The state-of-the-art for Relation Extraction, defined as the detection of existing relations between a pair of entities in a sentence, relies on neural networks that require a large number of training examples to perform well. To address that cost, Distant Supervision has become the preferred choice for collecting labeled sentences. However, Distant Supervision has many limitations and often introduces noise into the training set. Recent work has shown an alternative way of training neural methods for relation extraction, namely to provide a small number of annotated sentences and explanations for why those sentences express the relation. Training classifiers with this approach results in accuracy comparable to Distant Supervision, but requires humans to annotate the sentences and provide the explanations. In this paper, we show a way to generate synthetic explanations from a small number of relational trigger words, for each relation, whose resulting explanations achieve comparable accuracy to human produced ones. We validate the method on five relation extraction tasks with different entity types (person-person, person-location, etc.). Furthermore, experiments on two public datasets demonstrate the effectiveness of our generated synthetic explanations, with 6% improvement in accuracy on relation extraction and 19% improvement in F1-score on generating labeled training sentences compared to the next best methods.
{"title":"Relation Extraction with Synthetic Explanations and Neural Network","authors":"Rozan Chahardoli, Denilson Barbosa, Davood Rafiei","doi":"10.1145/3459104.3459147","DOIUrl":"https://doi.org/10.1145/3459104.3459147","url":null,"abstract":"The state-of-the-art for Relation Extraction, defined as the detection of existing relations between a pair of entities in a sentence, relies on neural networks that require a large number of training examples to perform well. To address that cost, Distant Supervision has become the preferred choice for collecting labeled sentences. However, Distant Supervision has many limitations and often introduces noise into the training set. Recent work has shown an alternative way of training neural methods for relation extraction, namely to provide a small number of annotated sentences and explanations for why those sentences express the relation. Training classifiers with this approach results in accuracy comparable to Distant Supervision, but requires humans to annotate the sentences and provide the explanations. In this paper, we show a way to generate synthetic explanations from a small number of relational trigger words, for each relation, whose resulting explanations achieve comparable accuracy to human produced ones. We validate the method on five relation extraction tasks with different entity types (person-person, person-location, etc.). Furthermore, experiments on two public datasets demonstrate the effectiveness of our generated synthetic explanations, with 6% improvement in accuracy on relation extraction and 19% improvement in F1-score on generating labeled training sentences compared to the next best methods.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131033710","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}
Thomaz Calasans, Anna Helena Reali Costa, Eduardo R. Hruschka
Contextualised word embeddings have recently become essential elements of Natural Language Processing (NLP) systems since these embedding models encode not only words but also their contexts to generate context-specific representations. Pre-trained models such as BERT, GPT, and derived architectures are increasingly present on NLP task benchmarks. Several comparative analyses of such models have been performed, but so far no one compares the most recent architectures in a dialogue generation dataset by considering multiple metrics relevant to the task. In this paper, we not only propose an encoder-decoder system that uses transfer learning with pre-trained word embeddings, but we also systematically compare various pretrained contextualised word embedding architectures on the DSTC-7 dataset, using metrics based on mutual information, dialogue length, and variety of answers. We use the word embeddings as a first layer of the encoder, making it possible to encode the texts in a latent space. As a decoder, we use an LSTM layer and a byte pair encoding tokenisation, aligned with state-of-the-art dialogue systems recently published. The networks are trained during the same amount of epochs, with the same optimisers and learning rates. Considering the quality of the dialogue, our results show that there is no superior technique on all metrics. However, there are relevant differences concerning the computational costs to encode the data.
{"title":"Contextualised Word Embeddings Based on Transfer Learning to Dialogue Response Generation: a Proposal and Comparisons","authors":"Thomaz Calasans, Anna Helena Reali Costa, Eduardo R. Hruschka","doi":"10.1145/3459104.3459169","DOIUrl":"https://doi.org/10.1145/3459104.3459169","url":null,"abstract":"Contextualised word embeddings have recently become essential elements of Natural Language Processing (NLP) systems since these embedding models encode not only words but also their contexts to generate context-specific representations. Pre-trained models such as BERT, GPT, and derived architectures are increasingly present on NLP task benchmarks. Several comparative analyses of such models have been performed, but so far no one compares the most recent architectures in a dialogue generation dataset by considering multiple metrics relevant to the task. In this paper, we not only propose an encoder-decoder system that uses transfer learning with pre-trained word embeddings, but we also systematically compare various pretrained contextualised word embedding architectures on the DSTC-7 dataset, using metrics based on mutual information, dialogue length, and variety of answers. We use the word embeddings as a first layer of the encoder, making it possible to encode the texts in a latent space. As a decoder, we use an LSTM layer and a byte pair encoding tokenisation, aligned with state-of-the-art dialogue systems recently published. The networks are trained during the same amount of epochs, with the same optimisers and learning rates. Considering the quality of the dialogue, our results show that there is no superior technique on all metrics. However, there are relevant differences concerning the computational costs to encode the data.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133435130","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 Predictive Control based on LSTM Neural Network and Differential Evolution optimization performs as a high-accuracy control of a Robotic Manipulator. Such system dynamics are known as highly non-linear systems, where multiple input and outputs are involved. Therefore, Model Predictive Control was selected as a regulator system to follow a complex trajectory given by a simulated problem. Based on simulated data, we trained a Neural predictor as an approximation of each robot-joint dynamics, where the controller computes an optimal signal for a reference-tracker problem. We validate our claim with a numeric simulation where a mechanical model is employed. Our results show an increase in precision and vibration reduction while demonstrating the feasibility of a Predictive control law with Differential Evolution optimization in this scenario.
