Program in Detail

The I4CS 2022 program flyer

You find all information and details on the conference in our program flyer.


Invited Speakers

Have a look at the details on our invited speakers.

Session 1: Applied Security & Privacy

Monday, June 13, 2021, 10:30 a.m.

Jörg RothA Platform for Offline Voice Assistants
Abstract: Smart speakers provide a convenient way to request information or control the smart home. Commercial devices require central services operated by large companies. As a result, many users are concerned about privacy and security. A solution could be to shift all involved software components to the end-user device. Even though we then cannot access the large variety of functions of commercial smart speakers, they often are sufficient for common applications such as weather forecast, public transportation timetables or to control smart home devices. Even though existing voice interaction platforms already provide basic functions such as wake word detection and speech recognition, a developer still has to put huge efforts to create smart speaker applications. In this paper we present the JabberBrick platform that significantly simplifies such developments.
Fatima Chahal, Dominique Gaiti and Hacene Fouchal

Consensus Algorithms in Cryptocurrency and V2X-IoT: Preliminary study

Abstract: Globalization has had a profound impact on human life, resulting in the digitalization of many essential jobs. This development, of course, demonstrated the need to improve everything in the business world in order to satisfy the demands of the modern-day. In recent decades, there has been a clear need for a distributed database, and the Blockchain has proven to be an excellent solution. The Blockchain is a technology that allows for the storage of various types of transactions in connected blocks, with no way of deleting what has been entered on the ledgers, and therefore all business transactions are saved and secured. The consensus algorithm, which is responsible for confirming the blocks, sorting them, and ensuring everyone agree on them, is at the heart of the blockchain design. And, because blockchain is used in a variety of domains, the requirements change, and the consensus algorithm must accommodate these changes, which has resulted in the development of hundreds of algorithms. The goal of this study is to present the most useable algorithm in the cryptocurrency domain, as well as V2X communication, then, based on basic criteria, we compared these algorithms to evaluate which one is more efficient.

Günter Fahrnberger

Realtime Risk Monitoring of SSH Brute Force Attacks
Abstract: The Secure Shell (SSH) has served for years as the primary protocol to securely control networked remote devices. In particular, administrators of Linux and, to an increasing degree, also Windows operating systems with powerful rights capitalize on the speed and convenience of SSH. Consequentially, villains zero in on acquiring these mighty privileges, preferably by attempting a myriad of credentials until success or exhaustion. All known pertinent scientific resources limit themselves to compiling of descriptive statistics or detecting of such brute force attacks. The reviewed articles and papers neglect that each penetration attempt implies a differing hazard for an aim. This contribution bridges the gap by surveying affine academical material and elaborating the blind spot of realtime risk monitoring of SSH brute force attacks. Beyond that, this document formally verifies the hazardously raised likeliness of SSH brute force attacks that knowingly or unwittingly use the same patterns as the passwords of their targets. Based on that, it presents a viable solution with a Condition Monitoring System (CMS) that monitors SSH brute force attacks and assesses their jeopardy in real time.

Back to Program Overview, Top

Session 2: Energy Harvesting & Environment Protection

Monday, June 13, 2022, 16:30

Michal Hodoň, Peter Ševčík, Juraj Miček, Veronika Olešnániková, Peter Šarafín, Jan Kapitulík and Lukáš Čechovič

Solar energy harvesting for the mobile robotic platform

Abstract: This paper describes the educational mobile robotic platform Solarcar. The platform is used for teaching purposes, especially for description of theoret-ical as well as practical aspects of using alternative energy sources in embedded system design. The robot was designed and built as the supportive material for the students of study field Computer engineering, for the subject Embedded sys-tems. Through its usage, the principles of so called Green computing in the back-ground of complex physics are taught in a playful, and for students interesting way.
Karl Seidenfad, Tobias Wagner, Razvan Hrestic and Ulrike LechnerDemonstrating Feasibility of Blockchain-Driven Carbon Accounting – a Design Study and Demonstrator
Abstract: Carbon accounting calls for innovative digital infrastructures. The Paris Agreement and the 26th UN Climate Change Conference held 2021 in Glasgow provide the frame for designing information systems for carbon accounting. This paper explores blockchain as a technology for carbon accounting and, in particular, for the Product Carbon Footprint. We explore a design to integrate carbon accounting into an existing supply chain with two main parts (1) a brief analysis of core architectural designs of carbon footprints, consortia, and token and smart contract infrastructure and (2) experiences from design and implementation of a demonstrator. A coffee supply chain exemplifies the approach. Hyperledger Fabric and Minifabric from Hyperledger Labs are the technical frameworks used.

Back to Program Overview, Top

Session 3: Smart Cities & Standardization

Thuesday, June 14, 2022, 8:30 a.m.

