Publications 2024

Script list Publications

(1) Advantages of Unsupervised Learning Analysis Methods in Single-Trace SCA Attacks
M. Aftowicz, I. Kabin, Z. Dyka, P. Langendörfer
Microprocessors and Microsystems 105, 104994 (2024)
DOI: 10.1016/j.micpro.2023.104994, (Total Resilience)
Machine learning techniques are commonly employed in the context of Side Channel Analysis attacks. The clustering algorithms can be successfully used as classifiers in single execution attacks against implementations of Elliptic Curve point multiplication known as kP operation. They can distinguish between the processing of ‘ones’ and ‘zeros’ during secret scalar processing in the binary kP algorithm. The successful SCA performed by designers can aid in recognizing the leakage sources in cryptographic designs and lead to improvement of the cryptographic implementations. In this work we investigate the influence of the hamming weight of scalar k on the success rate of the single-trace attack. We used the clustering method K-means and the statistical method the comparison to the mean. We analysed simulated power traces and power traces of an FPGA implementation to conclude that K-means, unlike the comparison to the mean, was able to deal with extracting the scalar even when it is consisted of less than 30% of ‘ones’ and more than 70% of ‘ones’.

(2) Simulation-Based Analysis and Modeling of Generated Single Event Transient Pulse Width
M. Andjelkovic, M. Krstic
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534612, (6G-TakeOff)

(3) On-Chip Particle Detectors for Self-Adaptive Integrated Circuits for Space Applications
M. Andjelkovic
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 1 (2024)
(6G-TakeOff)

(4) A Holistic Approach for Characterization of SET Effects in a Standard Digital Cell Library
M. Andjelkovic, M. Krstic
Proc. 15th IEEE Latin America Symposium on Circuits and System (LASCAS 2024), (2024)
DOI: 10.1109/LASCAS60203.2024.10506165, (6G-TakeOff)

(5) 6G-TakeOff: Holistic 3D Networks for 6G Wireless Communications
M. Andjelkovic, N. Maletic, Miglioranza, M. Krstic, E. Koeck, J. Buchholz, M. Taddiken, M. Fehrenz, S. Baradie, D. Wuebben, M. Breitbach
Proc. 27th Euromicro Conference Series on Digital System Design (DSD 2024), 435 (2024)
DOI: 10.1109/DSD64264.2024.00064, (6G-TakeOff)

(6) Simulation-Based Analysis and Modeling of Generated Single Event Transient Pulse Width
M. Andjelkovic, M. Krstic
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534612, (Open 6G Hub)

(7) A Holistic Approach for Characterization of SET Effects in a Standard Digital Cell Library
M. Andjelkovic, M. Krstic
Proc. 15th IEEE Latin America Symposium on Circuits and System (LASCAS 2024), (2024)
DOI: 10.1109/LASCAS60203.2024.10506165, (Open 6G Hub)

(8) Detection of Unhealthy Fruits using Image Classification based on a Deep Transfer Learning Framework
P. Bagchi, D. Markovic, Z. Stamenkovic, D. Stojic, D. Bhattacharjee
UNITECH - Selected Papers (2024)
(BB-KI-Chips)
This paper presents a methodology for detecting unhealthy lemons in a lemon dataset based on a deep Convo-lutional Neural Network (CNN) and transfer learning. Initially, a CNN model was developed and trained, after which a new model was framed on the existing CNN model using transfer learning. The base model was trained to a satisfying level of accuracy (of 98.55%). Afterwards, we incorporated this pre-trained model into a customized transfer learning framework. The final model was tested using a different augmented lemon dataset. In this case, no additional training was performed on the transfer learning model and the resultant model achieved an accuracy of 95.91 %.

(9) Investigating the SEU Immunity of a Selectively-Hardened Complex Digital Filter
A. Breitenreiter, T. Lange, E. Pun, C. Schulze, F. Vargas, M. Krstic
Proc. 36. ITG/GMM/GI-Workshop Testmethoden und Zuverlässigkeit von Schaltungen und Systemen (TuZ 2024), 47 (2024)

(10) D-Band Active Antenna Array with Lens Enabling Quasi-Optical and Analogue Beam Reconfiguration for 6G Applications
M.A. Campo, S. Bruni, W. Wischmann, A. Lauer, A. Friedrich, M. Wleklinski, C. Oikonomopoulos-Zachos, O. Litschke, K. KrishneGowda, C. Herold, N. Moroni, W. Keusgen
18th European Conference on Antennas and Propagation (EuCAP 2024), (2024)
DOI: 10.23919/EuCAP60739.2024.10501233

(11) BeGREEN Intelligent Plane for AI-Driven Energy Efficient O-RAN Management
M. Catalan-Cid, J. Pueyo, J. Sanchez-Gonzalez, J. Gutierrez Teran, M. Ghoraishi
Proc. 33rd Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit 2024), (2024)
DOI: 10.1109/EuCNC/6GSummit60053.2024.10597119, (BeGREEN)

(12) Failure Probability due to Radiation‑Induced Effects in FinFET SRAM Cells under Process Variations
V. Champac, H. Villacorta, R. Gomez‑Fuentes, F. Vargas, J. Segura
Journal of Electronic Testing 40, 75 (2024)
DOI: 10.1007/s10836-024-06102-0
This work studies radiation-induced effects in FinFET technology, the leading technology in advanced nodes for high-end embedded systems. As the fin height (HFIN) and the number of fins (NFIN) are two critical parameters in the development  of newer technologies, the soft-error robustness to radiation-induced effects in FinFET SRAM cells with HFIN and NFIN) is evaluated using Technology Computer-Aided Design (TCAD) tools. The ion strike direction and the process variations are considered. An analytical method to evaluate the failure probability of the memory cell due to radiation-induced effects under process variations is proposed. The amount of critical and collected charges of the memory cell are obtained with TCAD tools. The proposed method can be used to get insight into the robustness behavior of the memory cell with HFIN and NFIN and to guide the obtention of HFIN and NFIN parameters in developing new FinFET technologies.

(13) Agile Hardware Development Flow for Radiation-Hardened System in Aerospace Applications
J.-C. Chen, M. Andjelkovic, M. Krstic
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 109 (2024)
(Scale4Edge)

(14) Agile Hardware Development Flow for Radiation-Hardened System in Aerospace Applications
J.-C. Chen, M. Andjelkovic, M. Krstic
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 109 (2024)
(Open 6G Hub)

(15) Space Radiation Flux Driven Fault Injection for Evaluating Dynamic Mitigation Strategies
J.-C. Chen, L. Lu, M. Andjelkovic, F. Vargas, M. Krstic
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534594, (Scale4Edge)

(16) Space Radiation Flux Driven Fault Injection for Evaluating Dynamic Mitigation Strategies
J.-C. Chen, L. Lu, M. Andjelkovic, F. Vargas, M. Krstic
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534594, (Open 6G Hub)

(17) Reliability Assessment of Large DNN Models: Trading Off Performance and Accuracy
J.-C. Chen, G. Esposito, F.F. dos Santos, J.-D.Guerrero-Balaguera, A. Kritikakou, M. Krstic, R. Limas Sierra, J.E. Rodriguez Condia, M. Sonza Reorda, M. Traiola, A. Veronesi
Proc. IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC 2024), (2024)
DOI: 10.1109/VLSI-SoC62099.2024.10767814, (6G-RIC)

(18) Economic Feasibility of 5G-Based Autonomous Mobile Robots Solutions for Industry 4.0
L. Chinchilla-Romero, J. Prados-Garzon, R. Vasist, M. Goodarzi
IEEE Communications Magazine 62(11), 52 (2024)
DOI: 10.1109/MCOM.005.2400125
The adoption of Fifth Generation (5G) technology in industrial enterprises has been slower than expected despite its clear technical advantages, primarily due to the significant initial investment costs and uncertainties surrounding the return on investment (ROI). High costs associated with infrastructure deployment, combined with the complexity of assessing the economic benefits specific to different industries, have made the decision to switch to 5G a complex and cautious one for many companies. This situation is worsened due to the lack of comprehensive techno-economic analyses that could provide clearer insights on the potential ROI of 5G implementation across different industrial scenarios. In this article, we propose a 5G-based centralized control solution for automated mobile robots (AMRs). We provide a techno-economic analysis assessing the total cost of ownership (TCO) of acquiring this solution compared to its no acquisition in an Industry 4.0 environment. A sensitivity analysis is also included for the AMR-based solution identifying the variables with great impact on the TCO. Results show that despite the initial higher upfront costs of an AMR-based approach with respect to human-based approach, it incurs lower operational costs over time, requiring only 2.5 years to become more cost-effective than the human-based one.

