Signal and Information Processing for Intelligent Systems
Our target is to deliver high-quality research to provide innovative solutions by creating theories and algorithms that blend different disciplines. We focus on establishing synergies between fundamental theory, algorithmic solutions, and application-specific implementations with the goal of providing technical contributions that have important societal impacts. By providing a healthy and vibrating working environment, SIGIPRO gives profound importance to attract, consolidate, and encourage internationally recognized human resources devoted to fundamental and applied research.
SIGIPRO aims at generating impact in multiple application domains:
- smart water networks
- energy and communication networks
- e-health
- complex finance engineering systems
- brain networks and cognitive neuroscience
- collaborative robots
- industry 4.0/5.0, digitalization of industry
- embedded intelligence for next-generation batteries
- autonomous self-navigation
- human-machine interfaces
- process optimization in wind farms and hydropower plants
- transportation and biological networks
People at Signal and Information Processing for Intelligent Systems
Who we are?
Simula Metropolitan employees are researchers, postdoctoral fellows, PhD students, engineers and administrative people. We are from all over the world, ranging from newly educated to experienced researchers, all working on making research in digital engineering at the highest international level possible.
Publications at Signal and Information Processing for Intelligent Systems
Proceedings, refereed
Neighborhood Graph Neural Networks under Random Perturbations and Quantization Errors
In IEEE International Conference on Signal Processing Advances in Wireless Communications (SPAWC). IEEE, 2022.Status: Published
Neighborhood Graph Neural Networks under Random Perturbations and Quantization Errors
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2022 |
| Conference Name | IEEE International Conference on Signal Processing Advances in Wireless Communications (SPAWC) |
| Publisher | IEEE |
| Notes | This work is a joint collaboration between SimulaMet and University of Agder. This work was supported by the IKTPLUSS DEEPCOBOT grant 306640/O70 from the Research Council of Norway. |
| DOI | 10.1109/SPAWC51304.2022.9834020 |
Online Joint Nonlinear Topology Identification and Missing Data Imputation over Dynamic Graphs
In 30th European Signal Processing Conference (EUSIPCO). IEEE, 2022.Status: Published
Online Joint Nonlinear Topology Identification and Missing Data Imputation over Dynamic Graphs
Extracting causal graph structures from multivariate time series, termed topology identification, is a fundamental problem in network science with several important applications. Topology identification is a challenging problem in real-world sensor networks, especially when the available time series are partially observed due to faulty communication links or sensor failures. The problem becomes even more challenging when the sensor dependencies are nonlinear and nonstationary. This paper proposes a kernel-based online framework using random feature approximation to jointly estimate nonlinear causal dependencies and missing data from partial observations of streaming graph-connected time series. Exploiting the fact that real-world networks often exhibit sparse topologies, we propose a group lasso-based optimization framework for topology identification, which is solved online using alternating minimization techniques. The ability of the algorithm is illustrated using several numerical experiments conducted using both synthetic and real data.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2022 |
| Conference Name | 30th European Signal Processing Conference (EUSIPCO) |
| Publisher | IEEE |
| Notes | This work is a joint collaboration between SimulaMet and University of Agder. This work was supported by the IKTPLUSS INDURB grant 270730/O70 and the SFI Offshore Mechatronics grant 237896/O30 from the Research Council of Norway. |
| URL | https://ieeexplore.ieee.org/document/9909681 |
| DOI | 10.23919/EUSIPCO55093.2022.9909681 |
Transfer Learning Based Joint Resource Allocation for Underlay D2D Communications
In IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2022.Status: Published
Transfer Learning Based Joint Resource Allocation for Underlay D2D Communications
In this paper, we investigate the application of transfer learning to train a DNN model for joint channel and power allocation in underlay Device-to-Device communication. Based on the traditional optimization solutions, generating training dataset for scenarios with perfect CSI is not computationally demanding, compared to scenarios with imperfect CSI. Thus, a transfer learning-based approach can be exploited to transfer the DNN model trained for the perfect CSI scenarios to the imperfect CSI scenarios. We also consider the issue of defining the similarity between two types of resource allocation tasks. For this, we first determine the value of outage probability for which two resource allocation tasks are same, that is, for which our numerical results illustrate the minimal need of relearning from the transferred DNN model. For other values of outage probability, there is a mismatch between the two tasks and our results illustrate a more efficient relearning of the transferred DNN model. Our results show that the learning dataset required for relearning of the transferred DNN model is significantly smaller than the required training dataset for a DNN model without transfer learning.
