Pub Date : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182243
A. Anand, S. Nishanth, P. Vamsi Krishna, S. Krishna, T. Anjali
It is a common belief that with the advent of technology the livelihood of people in a developing community tends to get better over time. It may be true in many cases but in cases of domestic and sexual violence against women there have been no significant development. With the benefit of women, elders and basically any person who is in distress in mind and also the need for a socially centralized social network we have put forward an idea which may help curb rising crime rates by solving various issues which have been unattended by existing methodologies. Ally is a distress signal application with newer and innovative approach to solving the age old problem of rapid redressal. Existing models fail to identify the location of a person if there is no network coverage thus failing ultimately which is why we have implemented a feature to constantly track the location of a person and give the updates to guardians on an half-hourly basis. Also existing models rely on the police or the guardians to help the person in distress whereas we have taken it a step forward to crowd source help in the hour of need by sending distress signal to all nearby Ally app users within a kilometer.
{"title":"Ally - A Crowdsourced Distress Signal App","authors":"A. Anand, S. Nishanth, P. Vamsi Krishna, S. Krishna, T. Anjali","doi":"10.1109/ICCSP48568.2020.9182243","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182243","url":null,"abstract":"It is a common belief that with the advent of technology the livelihood of people in a developing community tends to get better over time. It may be true in many cases but in cases of domestic and sexual violence against women there have been no significant development. With the benefit of women, elders and basically any person who is in distress in mind and also the need for a socially centralized social network we have put forward an idea which may help curb rising crime rates by solving various issues which have been unattended by existing methodologies. Ally is a distress signal application with newer and innovative approach to solving the age old problem of rapid redressal. Existing models fail to identify the location of a person if there is no network coverage thus failing ultimately which is why we have implemented a feature to constantly track the location of a person and give the updates to guardians on an half-hourly basis. Also existing models rely on the police or the guardians to help the person in distress whereas we have taken it a step forward to crowd source help in the hour of need by sending distress signal to all nearby Ally app users within a kilometer.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117158839","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182294
B. Behera, S. Varshney, M. Mohanty
In recent scenario realization of a high-capacity transmission system is one of the biggest challenges in the optical domain. Space-division multiplexing (SDM) and Mode-division multiplexing are the new age techniques those claim to establish high-speed transmission using Few-mode fibers (FMFs). FMFs have the potential to drastically improve the fiber capacity by enabling SDM and MDM. In this paper, we have proposed the design of an FMF with a compound refractive index profile to support and guide the first seven LP modes (LP01, LP11, LP12, LP02, LP21, LP31, LP41). The fiber parameters are examined to meet the design conditions to transmit seven-LP modes effectively with low bending loss, large effective-area, and a large-effective-index difference (Δn-eff) between the LP-modes to limit the mode coupling between the spatial modes for weakly-coupled MDM transmission.
{"title":"Design of Seven-LP-Mode Compound-Index Few-Mode-Fiber for Mode-Division-Multiplexing Transmission","authors":"B. Behera, S. Varshney, M. Mohanty","doi":"10.1109/ICCSP48568.2020.9182294","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182294","url":null,"abstract":"In recent scenario realization of a high-capacity transmission system is one of the biggest challenges in the optical domain. Space-division multiplexing (SDM) and Mode-division multiplexing are the new age techniques those claim to establish high-speed transmission using Few-mode fibers (FMFs). FMFs have the potential to drastically improve the fiber capacity by enabling SDM and MDM. In this paper, we have proposed the design of an FMF with a compound refractive index profile to support and guide the first seven LP modes (LP01, LP11, LP12, LP02, LP21, LP31, LP41). The fiber parameters are examined to meet the design conditions to transmit seven-LP modes effectively with low bending loss, large effective-area, and a large-effective-index difference (Δn-eff) between the LP-modes to limit the mode coupling between the spatial modes for weakly-coupled MDM transmission.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123128228","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182259
R. Savitha, Vasudevan Karuppiah
This paper proposes a miniature, dual resonant filter to suppress the common-mode noise for high-speed digital circuit applications. This is a DGS(Defected Ground Structure) based filter. The uniqueness of this paper is that the single unit-cell DGS produces dual resonance. Both the two resonance are nearer to each other to provide wide stop bandwidth for common-mode noise. From the simulated results it is evident that the proposed filter allows the differential signal and attenuates the common-mode noise over the frequency band of interest. The filter is compact and it can be fabricated by using a standard PCB fabrication process.
