kth.sePublications
Change search
Link to record
Permanent link

Direct link
Barros da Silva Jr., José Mairton, Dr.ORCID iD iconorcid.org/0000-0002-4503-4242
Alternative names
Publications (10 of 31) Show all publications
Razavikia, S., Da Silva, J. M. & Fischione, C. (2023). ChannelComp: A General Method for Computation by Communications. IEEE Transactions on Communications, 1-1
Open this publication in new window or tab >>ChannelComp: A General Method for Computation by Communications
2023 (English)In: IEEE Transactions on Communications, ISSN 0090-6778, E-ISSN 1558-0857, p. 1-1Article in journal (Refereed) Published
Abstract [en]

Over-the-air computation (AirComp) is a well-known technique by which several wireless devices transmit by analog amplitude modulation to achieve a sum of their transmit signals at a common receiver. The underlying physical principle is the superposition property of the radio waves. Since such superposition is analog and in amplitude, it is natural that AirComp uses analog amplitude modulations. Unfortunately, this is impractical because most wireless devices today use digital modulations. It would be highly desirable to use digital communications because of their numerous benefits, such as error correction, synchronization, acquisition of channel state information, and widespread use. However, when we use digital modulations for AirComp, a general belief is that the superposition property of the radio waves returns a meaningless overlapping of the digital signals. In this paper, we break through such beliefs and propose an entirely new digital channel computing method named ChannelComp, which can use digital as well as analog modulations. We propose a feasibility optimization problem that ascertains the optimal modulation for computing arbitrary functions over-the-air. Additionally, we propose pre-coders to adapt existing digital modulation schemes for computing the function over the multiple access channel. The simulation results verify the superior performance of ChannelComp compared to AirComp, particularly for the product functions, with more than 10 dB improvement of the computation error.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
National Category
Communication Systems
Identifiers
urn:nbn:se:kth:diva-338912 (URN)10.1109/tcomm.2023.3324999 (DOI)001164695100015 ()2-s2.0-85174823953 (Scopus ID)
Note

QC 20231031

Available from: 2023-10-30 Created: 2023-10-30 Last updated: 2024-06-18Bibliographically approved
Razavikia, S., Barros da Silva Jr., J. M. & Fischione, C. (2023). Computing Functions Over-the-Air Using Digital Modulations. In: ICC 2023: IEEE International Conference on Communications: Sustainable Communications for Renaissance. Paper presented at 2023 IEEE International Conference on Communications, ICC 2023, Rome, Italy, May 28 2023 - Jun 1 2023 (pp. 5780-5786). Institute of Electrical and Electronics Engineers Inc., 2023
Open this publication in new window or tab >>Computing Functions Over-the-Air Using Digital Modulations
2023 (English)In: ICC 2023: IEEE International Conference on Communications: Sustainable Communications for Renaissance, Institute of Electrical and Electronics Engineers Inc. , 2023, Vol. 2023, p. 5780-5786Conference paper, Published paper (Refereed)
Abstract [en]

Over-the-air computation (AirComp) is a known technique in which wireless devices transmit values by analog amplitude modulation so that a function of these values is computed over the communication channel at a common receiver. The physical reason is the superposition properties of the electromagnetic waves, which naturally return sums of analog values. Consequently, the applications of AirComp are almost entirely restricted to analog communication systems. However, the use of digital communications for over-the-air computations would have several benefits, such as error correction, synchronization, acquisition of channel state information, and easier adoption by current digital communication systems. Nevertheless, a common belief is that digital modulations are generally unfeasible for computation tasks because the overlapping of digitally modulated signals returns signals that seem to be meaningless for these tasks. This paper breaks through such a belief and proposes a fundamentally new computing method, named ChannelComp, for performing over-the-air computations by any digital modulation. In particular, we propose digital modulation formats that allow us to compute a wider class of functions than AirComp can compute, and we propose a feasibility optimization problem that ascertains the optimal digital modulation for computing functions over-the-air. The simulation results verify the superior performance of ChannelComp in comparison to AirComp, particularly for the product functions, with around 10 dB improvement of the computation error.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2023
Series
IEEE International Conference on Communications, ISSN 1550-3607 ; 2023
Keywords
Digital communication, modulation, nomo-graphic functions, over-the-air computation, symmetric function
National Category
Communication Systems Telecommunications
Identifiers
urn:nbn:se:kth:diva-340806 (URN)10.1109/ICC45041.2023.10279784 (DOI)001094862605145 ()2-s2.0-85178299399 (Scopus ID)
Conference
2023 IEEE International Conference on Communications, ICC 2023, Rome, Italy, May 28 2023 - Jun 1 2023
Note

