Pub Date : 2019-03-07DOI: 10.1109/SPIN.2019.8711621
Ankur Lohachab, A. Jangra
Vision of Internet of Things (IoT) augments next generation Internet by promoting harmonious interaction between human societies and connected devices. Conventional way of connecting IoT devices is to build a global infrastructure-based environment for establishing relationships among objects, activities, people, places, and technologies. Adequate management of IoT-based systems in smart cities and communities lies not only in funneling, processing, and sensing of data, but also in the expedited mechanisms of networking for the IoT devices. More imperative demand of ubiquity and real-time operations compels for the quest of decentralized networking-based IoT infrastructure. Opportunistic Networks (OppNets) and Computing are new paradigms for decentralized-based computing. Despite the fact that IoT and OppNets are not correlated with each other and are considered as independently unique networking environments, this article proposes a novel Opportunistic IoT network architecture that collaborates the layers of IoT with OppNets. Moreover, how to create an efficient Opportunistic network by exploring inherent relationship between humans and smart things is one of the fundamental problems among Opportunistic communities. Considering these facts, this paper reviews several ground-breaking applications, imminent challenges, architecture of Opportunistic networks based on IoT environment, and taxonomy of OppNets forwarding algorithms. This article also correlates and measures the performance of OppNets forwarding algorithms in realistic model of smart city with the help of ‘THE ONE’ simulator.
{"title":"Opportunistic Internet of Things (IoT): Demystifying the Effective Possibilities of Opportunisitc Networks Towards IoT","authors":"Ankur Lohachab, A. Jangra","doi":"10.1109/SPIN.2019.8711621","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711621","url":null,"abstract":"Vision of Internet of Things (IoT) augments next generation Internet by promoting harmonious interaction between human societies and connected devices. Conventional way of connecting IoT devices is to build a global infrastructure-based environment for establishing relationships among objects, activities, people, places, and technologies. Adequate management of IoT-based systems in smart cities and communities lies not only in funneling, processing, and sensing of data, but also in the expedited mechanisms of networking for the IoT devices. More imperative demand of ubiquity and real-time operations compels for the quest of decentralized networking-based IoT infrastructure. Opportunistic Networks (OppNets) and Computing are new paradigms for decentralized-based computing. Despite the fact that IoT and OppNets are not correlated with each other and are considered as independently unique networking environments, this article proposes a novel Opportunistic IoT network architecture that collaborates the layers of IoT with OppNets. Moreover, how to create an efficient Opportunistic network by exploring inherent relationship between humans and smart things is one of the fundamental problems among Opportunistic communities. Considering these facts, this paper reviews several ground-breaking applications, imminent challenges, architecture of Opportunistic networks based on IoT environment, and taxonomy of OppNets forwarding algorithms. This article also correlates and measures the performance of OppNets forwarding algorithms in realistic model of smart city with the help of ‘THE ONE’ simulator.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127144108","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711732
Tanu Agarwal, A. Garg, Bhupendra Singh
In this paper, a novel frequency reconfigurable microstrip patch antenna with three parasitic patches has been proposed. This switchable band characteristics is achieved by introducing three PIN DIODES between the main patch and three parasitic patches. By different combination of PIN DIODES singl band, dual band and triple band characteristics can be achieved. FR4 Epoxy substrate with dielectric constant 4.4 and tangent loss 0.025 has been used. For the antenna simulation CST MW Studio software has been used.
