Pub Date : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029444
M. Kucarov, Mátyás Takács, B. Molnár, M. Kozlovszky
Transparent slide detection, pick and place automation are obtained in order to boost speed, accuracy and smooth workflow between slide coverslipping and digital scanning operation in digital pathology. Fully automatic, precise, robust solution has been developed by robotic arm using computer vision and image processing techniques. Magazine (slide holder) and gripper design, camera selection and mapping to robot base coordinate system are all guided. Python based software algorithms for slide detection and 3D position determination applied in dynamically changeable environment are also explained step by step. Complete automatic process control method is implemented and tested for different types of slide.
{"title":"Transparent Slide Detection and Gripper Design for Slide Transport by Robotic Arm","authors":"M. Kucarov, Mátyás Takács, B. Molnár, M. Kozlovszky","doi":"10.1109/CINTI-MACRo57952.2022.10029444","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029444","url":null,"abstract":"Transparent slide detection, pick and place automation are obtained in order to boost speed, accuracy and smooth workflow between slide coverslipping and digital scanning operation in digital pathology. Fully automatic, precise, robust solution has been developed by robotic arm using computer vision and image processing techniques. Magazine (slide holder) and gripper design, camera selection and mapping to robot base coordinate system are all guided. Python based software algorithms for slide detection and 3D position determination applied in dynamically changeable environment are also explained step by step. Complete automatic process control method is implemented and tested for different types of slide.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"266 1","pages":"000031-000036"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77491779","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029503
Eniko Nagy, Ildikó Holik
The technological developments of the 21st century have a significant impact on the way people live and work. Advances in artificial intelligence and robotics have enabled the appearance of industrial, agricultural, health, scientific, domestic, service and educational robots. Humanoid robots often evoke extreme emotions in humans. In our questionnaire survey of educators, we investigate negative attitudes towards robots. The results of the research highlighted the extreme feelings that the teachers surveyed have towards robots. In particular, they fear that robots will become too human-like. However, teachers who are open to the use of robots in several subjects can imagine robots acting as teaching assistants in teaching and administration. In order to develop and shape attitudes towards robots, it would be important to provide information and experience in teacher training and in-service teacher training.
{"title":"Examining negative attitudes towards robots among teachers","authors":"Eniko Nagy, Ildikó Holik","doi":"10.1109/CINTI-MACRo57952.2022.10029503","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029503","url":null,"abstract":"The technological developments of the 21st century have a significant impact on the way people live and work. Advances in artificial intelligence and robotics have enabled the appearance of industrial, agricultural, health, scientific, domestic, service and educational robots. Humanoid robots often evoke extreme emotions in humans. In our questionnaire survey of educators, we investigate negative attitudes towards robots. The results of the research highlighted the extreme feelings that the teachers surveyed have towards robots. In particular, they fear that robots will become too human-like. However, teachers who are open to the use of robots in several subjects can imagine robots acting as teaching assistants in teaching and administration. In order to develop and shape attitudes towards robots, it would be important to provide information and experience in teacher training and in-service teacher training.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"140 1","pages":"000221-000226"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77636139","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029641
K. Jäckel, Mónika Garai-Fodor
A significant challenge for human resources professionals is that there are currently four different generations working in the labour market. The youngest one, Generation Z, is the most different from the previous generations and therefore, managing them requires a different approach. It is crucial for employers to be aware of the mentality, values and expectations of Generation Z in order to create a generation-specific employer branding strategy. The objective has three components. To attract and retain the most valuable employees for the corporate culture in the long term, and to achieve the most effective cooperation between the 4 generations, taking into account both rational and emotional aspects. In our research we interviewed 540 people. The sample is not representative, but it allows us to formulate causal relationships.We believe that the results of our research could help employers and managers to pay attention to the differences, values, benefits and sometimes conflicts between the generations and to deal with them in a more differentiated approach.
{"title":"Intergenerational cooperation and generational differences at work","authors":"K. Jäckel, Mónika Garai-Fodor","doi":"10.1109/CINTI-MACRo57952.2022.10029641","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029641","url":null,"abstract":"A significant challenge for human resources professionals is that there are currently four different generations working in the labour market. The youngest one, Generation Z, is the most different from the previous generations and therefore, managing them requires a different approach. It is crucial for employers to be aware of the mentality, values and expectations of Generation Z in order to create a generation-specific employer branding strategy. The objective has three components. To attract and retain the most valuable employees for the corporate culture in the long term, and to achieve the most effective cooperation between the 4 generations, taking into account both rational and emotional aspects. In our research we interviewed 540 people. The sample is not representative, but it allows us to formulate causal relationships.We believe that the results of our research could help employers and managers to pay attention to the differences, values, benefits and sometimes conflicts between the generations and to deal with them in a more differentiated approach.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"120 1","pages":"000171-000176"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90779592","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029498
Márton Máté, Ferenc Tolvaly-Rosca, Norbert Hodgyai, M. Dragoi
This paper presents a new approach to defining the grinding wheel profile used for module gear hob’s helical rake face grinding. After a brief presentation of former results, the geometric and mathematic model of the grinding is analyzed. The model differs from those based on the classical meshing theory, using instead the method of the space restriction, when one of the involved surfaces splits the 3D space in two subspaces. The revolution surface of the grinding wheel must fit the limit surface obtained by the revolving of the helical surface of the rake face. The geometrical model is supported by numerical example, followed by CAD-simulation. The conclusion confirms that the actual technological system set as presented in this paper, and used as the same in many practical applications, is unable to realize a helical surface that fits the theoretical equations stated in the literature.