(19) On the Influence of Cell Libraries and Other Parameters to SCA Resistance of Crypto IP Cores
Z. Dyka, I. Kabin, M. Brzozowski, G. Panic, C. Calligaro, M. Krstic, P. Langendörfer
Proc. 13th Mediterranean Conference on Embedded Computing (MECO 2024), 80 (2024)
DOI: 10.1109/MECO62516.2024.10577776, (Total Resilience)

(20) 28-GHz SiGe Bidirectional 4-Element Beamformer Chip for 5G Applications based on a 4-Way Ultracompact Switchable Power Divider
A. Franzese, R. Negra, A. Malignaggi, N. Maletic, B. Sütbas, C. Carta
IEEE Transactions on Microwave Theory and Techniques 72(12), 7050 (2024)
DOI: 10.1109/TMTT.2024.3409571
This article describes the design of a 28-GHz bidirectional 4-element beamformer chip based on a 4-way ultracompact switchable power divider (SPD). The addition of the divider solves the ineffective power splitting and the inefficient use of valuable chip area. Therefore, this work is devoted to remove the drawbacks associated with the Wilkinson power dividers (PDs) and single-pole double-throw switches (SPDTs) leveraging a single-inductor N-way PD topology. In this article, the PD design is presented and its analysis is carried out, extending the previous literature. In addition, the embedding of the SPDTs within the PD is described in detail. Employing the proposed technique, the chip size is limited only to the dimensions of the main RF building blocks, analog circuitry, and digital logic; hence, eliminating the cumbersome divider chain which connects the transmitting/receiving (TRx) elements before going on-board. Finally, the measured performance of the beamformer designed in the IHP SG13S SiGe BiCMOS technology is reported. The beamformer achieves an OP1 dB of 11 dBm in Tx-mode with a power consumption of 231 mW for each element, whereas an IP1 dB of -28 dBm in Rx-mode is achieved consuming only 92 mW per element. The chip occupies a silicon area of 2.9×2.2 mm2. Moreover, a shift step of 11.25° is achieved with 2.4° and 0.4 dB of phase and amplitude root-mean-square error (RMSE), respectively. To the best of the authors’ knowledge, this is the first beamformer which substitutes the divider chain with a novel SPD. In this way, the chip length could be reduced by 1 mm with respect to their previous design, which proves that the proposed technique is promising for chips with high number of TRx elements.

(21) 56% PAE mm-Wave SiGe BiCMOS Power Amplifier Employing Local Backside Etching
A. Franzese, B. Sutbas, R. Hasan, A. Malignaggi, T. Mausolf, N. Maletic, M.-D. Wey, H. Zhou, C. Fager, C. Carta, R. Negra
IEEE Microwave and Wireless Technology Letters (MWTL) 34(8), 1023 (2024)
DOI: 10.1109/LMWT.2024.3409149
This letter presents a power amplifier (PA) with excellent power-added efficiency (PAE) for millimeter-wave (mm-wave) applications. The high efficiency is achieved by leveraging a local backside etching (LBE) process to enhance the quality factor ( Q ) of the output matching network. The PA was fabricated in a mature SiGe BiCMOS technology featuring heterojunction bipolar transistors (HBTs) having an fT / fmax of 250/340 GHz. While the measured peak PAE is 56% at 24 and 25 GHz, the PA provides 16 dB of peak gain and a 3-dB bandwidth of 19 GHz ranging from 13.5 to 32.5 GHz, which makes the circuit well suited for multiple purposes, such as sensors, radars, 5G, and satellite communications. The maximum PAE exceeds 40% from 22 to 28 GHz, with a peak saturated power (Psat) of 16.5 dBm at 25 GHz. To the best of authors’ knowledge, this PA achieves the highest PAE reported to date for silicon-based mm-wave amplifiers.

(22) Area-Efficient Digital Design using RRAM-CMOS Standardcells
M. Fritscher, M. Uhlmann, P. Ostrovskyy, D. Reiser, J.-C. Chen, M.A. Schubert, C. Schulze, G. Kahmen, D. Fey, M. Reichenbach, M. Kristic, Ch. Wenger
Proc. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2024), 81 (2024)
DOI: 10.1109/ISVLSI61997.2024.00026, (iCampus II)

(23) From Device to Application - Integrating RRAM Accelerator Blocks into Large AI Systems
M. Fritscher, Ch. Wenger, M. Krstic
Proc. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2024), 592 (2024)
DOI: 10.1109/ISVLSI61997.2024.00111, (6G-RIC)

(24) From Device to Application - Integrating RRAM Accelerator Blocks into Large AI Systems
M. Fritscher, Ch. Wenger, M. Krstic
Proc. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2024), 592 (2024)
DOI: 10.1109/ISVLSI61997.2024.00111, (iCampus II)

(25) A Flexible and Fast Digital Twin for RRAM Systems Applied for Training Resilient Neural Networks
M. Fritscher, S. Singh, T. Rizzi, A. Baroni, D. Reiser, M. Mallah, D. Hartmann, A. Bende, T. Kempen, M. Uhlmann, G. Kahmen, D. Fey, V. Rana, S. Menzel, M. Reichenbach, M. Krstic, F. Merchant, Ch. Wenger
Scientific Reports 14, 23695 (2024)
DOI: 10.1038/s41598-024-73439-z, (MIMEC)
Resistive Random Access Memory (RRAM) has gained considerable momentum due to its non-volatility and energy efficiency. Material and device scientists have been proposing novel material stacks that can mimic the “ideal memristor” which can deliver performance, energy efficiency, reliability and accuracy. However, designing RRAM-based systems is challenging. Engineering a new material stack, designing a device, and experimenting takes significant time for material and device researchers. Furthermore, the acceptability of the device is ultimately decided at the system level. We see a gap here where there is a need for facilitating material and device researchers with a “push button” modeling framework that allows to evaluate the efficacy of the device at system level during early device design stages. Speed, accuracy, and adaptability are the fundamental requirements of this modelling framework. In this paper, we propose a digital twin (DT)-like modeling framework that automatically creates RRAM device models from device measurement data. Furthermore, the model incorporates the peripheral circuit to ensure accurate energy and performance evaluations. We demonstrate the DT generation and DT usage for multiple RRAM technologies and applications and illustrate the achieved performance of our GPU implementation. We conclude with the application of our modeling approach to measurement data from two distinct fabricated devices, validating its effectiveness in a neural network processing an Electrocardiogram (ECG) dataset and incorporating Fault Aware Training (FAT).

