kth.sePublications
Change search
Refine search result
1234 1 - 50 of 154
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1. Ambat, S. K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Adaptive selection of search space in look ahead orthogonal matching pursuit2012In: 2012 National Conference on Communications, NCC 2012, 2012, p. 6176852-Conference paper (Refereed)
    Abstract [en]

    Compressive Sensing theory combines the signal sampling and compression for sparse signals resulting in reduction in sampling rate and computational complexity of the measurement system. In recent years, many recovery algorithms were proposed to reconstruct the signal efficiently. Look Ahead OMP (LAOMP) is a recently proposed method which uses a look ahead strategy and performs significantly better than other greedy methods. In this paper, we propose a modification to the LAOMP algorithm to choose the look ahead parameter L adaptively, thus reducing the complexity of the algorithm, without compromising on the performance. The performance of the algorithm is evaluated through Monte Carlo simulations.

  • 2. Ambat, S. K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Fusion of algorithms for Compressed Sensing2013In: ICASSP IEEE Int Conf Acoust Speech Signal Process Proc, 2013, p. 5860-5864Conference paper (Refereed)
    Abstract [en]

    Numerous algorithms have been proposed recently for sparse signal recovery in Compressed Sensing (CS). In practice, the number of measurements can be very limited due to the nature of the problem and/or the underlying statistical distribution of the non-zero elements of the sparse signal may not be known a priori. It has been observed that the performance of any sparse signal recovery algorithm depends on these factors, which makes the selection of a suitable sparse recovery algorithm difficult. To take advantage in such situations, we propose to use a fusion framework using which we employ multiple sparse signal recovery algorithms and fuse their estimates to get a better estimate. Theoretical results justifying the performance improvement are shown. The efficacy of the proposed scheme is demonstrated by Monte Carlo simulations using synthetic sparse signals and ECG signals selected from MIT-BIH database.

  • 3. Ambat, S. K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    On selection of search space dimension in compressive sampling matching pursuit2012In: TENCON 2012 - 2012 IEEE Region 10 Conference, IEEE , 2012, p. 6412345-Conference paper (Refereed)
    Abstract [en]

    Compressive Sampling Matching Pursuit (CoSaMP) is one of the popular greedy methods in the emerging field of Compressed Sensing (CS). In addition to the appealing empirical performance, CoSaMP has also splendid theoretical guarantees for convergence. In this paper, we propose a modification in CoSaMP to adaptively choose the dimension of search space in each iteration, using a threshold based approach. Using Monte Carlo simulations, we show that this modification improves the reconstruction capability of the CoSaMP algorithm in clean as well as noisy measurement cases. From empirical observations, we also propose an optimum value for the threshold to use in applications.

  • 4. Ambat, S. K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Subspace pursuit embedded in orthogonal matching pursuit2012In: TENCON 2012 - 2012 IEEE Region 10 Conference, IEEE , 2012, p. 6412325-Conference paper (Refereed)
    Abstract [en]

    Orthogonal Matching Pursuit (OMP) is a popular greedy pursuit algorithm widely used for sparse signal recovery from an undersampled measurement system. However, one of the main shortcomings of OMP is its irreversible selection procedure of columns of measurement matrix. i.e., OMP does not allow removal of the columns wrongly estimated in any of the previous iterations. In this paper, we propose a modification in OMP, using the well known Subspace Pursuit (SP), to refine the subspace estimated by OMP at any iteration and hence boost the sparse signal recovery performance of OMP. Using simulations we show that the proposed scheme improves the performance of OMP in clean and noisy measurement cases.

  • 5. Ambat, Sooraj K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    A Committee Machine Approach for Compressed Sensing Signal Reconstruction2014In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 62, no 7, p. 1705-1717Article in journal (Refereed)
    Abstract [en]

    Although many sparse recovery algorithms have been proposed recently in compressed sensing (CS), it is well known that the performance of any sparse recovery algorithm depends on many parameters like dimension of the sparse signal, level of sparsity, and measurement noise power. It has been observed that a satisfactory performance of the sparse recovery algorithms requires a minimum number of measurements. This minimum number is different for different algorithms. In many applications, the number of measurements is unlikely to meet this requirement and any scheme to improve performance with fewer measurements is of significant interest in CS. Empirically, it has also been observed that the performance of the sparse recovery algorithms also depends on the underlying statistical distribution of the nonzero elements of the signal, which may not be known a priori in practice. Interestingly, it can be observed that the performance degradation of the sparse recovery algorithms in these cases does not always imply a complete failure. In this paper, we study this scenario and show that by fusing the estimates of multiple sparse recovery algorithms, which work with different principles, we can improve the sparse signal recovery. We present the theoretical analysis to derive sufficient conditions for performance improvement of the proposed schemes. We demonstrate the advantage of the proposed methods through numerical simulations for both synthetic and real signals.