{"title":"LSTM Neural Network-based Predictive Control for a Robotic Manipulator","authors":"Edgar Ademir Morales-Perez, H. Iba","doi":"10.1145/3459104.3459127","DOIUrl":"https://doi.org/10.1145/3459104.3459127","url":null,"abstract":"In this paper, a Predictive Control based on LSTM Neural Network and Differential Evolution optimization performs as a high-accuracy control of a Robotic Manipulator. Such system dynamics are known as highly non-linear systems, where multiple input and outputs are involved. Therefore, Model Predictive Control was selected as a regulator system to follow a complex trajectory given by a simulated problem. Based on simulated data, we trained a Neural predictor as an approximation of each robot-joint dynamics, where the controller computes an optimal signal for a reference-tracker problem. We validate our claim with a numeric simulation where a mechanical model is employed. Our results show an increase in precision and vibration reduction while demonstrating the feasibility of a Predictive control law with Differential Evolution optimization in this scenario.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"499 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128217760","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}
This paper discusses the key technologies of designing and implementing thinking machine based on von Neumann architecture and the idea of analogy. Based on the three hypotheses: the creative thinking process is Turing computable, inspiration is composed of knowledge representation and commonsense judgment, and the type quantity of the knowledge representation and the commonsense used for judgment that form of inspiration is limited, the paper has established the creative thinking theory of knowledge representation and commonsense judgment, designed the working framework of the 3-loops thinking machine, and resolved the chickens and rabbits in the same cage problem in a humanoid way for example, the work flow and the data structure based thinking machine is explained. Finally, the key technical problems of realization of thinking machine are discussed.
{"title":"Key Technologies of Designing and Implementing Thinking Machine","authors":"Zhu Ping","doi":"10.1145/3459104.3459166","DOIUrl":"https://doi.org/10.1145/3459104.3459166","url":null,"abstract":"This paper discusses the key technologies of designing and implementing thinking machine based on von Neumann architecture and the idea of analogy. Based on the three hypotheses: the creative thinking process is Turing computable, inspiration is composed of knowledge representation and commonsense judgment, and the type quantity of the knowledge representation and the commonsense used for judgment that form of inspiration is limited, the paper has established the creative thinking theory of knowledge representation and commonsense judgment, designed the working framework of the 3-loops thinking machine, and resolved the chickens and rabbits in the same cage problem in a humanoid way for example, the work flow and the data structure based thinking machine is explained. Finally, the key technical problems of realization of thinking machine are discussed.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123243703","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}
Scenario-based testing is at present regarded as the enabling tool for the homologation of automated driving (AD) systems (SAE Level ≥ 3). This is mainly due to the aspiration of scenario-based testing for gaining understanding about the tested AD system, which provides support for arguments that shall convince ourselves about its capabilities. Since this way of testing involves system-dependent intertwinings, inconsistencies can thus impair the correctness of the homologation. In order to avoid this, we propose encapsulating these intertwinings by means of paradigms, which are individual mindsets towards homologation. For their definition, we introduce behaviors as a respective language, in combination with behavioral shifts, for the systematic derivation of what needs to be defined for a paradigm. The applicability is shown by mapping the derived paradigms against proposed approaches in automated driving. Furthermore, this systematics helps to identify concerns about using paradigms in scenario-based testing.
