for Control, Measurement, Electronics, Computing and Communications, December 2013.
- An Internet of Things Platform for Real-World and Digital Objects'. Scalable Computing: Practice and Experience, May 2012. (platform demo)
- Service modelling for the Internet of Things, IEEE Federated Conference on Computer Science and Information Systems (FEDCSIS), September 2011 (ontology)
Completed postgraduate research projects I have supervised
Yuchao Zhou (2013- 2017) (in collaboration with Prof. Klaus Moessner): Data-driven Cyber-Physical-Social System for Knowledge Discovery in Smart Cities
Postgraduate research supervision
External collaborative PhD supervisor for Qi Chen at the Xi’an Jiaotong-Liverpool University, China, November 2017 - 2020.
BEng project supervision
- 2018-19: Usamah F. Jassat, 'Latent Pattern Derivation in Smart City Big Data'
- 2018-19: Timur Engin, 'Social media sentiment as a reflection of real world outcomes: a Natural Language Processing analysis'
- 2016-2017: Alex Grace,‘Using Social Networks to Reveal City Dynamics'
MSc project supervision
- 2018-19: Cankat Inal, 'Using Deep Learning to Reveal Transportation Dynamics in Urban Regions'
- 2015-2016: Gideon Ewa, ‘Urban Tech for the Smart City’
- 2012-2013: Saurabh Gupta, ‘Multimedia Infotainer on Google Android Devices’
- 2012-2013: Yuchao Zhou, ‘Federated query processing on Linked Data’
- 2011-2012: Yuan Chen, ‘Google Android client for device discovery in future service platforms’
- 2011-2012: Panagiotis Mantzaridis, ‘User Preferences Learning for an Android Media Portal’
- 2011-2012: Marios Parthenios, ‘Events Playback – Automatic Presentation Generation from Media and News Sources’
- 2011-2012: Pallavi Subramaniam, ‘Personal Media Portal for Google Android Devices’
- 2009-2010: Gilbert Cassar, ‘Network Interface Transparent Service and Content Delivery’
by smart objects that are directly related to the physical world. A structured, machine-processible approach to provision such
real-world services is needed to make heterogeneous physical objects accessible on a large scale and to integrate them with the
digital world. The incorporation of observation and measurement data obtained from the physical objects with the Web data, using
information processing and knowledge engineering methods, enables the construction of ?intelligent and interconnected things?.
The current research mostly focuses on the communication and networking aspects between the devices that are used for sensing
amd measurement of the real world objects. There is, however, relatively less effort concentrated on creating dynamic infrastructures
to support integration of the data into the Web and provide unified access to such data on service and application levels. This
paper presents a semantic modelling and linked data approach to create an information framework for IoT. The paper describes
a platform to publish instances of the IoT related resources and entities and to link them to existing resources on the Web. The
developed platform supports publication of extensible and interoperable descriptions in the form of linked data.
context reasoning engine can derive meaning from the various context elements and
facilitate decision-taking for applications and context delivery mechanisms. The
heterogeneity of available device capabilities means that the recommendation
algorithm must be in a formal, effective and extensible form. Moreover, user
preferences, capability context and media metadata must be considered
simultaneously to determine appropriate presentation format. Towards this aim, this
paper presents a reasoning mechanism that supports service presentation through a
rule-based mechanism. The validation of the approach is presented through
application use cases.
situation will form the focus of ubiquitous environments. A description of the
networked environment at a semantic level will necessitate contextually
oriented knowledge acquisition methods. This then engenders unique
challenges for the crucial step of resource discovery. A number of service
discovery protocols exist to perform this role. In this paper, we identify the
requirements inherent for such an environment and investigate the suitability of
the available protocols against these. A suitable candidate solution is proposed
with an implementation with semantic extensions and reference points for
provisioning. The realization of such customizable smart spaces necessitates acquisition and processing of modality context information from a variety of devices in the ambient
environment. The heterogeneity of available device capabilities and description formats brings new challenges for a context reasoning engine that formulates content delivery decisions. Specifically, to ensure interoperability with existing application logic, the enabling components should support semantic queries.