  • 6. Ambat, Sooraj K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Fusion of Algorithms for Compressed Sensing2013In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 61, no 14, p. 3699-3704Article in journal (Refereed)
    Abstract [en]

    For compressed sensing (CS), we develop a new scheme inspired by data fusion principles. In the proposed fusion based scheme, several CS reconstruction algorithms participate and they are executed in parallel, independently. The final estimate of the underlying sparse signal is derived by fusing the estimates obtained from the participating algorithms. We theoretically analyze this fusion based scheme and derive sufficient conditions for achieving a better reconstruction performance than any participating algorithm. Through simulations, we show that the proposed scheme has two specific advantages: 1) it provides good performance in a low dimensional measurement regime, and 2) it can deal with different statistical natures of the underlying sparse signals. The experimental results on real ECG signals shows that the proposed scheme demands fewer CS measurements for an approximate sparse signal reconstruction.

  • 7. Ambat, Sooraj K.
    et al.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Progressive fusion of reconstruction algorithms for low latency applications in compressed sensing2014In: Signal Processing, ISSN 0165-1684, E-ISSN 1872-7557, Vol. 97, p. 146-151Article in journal (Refereed)
    Abstract [en]

    Recently, it has been shown that fusion of the estimates of a set of sparse recovery algorithms result in an estimate better than the best estimate in the set, especially when the number of measurements is very limited. Though these schemes provide better sparse signal recovery performance, the higher computational requirement makes it less attractive for low latency applications. To alleviate this drawback, in this paper, we develop a progressive fusion based scheme for low latency applications in compressed sensing. In progressive fusion, the estimates of the participating algorithms are fused progressively according to the availability of estimates. The availability of estimates depends on computational complexity of the participating algorithms, in turn on their latency requirement. Unlike the other fusion algorithms, the proposed progressive fusion algorithm provides quick interim results and successive refinements during the fusion process, which is highly desirable in low latency applications. We analyse the developed scheme by providing sufficient conditions for improvement of CS reconstruction quality and show the practical efficacy by numerical experiments using synthetic and real-world data.

  • 8.
    Ambat, Sooraj K.
    et al.
    IISc - Indian Institute of Science.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Hari, K.V.S.
    IISc - Indian Institute of Science.
    Fusion of greedy pursuits for compressed sensing signal reconstruction2012In: 2012 Proceedings Of The 20th European Signal Processing Conference (EUSIPCO), IEEE Computer Society, 2012, p. 1434-1438Conference paper (Refereed)
    Abstract [en]

    Greedy Pursuits are very popular in Compressed Sensing for sparse signal recovery. Though many of the Greedy Pursuits possess elegant theoretical guarantees for performance, it is well known that their performance depends on the statistical distribution of the non-zero elements in the sparse signal. Inpractice, the distribution of the sparse signal may not be knowna priori. It is also observed that performance of Greedy Pursuits degrades as the number of available measurements decreases from a threshold value which is method dependent. To improve the performance in these situations, we introduce a novel fusion framework for Greedy Pursuits and also propose two algorithms for sparse recovery. Through Monte Carlo simulations we show that the proposed schemes improve sparse signal recovery in clean as well as noisy measurement cases.

    Download full text (pdf)
    fulltext
  • 9.
    Amini, Mehdi
    et al.
    the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
    Mostafaei, Shayan
    the Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institute, Stockholm, Sweden.
    Poursamimi, Mohamad
    the Department of Medical Physics, School of Medicine, Semnan University of Medical Sciences, Semnan, Iran.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Mansouri, Zahra
    the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
    Ghorbani, Mehdi
    the Department of Biomedical Engineering and Medical Physics, Shahid Beheshti University of medical sciences, Tehran, Iran.
    Shiri, Isaac
    the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.
    Zaidi, Habib
    the Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, Switzerland; Geneva University Neurocenter, Geneva University, CH-1205 Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, Department of Nuclear Medicine and Molecular Imaging, University of Groningen; University Medical Center Groningen, 9700 RB Groningen, Netherlands; Department of Nuclear Medicine, University of Southern Denmark, DK-500, Odense, Denmark..
    Interpretable PET/CT Radiomic Based Prognosis Modeling of NSCLC Recurrent Following Complete Resection2022In: 2022 IEEE NSS/MIC RTSD - IEEE Nuclear Science Symposium, Medical Imaging Conference and Room Temperature Semiconductor Detector Conference, Institute of Electrical and Electronics Engineers (IEEE) , 2022Conference paper (Refereed)
    Abstract [en]

