kth.sePublications
Change search
Link to record
Permanent link

Direct link
Alternative names
Publications (10 of 153) Show all publications
Ghosh, A., Honore, A. & Chatterjee, S. (2024). DANSE: Data-Driven Non-Linear State Estimation of Model-Free Process in Unsupervised Learning Setup. IEEE Transactions on Signal Processing, 72, 1824-1838
Open this publication in new window or tab >>DANSE: Data-Driven Non-Linear State Estimation of Model-Free Process in Unsupervised Learning Setup
2024 (English)In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 72, p. 1824-1838Article in journal (Refereed) Published
Abstract [en]

We address the tasks of Bayesian state estimation and forecasting for a model-free process in an unsupervised learning setup. For a model-free process, we do not have any a-priori knowledge of the process dynamics. In the article, we propose DANSE - a Data-driven Nonlinear State Estimation method. DANSE provides a closed-form posterior of the state of the model-free process, given linear measurements of the state. In addition, it provides a closed-form posterior for forecasting. A data-driven recurrent neural network (RNN) is used in DANSE to provide the parameters of a prior of the state. The prior depends on the past measurements as input, and then we find the closed-form posterior of the state using the current measurement as input. The data-driven RNN captures the underlying non-linear dynamics of the model-free process. The training of DANSE, mainly learning the parameters of the RNN, is executed using an unsupervised learning approach. In unsupervised learning, we have access to a training dataset comprising only a set of (noisy) measurement data trajectories, but we do not have any access to the state trajectories. Therefore, DANSE does not have access to state information in the training data and can not use supervised learning. Using simulated linear and non-linear process models (Lorenz attractor and Chen attractor), we evaluate the unsupervised learning-based DANSE. We show that the proposed DANSE, without knowledge of the process model and without supervised learning, provides a competitive performance against model-driven methods, such as the Kalman filter (KF), extended KF (EKF), unscented KF (UKF), a data-driven deep Markov model (DMM) and a recently proposed hybrid method called KalmanNet. In addition, we show that DANSE works for high-dimensional state estimation.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024
Keywords
State estimation, Computational modeling, Training, Bayes methods, Noise measurement, Supervised learning, Unsupervised learning, Bayesian state estimation, forecasting, neural networks, recurrent neural networks
National Category
Computer Sciences
Identifiers
urn:nbn:se:kth:diva-346102 (URN)10.1109/TSP.2024.3383277 (DOI)001200035500017 ()2-s2.0-85189517590 (Scopus ID)
Note

QC 20240503

Available from: 2024-05-03 Created: 2024-05-03 Last updated: 2024-05-03Bibliographically approved
Ghosh, A., Abdalmoaty, M., Chatterjee, S. & Hjalmarsson, H. (2024). DeepBayes—An estimator for parameter estimation in stochastic nonlinear dynamical models. Automatica, 159, Article ID 111327.
Open this publication in new window or tab >>DeepBayes—An estimator for parameter estimation in stochastic nonlinear dynamical models
2024 (English)In: Automatica, ISSN 0005-1098, E-ISSN 1873-2836, Vol. 159, article id 111327Article in journal (Refereed) Published
Abstract [en]

Stochastic nonlinear dynamical systems are ubiquitous in modern, real-world applications. Yet, estimating the unknown parameters of stochastic, nonlinear dynamical models remains a challenging problem. The majority of existing methods employ maximum likelihood or Bayesian estimation. However, these methods suffer from some limitations, most notably the substantial computational time for inference coupled with limited flexibility in application. In this work, we propose DeepBayes estimators that leverage the power of deep recurrent neural networks. The method consists of first training a recurrent neural network to minimize the mean-squared estimation error over a set of synthetically generated data using models drawn from the model set of interest. The a priori trained estimator can then be used directly for inference by evaluating the network with the estimation data. The deep recurrent neural network architectures can be trained offline and ensure significant time savings during inference. We experiment with two popular recurrent neural networks — long short term memory network (LSTM) and gated recurrent unit (GRU). We demonstrate the applicability of our proposed method on different example models and perform detailed comparisons with state-of-the-art approaches. We also provide a study on a real-world nonlinear benchmark problem. The experimental evaluations show that the proposed approach is asymptotically as good as the Bayes estimator.