{"title":"Dual Resonant DGS based Common-Mode Filter for High-Speed Digital Circuit Applications","authors":"R. Savitha, Vasudevan Karuppiah","doi":"10.1109/ICCSP48568.2020.9182259","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182259","url":null,"abstract":"This paper proposes a miniature, dual resonant filter to suppress the common-mode noise for high-speed digital circuit applications. This is a DGS(Defected Ground Structure) based filter. The uniqueness of this paper is that the single unit-cell DGS produces dual resonance. Both the two resonance are nearer to each other to provide wide stop bandwidth for common-mode noise. From the simulated results it is evident that the proposed filter allows the differential signal and attenuates the common-mode noise over the frequency band of interest. The filter is compact and it can be fabricated by using a standard PCB fabrication process.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"7 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123318312","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182053
N.T Bushra Abdulla, K. A. Navas
Protection of data still remains as an anxiety to the researchers in spite of large number of techniques have been proposed in the literature to protect digital rights and authentication of documents. One of the methods to provide security to the right holders is digital watermarking; the technique of hiding secret message in the document to ensure authentication. Effectiveness of Watermarking depends on the robustness, imperceptibility and security. Presence of online data including audio, images, videos and diagrams in binary representation is fast increasing. New digitization techniques are capable of successfully attacking earlier watermarking techniques. This demands the need of developing new watermarking techniques to prevent the attacks on water-marked images. We attempted in this work to examine recently reported watermarking techniques in the literature which are claimed to be meritorious by the authors In this paper we discuss the merits and inefficiencies of the recently reported techniques which claim many merits. Identification of the room for research will be helpful to the researches to attempt on the development of new techniques.
{"title":"High Security Watermarking Techniques for Digital Rights Management: A Review","authors":"N.T Bushra Abdulla, K. A. Navas","doi":"10.1109/ICCSP48568.2020.9182053","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182053","url":null,"abstract":"Protection of data still remains as an anxiety to the researchers in spite of large number of techniques have been proposed in the literature to protect digital rights and authentication of documents. One of the methods to provide security to the right holders is digital watermarking; the technique of hiding secret message in the document to ensure authentication. Effectiveness of Watermarking depends on the robustness, imperceptibility and security. Presence of online data including audio, images, videos and diagrams in binary representation is fast increasing. New digitization techniques are capable of successfully attacking earlier watermarking techniques. This demands the need of developing new watermarking techniques to prevent the attacks on water-marked images. We attempted in this work to examine recently reported watermarking techniques in the literature which are claimed to be meritorious by the authors In this paper we discuss the merits and inefficiencies of the recently reported techniques which claim many merits. Identification of the room for research will be helpful to the researches to attempt on the development of new techniques.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124717438","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182149
Binish Fatimah, A. Javali, Haaris Ansar, B. Harshitha, Hemant Kumar
Solving an arithmetic problem is a complex task which involves fact retrieval, memory, sequencing and decision making. Automatic detection of such an activity from EEG signals will help in understanding of brain response to these cognitive tasks. In this work, we propose a mental arithmetic task detection algorithm from a single lead EEG signal. Fourier Decomposition method is used to decompose the signal into M uniform sub-bands and features, like energy, entropy, and variance, are computed from each of these sub-bands. Kruskal-Wallis method has been used to select only the statistically relevant features. These selected features are, then, used to classify the given EEG dataset into two classes using support vector machine with cubic kernel. To validate the efficacy of the proposed algorithm, simulation results are presented using dataset available on MIT PhysioNet, titled EEG during mental arithmetic task.
{"title":"Mental Arithmetic Task Classification using Fourier Decomposition Method","authors":"Binish Fatimah, A. Javali, Haaris Ansar, B. Harshitha, Hemant Kumar","doi":"10.1109/ICCSP48568.2020.9182149","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182149","url":null,"abstract":"Solving an arithmetic problem is a complex task which involves fact retrieval, memory, sequencing and decision making. Automatic detection of such an activity from EEG signals will help in understanding of brain response to these cognitive tasks. In this work, we propose a mental arithmetic task detection algorithm from a single lead EEG signal. Fourier Decomposition method is used to decompose the signal into M uniform sub-bands and features, like energy, entropy, and variance, are computed from each of these sub-bands. Kruskal-Wallis method has been used to select only the statistically relevant features. These selected features are, then, used to classify the given EEG dataset into two classes using support vector machine with cubic kernel. To validate the efficacy of the proposed algorithm, simulation results are presented using dataset available on MIT PhysioNet, titled EEG during mental arithmetic task.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124814196","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182045
Athira Devaraj, Aswathy K. Nair
This research work focuses on identifying a specific hand gesture from the given EMG signal, acquired by sensor-based band. Surface EMG and machine learning techniques are used for the identification and classification purpose. The raw EMG signal captured using the sensor is initially passed through suitable preprocessing steps to avoid the noise artifacts. Followed by this, 8 different time-domain features are collected from these raw EMG signals, using which a feature matrix is created. SVM and KNN are the machine learning classifiers used here. The entire system is implemented in MATLAB 2019a. Using these methods, a promising accuracy of 93% is obtained through KNN and an accuracy of 83% using SVM.
