This paper investigates a reconfigurable intelligent surface (RIS)-aided rate-splitting multiple access (RSMA) communication system. A base-station communicates with cell-edge users using the RSMA protocol with user-dedicated RIS. Using the univariate dimension reduction method, the expressions for the outage probability (OP) are derived considering the optimal and discrete phase-shifts introduced by RIS elements. The interdependent constraints of the threshold and the RSMA factors are derived and analyzed. Furthermore, the effects of various factors such as number of RIS elements, number of quantization bits, RSMA factors, threshold, etc. have been discussed and several interesting insights are presented. The derived expressions are validated using the Monte-Carlo simulations.
{"title":"Performance Analysis of RIS Assisted RSMA Communication System","authors":"Divyanshu Shambharkar, Shivani Dhok, Prabhat Kumar Sharma","doi":"10.1109/NCC55593.2022.9806718","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806718","url":null,"abstract":"This paper investigates a reconfigurable intelligent surface (RIS)-aided rate-splitting multiple access (RSMA) communication system. A base-station communicates with cell-edge users using the RSMA protocol with user-dedicated RIS. Using the univariate dimension reduction method, the expressions for the outage probability (OP) are derived considering the optimal and discrete phase-shifts introduced by RIS elements. The interdependent constraints of the threshold and the RSMA factors are derived and analyzed. Furthermore, the effects of various factors such as number of RIS elements, number of quantization bits, RSMA factors, threshold, etc. have been discussed and several interesting insights are presented. The derived expressions are validated using the Monte-Carlo simulations.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"121 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":"133680529","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/NCC55593.2022.9806733
Dhruvi Shah, Hareshwar Wani, M. Das, Deep Gupta, P. Radeva, Ashwini M. Bakde
Medical images from various modalities carry diverse information. The features from these source images are combined into a single image, constituting more information content, beneficial for subsequent medical applications. Recently, deep learning (DL) based networks have demonstrated the ability to produce promising fusion results by integrating the feature extraction and preservation task with less manual interventions. However, using a single network for extracting features from multi-modal source images characterizing distinct information results in the loss of crucial diagnostic information. Addressing this problem, we present structure and texture preserving generative adversarial networks based medical image fusion method (STPGANsFusion). Initially, the textural and structural components of the source images are separated using structure gradient and texture decorrelating regularizer (SGTDR) based image decomposition for more complementary information preservation and higher robustness for the model. Next, the fusion of the structure and the texture components is carried out using two generative adversarial networks (GANs) consisting of a generator and two discriminators to get fused structure and texture components. The loss function for each GAN is framed as per the characteristic of the component being fused to minimize the loss of complementary information. The fused image is reconstructed and undergoes adaptive mask-based structure enhancement to further boost its contrast and visualization. Substantial experimentation is carried out on a wide variety of neurological images. Visual and qualitative results exhibit notable improvement in the fusion performance of the proposed method in comparison to the state-of-the-art fusion methods.
{"title":"STPGANsFusion: Structure and Texture Preserving Generative Adversarial Networks for Multi-modal Medical Image Fusion","authors":"Dhruvi Shah, Hareshwar Wani, M. Das, Deep Gupta, P. Radeva, Ashwini M. Bakde","doi":"10.1109/NCC55593.2022.9806733","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806733","url":null,"abstract":"Medical images from various modalities carry diverse information. The features from these source images are combined into a single image, constituting more information content, beneficial for subsequent medical applications. Recently, deep learning (DL) based networks have demonstrated the ability to produce promising fusion results by integrating the feature extraction and preservation task with less manual interventions. However, using a single network for extracting features from multi-modal source images characterizing distinct information results in the loss of crucial diagnostic information. Addressing this problem, we present structure and texture preserving generative adversarial networks based medical image fusion method (STPGANsFusion). Initially, the textural and structural components of the source images are separated using structure gradient and texture decorrelating regularizer (SGTDR) based image decomposition for more complementary information preservation and higher robustness for the model. Next, the fusion of the structure and the texture components is carried out using two generative adversarial networks (GANs) consisting of a generator and two discriminators to get fused structure and texture components. The loss function for each GAN is framed as per the characteristic of the component being fused to minimize the loss of complementary information. The fused image is reconstructed and undergoes adaptive mask-based structure enhancement to further boost its contrast and visualization. Substantial experimentation is carried out on a wide variety of neurological images. Visual and qualitative results exhibit notable improvement in the fusion performance of the proposed method in comparison to the state-of-the-art fusion methods.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"32 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114124893","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/NCC55593.2022.9806737
Sonia Gupta, M. Agrawal, D. Deepak
Millions of people suffer from respiratory illness globally. Early diagnosis of respiratory diseases is hindered because of the lack of cost-effective and simple methods. Spirometry is the pulmonary function test used for diagnosis of obstructive diseases like asthma, chronic obstructive pulmonary disease (COPD) and restrictive diseases like interstitial lung disease (ILD), etc. This test requires repeated manoeuvre, is expensive and is done in laboratory which are not available in resource poor areas. Auscultation is an easy and cost-effective method which can play a vital role in early diagnosis of respiratory diseases. In this paper, a technique is proposed which could classify auscultation sounds into normal, obstructive and restrictive disease category similar to the findings of spirometry. The proposed work uses combination of multivariate variational mode decomposition and dynamic time warping for enhancing multi-channel signal. Further, pre-trained 3D ResNet18 neural network model is used for classification into three classes. Encouraging results are achieved with accuracy of 94.57%, sensitivity of 100% and specificity of 94.11%.