Lennox Kim, Frank Phillipson and Robert WezemanA Multi Service Capacitated Facility Location Problem with Stochastic Demand
Abstract: This paper considers the problem of identifying optimal locations for wireless service installations in smart cities. The problem is modelled as a facility location problem with multiple service types, known as the Multi Service Facility Location Problem (MSCFLP). Given a set of potential facility locations and demand point data, the goal is to identify at which locations the facilities should be opened, and which demand points should be serviced by each open facility in order to minimise costs. In this study, the demand quantities at each demand point are assumed to follow a probability distribution. An adaptive neighbourhood search heuristic is proposed in order to find a good solution to the problem, where the stochastic demand was translated to a deterministic capacity constraint. The heuristic iteratively improves the service allocations in sub-regions of the problem instances, starting from an initial feasible solution. The results show that the heuristic is able to find good solutions within very short time. Furthermore, we assessed the handling of the stochasticity by the model. Its performance is assessed by means of simulation, and results show that this approach works well in various scenarios of traffic models.
Rebekka Alsvåg, Anthony Bokolo and Sobah Abbas PetersenThe role of a Data Marketplace for innovation and value-added services in Smart and Sustainable cities
Abstract: In this era of digitization, data is seen as the new oil due to the abundance of data generated from Internet of Things (IoT) sensors, social media and other platforms. Although prior studies have explored the challenges and opportunities that may arise in using these data to provide value added services, few studies explore how data from public, private and commercial data owners in smart cities and communities could enhance data reuse and sharing and collaboration among the different stakeholders. This study employs the system design approach to develop a data marketplace prototype, which provides data to create value-added services that could improve the lives of citizens. The prototype is developed for easy sharing, trading and utilization of available data for innovative services through collaboration. Qualitative data was collected using semi-structured interviews from experts in academia and industry to validate the concept of a data marketplace. Findings from this study reveal that the prototype data marketplace is useful, easy to use, and supports data trading.

Dirk Von Hugo, Gerald Eichler and Behcet Sarikaya

Challenges of Future Smart and Secure IoT Networking
Abstract: Upcoming future telecommunication networks will have to provide reliable, secure, and high-quality connectivity between highly diverse devices and a plurality of service and content provider domains, using ideally compatible inter-operable fixed and mobile converged access technologies. Today, the majority of actual communication requests and user applications are initiated by both, human beings via personal handheld devices, and a plethora of types of machines, i.e., smart devices as sensors, watches, household appliances etc., setting up the so-called Internet of Things. The amount of the latter ones will increase, whereas new device types will emerge steadily and may span up a new market very well comparable to that of traditional human-centric communication – especially in view of the current vision to meet challenges to mankind as climate change, endemic diseases, unequal distribution of wealth and health in a global scale by means of digitalization and Information and Communication Technology. To enable ease of operation at affordable costs for secure automatic deployment, upgrade, and maintenance of IoT, new models are required also for bootstrapping, authenticating, and subsequently authorizing a device during network attachment procedure, even without demanding specific and potentially complex or error-prone customer activity. In cellular networks such authentication traditionally utilizes subscriber specific chip cards, whereas for local radio connections as attachment to WiFi routers, generally a user interaction in terms of, e.g., username/credential provision is required today. The need for much simpler and cost-efficient procedures resulted in approaches based on detecting and recognizing characteristic signals via, e.g., video/audio/haptic sensors, i.e., camera, microphone, or a touch-sensitive surface besides radio-based sensing of shapes or gestures. This contribution evaluates typical use cases and describes the problem space including underlying key issues related to sensing technologies and intelligent data analysis, but also measures to improve, e.g., reliability and resilience. The concepts investigated by different standard developing organizations are reviewed, and a set of open challenges and research topics are identified.

Back to Program Overview, Top

Session 4: Smart Mobility & Routing

Thuesday, June 14, 2022, 10:30 a.m.

