Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806736
Vinay Gupta, J. Meenakshinathan, T. Reddy, L. Behera
Riemannian Geometry-based features have been among the most promising electroencephalography(EEG) classification methods in recent years. However, these features can be classified using many machine learning(ML) algorithms. When compared against the standard methods, deep learning-based approaches are successful in classification accuracy and transfer learning. In this paper, we attempt to study Neural structured learning(NSL) to develop robust and regularized neural network models that preserve the similarity structure of the input EEG signals for a more reliable Brain-Computer Interface(BCI) classification. In this study, we have used the state-of-the-art Euclidean Tangent Space features projected from the Riemannian Covariance features of EEG to train the standard feedforward neural nets while incorporating the NSL module. It creates a similarity graph among the input samples and minimizes a graph regularization loss to maintain the neighbor structure. The proposed approach is evaluated on the standard 4-class Dataset 2a from BCI competition 2008. The results show that the proposed model improves accuracy compared to the base model without graph regularization. Surprisingly, it requires very few training samples to achieve almost state-of-the-art accuracy for some subjects using a mere two hidden layered neural network.
{"title":"Performance study of Neural Structured Learning using Riemannian Features for BCI Classification","authors":"Vinay Gupta, J. Meenakshinathan, T. Reddy, L. Behera","doi":"10.1109/NCC55593.2022.9806736","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806736","url":null,"abstract":"Riemannian Geometry-based features have been among the most promising electroencephalography(EEG) classification methods in recent years. However, these features can be classified using many machine learning(ML) algorithms. When compared against the standard methods, deep learning-based approaches are successful in classification accuracy and transfer learning. In this paper, we attempt to study Neural structured learning(NSL) to develop robust and regularized neural network models that preserve the similarity structure of the input EEG signals for a more reliable Brain-Computer Interface(BCI) classification. In this study, we have used the state-of-the-art Euclidean Tangent Space features projected from the Riemannian Covariance features of EEG to train the standard feedforward neural nets while incorporating the NSL module. It creates a similarity graph among the input samples and minimizes a graph regularization loss to maintain the neighbor structure. The proposed approach is evaluated on the standard 4-class Dataset 2a from BCI competition 2008. The results show that the proposed model improves accuracy compared to the base model without graph regularization. Surprisingly, it requires very few training samples to achieve almost state-of-the-art accuracy for some subjects using a mere two hidden layered neural network.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124618061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806792
Ashish Kumar Padhan, H. Sahu, P. R. Sahu, S. Samantaray
A three-hop long range communication system with mixed fading for smart grid (SG) wide area network (WAN) is proposed. The three hops proposed here are power line communication (PLC), radio frequency (RF) and free space optical (FSO) in cascade. The smart meter (SM) transfers the data to the access point (AP) through a PLC link. The AP is acting as a decode-and-forward (DF) relay. It retransmits the data to data aggregator unit (DAU) through RF link. The DAU also acts as a DF relay and retransmits the information to meter data management system (MDMS) through FSO link. The PLC, RF, and FSO links are distributed with Log-Normal, Nakagami-m, and Gamma-Gamma distribution, respectively. The modulation scheme considered here is binary phase shift keying (BPSK). A closed form expression for average bit error probability (ABEP) is obtained. Numerical and Monte-Carlo simulation results demonstrate the effect of impulsive noise scenario in the PLC channel, fading severity in Nakagami-m channel, and different FSO parameters in SG communication system.