{"title":"A Novel Reconfigurable Patch Antenna with Parasitic Patch","authors":"Tanu Agarwal, A. Garg, Bhupendra Singh","doi":"10.1109/SPIN.2019.8711732","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711732","url":null,"abstract":"In this paper, a novel frequency reconfigurable microstrip patch antenna with three parasitic patches has been proposed. This switchable band characteristics is achieved by introducing three PIN DIODES between the main patch and three parasitic patches. By different combination of PIN DIODES singl band, dual band and triple band characteristics can be achieved. FR4 Epoxy substrate with dielectric constant 4.4 and tangent loss 0.025 has been used. For the antenna simulation CST MW Studio software has been used.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115103806","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711646
Joyjit Chatterjee, G. Sharma, Ayush Sexena, Anu Mehra, Varun Gupta
Respiratory diseases affect more than 200 million people across the world and are one of the most intrinsic contributors towards deaths of adults and infants alike. Lung disorders range from mild symptoms like common cold and influenza, to life threatening instances like Pneumonia, Asthma and Lung Cancer. Therefore, early diagnosis of a respiratory disorder can often help prevent a tragedy. Medical Diagnostic of a lung disorder generally requires an auscultation of lung sounds, brief chest x-ray and in some cases can even include bronchoscopy, chest imaging and thoracoscopy. Auscultation is often subject to various biased opinions by different physicians and the results can be catastrophic if the physician is untrained. This research paper proposes statistical analysis and classification of the various auscultations of lung sounds. Here, the breathing rate of a person is chosen as the core parameter to segment the total number of breaths into mild, soft and hard breaths. In addition to this, the peak value of the envelope of the normalized signal is successfully used to predict the odds of having a lung disorder, from among Crackle, Pneumonia, Wheeze and Asthma. The proposed system reduces the need of a trained pra ctitioner which in turn makes the lung disorder diagnosis cost effective and also pro vides unbiased predictions. The time complexity of the system is very low which makes it suitable for the real time diagnosis of various lung disorders. The lung sounds are taken from the R.A.L.E, Canada repository.
{"title":"A Robust Automatic Algorithm for Statistical Analysis and Classification of Lung Auscultations","authors":"Joyjit Chatterjee, G. Sharma, Ayush Sexena, Anu Mehra, Varun Gupta","doi":"10.1109/SPIN.2019.8711646","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711646","url":null,"abstract":"Respiratory diseases affect more than 200 million people across the world and are one of the most intrinsic contributors towards deaths of adults and infants alike. Lung disorders range from mild symptoms like common cold and influenza, to life threatening instances like Pneumonia, Asthma and Lung Cancer. Therefore, early diagnosis of a respiratory disorder can often help prevent a tragedy. Medical Diagnostic of a lung disorder generally requires an auscultation of lung sounds, brief chest x-ray and in some cases can even include bronchoscopy, chest imaging and thoracoscopy. Auscultation is often subject to various biased opinions by different physicians and the results can be catastrophic if the physician is untrained. This research paper proposes statistical analysis and classification of the various auscultations of lung sounds. Here, the breathing rate of a person is chosen as the core parameter to segment the total number of breaths into mild, soft and hard breaths. In addition to this, the peak value of the envelope of the normalized signal is successfully used to predict the odds of having a lung disorder, from among Crackle, Pneumonia, Wheeze and Asthma. The proposed system reduces the need of a trained pra ctitioner which in turn makes the lung disorder diagnosis cost effective and also pro vides unbiased predictions. The time complexity of the system is very low which makes it suitable for the real time diagnosis of various lung disorders. The lung sounds are taken from the R.A.L.E, Canada repository.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"368 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114528843","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711652
M. Khulbe, M. Tripathy, H. Parthasarathy, Y. Shestopalov, B. Lagovsky
In this paper a mathematical technique is developed to find the parameters of a medium in terms of its scattered electromagnetic fields. Optical nonlinearity plays an important role in finding the scattering parameters of a medium. Using perturbation theory and nonlinear inverse scattering techniques with first order, second order and third order optical nonlinearity we find scattered electromagnetic fields. Using error minimization techniques parameters are estimated in term of permittivity and permeability up to second order.