Part of ISBN 9781538674628

QC 20231214

Available from: 2023-12-14 Created: 2023-12-14 Last updated: 2024-03-12Bibliographically approved
Kant, S., Barros da Silva Jr., J. M., Fodor, G., Göransson, B., Bengtsson, M. & Fischione, C. (2023). Federated Learning Using Three-Operator ADMM. IEEE Journal on Selected Topics in Signal Processing, 17(1), 205-221
Open this publication in new window or tab >>Federated Learning Using Three-Operator ADMM
Show others...
2023 (English)In: IEEE Journal on Selected Topics in Signal Processing, ISSN 1932-4553, E-ISSN 1941-0484, Vol. 17, no 1, p. 205-221Article in journal (Refereed) Published
Abstract [en]

Federated learning (FL) has emerged as an instance of distributed machine learning paradigm that avoids the transmission of data generated on the users' side. Although data are not transmitted, edge devices have to deal with limited communication bandwidths, data heterogeneity, and straggler effects due to the limited computational resources of users' devices. A prominent approach to overcome such difficulties is FedADMM, which is based on the classical two-operator consensus alternating direction method of multipliers (ADMM). The common assumption of FL algorithms, including FedADMM, is that they learn a global model using data only on the users' side and not on the edge server. However, in edge learning, the server is expected to be near the base station and have direct access to rich datasets. In this paper, we argue that leveraging the rich data on the edge server is much more beneficial than utilizing only user datasets. Specifically, we show that the mere application of FL with an additional virtual user node representing the data on the edge server is inefficient. We propose FedTOP-ADMM, which generalizes FedADMM and is based on a three-operator ADMM-type technique that exploits a smooth cost function on the edge server to learn a global model parallel to the edge devices. Our numerical experiments indicate that FedTOP-ADMM has substantial gain up to 33% in communication efficiency to reach a desired test accuracy with respect to FedADMM, including a virtual user on the edge server.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
National Category
Communication Systems
Identifiers
urn:nbn:se:kth:diva-323513 (URN)10.1109/jstsp.2022.3221681 (DOI)000937190500014 ()2-s2.0-85142775857 (Scopus ID)
Note

QC 20230426

Available from: 2023-01-31 Created: 2023-01-31 Last updated: 2023-10-16Bibliographically approved
Sousa, D. P., Du, R., Barros da Silva Jr., J. M., Cavalcante, C. C. & Fischione, C. (2023). Leakage detection in water distribution networks using machine-learning strategies. Water Science and Technology: Water Supply, 23(3), 1115-1126
Open this publication in new window or tab >>Leakage detection in water distribution networks using machine-learning strategies
Show others...
2023 (English)In: Water Science and Technology: Water Supply, ISSN 1606-9749, E-ISSN 1607-0798, Vol. 23, no 3, p. 1115-1126Article in journal (Refereed) Published
Abstract [en]

This work proposes a reliable leakage detection methodology for water distribution networks (WDNs) using machine-learning strategies. Our solution aims at detecting leakage in WDNs using efficient machine-learning strategies. We analyze pressure measurements from pumps in district metered areas (DMAs) in Stockholm, Sweden, where we consider a residential DMA of the water distribution network. Our proposed methodology uses learning strategies from unsupervised learning (K-means and cluster validation techniques), and supervised learning (learning vector quantization algorithms). The learning strategies we propose have low complexity, and the numerical experiments show the potential of using machine-learning strategies in leakage detection for monitored WDNs. Specifically, our experiments show that the proposed learning strategies are able to obtain correct classification rates up to 93.98%.