{"title":"Analysis of Smart Grid Wide Area Network for Three Hop Mixed PLC/RF/FSO Channel","authors":"Ashish Kumar Padhan, H. Sahu, P. R. Sahu, S. Samantaray","doi":"10.1109/NCC55593.2022.9806792","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806792","url":null,"abstract":"A three-hop long range communication system with mixed fading for smart grid (SG) wide area network (WAN) is proposed. The three hops proposed here are power line communication (PLC), radio frequency (RF) and free space optical (FSO) in cascade. The smart meter (SM) transfers the data to the access point (AP) through a PLC link. The AP is acting as a decode-and-forward (DF) relay. It retransmits the data to data aggregator unit (DAU) through RF link. The DAU also acts as a DF relay and retransmits the information to meter data management system (MDMS) through FSO link. The PLC, RF, and FSO links are distributed with Log-Normal, Nakagami-m, and Gamma-Gamma distribution, respectively. The modulation scheme considered here is binary phase shift keying (BPSK). A closed form expression for average bit error probability (ABEP) is obtained. Numerical and Monte-Carlo simulation results demonstrate the effect of impulsive noise scenario in the PLC channel, fading severity in Nakagami-m channel, and different FSO parameters in SG communication system.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123657927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806789
M. Kumar, S. Sharma, K. Deka, M. Thottappan
Reconfigurable intelligent surfaces (RIS) and non-orthogonal multiple access (NOMA) are promising technologies for next-generation wireless networks. RIS can reconfigure wire-less channels through passive reflecting elements, and NOMA enhances spectral efficiency (SE) and connectivity. In this paper, a base station (BS) transmits superimposed precoded symbols to near and far users via two different RIS deployment strategies. Initially, a single RIS is deployed at the BS and consists of N passive reflecting elements, referred to as centralized deployment of RIS-assisted NOMA (CDR-NOMA). On the other hand, two RISs having N/2 elements are kept at users and referred to as distributed deployment of RIS-assisted NOMA (DDR-NOMA). We have optimized the phase shift at RIS using the semidefinite relaxation (SDR) technique to maximize the received signal-to-noise ratio (SNR). Simulation results show that the bit error rate (BER) of the CDR-NOMA system is superior to the DDR-NOMA and a conventional RIS-assisted NOMA system. Further, the sum-rate of the proposed CDR-NOMA and DDR-NOMA is calculated and it is better than the orthogonal multiple access (OMA). Furthermore, impact of transmitting antennas and reflecting surfaces are studied on the sum-rate and BER performance in the CDR-NOMA and DDR-NOMA.
{"title":"Centralized and Distributed Reconfigurable Intelligent Surfaces Assisted NOMA","authors":"M. Kumar, S. Sharma, K. Deka, M. Thottappan","doi":"10.1109/NCC55593.2022.9806789","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806789","url":null,"abstract":"Reconfigurable intelligent surfaces (RIS) and non-orthogonal multiple access (NOMA) are promising technologies for next-generation wireless networks. RIS can reconfigure wire-less channels through passive reflecting elements, and NOMA enhances spectral efficiency (SE) and connectivity. In this paper, a base station (BS) transmits superimposed precoded symbols to near and far users via two different RIS deployment strategies. Initially, a single RIS is deployed at the BS and consists of N passive reflecting elements, referred to as centralized deployment of RIS-assisted NOMA (CDR-NOMA). On the other hand, two RISs having N/2 elements are kept at users and referred to as distributed deployment of RIS-assisted NOMA (DDR-NOMA). We have optimized the phase shift at RIS using the semidefinite relaxation (SDR) technique to maximize the received signal-to-noise ratio (SNR). Simulation results show that the bit error rate (BER) of the CDR-NOMA system is superior to the DDR-NOMA and a conventional RIS-assisted NOMA system. Further, the sum-rate of the proposed CDR-NOMA and DDR-NOMA is calculated and it is better than the orthogonal multiple access (OMA). Furthermore, impact of transmitting antennas and reflecting surfaces are studied on the sum-rate and BER performance in the CDR-NOMA and DDR-NOMA.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114847773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806716
Varsha Balakumar, R. Ganti
In this work, we consider the application of digital predistortion for MIMO mm-wave RF beamforming-based subarrays. We propose a single-input single-output (SISO) DPD model as a linearization technique to mitigate the nonlinear behaviour exhibited by the power amplifiers in mm-wave phased arrays. This model incorporates mutual coupling between the antenna elements. This particular SISO-based model is obtained by transforming a dual-input-based model that accounts for the load-impedance mismatch between the antenna elements. Our proposed SISO-based DPD model can be considered a possible replacement of complex dual-input-based modelling approaches. We provide simulation results of two different array beamforming configurations: Single user beamforming array system (A 64-element antenna array) and multi-user beamforming array system (4 x 64 elements antenna array).
