Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909816
M. Thomas, Fillatre Lionel, Deruaz-Pepin Laurent
Vessel noise classification is generally considered as a challenging task due to its need for robustness and reliability. Thus, classification in this domain mainly relied on expert feature. Raw waveform architectures have been historically avoided, despite their performances in other domains. This paper proposes a Learning-based Scattering Transform (LST) that efficiently learns temporal dependencies within cyclostationary signals, such as vessel noises. The LST is implememented as a Convolutional Neural Network (CNN) with short filters whose structure mimics a multiscale signal decomposition. By this way, the architecture of our neural network is intrinsically explainable. Numerical simulations compare our method to an other explainable model and classic convolutional neural networks.
{"title":"Learning-Based Scattering Transform for Explainable Classification","authors":"M. Thomas, Fillatre Lionel, Deruaz-Pepin Laurent","doi":"10.23919/eusipco55093.2022.9909816","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909816","url":null,"abstract":"Vessel noise classification is generally considered as a challenging task due to its need for robustness and reliability. Thus, classification in this domain mainly relied on expert feature. Raw waveform architectures have been historically avoided, despite their performances in other domains. This paper proposes a Learning-based Scattering Transform (LST) that efficiently learns temporal dependencies within cyclostationary signals, such as vessel noises. The LST is implememented as a Convolutional Neural Network (CNN) with short filters whose structure mimics a multiscale signal decomposition. By this way, the architecture of our neural network is intrinsically explainable. Numerical simulations compare our method to an other explainable model and classic convolutional neural networks.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122064864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909649
Kai Li, Xugang Lu, M. Akagi, J. Dang, Sheng Li, M. Unoki
Quantitatively revealing the relationship between speakers' physiological structure and acoustic speech signals by considering the properties of resonance and antiresonance can help us to extract effective speaker discriminative information (SDI) from speech signals. The conventional quantification method based on F-ratio only considers the power of acoustic speech in each frequency band independently. We propose a novel frequency-wise attentional neural network to learn the nonlinear combined effect of the frequency components on speaker identity. The learned results indicate that antiresonance frequency induced by the nasal cavity is another essential factor for speaker discrimination that the F-ratio method could not reveal. To further evaluate our findings, we designed a non-uniform subband processing strategy based on the learned results for speaker feature extraction and did automatic speaker verification (ASV). The ASV results confirmed that further emphasizing the spectral structure around the antiresonance frequency region can enhance speaker discrimination.
{"title":"Relationship Between Speakers' Physiological Structure and Acoustic Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional Neural Network","authors":"Kai Li, Xugang Lu, M. Akagi, J. Dang, Sheng Li, M. Unoki","doi":"10.23919/eusipco55093.2022.9909649","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909649","url":null,"abstract":"Quantitatively revealing the relationship between speakers' physiological structure and acoustic speech signals by considering the properties of resonance and antiresonance can help us to extract effective speaker discriminative information (SDI) from speech signals. The conventional quantification method based on F-ratio only considers the power of acoustic speech in each frequency band independently. We propose a novel frequency-wise attentional neural network to learn the nonlinear combined effect of the frequency components on speaker identity. The learned results indicate that antiresonance frequency induced by the nasal cavity is another essential factor for speaker discrimination that the F-ratio method could not reveal. To further evaluate our findings, we designed a non-uniform subband processing strategy based on the learned results for speaker feature extraction and did automatic speaker verification (ASV). The ASV results confirmed that further emphasizing the spectral structure around the antiresonance frequency region can enhance speaker discrimination.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122870047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909934
Hechuan Wang, Xiaokun Zhao, M. Bugallo
The precision of indoor localization, especially height estimation, is critical to unmanned aerial vehicle (UAV) navigation to avoid crashes because indoor environments are narrow and complex. The lack of satellite-based navigation signals makes this task very challenging. Moreover, objects in indoor environments could be randomly shaped and in motion, making map-based navigation unreliable. There exist solutions utilizing advanced sensor arrays such as laser scanners or multiple cameras, but the UAVs' weight load and computational resources are limited. In this paper, we propose a filtering-based method that allows for estimation of the height of the UAV by stand -alone range finders. Model-detecting particle filters are used to detect changes in objects while estimating the height of the UAV simultaneously. Multiple filters are utilized to speed up the computation. Numerical experiments show that the proposed method is more accurate than other methods.