Place, publisher, year, edition, pages
IWA Publishing, 2023
Keywords
clustering, leakage detection, machine-learning, supervised learning, unsupervised learning, water distribution network
National Category
Computer Sciences Water Engineering
Identifiers
urn:nbn:se:kth:diva-330902 (URN)10.2166/ws.2023.054 (DOI)000936903600001 ()2-s2.0-85153259498 (Scopus ID)
Note

QC 20230705

Available from: 2023-07-05 Created: 2023-07-05 Last updated: 2023-07-05Bibliographically approved
Giupponil, L., Fodor, G., Ambede, A., Hui, D., Göransson, B. & Barros da Silva Jr., J. M. (2023). Sub-Band Full-Duplex for 5G New Radio: Challenges, Solutions and Performance. In: Conference Record of the 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023: . Paper presented at 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023, Pacific Grove, United States of America, Oct 29 2023 - Nov 1 2023 (pp. 167-173). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Sub-Band Full-Duplex for 5G New Radio: Challenges, Solutions and Performance
Show others...
2023 (English)In: Conference Record of the 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023, Institute of Electrical and Electronics Engineers (IEEE) , 2023, p. 167-173Conference paper, Published paper (Refereed)
Abstract [en]

Recently, multiple works in the literature have presented encouraging results on the feasibility of in-band full-duplex (IBFD) communications in point-to-point and single cell arrangements, where the IBFD capability is provided by the base station. However, in multi-cell networks, in addition to high self-interference, full-duplex operations also face the severe problems of base station-to-base station cross-link interference (CLI), inter-sector CLI, user equipment-to-user equipment CLI, and inter-operator interference. Due to these difficulties, the research and engineering communities have recently proposed to adopt sub-band full-duplex (SBFD), as an intermediary step towards IBFD in the evolution of 5G New Radio systems. With SBFD, cellular base stations may operate the downlink and uplink on different non-overlapping frequency sub-bands within a time division duplexing carrier, which helps reduce self-interference and CLI due to the frequency isolation between the uplink and downlink sub-bands. In this paper, we focus on Frequency Range 1 operation, investigate the novel SBFD concept, and compare it to traditional time division duplexing, using realistic assumptions on multi-cell deployments, adjacent channel leakage, CLI and self-interference cancellation techniques. Our results indicate that SBFD operation may primarily be a candidate for low power deployments, with complexity and feasibility challenges in scenarios using high base station transmission power, sectorization, and in the presence of multiple operators.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
Keywords
cross-link interference, multiple antenna systems, self-interference cancellation, sub-band full-duplex
National Category
Communication Systems
Identifiers
urn:nbn:se:kth:diva-350284 (URN)10.1109/IEEECONF59524.2023.10476953 (DOI)2-s2.0-85190379402 (Scopus ID)
Conference
57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023, Pacific Grove, United States of America, Oct 29 2023 - Nov 1 2023
Note

Part of ISBN 9798350325744

QC 20240711

Available from: 2024-07-11 Created: 2024-07-11 Last updated: 2024-07-11Bibliographically approved
Mahmoudi, A., Barros da Silva Jr., J. M., Ghadikolaei, H. S. & Fischione, C. (2022). A-LAQ: Adaptive Lazily Aggregated Quantized Gradient. In: 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022: Proceedings. Paper presented at 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022, Virtual, Online, Brazil, Dec 4 2022 - Dec 8 2022 (pp. 1828-1833). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>A-LAQ: Adaptive Lazily Aggregated Quantized Gradient
2022 (English)In: 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022: Proceedings, Institute of Electrical and Electronics Engineers (IEEE) , 2022, p. 1828-1833Conference paper, Published paper (Refereed)
Abstract [en]

Federated Learning (FL) plays a prominent role in solving machine learning problems with data distributed across clients. In FL, to reduce the communication overhead of data between clients and the server, each client communicates the local FL parameters instead of the local data. However, when a wireless network connects clients and the server, the communication resource limitations of the clients may prevent completing the training of the FL iterations. Therefore, communication-efficient variants of FL have been widely investigated. Lazily Aggregated Quantized Gradient (LAQ) is one of the promising communication-efficient approaches to lower resource usage in FL. However, LAQ assigns a fixed number of bits for all iterations, which may be communication-inefficient when the number of iterations is medium to high or convergence is approaching. This paper proposes Adaptive Lazily Aggregated Quantized Gradient (A-LAQ), which is a method that significantly extends LAQ by assigning an adaptive number of communication bits during the FL iterations. We train FL in an energy-constraint condition and investigate the convergence analysis for A-LAQ. The experimental results highlight that A-LAQ outperforms LAQ by up to a 50% reduction in spent communication energy and an 11% increase in test accuracy.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022
Keywords
adaptive transmission, communication bits, edge learning, Federated learning, LAQ
National Category
Computer Sciences
Identifiers
urn:nbn:se:kth:diva-333440 (URN)10.1109/GCWkshps56602.2022.10008580 (DOI)2-s2.0-85146892229 (Scopus ID)
Conference
2022 IEEE GLOBECOM Workshops, GC Wkshps 2022, Virtual, Online, Brazil, Dec 4 2022 - Dec 8 2022
Note