    This study aimed to develop an interpretable prognostic model with a nomogram for Non-Small Cell Lung Cancer (NSCLC) recurrence prediction following complete resection, using multi-modality PET/CT fusion radiomics and patients' clinical features. Retrospectively, 181 NSCLC patients who had undergone18F-FDG PET/CT scan were enrolled and split into training (2/3) and testing (1/3) partitions. Before image fusion, PET and CT images were registered, resized to equal isotropic voxel size, and clipped and normalized. Guided Filtering Fusion GFF algorithm was used for image fusion. Two hundred eighteen radiomic features were extracted from each PET, CT, and fused image, including morphological, first-order statistical, and texture features. Clinical features included age, sex, smoking status, weight, radiation, chemotherapy, pathological stage, etc. Feature selection and univariate and multivariate modeling were performed using the CoxBoost algorithm. Harrell's Concordance index (C-index) was used to evaluate the performance of the models, and compare C test was used to statistically compare the performance of the models (p-values < 0.05 were considered significant). Clinical, Clinical+PET, Clinical+CT, and Clinical+GFF resulted in c-indices (confidence interval) of 0.701 (0.589-0.812), 0.757 (0.647-0.867), 0.706 (0.607, 0.807), and 0.824 (0.751-0.896), respectively. Statistical comparison of the performance of different models with the Clinical model revealed that while PET and GFF features can significantly increase the performance (p-values 0.009 and 0.001, respectively), CT features did not significantly improve the performance of the Clinical model (p-value 0.279). Therefore, the nomogram was developed based on the Clinical+GFF model (with the best performance). Radiomic features extracted from PET and PET/CT fusion images can improve the recurrence prognosis in NSCLC patients compared to the conventional clinical factors alone.

  • 10.
    Arian, Fatemeh
    et al.
    Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
    Amini, Mehdi
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva 4, CH-1211, Switzerland.
    Mostafaei, Shayan
    Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Stockholm, Sweden.
    Rezaei Kalantari, Kiara
    Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran; Cardio-Oncology Research Center, Rajaei Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
    Haddadi Avval, Atlas
    School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran.
    Shahbazi, Zahra
    Department of Biostatistics, School of Health, Kermanshah University of Medical Sciences, Kermanshah, Iran.
    Kasani, Kianosh
    Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran.
    Bitarafan Rajabi, Ahmad
    Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran; Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran; Echocardiography Research Center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran; Cardiovascular interventional research center, Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Sciences, Tehran, Iran.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Oveisi, Mehrdad
    Comprehensive Cancer Centre, School of Cancer & Pharmaceutical Sciences, Faculty of Life Sciences & Medicine, Kings College London, London, UK; Department of Computer Science, University of British Columbia, Vancouver BC, Canada.
    Shiri, Isaac
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva 4, CH-1211, Switzerland.
    Zaidi, Habib
    Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva 4, CH-1211, Switzerland; Geneva University Neurocenter, Geneva University, Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands; Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.
    Myocardial Function Prediction After Coronary Artery Bypass Grafting Using MRI Radiomic Features and Machine Learning Algorithms2022In: Journal of digital imaging, ISSN 0897-1889, E-ISSN 1618-727X, Vol. 35, no 6, p. 1708-1718Article in journal (Refereed)
    Abstract [en]

    The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images in patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 patients who had visible scars on short-axis LGE-CMR images and were candidates for CABG surgery were selected and enrolled in this study. MR imaging was performed preoperatively using a 1.5-T MRI scanner. All images were segmented by two expert radiologists (in consensus). Prior to extraction of radiomics features, all MR images were resampled to an isotropic voxel size of 1.8 × 1.8 × 1.8 mm3. Subsequently, intensities were quantized to 64 discretized gray levels and a total of 93 features were extracted. The applied algorithms included a smoothly clipped absolute deviation (SCAD)–penalized support vector machine (SVM) and the recursive partitioning (RP) algorithm as a robust classifier for binary classification in this high-dimensional and non-sparse data. All models were validated with repeated fivefold cross-validation and 10,000 bootstrapping resamples. Ten and seven features were selected with SCAD-penalized SVM and RP algorithm, respectively, for CABG responder/non-responder classification. Considering univariate analysis, the GLSZM gray-level non-uniformity-normalized feature achieved the best performance (AUC: 0.62, 95% CI: 0.53–0.76) with SCAD-penalized SVM. Regarding multivariable modeling, SCAD-penalized SVM obtained an AUC of 0.784 (95% CI: 0.64–0.92), whereas the RP algorithm achieved an AUC of 0.654 (95% CI: 0.50–0.82). In conclusion, different radiomics texture features alone or combined in multivariate analysis using machine learning algorithms provide prognostic information regarding myocardial function in patients after CABG.

  • 11.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Flåm, John T.
    NTNU - Norwegian University of Science and Technology.
    Kansanen, Kimmo
    NTNU - Norwegian University of Science and Technology.
    Ekman, Tobjorn
    NTNU - Norwegian University of Science and Technology.
    On MMSE estimation: A linear model under Gaussian mixture statistics2012In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 60, no 7, p. 3840-3845Article in journal (Refereed)
    Abstract [en]

    In a Bayesian linear model, suppose observation y = Hx + n stems from independent inputs x and n which are Gaussian mixture (GM) distributed. With known matrix H, the minimum mean square error (MMSE) estimator for x , has analytical form. However, its performance measure, the MMSE itself, has no such closed form. Because existing Bayesian MMSE bounds prove to have limited practical value under these settings, we instead seek analytical bounds for the MMSE, both upper and lower. This paper provides such bounds, and relates them to the signal-to-noise-ratio (SNR).