{"title":"Inverse Scattering and Imaging Using Second Order Optical Nonlinearities","authors":"M. Khulbe, M. Tripathy, H. Parthasarathy, Y. Shestopalov, B. Lagovsky","doi":"10.1109/SPIN.2019.8711652","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711652","url":null,"abstract":"In this paper a mathematical technique is developed to find the parameters of a medium in terms of its scattered electromagnetic fields. Optical nonlinearity plays an important role in finding the scattering parameters of a medium. Using perturbation theory and nonlinear inverse scattering techniques with first order, second order and third order optical nonlinearity we find scattered electromagnetic fields. Using error minimization techniques parameters are estimated in term of permittivity and permeability up to second order.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123440252","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711579
Shivani Dhok, Ankit A. Bhurane, A. Kothari
Hyperspectral imaging has transpired as a compelling tool in various fields like geology, mining, agriculture, etc with applications ranging from object detection to quality inspection. Feature extraction, as well as the methodology used for feature extraction, plays an indispensable role in increasing the accuracy of the classification of hyperspectral imaging (HSI). This paper proposes an algorithm for automated hyperspectral image classification using nine spatial-spectral features, which includes linear predictive coefficients, wavelet coefficients, standard deviation, average energy, mean, fractal dimension, entropy, Rényi entropy and Kraskov entropy. These features are further used for classification using the quadratic support vector machine (SVM). The elaborated scheme exercises 10-fold cross-validation. The collective effect of the excerpted features is determined and the accuracy trends for the various number of features is ascertained. Appreciable overall accuracies (OA) for all the three publicly available data sets are acquired as follows: Salinas-A data set $(mathbf{OA} = 99.60%)$, Salinas data set $(mathbf{OA}=92.4%)$ and Botswana data set $(mathbf{OA} =89.5%)$.
{"title":"Automated Hyperspectral Image Classification Using Spatial-Spectral Features","authors":"Shivani Dhok, Ankit A. Bhurane, A. Kothari","doi":"10.1109/SPIN.2019.8711579","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711579","url":null,"abstract":"Hyperspectral imaging has transpired as a compelling tool in various fields like geology, mining, agriculture, etc with applications ranging from object detection to quality inspection. Feature extraction, as well as the methodology used for feature extraction, plays an indispensable role in increasing the accuracy of the classification of hyperspectral imaging (HSI). This paper proposes an algorithm for automated hyperspectral image classification using nine spatial-spectral features, which includes linear predictive coefficients, wavelet coefficients, standard deviation, average energy, mean, fractal dimension, entropy, Rényi entropy and Kraskov entropy. These features are further used for classification using the quadratic support vector machine (SVM). The elaborated scheme exercises 10-fold cross-validation. The collective effect of the excerpted features is determined and the accuracy trends for the various number of features is ascertained. Appreciable overall accuracies (OA) for all the three publicly available data sets are acquired as follows: Salinas-A data set $(mathbf{OA} = 99.60%)$, Salinas data set $(mathbf{OA}=92.4%)$ and Botswana data set $(mathbf{OA} =89.5%)$.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124400289","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711570
Garima Mahendru, A. Shukla, P. Banerjee, L. Patnaik
A major breakthrough has been observed in wireless communication technology over the past few years. The advent of new wireless applications has choked the available bandwidth and pleads for a more efficient strategy for its allocation to users. Among the various proposed methods of spectrum de-congestion, Cognitive radio seems to be a promising solution to spectrum scarcity. Spectrum sensing is the first and most crucial step in establishing cognitive radio system. However, the available spectrum sensing techniques are severely limited by noise power fluctuations, fading, multipath propagation and low signal-to-noise ratio. These factors affect the sensing functionality in terms of increased missed detection and false alarm rates, reduced probability of detection and large number of samples. This paper proposes an adaptive threshold method to overcome sensing failure at very low SNR with uncertain noise power using a check parameter and double threshold concept. The double threshold concept tapers the width of the uncertainty zone and makes the detection process robust. Simulation results validate the new findings and improve the detection probability by 19.95% at a low SNR of −12 dB.