Place, publisher, year, edition, pages
Elsevier Ltd, 2024
Keywords
Deep learning, Dynamical systems, Nonlinear system identification, Parameter estimation, Recurrent neural networks
National Category
Control Engineering Other Electrical Engineering, Electronic Engineering, Information Engineering Probability Theory and Statistics
Identifiers
urn:nbn:se:kth:diva-339038 (URN)10.1016/j.automatica.2023.111327 (DOI)001161034600001 ()2-s2.0-85174673962 (Scopus ID)
Note

QC 20231129

Available from: 2023-11-29 Created: 2023-11-29 Last updated: 2024-05-02Bibliographically approved
Das, S., Boberg, B., Fallon, M. & Chatterjee, S. (2024). IMU-based Online Multi-lidar Calibration.
Open this publication in new window or tab >>IMU-based Online Multi-lidar Calibration
2024 (English)Manuscript (preprint) (Other academic)
Abstract [en]

Modern autonomous systems typically use several sensors for perception. For best performance, accurate and reliable extrinsic calibration is necessary. In this research, we proposea reliable technique for the extrinsic calibration of several lidars on a vehicle without the need for odometry estimation or fiducial markers. First, our method generates an initial guess of the extrinsics by matching the raw signals of IMUs co-located with each lidar. This initial guess is then used in ICP and point cloud feature matching which refines and verifies this estimate. Furthermore, we can use observability criteria to choose a subset of the IMU measurements that have the highest mutual information — rather than comparing all the readings. We have successfully validated our methodology using data gathered from Scania test vehicles.

National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:kth:diva-343534 (URN)
Note

Submitted to IEEE IV 2024​ 35th IEEE Intelligent Vehicles Symposium, June 2 - 5, 2024. Jeju Shinhwa World, Jeju Island, Korea

QC 20240216

Available from: 2024-02-16 Created: 2024-02-16 Last updated: 2024-02-16Bibliographically approved
Honore, A., Ghosh, A. & Chatterjee, S. (2023). Compressed Sensing of Generative Sparse-Latent (GSL) Signals. In: 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings: . Paper presented at 31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, Sep 4 2023 - Sep 8 2023 (pp. 1918-1922). European Signal Processing Conference, EUSIPCO
Open this publication in new window or tab >>Compressed Sensing of Generative Sparse-Latent (GSL) Signals
2023 (English)In: 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings, European Signal Processing Conference, EUSIPCO , 2023, p. 1918-1922Conference paper, Published paper (Refereed)
Abstract [en]

We consider reconstruction of an ambient signal in a compressed sensing (CS) setup where the ambient signal has a neural network based generative model. The generative model has a sparse-latent input and we refer to the generated ambient signal as generative sparse-latent signal (GSL). The proposed sparsity inducing reconstruction algorithm is inherently non-convex, and we show that a gradient based search provides a good reconstruction performance. We evaluate our proposed algorithm using simulated data.

Place, publisher, year, edition, pages
European Signal Processing Conference, EUSIPCO, 2023
Keywords
Compressed sensing, generative models, inverse problems
National Category
Signal Processing
Identifiers
urn:nbn:se:kth:diva-340801 (URN)10.23919/EUSIPCO58844.2023.10289923 (DOI)2-s2.0-85178384307 (Scopus ID)
Conference
31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, Sep 4 2023 - Sep 8 2023
Note

Part of ISBN 9789464593600

QC 20231214

Available from: 2023-12-14 Created: 2023-12-14 Last updated: 2023-12-14Bibliographically approved
Ghosh, A., Honore, A. & Chatterjee, S. (2023). DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Bayesian Setup. In: European Signal Processing Conference: . Paper presented at 31st European Signal Processing Conference, EUSIPCO 2023, 4 September 2023 through 8 September 2023 (pp. 870-874). Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Bayesian Setup
2023 (English)In: European Signal Processing Conference, Institute of Electrical and Electronics Engineers (IEEE) , 2023, p. 870-874Conference paper, Published paper (Refereed)
Abstract [en]

