Marcelo F. Caetano, George P. Kafentzis, A. Mouchtaris, Y. Stylianou
Percussive musical instrument sounds figure among the most challenging to model using sinusoids particularly due to the characteristic attack that features a sharp onset and transients. Attack transients present a highly nonstationary inharmonic behaviour that is very difficult to model with traditional sinusoidal models which use slowly varying sinusoids, commonly introducing an artifact known as pre-echo. In this work we use an adaptive sinusoidal model dubbed eaQHM to model percussive sounds from musical instruments such as plucked strings or percussion and investigate how eaQHM handles the sharp onsets and the nonstationary inharmonic nature of the attack transients. We show that adaptation renders a virtually perceptually identical sinusoidal representation of percussive sounds from different musical instruments, improving the Signal to Reconstruction Error Ratio (SRER) obtained with a traditional sinusoidal model. The result of a listening test revealed that the percussive sounds modeled with eaQHM were considered perceptually closer to the original sounds than their traditional-sinusoidal-modeled counterparts. Most listeners reported that they used the attack as cue.
{"title":"Adaptive sinusoidal modeling of percussive musical instrument sounds","authors":"Marcelo F. Caetano, George P. Kafentzis, A. Mouchtaris, Y. Stylianou","doi":"10.5281/ZENODO.43434","DOIUrl":"https://doi.org/10.5281/ZENODO.43434","url":null,"abstract":"Percussive musical instrument sounds figure among the most challenging to model using sinusoids particularly due to the characteristic attack that features a sharp onset and transients. Attack transients present a highly nonstationary inharmonic behaviour that is very difficult to model with traditional sinusoidal models which use slowly varying sinusoids, commonly introducing an artifact known as pre-echo. In this work we use an adaptive sinusoidal model dubbed eaQHM to model percussive sounds from musical instruments such as plucked strings or percussion and investigate how eaQHM handles the sharp onsets and the nonstationary inharmonic nature of the attack transients. We show that adaptation renders a virtually perceptually identical sinusoidal representation of percussive sounds from different musical instruments, improving the Signal to Reconstruction Error Ratio (SRER) obtained with a traditional sinusoidal model. The result of a listening test revealed that the percussive sounds modeled with eaQHM were considered perceptually closer to the original sounds than their traditional-sinusoidal-modeled counterparts. Most listeners reported that they used the attack as cue.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116741517","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}
Raul Hernandez-Aquino, D. McLernon, M. Ghogho, Syed Ali Raza Zaidi
In this paper, the energy efficiency in the downlink of a two-tier network consisting of macro- and femtocells using beamforming is analyzed. Orthogonal subchannel allocation is used in order to eliminate inter-tier interference. The random locations of the interferers in both tiers are modeled via a Poisson Point Process. Improvements in the energy efficiency of the system (in b/J/Hz), when several femtocells are deployed in a network, are observed under different scenarios. Finally, using realistic implementation parameters, we examine how the energy efficiency is affected by different antenna configurations, and we also obtain the optimal configurations.
{"title":"Energy efficiency in MIMO large scale two-tier networks with beamforming and adaptive modulation","authors":"Raul Hernandez-Aquino, D. McLernon, M. Ghogho, Syed Ali Raza Zaidi","doi":"10.5281/ZENODO.43731","DOIUrl":"https://doi.org/10.5281/ZENODO.43731","url":null,"abstract":"In this paper, the energy efficiency in the downlink of a two-tier network consisting of macro- and femtocells using beamforming is analyzed. Orthogonal subchannel allocation is used in order to eliminate inter-tier interference. The random locations of the interferers in both tiers are modeled via a Poisson Point Process. Improvements in the energy efficiency of the system (in b/J/Hz), when several femtocells are deployed in a network, are observed under different scenarios. Finally, using realistic implementation parameters, we examine how the energy efficiency is affected by different antenna configurations, and we also obtain the optimal configurations.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115541516","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}
In this paper a novel variant of the Normalized Nut (N-Cut) clustering algorithm that incorporates imposed constraints is implemented and evaluated on facial image clustering for 3D video analysis. The clustering problem is seen as a graph cut problem through a similarity matrix representing the relation among the vertices, i.e. facial images in this work. Mutual Information is used as similarity metric, applied on the HSV color space of the original images. This work considers the incorporation of constraints either regarding similarity or dissimilarity derived from a priori available information in the clustering procedure and evaluates the performance increase by their use. Experiments are conducted on 3D videos where a priori information about the facial images exists.