    Download full text (pdf)
    fulltext
  • 12.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hari, K. V. S.
    Händel, Peter
    KTH, School of Electrical Engineering (EES), Signal Processing.
    Skoglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Projection-based atom selection in orthogonal matching pursuit for compressive sensing2012In: 2012 National Conference on Communications, NCC 2012, IEEE , 2012, p. 6176797-Conference paper (Refereed)
    Abstract [en]

    For compressive sensing, we endeavor to improve the atom selection strategy of the existing orthogonal matching pursuit (OMP) algorithm. To achieve a better estimate of the underlying support set progressively through iterations, we use a least squares solution based atom selection method. From a set of promising atoms, the choice of an atom is performed through a new method that uses orthogonal projection along-with a standard matched filter. Through experimental evaluations, the effect of projection based atom selection strategy is shown to provide a significant improvement for the support set recovery performance, in turn, the compressive sensing recovery.

  • 13.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Kleijn, W. Bastiaan
    KTH, School of Electrical Engineering (EES), Sound and Image Processing.
    AUDITORY MODEL BASED MODIFIED MFCC FEATURES2010In: 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, p. 4590-4593Conference paper (Refereed)
    Abstract [en]

    Using spectral and spectro-temporal auditory models, we develop a computationally simple feature vector based on the design architecture of existing mel frequency cepstral coefficients (MFCCs). Along with the use of an optimized static function to compress a set of filter bank energies, we propose to use a memory-based adaptive compression function to incorporate the behavior of human auditory response across time and frequency. We show that a significant improvement in automatic speech recognition (ASR) performance is obtained for any environmental condition, clean as well as noisy.

  • 14.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Kleijn, W. Bastiaan
    KTH, School of Electrical Engineering (EES), Sound and Image Processing.
    Auditory Model-Based Design and Optimization of Feature Vectors for Automatic Speech Recognition2011In: IEEE Transactions on Audio, Speech, and Language Processing, ISSN 1558-7916, E-ISSN 1558-7924, Vol. 19, no 6, p. 1813-1825Article in journal (Refereed)
    Abstract [en]

    Using spectral and spectro-temporal auditory models along with perturbation-based analysis, we develop a new framework to optimize a feature vector such that it emulates the behavior of the human auditory system. The optimization is carried out in an offline manner based on the conjecture that the local geometries of the feature vector domain and the perceptual auditory domain should be similar. Using this principle along with a static spectral auditory model, we modify and optimize the static spectral mel frequency cepstral coefficients (MFCCs) without considering any feedback from the speech recognition system. We then extend the work to include spectro-temporal auditory properties into designing a new dynamic spectro-temporal feature vector. Using a spectro-temporal auditory model, we design and optimize the dynamic feature vector to incorporate the behavior of human auditory response across time and frequency. We show that a significant improvement in automatic speech recognition (ASR) performance is obtained for any environmental condition, clean as well as noisy.

  • 15.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Sound and Image Processing.
    Koniaris, Christos
    KTH, School of Electrical Engineering (EES), Sound and Image Processing.
    Kleijn, W. Baastian
    KTH, School of Electrical Engineering (EES), Sound and Image Processing.
    Auditory model based optimization of MFCCs improves automatic speech recognition performance2009In: INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, 2009, p. 2943-2946Conference paper (Refereed)
    Abstract [en]

    Using a spectral auditory model along with perturbation based analysis, we develop a new framework to optimize a set of features such that it emulates the behavior of the human auditory system. The optimization is carried out in an off-line manner based on the conjecture that the local geometries of the feature domain and the perceptual auditory domain should be similar. Using this principle, we modify and optimize the static mel frequency cepstral coefficients (MFCCs) without considering any feedback from the speech recognition system. We show that improved recognition performance is obtained for any environmental condition, clean as well as noisy.

  • 16.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Koslicki, David
    Dept of Mathematics, Oregon State University, Corvallis, USA.
    Dong, Siyuan
    KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.
    Innocenti, Nicolas
    KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.
    Cheng, Lu
    Dept of Mathematics and Statistics, University of Helsinki, Finland.
    Lan, Yueheng
    Dept of Physics, Tsinghua University, Beijing, China.
    Vehkaperä, Mikko
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Skoglund, Mikael
    KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre. KTH, School of Electrical Engineering (EES), Communication Theory.
    K. Rasmussen, Lars
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Aurell, Erik
    KTH, School of Computer Science and Communication (CSC), Computational Biology, CB.
    Corander, Jukka
    Dept of Signal Processing, Aalto University, Finland.
    SEK: Sparsity exploiting k-mer-based estimation of bacterial community composition2014In: Bioinformatics, ISSN 1460-2059, Vol. 30, no 17, p. 2423-2431Article in journal (Refereed)
    Abstract [en]

    Motivation: Estimation of bacterial community composition from a high-throughput sequenced sample is an important task in metagenomics applications. As the sample sequence data typically harbors reads of variable lengths and different levels of biological and technical noise, accurate statistical analysis of such data is challenging. Currently popular estimation methods are typically time-consuming in a desktop computing environment.