Secondly, situations where variously formatted context input may not provide enough information to answer queries, should be intelligently handled. Towards this aim, this paper discusses a context reasoning and query interface component as part of a Service Context Manager (SCM) framework that supports semantic querying and handles incomplete context information through a rule-based mechanism. The validation of the approach is provided by showing the mapping of disparate UAProf and UPnP descriptions into the framework and querying of supported modality services.
ubiquitous environments opens a number of interlinked research challenges. On the lowest level of such systems, discovery mechanisms and flexible semantic descriptions of available devices and services form the basis for end-user service personalization. The challenge is to design a description model that leverages implicit semantic information obtained, while being cognizant of resource constraints of a
device. To encounter the different device
characteristics and personalization challenges, this paper proposes a device and service description approach that provides a high level contextual view of device information. The work has been performed as part of the Personal Distributed Environment concept, also described in the paper. Further, a user-centric view of multiple user interface devices to access
services in a heterogeneous and dynamic networked
environment has been implemented by extending UPnP device discovery. A comparison with existing state of the art approaches concludes the work.
distributed context handlers to derive meaning from context and combine it with application logic. Towards this aim, this paper presents a Service Context Manager (SCM) framework that
handles all the stages of context gathering, processing and reasoning to enable personalized service presentation. The validation of the approach is shown through application use cases.
become fundamental to resolve the problem of
interoperability given the distributed and heterogeneous
nature of the ?Things?. Most of the current research has
primarily focused on devices and resources modeling while
paid less attention on access and utilisation of the
information generated by the things. The idea that things are
able to expose standard service interfaces coincides with the
service oriented computing and more importantly,
represents a scalable means for business services and
applications that need context awareness and intelligence to
access and consume the physical world information. We
present the design of a comprehensive description ontology
for knowledge representation in the domain of Internet of
Things and discuss how it can be used to support tasks such
as service discovery, testing and dynamic composition.
Sensing Environments, Sensors MDPI
Things applications, which need to collect, process and analyze huge amounts of sensor stream data.
The problem in fact has been well studied for data generated by sensors that are installed at fixed
locations; however, challenges emerge along with the popularity of opportunistic sensing applications
in which mobile sensors keep reporting observation and measurement data at variable intervals and
changing geographical locations. To address these challenges, we develop the Geohash-Grid Tree,
a spatial indexing technique specially designed for searching data integrated from heterogeneous
sources in a mobile sensing environment. Results of the experiments on a real-world dataset collected
from the SmartSantander smart city testbed show that the index structure allows efficient search
based on spatial distance, range and time windows in a large time series database.
the Internet of Things (IoT). However, current work has mostly focused on IoT resource management while not
on the access and utilisation of information generated by the ?Things?. We present the design of a comprehensive
and lightweight semantic description model for knowledge representation in the IoT domain. The design follows
the widely recognised best practices in knowledge engineering and ontology modelling. Users are allowed to
extend the model by linking to external ontologies, knowledge bases or existing linked data. Scalable access to IoT
services and resources is achieved through a distributed, semantic storage design. The usefulness of the model is
also illustrated through an IoT service discovery method.
Applications, Proceedings of WoWMoM 2017
Things, embedded devices can be built into every fabric of urban
environments and connected to each other; and data continuously
produced by these devices can be processed, integrated at different
levels, and made available in standard formats through open
services. The data, obviously f a form of ?big data?, is now seen as
the most valuable asset in developing intelligent applications. As
the sizes of the IoT data continue to grow, it becomes inefficient
to transfer all the raw data to a centralised, cloud-based data
centre and to perform efficient analytics even with the state-ofthe-
art big data processing technologies. To address the problem,
this article demonstrates the idea of ?distributed intelligence? for
sensor data computing, which disperses intelligent computation
to the much smaller while autonomous units, e.g., sensor network
gateways, smart phones or edge clouds in order to reduce
data sizes and to provide high quality data for data centres.
As these autonomous units are usually in close proximity to
data consumers, they also provide potential for reduced latency
and improved quality of services. We present our research on
designing methods and apparatus for distributed computing on
sensor data, e.g., acquisition, discovery, and estimation, and
provide a case study on urban air pollution monitoring and
This thesis presents a data-centric framework for CPSS that contains management and processing capabilities for knowledge discovery from mobile sensing data and social networks content, by mainly addressing challenges from mobile sensing scenarios in CPSS, including: 1) interoperability issues caused by the vast amount of heterogeneous data sources; 2) thematic-spatial-temporal information retrieval of opportunistic mobile sensing; 3) incomplete datasets generated from noisy data sources of mobile sensing techniques; 4) different scales/types of data and information, which cannot be correlated directly.
The contributions of the thesis include 1) a data retrieval method that addresses the issue of searching for both current and historical sensor measurement values from the heterogeneous data sources; 2) a novel spatio-temporal model for regression analysis that can perform missing data estimation in the incomplete datasets; 3) a knowledge discovery mechanism that merges and correlates physical and social sensing data, enabling links between different scales/types of data: numeric values of sensor observation data and textual content of social networks? messages.