{"title":"Facial image clustering in 3D video using constrained Ncut","authors":"G. Orfanidis, N. Nikolaidis, I. Pitas","doi":"10.5281/ZENODO.43742","DOIUrl":"https://doi.org/10.5281/ZENODO.43742","url":null,"abstract":"In this paper a novel variant of the Normalized Nut (N-Cut) clustering algorithm that incorporates imposed constraints is implemented and evaluated on facial image clustering for 3D video analysis. The clustering problem is seen as a graph cut problem through a similarity matrix representing the relation among the vertices, i.e. facial images in this work. Mutual Information is used as similarity metric, applied on the HSV color space of the original images. This work considers the incorporation of constraints either regarding similarity or dissimilarity derived from a priori available information in the clustering procedure and evaluates the performance increase by their use. Experiments are conducted on 3D videos where a priori information about the facial images exists.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115152969","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}
The amount of online multimedia files is increasing day by day with the ever increasing popularity of video sharing websites. This has led to a huge interest in content analysis of multimedia files. Audio being a major component of multimedia has the potential to help analyze different events occurring in a multimedia recording. In this paper we present an audio event detection mechanism based on Gaussian Mixture Model (GMM) and Random Forest Classifier. Experiments show that our proposed mechanism shows significant improvement in detection of specifically finer audio events in short duration recordings.
{"title":"Event detection in short duration audio using Gaussian Mixture Model and Random Forest Classifier","authors":"Anurag Kumar, R. Hegde, Rita Singh, B. Raj","doi":"10.5281/ZENODO.43595","DOIUrl":"https://doi.org/10.5281/ZENODO.43595","url":null,"abstract":"The amount of online multimedia files is increasing day by day with the ever increasing popularity of video sharing websites. This has led to a huge interest in content analysis of multimedia files. Audio being a major component of multimedia has the potential to help analyze different events occurring in a multimedia recording. In this paper we present an audio event detection mechanism based on Gaussian Mixture Model (GMM) and Random Forest Classifier. Experiments show that our proposed mechanism shows significant improvement in detection of specifically finer audio events in short duration recordings.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114883485","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}
Olivier Janssens, Jonas De Vylder, J. Aelterman, S. Verstockt, W. Philips, D. Straeten, S. Hoecke, R. Walle
Over the last 4 years phenotyping is becoming more and more automated, decreasing a lot of manual labour. Features, which uniquely define the plant, can be extracted automatically from images. As a lot of plant data has to be processed in order to extract the features, fast processing of these features is a challenge. Therefore in this paper, a new method for automatic segmentation of individual leaves from plants with a circular arrangement of leaves (rosettes) is proposed, together with an algorithm to extract the line of symmetry of the leaf. Furthermore, in order to achieve fast processing for phenotyping plants, four feature extraction methods are parallelised in order to run on the CPU and GPU. Our evaluation results show that by parallelizing the feature extraction methods, it is possible to calculate the image moments, area, histogram and sum of intensities 5 to 45 times faster than single threaded implementations.
{"title":"Leaf segmentation and parallel phenotyping for the analysis of gene networks in plants","authors":"Olivier Janssens, Jonas De Vylder, J. Aelterman, S. Verstockt, W. Philips, D. Straeten, S. Hoecke, R. Walle","doi":"10.5281/ZENODO.43589","DOIUrl":"https://doi.org/10.5281/ZENODO.43589","url":null,"abstract":"Over the last 4 years phenotyping is becoming more and more automated, decreasing a lot of manual labour. Features, which uniquely define the plant, can be extracted automatically from images. As a lot of plant data has to be processed in order to extract the features, fast processing of these features is a challenge. Therefore in this paper, a new method for automatic segmentation of individual leaves from plants with a circular arrangement of leaves (rosettes) is proposed, together with an algorithm to extract the line of symmetry of the leaf. Furthermore, in order to achieve fast processing for phenotyping plants, four feature extraction methods are parallelised in order to run on the CPU and GPU. Our evaluation results show that by parallelizing the feature extraction methods, it is possible to calculate the image moments, area, histogram and sum of intensities 5 to 45 times faster than single threaded implementations.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"776 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126946957","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}
A. Kalis, M. Milis, A. Kounoudes, A. Constantinides
The objective of this work is to propose the use of innovative low-cost wireless sensor network nodes equipped with smart antennas, so as to meet the goal of creating a sustainable and safe building environment. The proposed wireless sensor network system can provide information on people density within building areas, information that can be used in a number of applications such as energy footprint optimization, predictive maintenance and building safe evacuation. The unique design of the proposed sensor nodes can be supportive to the aforementioned applications by providing people location information and building area usage in a bandwidth efficient way, in order to enable such systems to be integrated into existing low-bandwidth in-building communication systems, such as fire alert and automation networks. Node architecture is based on the use of low-cost and low-complexity switched beam antennas and the use of a localization estimation algorithm based on angle of arrival measurements which, as opposed to popular received signal strength based algorithms, are not affected by the severe multipath environment of indoor communications systems.