    Results: Using sparsity enforcing methods from the general sparse signal processing field (such as compressed sensing), we derive a solution to the community composition estimation problem by a simultaneous assignment of all sample reads to a pre-processed reference database. A general statistical model based on kernel density estimation techniques is introduced for the assignment task, and the model solution is obtained using convex optimization tools. Further, we design a greedy algorithm solution for a fast solution. Our approach offers a reasonably fast community composition estimation method, which is shown to be more robust to input data variation than a recently introduced related method.

    Availability and implementation: A platform-independent Matlab implementation of the method is freely available at http://www.ee.kth.se/ctsoftware; source code that does not require access to Matlab is currently being tested and will be made available later through the above Web site.

    Download full text (pdf)
    SEK paper
    Download (zip)
    SEK Code
  • 17.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Skoglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Structured Gaussian Mixture model based product VQ2010In: 18th European Signal Processing Conference (EUSIPCO-2010), EUROPEAN ASSOC SIGNAL SPEECH & IMAGE PROCESSING-EURASIP , 2010, p. 771-775Conference paper (Refereed)
    Abstract [en]

    In this paper, the Gaussian mixture model (GMM) based parametric framework is used to design a product vector quantization (PVQ) method that provides rate-distortion (R/D) performance optimality and bitrate scalability. We use a GMM consisting of a large number of Gaussian mixtures and invoke a block isotropic structure on the covariance matrices of the Gaussian mixtures. Using such a structured GMM, we design an optimum and bitrate scalable PVQ, namely an split (SVQ), for each Gaussian mixture. The use of an SVQ allows for a trade-off between complexity and R/D performance that spans the two extreme limits provided by an optimum scalar quantizer and an unconstrained vector quantizer. The efficacy of the new GMM based PVQ (GMPVQ) method is demonstrated for the application of speech spectrum quantization.

  • 18.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    A mixed-split scheme for 2D-DPCM based LSF quantization2005In: TENCON 2005 - 2005 IEEE REGION 10 CONFERENCE, VOLS 1-5, 2005, p. 864-869Conference paper (Refereed)
  • 19.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Analysis of conditional PDF based split VQ2007In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 14, no 11, p. 781-784Article in journal (Refereed)
  • 20.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Analysis-by-synthesis based switched transform domain split VQ using Gaussian mixture model2009In: 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, p. 4117-4120Conference paper (Refereed)
  • 21.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Comparison of prediction based LSF quantization methods using split VQ2006In: INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, p. 237-240Conference paper (Refereed)
  • 22.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Computationally efficient optimum weighting function for vector quantization of LSF parameters2007In: 2007 9TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOLS 1-3  Pages: 732-735, 2007Conference paper (Refereed)
  • 23.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Conditional PDF-based split vector quantization of wideband LSF parameters2007In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 14, no 9, p. 641-644Article in journal (Refereed)
  • 24.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Gaussian mixture model based switched split vector quantization of LSF parameters2007In: 2007 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, VOLS 1-3, 2007, p. 704-709Conference paper (Refereed)
  • 25.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Joint inter-frame and intra-frame predictive coding of LSF parameters2007In: 2007 9TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOLS 1-3, 2007Conference paper (Refereed)
    Abstract [en]

    We explore the performance of two dimensional (2-D) prediction based LSF quantization method for both wide-band and telephone-band (narrow-band) speech. The 2-D prediction based method exploits both the inter-frame and intra-frame correlations of LSF parameters. We show that a 4th order 2-D predictor provides optimum prediction gain as well as improved quantization performance at various choices of frame shift for both wide-band and telephone-band speech. Existing one dimensional (1-D) predictive method, exploiting only inter-frame correlation, results in poor performance at larger frame shifts; whereas proposed 2-D predictor provides lower spectral distortion as well as lower number of outliers compared to existing memory-based and memory-less methods.