{"title":"Classification of Auscultation Sounds into Objective Spirometry Findings using MVMD and 3D CNN","authors":"Sonia Gupta, M. Agrawal, D. Deepak","doi":"10.1109/NCC55593.2022.9806737","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806737","url":null,"abstract":"Millions of people suffer from respiratory illness globally. Early diagnosis of respiratory diseases is hindered because of the lack of cost-effective and simple methods. Spirometry is the pulmonary function test used for diagnosis of obstructive diseases like asthma, chronic obstructive pulmonary disease (COPD) and restrictive diseases like interstitial lung disease (ILD), etc. This test requires repeated manoeuvre, is expensive and is done in laboratory which are not available in resource poor areas. Auscultation is an easy and cost-effective method which can play a vital role in early diagnosis of respiratory diseases. In this paper, a technique is proposed which could classify auscultation sounds into normal, obstructive and restrictive disease category similar to the findings of spirometry. The proposed work uses combination of multivariate variational mode decomposition and dynamic time warping for enhancing multi-channel signal. Further, pre-trained 3D ResNet18 neural network model is used for classification into three classes. Encouraging results are achieved with accuracy of 94.57%, sensitivity of 100% and specificity of 94.11%.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"357 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":"114759251","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/NCC55593.2022.9806755
Avinash Ratre, Vinod Pankajakshan
Surveillance video data often exhibit highly imbal-anced data distribution, i.e., majority or normal class instances outnumber the minority or anomalous class instances, which are the point of concern in video anomaly detection (AD). The existing deep learning methods often adopt various ensemble methods consisting of an early or late fusion of the cascade of either deep discriminative or generative learning models. These methods lack the diversity in applying the deep learning algorithms to imbalanced data learning for AD in real-world unlabeled and imbalanced surveillance video data. In this paper, decision level late fusion of two complementary deep learning models is accomplished using a loss function weighted regression model towards imbalanced data learning for video AD. Under the algorithmic level actions, the learning model's architecture consists of two complementary parallel discriminative-generative channels, i.e., a discriminative deep residual network (DRN) channel and a generative deep regression long short-term memory (LSTM) channel. The proposed complementary deep LSTM-DRN-based imbalanced data learning approach improves effectiveness in detecting anomalies compared to state-of-the-art methods.