{"title":"Adaptive Double Threshold Based Spectrum Sensing to Overcome Sensing Failure in Presence of Noise Uncertainty","authors":"Garima Mahendru, A. Shukla, P. Banerjee, L. Patnaik","doi":"10.1109/SPIN.2019.8711570","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711570","url":null,"abstract":"A major breakthrough has been observed in wireless communication technology over the past few years. The advent of new wireless applications has choked the available bandwidth and pleads for a more efficient strategy for its allocation to users. Among the various proposed methods of spectrum de-congestion, Cognitive radio seems to be a promising solution to spectrum scarcity. Spectrum sensing is the first and most crucial step in establishing cognitive radio system. However, the available spectrum sensing techniques are severely limited by noise power fluctuations, fading, multipath propagation and low signal-to-noise ratio. These factors affect the sensing functionality in terms of increased missed detection and false alarm rates, reduced probability of detection and large number of samples. This paper proposes an adaptive threshold method to overcome sensing failure at very low SNR with uncertain noise power using a check parameter and double threshold concept. The double threshold concept tapers the width of the uncertainty zone and makes the detection process robust. Simulation results validate the new findings and improve the detection probability by 19.95% at a low SNR of −12 dB.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129947621","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711632
R. Devi, Hitender Kumar Tyagi, D. Kumar
ECG denoising using different kinds of scientific techniques and methods has been an interesting research area among the signal processing research fraternity. There are various kinds of noises that interfere with ECG signal at different levels. Powerline interference, baseline wander noise and electromyography noise are at highest priority to remove from the desired signal. Several sparsity based adaptive and wavelet digital filtering techniques have been proposed in previous investigations for denoising of ECG signal. But there qualitative and quantitative performance analysis against each other is lacking in the literature. In this paper, we reviewed various sparsity based noise reduction techniques of adaptive and wavelet algorithms. Using the benchmark dataset of MIT/BIH, a detailed and fair comparison of LMS, RLS and DWT were implemented for their performance analysis. The qualitative analysis has been presented in terms of the morphology differences in the denoised signal and the quantitative analysis is presented in terms of various performance measuring parameters of signal-to-noise ratio (SNR), mean square error (MSE), percentage root mean square difference (PRD) and peak-signal-to-noise ratio (PSNR). The obtained results show that adaptive filtering using RLS algorithm performs better in more dense noisy conditions whereas the wavelet filtering is better to perform in less noisy conditions. Further, all three algorithms were tested on different kinds of noises like power-line interference, baseline wander and abrupt shift in the ECG data, where, DWT based filtering approach was found superior on removal of powerline and baseline wander interferences, but it fails to remove the abrupt shift kind of noise. The abrupt shift noise was best removed by both LMS and RLS adaptive algorithms but at the cost of low speed and poor quality. Thus, the presented optimized analysis of advanced three sparsity based filtering techniques would provide great potential benefits in biomedical applications of ECG signal processing, feature extraction, analysis and other related fields.