Jesper Slik and Sandjai BhulaiUnderstanding human mobility for data-driven policy making
Abstract: This study aims to identify the patterns of behavior which underlie human mobility. More specifically, we compare commuters who drive in a car with those who use the train in the same geographic region of the Netherlands. We try to understand the mode choices of the commuters based on three factors: the cost of the transport mode, the CO$_2$ emissions, and the travel time. The analysis has been based on data consisting of travel transactions in the Netherlands during 2018 containing over half a million records. We show how this raw data can be transformed into relevant insights on the three factors. A large difference is observed in terms of CO$_2$ emissions and cost, a minor difference in speed. Besides, the computation of congestion shows intuitive results. These results can be used to stimulate behavioral change proactively and to improve trip planners.
Moritz Peter Weber and Ilenia SalvadoriResearch on detecting similarity in trajectory data and possible use cases
Abstract: Today’s road traffic is extremely complex and its management offers many opportunities for improvement. By determining similarities between different tracks, it should be possible to reduce congestion times, for example by suggesting car sharing among the different participants. This traffic data should be analyzed on the foundation of similarity calculations in order to recognize possible future dangerous situations in advance and to prevent them with the help of a warning to the participants. With this work an attempt has been made to identify similar tracks based on different criteria, in such a way to build the basis of a more complex system which could potentially address different use cases in the road traffic system. In the following sections, the use cases will first be described in more detail and examined for possible solutions that are already available. After that, the paper deals with the main topic of geographic similarity and its definition until two approaches to solve the problem are described.
Emilien Bourdy, Marwane Ayaida and Hacene FouchalMisbehavior Verification on Cooperative Intelligent Transport System
Abstract: Cooperative Intelligent Transport System is a branch of the Vehicular Ad-Hoc Network, where all messages are used to improve safety of users. Since these messages are sent clearly, anyone could send false messages, and anyone could track a user. To overcome these problems, messages are signed with a certificate, which guarantee their authenticity and integrity. Furthermore, these certificates enable a pseudonym mechanism for the privacy. However, if a malicious node joins the system with a valid certificate, we need to detect it, and revoke it from the system. Some works already exist on the detection and reporting of misbehavior. However, how can we manage a node making fake report to untrust honest nodes? In this paper, we propose to add a verification with the neighborhood after the reception of misbehavior report in order to avoid any misuse of this mechanism.

Back to Program Overview, Top

Session 5: eHealth & Infrastructure

Tuesday, June 14, 2022, 14:00

Dan Wu and Imran Shafiq AhmadEmergency Evacuation Software Simulation Process For Physical Changes
Abstract: Public safety mandate throughout of the world requires indoor public spaces such as schools, shopping malls, cinemas, sporting complex, etc. to have an emergency evacuation plan for a safe exit of the occupants. For many years, evacuation planning and development of safety measures are accomplished on the basis of simulation models available through various different software applications. While computer scientists are working on improving algorithms for software simulations, architect/builders are inventing various new structures/fixtures and measures to potentially save lives during an emergency. This paper proposes a process that creates a 3D base model of an evacuation systems to simulate physical changes such as retractable seats, movable walls etc., to evaluate their effectiveness before embarking on costly and time consuming physical changes in a given indoor environments. To develop our model, tools like Unity 3D and ©Autodesk Maya are used to simulate suggested changes. This proposed process is intended to provide planners/ engineers and researchers a new perspective to work on simulating the existing models with new recommendations or physical changes before committing on making such changes and evaluate their effectiveness when designing or renovating indoor public spaces.
Steffen Späthe, Florian Greulich and Sebastian ApelContext Information Management in a Microservice Based Measurement and Processing Infrastructure
Abstract: Within a distributed software system for measuring and processing data streams the services require knowledge to contextualization of information. Using microservices in combination with a network of heterogeneous devices - as usual in an internet of things setting - requires the management of knowledge about integrated data and its context. Reference architectures suggest here the centralization of this knowledge management. This contribution deals with the question of how this knowledge can be structured and how to apply integration and processing services in a microservice architecture. The main focus here is on how data collection and context can be combined independently of the corresponding services and without influencing participating services. The result is a data model and a query language, which we used within the architecture to manage knowledge and used by integration and processing services. The result is evaluated based on scenario considerations in the internet of things setting, such as adding, replacing and removing devices while maintaining the context. Additionally, we provide an insight into the practical application of the approach in a realized microservice infrastructure for the management and optimization of a local smart grid.
Udo Krieger and Marcel GroßmannA Web Architecture for E-Health Applications Supporting the Efficient Multipath Transport of Medical Images
Abstract: New advanced e-health applications are required to support the effective processing of diagnostic and therapeutic healthcare protocols in modern societies. Looking at the work flow handled by the consulted medical staff in the first level of a medical treatment chain such as family doctors, an effective treatment usually requires the processing of pre-recorded medical images of a patient during the first diagnostic phase. We consider the development of a Web server architecture that offers the transport of medical images by an Android application and illustrate its design by a realized PACS prototype. The effective data transport of medical images is realized by a multipath-QUIC protocol which is integrated into a DICOM proxy server. Its further development can integrate other fog computing systems which support additional interconnected e-health applications employed by a consortium of users in a medical treatment process.

Back to Program Overview, Top 

Session 6: Quantum Computing

Wednesdy, June 15, 2022, 8:30 a.m.

Niels Neumann and Robert WezemanDistributed Quantum Machine Learning
Abstract: Quantum computers can solve specific complex tasks for which no reasonable-time classical algorithm is known. Quantum computers do however also offer inherent security of data, as measurements destroy quantum states. Using shared entangled states, multiple parties can collaborate and securely compute quantum algorithms. In this paper we propose an approach for distributed quantum machine learning, which allows multiple parties to securely perform computations, without having to reveal their data. We will consider a distributed adder and a distributed distance-based classifier.
Christoph Roch, David Winderl, Claudia Linnhoff-Popien and Sebastian FeldA Quantum Annealing Approach for Solving hard Variants of the Stable Marriage Problem
Abstract: The Stable Marriage Problem (SMP) describes the problem, of finding a stable matching between two equally sized sets of elements (e.g., males and females) given an ordering of preferences for each element. A matching is stable, when there does not exist any match of a male and female which both prefer each other to their current partner under the matching. Finding such a matching of maximum cardinality, when ties and incomplete preference lists are allowed, is called MAX-SMTI and is an NP-hard variation of the SMP. In this work a Quadratic Unconstrained Binary Optimization (QUBO) formulation for MAX-SMTI is introduced and solved both with D-Wave Systems quantum annealing hardware and by their classical meta-heuristic QBSolv. Both approaches are reviewed against existing state-of-the-art approximation algorithms for MAX-SMTI. Additionally, the proposed QUBO problem can also be used to count stable matchings in SMP instances, which is proven to be a \#P-complete problem. The results show, that the proposed (quantum) methods can compete with the classical ones regarding the solution quality and might be a relevant alternative, when quantum hardware scales with respect to the number of qubits and their connectivity.
Merel Schalkers and Matthias MöllerLearning Based Hardware-Centric Quantum Circuit Generation
Abstract: In this paper we present an approach to find quantum circuits suitable to mimic probabilistic operations and search operations on a chosen NISQ device. We present one gradient based and one non-gradient based machine learning approach to optimize the created quantum circuits. In our optimization procedure we make use of a cost function that differentiates between the vector representing the probabilities of measurement of each basis state after applying our learned circuit and the desired probability vector. As such our quantum circuit generation (QCG) approach leads to thinner quantum circuits which behave better when prformed on physical quantum computers. Our approach moreover ensures that the created quantum circuit obeys the restrictions of the chosen hardware. By catering to specific quantum hardware we can avoid unforeseen and potentially unnecessary circuit depth, and we return circuits that need no compiling. We present the results of running the created circuits on IBM, Rigetti and Quantum Inspire quantum computers.
Frank Phillipson and Irina ChiscopA Quantum Approach for Tactical Capacity Management of Distributed Electricity Generation
Abstract: Matching electricity demand and supply by decentralised generators will be very important in the near future, where more and more electricity has to be produced sustainably. Optimisation problems that address this problem often have quadratic objective functions or constraints, due to the quadratic nature of energy loss. Where classical solvers struggle with quadratic, often integer or binary, optimisation problems, quantum computing (inspired) solvers are well equipped for this kind of problems. In this paper, we present such an optimisation problem and the performance of the quantum annealer in solving this problem, in comparison with classical methods and commercial solvers. We show that the hybrid, quantum-classical, solvers provided by D-Wave can outperform classical solvers despite the small-scale of the available quantum hardware.

Back to Program Overview, Top  

Session 7: Applied Machine Learning

Wednesdy, June 15, 2022, 13:00

Pranav Kumar Singh and Bhabesh MaliTowards Simulating a Global Robust Model for Early Asthma Detection
Abstract: Asthma is a chronic non-communicable disease that affects the lungs and can cause breathlessness leading to fatal exacerbation. This disease mainly starts developing in childhood and can affect the lungs and lifestyle throughout life. Ignoring asthma at any age can be fatal. Therefore, this disease should be detected as early as possible. So, in this regard, we decided to build a machine learning model to predict early asthma in children. We simulated the federated learning process to build the model and created four virtual hospitals. We have simulated federated learning to build a global robust model where multiple datasets from the different institutions can take part in the training process, which can be used in various regions of the world for predicting early asthma. We have trained the models using both IID (Independent and Identically Distributed) and non-IID approaches of splitting the dataset. We also checked the performance of the models by measuring the predictive accuracy and AUC (Area Under the Receiver Operating Characteristic Curve) score for test data. We got a predictive accuracy of 91.57% and 93.68% for the IID and non-IID approaches. While we got the AUC score of 0.895 and 0.918 for the IID approach and non-IID approaches.
Chérifa Boucetta, Laurent Hussenet and Michel HerbinPractical Method for Multidimensional Data Ranking: Application For Virtual Machine Migration
Abstract: This paper proposes a practical and generic approach for multidimensional data ranking in order to facilitate the exploration of data in an orderly manner. We examine each dimension and we calculate the rank per variable. Then, we transform the number of possibly correlated variables into a smaller number of variables called principal components in order to extract the important information from the data set. We validate this method using open datasets. To assess the proposed method, we consider as a criterion the number of the class changes when scanning multidimensional data set. Then, we apply this method to rank the virtual machines of the IT department in Networking & Telecommunication of our institute according to their resource consumption in order to identify those that consume many resources.

Back to Program Overview, Top