{"title":"Digital Predistortion for mm-Wave MIMO Phased Arrays","authors":"Varsha Balakumar, R. Ganti","doi":"10.1109/NCC55593.2022.9806716","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806716","url":null,"abstract":"In this work, we consider the application of digital predistortion for MIMO mm-wave RF beamforming-based subarrays. We propose a single-input single-output (SISO) DPD model as a linearization technique to mitigate the nonlinear behaviour exhibited by the power amplifiers in mm-wave phased arrays. This model incorporates mutual coupling between the antenna elements. This particular SISO-based model is obtained by transforming a dual-input-based model that accounts for the load-impedance mismatch between the antenna elements. Our proposed SISO-based DPD model can be considered a possible replacement of complex dual-input-based modelling approaches. We provide simulation results of two different array beamforming configurations: Single user beamforming array system (A 64-element antenna array) and multi-user beamforming array system (4 x 64 elements antenna array).","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134229515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806741
Aditya Singh, Surender Redhu, R. Hegde
Energy harvesting plays a crucial role in improving the operational lifetime of an IoT network. Moreover, the source and receiver separation dominates the amount of energy har-vested in rechargeable IoT networks. In recent, Unmanned Aerial Vehicles (UAVs) have been utilized as RF energy transmitters for energy harvesting IoT networks. In this work, a method is proposed for optimizing the altitude of UAV s for energy-efficient charging of the IoT nodes. The proposed method maximizes the energy usage efficiency of the UAV over the IoT network subject to altitude and energy harvesting constraints. The proposed maximization problem is first transformed into an equivalent convex optimization problem using the First-Order Taylor Series Approximation. A heuristic algorithm based on the sequential convex programming approach is employed to obtain the optimal UAV altitude above the IoT network. The accuracy of the obtained results is evaluated analytically by computing the global optimum of the optimization problem via monotonic transformations. The results motivate the usage of UAV-aided energy harvesting in self-sustaining IoT networks.
{"title":"UAV Altitude Optimization for Efficient Energy Harvesting in IoT Networks","authors":"Aditya Singh, Surender Redhu, R. Hegde","doi":"10.1109/NCC55593.2022.9806741","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806741","url":null,"abstract":"Energy harvesting plays a crucial role in improving the operational lifetime of an IoT network. Moreover, the source and receiver separation dominates the amount of energy har-vested in rechargeable IoT networks. In recent, Unmanned Aerial Vehicles (UAVs) have been utilized as RF energy transmitters for energy harvesting IoT networks. In this work, a method is proposed for optimizing the altitude of UAV s for energy-efficient charging of the IoT nodes. The proposed method maximizes the energy usage efficiency of the UAV over the IoT network subject to altitude and energy harvesting constraints. The proposed maximization problem is first transformed into an equivalent convex optimization problem using the First-Order Taylor Series Approximation. A heuristic algorithm based on the sequential convex programming approach is employed to obtain the optimal UAV altitude above the IoT network. The accuracy of the obtained results is evaluated analytically by computing the global optimum of the optimization problem via monotonic transformations. The results motivate the usage of UAV-aided energy harvesting in self-sustaining IoT networks.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"61 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133038648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806777
Ajit Kumar, Sudhir Kumar
The nanomachine has a finite processing capability due to size, power, and complexity constraints. To overcome these issues, nanomachine must cooperate to optimize its information exchange operations. Clock synchronization is required for nanomachine cooperation. In Molecular Communication (MC), synchronization is a challenging task due to the random move-ment of molecules that causes inter-symbol interference (ISI) and non-stationary noise. In this paper, we propose a method for clock synchronization between the transmitter nanomachine (TN) and the receiver nanomachine (RN) based on the molecule's emission time estimation. In the presence of both signal-dependent noise and ISI, clock synchronization is performed using maximum likelihood estimation (MLE). The proposed method takes into account a non-zero emission duration of molecules by the TN. The clock synchronization with rectangular input concentration is realistic for practical applications because the emission duration of molecules can not be zero. The effectiveness of the proposed method is shown by numerical results.
{"title":"Emission Time Estimation with Rectangular Input Concentration in Molecular Communication Systems","authors":"Ajit Kumar, Sudhir Kumar","doi":"10.1109/NCC55593.2022.9806777","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806777","url":null,"abstract":"The nanomachine has a finite processing capability due to size, power, and complexity constraints. To overcome these issues, nanomachine must cooperate to optimize its information exchange operations. Clock synchronization is required for nanomachine cooperation. In Molecular Communication (MC), synchronization is a challenging task due to the random move-ment of molecules that causes inter-symbol interference (ISI) and non-stationary noise. In this paper, we propose a method for clock synchronization between the transmitter nanomachine (TN) and the receiver nanomachine (RN) based on the molecule's emission time estimation. In the presence of both signal-dependent noise and ISI, clock synchronization is performed using maximum likelihood estimation (MLE). The proposed method takes into account a non-zero emission duration of molecules by the TN. The clock synchronization with rectangular input concentration is realistic for practical applications because the emission duration of molecules can not be zero. The effectiveness of the proposed method is shown by numerical results.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134461657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806768
Jagabandhu Mishra, Soma Siddhartha, S. Prasanna
Spoken LID systems generally capture the long term temporal dynamic information present in the speech signal. To achieve that, sequence modeling techniques are used after the feature extraction process. But, the performance of the spoken LID system degrades in cross channel and noisy scenarios. From the literature, we can observe the benefit of excitation source information in noisy and cross-channel scenarios. Besides that, excitation features are also used as complementary evidence in spoken LID systems with spectral features. Motivated from this, an excitation based feature called integrated residual linear frequency cepstral coefficient (IRLFCC) has been proposed in this work. This work also provides a comparison between various deep learning based sequence modeling architectures towards capturing spoken language specific information. The experiments are performed using OLR2020 dataset. From the experiments, it can be observed that in the cross channel scenario, the proposed best system provides a relative improvement of 70.5% and 57.2% over the baseline in terms of $EER_{avg}$ and $C_{avg}$ respectively. Similarly, in the noisy scenario, the proposed best system provides a relative improvement of 37.8% and 45 % over the baseline system.