{"title":"Performance Comparison and Applications of Sparsity Based Techniques for Denoising of ECG Signal","authors":"R. Devi, Hitender Kumar Tyagi, D. Kumar","doi":"10.1109/SPIN.2019.8711632","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711632","url":null,"abstract":"ECG denoising using different kinds of scientific techniques and methods has been an interesting research area among the signal processing research fraternity. There are various kinds of noises that interfere with ECG signal at different levels. Powerline interference, baseline wander noise and electromyography noise are at highest priority to remove from the desired signal. Several sparsity based adaptive and wavelet digital filtering techniques have been proposed in previous investigations for denoising of ECG signal. But there qualitative and quantitative performance analysis against each other is lacking in the literature. In this paper, we reviewed various sparsity based noise reduction techniques of adaptive and wavelet algorithms. Using the benchmark dataset of MIT/BIH, a detailed and fair comparison of LMS, RLS and DWT were implemented for their performance analysis. The qualitative analysis has been presented in terms of the morphology differences in the denoised signal and the quantitative analysis is presented in terms of various performance measuring parameters of signal-to-noise ratio (SNR), mean square error (MSE), percentage root mean square difference (PRD) and peak-signal-to-noise ratio (PSNR). The obtained results show that adaptive filtering using RLS algorithm performs better in more dense noisy conditions whereas the wavelet filtering is better to perform in less noisy conditions. Further, all three algorithms were tested on different kinds of noises like power-line interference, baseline wander and abrupt shift in the ECG data, where, DWT based filtering approach was found superior on removal of powerline and baseline wander interferences, but it fails to remove the abrupt shift kind of noise. The abrupt shift noise was best removed by both LMS and RLS adaptive algorithms but at the cost of low speed and poor quality. Thus, the presented optimized analysis of advanced three sparsity based filtering techniques would provide great potential benefits in biomedical applications of ECG signal processing, feature extraction, analysis and other related fields.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130873055","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711788
Sarabdeep Singh, A. Raman, Naveen Kumar, Ravi Ranjan, Deep Shekhar, S. Anand
This paper demonstrate the comparative study of various linearity as well as intermodulation distortion (IMD) parameters for junctionless (JL) and charge plasma (CP) dopingless nanowire FETs with dual material gate (DM). The various parameters considered for analysis includes higher order transconductance coefficients: gm2 (second-order) & gm3 (third-order), second-third order harmonic distortion HD2 &HD3, third order current intercept point (IIP3), third order IMD (IMD3), higher order voltage intercept points (VIP2 & VIP3) etc. The simulation study results reveals that analog parameters namely transconductance gm and transconductance gain factor (TGF) along with cut-off frequency fT are better for CP_DM. The other parameters including Cgg, gm3, HD2, HD3, IIP3 and VIP3 for JL_DM shows enhanced performance over CP_DM.
{"title":"Linearity Analysis of Gate Engineered Dopingless and Junctionless Silicon Nanowire FET","authors":"Sarabdeep Singh, A. Raman, Naveen Kumar, Ravi Ranjan, Deep Shekhar, S. Anand","doi":"10.1109/SPIN.2019.8711788","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711788","url":null,"abstract":"This paper demonstrate the comparative study of various linearity as well as intermodulation distortion (IMD) parameters for junctionless (JL) and charge plasma (CP) dopingless nanowire FETs with dual material gate (DM). The various parameters considered for analysis includes higher order transconductance coefficients: gm2 (second-order) & gm3 (third-order), second-third order harmonic distortion HD2 &HD3, third order current intercept point (IIP3), third order IMD (IMD3), higher order voltage intercept points (VIP2 & VIP3) etc. The simulation study results reveals that analog parameters namely transconductance gm and transconductance gain factor (TGF) along with cut-off frequency fT are better for CP_DM. The other parameters including Cgg, gm3, HD2, HD3, IIP3 and VIP3 for JL_DM shows enhanced performance over CP_DM.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121635521","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711724
S. Roy, Aditi Panda, R. Naskar
Successful training of deep neural network models for Image Segmentation requires large datasets with proper ground truth annotations. In most bio-medical applications obtaining sufficiently large labelled datasets for training such networks, is a tedious task. Hence addressing this problem, we propose a simple light-weight neural network based model that generates ground truth masks of the neuronal structures of Electron Microscopy(EM) stacks training images. It is followed by image augmentation to create an extensive dataset of image-mask pairs for training the segmentation network. The proposed segmentation model is inspired by the state-of-the-art Unet++ architecture. We compare the segmentation predicts of the proposed model (unsupervised) with the manual ground truth masks to validate our results and efficiency of the model proposed. The proposed network model for unsupervised segmentation can be trained effectively with less number of train images even without the presence of proper ground truth masks. It predicts high quality segmentation outputs for the images under test with optimal time requirement(less than a second using a Google Colab Nvidia Tesla K80 GPU).
