Pub Date : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509810
Rawhia S. Hamouda, Mohamed A. Eldosokyl, Ahmed S. Elhggar
Radiofrequency ablation of the renal tumors considered the least invasive technique to get rid of malignancies cells. High-frequency waves in the range of 0.9 – 2.5 GHz were applied to the cancerous cells. Consequently, resistive heating was generated used to destroy the cancerous cells. In this paper, this technique had been applied to a 3D accurate model of the kidney with similar dimensions and shape including its artery, vein, and ureter. The next step was to design an RF probe to get high values of specific absorption rate for the cancerous cells and minimum values for the normal cells of the kidney. Simulation results showed that the shape of the model has the greatest effect on the resulting lesion volume and shape. In this work, the internally cooled electrode using Gil was designed from aluminum material with its tines revolved to 270° and Gaussian signal as the excitation signal.
{"title":"Radiofrequency Ablation of the Renal Tumors","authors":"Rawhia S. Hamouda, Mohamed A. Eldosokyl, Ahmed S. Elhggar","doi":"10.1109/NRSC52299.2021.9509810","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509810","url":null,"abstract":"Radiofrequency ablation of the renal tumors considered the least invasive technique to get rid of malignancies cells. High-frequency waves in the range of 0.9 – 2.5 GHz were applied to the cancerous cells. Consequently, resistive heating was generated used to destroy the cancerous cells. In this paper, this technique had been applied to a 3D accurate model of the kidney with similar dimensions and shape including its artery, vein, and ureter. The next step was to design an RF probe to get high values of specific absorption rate for the cancerous cells and minimum values for the normal cells of the kidney. Simulation results showed that the shape of the model has the greatest effect on the resulting lesion volume and shape. In this work, the internally cooled electrode using Gil was designed from aluminum material with its tines revolved to 270° and Gaussian signal as the excitation signal.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"349 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116499096","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509817
A. S. Zainud-Deen, H. Malhat, M. Badway, M. Rihan
This paper investigates the using of particle swarm optimization technique (PSO) in detecting the number and locations of failed antenna elements in a time modulated linear array (TMLA) from their damaged radiation patterns. A systematic process for radiation pattern correction is investigated. The TMLA operates by sampling the input for array elements in a switched time sequence rather than phase shift in phased antenna arrays. The failure of the array elements damages the radiation patterns which appears in different sidelobe levels (SLLs) and the locations of nulls. The TMLA elements are connected to RF switches with their on-time instants and the on-time durations sequences reconfigured to compensate the damage in the radiated pattern. The correction method involves the calculation of damaged array radiation pattern. Then, the PSO compares the damaged pattern with an optimized pattern through the minimization of the cost function. The periodic on-off sequences for array excitation are estimated using the PSO for optimum pattern. The performance of this technique is applied on 32-elements TMLA with Dolph-Chebyshev excitation. Single and multiple faults are detected and the radiation pattern are corrected using the PSO.
{"title":"Detection and Correction of Faulty Patterns in Four-Dimensional Antenna Linear Array Using Particle Swarm Optimization","authors":"A. S. Zainud-Deen, H. Malhat, M. Badway, M. Rihan","doi":"10.1109/NRSC52299.2021.9509817","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509817","url":null,"abstract":"This paper investigates the using of particle swarm optimization technique (PSO) in detecting the number and locations of failed antenna elements in a time modulated linear array (TMLA) from their damaged radiation patterns. A systematic process for radiation pattern correction is investigated. The TMLA operates by sampling the input for array elements in a switched time sequence rather than phase shift in phased antenna arrays. The failure of the array elements damages the radiation patterns which appears in different sidelobe levels (SLLs) and the locations of nulls. The TMLA elements are connected to RF switches with their on-time instants and the on-time durations sequences reconfigured to compensate the damage in the radiated pattern. The correction method involves the calculation of damaged array radiation pattern. Then, the PSO compares the damaged pattern with an optimized pattern through the minimization of the cost function. The periodic on-off sequences for array excitation are estimated using the PSO for optimum pattern. The performance of this technique is applied on 32-elements TMLA with Dolph-Chebyshev excitation. Single and multiple faults are detected and the radiation pattern are corrected using the PSO.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127872586","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509830
Mirehan A. Aboulila, Radwa K. Hamad, A. Zaki, M. Aly
In this paper, a compact dual band microstrip patch antenna is proposed for fifth generation (5G) wireless applications. This novel dual band antenna operates at the 38 and 60 GHz bands with a bandwidth around the two center frequencies (38/60 GHz) of 700 MHz and 1 GHz, respectively. The antenna consists of a semi-circular patch containing a slot, in addition to the etched two circular drained patches with optimized positions and dimensions. Moreover, a slotted partial ground is added for performance enhancement and bandwidth adjustment. The proposed antenna achieves a good performance regarding the return loss, bandwidth as well as the radiation pattern. The minimum attained return losses are −35.2 for the 38 GHz band and −36.9 dB for the 60 GHz band, while maintaining a compact antenna size. The simulated radiation pattern conforms with that needed for 5G antenna operation.