{"title":"Importance of excitation source and sequence learning towards spoken language identification task","authors":"Jagabandhu Mishra, Soma Siddhartha, S. Prasanna","doi":"10.1109/NCC55593.2022.9806768","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806768","url":null,"abstract":"Spoken LID systems generally capture the long term temporal dynamic information present in the speech signal. To achieve that, sequence modeling techniques are used after the feature extraction process. But, the performance of the spoken LID system degrades in cross channel and noisy scenarios. From the literature, we can observe the benefit of excitation source information in noisy and cross-channel scenarios. Besides that, excitation features are also used as complementary evidence in spoken LID systems with spectral features. Motivated from this, an excitation based feature called integrated residual linear frequency cepstral coefficient (IRLFCC) has been proposed in this work. This work also provides a comparison between various deep learning based sequence modeling architectures towards capturing spoken language specific information. The experiments are performed using OLR2020 dataset. From the experiments, it can be observed that in the cross channel scenario, the proposed best system provides a relative improvement of 70.5% and 57.2% over the baseline in terms of $EER_{avg}$ and $C_{avg}$ respectively. Similarly, in the noisy scenario, the proposed best system provides a relative improvement of 37.8% and 45 % over the baseline system.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115512775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806751
G. K. Sahoo, S. Das, Poonam Singh
This study proposes deep learning-based facial emotion recognition (FER) for driver health care. The FER system will monitor the emotional state of the driver's face to identify the driver's negligence and provide immediate assistance for safety. This work uses a transfer learning-based framework for FER which will help in developing an in-vehicle driver assistance system. It implements transfer learning SqueezeNet 1.1 to classify different facial expressions. Data preprocessing techniques such as image resizing and data augmentation have been employed to improve performance. The experimental study uses static facial expressions publicly available on several benchmark databases such as CK+, KDEF, FER2013, and KMU-FED to evaluate the model's performance. The performance comparison only showed superiority over state-of-the-art technologies in the case of the KMU-FED database, i.e., maximum accuracy of 95.83 %, and the results showed comparable performance to the rest of the benchmark databases.
{"title":"Deep Learning-Based Facial Emotion Recognition for Driver Healthcare","authors":"G. K. Sahoo, S. Das, Poonam Singh","doi":"10.1109/NCC55593.2022.9806751","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806751","url":null,"abstract":"This study proposes deep learning-based facial emotion recognition (FER) for driver health care. The FER system will monitor the emotional state of the driver's face to identify the driver's negligence and provide immediate assistance for safety. This work uses a transfer learning-based framework for FER which will help in developing an in-vehicle driver assistance system. It implements transfer learning SqueezeNet 1.1 to classify different facial expressions. Data preprocessing techniques such as image resizing and data augmentation have been employed to improve performance. The experimental study uses static facial expressions publicly available on several benchmark databases such as CK+, KDEF, FER2013, and KMU-FED to evaluate the model's performance. The performance comparison only showed superiority over state-of-the-art technologies in the case of the KMU-FED database, i.e., maximum accuracy of 95.83 %, and the results showed comparable performance to the rest of the benchmark databases.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123648574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806796
Mahari B. Tsegay, Kalpana Dhaka, R. Bhattacharjee
Device-to-device (D2D) underlay cellular network allows spectrum reuse that improves the spectral efficiency of the network. The challenge in allowing D2D links or relay-assisted D2D links to use the same resources as the traditional cellular down/uplink transmissions is the mutual interference between them. The cellular link contributes majorly to the interference due to the high power transmitted over the link. In this work, we consider interference due to cellular transmission at the relay and destination node of the relay-assisted D2D link are mitigated using decoding matrices obtained using interference alignment techniques. The exact expressions of the end-to-end outage probability and symbol error probability are obtained. The analysis is presented for a general scenario with multiple transmit and receive antennas. Numerical results are plotted to show the impact of the modulation order, interference due to other D2D devices, and power transmitted at the source and relay nodes.