成功训练用于图像分割的深度神经网络模型需要具有适当的基础真值注释的大型数据集。在大多数生物医学应用中，获得足够大的标记数据集来训练这样的网络是一项繁琐的任务。因此，为了解决这个问题，我们提出了一个简单的轻量级的基于神经网络的模型，该模型生成电子显微镜(EM)堆栈训练图像的神经元结构的真实掩模。其次是图像增强，以创建一个广泛的图像掩码对数据集，用于训练分割网络。所提出的分割模型受到最先进的Unet++体系结构的启发。我们将所提出的模型(无监督)的分割预测与手动地面真值掩模进行比较，以验证我们的结果和所提出模型的效率。所提出的无监督分割网络模型即使在没有适当的地面真值掩模的情况下，也可以使用较少的列车图像进行有效的训练。它以最佳时间要求(使用Google Colab Nvidia Tesla K80 GPU不到一秒)预测被测图像的高质量分割输出。
{"title":"Unsupervised Ground Truth Generation for Automated Brain EM Image Segmentation","authors":"S. Roy, Aditi Panda, R. Naskar","doi":"10.1109/SPIN.2019.8711724","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711724","url":null,"abstract":"Successful training of deep neural network models for Image Segmentation requires large datasets with proper ground truth annotations. In most bio-medical applications obtaining sufficiently large labelled datasets for training such networks, is a tedious task. Hence addressing this problem, we propose a simple light-weight neural network based model that generates ground truth masks of the neuronal structures of Electron Microscopy(EM) stacks training images. It is followed by image augmentation to create an extensive dataset of image-mask pairs for training the segmentation network. The proposed segmentation model is inspired by the state-of-the-art Unet++ architecture. We compare the segmentation predicts of the proposed model (unsupervised) with the manual ground truth masks to validate our results and efficiency of the model proposed. The proposed network model for unsupervised segmentation can be trained effectively with less number of train images even without the presence of proper ground truth masks. It predicts high quality segmentation outputs for the images under test with optimal time requirement(less than a second using a Google Colab Nvidia Tesla K80 GPU).","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125244301","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 : 2019-03-07DOI: 10.1109/SPIN.2019.8711602
G. Saxena, P. Jain, Yogendra K Awasthi
In this article, a high isolation EBG based MIMO antenna is designed to achieve intended characteristics. Proposed antenna is tailored on FR-4 substrate with size of $55times 49times 1.6mathbf{mm}^{3}$. This antenna has circular patches with extruded triangular and circular shapes which provides better radiation efficiency (>0.45) in the X-band (8.0 to 12GHz). High isolation (−22dB) is achieved in entire bandwidth by using mushroom shaped EBG structure near the microstrip feeding line. Diversity performance of antenna is also judged by the various parameters like ECC, Diversity gain, CCL and TARC, which has the practically accepted values <0.016, >9.96dB <0.3bits/sec/Hz and <−35dB correspondingly.
{"title":"High Isolation EBG Based MIMO Antenna for X-Band Applications","authors":"G. Saxena, P. Jain, Yogendra K Awasthi","doi":"10.1109/SPIN.2019.8711602","DOIUrl":"https://doi.org/10.1109/SPIN.2019.8711602","url":null,"abstract":"In this article, a high isolation EBG based MIMO antenna is designed to achieve intended characteristics. Proposed antenna is tailored on FR-4 substrate with size of $55times 49times 1.6mathbf{mm}^{3}$. This antenna has circular patches with extruded triangular and circular shapes which provides better radiation efficiency (>0.45) in the X-band (8.0 to 12GHz). High isolation (−22dB) is achieved in entire bandwidth by using mushroom shaped EBG structure near the microstrip feeding line. Diversity performance of antenna is also judged by the various parameters like ECC, Diversity gain, CCL and TARC, which has the practically accepted values <0.016, >9.96dB <0.3bits/sec/Hz and <−35dB correspondingly.","PeriodicalId":344030,"journal":{"name":"2019 6th International Conference on Signal Processing and Integrated Networks (SPIN)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121741418","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：