(26) A Flexible and Fast Digital Twin for RRAM Systems Applied for Training Resilient Neural Networks
M. Fritscher, S. Singh, T. Rizzi, A. Baroni, D. Reiser, M. Mallah, D. Hartmann, A. Bende, T. Kempen, M. Uhlmann, G. Kahmen, D. Fey, V. Rana, S. Menzel, M. Reichenbach, M. Krstic, F. Merchant, Ch. Wenger
Scientific Reports 14, 23695 (2024)
DOI: 10.1038/s41598-024-73439-z, (6G-RIC)
Resistive Random Access Memory (RRAM) has gained considerable momentum due to its non-volatility and energy efficiency. Material and device scientists have been proposing novel material stacks that can mimic the “ideal memristor” which can deliver performance, energy efficiency, reliability and accuracy. However, designing RRAM-based systems is challenging. Engineering a new material stack, designing a device, and experimenting takes significant time for material and device researchers. Furthermore, the acceptability of the device is ultimately decided at the system level. We see a gap here where there is a need for facilitating material and device researchers with a “push button” modeling framework that allows to evaluate the efficacy of the device at system level during early device design stages. Speed, accuracy, and adaptability are the fundamental requirements of this modelling framework. In this paper, we propose a digital twin (DT)-like modeling framework that automatically creates RRAM device models from device measurement data. Furthermore, the model incorporates the peripheral circuit to ensure accurate energy and performance evaluations. We demonstrate the DT generation and DT usage for multiple RRAM technologies and applications and illustrate the achieved performance of our GPU implementation. We conclude with the application of our modeling approach to measurement data from two distinct fabricated devices, validating its effectiveness in a neural network processing an Electrocardiogram (ECG) dataset and incorporating Fault Aware Training (FAT).

(27) A Flexible and Fast Digital Twin for RRAM Systems Applied for Training Resilient Neural Networks
M. Fritscher, S. Singh, T. Rizzi, A. Baroni, D. Reiser, M. Mallah, D. Hartmann, A. Bende, T. Kempen, M. Uhlmann, G. Kahmen, D. Fey, V. Rana, S. Menzel, M. Reichenbach, M. Krstic, F. Merchant, Ch. Wenger
Scientific Reports 14, 23695 (2024)
DOI: 10.1038/s41598-024-73439-z, (iCampus II)
Resistive Random Access Memory (RRAM) has gained considerable momentum due to its non-volatility and energy efficiency. Material and device scientists have been proposing novel material stacks that can mimic the “ideal memristor” which can deliver performance, energy efficiency, reliability and accuracy. However, designing RRAM-based systems is challenging. Engineering a new material stack, designing a device, and experimenting takes significant time for material and device researchers. Furthermore, the acceptability of the device is ultimately decided at the system level. We see a gap here where there is a need for facilitating material and device researchers with a “push button” modeling framework that allows to evaluate the efficacy of the device at system level during early device design stages. Speed, accuracy, and adaptability are the fundamental requirements of this modelling framework. In this paper, we propose a digital twin (DT)-like modeling framework that automatically creates RRAM device models from device measurement data. Furthermore, the model incorporates the peripheral circuit to ensure accurate energy and performance evaluations. We demonstrate the DT generation and DT usage for multiple RRAM technologies and applications and illustrate the achieved performance of our GPU implementation. We conclude with the application of our modeling approach to measurement data from two distinct fabricated devices, validating its effectiveness in a neural network processing an Electrocardiogram (ECG) dataset and incorporating Fault Aware Training (FAT).

(28) Area-Efficient Digital Design using RRAM-CMOS Standardcells
M. Fritscher, M. Uhlmann, P. Ostrovskyy, D. Reiser, J.-C. Chen, M.A. Schubert, C. Schulze, G. Kahmen, D. Fey, M. Reichenbach, M. Kristic, Ch. Wenger
Proc. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2024), 81 (2024)
DOI: 10.1109/ISVLSI61997.2024.00026, (6G-RIC)

(29) Area-Efficient Digital Design using RRAM-CMOS Standardcells
M. Fritscher, M. Uhlmann, P. Ostrovskyy, D. Reiser, J.-C. Chen, M.A. Schubert, C. Schulze, G. Kahmen, D. Fey, M. Reichenbach, M. Kristic, Ch. Wenger
Proc. IEEE Computer Society Annual Symposium on VLSI (ISVLSI 2024), 81 (2024)
DOI: 10.1109/ISVLSI61997.2024.00026, (KI-IoT)

(30) Machine Learning Based Beam Selection for Maximizing Wireless Network Capacity
P. Geranmayeh, E. Grass
IEEE Access 12, 45176 (2024)
DOI: 10.1109/ACCESS.2024.3381542, (5G-REMOTE)
In today’s and future wireless communications, especially in 5G and 6G networks, machine learning (ML) methods are crucial. Potentially, these techniques bring many benefits such as increased data throughput, improved security, reduced latency, and, on the whole, enhanced network efficiency. Furthermore, to facilitate the processing of large amounts of data in real-time situations, machine learning is used for various functions in wireless networks. This article aims to explore the significance and application of machine learning, with a particular focus on classic reinforcement learning, in the context of predicting optimal beam configurations within wireless communications scenarios. Our goal is to minimize interference between transmitters by finding the optimal beamforming angles. For this, ray tracing techniques are deployed. We see this research as a step forward towards integrating digital twin (DT) technology in network management and control. In this article, different machine learning methods are used and their performance is compared. Firstly, the most effective angles for beamforming, maximizing channel capacity are identified. Then, by using these methods and after verifying their accuracy, the optimal antenna angles in scenarios with an increased number of transmitters and receivers is found and evaluated.

(31) Comparison of Optimization Techniques and Machine Learning Methods for Optimized Beamforming in Wireless Networks
P. Geranmayeh, E. Grass
Proc. IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC 2024), 66 (2024)
DOI: 10.1109/APWC61918.2024.10701890, (5G-REMOTE)

(32) Neural Networks for Predicting the Optimal Beamforming Angles for Maximized Overall Wireless Network Capacity
P. Geranmayeh, E. Grass
Proc. 6th  International Conference on Artificial Intelligence in Information and Communication (ICAIIC 2024), 77 (2024)
DOI: 10.1109/ICAIIC60209.2024.10463195, (5G-REMOTE)

(33) Neural Networks for Predicting the Optimal Beamforming Angles for Maximized Overall Wireless Network Capacity
P. Geranmayeh, E. Grass
Proc. 6th  International Conference on Artificial Intelligence in Information and Communication (ICAIIC 2024), 77 (2024)
DOI: 10.1109/ICAIIC60209.2024.10463195, (IHP - Humboldt-Universität Joint-Lab)

(34) Self-Aware Reliable and Reconfigurable Computing Systems - An Overview
D. Göhringer, A. Podlubne, F. Vargas, M. Krstic
Proc. IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW 2024), 124 (2024)
DOI: 10.1109/IPDPSW63119.2024.00036

(35) A Feature Extraction Approach for the Detection of Phishing Websites Using Machine Learning
S.C. Gundla, M.K. Praveen, M.J.K. Reddy, G. Gourav, A. Pankaj, Z. Stamenkovic, S.P. Raja
Journal of Circuits, Systems, and Computers (JCSC) 33(2), 2450031 (2024)
DOI: 10.1142/S0218126624500312, (BB-KI-Chips)
In this growing world of the internet, most of our daily routine tasks are somehow connected to the internet, from smartphones to IoT devices to cloud networks. Internet users are growing rapidly, and the internet is accessible to everyone from anywhere. Data phishing is a cyber security attack that uses deception to trick internet users to get their content and information. In these some malicious users try to steal personal data such as bank details, login credentials, credit card details, and health care information of others on the internet. They exploit users’ sensitive information using vulnerabilities. Information stealers are known as Phishers. Phishers use different techniques for phishing. One of the most common methods is to direct users to some false website to enter their login credentials and their details on these phishing sites. They look the same as the original websites. Phishers use these details to get access to the user’s accounts and hijack the user account for monetary purposes. Many internet users get into this trap of phishing sites and share their personal and sensitive details. In this paper, we will analyze and implement machine-learning techniques to detect phishing attacks. There are different methods to identify phishing attacks, one of them is by checking the URL address using Machine learning. ML is used as a way to teach a machine to differentiate between phishing and original site URLs. There are many different techniques to overcome this attack. This research paper aims to provide accurate and true phishing detection with less time complexity.