{"title":"Performance Analysis of a Relay-Assisted D2D Underlay Cellular Network","authors":"Mahari B. Tsegay, Kalpana Dhaka, R. Bhattacharjee","doi":"10.1109/NCC55593.2022.9806796","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806796","url":null,"abstract":"Device-to-device (D2D) underlay cellular network allows spectrum reuse that improves the spectral efficiency of the network. The challenge in allowing D2D links or relay-assisted D2D links to use the same resources as the traditional cellular down/uplink transmissions is the mutual interference between them. The cellular link contributes majorly to the interference due to the high power transmitted over the link. In this work, we consider interference due to cellular transmission at the relay and destination node of the relay-assisted D2D link are mitigated using decoding matrices obtained using interference alignment techniques. The exact expressions of the end-to-end outage probability and symbol error probability are obtained. The analysis is presented for a general scenario with multiple transmit and receive antennas. Numerical results are plotted to show the impact of the modulation order, interference due to other D2D devices, and power transmitted at the source and relay nodes.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122093237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-24DOI: 10.1109/NCC55593.2022.9806466
N. Suresh, Pavan Manesh Mylavarapu, Naga Sailaja Mahankali, Sumohana S. Channappayya
This work addresses the problem of efficient noreference video quality assessment (NR-VQA). The motivation for this work is that even the best and fastest VQA algorithms do not achieve real-time performance. The speed of quality evaluation is impeded primarily by the spatio-temporal feature extraction stage. This impediment is common to both traditional as well as deep learning models. To address this issue, we explore the efficacy of features used in the action recognition problem for NR- VQA. Specifically, we leverage the efficiency offered by Gate Shift Module (GSM) in extracting spatio-temporal features. A simple yet effective improvement to the GSM model is proposed by adding the self-attention module. We first show that GSM features are indeed effective for NR-VQA. We then demonstrate a speed-up that is orders of magnitude faster than the current state-of-the-art VQA algorithms, albeit at the cost of overall performance. We evaluate the efficacy of our algorithm on both Standard Dynamic Range (SDR) and High Dynamic Range (HDR) datasets like KoNViD-1K, LIVE VQC, HDR.
本工作解决了高效无参考视频质量评估(NR-VQA)的问题。这项工作的动机是，即使是最好和最快的VQA算法也无法实现实时性能。质量评价的速度主要受时空特征提取阶段的影响。这种障碍在传统和深度学习模型中都很常见。为了解决这个问题，我们探讨了在NR- VQA的动作识别问题中使用的特征的有效性。具体来说，我们利用门移模块(GSM)在提取时空特征方面提供的效率。通过增加自关注模块，对GSM模型进行了简单而有效的改进。我们首先证明GSM特性确实对NR-VQA有效。然后我们演示了一种比当前最先进的VQA算法快几个数量级的加速，尽管是以整体性能为代价的。我们评估了算法在标准动态范围(SDR)和高动态范围(HDR)数据集(如KoNViD-1K, LIVE VQC, HDR)上的有效性。
{"title":"A Fast and Efficient No-Reference Video Quality Assessment Algorithm Using Video Action Recognition Features","authors":"N. Suresh, Pavan Manesh Mylavarapu, Naga Sailaja Mahankali, Sumohana S. Channappayya","doi":"10.1109/NCC55593.2022.9806466","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806466","url":null,"abstract":"This work addresses the problem of efficient noreference video quality assessment (NR-VQA). The motivation for this work is that even the best and fastest VQA algorithms do not achieve real-time performance. The speed of quality evaluation is impeded primarily by the spatio-temporal feature extraction stage. This impediment is common to both traditional as well as deep learning models. To address this issue, we explore the efficacy of features used in the action recognition problem for NR- VQA. Specifically, we leverage the efficiency offered by Gate Shift Module (GSM) in extracting spatio-temporal features. A simple yet effective improvement to the GSM model is proposed by adding the self-attention module. We first show that GSM features are indeed effective for NR-VQA. We then demonstrate a speed-up that is orders of magnitude faster than the current state-of-the-art VQA algorithms, albeit at the cost of overall performance. We evaluate the efficacy of our algorithm on both Standard Dynamic Range (SDR) and High Dynamic Range (HDR) datasets like KoNViD-1K, LIVE VQC, HDR.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127896084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：