{"title":"Deep Imbalanced Data Learning Approach for Video Anomaly Detection","authors":"Avinash Ratre, Vinod Pankajakshan","doi":"10.1109/NCC55593.2022.9806755","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806755","url":null,"abstract":"Surveillance video data often exhibit highly imbal-anced data distribution, i.e., majority or normal class instances outnumber the minority or anomalous class instances, which are the point of concern in video anomaly detection (AD). The existing deep learning methods often adopt various ensemble methods consisting of an early or late fusion of the cascade of either deep discriminative or generative learning models. These methods lack the diversity in applying the deep learning algorithms to imbalanced data learning for AD in real-world unlabeled and imbalanced surveillance video data. In this paper, decision level late fusion of two complementary deep learning models is accomplished using a loss function weighted regression model towards imbalanced data learning for video AD. Under the algorithmic level actions, the learning model's architecture consists of two complementary parallel discriminative-generative channels, i.e., a discriminative deep residual network (DRN) channel and a generative deep regression long short-term memory (LSTM) channel. The proposed complementary deep LSTM-DRN-based imbalanced data learning approach improves effectiveness in detecting anomalies compared to state-of-the-art methods.","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":"116049741","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/NCC55593.2022.9806757
J. Singh, Indranil Chatterjee, Suraj Srivastava, A. Jagannatham
A hybrid transceiver architecture along with the optimal power allocation is conceived for a downlink millimeter wave (mmWave) multi-input multi-output (MIMO) cognitive radio (CR) system operating in the underlay mode. Towards this, the non-convex objective and constraints of the sum spectral ef-ficiency (SE) maximization problem are simplified by decoupling the hybrid precoder and combiner designs. First, considering the perfect knowledge of the downlink mmWave MIMO channel, we design the combiner at each SU. Subsequently, the front-end digital baseband (BB) precoder and analog-domain RF precoder are designed using the best-approximation problem to the capacity-optimal fully-digital precoder. Moreover, our design also considers the spatial correlation among the mmWave MIMO channels, thereby significantly reducing the computational complexity for the analog precoder/combiner design. Furthermore, in order to cancel the multiuser interference (MUI), the back-end of the BB precoder has been designed using the low-complexity zero-forcing (ZF) technique. Finally, a closed-form solution to the optimal power allocation problem is derived, which maximizes the overall SE of the downlink mm Wave MIMO CR system under the interference power constraint imposed by the primary user (PU). Our simulation findings show an improved SE compared to state-of-the-art approaches while performing close to the ideal fully-digital benchmark.
{"title":"Hybrid Transceiver Design and Optimal Power Allocation in Downlink mmWave Hybrid MIMO Cognitive Radio Systems","authors":"J. Singh, Indranil Chatterjee, Suraj Srivastava, A. Jagannatham","doi":"10.1109/NCC55593.2022.9806757","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806757","url":null,"abstract":"A hybrid transceiver architecture along with the optimal power allocation is conceived for a downlink millimeter wave (mmWave) multi-input multi-output (MIMO) cognitive radio (CR) system operating in the underlay mode. Towards this, the non-convex objective and constraints of the sum spectral ef-ficiency (SE) maximization problem are simplified by decoupling the hybrid precoder and combiner designs. First, considering the perfect knowledge of the downlink mmWave MIMO channel, we design the combiner at each SU. Subsequently, the front-end digital baseband (BB) precoder and analog-domain RF precoder are designed using the best-approximation problem to the capacity-optimal fully-digital precoder. Moreover, our design also considers the spatial correlation among the mmWave MIMO channels, thereby significantly reducing the computational complexity for the analog precoder/combiner design. Furthermore, in order to cancel the multiuser interference (MUI), the back-end of the BB precoder has been designed using the low-complexity zero-forcing (ZF) technique. Finally, a closed-form solution to the optimal power allocation problem is derived, which maximizes the overall SE of the downlink mm Wave MIMO CR system under the interference power constraint imposed by the primary user (PU). Our simulation findings show an improved SE compared to state-of-the-art approaches while performing close to the ideal fully-digital benchmark.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"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":"124481871","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/NCC55593.2022.9806790
Adit Jain, D. Rahul, Salil Kashyap, Rimalapudi Sarvendranath
In recent literature, intelligent reflecting surfaces (IRS) based wireless system design has been a significant point of excitement among the wireless community. We consider the problem of configuring the IRS elements efficiently and effectively for a practical IRS with discrete phase shifts and coupled elements deployed in an orthogonal frequency-division multiplexing (OFDM) based environment. We propose two near-optimal low complexity extremely scalable heuristic algorithms to design phase shifts at IRS in an OFDM system when the number of bits used to configure the IRS is limited, and the reflected channels via the IRS are spatially correlated. We benchmark the sum data rate performance of our algorithms against the theoretical upper bound and the time performance against the existing successive convex approximation. Results indicate that 4 bits are sufficient to obtain theoretically optimum sum data rates and that our proposed algorithms obtain a good trade-off between complexity and performance.