(36) Seamless Integration of Efficient 6G Wireless Technologies for Communication and Sensing Enabling Ecosystems
J. Gutierrez Teran, V. Sark, M. Ozätes, A. Tzanakaki, M. Anastasopoulos, V. Frascolla, I. Mesogiti, E. Theodoropoulou, G. Lyberopoulos, L. Díez, R. Agüero, I. Santamaría, P. Sen, S. Pryor, S. Mumtaz, S. Pontarelli, F. Trombetti, N. Bartolini, E. Jorswieck, X. Ding, N. Nikaein
Proc. 9th Workshop on 5G - Putting Intelligence to the Network Edge (5G-PINE 2024) in: Artificial Intelligence Applications and Innovations. AIAI 2024 IFIP WG 12.5 International Workshops, Springer, IFIPAICT 715, 190 (2024)
DOI: 10.1007/978-3-031-63227-3_13, (6G-SENSES)

(37) Understanding Transistor Aging Impact on the Behavior of RRAM Cells
S.H. Hashemi Shadmehri, S. Chakraborty, T. Copetti, F. Vargas, L. Bolzani Poehls
Proc. IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC 2024), (2024)
(TAICHIP)

(38) Exploiting Static Power Consumption in Side-Channel Analysis
I. Kabin, P. Langendörfer, Z. Dyka
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534604, (Total Resilience)

(39) Static Power Consumption as a New Side-Channel Analysis Threat to Elliptic Curve Cryptography Implementations
I. Kabin, Z. Dyka, A.A. Sigourou, P. Langendörfer
Proc. IEEE  International Conference on Cyber Security and Resilience: Workshop on Hardware Cybersecurity Systems (HACS 2024), 884 (2024)
DOI: 10.1109/CSR61664.2024.10679507, (Total Resilience)

(40) Stealth Attacks on PCBs: An Experimental Plausibility Analysis
I. Kabin, J. Schäffner, A.A. Sigourou, D. Petryk, Z. Dyka,, D. Klein, S. Freud, P. Langendörfer
Proc. IEEE International Conference on Cyber Security and Resilience: Workshop on Hardware Cybersecurity Systems (HACS 2024), 905 (2024)
DOI: 10.1109/CSR61664.2024.10679465, (PANDA)

(41) Resilience-by-Design in 6G Networks: Literature Review and Novel Enabling Concepts
L. Khaloopour, Y. Su, F. Raskob, T. Meuser, R. Bless, L. Würsching, K. Abedi , M. Andjelkovic, H. Chaari, P. Chakraborty, M. Kreutzer, M. Hollick, T. Strufe, N. Franchi, V. Jamali
IEEE Access 12, 155666 (2024)
DOI: 10.1109/ACCESS.2024.3480275, (Open 6G Hub)
The sixth generation (6G) mobile communication networks are expected to intelligently integrate into various aspects of modern digital society, including smart cities, homes, health-care, transportation, and factories. While offering a multitude of services, it is likely that societies become increasingly reliant on 6G infrastructure. Any disruption to these digital services, whether due to human or technical failures, natural disasters, or terrorism, would significantly impact citizens’ daily lives. Hence, 6G networks need not only to provide high-performance services but also to be resilient in maintaining essential services in the face of potentially unknown challenges. This paper provides a general review of the state of the art on resilient systems, definitions, concepts, and approaches. Moreover, it introduces a comprehensive concept, i.e., resilience-by-design (RBD), in three different levels for designing resilient 6G communication networks, summarizing our initial studies within the German Open6GHub project. First, we outline the general RBD enabling principles and discuss their related sub-categories. Next, adopting an interdisciplinary approach, we propose to embed these principles across all 6G layers/perspectives including electronics, physical channel, network components and functions, networks, services, and cross-layer and cross-infrastructure considerations and discuss their challenges. We further elaborate the RBD principles and their realizations along with several 6G use-cases. The paper is concluded by presenting a comprehensive list of open problems for future research on 6G resilience.

(42) Peakrad - A Completely European, ITAR-Free Microcontroller for Space Applications
F.A. Kuentzer, M. Krstic, K. Tittelbach-Helmrich, J. Cueto, C. Duran, M. Schmidt, C. Ferdinand, A. von Blomberg, C. Calligaro, U. Gatti
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 111 (2024)
(MORAL)

(43) Towards SEU Fault Propagation Prediction with Spatio-Temporal Graph Convolutional Networks
L. Lu, J.-C. Chen, M. Ulbricht, M. Krstic
Proc. 27th Design, Automation and Test in Europe (DATE 2024), (2024)
(VE-HEP)

(44) Machine Learning Methodologies to Predict the Rresults of Simulation-Based Fault Injection
L. Lu, J.-C. Chen, M. Ulbricht, M. Krstic
IEEE Transactions on Circuits and Systems I 71(5), 1978 (2024)
DOI: 10.1109/TCSI.2024.3349928, (VE-HEP)
Simulation-based fault injection is a widely used technique for early-stage circuit reliability analysis. However, it consumes significant time, particularly for complex circuits. This paper introduces two Machine Learning (ML) methodologies to predict simulation-based fault injection outcomes at the gate level. The initial approach employs Neural Networks (NNs), extracting structural features from synthesis reports and simulation-related characteristics from Value Change Dump (VCD) waveforms. Nevertheless, NNs are restricted to learning from individual gate attributes. To exploit the comprehensive structure of entire circuits, we propose a method to convert circuits into graphs. This facilitates the utilization of Graph Neural Networks (GNNs) as advanced models, resulting in improved prediction performance. We select six open-source circuits with diverse complexities and functions to validate these methodologies and explore their adaptability across various circuits. Our experiments demonstrate the superior performance of GNNs compared to NNs in terms of prediction accuracy, efficiency in hyperparameter search, and the ability to address imbalanced datasets. Additionally, we investigate the feasibility of deploying the trained models to predict results in new circuits. Based on the experimental outcomes, we present an approach for leveraging the proposed methodology to accelerate simulation-based fault injection.

(45) Towards Critical Flip-Flop Identification for Soft-Error Tolerance with Graph Neural Networks
L. Lu, J.-C. Chen, M. Ulbricht, M. Krstic
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43(4), 1135 (2024)
DOI: 10.1109/TCAD.2023.3331968, (VE-HEP)
Nanometer circuits are becoming increasingly susceptible to soft errors. Selective hardening is a less expensive technique to improve the reliability of circuits because it hardens the critical components instead of hardening an entire circuit. One challenge of selective hardening is efficiently and effectively identifying the critical parts in circuits. Simulation-based fault injection is commonly used but extremely time-consuming, especially for complex circuits. This article proposes an approach based on graph neural networks (GNNs) to identify critical flip-flops in circuits. GNNs can take advantage of the circuit’s structural features and the features of individual flip-flops. To convert the features into abstract data that can be fed into GNNs, we provide a feature extraction method that uses a graph model to represent the relevant features of the circuit. The method converts the target circuit into a graph representing its architecture. The graph also contains features of individual flip-flops extracted from the circuit’s netlist and the value change dump (VCD) waveforms of the test used for fault simulation. Additionally, we extract edge features in the graph to utilize the information on combinational gates on the path between flip-flops. Datasets generated based on two open-source RISC-V cores are used to validate the proposed approach. We compare the performance of different GNNs on them and discuss the contribution of edge features to their performance. Our experiments show that the prediction accuracy increases significantly with edge features. GraphSAGE and SAGE-GCN with edge features perform best among the selected GNNs. The highest accuracy we achieved on Ibex and RI5CY is 97.75% and 98.67%, respectively. We also provide a method to accelerate the process of critical flip-flop identification.

