Lahiru D. Chamain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lahiru D. Chamain has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chintha Tellambura
University of Alberta
1 shared publication - Prathapasinghe Dharmawansa
University of Oulu
1 shared publication - Saman Atapattu
Department of Electrical and Electronic Engineering, School of Engineering, RMIT University, Melbourne, VIC, Australia
1 shared publication - Siyu Qi
Department of Electrical and Computer Engineering, University of California, Davis, CA 95616, USA
1 shared publication - Zhi Ding
University of California at Davis
1 shared publication
Latest Publications
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (21) , 21916-21931
End-to-End Image Classification and Compression With Variational Autoencoders
The past decade has witnessed the rising dominance of deep learning and artificial intelligence in a wide range of applications. In particular, the ocean of wireless smartphones and IoT devices continue to fuel the tremendous growth of edge/cloud-based machine learning (ML) systems, including image/speech recognition and classification. To overcome the infrastructural barrier of limited network bandwidth in cloud ML, existing solutions have mainly relied on traditional compression codecs such as JPEG that were historically engineered for human-end users instead of ML algorithms. Traditional codecs do not necessarily preserve features important to ML algorithms under limited bandwidth, leading to potentially inferior performance. This work investigates application-driven optimization of programmable commercial codec settings for networked learning tasks such as image classification. Based on the foundation of variational autoencoders (VAEs), we develop an end-to-end networked learning framework by jointly optimizing the codec and classifier without reconstructing images for a given data rate (bandwidth). Compared with the standard JPEG codec, the proposed VAE joint compression and classification framework achieves classification accuracy improvement by over 10% and 4%, respectively, for CIFAR-10 and ImageNet-1k data sets at data rate of 0.8 bpp. Our proposed VAE-based models show 65%–99% reductions in encoder size, $\times 1.5$ – $\times 13.1$ improvements in inference speed, and 25%–99% savings in power compared to baseline models. We further show that a simple decoder can reconstruct images with sufficient quality without compromising classification accuracy.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 9 (21) , 21916-21931
End-to-End Image Classification and Compression With Variational Autoencoders
The past decade has witnessed the rising dominance of deep learning and artificial intelligence in a wide range of applications. In particular, the ocean of wireless smartphones and IoT devices continue to fuel the tremendous growth of edge/cloud-based machine learning (ML) systems, including image/speech recognition and classification. To overcome the infrastructural barrier of limited network bandwidth in cloud ML, existing solutions have mainly relied on traditional compression codecs such as JPEG that were historically engineered for human-end users instead of ML algorithms. Traditional codecs do not necessarily preserve features important to ML algorithms under limited bandwidth, leading to potentially inferior performance. This work investigates application-driven optimization of programmable commercial codec settings for networked learning tasks such as image classification. Based on the foundation of variational autoencoders (VAEs), we develop an end-to-end networked learning framework by jointly optimizing the codec and classifier without reconstructing images for a given data rate (bandwidth). Compared with the standard JPEG codec, the proposed VAE joint compression and classification framework achieves classification accuracy improvement by over 10% and 4%, respectively, for CIFAR-10 and ImageNet-1k data sets at data rate of 0.8 bpp. Our proposed VAE-based models show 65%–99% reductions in encoder size, $\times 1.5$ – $\times 13.1$ improvements in inference speed, and 25%–99% savings in power compared to baseline models. We further show that a simple decoder can reconstruct images with sufficient quality without compromising classification accuracy.
- 28 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 66 (10) , 6413-6433
Eigenvalue-Based Detection of a Signal in Colored Noise: Finite and Asymptotic Analyses
Signal detection in colored noise with an unknown covariance matrix has a myriad of applications in diverse scientific/engineering fields. The test statistic is the largest generalized eigenvalue (l.g.e.) of the whitened sample covariance matrix, which is constructed via m-dimensional p signal-plusnoise samples and m-dimensional n noise-only samples. A finite dimensional characterization of this statistic under the alternative hypothesis has hitherto been an open problem. We answer this problem by deriving cumulative distribution function (c.d.f.) of this l.g.e. via the powerful orthogonal polynomial approach, exploiting the deformed Jacobi unitary ensemble (JUE). Two special cases and an asymptotic version of the c.d.f. are also derived. With this new c.d.f., we comprehensively analyze the receiver operating characteristics (ROC) of the detector. Importantly, when the noise-only covariance matrix is nearly rank deficient (i.e., m = n), we show that (a) when m and p increase such that m=p is fixed, at each fixed signal-to-noise ratio (SNR), there exists an optimal ROC profile. We also establish a tight approximation of it; and (b) asymptotically, reliable signal detection is always possible if SNR scales with m.
- 28 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 66 (10) , 6413-6433
Eigenvalue-Based Detection of a Signal in Colored Noise: Finite and Asymptotic Analyses
Signal detection in colored noise with an unknown covariance matrix has a myriad of applications in diverse scientific/engineering fields. The test statistic is the largest generalized eigenvalue (l.g.e.) of the whitened sample covariance matrix, which is constructed via m-dimensional p signal-plusnoise samples and m-dimensional n noise-only samples. A finite dimensional characterization of this statistic under the alternative hypothesis has hitherto been an open problem. We answer this problem by deriving cumulative distribution function (c.d.f.) of this l.g.e. via the powerful orthogonal polynomial approach, exploiting the deformed Jacobi unitary ensemble (JUE). Two special cases and an asymptotic version of the c.d.f. are also derived. With this new c.d.f., we comprehensively analyze the receiver operating characteristics (ROC) of the detector. Importantly, when the noise-only covariance matrix is nearly rank deficient (i.e., m = n), we show that (a) when m and p increase such that m=p is fixed, at each fixed signal-to-noise ratio (SNR), there exists an optimal ROC profile. We also establish a tight approximation of it; and (b) asymptotically, reliable signal detection is always possible if SNR scales with m.