{"title":"A Dual-Band (38 – 60 GHz) Antenna Designed for Millimeter Wave Wireless Communication Systems","authors":"Mirehan A. Aboulila, Radwa K. Hamad, A. Zaki, M. Aly","doi":"10.1109/NRSC52299.2021.9509830","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509830","url":null,"abstract":"In this paper, a compact dual band microstrip patch antenna is proposed for fifth generation (5G) wireless applications. This novel dual band antenna operates at the 38 and 60 GHz bands with a bandwidth around the two center frequencies (38/60 GHz) of 700 MHz and 1 GHz, respectively. The antenna consists of a semi-circular patch containing a slot, in addition to the etched two circular drained patches with optimized positions and dimensions. Moreover, a slotted partial ground is added for performance enhancement and bandwidth adjustment. The proposed antenna achieves a good performance regarding the return loss, bandwidth as well as the radiation pattern. The minimum attained return losses are −35.2 for the 38 GHz band and −36.9 dB for the 60 GHz band, while maintaining a compact antenna size. The simulated radiation pattern conforms with that needed for 5G antenna operation.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"785 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123281938","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509827
Mohamed Abdelraheem, Reham M. Al-Hashmy, U. S. Mohamed
In this paper, we study the throughput enhancement achieved by cooperative communication technique in cognitive radio networks for different global objectives and constraints. The secondary network coordinator distributes the nodes among the available channels and pairs them in a cooperative collation to enhance their transmission characteristics. The coordinator objective is to maximize the total throughput or to achieve a fair distribution of the available resources under some minimum throughput demand constraints. We formulate the optimization problems for different throughput objectives in the cooperative and non-cooperative modes. The results show a noticeable enhancement in the total throughput achieved by the network as well as the slow node in the cooperative mode compared to the non-cooperative one. Also, the proportional fairness, and maximizing the minimum user throughput objectives gives a fair distribution for the available resources which significantly enhances the throughput of the slow nodes compared to the case when the objective is to maximize the total throughput.
{"title":"Quantification of Throughput Enhancement using Cooperative Communication in Cognitive Radio Networks","authors":"Mohamed Abdelraheem, Reham M. Al-Hashmy, U. S. Mohamed","doi":"10.1109/NRSC52299.2021.9509827","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509827","url":null,"abstract":"In this paper, we study the throughput enhancement achieved by cooperative communication technique in cognitive radio networks for different global objectives and constraints. The secondary network coordinator distributes the nodes among the available channels and pairs them in a cooperative collation to enhance their transmission characteristics. The coordinator objective is to maximize the total throughput or to achieve a fair distribution of the available resources under some minimum throughput demand constraints. We formulate the optimization problems for different throughput objectives in the cooperative and non-cooperative modes. The results show a noticeable enhancement in the total throughput achieved by the network as well as the slow node in the cooperative mode compared to the non-cooperative one. Also, the proportional fairness, and maximizing the minimum user throughput objectives gives a fair distribution for the available resources which significantly enhances the throughput of the slow nodes compared to the case when the objective is to maximize the total throughput.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130295322","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509819
A. S. Zainud-Deen, H. Malhat, M. Badway, M. Rihan
In this paper, a time-modulated antenna array (TMAA) include of 16-half-wavelength dipole elements are studied under different time switching schemes. The 16-dipoles TMAA are arranged in a parabolic trace separated by λo/2 with each dipole connected to RF switch. The TMAA is fed via half-wavelength dipole placed at 10λo from the parabolic trace. Each time switching scheme with switching rate, fp, produces beam at the fundamental-frequency, fo, and other beams at the harmonic-frequencies fo± mfp. The switching time scheme introduces an extra design variable to control the radiation patterns at the harmonic frequencies. The patterns at the fundamental and sideband frequencies are all simulated using the method of moments (MoM) while taking into account the element radiation pattern and mutual coupling. A comparison between the MoM full wave simulation and the TMAA of isotropic elements fed by the same time switching schemes is introduced. Numerical results depict the efficiency MoM in the analysis of TMAAs with high accuracy.