(46) Analysis of IQ Imbalance Effects on Physical Layer Secure Key Generation in mmWave Systems
N. Manjappa, N. Maletic, L. Wimmer, E. Grass
Proc. 11th Intenational Symposium on Networks, Computers and Communications (ISNCC 2024), (2024)
DOI: 10.1109/ISNCC62547.2024.10759029, (Open 6G Hub)

(47) A Novel Ensemble Machine Learning Algorithm for Predicting the Suitable Crop to Cultivate Based on Soil and Environment Characteristics
G. Mariammal, A. Suruliandi, Z. Stamenkovic, S.P. Raja
IEEE Canadian Journal of Electrical and Computer Engineering 47(3), 127 (2024)
DOI: 10.1109/ICJECE.2024.3400048, (BB-KI-Chips)
Research in agriculture is a promising field, and crop prediction for particular land areas is especially critical to agriculture. Such prediction depends on the soil, minerals and environment, the last of which has been short-changed by changing climatic conditions. Consequently, crop prediction for a particular zone presents difficulties for farmers. This is where machine learning steps in with techniques that are widely applied in agriculture. This work proposes a Weighted Stacked Ensemble method for the crop prediction process. It combines two base learners or classifiers to construct the Weighted Stacked Ensemble, which is a single predictive ensemble model, using weighted instances. The experimental outcomes show that the proposed Weighted Stacked Ensemble outperforms other classification and ensemble techniques in terms of improved crop prediction accuracy.

(48) Image Processing for Smart Agriculture Applications using Cloud-Fog Computing
D. Markovic, Z. Stamenkovic, B. Dordevic, S. Randic
Sensors (MDPI) 24(18), 5965 (2024)
DOI: 10.3390/s24185965
The widespread use of IoT devices has led to the generation of a huge amount of data and driven the need for analytical solutions in many areas of human activities, such as the field of smart agriculture. Continuous monitoring of crop growth stages enables timely interventions, such as control of weeds and plant diseases, as well as pest control, ensuring optimal development. Decision-making systems in smart agriculture involve image analysis with the potential to increase productivity, efficiency and sustainability. By applying Convolutional Neural Networks (CNNs), state recognition and classification can be performed based on images from specific locations. Thus, we have developed a solution for early problem detection and resource management optimization. The main concept of the proposed solution relies on a direct connection between Cloud and Edge devices, which is achieved through Fog computing. The goal of our work is creation of a deep learning model for image classification that can be optimized and adapted for implementation on devices with limited hardware resources at the level of Fog computing. This could increase the importance of image processing in the reduction of agricultural operating costs and manual labor. As a result of the off-load data processing at Edge and Fog devices, the system responsiveness can be improved, the costs associated with data transmission and storage can be reduced, and the overall system reliability and security can be increased. The proposed solution can choose classification algorithms to find a trade-off between size and accuracy of the model optimized for devices with limited hardware resources. After testing our model for tomato disease classification compiled for execution on FPGA, it was found that the decrease in test accuracy is as small as 0.83% (from 96.29% to 95.46%).

(49) Towards Secure and Reliable Heterogeneous Real-Time Telemetry Communication in Autonomous UAV Swarms
P. Mykytyn, M. Brzozowski, Z. Dyka, P. Langendörfer
Proc. iCampus Cottbus Conference (iCCC 2024), 165 (2024)
DOI: 10.5162/iCCC2024/P15, (iCampus)

(50) A Survey on Sensor- and Communication-based Issues of Autonomous UAVs
P. Mykytyn, M. Brzozowski, Z. Dyka, P. Langendörfer
Computer Modeling in Engineering & Sciences 138(2), 1019 (2024)
DOI: 10.32604/cmes.2023.029075, (iCampus II)
The application field for Unmanned Aerial Vehicle (UAV) technology and its adoption rate have been increasing steadily in the past years. Decreasing cost of commercial drones has enabled their use at a scale broader than ever before. However, increasing the complexity of UAVs and decreasing the cost, both contribute to a lack of implemented security measures and raise new security and safety concerns. For instance, the issue of implausible or tampered UAV sensor measurements is barely addressed in the current research literature and thus, requires more attention from the research community. The goal of this survey is to extensively review state-of-the-art literature regarding common sensor- and communication-based vulnerabilities, existing threats, and active or passive cyber-attacks against UAVs, as well as shed light on the research gaps in the literature. In this work, we describe the Unmanned Aerial System (UAS) architecture to point out the origination sources for security and safety issues. We evaluate the coverage and completeness of each related research work in a comprehensive comparison table as well as classify the threats, vulnerabilities and cyber-attacks into sensor-based and communication-based categories. Additionally, for each individual cyber-attack, we describe existing countermeasures or detection mechanisms and provide a list of requirements to ensure UAV’s security and safety. We also address the problem of implausible sensor measurements and introduce the idea of a plausibility check for sensor data. By doing so, we discover additional measures to improve security and safety and report on a research niche that is not well represented in the current research literature.

(51) Enhancing the WLAN OFDM-PHY by OTFS Precoding
M. Nauman, L. Lopacinski, N. Maletic, M. Scheide, J. Gutiérrez Teran, M. Krstic, E. Grass
Proc. 33rd Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit 2024), (2024)
DOI: 10.1109/EuCNC/6GSummit60053.2024.10597133, (PSSS-FEC)

(52) Software Implemented Implication-based Online Error Detection
J. Nedeljkovic, G. Nikolic, M. Andjelkovic, T Nikolic
Proc. 59th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST 2024), (2024)
DOI: 10.1109/ICEST62335.2024.10639740

(53) An Efficient and Low Complexity Greedy Power Allocation Algorithm for URLLC Links
N. Odhah, E. Grass, R. Kraemer
Proc. iCampus Cottbus Conference (iCCC 2024), 175 (2024)
(5G-REMOTE)

(54) Unsourced Random Access Using ODMA and Polar Codes 
M. Özates, M. Kazemi, T.M. Duman
IEEE Wireless Communications Letters 13(4), 1044 (2024)
DOI: 10.1109/LWC.2024.3359270
We utilize the on-off division multiple access technique in unsourced random access and develop a high-performing solution operating on both Gaussian and fading multiple access channels based on polar coding. We propose a transmission structure where a fixed part of the transmission frame is utilized for pilot transmission while the users exploit a randomly-selected small fraction of the rest of the frame for data transmission. Our proposed scheme employs a simple, yet efficient pattern detection and single-user decoding algorithm at the receiver, which leads to a superior performance with similar complexity, or a competitive performance with a significantly lower complexity compared to the existing approaches.