  • 26.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Low complexity wide-band LSF quantization using GMM of uncorrelated Gaussian Mixtures2008Conference paper (Refereed)
  • 27.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Normalized two stage SVQ for minimum complexity wide-band LSF quantization2007In: INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, p. 261-264Conference paper (Refereed)
  • 28.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Optimum switched split vector quantization of LSF parameters2008In: Signal Processing, ISSN 0165-1684, E-ISSN 1872-7557, Vol. 88, no 6, p. 1528-1538Article in journal (Refereed)
  • 29.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Optimum transform domain split VQ2008In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 15, p. 285-288Article in journal (Refereed)
  • 30.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Predicting VQ performance bound for LSF coding2008In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 15, p. 166-169Article in journal (Refereed)
  • 31.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Reduced complexity two stage vector quantization2009In: Digital signal processing (Print), ISSN 1051-2004, E-ISSN 1095-4333, Vol. 19, no 3, p. 476-490Article in journal (Refereed)
  • 32.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Sequential split vector quantization of LSF parameters using conditional PDF2007In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol IV, Pts 1-3, 2007, p. 1101-1104Conference paper (Refereed)
  • 33.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Switched conditional PDF-based split VQ using Gaussian mixture model2008In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 15, p. 91-94Article in journal (Refereed)
  • 34.
    Chatterjee, Saikat
    et al.
    Indian Institute of Science.
    Sreenivas, T.V.
    Indian Institute of Science.
    Two stage transform vector quantization of LSFs for wideband speech coding2006In: INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, p. 233-236Conference paper (Refereed)
  • 35.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Sundman, Dennis
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Skoglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Hybrid greedy pursuit2011In: 19th European Signal Processing Conference (EUSIPCO 2011), European Association for Signal and Image Processing, 2011, p. 343-347Conference paper (Refereed)
    Abstract [en]

    For constructing the support set of a sparse vector in the standardcompressive sensing framework, we develop a hybridgreedy pursuit algorithm that combines the advantages ofserial and parallel atom selection strategies. In an iterativeframework, the hybrid algorithm uses a joint sparsity informationextracted from the independent use of serial and parallelgreedy pursuit algorithms. Through experimental evaluations,the hybrid algorithm is shown to provide a significantimprovement for the support set recovery performance.

  • 36.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Sundman, Dennis
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Skoglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Look ahead orthogonal matching pursuit2011In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2011, p. 4024-4027Conference paper (Refereed)
  • 37.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Sundman, Dennis
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Skolglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Robust matching pursuit for recovery of Gaussian sparse signal2011In: 2011 Digital Signal Processing and Signal Processing Education Meeting, DSP/SPE 2011 - Proceedings, 2011, p. 420-424Conference paper (Refereed)
    Abstract [en]

    For compressive sensing (CS) recovery of Gaussian sparse signal, we explore the framework of Bayesian linear models to achieve a robust reconstruction performance in the presence of measurement noise. Using a priori statistical knowledge, we develop a minimum mean square error (MMSE) estimation based iterative greedy search algorithm. Through experimental evaluations, we show that the new algorithm provides a robust CS reconstruction performance compared to an existing least square based algorithm.

  • 38.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Sundman, Dennis
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Skolglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Statistical post-processing improves basis pursuit denoising performance2010In: 2010 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2010, 2010, p. 23-27Conference paper (Refereed)
  • 39.
    Chatterjee, Saikat
    et al.
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Sundman, Dennis
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Vehkaperä, Mikko
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Skolglund, Mikael
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Projection-based and look ahead strategies for atom selection2012In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 60, no 2, p. 634-647Article in journal (Refereed)
    Abstract [en]

    In this paper, we improve iterative greedy search algorithms in which atoms are selected serially over iterations, i.e., one-by-one over iterations. For serial atom selection, we devise two new schemes to select an atom from a set of potential atoms in each iteration. The two new schemes lead to two new algorithms. For both the algorithms, in each iteration, the set of potential atoms is found using a standard matched filter. In case of the first scheme, we propose an orthogonal projection strategy that selects an atom from the set of potential atoms. Then, for the second scheme, we propose a look-ahead strategy such that the selection of an atom in the current iteration has an effect on the future iterations. The use of look-ahead strategy requires a higher computational resource. To achieve a tradeoff between performance and complexity, we use the two new schemes in cascade and develop a third new algorithm. Through experimental evaluations, we compare the proposed algorithms with existing greedy search and convex relaxation algorithms.

    Download full text (pdf)
    fulltext
  • 40.
    Cumlin, Fredrik
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Schüldt, Christian
    Google LLC, Stockholm, Sweden.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering. Digital Futures, Stockholm, Sweden.
    Latent-based Neural Net for Non-intrusive Speech Quality Assessment2023In: 31st European Signal Processing Conference, EUSIPCO 2023 - Proceedings, European Signal Processing Conference, EUSIPCO , 2023, p. 226-230Conference 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.

  • 41.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering. Scania, Sweden.
    Boberg, Bengt
    Scania, Sweden.
    Fallon, Maurice
    ORI, University of Oxford, UK.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    IMU-based Online Multi-lidar Calibration2024Manuscript (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.