{"title":"Low Complexity Passive Beamforming Algorithms for Intelligent Reflecting Surfaces with Discrete Phase-Shifts over OFDM Systems","authors":"Adit Jain, D. Rahul, Salil Kashyap, Rimalapudi Sarvendranath","doi":"10.1109/NCC55593.2022.9806790","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806790","url":null,"abstract":"In recent literature, intelligent reflecting surfaces (IRS) based wireless system design has been a significant point of excitement among the wireless community. We consider the problem of configuring the IRS elements efficiently and effectively for a practical IRS with discrete phase shifts and coupled elements deployed in an orthogonal frequency-division multiplexing (OFDM) based environment. We propose two near-optimal low complexity extremely scalable heuristic algorithms to design phase shifts at IRS in an OFDM system when the number of bits used to configure the IRS is limited, and the reflected channels via the IRS are spatially correlated. We benchmark the sum data rate performance of our algorithms against the theoretical upper bound and the time performance against the existing successive convex approximation. Results indicate that 4 bits are sufficient to obtain theoretically optimum sum data rates and that our proposed algorithms obtain a good trade-off between complexity and performance.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"1 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":"129290512","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/NCC55593.2022.9806785
Rudrabhotla Sri Prakash, N. Karamchandani, Sharayu Moharir
We consider the problem of best arm identification in the fixed confidence setting for a variant of the multi-arm bandit problem. In our problem, each arm is associated with two attributes, a known deterministic cost, and an unknown stochastic reward. In addition, it is known that arms with higher costs have higher rewards across every sample path. The net utility of each arm is defined as the difference between its expected reward and cost. We consider two information models, namely, the full information feedback and sequential bandit feedback. We derive a fundamental lower bound on the sample complexity of any policy and also propose policies with provable performance guarantees that exploit the structure of our problem. We supplement our analytical results by comparing the performance of various candidate policies via synthetic and data-driven simulations.
{"title":"Best Arm Identification in Sample-path Correlated Bandits","authors":"Rudrabhotla Sri Prakash, N. Karamchandani, Sharayu Moharir","doi":"10.1109/NCC55593.2022.9806785","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806785","url":null,"abstract":"We consider the problem of best arm identification in the fixed confidence setting for a variant of the multi-arm bandit problem. In our problem, each arm is associated with two attributes, a known deterministic cost, and an unknown stochastic reward. In addition, it is known that arms with higher costs have higher rewards across every sample path. The net utility of each arm is defined as the difference between its expected reward and cost. We consider two information models, namely, the full information feedback and sequential bandit feedback. We derive a fundamental lower bound on the sample complexity of any policy and also propose policies with provable performance guarantees that exploit the structure of our problem. We supplement our analytical results by comparing the performance of various candidate policies via synthetic and data-driven simulations.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"3 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":"128549056","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/NCC55593.2022.9806782
Anish Monsley Kirupakaran, K. Yadav, R. Laskar
Unlike real-world objects which remains the same irrespective of the changes in size on a fixed/varying scale, few English alphabets become identical to each other because of case ambiguity. Recognizing alphabets becomes further complex when different characters are gesticulated with the same pattern or become similar due to the gesticulation style. The generalization ability of deep convolutional neural networks (DCNN) results in misclassifying these characters. To overcome this, we propose a two-stage recognition model that comprises of DCNN and advisor unit (AU) followed by a post-decision support module (P-DSM). It differentiates these similar characters based on actual gesticulated size and extracts features from the 1D, 2D perspective and captures the demographics in the gesticulation. This model is able to discriminate these similar characters with an accuracy of ~92% for the NITS hand gesture database. Experimenting with this on popular handwritten EMNIST database suggests that pre-processing steps followed in it make the characters lose their size information.
