Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
10 results
Search Results
Item Noniterative content-adaptive distributed encoding through ML techniques(Society of Motion Picture and Television Engineers, 2018) Sethuraman, S.; Nithya, V.S.; Venkata Narayanababu Laveti, D.Distributed encoding is desirable for content preparation cloud workflows to reduce turnaround times. Content-adaptive bit allocation strategies have been proposed to achieve efficiencies in storage and delivery. Many of these methods tend to be iterative in nature and consume significant additional compute resources. There is a need to limit this increase in computational complexity. In this paper, we propose a noniterative codec-agnostic approach that employs machine learning techniques to achieve average bitrate savings and a target consistent quality by selecting a content-adaptive bitrate and resolution for each adaptive bitrate (ABR) segment within each ABR representation in a manner that makes it equally suitable for live and on-demand workflows. Test results are presented over a wide range of content types. Initial results indicate that the proposed approach can recover 85% of the bit savings possible with more exhaustive techniques while its computational complexity is only 15%-20% of two-pass variable bitrate (VBR) encoding. © 2002 Society of Motion Picture and Television Engineers, Inc.Item A High Performance Early Acknowledged Asynchronous Pipeline using Hybrid-logic Encoding(Elsevier B.V., 2020) Girija Sravani, K.; Rao, R.This paper details a novel asynchronous pipelining methodology that maximizes the throughput buffering capacity and robustness of gate-level pipelined systems. The data paths in the proposed pipeline style are encoded using hybrid logic encoding scheme, which incorporates simplicity of the single-rail encoding and robustness of the dual-rail encoding. The control path that provides the synchronization between pipeline stages is constructed based on the simple and high-speed early acknowledgment protocol. Further, the proposed pipeline accommodates isolate phase to achieve 100% storage capacity. Two test cases: A 4-bit,10-stage FIFO and a 16-bit adder, have been designed in 90 nm technology to validate the proposed pipeline style. The FIFO has been laid out in the UMC 180 nm process using the cadence tool suite. The post-layout results of FIFO show 12.5% better throughput than the high capacity single-rail pipeline. Simulation results of the adder also reveal that the proposed structure achieves the throughput of 3.44 Giga-items/sec, which is 44.18% higher than the APCDP (Asynchronous pipeline based on constructed critical path) and 11.9% higher than the high capacity single-rail pipelines. © 2019 Elsevier B.V.Item Distributed video coding based on classification of frequency bands with block texture conditioned key frame encoder for wireless capsule endoscopy(Elsevier Ltd, 2020) Sushma, B.; Aparna., P.Wireless capsule endoscopy (WCE) has provided remarkable improvement in diagnosing gastrointestinal disorders by scanning the entire digestive tract. The system still need refinement, to upgrade the quality of images, frame rate and battery life. The principal component of the system that can address these issues is low complexity video compressor. Motivated by low computational complexity requirements of WCE video encoding, this paper presents a distributed video coding framework based on frequency bands classification. The lower frequency bands are used to generate good quality side information (SI) as they exhibit high temporal correlation. This reduces the complexity of hash generation at the encoder, thus eliminating the latency in SI creation. Apart from this, SI creation involves only a simple block search and doesn't depend on Wyner–Ziv (WZ) bands. Also different approach for distributed coding of sub-sampled chroma components of WZ frame is proposed. Low complexity JPEG based key frame encoding is proposed that take advantage of WCE image textural properties to reduce the complexity of encoding smooth blocks by 81% at the quantization and encoding stage. Other novel features include use of discrete Tchebichef transform (DTT), Golomb–Rice code for entropy coding. Performance evaluation shows that the proposed method achieves 60% improvement in compression over Motion JPEG with low computational complexity. © 2020 Elsevier LtdItem L, r-Stitch Unit: Encoder-Decoder-CNN Based Image-Mosaicing Mechanism for Stitching Non-Homogeneous Image Sequences(Institute of Electrical and Electronics Engineers Inc., 2021) Chilukuri, P.K.; Padala, P.; Padala, P.; Desanamukula, V.S.; Pvgd, P.R.Image-stitching (or) mosaicing is considered an active research-topic with numerous use-cases in computer-vision, AR/VR, computer-graphics domains, but maintaining homogeneity among the input image sequences during the stitching/mosaicing process is considered as a primary-limitation major-disadvantage. To tackle these limitations, this article has introduced a robust and reliable image stitching methodology (l,r-Stitch