{"title":"Indoor UAV Height Estimation with Multiple Model-Detecting Particle Filters","authors":"Hechuan Wang, Xiaokun Zhao, M. Bugallo","doi":"10.23919/eusipco55093.2022.9909934","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909934","url":null,"abstract":"The precision of indoor localization, especially height estimation, is critical to unmanned aerial vehicle (UAV) navigation to avoid crashes because indoor environments are narrow and complex. The lack of satellite-based navigation signals makes this task very challenging. Moreover, objects in indoor environments could be randomly shaped and in motion, making map-based navigation unreliable. There exist solutions utilizing advanced sensor arrays such as laser scanners or multiple cameras, but the UAVs' weight load and computational resources are limited. In this paper, we propose a filtering-based method that allows for estimation of the height of the UAV by stand -alone range finders. Model-detecting particle filters are used to detect changes in objects while estimating the height of the UAV simultaneously. Multiple filters are utilized to speed up the computation. Numerical experiments show that the proposed method is more accurate than other methods.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"1102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122918373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909793
D. Vukobratović, Milan Lukić, I. Mezei, D. Bajović, Dragan Danilovic, Milos Savic, Zarko Bodroski, S. Skrbic, D. Jakovetić
The emergence of cellular Internet of Things (IoT) standards such as NB-IoT brings novel opportunities for low-cost wide-area IoT applications. Augmenting massive IoT deployments with Machine Learning (ML) algorithms deployed at the edge enables design and implementation of a novel intelligent IoT services. In this paper, we present an architectural outlook and an overview of our recent activities that target integration of ML modules into the cellular IoT architecture. The three-layer architecture considered in this paper embeds ML modules at the edge devices (ML-EDGE), within the core network (ML-FOG) and at the cloud servers (ML-CLOUD), thus balancing between the system response time and accuracy. We discuss alignment of the proposed architecture with ongoing trends in 3GPP architecture evolution. We design, integrate and demonstrate edge ML use cases relying on our real-world deployment of about 150 static and mobile nodes integrated into the NB-IoT network.
{"title":"Edge Machine Learning in 3GPP NB-IoT: Architecture, Applications and Demonstration","authors":"D. Vukobratović, Milan Lukić, I. Mezei, D. Bajović, Dragan Danilovic, Milos Savic, Zarko Bodroski, S. Skrbic, D. Jakovetić","doi":"10.23919/eusipco55093.2022.9909793","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909793","url":null,"abstract":"The emergence of cellular Internet of Things (IoT) standards such as NB-IoT brings novel opportunities for low-cost wide-area IoT applications. Augmenting massive IoT deployments with Machine Learning (ML) algorithms deployed at the edge enables design and implementation of a novel intelligent IoT services. In this paper, we present an architectural outlook and an overview of our recent activities that target integration of ML modules into the cellular IoT architecture. The three-layer architecture considered in this paper embeds ML modules at the edge devices (ML-EDGE), within the core network (ML-FOG) and at the cloud servers (ML-CLOUD), thus balancing between the system response time and accuracy. We discuss alignment of the proposed architecture with ongoing trends in 3GPP architecture evolution. We design, integrate and demonstrate edge ML use cases relying on our real-world deployment of about 150 static and mobile nodes integrated into the NB-IoT network.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126326115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909631
Manoj K. Panda, B. Subudhi, T. Veerakumar, V. Jakhetiya
Image fusion is a technique that combines the complementary details from the images captured from different sensors into a single image with high perception capability. In the fusion process, the significant details from different source images are combined in a meaningful way. In this article, we propose a unique and first effort of infrared and visible image fusion technique with bi-dimensional empirical mode decomposition (BEMD) induced VGG-16 deep neural network. The proposed BEMD strategy is incorporated with a pre-trained VGG-16 network that can effectively handle the vagueness of infrared and visible images and retain deep multi-layer features at different scales on the frequency domain. A novel fusion strategy is proposed here to analyze the spatial inter-dependency between these features and precisely preserve the correlative information from the source images. The minimum selection strategy is explored in the proposed algorithm to keep the standard details with reduced artifacts in the fused image. The competency of the proposed algorithm is estimated using qualitative and quantitative assessments. The efficiency of the proposed technique is corroborated against fifteen existing state-of-the-art fusion techniques and found to be efficient.