    Download full text (pdf)
    fulltext
  • 42.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Javid, Alireza M.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Borpatra Gohain, Prakash
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Eldar, Yonina C.
    Weizmann Inst Sci, Math & Comp Sci, Rehovot, Israel..
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Neural Greedy Pursuit for Feature Selection2022In: 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), Institute of Electrical and Electronics Engineers (IEEE) , 2022Conference paper (Refereed)
    Abstract [en]

    We propose a greedy algorithm to select N important features among P input features for a non-linear prediction problem. The features are selected one by one sequentially, in an iterative loss minimization procedure. We use neural networks as predictors in the algorithm to compute the loss and hence, we refer to our method as neural greedy pursuit (NGP). NGP is efficient in selecting N features when N << P, and it provides a notion of feature importance in a descending order following the sequential selection procedure. We experimentally show that NGP provides better performance than several feature selection methods such as DeepLIFT and Drop-one-out loss. In addition, we experimentally show a phase transition behavior in which perfect selection of all N features without false positives is possible when the training data size exceeds a threshold.

  • 43.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering. Scan CV AB, S-15132 Södertälje, Sweden..
    Klinteberg, Ludvig af
    Scan CV AB, S-15132 Södertälje, Sweden..
    Fallon, Maurice
    Oxford Robot Inst, Oxford OX2 6NN, England..
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Observability-Aware Online Multi-Lidar Extrinsic Calibration2023In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 8, no 5, p. 2860-2867Article in journal (Refereed)
    Abstract [en]

    Accurate and robust extrinsic calibration is necessary for deploying autonomous systems which need multiple sensors for perception. In this letter, we present a robust system for real-time extrinsic calibration of multiple lidars in vehicle base framewithout the need for any fiducialmarkers or features. We base our approach on matching absolute GNSS (Global Navigation Satellite System) and estimated lidar poses in real-time. Comparing rotation components allows us to improve the robustness of the solution than traditional least-square approach comparing translation components only. Additionally, instead of comparing all corresponding poses, we select poses comprising maximum mutual information based on our novel observability criteria. This allows us to identify a subset of the poses helpful for real-time calibration. We also provide stopping criteria for ensuring calibration completion. To validate our approach extensive tests were carried out on data collected using Scania test vehicles (7 sequences for a total of approximate to 6.5 Km). The results presented in this letter show that our approach is able to accurately determine the extrinsic calibration for various combinations of sensor setups.

  • 44.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering. Scania, Sweden.
    Mahabadi, Navid
    Scania, Sweden.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Fallon, Maurice
    Oxford Robotics Institute, UK.
    Multi-modal curb detection and filtering2022Conference paper (Other academic)
    Abstract [en]

    Reliable knowledge of road boundaries is critical for autonomous vehicle navigation. We propose a robust curb detection and filtering technique based on the fusion of camera semantics and dense lidar point clouds. The lidar point clouds are collected by fusing multiple lidars for robust feature detection. The camera semantics are based on a modified EfficientNet architecture which is trained with labeled data collected from onboard fisheye cameras. The point clouds are associated with the closest curb segment with L2-norm analysis after projecting into the image space with the fisheye model projection. Next, the selected points are clustered using unsupervised density-based spatial clustering to detect different curb regions. As new curb points are detected in consecutive frames they are associated with the existing curb clusters using temporal reachability constraints. If no reachability constraints are found a new curb cluster is formed from these new points. This ensures we can detect multiple curbs present in road segments consisting of multiple lanes if they are in the sensors' field of view. Finally, Delaunay filtering is applied for outlier removal and its performance is compared to traditional RANSAC-based filtering. An objective evaluation of the proposed solution is done using a high-definition map containing ground truth curb points obtained from a commercial map supplier. The proposed system has proven capable of detecting curbs of any orientation in complex urban road scenarios comprising straight roads, curved roads, and intersections with traffic isles. 

    Download full text (pdf)
    fulltext
  • 45.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering. Scania CV AB, Södertälje, Sweden..
    Mahabadi, Navid
    Scania CV AB, Södertälje, Sweden..
    Djikic, Addi
    Scania CV AB, Södertälje, Sweden..
    Nassir, Cesar
    Scania CV AB, Södertälje, Sweden..
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Fallon, Maurice
    Oxford Robot Inst, Oxford, England..
    Extrinsic Calibration and Verification of Multiple Non-overlapping Field of View Lidar Sensors2022In: 2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022), Institute of Electrical and Electronics Engineers (IEEE) , 2022Conference paper (Refereed)
    Abstract [en]

    We demonstrate a multi-lidar calibration framework for large mobile platforms that jointly calibrate the extrinsic parameters of non-overlapping Field-of-View (FoV) lidar sensors, without the need for any external calibration aid. The method starts by estimating the pose of each lidar in its corresponding sensor frame in between subsequent timestamps. Since the pose estimates from the lidars are not necessarily synchronous, we first align the poses using a Dual Quaternion (DQ) based Screw Linear Interpolation. Afterward, a HandEye based calibration problem is solved using the DQ-based formulation to recover the extrinsics. Furthermore, we verify the extrinsics by matching chosen lidar semantic features, obtained by projecting the lidar data into the camera perspective after time alignment using vehicle kinematics. Experimental results on the data collected from a Scania vehicle [similar to 1 Km sequence] demonstrate the ability of our approach to obtain better calibration parameters than the provided vehicle CAD model calibration parameters. This setup can also be scaled to any combination of multiple lidars.