(55) Employing Optical Beam-Induced Current Measurement in Side-Channel Analysis
D. Petryk, I. Kabin, J. Bělohoubek, P. Fišer, J. Schmidt, M. Krstic, Z. Dyka
Proc. 36. ITG/GMM/GI-Workshop Testmethoden und Zuverlässigkeit von Schaltungen und Systemen (TuZ 2024), 15 (2024)
(Total Resilience)

(56) On the Importance of Reproducibility of Experimental Results Especially in the Domain of Security
D. Petryk, I. Kabin, P. Langendörfer, Z. Dyka
Proc. 13th Mediterranean Conference on Embedded Computing (MECO 2024), 311 (2024)
DOI: 10.1109/MECO62516.2024.10577919, (Total Resilience)

(57) Resistance of Radiation Tolerant TMR Shift Registers to Optical Fault Injections
D. Petryk, P. Langendörfer, Z. Dyka
Works in Progress in Embedded Computing Journal (WiPiEC) 10(2), 1 (2024)
(Total Resilience)
Protection of information is essential for IoT devices. They are often subject to lab analysis with the objective to reveal secret hidden information. One of the ways to reveal the cryptographic key is to perform optical Fault Injection attacks. In this work, we investigated the IHP radiation tolerant shift registers built of Triple Modular Redundant flip-flops. In our experiments, we were able to inject different transient faults into TMR registers using a single laser beam.

(58) Resistance of Radiation Tolerant TMR Shift Registers to Optical Fault Injections
D. Petryk, P. Langendörfer, Z. Dyka
Proc. 27th Euromicro Conference Series on Digital System Design (DSD 2024), (2024)
(Total Resilience)

(59) Design and Analysis of an Adaptive Radiation Resilient RRAM Subsystem for Processing Systems in Satellites
D. Reiser, J.-C. Chen, J. Knödtel, M. Krstic, M. Reichenbach
Design Automation for Embedded Systems 28, 111 (2024)
DOI: 10.1007/s10617-024-09285-z, (Open 6G Hub)
Among the numerous benefits that novel RRAM devices offer over conventional memory technologies is an inherent resilience to the effects of radiation. Hence, they appear suitable for use as a memory subsystem in a computer architecture for satellites. In addition to memory devices resistant to radiation, the concept of applying protective measures dynamically promises a system with low susceptibility to errors during radiation events, while also ensuring efficient performance in the absence of radiation events. This paper presents the first RRAM-based memory subsystem for satellites with a dynamic response to radiation events. We integrate this subsystem into a computing platform that employs the same dynamic principles for its processing system and implements modules for timely detection and even prediction of radiation events. To determine which protection mechanism is optimal, we examine various approaches and simulate the probability of errors in memory. Additionally, we are studying the impact on the overall system by investigating different software algorithms and their radiation robustness requirements using a fault injection simulation. Finally, we propose a potential implementation of the dynamic RRAM-based memory subsystem that includes different levels of protection and can be used for real applications in satellites.

(60) Design and Analysis of an Adaptive Radiation Resilient RRAM Subsystem for Processing Systems in Satellites
D. Reiser, J.-C. Chen, J. Knödtel, M. Krstic, M. Reichenbach
Design Automation for Embedded Systems 28, 111 (2024)
DOI: 10.1007/s10617-024-09285-z, (Scale4Edge)
Among the numerous benefits that novel RRAM devices offer over conventional memory technologies is an inherent resilience to the effects of radiation. Hence, they appear suitable for use as a memory subsystem in a computer architecture for satellites. In addition to memory devices resistant to radiation, the concept of applying protective measures dynamically promises a system with low susceptibility to errors during radiation events, while also ensuring efficient performance in the absence of radiation events. This paper presents the first RRAM-based memory subsystem for satellites with a dynamic response to radiation events. We integrate this subsystem into a computing platform that employs the same dynamic principles for its processing system and implements modules for timely detection and even prediction of radiation events. To determine which protection mechanism is optimal, we examine various approaches and simulate the probability of errors in memory. Additionally, we are studying the impact on the overall system by investigating different software algorithms and their radiation robustness requirements using a fault injection simulation. Finally, we propose a potential implementation of the dynamic RRAM-based memory subsystem that includes different levels of protection and can be used for real applications in satellites.

(61) MIMO Capacity Maximization with Beyond-Diagonal RIS
I. Santamaria, M. Soleymani, E. Jorswieck, J. Gutiérrez Teran
Proc. 25th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2024), 936 (2024)
DOI: 10.1109/SPAWC60668.2024.10694491, (6G-SENSES)

(62) Radiation-Hardening-by-Design Triple Modular Redundancy Flip-Flops with Self-Correction
O. Schrape, A. Breitenreiter, L. Lu, M. Andjelkovic, E.P. Garcia, M. Lopez-Vallejo, M. Krstic
Proc. IEEE Nordic Circuits and Systems Conference (NorCAS 2024), (2024)
DOI: 10.1109/NorCAS64408.2024.10752481
Saving power is one of the most important things in space applications and power consumption has a direct impact on system complexity and costs. One straightforward approach to reduce the power of digital systems is to stop the clock activity, i.e., clock gating (CG). When circuits are exposed to radiation and the clock activity has stopped, resulting upsets accumulate and may destroy the systems’ configuration. Thus, a self-correction (SC) mechanism has to be developed in order to mitigate Single Event Effects (SEE) even though the clock signals are deactivated. This paper proposes a circuit solution for self-correcting Radiation-Hardening-by-Design (RHBD) Triple Modular Redundancy (TMR) flip-flops. The transistor- and gate- level scheme are presented, discussed and compared. A prototype chip is fabricated in a 130 nm BiCMOS technology. Radiation results show a robustness in LET above 52.5 MeV cm2 mg-1 for the novel self-correcting RHBD TMR flip-flop.

(63) Experimental Object Localization using mmWave Beamforming Communication System
E. Sedunova, N. Maletic, D. Cvetkovski, E. Grass
Proc. 287. ITG Fachtagung Mobilkommunikation (2024), in: ITG-Fachbericht: Mobilkommunikation – Technologien und Anwendungen, VDE ITG, 316, 143 (2024)
(Open 6G Hub)

(64) Analysis of LoS MIMO Channel for the D-Band
P. Shakya, D. Cvetkovski, K. Krishnegowda, L. Lopancinski, E. Grass
Proc. IEEE Future Networks World Forum (FNWF 2024), (2024)
(PSSS-FEC)

(65) Analysis of LoS MIMO Channel for the D-Band
P. Shakya, D. Cvetkovski, K. Krishnegowda, L. Lopancinski, E. Grass
Proc. IEEE Future Networks World Forum (FNWF 2024), (2024)
(6G-RIC)

(66) Joint Radar and Communications: Architectures, Use Cases, Aspects of Radio Access, Signal Processing, and Hardware
V. Shatov, B. Nuss, S. Schieler, P.K. Bishoyi, L. Wimmer, M. Lübke, N. Keshtiarast, Ch. Fischer, D. Lindenschmitt, B. Geiger, R. Thomä, A. Fellan, L. Schmalen, M. Petrova, H.D. Schotten, N. Franchi
IEEE Access 12, 47888 (2024)
DOI: 10.1109/ACCESS.2024.3383771, (Open 6G Hub)
Integrated Radar and Communications (JRC) can satisfy the apparent demand for applications based on object detection, tracking, ranging, and positioning. JRC is, therefore, often seen as candidate technology for 6G mobile systems. Implementing JRC will require novel approaches in many research and engineering fields, including protocol design, digital and analog signal processing, and hardware development. The ongoing debates on JRC already include many white papers and research articles ranging in content from very specific technical problems to comprehensive bird’s eye-level reviews. This paper represents the work within the Open6GHub research project in Germany, which aims to investigate and implement potential end-to-end solutions for 6G. In this framework, we propose a consolidated vision for potential JRC architectural approaches. The subsequent discussion on integrating radar sensing with communications highlights this technology’s state-of-the-art and presents relevant opportunities and challenges.