{"title":"Integration of Bi-dimensional Empirical Mode Decomposition With Two Streams Deep Learning Network for Infrared and Visible Image Fusion","authors":"Manoj K. Panda, B. Subudhi, T. Veerakumar, V. Jakhetiya","doi":"10.23919/eusipco55093.2022.9909631","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909631","url":null,"abstract":"Image fusion is a technique that combines the complementary details from the images captured from different sensors into a single image with high perception capability. In the fusion process, the significant details from different source images are combined in a meaningful way. In this article, we propose a unique and first effort of infrared and visible image fusion technique with bi-dimensional empirical mode decomposition (BEMD) induced VGG-16 deep neural network. The proposed BEMD strategy is incorporated with a pre-trained VGG-16 network that can effectively handle the vagueness of infrared and visible images and retain deep multi-layer features at different scales on the frequency domain. A novel fusion strategy is proposed here to analyze the spatial inter-dependency between these features and precisely preserve the correlative information from the source images. The minimum selection strategy is explored in the proposed algorithm to keep the standard details with reduced artifacts in the fused image. The competency of the proposed algorithm is estimated using qualitative and quantitative assessments. The efficiency of the proposed technique is corroborated against fifteen existing state-of-the-art fusion techniques and found to be efficient.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126508785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909566
Yang Li, G. Mateos
Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning framework to model the relationship between brain structural connectivity (SC) and functional connectivity (FC) via a graph encoder-decoder system. Specifically, we propose a Siamese network architecture equipped with graph convolutional encoders to learn graph (i.e., subject)-level embeddings that preserve application-dependent similarity measures between brain networks. This way, we effectively increase the number of training samples and bring in the flexibility to incorporate additional prior information via the prescribed target graph-level distance. While information on the brain structure-function coupling is implicitly distilled via reconstruction of brain FC from SC, our model also manages to learn representations that preserve the similarity between input graphs. The superior discriminative power of the learnt representations is demonstrated in downstream tasks including subject classification and visualization. All in all, this work advocates the prospect of leveraging learnt graph-level, similarity-preserving embeddings for brain network analysis, by bringing to bear standard tools of metric data analysis.