We propose DANSE - a data-driven non-linear state estimation method. DANSE provides a closed-form posterior of the state of a model-free process, given linear measurements of the state in a Bayesian setup, like the celebrated Kalman filter (KF). Non-linear dynamics of the state are captured by data-driven recurrent neural networks (RNNs). The training of DANSE combines maximum-likelihood and gradient-descent in an unsupervised framework, i.e. only measurement data and no process data are required. Using simulated linear and non-linear process models, we demonstrate that DANSE - without knowledge of the process model - provides competitive performance against model-based approaches such as KF, unscented KF (UKF), extended KF (EKF), and a hybrid approach such as KalmanNet.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
Keywords
deep learning, neural networks, recurrent neural networks, state estimation, Bayesian networks, Deep neural networks, Gradient methods, Maximum likelihood estimation, Bayesian, Closed form, Data driven, Linear state estimation, Model free, Neural-networks, Nonlinear state, Process-models, State estimation methods
National Category
Control Engineering
Identifiers
urn:nbn:se:kth:diva-346076 (URN)10.23919/EUSIPCO58844.2023.10289946 (DOI)2-s2.0-85165166616 (Scopus ID)9789464593600 (ISBN)
Conference
31st European Signal Processing Conference, EUSIPCO 2023, 4 September 2023 through 8 September 2023
Note

QC 20240502

Available from: 2024-05-02 Created: 2024-05-02 Last updated: 2024-05-02Bibliographically approved
Liang, X., Cumlin, F., Schüldt, C. & Chatterjee, S. (2023). DeePMOS: Deep Posterior Mean-Opinion-Score of Speech. In: Interspeech 2023: . Paper presented at 24th International Speech Communication Association, Interspeech 2023, Dublin, Ireland, Aug 20 2023 - Aug 24 2023 (pp. 526-530). International Speech Communication Association
Open this publication in new window or tab >>DeePMOS: Deep Posterior Mean-Opinion-Score of Speech
2023 (English)In: Interspeech 2023, International Speech Communication Association , 2023, p. 526-530Conference paper, Published paper (Refereed)
Abstract [en]

We propose a deep neural network (DNN) based method that provides a posterior distribution of mean-opinion-score (MOS) for an input speech signal. The DNN outputs parameters of the posterior, mainly the posterior's mean and variance. The proposed method is referred to as deep posterior MOS (DeePMOS). The relevant training data is inherently limited in size (limited number of labeled samples) and noisy due to the subjective nature of human listeners. For robust training of DeePMOS, we use a combination of maximum-likelihood learning, stochastic gradient noise, and a student-teacher learning setup. Using the mean of the posterior as a point estimate, we evaluate standard performance measures of the proposed DeePMOS. The results show comparable performance with existing DNN-based methods that only provide point estimates of the MOS. Then we provide an ablation study showing the importance of various components in DeePMOS.

Place, publisher, year, edition, pages
International Speech Communication Association, 2023
Keywords
deep neural network, maximum-likelihood, Speech quality assessment, voice conversion challenge
National Category
Signal Processing
Identifiers
urn:nbn:se:kth:diva-337876 (URN)10.21437/Interspeech.2023-1436 (DOI)2-s2.0-85171537160 (Scopus ID)
Conference
24th International Speech Communication Association, Interspeech 2023, Dublin, Ireland, Aug 20 2023 - Aug 24 2023
Note

QC 20231010

Available from: 2023-10-10 Created: 2023-10-10 Last updated: 2023-10-23Bibliographically approved
Fontcuberta, A. E., Ghosh, A., Chatterjee, S., Mitra, D. & Nandy, D. (2023). Forecasting Solar Cycle 25 with Physical Model-Validated Recurrent Neural Networks. Solar Physics, 298(1), Article ID 8.
Open this publication in new window or tab >>Forecasting Solar Cycle 25 with Physical Model-Validated Recurrent Neural Networks
Show others...
2023 (English)In: Solar Physics, ISSN 0038-0938, E-ISSN 1573-093X, Vol. 298, no 1, article id 8Article in journal (Refereed) Published
Abstract [en]