{"title":"Bandwidth efficient localization for sustainable and safe building environments","authors":"A. Kalis, M. Milis, A. Kounoudes, A. Constantinides","doi":"10.5281/ZENODO.43585","DOIUrl":"https://doi.org/10.5281/ZENODO.43585","url":null,"abstract":"The objective of this work is to propose the use of innovative low-cost wireless sensor network nodes equipped with smart antennas, so as to meet the goal of creating a sustainable and safe building environment. The proposed wireless sensor network system can provide information on people density within building areas, information that can be used in a number of applications such as energy footprint optimization, predictive maintenance and building safe evacuation. The unique design of the proposed sensor nodes can be supportive to the aforementioned applications by providing people location information and building area usage in a bandwidth efficient way, in order to enable such systems to be integrated into existing low-bandwidth in-building communication systems, such as fire alert and automation networks. Node architecture is based on the use of low-cost and low-complexity switched beam antennas and the use of a localization estimation algorithm based on angle of arrival measurements which, as opposed to popular received signal strength based algorithms, are not affected by the severe multipath environment of indoor communications systems.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127239210","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}
In a recent study a novel classification algorithm called the Sparse Classifier (SC) assumes that if a test sample belongs to class k then it can be approximately represented by a linear combination of the training samples belonging to k. Good face recognition results were obtained by the SC method. This paper proposes two generalizations of the aforesaid assumption. The first generalization assumes that the test sample raised to a power can be approximated by a linear combination of the training samples of that class raised to the same powers. The second generalization assumes that the test samples raised to a power can be approximately represented by a non-linear combination of the training samples raised to the same power. The first generalization requires solving a group-sparse optimization problem with linear constraints while the second assumption requires solving a group-sparse optimization problem with non-linear constraints. We propose two greedy sub-optimal algorithms to solve the said problems. The classifiers developed in this work are used for single-image-per-person face recognition. We find that our first generalization leads to an improvement of 2-3% in recognition accuracy over SC, while the second generalization improves the recognition accuracy even further; about 6-7% better than the first generalization.
{"title":"Generalized Non-linear Sparse Classifier","authors":"A. Majumdar, R. Ward, T. Aboulnasr","doi":"10.5281/ZENODO.43381","DOIUrl":"https://doi.org/10.5281/ZENODO.43381","url":null,"abstract":"In a recent study a novel classification algorithm called the Sparse Classifier (SC) assumes that if a test sample belongs to class k then it can be approximately represented by a linear combination of the training samples belonging to k. Good face recognition results were obtained by the SC method. This paper proposes two generalizations of the aforesaid assumption. The first generalization assumes that the test sample raised to a power can be approximated by a linear combination of the training samples of that class raised to the same powers. The second generalization assumes that the test samples raised to a power can be approximately represented by a non-linear combination of the training samples raised to the same power. The first generalization requires solving a group-sparse optimization problem with linear constraints while the second assumption requires solving a group-sparse optimization problem with non-linear constraints. We propose two greedy sub-optimal algorithms to solve the said problems. The classifiers developed in this work are used for single-image-per-person face recognition. We find that our first generalization leads to an improvement of 2-3% in recognition accuracy over SC, while the second generalization improves the recognition accuracy even further; about 6-7% better than the first generalization.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128878090","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}
Pascal Schöttle, Aron Laszka, Benjamin Johnson, Jens Grossklags, Rainer Böhme
We provide a game-theoretic analysis of a scenario from the field of content-adaptive steganography. Alice, a steganographer, wants to embed a secret message into a random binary sequence with a known distribution in which the value of each position is independently but non-identically distributed. Eve, a steganalyst, observes the sequence and wants to determine whether it contains a hidden message. Alice is allowed to flip binary values independently at random, with the constraint that the expected number of changes is a fixed constant. Eve may choose to classify each sequence as either unmodified (cover) or modified (stego). The payoff for Eve in the game is the probability that her classification is correct; and the payoff for Alice is the probability that Eve's classification is incorrect, so that the game is constant-sum. We show that Eve's best response strategy in this game can be expressed as a linear aggregation threshold formula similar to those used in practical steganalysis. We give a general formula for Alice's best response strategy; and we compute explicit pure strategy equilibria for the special case of changing one bit in a length-two sequence.
