Susanto Rahardja

Susanto Rahardja

orcid

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 March 2019 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
MWMou Wang
Mou Wang
MZMin Zhao
Min Zhao
JCJie Chen
Jie Chen
SRSusanto Rahardja
Susanto Rahardja
Nonlinear spectral unmixing is an important and challenging problem in hyperspectral image processing. Classical nonlinear algorithms are usually derived based on specific assumptions on the nonlinearity. In recent years, deep learning shows its advantage in addressing general nonlinear problems. However, existing ways of using deep neural networks for unmixing are limited and restrictive. In this letter, we develop a novel blind hyperspectral unmixing scheme based on a deep autoencoder network. Both encoder and decoder of the network are carefully designed so that we can conveniently extract estimated endmembers and abundances simultaneously from the nonlinearly mixed data. Because an autoencoder is essentially an unsupervised algorithm, this scheme only relies on the current data and, therefore, does not require additional training. Experimental results validate the proposed scheme and show its superior performance over several existing algorithms.

22 December 2017 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
YSYingxiang Sun
Yingxiang Sun
JCJiajia Chen
Jiajia Chen
Chau YuenChau Yuen
Chau Yuen
SRSusanto Rahardja
Susanto Rahardja
It is known that adverse environments such as high reverberation and low signal-to-noise ratio (SNR) pose a great challenge to indoor sound source localization (SSL). To address this challenge, in this paper, we propose an SSL algorithm based on a probabilistic neural network, namely a generalized cross-correlation classification algorithm (GCA). Experimental results for adverse environments with high reverberation time T 60 up to 600 ms and low SNR such as -10 dB show that the average azimuth angle error and elevation angle error by GCA are only 4.6° and 3.1°, respectively. Compared with three recently published algorithms, GCA has increased the success rate on direction of arrival estimation significantly with good robustness to environmental changes. These results show that the proposed GCA can localize accurately and robustly for diverse indoor applications where the site acoustic features can be studied prior to the localization stage.

14 October 2020 in IEEE Transactions on Affective Computing
Verified
Journal Article
Open access
JYJiawei Yang
Jiawei Yang
GCGulraiz Iqbal Choudhary
Gulraiz Iqbal Choudhary
SRSusanto Rahardja
Susanto Rahardja
Pasi FräntiPasi Fränti
Pasi Fränti
Classification of interbeat interval time-series which fluctuates in an irregular and complex manner is very challenging. Typically, entropy methods are employed to quantify the complexity of the time-series for classifying. Traditional entropy methods focus on the frequency distribution of all the observations in a time-series. This requires a relatively long time-series with at least a couple of thousands of data points, which limits their usages in practical applications. The methods are also sensitive to the parameter settings. In this paper, we propose a conceptually new approach called attention entropy, which pays attention only to the key observations. Instead of counting the frequency of all observations, it analyzes the frequency distribution of the intervals between the key observations in a time-series. The advantages of the attention entropy are that it does not need any parameter to tune, is robust to the time-series length, and requires only linear time to compute. Experiments show that it outperforms fourteen state-of-the-art entropy methods evaluated by real-world datasets. It achieves average classification accuracy of AUC=0.71 while the second-best method, multiscale entropy, achieves AUC=0.62 when classifying four groups of people with a time-series length of 100.

27 February 2023 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
JCJie Chen
Jie Chen
MZMin Zhao
Min Zhao
XWXiuheng Wang
Xiuheng Wang
CRCédric Richard
Cédric Richard
SRSusanto Rahardja
Susanto Rahardja
Spectral unmixing is central when analyzing hyperspectral data. To accomplish this task, physics-based methods have become popular because, with their explicit mixing models, they can provide a clear interpretation. Nevertheless, because of their limited modeling capabilities, especially when analyzing real scenes with unknown complex physical properties, these methods may not be accurate. On the other hand, data-driven methods using deep learning in particular have developed rapidly in recent years, thanks to their superior capability in modeling complex nonlinear systems. Simply transferring these methods as black boxes to perform unmixing may lead to low interpretability and poor generalization ability. To bring together the best of two worlds, recent research efforts have focused on combining the advantages of both physics-based models and data-driven methods. In this article, we present an overview of recent advances on this topic from various perspectives, including deep neural network (DNN) design, prior capturing, and loss selection. We summarize these methods within a common optimization framework and discuss ways of enhancing our understanding of these methods. The related source codes are made publicly available at http://github.com/xiuheng-wang/awesome-hyperspectral-image-unmixing .

2 August 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
MZMin Zhao
Min Zhao
MWMou Wang
Mou Wang
JCJie Chen
Jie Chen
SRSusanto Rahardja
Susanto Rahardja
Spectral unmixing is an important task in hyperspectral image processing for separating the mixed spectral data pertaining to various materials observed aiming at analyzing the material components in observed pixels. Recently, nonlinear spectral unmixing has received particular attention in hyperspectral image processing, as there are many situations in which the linear mixture model may not be appropriate and could be advantageously replaced by a nonlinear one. Existing nonlinear unmixing approaches are often based on specific assumptions on the nonlinearity and can be less effective when used for scenes with unknown nonlinearity. This article presents an unsupervised nonlinear spectral unmixing method that addresses a general model that consists of a linear mixture part and an additive nonlinear mixture part. The structure of a deep autoencoder network, which has a clear physical interpretation, is specifically designed to achieve this purpose. Moreover, a convolutional neural network (CNN) is used to capture the spectral-spatial priors from hyperspectral data. Extensive experiments with synthetic and real data illustrate the generality and effectiveness of this scheme compared with state-of-the-art methods.

6 October 2017 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
IKIshtiaq Rasool Khan
Ishtiaq Rasool Khan
SRSusanto Rahardja
Susanto Rahardja
MKMuhammad Murtaza Khan
Muhammad Murtaza Khan
MMMuhammad Mobeen Movania
Muhammad Mobeen Movania
FAFidaa Abed
Fidaa Abed
High-dynamic-range (HDR) images require tone mapping to be displayed properly on lower dynamic range devices. In this paper, a tone-mapping algorithm that uses histogram of luminance to construct a lookup table (LUT) for tone mapping is presented. Characteristics of the human visual system (HVS) are used to give more importance to visually distinguishable intensities while constructing the histogram bins. The method begins with constructing a histogram of the luminance channel, using bins that are perceived to be uniformly spaced by the HVS. Next, a refinement step is used, which removes the pixels from the bins that are indistinguishable by the HVS. Finally, the available display levels are distributed among the bins proportionate to the pixels counts thus giving due consideration to the visual contribution of each bin in the image. Quality assessment using both quantitative evaluations and user studies suggests that the presented algorithm produces tone-mapped images that are visually pleasant and preserve details of the original image better than the existing methods. Finally, implementation details of the algorithm on GPU for parallel processing are presented, which could achieve a significant gain in speed over CPU-based implementation.