{"title":"Learning Similarity-Preserving Representations of Brain Structure-Function Coupling","authors":"Yang Li, G. Mateos","doi":"10.23919/eusipco55093.2022.9909566","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909566","url":null,"abstract":"Advances in graph signal processing for network neuroscience offer a unique pathway to integrate brain structure and function, with the goal of revealing some of the brain's organizing principles at the system level. In this direction, we develop a supervised graph representation learning framework to model the relationship between brain structural connectivity (SC) and functional connectivity (FC) via a graph encoder-decoder system. Specifically, we propose a Siamese network architecture equipped with graph convolutional encoders to learn graph (i.e., subject)-level embeddings that preserve application-dependent similarity measures between brain networks. This way, we effectively increase the number of training samples and bring in the flexibility to incorporate additional prior information via the prescribed target graph-level distance. While information on the brain structure-function coupling is implicitly distilled via reconstruction of brain FC from SC, our model also manages to learn representations that preserve the similarity between input graphs. The superior discriminative power of the learnt representations is demonstrated in downstream tasks including subject classification and visualization. All in all, this work advocates the prospect of leveraging learnt graph-level, similarity-preserving embeddings for brain network analysis, by bringing to bear standard tools of metric data analysis.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125873113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909969
Xiaohan Zhao, Yongzhe Li, R. Tao
In this paper, we focus on the unimodular waveform design with good correlation property, i.e., with low integrated sidelobe level (ISL). In contrast to existing approaches that commonly involve constraints on the moduli of waveform elements, we come up with the idea of designing the waveform via directly optimizing its phase values. Using this idea, the standard ISL-minimization based waveform design is converted as an unconstrained optimization problem with respect to the phase values of waveform elements, which avoids the repetitive procedure of projecting non-unimodular complex values into the best approximations of constant magnitudes. To this end, we first reformulate the ISL metric into a function of the phase values to be obtained for the waveform, and then solve the new unconstrained ISL-minimization-based waveform design using majorization-minimization techniques. The first-order gradient of the reformulated objective function is derived, by which the majorant of the objective is elaborated. Based on this, we finally tackle the design via iterations, at each of which we obtain a closed-form solution with fast implementations. An algorithm is proposed, with whose simpleness and effectiveness are verified by simulations.
{"title":"Design of Single Unimodular Waveform With Good Correlation Level Via Phase Optimizations","authors":"Xiaohan Zhao, Yongzhe Li, R. Tao","doi":"10.23919/eusipco55093.2022.9909969","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909969","url":null,"abstract":"In this paper, we focus on the unimodular waveform design with good correlation property, i.e., with low integrated sidelobe level (ISL). In contrast to existing approaches that commonly involve constraints on the moduli of waveform elements, we come up with the idea of designing the waveform via directly optimizing its phase values. Using this idea, the standard ISL-minimization based waveform design is converted as an unconstrained optimization problem with respect to the phase values of waveform elements, which avoids the repetitive procedure of projecting non-unimodular complex values into the best approximations of constant magnitudes. To this end, we first reformulate the ISL metric into a function of the phase values to be obtained for the waveform, and then solve the new unconstrained ISL-minimization-based waveform design using majorization-minimization techniques. The first-order gradient of the reformulated objective function is derived, by which the majorant of the objective is elaborated. Based on this, we finally tackle the design via iterations, at each of which we obtain a closed-form solution with fast implementations. An algorithm is proposed, with whose simpleness and effectiveness are verified by simulations.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129848310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909725
Esther Rodrigo Bonet, T. Do, Xuening Qin, J. Hofman, V. Manna, Wilfried Philips, Nikos Deligiannis
To control air pollution and mitigate its negative effect on health, it is of the utmost importance to have accurate real-time forecasting models. Existing deep-learning-based air quality forecasting models typically deploy temporal and-less often-spatial modules. Yet, data scarcity emerges as a real issue in this domain, a problem that can be solved by capturing the data distribution. In this work, we address data scarcity by proposing a novel conditional variational graph autoencoder. Our model is able to forecast air pollution by efficiently encoding the spatio-temporal correlations of the known data. Additionally, we leverage dynamic context data such as weather or satellite images to condition the model's behaviour. We formulate the problem as a context-aware graph-based matrix completion task and utilize street-level data from mobile stations. Experiments on real-world air quality datasets show the improved performance of our model with respect to state-of-the-art approaches.