The above contributions were evaluated through experimentation on real smart city datasets and data collected from the Twitter social network to prove their accuracy and reliability, as well as to show the applicability of the proposed approaches to existing smart cities.
applications because of their cost efficiency, wide coverage and flexibility. However, these techniques are
unreliable in many situations due to noise of different kinds, loss of communication, or insufficient energy.
As such, datasets created from mobile sensing scenarios are likely to contain large amount of missing data,
which makes further data analysis difficult, inaccurate, or even impossible. We find that the existing
estimation models and techniques developed for static sensing do not work well in the mobile sensing
scenarios. To address the problem, we propose a spatio-temporal method, which is specifically designed for
answering queries in such applications. Experiments on a real-world, incomplete mobile sensing dataset
show that the proposed method outperforms the state-of-the-art noticeably in terms of estimation errors.
More importantly, the proposed model is tolerant to datasets with extremely high missing data rates.
Training with the proposed model is also efficient, which makes it suitable for deployment on
computationally constrained devices and platforms that need to process massive amounts of data in real
building a product passport and data exchange enabling the next stage of the circular economy.
SmartTags based on printed sensors (i.e., using functional ink) and a modified GS1 barcode standard
enable unique identification of objects on a per item-level (including Fast-Moving Consumer
Goods?FMCG), collecting, sensing, and reading of parameters from environment as well as tracking
a products? lifecycle. The developed ontology is the first effort to define a semantic model for
dynamic sensors, including datamatrix and QR codes. The evaluation of decoding and readability
of identifiers (QR codes) showed good performance for detection of sensor state printed over and
outside the QR code data matrix, i.e., the recognition ability with image vision algorithm was possible.
The evaluation of the decoding performance of the QR code data matrix printed with sensors was
also efficient, i.e., the QR code ability to be decoded with the reader after reversible and irreversible
process of ink (dis)appearing was preserved, with slight drop in performance if ink density is low.
consumption, public safety and so on. Research on smart cities aims to address these issues with various technologies developed for
the Internet of Things. Very recently, the research focus has shifted towards processing of massive amount of data continuously generated
within a city environment, e.g., physical and participatory sensing data on traffic flow, air quality, and healthcare. Techniques from computational intelligence have been applied to process and analyse such data, and to extract useful knowledge that helps citizens better understand their surroundings and informs city authorities to provide better and more efficient public services. Deep learning, as a relatively new paradigm in computational intelligence, has attracted substantial attention of the research community and demonstrated greater potential over traditional techniques. This paper provides a survey of the latest research on the convergence of deep learning and smart city from two perspectives: while the technique-oriented review pays attention to the popular and extended deep learning models, the application-oriented review emphasises the representative application domains in smart cities. Our study showed that there are still many challenges ahead for this emerging area owing to the complex nature of deep learning and wide coverage of smart city applications. We pointed out a number of future directions related to deep learning efficiency, emergent deep learning paradigms, knowledge fusion and privacy preservation, and hope these would move the relevant research one step further in creating truly distributed intelligence for smart cities.
The Internet of Things is infiltrating many businesses. It provides simple means to collect and analyze technical system data to
identify and optimize the performance of many things in our private and work lives. This technical revolution is also revealing new
challenges and issues with our current IoT technologies. New solutions like artificial intelligence, blockchain, and 5G promise to
overcome these challenges. Within this article we discuss with leading experts the pros and cons of these technologies and what it
means for future IoT business.
The Internet of Things envisions the creation of an environment
where everyday objects (e.g., microwaves, fridges,
cars, coffee machines) are connected to the Internet and make
users? lives more productive, efficient, and convenient. During
this process, everyday objects capture a vast amount of data
that can be used to understand individuals and their behaviors.
In the current IoT ecosystems, such data is collected and used
only by the respective IoT solutions. There is no formal way to
share data with external entities. We believe this is very inefficient
and unfair for users. We believe that users, as data owners,
should be able to control, manage, and share data about
them in any way that they choose and make or gain value out
of them. To achieve this, we proposed the sensing as a service
(S2aaS) model. In this article, we discuss the (S2aaS) ecosystem
in terms of its architecture, components, and related user interaction
designs. This article aims to highlight the weaknesses of
the current IoT ecosystem and to explain how S2aaS would
eliminate those weaknesses. We also discuss how an everyday
user may engage with the S2aaS ecosystem as well as design