| Afilliation | Communication Systems, Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2022 |
| Conference Name | IEEE Wireless Communications and Networking Conference (WCNC) |
| Publisher | IEEE |
| Notes | This research work was carried out at University of Agder with funding from the FRIPRO TOPPFORSK WISECART grant 250910/F20, and completed after the SIGIPRO Department was created. |
Journal Article
Energy Efficient AoI Minimization in Opportunistic NOMA/OMA Broadcast Wireless Networks
IEEE Transactions on Green Communications and Networking (2021).Status: Accepted
Energy Efficient AoI Minimization in Opportunistic NOMA/OMA Broadcast Wireless Networks
The concept of Age of Information (AoI) minimization in wireless networks has garnered huge interest in recent times. While current literature focuses on scheduling for AoI minimization, there is also a need to efficiently utilize the underlying physical layer resources. In this paper, we consider the problem of energy-efficient scheduling for AoI minimization in an opportunistic NOMA/OMA downlink broadcast wireless network, where the user equipment operate with diverse QoS requirements. We first formulate a resource allocation problem to minimize the average AoI of the network, with energy-efficiency factored in by restricting the long term average transmit power to a predetermined threshold. A heuristic adaptation of the driftplus-penalty approach from the Lyapunov framework is then utilized to solve the original long-term mixed-integer nonlinear problem on a per time-slot basis. The single time-slot problem is further decomposed into multiple sub-problems, solving for power allocation and user scheduling separately. However, the attained power allocation sub-problems being non-convex, we propose an efficient piece-wise linear approximation to obtain a tractable solution. The scheduling sub-problem is solved optimally by using the integrality property of the linear program. Finally, we provide extensive numerical simulations to show that our proposed approach outperforms the state of the art.
| Afilliation | Communication Systems |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Journal Article |
| Year of Publication | 2021 |
| Journal | IEEE Transactions on Green Communications and Networking |
| Publisher | IEEE |
| Place Published | IEEE Transactions on Green Communications and Networking |
| Notes | This research work was carried out at University of Agder and completed after the SIGIPRO Department was created. This work was supported by the Research Council of Norway through FRIPRO TOPPFORSK under Grant WISECART 250910/F20. |
| DOI | 10.1109/TGCN.2021.3135351 |
Quantization Analysis and Robust Design in Distributed Graph Filters
IEEE Transactions on Signal Processing 70 (2021): 643-658.Status: Published
Quantization Analysis and Robust Design in Distributed Graph Filters
Distributed graph filters have recently found applications in wireless sensor networks (WSNs) to solve distributed tasks such as reaching consensus, signal denoising, and reconstruction. However, when implemented over WSNs, the graph filters should deal with network limited energy constraints as well as processing and communication capabilities.Quantization plays a fundamental role to improve the latter but its effects on distributed graph filtering are little understood. WSNs are also prone to random link losses due to noise and interference. In this instance, the filter output is affected by both the quantization error and the topological randomness error, which, if it is not properly accounted in the filter design phase, may lead to an accumulated error through the filtering iterations and significantly degrade the performance. In this paper, we analyze how quantization affects distributed graph filtering over both time-invariant and time-varying graphs. We bring insights on the quantization effects for the twomost common graph filters: the finite impulse response (FIR) and autoregressive moving average (ARMA) graph filter. Besides providing a comprehensive analysis, we devise theoretical performance guarantees on the filter performancewhen the quantization stepsize is fixed or changes dynamically over the filtering iterations. For FIR filters, we show that a dynamic quantization stepsize leads to more reduction of the quantization noise than in the fixed-stepsize quantization. For ARMAgraph filters,we showthat decreasing the quantization stepsize over the iterations reduces the quantization noise to zero at the steady-state. In addition, we propose robust filter design strategies that minimize the quantization noise for both time-invariant and time-varying networks. Numerical experiments on synthetic and two real data sets corroborate our findings and show the different trade-offs between quantization bits, filter order, and robustness to topological randomness.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Journal Article |