{"title":"Hand Gesture Signal Classification using Machine Learning","authors":"Athira Devaraj, Aswathy K. Nair","doi":"10.1109/ICCSP48568.2020.9182045","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182045","url":null,"abstract":"This research work focuses on identifying a specific hand gesture from the given EMG signal, acquired by sensor-based band. Surface EMG and machine learning techniques are used for the identification and classification purpose. The raw EMG signal captured using the sensor is initially passed through suitable preprocessing steps to avoid the noise artifacts. Followed by this, 8 different time-domain features are collected from these raw EMG signals, using which a feature matrix is created. SVM and KNN are the machine learning classifiers used here. The entire system is implemented in MATLAB 2019a. Using these methods, a promising accuracy of 93% is obtained through KNN and an accuracy of 83% using SVM.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124968572","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182049
Divya Sasidharan, G. Venugopal
Muscle fatigue is a common experience for all age groups. In this work a model to fit the fatigue and non fatigue surface electromyography (sEMG) signals using sum of sines is proposed. Signals are recorded from Biceps Brachii muscle of five healthy volunteers until fatigue using a well defined protocol. The fatigue and non fatigue conditions are analysed separately by non linear dynamical model. The sum of sine model is selected for fitting the signals. The sin7 model is found to be the best non linear fit for non fatigue condition and sin8 for fatigue condition. The Root Mean Square Error (RMSE) of fatigue condition reduced by 4 from sin7 model to sin8 model. Also the fatigue signal tends to be periodic than non fatigue signal. This method may be further extended to the non linear analysis of muscular disorders.
{"title":"Analysis of Surface EMG Signals under Fatigue Conditions using Sum of Sines Models","authors":"Divya Sasidharan, G. Venugopal","doi":"10.1109/ICCSP48568.2020.9182049","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182049","url":null,"abstract":"Muscle fatigue is a common experience for all age groups. In this work a model to fit the fatigue and non fatigue surface electromyography (sEMG) signals using sum of sines is proposed. Signals are recorded from Biceps Brachii muscle of five healthy volunteers until fatigue using a well defined protocol. The fatigue and non fatigue conditions are analysed separately by non linear dynamical model. The sum of sine model is selected for fitting the signals. The sin7 model is found to be the best non linear fit for non fatigue condition and sin8 for fatigue condition. The Root Mean Square Error (RMSE) of fatigue condition reduced by 4 from sin7 model to sin8 model. Also the fatigue signal tends to be periodic than non fatigue signal. This method may be further extended to the non linear analysis of muscular disorders.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123568428","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182451
S. Bhimavarapu, P. Vinitha
Infrastructural defects to determine the sicknesses of the crop utilized within the agricultural quarter improvising special standards and solutions. The diagnosis of the different scenario and cause for diseases had been let to indulge in the current mobile technology suitable for the controlling of the disease using wireless scenario or switches. Our paper imparts on the current existing design technique as SVM, providing the mathematical and functional aspects of the design ensuring to improve the locating diseases using test and train scenarios. The setup for the SVM model is also taken in account for considerations of the different data sets of the images related different crops noting to provide the correct information of the problem scenario. These problems might exist due to natural or man-made for each set of the disease observed and identified. Hence recognition of the diseases would suffice the design criteria ensuring different parametric criteria for each level of training and test set provided. To ensure the novel and more accurate scenario different set of data set have been in consideration for different test and train images providing higher and reliable accuracy for the proposed model as part of CNN applying as Transfer learning. Different scenarios of the plant disease image have been considered as data set of 15617 images under restricted cases improvising a train model on CNN with transfer learning. The accuracy observed from the design model is observed 98.56% on the considered test vectors providing required feasibility. These designs also provide a better and convenient solutions for the people utilizing the current technologies.