{"title":"Resolving the ambiguity in recognizing case-sensitive characters gesticulated in mid-air through post-decision support modules","authors":"Anish Monsley Kirupakaran, K. Yadav, R. Laskar","doi":"10.1109/NCC55593.2022.9806782","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806782","url":null,"abstract":"Unlike real-world objects which remains the same irrespective of the changes in size on a fixed/varying scale, few English alphabets become identical to each other because of case ambiguity. Recognizing alphabets becomes further complex when different characters are gesticulated with the same pattern or become similar due to the gesticulation style. The generalization ability of deep convolutional neural networks (DCNN) results in misclassifying these characters. To overcome this, we propose a two-stage recognition model that comprises of DCNN and advisor unit (AU) followed by a post-decision support module (P-DSM). It differentiates these similar characters based on actual gesticulated size and extracts features from the 1D, 2D perspective and captures the demographics in the gesticulation. This model is able to discriminate these similar characters with an accuracy of ~92% for the NITS hand gesture database. Experimenting with this on popular handwritten EMNIST database suggests that pre-processing steps followed in it make the characters lose their size information.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"47 50","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120942160","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/NCC55593.2022.9806743
Soumya Chakravarty, Aman Kumar, T. Chakravarty, Arpan Pal, R. Ghatak
In this paper, a probe-fed, transmissive metasurface lens-based antenna system in the sub-6 GHz frequency range for possible fifth-generation (5G) applications is proposed. The design facilitates for gain enhancement and phase shifter less beam tilting architecture. The structure consists of a probe-fed compact patch antenna, printed on FR4 substrate. The antenna resonates at 5.8 GHz with the −10 dB impedance bandwidth of 210 MHz extending from 5.68 till 5.89 GHz. The maximum realized gain at resonance is 2.6 dBi. The double-sided metasurface, printed on Rogers RT-Duroid 5880 substrate, is placed on top of the antenna with an air gap of 24.5 mm. This arrangement exhibits a maximum transmission gain of 7.98 dBi at resonance, with a gain enhancement of 5.38 dB in conjunction to a impedance bandwidth of 150 MHz from 5.72 - 5.87 GHz. The metasurface is polarization independent. The proposed antenna structure has been simulated for different incidence angles by rotating the metasurface around the antenna by 10° and 20°, with the resulting transmitted beam also rotating by the respective angles, thus demonstrating the beam-tilting capability of the system. This beam-tilting is achieved by only mechanically rotating the metasurface. The design has been fabricated and measured, with the experimental results matching with simulated data, with only a variation of less than 1 dB in the gain values and a shift of 50 MHz in the resonance frequency. This is attributed to variation in precise adjustment of the air-gap. The design is scalable and the process of validating the design in Frequency Range (FR2) band (24.25 - 52.6 GHz) is in progress. The proposed antenna-metasurface system is lightweight and low-cost alternative to 5G sub-6 GHz frequency band applications.
{"title":"A Metasurface-Enabled Lens Antenna Demonstrating Electromechanical Beam-Tilting for 5G Applications","authors":"Soumya Chakravarty, Aman Kumar, T. Chakravarty, Arpan Pal, R. Ghatak","doi":"10.1109/NCC55593.2022.9806743","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806743","url":null,"abstract":"In this paper, a probe-fed, transmissive metasurface lens-based antenna system in the sub-6 GHz frequency range for possible fifth-generation (5G) applications is proposed. The design facilitates for gain enhancement and phase shifter less beam tilting architecture. The structure consists of a probe-fed compact patch antenna, printed on FR4 substrate. The antenna resonates at 5.8 GHz with the −10 dB impedance bandwidth of 210 MHz extending from 5.68 till 5.89 GHz. The maximum realized gain at resonance is 2.6 dBi. The double-sided metasurface, printed on Rogers RT-Duroid 5880 substrate, is placed on top of the antenna with an air gap of 24.5 mm. This arrangement exhibits a maximum transmission gain of 7.98 dBi at resonance, with a gain enhancement of 5.38 dB in conjunction to a impedance bandwidth of 150 MHz from 5.72 - 5.87 GHz. The metasurface is polarization independent. The proposed antenna structure has been simulated for different incidence angles by rotating the metasurface around the antenna by 10° and 20°, with the resulting transmitted beam also rotating by the respective angles, thus demonstrating the beam-tilting capability of the system. This beam-tilting is achieved by only mechanically rotating the metasurface. The design has been fabricated and measured, with the experimental results matching with simulated data, with only a variation of less than 1 dB in the gain values and a shift of 50 MHz in the resonance frequency. This is attributed to variation in precise adjustment of the air-gap. The design is scalable and the process of validating the design in Frequency Range (FR2) band (24.25 - 52.6 GHz) is in progress. The proposed antenna-metasurface system is lightweight and low-cost alternative to 5G sub-6 GHz frequency band applications.