Unit), which considers multiple non-homogeneous image sequences as input to generate a reliable panoramically stitched wide view as the final output. The l,r-Stitch Unit further consists of a pre-processing, post-processing sub-modules a l,r-PanoED-network, where each sub-module is a robust ensemble of several deep-learning, computer-vision image-handling techniques. This article has also introduced a novel convolutional-encoder-decoder deep-neural-network (l,r-PanoED-network) with a unique split-encoding-network methodology, to stitch non-coherent input left, right stereo image pairs. The encoder-network of the proposed l,r-PanoED extracts semantically rich deep-feature-maps from the input to stitch/map them into a wide-panoramic domain, the feature-extraction feature-mapping operations are performed simultaneously in the l,r-PanoED's encoder-network based on the split-encoding-network methodology. The decoder-network of l,r-PanoED adaptively reconstructs the output panoramic-view from the encoder networks' bottle-neck feature-maps. The proposed l,r-Stitch Unit has been rigorously benchmarked with alternative image-stitching methodologies on our custom-built traffic dataset and several other public-datasets. Multiple evaluation metrics (SSIM, PSNR, MSE, L_{\alpha,\beta,\gamma } , FM-rate, Average-latency-time) wild-Conditions (rotational/color/intensity variances, noise, etc) were considered during the benchmarking analysis, and based on the results, our proposed method has outperformed among other image-stitching methodologies and has proved to be effective even in wild non-homogeneous inputs. © 2013 IEEE.Item Robust transmission using channel encoding towards 5G New Radio: A telemetry approach(Elsevier Ltd, 2021) Sharma, V.; Arya, R.K.; Kumar, S.This paper presents a robust channel encoding scheme under adaptive modulation and coding for a massive machine type communication device in 5G new radio. For the very first time, mode-selection and distance statistics algorithms have been simultaneously evaluated, in which together it provides the closest approximation of efficient adaptive modulation and coding with robust transmission. The prediction of optimum adaptive modulation and coding is based on the analysis of uplink packet using distance statistics, and downlink packet using mode-selection mechanism. The performance of 5G new radio by incorporating OFDM subcarrier has been evaluated using analytical as well as simulation approach. Mode-selection algorithm has been considered to predict the environmental condition under a fading channel while the distance statistics provide feedback of the previously transmitted channel condition. The result of both the approaches provide a better bit error rate for adaptive modulation & coding profile under 1/4, 1/18, 1/16 and 1/32 cyclic prefix. © 2021Item A Novel Approach for Asymmetric Quantum Error Correction With Syndrome Measurement(Institute of Electrical and Electronics Engineers Inc., 2022) Mummadi, M.; Rudra, B.Most of the quantum error correction methods are symmetric. Symmetric methods are implemented by considering the amplitude of bit flip(X) and phase flip(Z) errors as same. With the quantum experiments, it is observed that the amplitude of Z errors are more compared to X errors. Due to which the need of asymmetric error correction has increased. This paved a path for the development of asymmetric error correction methods. In this paper, we discussed the concept of asymmetric quantum error correction (AQEC) and proposed an efficient approach for AQEC with encoding, syndrome measurement and decoding operations with increased fidelity to 85.89% and reduced circuit depth to 48%. © 2013 IEEE.Item Contribution of frequency compressed temporal fine structure cues to the speech recognition in noise: An implication in cochlear implant signal processing(Elsevier Ltd, 2022) Poluboina, V.; Pulikala, A.; Pitchai Muthu, A.N.The study investigated the effect of proportionally frequency compressed encoding of temporal fine structure information on speech perception in noise using vocoder simulations of cochlear implant signal processing. The study proposed a pitch synchronous overlap-add algorithm (PSOLA) for downward frequency shifting of TFS. The speech recognition scores (SRS) were measured at −10 dB, 0 dB, and +10 dB for eight signal processing conditions corresponding to sinewave vocoder without TFS (NO-TFS), four unshifted TFS conditions including full band TFS, TFS up to 2000, 1000, and 600 Hz, and three conditions with PSOLA which shifted 2000, 1000 and 600 Hz TFS to 1000, 500 and 300 Hz respectively. The original envelope was unchanged across the conditions. SRS at +10 dB and −10 dB SNR reached ceiling and floor respectively, in most conditions. Hence, SRS at 0 dB SNR was compared across the conditions. The results showed that the SRS was highest with full band TFS and lowest for the NO-TFS condition.The SRS for TFS 600 Hz shifted to 300 Hz through PSOLA was higher than the NO-TFS condition. Study findings suggest that encoding TFS by proportional frequency