| Year of Publication | 2021 |
| Journal | IEEE Transactions on Signal Processing |
| Volume | 70 |
| Pagination | 643 - 658 |
| Date Published | 12/2021 |
| Publisher | IEEE |
| Place Published | IEEE Transactions on Signal Processing |
| ISSN | 1053-587X |
| Notes | This work is a joint collaboration between SimulaMet and University of Agder. This work was supported in part by the TOPPFORSK WISECART under Grant 250910/F20 and in part by the IKTPLUSS INDURB under Grant 270730/O70 from the Research Council of Norway. |
| URL | https://ieeexplore.ieee.org/document/9665348 |
| DOI | 10.1109/TSP.2021.3139208 |
Cyber-Physical Systems for Smart Water Networks: A Review
IEEE Sensors Journal 21, no. 23 (2021): 26447-26469.Status: Published
Cyber-Physical Systems for Smart Water Networks: A Review
There is a growing demand to equip Smart Water Networks (SWN) with advanced sensing and computation capabilities in order to detect anomalies and apply autonomous event-triggered control. Cyber-Physical Systems (CPSs) have emerged as an important research area capable of intelligently sensing the state of SWN and reacting autonomously in scenarios of unexpected crisis development. Through computational algorithms, CPSs can integrate physical components of SWN, such as sensors and actuators, and provide technological frameworks for data analytics, pertinent decision making, and control. The development of CPSs in SWN requires the collaboration of diverse scientific disciplines such as civil, hydraulics, electronics, environment, computer science, optimization, communication, and control theory. For efficient and successful deployment of CPS in SWN, there is a need for a common methodology in terms of design approaches that can involve various scientific disciplines. This paper reviews the state of the art, challenges, and opportunities for CPSs, that could be explored to design the intelligent sensing, communication, and control capabilities of CPS for SWN. In addition, we look at the challenges and solutions in developing a computational framework from the perspectives of machine learning, optimization, and control theory for SWN.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Journal Article |
| Year of Publication | 2021 |
| Journal | IEEE Sensors Journal |
| Volume | 21 |
| Issue | 23 |
| Pagination | 26447 - 26469 |
| Date Published | Jan-12-2021 |
| Publisher | IEEE |
| ISSN | 1530-437X |
| Notes | This research work was carried out at University of Agder with funding from the IKTPLUSS INDURB grant 270730/O70 from the Research Council of Norway, and completed after the SIGIPRO Department was created. |
| URL | https://ieeexplore.ieee.org/document/9580916 |
| DOI | 10.1109/JSEN.2021.3121506 |
Proceedings, refereed
Tracking of quantized signals based on online kernel regression
In IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2021.Status: Published
Tracking of quantized signals based on online kernel regression
Kernel-based approaches have achieved noticeable success as non-parametric regression methods under the framework of stochastic optimization. However, most of the kernel-based methods in the literature are not suitable to track sequentially streamed quantized data samples from dynamic environments. This shortcoming occurs mainly for two reasons: first, their poor versatility in tracking variables that may change unpredictably over time, primarily because of their lack of flexibility when choosing a functional cost that best suits the associated regression problem; second, their indifference to the smoothness of the underlying physical signal generating those samples. This work introduces a novel algorithm constituted by an online regression problem that accounts for these two drawbacks and a stochastic proximal method that exploits its structure. In addition, we provide tracking guarantees by analyzing the dynamic regret of our algorithm. Finally, we present some experimental results that support our theoretical analysis and show that our algorithm has a favorable performance compared to the state-of-the-art.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2021 |
| Conference Name | IEEE International Workshop on Machine Learning for Signal Processing (MLSP) |
| Publisher | IEEE |
| ISBN Number | 978-1-7281-6338-3 |
| Notes | This work was carried out at University of Agder with the funding from the IKTPLUSS INDURB grant 270730/O70 and the SFI Offshore Mechatronics grant 237896/O30 from the Research Council of Norway. |
| DOI | 10.1109/MLSP52302.2021.9596115 |
Random Feature Approximation for Online Nonlinear Graph Topology Identification
In 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP). Gold Coast, Australia: IEEE, 2021.Status: Published
Random Feature Approximation for Online Nonlinear Graph Topology Identification