{"title":"Conditional Variational Graph Autoencoder for Air Quality Forecasting","authors":"Esther Rodrigo Bonet, T. Do, Xuening Qin, J. Hofman, V. Manna, Wilfried Philips, Nikos Deligiannis","doi":"10.23919/eusipco55093.2022.9909725","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909725","url":null,"abstract":"To control air pollution and mitigate its negative effect on health, it is of the utmost importance to have accurate real-time forecasting models. Existing deep-learning-based air quality forecasting models typically deploy temporal and-less often-spatial modules. Yet, data scarcity emerges as a real issue in this domain, a problem that can be solved by capturing the data distribution. In this work, we address data scarcity by proposing a novel conditional variational graph autoencoder. Our model is able to forecast air pollution by efficiently encoding the spatio-temporal correlations of the known data. Additionally, we leverage dynamic context data such as weather or satellite images to condition the model's behaviour. We formulate the problem as a context-aware graph-based matrix completion task and utilize street-level data from mobile stations. Experiments on real-world air quality datasets show the improved performance of our model with respect to state-of-the-art approaches.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129973693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909702
Thanh Trung LE, K. Abed-Meraim, N. Trung, A. Hafiane
Robust tensor tracking or robust adaptive tensor decomposition of streaming tensors is crucial when observations are corrupted by sparse outliers and missing data. In this paper, we introduce a novel tensor tracking algorithm for factorizing incomplete streaming tensors with sparse outliers under tensor-train (TT) format. The proposed algorithm consists of two main stages: online outlier rejection and tracking of TT-cores. In the former stage, outliers affecting the data streams are efficiently detected by an ADMM solver. In the latter stage, we propose an effective recursive least-squares solver to incrementally update TT-cores at each time $t$. Several numerical experiments on both simulated and real data are presented to verify the effectiveness of the proposed algorithm.
{"title":"Robust Tensor Tracking With Missing Data Under Tensor-Train Format","authors":"Thanh Trung LE, K. Abed-Meraim, N. Trung, A. Hafiane","doi":"10.23919/eusipco55093.2022.9909702","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909702","url":null,"abstract":"Robust tensor tracking or robust adaptive tensor decomposition of streaming tensors is crucial when observations are corrupted by sparse outliers and missing data. In this paper, we introduce a novel tensor tracking algorithm for factorizing incomplete streaming tensors with sparse outliers under tensor-train (TT) format. The proposed algorithm consists of two main stages: online outlier rejection and tracking of TT-cores. In the former stage, outliers affecting the data streams are efficiently detected by an ADMM solver. In the latter stage, we propose an effective recursive least-squares solver to incrementally update TT-cores at each time $t$. Several numerical experiments on both simulated and real data are presented to verify the effectiveness of the proposed algorithm.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129751898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.23919/eusipco55093.2022.9909919
Matthias Pollach, Felix Schiegg, Matthias Ludwig, A. Bette, Alois Knoll
This work proposes an automated semantic segmen-tation approach for high resolution scanning electron microscope images, which enables the detection of hardware Trojans and counterfeit integrated circuits. We evaluate state of the art segmentation approaches and leverage expert domain knowledge to propose a neural network architecture tailored for our use case. We further address the challenge of the limited availability of training images and evaluate which pre-trained encoder can be leveraged most effectively for the given use case. The proposed segmentation network uses expert domain knowledge to account for the importance of separating technology features on a fine-grain level by introducing a separate boundary stream. The test results compare our network to a baseline approach and to two state-of-the-art segmentation networks.
{"title":"Boundary Enhanced Semantic Segmentation for High Resolution Electron Microscope Images","authors":"Matthias Pollach, Felix Schiegg, Matthias Ludwig, A. Bette, Alois Knoll","doi":"10.23919/eusipco55093.2022.9909919","DOIUrl":"https://doi.org/10.23919/eusipco55093.2022.9909919","url":null,"abstract":"This work proposes an automated semantic segmen-tation approach for high resolution scanning electron microscope images, which enables the detection of hardware Trojans and counterfeit integrated circuits. We evaluate state of the art segmentation approaches and leverage expert domain knowledge to propose a neural network architecture tailored for our use case. We further address the challenge of the limited availability of training images and evaluate which pre-trained encoder can be leveraged most effectively for the given use case. The proposed segmentation network uses expert domain knowledge to account for the importance of separating technology features on a fine-grain level by introducing a separate boundary stream. The test results compare our network to a baseline approach and to two state-of-the-art segmentation networks.","PeriodicalId":231263,"journal":{"name":"2022 30th European Signal Processing Conference (EUSIPCO)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121975224","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：