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"24 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":"125924853","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/NCC55593.2022.9806722
Arpita Panigrahi, H. Sharma
Nowadays, non-contact vital sign measurement from facial videos using an RGB camera has gained popularity among researchers as it is a feasible and convenient method suitable for personalized and clinical health monitoring. This paper proposes a simple but cogent technique for heart rate (HR) estimation from the facial RGB videos. It is suggested that the integration of color channels from different color spaces derived from the RGB model can provide a better estimation of the pulsating component of arterial blood synchronous with the cardiac cycle. The shared pulse signal related to blood volumetric changes underneath the skin existing in these color signals is separated using the principal component analysis, and the resultant signal is used to determine the HR value using the short-time Fourier transform. The experiments are performed using three publicly available datasets including PURE, UBFC-rPPG, and Cohface. In the experimental analysis, the proposed technique yields lower values of the mean absolute error (MAE) and root mean square error (RMSE) for the three datasets as, PURE: MAE = 1.65 beats per minute (bpm) and RMSE = 2.9 bpm, UBFC-rPPG: MAE = 2.57 and RMSE = 5.57 bpm, and Cohface: MAE = 4.51bpm and RMSE = 6.5 bpm. These performance measures for the proposed technique are found to be lower than those obtained from some of the state-of-art methods. This study suggests that color channels from the alternative color spaces can be used for non-contact vital sign monitoring.
目前，使用RGB相机对面部视频进行非接触生命体征测量是一种可行且方便的方法，适用于个性化和临床健康监测，受到了研究人员的欢迎。本文提出了一种简单而有效的人脸RGB视频心率估计方法。结果表明，基于RGB模型的不同颜色空间的颜色通道的整合可以更好地估计与心脏周期同步的动脉血的脉动成分。利用主成分分析将这些颜色信号中存在的与皮肤下血容量变化相关的共享脉冲信号分离，并利用短时傅里叶变换将所得信号用于确定HR值。实验使用三个公开可用的数据集进行，包括PURE, UBFC-rPPG和Cohface。在实验分析中，所提出的技术对三个数据集的平均绝对误差(MAE)和均方根误差(RMSE)的值较低，分别为:PURE: MAE = 1.65 bpm和RMSE = 2.9 bpm, UBFC-rPPG: MAE = 2.57和RMSE = 5.57 bpm, Cohface: MAE = 4.51bpm和RMSE = 6.5 bpm。所提出的技术的这些性能指标被发现低于从一些最先进的方法中获得的性能指标。本研究表明，可选色彩空间中的色彩通道可用于非接触式生命体征监测。
{"title":"Non-Contact HR Extraction from Different Color Spaces Using RGB Camera","authors":"Arpita Panigrahi, H. Sharma","doi":"10.1109/NCC55593.2022.9806722","DOIUrl":"https://doi.org/10.1109/NCC55593.2022.9806722","url":null,"abstract":"Nowadays, non-contact vital sign measurement from facial videos using an RGB camera has gained popularity among researchers as it is a feasible and convenient method suitable for personalized and clinical health monitoring. This paper proposes a simple but cogent technique for heart rate (HR) estimation from the facial RGB videos. It is suggested that the integration of color channels from different color spaces derived from the RGB model can provide a better estimation of the pulsating component of arterial blood synchronous with the cardiac cycle. The shared pulse signal related to blood volumetric changes underneath the skin existing in these color signals is separated using the principal component analysis, and the resultant signal is used to determine the HR value using the short-time Fourier transform. The experiments are performed using three publicly available datasets including PURE, UBFC-rPPG, and Cohface. In the experimental analysis, the proposed technique yields lower values of the mean absolute error (MAE) and root mean square error (RMSE) for the three datasets as, PURE: MAE = 1.65 beats per minute (bpm) and RMSE = 2.9 bpm, UBFC-rPPG: MAE = 2.57 and RMSE = 5.57 bpm, and Cohface: MAE = 4.51bpm and RMSE = 6.5 bpm. These performance measures for the proposed technique are found to be lower than those obtained from some of the state-of-art methods. This study suggests that color channels from the alternative color spaces can be used for non-contact vital sign monitoring.","PeriodicalId":403870,"journal":{"name":"2022 National Conference on Communications (NCC)","volume":"24 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":"126084003","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：