{"title":"Full-wave Simulation of Time-modulated Parabolic Linear Array Using the Method of Moments","authors":"A. S. Zainud-Deen, H. Malhat, M. Badway, M. Rihan","doi":"10.1109/NRSC52299.2021.9509819","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509819","url":null,"abstract":"In this paper, a time-modulated antenna array (TMAA) include of 16-half-wavelength dipole elements are studied under different time switching schemes. The 16-dipoles TMAA are arranged in a parabolic trace separated by λo/2 with each dipole connected to RF switch. The TMAA is fed via half-wavelength dipole placed at 10λo from the parabolic trace. Each time switching scheme with switching rate, fp, produces beam at the fundamental-frequency, fo, and other beams at the harmonic-frequencies fo± mfp. The switching time scheme introduces an extra design variable to control the radiation patterns at the harmonic frequencies. The patterns at the fundamental and sideband frequencies are all simulated using the method of moments (MoM) while taking into account the element radiation pattern and mutual coupling. A comparison between the MoM full wave simulation and the TMAA of isotropic elements fed by the same time switching schemes is introduced. Numerical results depict the efficiency MoM in the analysis of TMAAs with high accuracy.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115739087","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509813
Karam M. Ebrahiem, H. Soliman, S. Abuelenin, H. El-Badawy
This paper studies the applications of Deep Learning (branch of Machine Learning) in 5G wireless communication systems. Deep Learning requires having large sets of data for training and testing purposes. Obtaining such large datasets through measurement campaigns is a challenging and costly task. Therefore, it is a common practice to use synthesized data. The aim of the current paper is to survey different applications of deep learning in 5G systems, and more specifically, that implementing the massive multiple input multiple output (mMIMO) using deep learning, for estimating the wideband mMIMO channel, and for beamforming co-operative transmission. Then, methods for dataset generation for such systems are covered and reviewed. The required datasets for deep-learning may be constructed via ray-tracing simulators. Illustration of the methodology with some deployment scenarios relying on Remcom wireless InSite® ray-tracing simulator are introduced. These scenarios are used to provide the required datasets to be used for deep learning. Then, several directions are proposed for future work that are based on sensing the environment type, (Indoor/Outdoor), and jointly estimating the channel vector, Direction-of-Arrival (DoA), Direction of Departure (DoD), and Rx point power allocation. In a manner similar to adaptive beamforming, the RF radiation pattern can be adapted according to the time-varying DoA and DoD, and estimated channel.
{"title":"A Deep Learning Approach for Channel Estimation in 5G Wireless Communications","authors":"Karam M. Ebrahiem, H. Soliman, S. Abuelenin, H. El-Badawy","doi":"10.1109/NRSC52299.2021.9509813","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509813","url":null,"abstract":"This paper studies the applications of Deep Learning (branch of Machine Learning) in 5G wireless communication systems. Deep Learning requires having large sets of data for training and testing purposes. Obtaining such large datasets through measurement campaigns is a challenging and costly task. Therefore, it is a common practice to use synthesized data. The aim of the current paper is to survey different applications of deep learning in 5G systems, and more specifically, that implementing the massive multiple input multiple output (mMIMO) using deep learning, for estimating the wideband mMIMO channel, and for beamforming co-operative transmission. Then, methods for dataset generation for such systems are covered and reviewed. The required datasets for deep-learning may be constructed via ray-tracing simulators. Illustration of the methodology with some deployment scenarios relying on Remcom wireless InSite® ray-tracing simulator are introduced. These scenarios are used to provide the required datasets to be used for deep learning. Then, several directions are proposed for future work that are based on sensing the environment type, (Indoor/Outdoor), and jointly estimating the channel vector, Direction-of-Arrival (DoA), Direction of Departure (DoD), and Rx point power allocation. In a manner similar to adaptive beamforming, the RF radiation pattern can be adapted according to the time-varying DoA and DoD, and estimated channel.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131528921","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509808
Sarah. Elgiddawy, H. Malhat, S. Zainud-Deen, A. Ibrahim, Hisham Hamed
This paper proposes a reconfigurable polarization square microstrip patch antenna (SMSPA) using plasma and its multiple-input multiple-output (MIMO) for 5G wireless networks. The SMSPA has two square etched boxes with asymmetric length and positions from the SMSPA center along its diagonal. The single antenna has an overall size of 96 mm × 96 mm × 4.6 mm (0.78 λ × 0.78 λ × 0.0377 λ). The two square boxes length and position are optimized for achieving minimum axial-ratio of 0.608 dB dB at 2.44 GHz. Four polarization cases are achieved, case (1) and case (2) for left-hand and right-hand circular polarization (CP), while case (3) and case (4) for linear polarization. The overall dimensions of the proposed 4-port (2×2) MIMO antenna are 160 mm × 160 mm × 4.6 mm. The proposed MIMO antenna layout guarantee compact size with spacing distance 0.25 lamda (30.5 mm) between MIMO elements with isolation higher than 22.44 dB and an envelope correlation coefficient ECC lower than 0.015 between elements.