compression results in better speech perception in noise compared to NO-TFS. An important observation of this current study is that the speech recognition was better than the sine wave vocoder for all TFS conditions including frequency compressed 600 Hz TFS. © 2021 Elsevier LtdItem Deep chroma prediction of Wyner–Ziv frames in distributed video coding of wireless capsule endoscopy video(Academic Press Inc., 2022) Sushma, B.; Aparna., P.Compression of captured video frames is crucial for saving the power in wireless capsule endoscopy (WCE). A low complexity encoder is desired to limit the power consumption required for compressing the WCE video. Distributed video coding (DVC) technique is best suitable for designing a low complexity encoder. In this technique, frames captured in RGB colour space are converted into YCbCr colour space. Both Y and CbCr representing luma and chroma components of the Wyner–Ziv (WZ) frames are processed and encoded in existing DVC techniques proposed for WCE video compression. In the WCE video, consecutive frames exhibit more similarity in texture and colour properties. The proposed work uses these properties to present a method for processing and encoding only the luma component of a WZ frame. The chroma components of the WZ frame are predicted by an encoder–decoder based deep chroma prediction model at the decoder by matching luma and texture information of the keyframe and WZ frame. The proposed method reduces the computations required for encoding and transmitting of WZ chroma component. The results show that the proposed DVC with a deep chroma prediction model performs better when compared to motion JPEG and existing DVC systems for WCE at the reduced encoder complexity. © 2022 Elsevier Inc.Item Design and Verification of an Asynchronous NoC Router Architecture for GALS Systems(Springer, 2024) Saranya, M.N.; Rao, R.The increasing multi-core system complexity with technology scaling introduces new constraints and challenges to interconnection network design. Consequently, the research community has a converging trend toward an asynchronous design paradigm for Network-on-Chip (NoC) architecture as a promising solution to these challenges. This paper addresses the design and functional verification aspects of an asynchronous NoC router microarchitecture for a Globally Asynchronous Locally Synchronous (GALS) system. Firstly, the paper introduces a novel mixed-level abstract simulation approach for faster functional verification of the asynchronous architecture using the commercially available Spectre Analog and mixed-signal simulation (AMS) Designer tool. This simulation methodology intends to ensure the feasibility of the design and identify shortcomings, if any, before the subsequent implementation stages of the design. Also, the paper proposes a new baseline asynchronous router built on a domino logic pipeline template with a novel hybrid encoding scheme. The new hybrid encoding scheme facilitates simple architecture with no additional timing constraints. The proposed verification methodology evaluates the baseline asynchronous router’s functional verification in Cadence’s AMS designer tool. Preliminary simulation results conform to the objectives of the paper. Further, the same verification setup establishes the design validation in subsequent stages of the design implementation. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.Item Machine Learning Framework for Classification of COVID-19 Variants Using K-mer Based DNA Sequencing(John Wiley and Sons Inc, 2025) Kumar, S.; Raju, S.; Bhowmik, B.Accurate classification of viral DNA sequences is essential for tracking mutations, understanding viral evolution, and enabling timely public health responses. Traditional alignment-based methods are often computationally intensive and less effective for highly mutating viruses. This article presents a machine learning framework for classifying DNA sequences of COVID-19 variants using K-mer-based tokenization and vectorization techniques inspired by Natural Language Processing (NLP). DNA sequences corresponding to Alpha, Beta, Gamma, and Omicron variants are obtained from the Global Initiative on Sharing All Influenza Data (GISAID) database and encoded into feature vectors. Multiple classifiers, including Extra Trees, Random Forest, Support Vector Classifier (SVC), Decision Tree, Logistic Regression, Naive Bayes, K-Nearest Neighbor (KNN), Ridge Classifier, Stochastic Gradient Descent (SGD), and XGBoost, are evaluated based on accuracy, precision, recall, and F1-score. The Extra Trees model achieved the highest accuracy of 93.10% (Formula presented.) 0.42, followed by Random Forest with 92.60% (Formula presented.) 0.38, both demonstrating robust and balanced performance. Statistical significance tests confirmed the robustness of the results. The results validate the effectiveness of K-mer-based encoding combined with traditional machine learning models in classifying COVID-19 variants, offering a scalable and efficient solution for genomic surveillance. © 2025 Wiley Periodicals LLC.