  • 46.
    Das, Sandipan
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Mahabadi, Navid
    Stockholm, Sweden.
    Fallon, Maurice
    Oxford Robotics Institute University of Oxford, Oxford, United Kingdom.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    M-LIO: Multi-lidar, multi-IMU odometry with sensor dropout tolerance2023In: IV 2023 - IEEE Intelligent Vehicles Symposium, Proceedings, Institute of Electrical and Electronics Engineers (IEEE) , 2023Conference 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.

  • 47. Flam, J. T.
    et al.
    Zachariah, Dave
    KTH, School of Electrical Engineering (EES), Signal Processing. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Vehkaperä, mikko
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    The linear model under mixed gaussian inputs: Designing the transfer matrix2013In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 61, no 21, p. 5247-5259Article in journal (Refereed)
    Abstract [en]

    Suppose a linear model Y = Hx+n, where inputs x, n are independent Gaussian mixtures. The problem is to design the transfer matrix so as to minimize the mean square error (MSE) when estimating x from . This problem has important applications, but faces at least three hurdles. Firstly, even for a fixed H, the minimum MSE (MMSE) has no analytical form. Secondly, theMMSE is generally not convex in . Thirdly, derivatives of the MMSEw.r.t. are hard to obtain. This paper casts theproblemas a stochastic program and invokes gradient methods. The study is motivated by two applications in signal processing. One concerns the choice of error-reducing precoders; the other deals with selection of pilot matrices for channel estimation. In either setting, our numerical results indicate improved estimation accuracy-markedly better than those obtained by optimal design based on standard linear estimators. Some implications of the non-convexities of the MMSE are noteworthy, yet, to our knowledge, not well known. For example, there are cases in which more pilot power is detrimental for channel estimation. This paper explains why.

  • 48. Flåm, John
    et al.
    Björnson, Emil
    KTH, School of Electrical Engineering (EES), Signal Processing.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Communication Theory.
    Pilot design for MIMO channel estimation: An alternative to the Kronecker structure assumption2013In: ICASSP IEEE Int Conf Acoust Speech Signal Process Proc, IEEE conference proceedings, 2013, p. 5061-5064Conference paper (Refereed)
    Abstract [en]

    This work seeks to design a pilot signal, under a power constraint, such that the channel can be estimated with minimum mean square error. The procedure we derive does not assume Kronecker structure on the underlying covariance matrices, and the pilot signal is obtained in three main steps. Firstly, we solve a relaxed convex version of the original minimization problem. Secondly, its solution is projected onto the feasible set. Thirdly we use the projected solution as starting point for an augmented Lagrangian method. Numerical experiments indicate that this procedure may produce pilot signals that are far better than those obtained under the Kronecker structure assumption.

    Download full text (pdf)
    fulltext
  • 49. Flåm, John
    et al.
    Jaldén, Joakim
    KTH, School of Electrical Engineering (EES), Signal Processing. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering (EES), Signal Processing. KTH, School of Electrical Engineering (EES), Centres, ACCESS Linnaeus Centre.
    Gaussian mixture modeling for source localization2011In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2011, p. 2604-2607Conference paper (Refereed)
    Abstract [en]

    Exploiting prior knowledge, we use Bayesian estimation to localize a source heard by a fixed sensor network. The method has two main aspects: Firstly, the probability density function (PDF) of a function of the source location is approximated by a Gaussian mixture model (GMM). This approximation can theoretically be made arbitrarily accurate, and allows a closed form minimum mean square error (MMSE) estimator for that function. Secondly, the source location is retrieved by minimizing the Euclidean distance between the function and its MMSE estimate using a gradient method. Our method avoids the issues of a numerical MMSE estimator but shows comparable accuracy.

  • 50.
    Fontcuberta, Aleix Espuna
    et al.
    KTH, Centres, Nordic Institute for Theoretical Physics NORDITA. Stockholm Univ, Hannes Alfvens vag 12, SE-10691 Stockholm, Sweden..
    Ghosh, Anubhab
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Chatterjee, Saikat
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Information Science and Engineering.
    Mitra, Dhrubaditya
    KTH, Centres, Nordic Institute for Theoretical Physics NORDITA. Stockholm Univ, Hannes Alfvens vag 12, SE-10691 Stockholm, Sweden..
    Nandy, Dibyendu
    Indian Inst Sci Educ & Res Kolkata, Ctr Excellence Space Sci India, Mohanpur 741246, India.;Indian Inst Sci Educ & Res Kolkata, Dept Phys Sci, Mohanpur 741246, India..
    Forecasting Solar Cycle 25 with Physical Model-Validated Recurrent Neural Networks2023In: Solar Physics, ISSN 0038-0938, E-ISSN 1573-093X, Vol. 298, no 1, article id 8Article in journal (Refereed)
    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.

1234 1 - 50 of 154
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf