Publications 2021

Script list Publications

(1) Extended Horizontal SCA Attack using Clustering Algorithm
M. Aftowicz, D. Klann, I. Kabin, Z. Dyka, P. Langendörfer
Proc. 32nd Crypto Day Matters 2021, (2021)
DOI: 10.18420/cdm-2021-32-25

(2) Clustering versus Statistical Analysis for SCA: When Machine Learning is Better
M. Aftowicz, I. Kabin, Z. Dyka, P. Langendörfer
Proc. 10th Mediterranean Conference on Embedded Computing (MECO 2021), 174 (2021)
DOI: 10.1109/MECO52532.2021.9460161, (Total Resilience)

(3) A Fully-Blind False Data Injection on PROFINET I/O Systems
W. Alsabbagh, P. Langendörfer
Proc. 30th International Symposium on Industrial Electronics (ISIE 2021), (2021)

(4) A Stealth Program Injection Attack against S7-300 PLCs
W. Alsabbagh, P. Langendörfer
Proc. 22nd International Conference on Industrial Technology (ICIT 2021), 986 (2021)
DOI: 10.1109/ICIT46573.2021.9453483

(5) Patch Now and Attack Later - Exploiting S7 PLCs by Time-Of-Day Block
W. Alsabbagh, P. Langendörfer
Proc. 4th IEEE International Conference on Industrial Cyber-Physical Systems (ICPS 2021), 144 (2021)
DOI: 10.1109/ICPS49255.2021.9468226

(6) Four-Stream Line-of-Sight Spatial Multiplexing for 60 GHz Backhaul Applications
D. Cvetkovski, T. Hälsig, B. Lankl, E. Grass
IEEE Wireless Communications Letters 10(8), 1648 (2021)
DOI: 10.1109/LWC.2021.3076161, (maximumMIMO)
This work presents experimental results for a four-stream spatial multiplexing setup in a line-ofsight (LoS) wireless backhaul scenario at 60 GHz. With optimal antenna arrangement, a highly orthogonal wireless channel with a measured condition number of 1.42 is observed, whereby the channel tap distribution shows a dominant LoS component. Two different equalizers, symbolwise and block-wise adaptive, are presented and evaluated in terms of error vector magnitude (EVM) performance and bandwidth efficiency. For both approaches, an errorfree transmission with a throughput of 14.08 Gbits is demonstrated, thus validating the practical suitability of LoS MIMO for wireless backhaul applications.

(7) Experimental Evaluation of Line-of-Sight MIMO Transmission for Sub-6GHz Carrier Frequencies
D. Cvetkovski, T. Schlegel, E. Grass
Frequenz: Journal of RF-Engineering and Telecommunications 75(5-6), 165 (2021)
DOI: 10.1515/freq-2020-0135, (maximumMIMO)
For the next generation wireless networks, backhaul links with data rates of several 𝐺𝑏𝑖𝑡/𝑠 are required. Line-of-Sight-MIMO with optimally arranged antennas can exploit the full multiplexing gain of orthogonal MIMO streams to achieve high throughput, as shown in recent works utilizing the 60𝐺𝐻𝑧 millimeter wave band. In contrast, conventional MIMO systems operating at sub-6𝐺𝐻𝑧 carrier frequencies, as utilized in modern WLAN networks, rely on rich scattering channels to enable reliable transmissions. In this work, we explore the feasibility of applying the LoS-MIMO concept to wireless single-carrier links operating at sub-6𝐺𝐻𝑧 frequencies. For this, we investigate the sub-6𝐺𝐻𝑧 LoS-MIMO channel in a 4x4 MIMO configuration by performing measurements in an anechoic chamber and an outdoor backhaul-like environment. In addition, different adaptive equalizers are evaluated. The results show, that the LoS-MIMO concept holds for sub6𝐺𝐻𝑧 frequencies both in pure LoS and in outdoor environments. It provides high multiplexing gain, however, the multipath propagation limits the potential performance of the equalizers in terms of achievable BER.

(8) Experimental Evaluation of Line-of-Sight MIMO Transmission for Sub-6GHz Carrier Frequencies
D. Cvetkovski, T. Schlegel, E. Grass
Frequenz: Journal of RF-Engineering and Telecommunications 75(5-6), 165 (2021)
DOI: 10.1515/freq-2020-0135, (IHP - Humboldt-Universität Joint-Lab)
For the next generation wireless networks, backhaul links with data rates of several 𝐺𝑏𝑖𝑡/𝑠 are required. Line-of-Sight-MIMO with optimally arranged antennas can exploit the full multiplexing gain of orthogonal MIMO streams to achieve high throughput, as shown in recent works utilizing the 60𝐺𝐻𝑧 millimeter wave band. In contrast, conventional MIMO systems operating at sub-6𝐺𝐻𝑧 carrier frequencies, as utilized in modern WLAN networks, rely on rich scattering channels to enable reliable transmissions. In this work, we explore the feasibility of applying the LoS-MIMO concept to wireless single-carrier links operating at sub-6𝐺𝐻𝑧 frequencies. For this, we investigate the sub-6𝐺𝐻𝑧 LoS-MIMO channel in a 4x4 MIMO configuration by performing measurements in an anechoic chamber and an outdoor backhaul-like environment. In addition, different adaptive equalizers are evaluated. The results show, that the LoS-MIMO concept holds for sub6𝐺𝐻𝑧 frequencies both in pure LoS and in outdoor environments. It provides high multiplexing gain, however, the multipath propagation limits the potential performance of the equalizers in terms of achievable BER.

(9) Four-Stream Line-of-Sight Spatial Multiplexing for 60 GHz Backhaul Applications
D. Cvetkovski, T. Hälsig, B. Lankl, E. Grass
IEEE Wireless Communications Letters 10(8), 1648 (2021)
DOI: 10.1109/LWC.2021.3076161, (IHP - Humboldt-Universität Joint-Lab)
This work presents experimental results for a four-stream spatial multiplexing setup in a line-ofsight (LoS) wireless backhaul scenario at 60 GHz. With optimal antenna arrangement, a highly orthogonal wireless channel with a measured condition number of 1.42 is observed, whereby the channel tap distribution shows a dominant LoS component. Two different equalizers, symbolwise and block-wise adaptive, are presented and evaluated in terms of error vector magnitude (EVM) performance and bandwidth efficiency. For both approaches, an errorfree transmission with a throughput of 14.08 Gbits is demonstrated, thus validating the practical suitability of LoS MIMO for wireless backhaul applications.

(10) Multiplier as a Mean for Reducing Vulnerability of Atomic Patterns to Horizontal Address-Bit Attacks
Z. Dyka, I. Kabin, D. Klann, P. Langendörfer
Proc. 10th Mediterranean Conference on Embedded Computing (MECO 2021), 183 (2021)
DOI: 10.1109/MECO52532.2021.9460158, (Total Resilience)

(11) Challenges in Developing a Wireless Sensor Network for an Agricultural Monitoring and Decision System
M. Frohberg, St. Weidling, P. Langendörfer
Proc. 12th International Networking Conference (INC 2020), in: Selected Papers from the 12th International Networking Conference, Springer, LNNS 180, 224 (2021)
DOI: 10.1007/978-3-030-64758-2_16, (DAKIS)
Demand for food, efficient use of resources and the need for climate change adaptation are conflicting objectives of today's agriculture. WSN could help to balance these contradicting requirements. A decisive advantage of a WSN is that data can be obtained from the sensors at any time without the physical presence of farmers. But in addition to a large number of technical challenges, a major challenge is to monitor necessary parameters with a sufficiently high temporal and spatial resolution. The present work discusses those challenges in detail. Furthermore, an approach is proposed to designing a WSN for sensor-assisted landscape monitoring, that aims to support small-scale real time acquisition of site-specific requirements. Continuous monitoring is intended to lay the foundation for agricultural management strategies to be adapted at any time using real-time information.

(12) Impact of Data Preparation in Freezing of Gait Detection using Feature-Less Recurrent Neural Network
A. Haddadi Esfahani, Z. Dyka, St. Ortmann, P. Langendörfer
IEEE Access 9, 138120 (2021)
DOI: 10.1109/ACCESS.2021.3117543, (FastGait)
Many studies showed the feasibility of detecting Freezing of Gait (FOG) of Parkinson patients by using several numbers of inertial sensors worn at the body and back-end computing power. This work uses machine learning approaches analyzing the data of one single body-worn inertial sensor system to classify and detect FOG. Long-Short-Term-Memory (LSTM) is employed as the FOG detection algorithm and the Daphnet (FOG and normal gait) dataset provides the data for model training and testing in this paper. The model considers raw data from three channels of the acceleration sensor mounted on the patient’s shank and ignores all other data from other sensors. The model is patient dependent and sensitivity and specificity metrics are used to evaluate the model’s performance. In this paper, we propose a novel padding method that is applied to the windows of FOG and non-FOG with zero overlaps on the training set and adapts the padding to the individual regions. This method produces windows containing only one type of data and label. The proposed padding method reduces the padding amount by two orders of magnitude compared to bigger batch-sizes in the sequence splitting method offered by MATLAB 2019a. The padding amount is independent of the batch-size. Raw data is fed to the model in the testing mode without any pre-processing or data transformation. The standard rolling window generates fixed-size windows for the test set without overlap and the higher amount of FOG or Normal walking data defines the label of the individual window. The model for One-second long windows applied in this work outperformed the literature results with a sensitivity of 92.57% and a specificity of 95.62% compared to 82% and 94% reported by Masiala et al.

(13) Artificial Intelligence in Marketing – Friend or Foe of Sustainable Consumption?
E. Hermann
AI & Society (2021)
DOI: 10.1007/s00146-021-01227-8, (Kompetenzzentrum IHP/BTU)
A pivotal assumption of neoclassical economics is that both companies and consumers aim at optimizing self-interests. While the former seek to maximize profits, the latter pursue maximizing utility, satisfaction, and happiness. Consumers (can) derive utility and happiness from consumption, whose scale and scope is a function of their standard of living, among other things. Whether these tenets can and should be countered by anti-consumption, de-growth, and sufficiency is a higher-level discussion and out of scope of this paper. Instead, I adopt an advocacy perspective propagating to optimize the status quo by leveraging AI in marketing to gradually approach sustainable consumption.

(14) Leveraging Artificial Intelligence in Marketing for Social Good - An Ethical Perspective
E. Hermann
Journal of Business Ethics (2021)
DOI: 10.1007/s10551-021-04843-y, (Kompetenzzentrum IHP/BTU)
Artificial intelligence (AI) is (re)shaping strategy, activities, interactions, and relationships in business and specifically in marketing. The drawback of the substantial opportunities AI systems and applications (will) provide in marketing are ethical controversies. Building on the literature on AI ethics, the authors systematically scrutinize the ethical challenges of deploying AI in marketing from a multi-stakeholder perspective. By revealing interdependencies and tensions between ethical principles, the authors shed light on the applicability of a purely principled, deontological approach to AI ethics in marketing. To reconcile some of these tensions and account for the AI-for-social-good perspective, the authors make suggestions of how AI in marketing can be leveraged to promote societal and environmental well-being.

(15) Anthropomorphized Artificial Intelligence, Attachment, and Consumer Behavior
E. Hermann
Marketing Letters (2021)
DOI: 10.1007/s11002-021-09587-3, (Kompetenzzentrum IHP/BTU)
The increasing humanization and emotional intelligence of AI applications have the potential to induce consumers’ attachment to AI and to transform human-to-AI interactions into human-to-human-like interactions. In turn, consumer behavior as well as consumers’ individual and social lives can be affected in various ways. Following this reasoning, I illustrate the implications and research opportunities related to consumers’ (potential) attachment to humanized AI applications along the stages of the consumption process.

(16) Artificial Intelligence and Mass Personalization of Communication Content - An Ethical and Literacy Perspective
E. Hermann
New Media & Society (2021)
DOI: 10.1177/14614448211022702, (Kompetenzzentrum IHP/BTU)
Artificial intelligence (AI) is (re)shaping communication and contributes to (commercial and informational) need satisfaction by means of mass personalization. However, the substantial personalization and targeting opportunities do not come without ethical challenges. Following an AI-for-social-good perspective, the authors systematically scrutinize the ethical challenges of deploying AI for mass personalization of communication content from a multi-stakeholder perspective. The conceptual analysis reveals interdependencies and tensions between ethical principles, which advocate the need of a basic understanding of AI inputs, functioning, agency, and outcomes. By this form of AI literacy, individuals could be empowered to interact with and treat mass-personalized content in a way that promotes individual and social good while preventing harm.

(17) Ethical Artificial Intelligence in Chemical Research and Development: A Dual Advantage for Sustainability
E. Hermann, G. Hermann, J.-C. Tremblay
Science and Engineering Ethics 27, 45 (2021)
DOI: 10.1007/s11948-021-00325-6, (Kompetenzzentrum IHP/BTU)
Artificial intelligence can be a game changer to address the global challenge of sustainable development. Since chemical research and development lay the foundation for innovative products and solutions, we argue that backing chemical research and development with artificial intelligence and guiding ethical principles can be a starting point to account for both process- and outcome-related sustainability. Particularly in ethically salient contexts, ethical principles should accompany research and development powered by artificial intelligence to promote social and environmental good and sustainability (beneficence) while preventing any harm (non-maleficence) for all stakeholders affected.

(18) On the Complexity of Attacking Commercial Authentication Products
I. Kabin, Z. Dyka, D. Klann, J. Schäffner, P. Langendörfer
Microprocessors and Microsystems 80, 103480 (2021)
DOI: 10.1016/j.micpro.2020.103480, (Total Resilience)
In this paper we discuss the difficulties of mounting successful attack against crypto implementations when essential information is missing. We start with a detailed description of our attack against our own design, to highlight which information is needed to increase the success of an attack, i.e. we use it as a blueprint to the following attack against commercially available crypto chips. We would like to stress that our attack against our own design is very similar to what happens during certification e.g. according to Common Criteria Standard as in those cases the manufacturer need to provide detailed information. When attacking the commercial designs without signing NDAs, we needed to intensively search the Internet for information about the designs. We cannot to reveal the private keys used by the attacked commercial authentication chips 100% correctly. Moreover, the missing knowledge of the used keys does not allow us to evaluate the success of our attack. We were able to reveal information on the processing sequence during the authentication process even as detailed as identifying the clock cycles in which the individual key bits are processed. To summarize the effort of such an attack is significantly higher than the one of attacking a well-known implementation.

(19) FFT based Horizontal SCA Attack against ECC
I. Kabin, Z. Dyka, D. Klann, M. Aftowicz, P. Langendörfer
Proc. 11th IFIP International Conference on New Technologies, Mobility & Security (NTMS 2021), (2021)
DOI: 10.1109/NTMS49979.2021.9432665, (Total Resilience)

(20) Breaking of an Open Source Fully Balanced Elliptic Curve Design using Automated Simple SCA
I. Kabin, Z. Dyka, D. Klann, P. Langendörfer
Proc. 32nd Crypto-Day Matters 2021, (2021)
DOI: 10.18420/cdm-2021-32-23, (Total Resilience)

(21) Fast Dual-Field ECDSA Accelerator with Increased Resistance against Horizontal SCA Attacks
I. Kabin, D. Klann, Z. Dyka, P. Langendörfer
Proc. IEEE International Conference on Cyber Security and Resilience (CSR 2021), 273 (2021)
DOI: 10.1109/CSR51186.2021.9527912, (Total Resilience)

(22) EC P-256: Successful Simple Power Analysis
I. Kabin, Z. Dyka, D. Klann, P. Langendörfer
zu finden unter: https://arxiv.org/abs/2106.12321
(Total Resilience)

(23) Resistance of the Montgomery Ladder against Simple SCA: Theory and Practice
I. Kabin, Z. Dyka, D. Klann, M. Aftowicz, P. Langendörfer
Journal of Electronic Testing 37, 289 (2021)
DOI: 10.1007/s10836-021-05951-, (Total Resilience)
The Montgomery kP algorithm i.e. the Montgomery ladder is reported in literature as resistant against simple SCA due to the fact that the processing of each key bit value of the scalar k is done using the same sequence of operations. We implemented the Montgomery kP algorithm using Lopez-Dahab projective coordinates for the NIST elliptic curve B-233. We instantiated the same VHDL code for a wide range of clock frequencies for the same target FPGA and using the same compiler options. We measured electromagnetic traces of the kP executions using the same input data, i.e. scalar k and elliptic curve point P, and measurement setup. Additionally, we synthesized the same VHDL code for two IHP CMOS technologies, for a broad spectrum of frequencies. We simulated the power consumption of each synthesized design during an execution of the kP operation, always using the same scalar k and elliptic curve point P as inputs. Our experiments clearly show that the success of simple electromagnetic analysis attacks against FPGA implementations as well as the one of simple power analysis attacks against synthesized ASIC designs depends on the target frequency for which the design was implemented and at which it is executed significantly. In our experiments the scalar k was successfully revealed via simple visual inspection of the electromagnetic traces of the FPGA for frequencies from 40 to 100 MHz when standard compile options were used as well as from 50 MHz up to 240 MHz when performance optimizing compile options were used. We obtained similar results attacking the power traces simulated for the ASIC. Despite the significant differences of the here investigated technologies the designs’ resistance against the attacks performed is similar: only a few points in the traces represent strong leakage sources allowing to reveal the key at very low and very high frequencies. For the “middle” frequencies the number of points which allow to successfully reveal the key increases when increasing the frequency.

(24) Generic Energy Production Model for Smart Grid Emulation
M. Krysik, K. Piotrowski, R. Rybski
Measurement Systems in Theory and Practice, 1st Edition, Editor: R. Rybski, Generic Energy Production Model for Smart Grid Emulation, Verlag der Universität Zielona Góra, 11 (2021)
(ebalance plus)

(25) Simplified Control Flow Integrity Method for Permutated Programs
K. Lehniger, M. Schölzel, P. Tabatt, M. Aftowicz, P. Langendörfer
Proc. 32nd Crypto-Day Matters 2021, (2021)
DOI: 10.18420/cdm-2021-32-21, (MORFEUS)

(26) A Study of Barker Spreading Codes for High-Speed PSSS Wireless Systems
L. Lopacinski, N. Maletic, A. Hasani, K. Krishnegowda, J. Gutierrez Teran, R. Kraemer, E. Grass
Proc. 30th European Conference on Networks and Communications (EuCNC 2021), 122 (2021)
DOI: 10.1109/EuCNC/6GSummit51104.2021.948254, (PSSS-FEC)

(27) Flood Embankments Monitoring System in On-Line Mode
E. Michta, P. Powroznik, R. Rybski, R. Szulim, K. Piotrowski, U. Kolodziejczyk, J. Kostecki
Measurement Systems in Theory and Practice, 1st Edition, Editor: R. Rybski, Flood Embankments Monitoring System in On-Line Mode, Verlag der Universität Zielona Góra, 1 (2021)
(SmartRiver)

(28) Jamming Detection for IR-UWB Ranging Technology in Autonomous UAV Swarms
P. Mykytyn, M. Brzozowski, Z. Dyka, P. Langendörfer
Proc. 9th International Conference on Cyber-Physical Systems and Internet-of-Things (CPSIoT 2021), 81 (2021)
DOI: 10.1109/MECO52532.2021.9460250, (iCampus)

(29) Optical Fault Injection Attacks against Radiation-Hard Registers
D. Petryk, Z. Dyka, R. Sorge, J. Schäffner, P. Langendörfer
Proc. 24th EUROMICRO Conference on Digital System Design (DSD 2021), Special Session: Architectures and Hardware for Security Applications (AHSA), 371 (2021)
DOI: 10.1109/DSD53832.2021.00062, (RESCUE)

(30) Radiation Hardness Does Not Mean Tamper Resistance
D. Petryk, Z. Dyka, P. Langendörfer
Proc. Design, Automation and Test in Europe Conference (DATE 2021), Workshop on Interdependent Challenges of Reliability, Security and Quality (RESCUE 2021), (2021)
(RESCUE)

(31) Household Energy Management
P. Powroznik, R. Szulim, W. Miczulski, K. Piotrowski
Applied Sciences 11(4), 1626 (2021)
DOI: 10.3390/app11041626, (ebalance plus)
Ensuring flexibility and security in power systems requires the use of appropriate management measures on the demand side. The article presents the results of work related to energy management in households in which renewable energy sources (RES)can be installed. The main part of the article is about the developed elastic energy management algorithm (EEM), consisting of two algorithms, EEM1 and EEM2. The EEM1 algorithm is activated in time periods with a higher energy price. Its purpose is to reduce the power consumed by the appliances to the level defined by the consumer. In contrast, the EEM2 algorithm is run by the Distribution System Operator (DSO) when peak demand occurs. Its purpose is to reduce the power of appliances in a specified time period to the level defined by the DSO. The optimization tasks in both algorithms are based on the Greedy Randomized Adaptive Search Procedure (GRASP) metaheuristic algorithm. The EEM1 and EEM2 algorithms also provide energy consumer comfort. For this purpose, both algorithms take into account the smart appliance parameters proposed in the article: sections of the working devices, power reduction levels, priorities and enablingof time shifting devices. The EEM algorithm in its operation also takes into account the information about the production of power, e.g., generated by the photovoltaic systems. On this basis, it makes decisions on the control of smart appliances. The EEM algorithm also enables inverter control to limit the power transferred from the photovoltaic system to the energy system. Such action is taken on the basis of the DSO request containing the information on the power limits. Such a structure of EEM enables the balancing of energy demand and supply. The possibility of peak demand phenomenon will be reduced. The simulation and experiment results presented in the paper confirmed the rationality and effectiveness of the EEM algorithm.