{"title":"Paradigms in Scenario-Based Testing for Automated Driving","authors":"Tino Brade, Birte Kramer, Christian Neurohr","doi":"10.1145/3459104.3459208","DOIUrl":"https://doi.org/10.1145/3459104.3459208","url":null,"abstract":"Scenario-based testing is at present regarded as the enabling tool for the homologation of automated driving (AD) systems (SAE Level ≥ 3). This is mainly due to the aspiration of scenario-based testing for gaining understanding about the tested AD system, which provides support for arguments that shall convince ourselves about its capabilities. Since this way of testing involves system-dependent intertwinings, inconsistencies can thus impair the correctness of the homologation. In order to avoid this, we propose encapsulating these intertwinings by means of paradigms, which are individual mindsets towards homologation. For their definition, we introduce behaviors as a respective language, in combination with behavioral shifts, for the systematic derivation of what needs to be defined for a paradigm. The applicability is shown by mapping the derived paradigms against proposed approaches in automated driving. Furthermore, this systematics helps to identify concerns about using paradigms in scenario-based testing.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126518116","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 article, we introduce an accurate yet robust method to recover the 6D pose of the object from an RGB image. The core of our method is using the farthest point sampling algorithm to design a set of representative keypoints on the object model surface, and then use the improved stacked hourglass network (ISHN) with multi-scale aggregation module to localize them in the 2D image by predicting the keypoints heatmaps. Finally, the PnP algorithm can recover the 6D pose according to the 3D-2D relationship of keypoints. Besides, when the object is partially occluded, we can successfully recover the pose of the object by selecting the most confident keypoints. Our method can simultaneously detect and recover the 6D pose of the instance object in the RGB image without additional post-processing steps. Experimental results show that compared with the state-of-the-art RGB-based pose estimation methods, our method can achieve competitive or more superior performance on two benchmark datasets.
{"title":"Improved Stacked Hourglass Network for Robust 6D Object Pose Estimation","authors":"Kun Li, Hui Zhang, Lei Peng","doi":"10.1145/3459104.3459177","DOIUrl":"https://doi.org/10.1145/3459104.3459177","url":null,"abstract":"In this article, we introduce an accurate yet robust method to recover the 6D pose of the object from an RGB image. The core of our method is using the farthest point sampling algorithm to design a set of representative keypoints on the object model surface, and then use the improved stacked hourglass network (ISHN) with multi-scale aggregation module to localize them in the 2D image by predicting the keypoints heatmaps. Finally, the PnP algorithm can recover the 6D pose according to the 3D-2D relationship of keypoints. Besides, when the object is partially occluded, we can successfully recover the pose of the object by selecting the most confident keypoints. Our method can simultaneously detect and recover the 6D pose of the instance object in the RGB image without additional post-processing steps. Experimental results show that compared with the state-of-the-art RGB-based pose estimation methods, our method can achieve competitive or more superior performance on two benchmark datasets.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115845979","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}
Ferroelectric europium-doped strontium bismuth tantalate (Eu-SBT) phosphors are one of promising materials in the electro-mechano-optical coupling. To provide the coupling device driving at low voltage, the crystallinity, ferroelectric and photoluminescent properties of sol-gel-derived Eu-SBT thin films were investigated in the film thickness ranging from 98 nm to 47 nm. The prepared Eu-SBT thin films exhibited the well-saturated hysteresis loop according to the polarization reversal. The remanent polarization decreased with the film thickness, however, its value of about 2 μC/cm2 was remained even when the film thickness was 47 nm. The degradation of the remanent polarization led to the changing of the photoluminescent spectrum. The emission peaks at 615 nm associated with the 5D0→7F2 transition of the Eu3+ ion was reduced in the thick Eu-SBT films, however, was enhanced in the thinner films. The sub-100-mm thick Eu-SBT films were promising candidate as red-phosphor thin film with the electro-mechano-optical coupling function.
{"title":"Photoluminescent Spectrum Changes Associated With Remanent Polarization Degradation in Sub-100-nm-thick europium-doped Strontium Bismuth Tantalate Red-phosphor Thin Films","authors":"K. Aizawa","doi":"10.1145/3459104.3459157","DOIUrl":"https://doi.org/10.1145/3459104.3459157","url":null,"abstract":"Ferroelectric europium-doped strontium bismuth tantalate (Eu-SBT) phosphors are one of promising materials in the electro-mechano-optical coupling. To provide the coupling device driving at low voltage, the crystallinity, ferroelectric and photoluminescent properties of sol-gel-derived Eu-SBT thin films were investigated in the film thickness ranging from 98 nm to 47 nm. The prepared Eu-SBT thin films exhibited the well-saturated hysteresis loop according to the polarization reversal. The remanent polarization decreased with the film thickness, however, its value of about 2 μC/cm2 was remained even when the film thickness was 47 nm. The degradation of the remanent polarization led to the changing of the photoluminescent spectrum. The emission peaks at 615 nm associated with the 5D0→7F2 transition of the Eu3+ ion was reduced in the thick Eu-SBT films, however, was enhanced in the thinner films. The sub-100-mm thick Eu-SBT films were promising candidate as red-phosphor thin film with the electro-mechano-optical coupling function.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"264 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116668596","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 order to avoid the over-fitting of the model, the adaptive LASSO method was used to the variables selection of the binary quantile regression model. Bayesian method is use to construct the Gibbs sampling algorithm and the constraint condition that does not affect the predictive result is used to improve the stability of the sampling value. That the improved model has better parameter estimation efficiency and variable selection effect and classification ability are illustrated in the numerical simulation.