(67) Energy Efficiency Comparison of RIS Architectures in MISO Broadcast Channels
M. Soleymani, I. Santamaria, E. Jorswieck, M. Di Renzo, J. Gutiérrez Teran
Proc. 25th IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2024), 701 (2024)
DOI: 10.1109/SPAWC60668.2024.10694177, (6G-SENSES)

(68) Test Cost Reduction for VLSI Adaptive Test with K-Nearest Neighbor Classification Algorithm
T. Song, Z. Huang, Q. Hong, L. Zhang, M. Krstic
IEEE Transactions on Circuits and Systems II 71(7), 3508 (2024)
DOI: 10.1109/TCSII.2024.3362957
Ensuring the impeccable quality of integrated circuits (ICs) is of utmost importance to the customers. However, the increasing scaling of advanced nanoscale circuits has resulted in also increased cost of tests. In order to optimize test cost without compromising IC quality, it is imperative to reduce test time. Addressing the issue of prolonged test duration, associated with conventional full-pattern tests approaches, this paper introduces a novel and efficient pattern selection method known as stepwise k-nearest neighbors (KNN). By harnessing the power of a classification model, this method selectively identifies and applies only the most potent patterns, that are likely to lead to test failures. This approach dramatically expedites the testing process, resulting in substantial time savings. Experimental results showcase an impressive 27% enhancement in the accuracy of the proposed approach compared to Support Vector Machine (SVM) techniques. This signifies the effectiveness and superiority of the presented method in enhancing both the efficiency and reliability of IC testing.

(69) An Ultra-Low Cost and Multicast-Enabled Asynchronous NoC for Neuromorphic Edge Computing
Z. Su, S. Ramini, D.C. Marcolin, A. Veronesi, M. Krstic, G. Indiveri, D. Bertozzi, S. Nowick
IEEE Journal on Emerging and Selected Topics in Circuits and Systems 14(3), 409 (2024)
DOI: 10.1109/JETCAS.2024.3433427
Biological brains are increasingly taken as a guide toward more efficient forms of computing. The latest frontier considers the use of spiking neural-network-based neuromorphic processors for near-sensor data processing, in order to fit the tight power and resource budgets of edge computing devices. However, a prevailing focus on brain-inspired computing and storage primitives in the design of neuromorphic systems is currently bringing a fundamental bottleneck to the forefront: chip-scale communications. While communication architectures (typically, a network-on-chip) are generally inspired by, or even borrowed from, general purpose computing, neuromorphic communications exhibit unique characteristics: they consist of the event-driven routing of small amounts of information to a large number of destinations within tight area and power budgets. This article aims at an inflection point in network-on-chip design for brain-inspired communications, revolving around the combination of cost-effective and robust asynchronous design, architecture specialization for short messaging and lightweight hardware support for tree-based multicast. When validated with functional spiking neural network traffic, the proposed NoC delivers energy savings ranging from 42% to 71% over a state-of-the-art NoC used in a real multi-core neuromorphic processor for edge computing applications.

(70) FPGA Implementation of a Fault-Tolerant Fused and Branched CNN Accelerator with Reconfigurable Capabilities
R.T. Syed, Y. Zhao, J.-C. Chen, M. Andjelkovic, M. Ulbricht, M. Krstic
IEEE Access 12, 57847 (2024)
DOI: 10.1109/ACCESS.2024.3392240, (Open 6G Hub)
The ImageNet moment was a turning point for Convolutional Neural Networks (CNNs), as it demonstrated their potential to revolutionize computer vision tasks. This triumph of CNNs has motivated solving even more complex problems involving multiple tasks from multiple data modalities. Conventionally, a single CNN accelerator has been optimized to perform just one task or multiple correlated tasks. This study presents a shared-layers approach that leverages the pattern-learning capabilities of CNNs to perform multiple uncorrelated tasks from different modalities using a single hardware accelerator. We overcame the challenge of data imbalance in multi-modal learning by synthetic data generation. We achieved an average classification accuracy above 90% on a single CNN accelerator, which would otherwise require three accelerators. Due to the reliability concerns imposed by transistor shrinking and aging, we extended the shared layers methodology and introduced a fault-tolerant CNN accelerator with reconfigurable capabilities supporting fault-tolerant (FT), high-performance (HP), and de-stress (DS) modes. FT mode provides high reliability against soft errors utilizing double/triple modular redundancy, HP mode offers peak performance of 0.979 TOPs using parallel execution, and DS mode reduces dynamic power consumption by up to 68.6% in clock-gated design and even more using a partial reconfiguration method, contributing to decelerating the aging process of the circuit. We have comprehensively evaluated two different CNN architectures (i.e., fused and branched), for three distinct tasks, in three different operating modes, based on accuracy, quantization, pruning, hardware resource utilization, power, energy, performance, and reliability.

(71) Aging and Soft Error Resilience in Reconfigurable CNN Accelerators Employing a Multi-Purpose On-Chip Sensor
R.T. Syed, F. Vargas, M. Andjelkovic, M. Ulbricht, M. Krstic
Proc. 25th IEEE Latin-American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534625, (Open 6G Hub)

(72) A Survey on Multi-Level Fault Injection in AI Accelerators
R.T. Syed, M. Andjelkovic, F. Vargas, M. Ulbricht, M. Krstic
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 110 (2024)
(Open 6G Hub)

(73) The Impact of 5G-Enabled Edge-Cloud Services on Energy Facilities in Industry 4.0
N. Tzanis, E. Mylonas, P. Papaioannou, C. Politi, A. Birbas, C. Tranoris, S. Denazis, I. Moraitis, A. Papalexopoulos, A. Tzanakaki, J. Gutiérrez
Edge Computing Architecture - Foundations, Applications, and Frontiers, 1st Edition, Editor: Y. Chen, R. Xu, The Impact of 5G-Enabled Edge-Cloud Services on Energy Facilities in Industry 4.0, IntechOpen, 1 (2024)
DOI: 10.5772/intechopen.1005514, (5G-VICTORI)

(74) Ein Ansatz zur Optimierung konfigurierbarer fehlertoleranter Systeme
M. Ulbricht, M. Krstic
Proc. 36. ITG/GMM/GI-Workshop Testmethoden und Zuverlässigkeit von Schaltungen und Systemen (TuZ 2024), 12 (2024)
(Scale4Edge)

(75) Machine Learning Model for Classification of Space Radiation
S. Vairachilai, Z. Stamenkovic, S.P. Raja
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 107 (2024)
(BB-KI-Chips)

(76) On-Chip Infrastructure for Mission-Mode Monitoring of Aero-Space Applications: Towards Silicon Lifecycle Management
F. Vargas
Proc. 31st International Conference Mixed Design of Integrated Circuits and Systems (MIXDES 2024), abstr. book 18 (2024)

(77) Robust Systems and Technology Dissemination for Space Applications: From Cross-Layer Analytics to an Open-Access Reliability Framework
F. Vargas, M. Krstic, M. Andjelkovic, S. Andreev, A. Balashov, M. Ulbricht, J.-C. Chen
Proc. International Conference on Radiation Applications (RAP 2024), abstr. book 108 (2024)
(COCHISA)

(78) On-Chip Cross-Layer Infrastructure to Leverage System Reliability for Aero-Space Applications
F. Vargas
Proc. 27th IEEE International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS 2024), 116 (2024)
DOI: 10.1109/DDECS60919.2024.10508909

(79) On-Chip Sensor to Monitor Aging Evolution in FinFET-Based Memories
F. Vargas, V. Galstyan, G. Harutyunyan, Y. Zorian
Proc. 30th IEEE International Symposium on On-Line Testing and Robust System Design (IOLTS 2024), (2024)
DOI: 10.1109/IOLTS60994.2024.10616091