{"title":"Analysis and Characterization of Plant Diseases using Transfer Learning","authors":"S. Bhimavarapu, P. Vinitha","doi":"10.1109/ICCSP48568.2020.9182451","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182451","url":null,"abstract":"Infrastructural defects to determine the sicknesses of the crop utilized within the agricultural quarter improvising special standards and solutions. The diagnosis of the different scenario and cause for diseases had been let to indulge in the current mobile technology suitable for the controlling of the disease using wireless scenario or switches. Our paper imparts on the current existing design technique as SVM, providing the mathematical and functional aspects of the design ensuring to improve the locating diseases using test and train scenarios. The setup for the SVM model is also taken in account for considerations of the different data sets of the images related different crops noting to provide the correct information of the problem scenario. These problems might exist due to natural or man-made for each set of the disease observed and identified. Hence recognition of the diseases would suffice the design criteria ensuring different parametric criteria for each level of training and test set provided. To ensure the novel and more accurate scenario different set of data set have been in consideration for different test and train images providing higher and reliable accuracy for the proposed model as part of CNN applying as Transfer learning. Different scenarios of the plant disease image have been considered as data set of 15617 images under restricted cases improvising a train model on CNN with transfer learning. The accuracy observed from the design model is observed 98.56% on the considered test vectors providing required feasibility. These designs also provide a better and convenient solutions for the people utilizing the current technologies.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125569223","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182270
K. Karunya, S. Aarthy, R. Karthika, L. Jegatha Deborah
An important criterion in teaching is to analyze how well the teaching has been effective for the student’s. In order to do such analysis student’s feedback is obtained which would depict the quality and quantity of teaching. The existing evaluation technique tells about the opinion levels but does not clearly inform is it necessary to bring immediate changes in teaching or can proceed with the current teaching strategy. To address this drawback an automated ideology is proposed to initially analyze the student feedback comments and further based on the analysis introduce a recommendation system that would give a clear idea whether to bring in changes or proceed with the currently adopted teaching technique. This would provide tutors insight about opinion and allow them to make professionally sound decision so as to upgrade the performance of students.
{"title":"Analysis of Student Feedback and Recommendation to Tutors","authors":"K. Karunya, S. Aarthy, R. Karthika, L. Jegatha Deborah","doi":"10.1109/ICCSP48568.2020.9182270","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182270","url":null,"abstract":"An important criterion in teaching is to analyze how well the teaching has been effective for the student’s. In order to do such analysis student’s feedback is obtained which would depict the quality and quantity of teaching. The existing evaluation technique tells about the opinion levels but does not clearly inform is it necessary to bring immediate changes in teaching or can proceed with the current teaching strategy. To address this drawback an automated ideology is proposed to initially analyze the student feedback comments and further based on the analysis introduce a recommendation system that would give a clear idea whether to bring in changes or proceed with the currently adopted teaching technique. This would provide tutors insight about opinion and allow them to make professionally sound decision so as to upgrade the performance of students.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"71 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126245520","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 : 2020-07-01DOI: 10.1109/ICCSP48568.2020.9182336
C. Sidharth, S. Hiremath, S. K. Patra
Millimeter Wave (mmWave) and massive MIMO (Multiple Input Multiple Output) are promising solutions for 5G communications. Hybrid precoding architecture (analog and digital) is generally employed to resolve high hardware complexity and energy consumption issues. The current hybrid precoding architectures are computationally complex. This proposes a novel deep neural network based precoding architecture named ‘ComcepNet’. The network combines the features of Complex Convolution blocks and Inception Network. The network is observed to deliver superior performance in terms of accuracy and achievable datarate compared to the present Autoprecoder network.
{"title":"Deep Learning based Hybrid Precoding for mmWave Massive MIMO system using ComcepNet","authors":"C. Sidharth, S. Hiremath, S. K. Patra","doi":"10.1109/ICCSP48568.2020.9182336","DOIUrl":"https://doi.org/10.1109/ICCSP48568.2020.9182336","url":null,"abstract":"Millimeter Wave (mmWave) and massive MIMO (Multiple Input Multiple Output) are promising solutions for 5G communications. Hybrid precoding architecture (analog and digital) is generally employed to resolve high hardware complexity and energy consumption issues. The current hybrid precoding architectures are computationally complex. This proposes a novel deep neural network based precoding architecture named ‘ComcepNet’. The network combines the features of Complex Convolution blocks and Inception Network. The network is observed to deliver superior performance in terms of accuracy and achievable datarate compared to the present Autoprecoder network.","PeriodicalId":321133,"journal":{"name":"2020 International Conference on Communication and Signal Processing (ICCSP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126377142","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}