提出了一种基于等离子体及其多输入多输出(MIMO)的可重构极化方形微带贴片天线(SMSPA)，用于5G无线网络。SMSPA有两个方形蚀刻盒，其长度和位置不对称，从SMSPA中心沿其对角线开始。单天线的整体尺寸为96 mm × 96 mm × 4.6 mm (0.78 λ × 0.78 λ × 0.0377 λ)。两个方盒的长度和位置进行了优化，以实现2.44 GHz时0.608 dB dB的最小轴向比。实现了四种极化情况，情况(1)和情况(2)为左圆极化和右圆极化(CP)，情况(3)和情况(4)为线极化。建议的4端口(2×2) MIMO天线的整体尺寸为160 mm × 160 mm × 4.6 mm。所提出的MIMO天线布局保证了MIMO元件之间间距为0.25 lamda (30.5 mm)的紧凑尺寸，隔离度高于22.44 dB，元件之间的包络相关系数ECC低于0.015。
{"title":"Compact Reconfigurable Polarization Plasma Square Microstrip Patch MIMO Antenna for 5G Wireless Applications","authors":"Sarah. Elgiddawy, H. Malhat, S. Zainud-Deen, A. Ibrahim, Hisham Hamed","doi":"10.1109/NRSC52299.2021.9509808","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509808","url":null,"abstract":"This paper proposes a reconfigurable polarization square microstrip patch antenna (SMSPA) using plasma and its multiple-input multiple-output (MIMO) for 5G wireless networks. The SMSPA has two square etched boxes with asymmetric length and positions from the SMSPA center along its diagonal. The single antenna has an overall size of 96 mm × 96 mm × 4.6 mm (0.78 λ × 0.78 λ × 0.0377 λ). The two square boxes length and position are optimized for achieving minimum axial-ratio of 0.608 dB dB at 2.44 GHz. Four polarization cases are achieved, case (1) and case (2) for left-hand and right-hand circular polarization (CP), while case (3) and case (4) for linear polarization. The overall dimensions of the proposed 4-port (2×2) MIMO antenna are 160 mm × 160 mm × 4.6 mm. The proposed MIMO antenna layout guarantee compact size with spacing distance 0.25 lamda (30.5 mm) between MIMO elements with isolation higher than 22.44 dB and an envelope correlation coefficient ECC lower than 0.015 between elements.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133018879","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509823
Mohamed S. Ghoneim, Amr Mohammaden, L. Said, A. Madian, A. Radwan, A. Eltawil
This paper presents a comparative study of different human skin impedance models using meta-heuristic optimization Flower Pollination Algorithm (FPA). Four different models: Montague, Tregear, Lykken, and modified Montague skin models were used. There are two categories of electrical modelling; the RC-based model and the CPE-based model. The RC-based model focuses on skin stratification, while the CPE-based model focuses on the skin’s biological properties. Six samples were taken as an experiment to acquire the skin impedance data to find the most accurate fitting model.
{"title":"A Comparative Study of Different Human Skin Impedance Models","authors":"Mohamed S. Ghoneim, Amr Mohammaden, L. Said, A. Madian, A. Radwan, A. Eltawil","doi":"10.1109/NRSC52299.2021.9509823","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509823","url":null,"abstract":"This paper presents a comparative study of different human skin impedance models using meta-heuristic optimization Flower Pollination Algorithm (FPA). Four different models: Montague, Tregear, Lykken, and modified Montague skin models were used. There are two categories of electrical modelling; the RC-based model and the CPE-based model. The RC-based model focuses on skin stratification, while the CPE-based model focuses on the skin’s biological properties. Six samples were taken as an experiment to acquire the skin impedance data to find the most accurate fitting model.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075442","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509825
S. El-Khamy, A. Al-Kabbany, Shimaa El-bana
MobileNet is a light-weight neural network model that has facilitated harnessing the power of deep learning on mobile devices. The advances in pervasive computing and the ever-increasing interest in deep learning has resulted in a growing research attention on the enhancement of the MobileNet architecture. Beside the enhancement in convolution layers, recent literature has featured new directions for implementing the pooling layers. In this work, we propose a new model based on the MobileNet-V1 architecture, and we investigate the impact of wavelet pooling on the performance of the proposed model. While traditional neighborhood pooling can result in information loss, which negatively impacts any succeeding feature extraction, wavelet pooling allows us to utilize spectral information which is useful in most image processing tasks. On two widely adopted datasets, we evaluated the performance of the proposed model, and compared to the baseline MobileNet, we attained a 10% and a 16% increase in classification accuracy on CIFAR-10 and CIFAR-100 respectively. We also evaluated a shallow version of the proposed architecture with wavelet pooling, and we showed that it maintained the classification accuracy either higher than, or <1% less than, the deep versions of MobileNet while decreasing the number of model parameters by almost 40%.