(32) Household Energy Management
P. Powroznik, R. Szulim, W. Miczulski, K. Piotrowski
Applied Sciences 11(4), 1626 (2021)
DOI: 10.3390/app11041626, (SmartGrid Plattform)
Ensuring flexibility and security in power systems requires the use of appropriate management measures on the demand side. The article presents the results of work related to energy management in households in which renewable energy sources (RES)can be installed. The main part of the article is about the developed elastic energy management algorithm (EEM), consisting of two algorithms, EEM1 and EEM2. The EEM1 algorithm is activated in time periods with a higher energy price. Its purpose is to reduce the power consumed by the appliances to the level defined by the consumer. In contrast, the EEM2 algorithm is run by the Distribution System Operator (DSO) when peak demand occurs. Its purpose is to reduce the power of appliances in a specified time period to the level defined by the DSO. The optimization tasks in both algorithms are based on the Greedy Randomized Adaptive Search Procedure (GRASP) metaheuristic algorithm. The EEM1 and EEM2 algorithms also provide energy consumer comfort. For this purpose, both algorithms take into account the smart appliance parameters proposed in the article: sections of the working devices, power reduction levels, priorities and enablingof time shifting devices. The EEM algorithm in its operation also takes into account the information about the production of power, e.g., generated by the photovoltaic systems. On this basis, it makes decisions on the control of smart appliances. The EEM algorithm also enables inverter control to limit the power transferred from the photovoltaic system to the energy system. Such action is taken on the basis of the DSO request containing the information on the power limits. Such a structure of EEM enables the balancing of energy demand and supply. The possibility of peak demand phenomenon will be reduced. The simulation and experiment results presented in the paper confirmed the rationality and effectiveness of the EEM algorithm.

(33) Octopuses: Biological Facts and Technical Solutions
O. Shamilyan, I. Kabin, Z. Dyka, M. Kuba, P. Langendörfer
Proc. 9th International Conference on Cyber-Physical Systems and Internet-of-Things (CPS&IoT 2021), 91 (2021)
DOI: 10.1109/MECO52532.2021.9459727, (Total Resilience)

(34) Simulation of Electromagnetic Emanation of Cryptographic ICs: Tools, Methods, Problems
A. Sosa, Z. Dyka, I. Kabin, P. Langendörfer
Proc. 19th IEEE East-West Design & Test Symposium (EWDTS 2021), 12 (2021)
(Total Resilience)

(35) Fault Resilience Analysis of Quantized Deep Neural Networks
R.T. Syed, M. Ulbricht, K. Piotrowski, M. Krstic
Proc. 32nd International Conference on Microelectronics (MIEL 2021), 275 (2021)
(Space Region)

(36) Immunität eingebetteter verteilter Systeme gegen ROP-Angriffe durch Mutationen
P. Tabatt, M. Schölzel, K. Lehniger
Proc. 33. GI/GMM/ITG-Workshop Testmethoden und Zuverlässigkeit von Schaltungen und Systemen (TuZ 2021), 45 (2021)

(37) A Framework to Support Creation of AI Applications for Low-Power WSN Nodes
K. Turchan, K. Piotrowski
Proc. 8th Machine Intelligence and Digital Interaction (MIDI 2020), in: Advances in Intelligent Systems and Computing, Springer, AISC 1376, 73 (2021)
DOI: 10.1007/978-3-030-74728-2_7, (SmartRiver)

(38) A Framework to Support Creation of AI Applications for Low-Power WSN Nodes
K. Turchan, K. Piotrowski
Proc. 8th Machine Intelligence and Digital Interaction (MIDI 2020), in: Advances in Intelligent Systems and Computing, Springer, AISC 1376, 73 (2021)
DOI: 10.1007/978-3-030-74728-2_7, (AMMOD)

The website is designed for modern browsers. Please use a current browser.