{"title":"Improvement of Adaptive Lasso in Binary Quantile Regression","authors":"Sheng Fu","doi":"10.1145/3459104.3459190","DOIUrl":"https://doi.org/10.1145/3459104.3459190","url":null,"abstract":"In order to avoid the over-fitting of the model, the adaptive LASSO method was used to the variables selection of the binary quantile regression model. Bayesian method is use to construct the Gibbs sampling algorithm and the constraint condition that does not affect the predictive result is used to improve the stability of the sampling value. That the improved model has better parameter estimation efficiency and variable selection effect and classification ability are illustrated in the numerical simulation.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121722287","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}
K. Namee, Nimit Srikamta, Somchoke Kittisitthipong, J. Polpinij
Most of today's technology has begun to move towards wireless technology. Even the network technology itself. That has been used WiFi technology, or the full name is Wireless Fidelity to replace the traditional network connection that uses LAN cable. For more convenience to use, it is at this point that WiFi technology is required to use a signal to link data between a user's device and a device in the system. For this reason, most company has a need to provide wireless network service to users. Helps service customers know the location of the users within the building. Allowing customers to use the Free Internet service of customers to promote the location to customers. The researchers have therefore studied and saw the positioning technology of devices entering the access point distribution range. It uses the same positioning theory used in GPS so that service providers can monitor people who enter the building. Also, can be furthered to find the user in different areas to allocate resources in that area appropriately. The technology selected for this propose is CMX because there is a work that meets the needs of all clients and most importantly, all devices in this work, whether they are access points, switches and servers.
{"title":"Applying CMX Tracking for Identifying the Indoor Positioning of Wireless Devices","authors":"K. Namee, Nimit Srikamta, Somchoke Kittisitthipong, J. Polpinij","doi":"10.1145/3459104.3459140","DOIUrl":"https://doi.org/10.1145/3459104.3459140","url":null,"abstract":"Most of today's technology has begun to move towards wireless technology. Even the network technology itself. That has been used WiFi technology, or the full name is Wireless Fidelity to replace the traditional network connection that uses LAN cable. For more convenience to use, it is at this point that WiFi technology is required to use a signal to link data between a user's device and a device in the system. For this reason, most company has a need to provide wireless network service to users. Helps service customers know the location of the users within the building. Allowing customers to use the Free Internet service of customers to promote the location to customers. The researchers have therefore studied and saw the positioning technology of devices entering the access point distribution range. It uses the same positioning theory used in GPS so that service providers can monitor people who enter the building. Also, can be furthered to find the user in different areas to allocate resources in that area appropriately. The technology selected for this propose is CMX because there is a work that meets the needs of all clients and most importantly, all devices in this work, whether they are access points, switches and servers.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121881284","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}
Andrea Borgese, L. Cantelli, D. Guastella, Giuseppe Sutera, G. Muscato
Robots and drones are useful devices where operations are expensive, tedious, or dangerous for humans. Recently the decrease of cost of robotic devices has extended the range of applications of robotic systems particularly in hazardous environments. The cooperation between drones and robots can give further possibilities and opens new challenges. In this work some environments and scenarios where robots and drones and their cooperation could be effective, are shortly reviewed and commented. In particular, four different situations are described with experimental results: the exploration of active volcanic environments, the search of mines for humanitarian demining, the radioactive waste inspections and the assessment on terrains with high landslide risk. Finally, some conclusions and perspectives for future applications conclude the paper.
{"title":"Highlights on some Robots and Drones for Hazardous Environments","authors":"Andrea Borgese, L. Cantelli, D. Guastella, Giuseppe Sutera, G. Muscato","doi":"10.1145/3459104.3459114","DOIUrl":"https://doi.org/10.1145/3459104.3459114","url":null,"abstract":"Robots and drones are useful devices where operations are expensive, tedious, or dangerous for humans. Recently the decrease of cost of robotic devices has extended the range of applications of robotic systems particularly in hazardous environments. The cooperation between drones and robots can give further possibilities and opens new challenges. In this work some environments and scenarios where robots and drones and their cooperation could be effective, are shortly reviewed and commented. In particular, four different situations are described with experimental results: the exploration of active volcanic environments, the search of mines for humanitarian demining, the radioactive waste inspections and the assessment on terrains with high landslide risk. Finally, some conclusions and perspectives for future applications conclude the paper.","PeriodicalId":142284,"journal":{"name":"2021 International Symposium on Electrical, Electronics and Information Engineering","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133187813","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：