{"title":"A game-theoretic analysis of content-adaptive steganography with independent embedding","authors":"Pascal Schöttle, Aron Laszka, Benjamin Johnson, Jens Grossklags, Rainer Böhme","doi":"10.5281/ZENODO.43653","DOIUrl":"https://doi.org/10.5281/ZENODO.43653","url":null,"abstract":"We provide a game-theoretic analysis of a scenario from the field of content-adaptive steganography. Alice, a steganographer, wants to embed a secret message into a random binary sequence with a known distribution in which the value of each position is independently but non-identically distributed. Eve, a steganalyst, observes the sequence and wants to determine whether it contains a hidden message. Alice is allowed to flip binary values independently at random, with the constraint that the expected number of changes is a fixed constant. Eve may choose to classify each sequence as either unmodified (cover) or modified (stego). The payoff for Eve in the game is the probability that her classification is correct; and the payoff for Alice is the probability that Eve's classification is incorrect, so that the game is constant-sum. We show that Eve's best response strategy in this game can be expressed as a linear aggregation threshold formula similar to those used in practical steganalysis. We give a general formula for Alice's best response strategy; and we compute explicit pure strategy equilibria for the special case of changing one bit in a length-two sequence.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132660060","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}
Muhammad-Adeel Waris, Honglei Zhang, I. Ahmad, S. Kiranyaz, M. Gabbouj
True authentication predicted on biometrics has received upsurge attention during the last few years, as it provides facile way to access the system through basic physical and behavioral characteristics. Face recognition being a non-intrusive recognition requires less participation from the user compared to iris, speech and fingerprint based biometric. Resistance to false authentication from photographs and video playbacks is a vigorous issue for successful biometric system. This paper analyzes different textural features and proposes a novel approach for anti-spoofing solution. Experiments were conducted on a publicly available face spoofing database REPLAY-ATTACK to validate textural analysis over a database containing printed photographs, photos and videos displayed on electronic screens. Results show that the approach is superior to the other existing state of art approaches tested on same database.
{"title":"Analysis of textural features for face biometric anti-spoofing","authors":"Muhammad-Adeel Waris, Honglei Zhang, I. Ahmad, S. Kiranyaz, M. Gabbouj","doi":"10.5281/ZENODO.43537","DOIUrl":"https://doi.org/10.5281/ZENODO.43537","url":null,"abstract":"True authentication predicted on biometrics has received upsurge attention during the last few years, as it provides facile way to access the system through basic physical and behavioral characteristics. Face recognition being a non-intrusive recognition requires less participation from the user compared to iris, speech and fingerprint based biometric. Resistance to false authentication from photographs and video playbacks is a vigorous issue for successful biometric system. This paper analyzes different textural features and proposes a novel approach for anti-spoofing solution. Experiments were conducted on a publicly available face spoofing database REPLAY-ATTACK to validate textural analysis over a database containing printed photographs, photos and videos displayed on electronic screens. Results show that the approach is superior to the other existing state of art approaches tested on same database.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132958089","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}
Mobile wideband speech communication (HD Voice) is more and more available in the past years, primarily in 3G networks. The specifics of mobile communication - even if it is packet-switched - is that received frames with residual bit errors after channel decoding must not necessarily be marked as lost, instead they may be marked as bad (bad frame indicator, BFI). In this work we present how to exploit the information of a soft input (i. e., a log-likelihood ratio input) within the Adaptive Multirate Wideband (AMR-WB) speech decoder, allowing a more robust error concealment as compared to the 3GPP Recommendation. Log-likelihood ratios may be taken from a soft-output channel decoder, or, as in our generic simulation, directly from the demodulator, without the need of a BFI. Since error concealment is non-mandatory, chipset manufacturers are free to implement this alternative speech decoding scheme still in a standard-compliant fashion.
{"title":"Improved amr wideband error concealment for mobile communications","authors":"Sai Han, Florian Pflug, T. Fingscheidt","doi":"10.5281/ZENODO.43321","DOIUrl":"https://doi.org/10.5281/ZENODO.43321","url":null,"abstract":"Mobile wideband speech communication (HD Voice) is more and more available in the past years, primarily in 3G networks. The specifics of mobile communication - even if it is packet-switched - is that received frames with residual bit errors after channel decoding must not necessarily be marked as lost, instead they may be marked as bad (bad frame indicator, BFI). In this work we present how to exploit the information of a soft input (i. e., a log-likelihood ratio input) within the Adaptive Multirate Wideband (AMR-WB) speech decoder, allowing a more robust error concealment as compared to the 3GPP Recommendation. Log-likelihood ratios may be taken from a soft-output channel decoder, or, as in our generic simulation, directly from the demodulator, without the need of a BFI. Since error concealment is non-mandatory, chipset manufacturers are free to implement this alternative speech decoding scheme still in a standard-compliant fashion.","PeriodicalId":400766,"journal":{"name":"21st European Signal Processing Conference (EUSIPCO 2013)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133219417","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：