(80) Silicon Lifecycle Management Based on On-Chip Cross-Layer Sensing and Analytics for Space Applications
F. Vargas, M. Krstic, M. Andjelkovic, M. Ulbricht, J.-C. Chen
Proc. 25th IEEE Latin American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534623

(81) Multi-Technology Localization-Assisted Millimeter Wave Beam Tracking
R. Vasist, V. Sark, J. Gutierrez Teran, E. Grass
Proc. 100th IEEE Vehicular Technology Conference (VTC-Fall 2024), (2024)
(BeGREEN)

(82) Cross-Layer Reliability Analysis of NVDLA Accelerators: Exploring the Configuration Space
A. Veronesi, A. Nazzari, D. Passarello, M. Krstic, M. Favalli, L. Cassano, A. Miele, D. Bertozzi, C. Bolchini
29th IEEE European Test Symposium (ETS 2024), (2024)
DOI: 10.1109/ETS61313.2024.10568018, (6G-RIC)

(83) Machine Learning Based Crop Yield Prediction in South India: Performance Analysis of Various Models
U. Vijay Nikhil, A.M. Pandiyan, S.P. Raja, Z. Stamenkovic
Computers (MDPI) 13(6), 137 (2024)
DOI: 10.3390/computers, (BB-KI-Chips)
Agriculture is one of the most important activities that produces crop and food that is crucial for the sustenance of a human being. In the present day, agricultural products and crops are not only used for local demand, but globalization has allowed us to export produce to other countries and import from other countries. India is an agricultural nation and depends a lot on its agricultural activities. Prediction of crop production and yield is a necessary activity that allows farmers to estimate storage, optimize resources, increase efficiency and decrease costs. However, farmers usually predict crops based on the region, soil, weather conditions and the crop itself based on experience and estimates which may not be very accurate especially with the constantly changing and unpredictable climactic conditions of the present day. To solve this problem, we aim to predict the production and yield of various crops such as rice, sorghum, cotton, sugarcane and rabi using Machine Learning (ML) models. We train these models with the weather, soil and crop data to predict future crop production and yields of these crops. We have compiled a dataset of attributes that impact crop production and yield from specific states in India and performed a comprehensive study of the performance of various ML Regression Models in predicting crop production and yield. The results indicated that the Extra Trees Regressor achieved the highest performance among the models examined. It attained a R-Squared score of 0.9615 and showed lowest Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) of 21.06 and 33.99. Following closely behind are the Random Forest Regressor and LGBM Regressor, achieving R-Squared scores of 0.9437 and 0.9398 respectively. Moreover, additional analysis revealed that tree-based models, showing a R-Squared score of 0.9353, demonstrate better performance compared to linear and neighbors-based models, which achieved R-Squared scores of 0.8568 and 0.9002 respectively.

(84) A Study of Elliptic Curve Cryptography and its Applications
U. Vijay Nikhil, Z. Stamenkovic, S.P. Raja
International Journal of Image and Graphics (2024)
DOI: 10.1142/S0219467825500627
This paper aims to provide a comprehensive review on Elliptic Curve Cryptography (ECC), a public key cryptographic system and its applications. The paper discusses important mathematical properties and operations of elliptic curves, like point addition and multiplication operations and its implementation in cryptographic methods such as encryption and decryption. This paper provides a detailed workout on important mathematical problems on elliptic curves and ECC which provides insight into working of essential cryptographic techniques in ECC. And the paper also provides a literature review of research works based on ECC in various fields such as Internet of Things (IoT), Cloud computing, Blockchain, Image Security etc. And the paper further provides insight into the recent applications of elliptic curve cryptography in fields like IoT and Blockchain by comprehensively discussing the proposed mechanism for each of the recent applications and also briefly discussing the security of the proposed mechanism.

(85) Towards Reliable and Energy-Efficient RRAM based Discrete Fourier Transform Accelerator
J. Wen, A. Baroni, E. Perez, M. Uhlmann, M. Fritscher, K. KrishneGowda, M. Ulbricht, Ch. Wenger, M. Krstic
Proc. 27th Design, Automation and Test in Europe (DATE 2024), (2024)
(6G-RIC)

(86) Cycle-Accurate FPGA Emulation of RRAM Crossbar Array: Efficient Device and Variability Modeling with Energy Consumption Assessment
J. Wen, F. Vargas, F. Zhu, D. Reiser, A. Baroni, M. Fritscher, E. Perez, M. Reichenbach, Ch. Wenger, M. Krstic
Proc. 25th IEEE Latin-American Test Symposium (LATS 2024), (2024)
DOI: 10.1109/LATS62223.2024.10534601, (6G-RIC)

(87) Room Reconstruction Based on Bi-static mmWave Radar using the Antenna Pattern Information
L. Wimmer, M. Petri, E. Grass
IEEE Access 12, 109759 (2024)
DOI: 10.1109/ACCESS.2024.3440635, (Open 6G Hub)
Joint communication and sensing (JCAS) is one of the key topics of the upcoming 6G mobile communication standard. We propose a novel three-step method to extract the position of reflectors from channel impulse responses (CIRs) obtained by multiple bi-static RADAR measurements. The method consists of the extraction of angle-of-departure (AoD) and angle-of-arrival (AoA), the computation of potential reflecting points and the classification of the propagation paths. For the extraction of AoD and AoA, we propose a novel algorithm with low computational effort. It has a better resolution than the step size of the underlying beam search process by utilizing the antenna beam pattern together with the evaluation of the CIR. The algorithm is compared to a straightforward approach in a raytracing simulation. The evaluation shows that the proposed novel algorithm outperforms the state-of-the-art approach. Furthermore, we discuss the limitations of the proposed room reconstruction method and the potential impacts of physical effects not covered in the simulation.

(88) Real-Time Wideband Video Synchronization via an Analog QPSK Costas Loop in a Laboratory Demonstration of an E-Band Satellite Downlink
J. Wörmann, L. Manoliu, S. Haussmann, M. Krstic, I. Kallfass
Proc. IEEE Space Hardware and Radio Conference (SHaRC 2024), 23 (2024)
DOI: 10.1109/SHaRC59908.2024.10438501

(89) Multi-Target Vital Signs Monitoring using SIMO CW RADAR
Y. Zhao, V. Sark, N. Maletic, M. Krstic, E. Grass
Proc. iCampus Cottbus Conference (iCCC 2024), 153 (2024)
DOI: 10.5162/iCCC2024/P12, (iCampus)

(90) Low-Complexity Gesture Recognition based on FMCW Radar
Y. Zhao, V. Sark, M. Krstic, E. Grass
Proc. 21st European Radar Conference (EuRAD 2024), 388 (2024)
DOI: 10.23919/EuRAD61604.2024.10734900, (iCampus)

(91) High-Efficiency Gesture Recognition Using Multiple mmWave FMCW RADARs
Y. Zhao, V. Sark, M. Krstic, E. Grass
Proc. 11th International Symposium on Networks, Computers and Communications (ISNCC 2024), (2024)
DOI: 10.1109/ISNCC62547.2024.10758972, (Open 6G Hub)

(92) High-Efficiency Gesture Recognition Using Multiple mmWave FMCW RADARs
Y. Zhao, V. Sark, M. Krstic, E. Grass
Proc. 11th International Symposium on Networks, Computers and Communications (ISNCC 2024), (2024)
DOI: 10.1109/ISNCC62547.2024.10758972, (iCampus)

(93) Low-Complexity Gesture Recognition based on FMCW Radar
Y. Zhao, V. Sark, M. Krstic, E. Grass
Proc. 21st European Radar Conference (EuRAD 2024), 388 (2024)
DOI: 10.23919/EuRAD61604.2024.10734900, (Open 6G Hub)

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