{"title":"Going Shallower with MobileNets: On the Impact of Wavelet Pooling","authors":"S. El-Khamy, A. Al-Kabbany, Shimaa El-bana","doi":"10.1109/NRSC52299.2021.9509825","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509825","url":null,"abstract":"MobileNet is a light-weight neural network model that has facilitated harnessing the power of deep learning on mobile devices. The advances in pervasive computing and the ever-increasing interest in deep learning has resulted in a growing research attention on the enhancement of the MobileNet architecture. Beside the enhancement in convolution layers, recent literature has featured new directions for implementing the pooling layers. In this work, we propose a new model based on the MobileNet-V1 architecture, and we investigate the impact of wavelet pooling on the performance of the proposed model. While traditional neighborhood pooling can result in information loss, which negatively impacts any succeeding feature extraction, wavelet pooling allows us to utilize spectral information which is useful in most image processing tasks. On two widely adopted datasets, we evaluated the performance of the proposed model, and compared to the baseline MobileNet, we attained a 10% and a 16% increase in classification accuracy on CIFAR-10 and CIFAR-100 respectively. We also evaluated a shallow version of the proposed architecture with wavelet pooling, and we showed that it maintained the classification accuracy either higher than, or <1% less than, the deep versions of MobileNet while decreasing the number of model parameters by almost 40%.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131045119","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 : 2021-07-27DOI: 10.1109/NRSC52299.2021.9509811
S. I. Abd El-Rahman, A. Attiya
In this paper we present the analysis and design of a dual band cavity baked antenna element for ka band satellite communication systems. This element represent the basic block for a planar antenna array to be used for on-move satellite system. The proposed cavity backed antenna is composed of 3x3 circular apertures on a conducting plane. These circular apertures are fed by a rectangular cavity. This cavity is fed through a square aperture located at the bottom side. This aperture is fed by two cascaded rectangular cavities corresponding to the lower and upper frequency bands. These cascaded cavities are fed by two orthogonal rectangular waveguide sections. These orthogonal waveguide arrangement introduces orthogonal polarizations for the upper and lower frequency bands. The analysis of the proposed cavity backed antenna is developed by using HFSS and verified by using CST. A 2x2 array of this cavity backed element is also investigated. It is found that the closed cavity configuration reduces the mutual coupling between the nearby elements.
{"title":"Dual-Band Cavity-Backed Ka-Band Antenna for Satellite Communication","authors":"S. I. Abd El-Rahman, A. Attiya","doi":"10.1109/NRSC52299.2021.9509811","DOIUrl":"https://doi.org/10.1109/NRSC52299.2021.9509811","url":null,"abstract":"In this paper we present the analysis and design of a dual band cavity baked antenna element for ka band satellite communication systems. This element represent the basic block for a planar antenna array to be used for on-move satellite system. The proposed cavity backed antenna is composed of 3x3 circular apertures on a conducting plane. These circular apertures are fed by a rectangular cavity. This cavity is fed through a square aperture located at the bottom side. This aperture is fed by two cascaded rectangular cavities corresponding to the lower and upper frequency bands. These cascaded cavities are fed by two orthogonal rectangular waveguide sections. These orthogonal waveguide arrangement introduces orthogonal polarizations for the upper and lower frequency bands. The analysis of the proposed cavity backed antenna is developed by using HFSS and verified by using CST. A 2x2 array of this cavity backed element is also investigated. It is found that the closed cavity configuration reduces the mutual coupling between the nearby elements.","PeriodicalId":231431,"journal":{"name":"2021 38th National Radio Science Conference (NRSC)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115167586","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：