The Sun's activity, which is associated with the solar magnetic cycle, creates a dynamic environment in space known as space weather. Severe space weather can disrupt space-based and Earth-based technologies. Slow decadal-scale variations on solar-cycle timescales are important for radiative forcing of the Earth's atmosphere and impact satellite lifetimes and atmospheric dynamics. Predicting the solar magnetic cycle is therefore of critical importance for humanity. In this context, a novel development is the application of machine-learning algorithms for solar-cycle forecasting. Diverse approaches have been developed for this purpose; however, with no consensus across different techniques and physics-based approaches. Here, we first explore the performance of four different machine-learning algorithms - all of them belonging to a class called Recurrent Neural Networks (RNNs) - in predicting simulated sunspot cycles based on a widely studied, stochastically forced, nonlinear time-delay solar dynamo model. We conclude that the algorithm Echo State Network (ESN) performs the best, but predictability is limited to only one future sunspot cycle, in agreement with recent physical insights. Subsequently, we train the ESN algorithm and a modified version of it (MESN) with solar-cycle observations to forecast Cycles 22 - 25. We obtain accurate hindcasts for Solar Cycles 22 - 24. For Solar Cycle 25 the ESN algorithm forecasts a peak amplitude of 131 +/- 14 sunspots around July 2024 and indicates a cycle length of approximately 10 years. The MESN forecasts a peak of 137 +/- 2 sunspots around April 2024, with the same cycle length. Qualitatively, both forecasts indicate that Cycle 25 will be slightly stronger than Cycle 24 but weaker than Cycle 23. Our novel approach bridges physical model-based forecasts with machine-learning-based approaches, achieving consistency across these diverse techniques.

Place, publisher, year, edition, pages
Springer Nature, 2023
Keywords
Solar cycle, Sunspots, Statistics
National Category
Astronomy, Astrophysics and Cosmology
Identifiers
urn:nbn:se:kth:diva-323588 (URN)10.1007/s11207-022-02104-3 (DOI)000913507700001 ()2-s2.0-85146268485 (Scopus ID)
Note

QC 20230208

Available from: 2023-02-08 Created: 2023-02-08 Last updated: 2023-02-08Bibliographically approved
Cumlin, F., Schüldt, C. & Chatterjee, S. (2023). Latent-based Neural Net for Non-intrusive Speech Quality Assessment. In: 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings: . Paper presented at 31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, Sep 4 2023 - Sep 8 2023 (pp. 226-230). European Signal Processing Conference, EUSIPCO
Open this publication in new window or tab >>Latent-based Neural Net for Non-intrusive Speech Quality Assessment
2023 (English)In: 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings, European Signal Processing Conference, EUSIPCO , 2023, p. 226-230Conference paper, Published paper (Refereed)
Abstract [en]

For non-intrusive speech quality assessment, we treat the mean-opinion-score (MOS) of a speech signal as a latent, and propose a latent MOS network (LaMOSNet) to estimate the MOS. At the time of training, the proposed LaMOSNet has two parts in series, with the first part providing the latent estimate, i.e. the MOS of an input speech signal, and the second part providing an estimated score by a given judge. Only the first part is used for testing. We address two inherent aspects - limited-data and noisy-data aspects - in training using stochastic gradient noise and a student-teacher type of training, motivated by semi-supervised learning. It is shown that LaMOSNet provides good performance on the Voice Conversion Challenge 2018 dataset, and state-of-the-art correlation performance on the Voice Conversion Challenge 2016 dataset.

Place, publisher, year, edition, pages
European Signal Processing Conference, EUSIPCO, 2023
National Category
Signal Processing
Identifiers
urn:nbn:se:kth:diva-340802 (URN)10.23919/EUSIPCO58844.2023.10289840 (DOI)2-s2.0-85178344523 (Scopus ID)
Conference
31st European Signal Processing Conference, EUSIPCO 2023, Helsinki, Finland, Sep 4 2023 - Sep 8 2023
Note

Part of ISBN 9789464593600

QC 20231214

Available from: 2023-12-14 Created: 2023-12-14 Last updated: 2023-12-14Bibliographically approved
Mostafaei, S., Hoang, M. T., Jurado, P. G., Xu, H., Zacarias-Pons, L., Eriksdotter, M., . . . Garcia-Ptacek, S. (2023). Machine learning algorithms for identifying predictive variables of mortality risk following dementia diagnosis: a longitudinal cohort study. Scientific Reports, 13(1)
Open this publication in new window or tab >>Machine learning algorithms for identifying predictive variables of mortality risk following dementia diagnosis: a longitudinal cohort study
Show others...
2023 (English)In: Scientific Reports, E-ISSN 2045-2322, Vol. 13, no 1Article in journal (Refereed) Published
Abstract [en]

Machine learning (ML) could have advantages over traditional statistical models in identifying risk factors. Using ML algorithms, our objective was to identify the most important variables associated with mortality after dementia diagnosis in the Swedish Registry for Cognitive/Dementia Disorders (SveDem). From SveDem, a longitudinal cohort of 28,023 dementia-diagnosed patients was selected for this study. Sixty variables were considered as potential predictors of mortality risk, such as age at dementia diagnosis, dementia type, sex, body mass index (BMI), mini-mental state examination (MMSE) score, time from referral to initiation of work-up, time from initiation of work-up to diagnosis, dementia medications, comorbidities, and some specific medications for chronic comorbidities (e.g., cardiovascular disease). We applied sparsity-inducing penalties for three ML algorithms and identified twenty important variables for the binary classification task in mortality risk prediction and fifteen variables to predict time to death. Area-under-ROC curve (AUC) measure was used to evaluate the classification algorithms. Then, an unsupervised clustering algorithm was applied on the set of twenty-selected variables to find two main clusters which accurately matched surviving and dead patient clusters. A support-vector-machines with an appropriate sparsity penalty provided the classification of mortality risk with accuracy = 0.7077, AUROC = 0.7375, sensitivity = 0.6436, and specificity = 0.740. Across three ML algorithms, the majority of the identified twenty variables were compatible with literature and with our previous studies on SveDem. We also found new variables which were not previously reported in literature as associated with mortality in dementia. Performance of basic dementia diagnostic work-up, time from referral to initiation of work-up, and time from initiation of work-up to diagnosis were found to be elements of the diagnostic process identified by the ML algorithms. The median follow-up time was 1053 (IQR = 516-1771) days in surviving and 1125 (IQR = 605-1770) days in dead patients. For prediction of time to death, the CoxBoost model identified 15 variables and classified them in order of importance. These highly important variables were age at diagnosis, MMSE score, sex, BMI, and Charlson Comorbidity Index with selection scores of 23%, 15%, 14%, 12% and 10%, respectively. This study demonstrates the potential of sparsity-inducing ML algorithms in improving our understanding of mortality risk factors in dementia patients and their application in clinical settings. Moreover, ML methods can be used as a complement to traditional statistical methods.

Place, publisher, year, edition, pages
Springer Nature, 2023
National Category
Medical and Health Sciences
Identifiers
urn:nbn:se:kth:diva-332204 (URN)10.1038/s41598-023-36362-3 (DOI)001003940000015 ()37301891 (PubMedID)2-s2.0-85163058014 (Scopus ID)
Note

QC 20230721

Available from: 2023-07-21 Created: 2023-07-21 Last updated: 2023-07-21Bibliographically approved
Das, S., Mahabadi, N., Fallon, M. & Chatterjee, S. (2023). M-LIO: Multi-lidar, multi-IMU odometry with sensor dropout tolerance. In: IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings: . Paper presented at 34th IEEE Intelligent Vehicles Symposium, IV 2023, Anchorage, United States of America, Jun 4 2023 - Jun 7 2023. Institute of Electrical and Electronics Engineers (IEEE)
Open this publication in new window or tab >>M-LIO: Multi-lidar, multi-IMU odometry with sensor dropout tolerance
2023 (English)In: IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings, Institute of Electrical and Electronics Engineers (IEEE) , 2023Conference paper, Published paper (Refereed)
Abstract [en]

We present a robust system for state estimation that fuses measurements from multiple lidars and inertial sensors with GNSS data. To initiate the method, we use the prior GNSS pose information. We then perform motion estimation in real-time, which produces robust motion estimates in a global frame by fusing lidar and IMU signals with GNSS translation components using a factor graph framework. We also propose methods to account for signal loss with a novel synchronization and fusion mechanism. To validate our approach extensive tests were carried out on data collected using Scania test vehicles (5 sequences for a total of ≈ 7 Km). From our evaluations, we show an average improvement of 61% in relative translation and 42% rotational error compared to a state-of-the-art estimator fusing a single lidar/inertial sensor pair, in sensor dropout scenarios.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2023
Keywords
Odometry estimation, Sensor fusion, SLAM
National Category
Computer Vision and Robotics (Autonomous Systems) Signal Processing
Identifiers
urn:nbn:se:kth:diva-335040 (URN)10.1109/IV55152.2023.10186548 (DOI)001042247300023 ()2-s2.0-85168001725 (Scopus ID)
Conference
34th IEEE Intelligent Vehicles Symposium, IV 2023, Anchorage, United States of America, Jun 4 2023 - Jun 7 2023
Note

Part of ISBN 9798350346916

QC 20230831

Available from: 2023-08-31 Created: 2023-08-31 Last updated: 2024-02-13Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-2638-6047

Search in DiVA

Show all publications