Online topology estimation of graph-connected time series is challenging, especially since the causal dependencies in many real-world networks are nonlinear. In this paper, we propose a kernel-based algorithm for graph topology estimation. The algorithm uses a Fourier-based Random feature approximation to tackle the curse of dimensionality associated with the kernel representations. Exploiting the fact that the real-world networks often exhibit sparse topologies, we propose a group lasso based optimization framework, which is solved using an iterative composite objective mirror descent method, yielding an online algorithm with fixed computational complexity per iteration. The experiments conducted on real and synthetic data show that the proposed method outperforms its competitors.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2021 |
| Conference Name | 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) |
| Date Published | 10/2021 |
| Publisher | IEEE |
| Place Published | Gold Coast, Australia |
| Notes | This work was carried out at University of Agder with the funding from the IKTPLUSS INDURB grant 270730/O70 and the SFI Offshore Mechatronics grant 237896/O30 from the Research Council of Norway. |
| URL | https://ieeexplore.ieee.org/document/9596512 |
| DOI | 10.1109/MLSP52302.2021.9596512 |
Data-Driven Pump Scheduling for Cost Minimization in Water Networks
In 2021 IEEE International Conference on Autonomous Systems (ICAS)2021 IEEE International Conference on Autonomous Systems (ICAS). Montreal, QC, Canada: IEEE, 2021.Status: Published
Data-Driven Pump Scheduling for Cost Minimization in Water Networks
Pumps consume a significant amount of energy in a water distribution network (WDN). With the emergence of dynamic energy cost, the pump scheduling as per user demand is a computationally challenging task. Computing the decision variables of pump scheduling relies over mixed integer optimization (MIO) formulations. However, MIO formulations are NP-hard in general and solving such problems is inefficient in terms of computation time and memory. Moreover, the computational complexity of solving such MIO formulations increases exponentially with the size of the WDN. As an alternative, we propose a data-driven approach to estimate the decision variables of pump scheduling using deep neural networks (DNN). We evaluate the performance of our trained DNN relative to a state-of-the-art MIO solver, and conclude that our DNN based approach can be used to minimize the pump switching and cost incurred due to dynamic energy in a given WDN with much lower complexity.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2021 |
| Conference Name | 2021 IEEE International Conference on Autonomous Systems (ICAS)2021 IEEE International Conference on Autonomous Systems (ICAS) |
| Date Published | 08/2021 |
| Publisher | IEEE |
| Place Published | Montreal, QC, Canada |
| Notes | This work was carried out at University of Agder with the funding from the IKTPLUSS INDURB grant 270730/O70 from the Research Council of Norway. |
| URL | https://ieeexplore.ieee.org/document/9551168 |
| DOI | 10.1109/ICAS49788.2021.9551168 |
Online Non-linear Topology Identification from Graph-connected Time Series
In 2021 IEEE Data Science and Learning Workshop (DSLW)2021 IEEE Data Science and Learning Workshop (DSLW). Toronto, ON, Canada: IEEE, 2021.Status: Published
Online Non-linear Topology Identification from Graph-connected Time Series
Estimating the unknown causal dependencies among graph-connected time series plays an important role in many applications, such as sensor network analysis, signal processing over cyber-physical systems, and financial engineering. Inference of such causal dependencies, often known as topology identification, is not well studied for non-linear non-stationary systems, and most of the existing methods are batch-based which are not capable of handling streaming sensor signals. In this paper, we propose an online kernel-based algorithm for topology estimation of non-linear vector autoregressive time series by solving a sparse online optimization framework using the composite objective mirror descent method. Experiments conducted on real and synthetic data sets show that the proposed algorithm outperforms the state-of-the-art methods for topology estimation.
| Afilliation | Machine Learning |
| Project(s) | Signal and Information Processing for Intelligent Systems |
| Publication Type | Proceedings, refereed |
| Year of Publication | 2021 |
| Conference Name | 2021 IEEE Data Science and Learning Workshop (DSLW)2021 IEEE Data Science and Learning Workshop (DSLW) |
| Date Published | June/2021 |
| Publisher | IEEE |
| Place Published | Toronto, ON, Canada |
| Notes | This work was carried out at University of Agder with the funding from the IKTPLUSS INDURB grant 270730/O70 and the SFI Offshore Mechatronics grant 237896/O30 from the Research Council of Norway. |
| URL | https://ieeexplore.ieee.org/document/9523399 |
| DOI | 10.1109/DSLW51110.2021.9523399 |