Part of ISBN 9781665459754

QC 20230802

Available from: 2023-08-02 Created: 2023-08-02 Last updated: 2023-08-02Bibliographically approved
Razavikia, S., Peris, J. A., Barros da Silva Jr., J. M. & Fischione, C. (2022). Blind Asynchronous Over-the-Air Federated Edge Learning. In: 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022: Proceedings. Paper presented at 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022, Virtual, Online, Brazil, Dec 4 2022 - Dec 8 2022 (pp. 1834-1839). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Blind Asynchronous Over-the-Air Federated Edge Learning
2022 (English)In: 2022 IEEE GLOBECOM Workshops, GC Wkshps 2022: Proceedings, Institute of Electrical and Electronics Engineers (IEEE) , 2022, p. 1834-1839Conference paper, Published paper (Refereed)
Abstract [en]

Federated Edge Learning (FEEL) is a distributed machine learning technique where each device contributes to training a global inference model by independently performing local computations with their data. More recently, FEEL has been merged with over-the-air computation (OAC), where the global model is calculated over the air by leveraging the superposition of analog signals. However, when implementing FEEL with OAC, there is the challenge on how to precode the analog signals to overcome any time misalignment at the receiver. In this work, we propose a novel synchronization-free method to recover the parameters of the global model over the air without requiring any prior information about the time misalignments. For that, we construct a convex optimization based on the norm minimization problem to directly recover the global model by solving a convex semi-definite program. The performance of the proposed method is evaluated in terms of accuracy and convergence via numerical experiments. We show that our proposed algorithm is close to the ideal synchronized scenario by 10%, and performs 4times better than the simple case where no recovering method is used.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2022
Keywords
Asynchronous, federated edge learning, over-the-air computation, time misalignment
National Category
Computer Sciences
Identifiers
urn:nbn:se:kth:diva-333461 (URN)10.1109/GCWkshps56602.2022.10008588 (DOI)2-s2.0-85146155208 (Scopus ID)
Conference
2022 IEEE GLOBECOM Workshops, GC Wkshps 2022, Virtual, Online, Brazil, Dec 4 2022 - Dec 8 2022
Note

Part of ISBN 9781665459754

QC 20230802

Available from: 2023-08-02 Created: 2023-08-02 Last updated: 2023-11-01Bibliographically approved
Sousa, D. P., Du, R., B. da Silva Jr., J. M., Cavalcante, C. C. & Fischione, C. (2022). Leakage Detection In Water Distribution Networks: Efficient Training By Data Clustering. In: IWA World Water Congress & Exhibition, Sep. 2022: . Paper presented at IWA World Water Congress & Exhibition, 11-15 September 2022 Bella Center | Copenhagen, Denmark. IWA Publishing
Open this publication in new window or tab >>Leakage Detection In Water Distribution Networks: Efficient Training By Data Clustering
Show others...
2022 (English)In: IWA World Water Congress & Exhibition, Sep. 2022, IWA Publishing, 2022Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

This work proposes a reliable leakage detection methodology for water distribution networks based on machine learning techniques. The design is developed through real data acquisition from a municipal area of a water distribution network. We propose to combine both unsupervised learning (K-means and cluster validation techniques) and supervised learning (LVQ-type algorithms) for the efficient design of prototype-based classifiers. We investigated several metrics aiming to define the optimal number of clusters, in which we succeeded in reporting attractive classification accuracies (approximately 90%) on scenarios of severely limited number of prototypes.

Place, publisher, year, edition, pages
IWA Publishing, 2022
Keywords
learning vector quantization, water monitoring, clustering, unsupervised learning
National Category
Other Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:kth:diva-313005 (URN)
Conference
IWA World Water Congress & Exhibition, 11-15 September 2022 Bella Center | Copenhagen, Denmark
Projects
Mistra-InfraMaint ATITAN
Funder
Mistra - The Swedish Foundation for Strategic Environmental Research
Note

QC 20221011

Available from: 2022-05-27 Created: 2022-05-27 Last updated: 2024-03-15Bibliographically approved
Hellström, H., Barros da Silva Jr., J. M., Amiri, M. M., Chen, M., Fodor, V., Poor, H. V. & Fischione, C. (2022). Wireless for Machine Learning: A Survey. Foundations and Trends in Signal Processing, 15(4), 290-399
Open this publication in new window or tab >>Wireless for Machine Learning: A Survey
Show others...
2022 (English)In: Foundations and Trends in Signal Processing, ISSN 1932-8346, Vol. 15, no 4, p. 290-399Article, review/survey (Refereed) Accepted
Abstract [en]

As data generation increasingly takes place on devices withouta wired connection, Machine Learning (ML) related traffic willbe ubiquitous in wireless networks. Many studies have shownthat traditional wireless protocols are highly inefficient or unsustainableto support ML, which creates the need for new wirelesscommunication methods. In this monograph, we give a comprehensivereview of the state-of-the-art wireless methods that arespecifically designed to support ML services over distributeddatasets. Currently, there are two clear themes within the literature,analog over-the-air computation and digital radio resourcemanagement optimized for ML. This survey gives an introductionto these methods, reviews the most important works, highlightsopen problems, and discusses application scenarios.

Place, publisher, year, edition, pages
Now Publishers Inc., 2022
Keywords
wireless communications, machine learning, federated learning, resource allocation
National Category
Telecommunications
Research subject
Electrical Engineering
Identifiers
urn:nbn:se:kth:diva-313006 (URN)10.1561/2000000114 (DOI)
Note

QC 20220610

Available from: 2022-05-27 Created: 2022-05-27 Last updated: 2024-03-15Bibliographically approved
Kim, Y., Al Hakim, E., Haraldson, J., Eriksson, H., Barros Da Silva Junior, J. M. & Fischione, C. (2021). Dynamic Clustering in Federated Learning. In: ICC 2021 - IEEE International Conference on Communications: . Paper presented at IEEE International Conference on Communications (ICC), JUN 14-23, 2021, Conference Location: Montreal, QC, Canada. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>Dynamic Clustering in Federated Learning
Show others...
2021 (English)In: ICC 2021 - IEEE International Conference on Communications, Institute of Electrical and Electronics Engineers (IEEE) , 2021Conference paper, Published paper (Refereed)
Abstract [en]

In the resource management of wireless networks, Federated Learning has been used to predict handovers. However, non-independent and identically distributed data degrade the accuracy performance of such predictions. To overcome the problem, Federated Learning can leverage data clustering algorithms and build a machine learning model for each cluster. However, traditional data clustering algorithms, when applied to the handover prediction, exhibit three main limitations: the risk of data privacy breach, the fixed shape of clusters, and the non-adaptive number of clusters. To overcome these limitations, in this paper, we propose a three-phased data clustering algorithm, namely: generative adversarial network-based clustering, cluster calibration, and cluster division. We show that the generative adversarial network-based clustering preserves privacy. The cluster calibration deals with dynamic environments by modifying clusters. Moreover, the divisive clustering explores the different number of clusters by repeatedly selecting and dividing a cluster into multiple clusters. A baseline algorithm and our algorithm are tested on a time series forecasting task. We show that our algorithm improves the performance of forecasting models, including cellular network handover, by 43%.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2021
Series
IEEE International Conference on Communications, ISSN 1550-3607
Keywords
clustering, Federated Learning, GAN, non-HD, handover prediction
National Category
Computer Sciences
Identifiers
urn:nbn:se:kth:diva-306508 (URN)10.1109/ICC42927.2021.9500877 (DOI)000719386003137 ()2-s2.0-85115675502 (Scopus ID)
Conference
IEEE International Conference on Communications (ICC), JUN 14-23, 2021, Conference Location: Montreal, QC, Canada
Note

QC 20211220

Part of proceeding: ISBN 978-1-7281-7122-7

Available from: 2021-12-20 Created: 2021-12-20 Last updated: 2024-03-18Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-4503-4242

Search in DiVA

Show all publications