{"title":"A new approach of defining the grinding wheel profile of the Gear Hob’s Rake Face","authors":"Márton Máté, Ferenc Tolvaly-Rosca, Norbert Hodgyai, M. Dragoi","doi":"10.1109/CINTI-MACRo57952.2022.10029498","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029498","url":null,"abstract":"This paper presents a new approach to defining the grinding wheel profile used for module gear hob’s helical rake face grinding. After a brief presentation of former results, the geometric and mathematic model of the grinding is analyzed. The model differs from those based on the classical meshing theory, using instead the method of the space restriction, when one of the involved surfaces splits the 3D space in two subspaces. The revolution surface of the grinding wheel must fit the limit surface obtained by the revolving of the helical surface of the rake face. The geometrical model is supported by numerical example, followed by CAD-simulation. The conclusion confirms that the actual technological system set as presented in this paper, and used as the same in many practical applications, is unable to realize a helical surface that fits the theoretical equations stated in the literature.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"1 1","pages":"000069-000076"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89612836","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029486
Katalin Ferencz, J. Domokos, L. Kovács
The integration of sensors in our everyday lives and in industry presents a serious challenge to data analysis professionals. Since the use of smart devices has exponentially increased the amount of data collected in all areas, we must not only store these data, but also extract valuable information from those using some data analysis method. In many cases, the increased amount of data also causes problems for data analysis algorithms, so we need to be continuously updated and specialized for fundamental purposes. In the article, we will present some data analysis techniques, starting from the simplest statistical methods to more complex techniques using machine learning and presenting one of their possible applications. In our study, we will use the KMeans clustering algorithm and examine its effectiveness in time series sensor data analysis.
{"title":"Analysis of time series data for anomaly detection","authors":"Katalin Ferencz, J. Domokos, L. Kovács","doi":"10.1109/CINTI-MACRo57952.2022.10029486","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029486","url":null,"abstract":"The integration of sensors in our everyday lives and in industry presents a serious challenge to data analysis professionals. Since the use of smart devices has exponentially increased the amount of data collected in all areas, we must not only store these data, but also extract valuable information from those using some data analysis method. In many cases, the increased amount of data also causes problems for data analysis algorithms, so we need to be continuously updated and specialized for fundamental purposes. In the article, we will present some data analysis techniques, starting from the simplest statistical methods to more complex techniques using machine learning and presenting one of their possible applications. In our study, we will use the KMeans clustering algorithm and examine its effectiveness in time series sensor data analysis.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"35 1","pages":"000095-000100"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80942795","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029656
Paulo A. Salgado, T. Perdicoulis, P. Santos
The use of robots is widely spread across the industry. It is paramount that the robot end-effector tracks a pre-defined trajectory with the lowest energy loss. To contribute to the solution of this problem, the robot trajectory is defined using a tracking parameter which is optimised using the Matlab® fntinunc function and the Particle Swam optimisation algorithm. This approach was tested for a case study with the energy loss being reduced in approximately 96.15%.
{"title":"Energy loss optimisation of a robotic arm","authors":"Paulo A. Salgado, T. Perdicoulis, P. Santos","doi":"10.1109/CINTI-MACRo57952.2022.10029656","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029656","url":null,"abstract":"The use of robots is widely spread across the industry. It is paramount that the robot end-effector tracks a pre-defined trajectory with the lowest energy loss. To contribute to the solution of this problem, the robot trajectory is defined using a tracking parameter which is optimised using the Matlab® fntinunc function and the Particle Swam optimisation algorithm. This approach was tested for a case study with the energy loss being reduced in approximately 96.15%.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"228 1","pages":"000101-000106"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75690171","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029554
Keyvan Rahimi, R. Rituraj, D. Ecker
Clinically, using fundus pictures for predicting and detecting blind illnesses such as diabetic retinopathy (DR) is crucial. Deep learning (DL) is becoming a more common and promising technique in the different applications of DR, such as prediction, detection, classification, and disease diagnosis. Developing a review paper to analyze the DL techniques and their performance in the field is essential. We prepared a standard systematic review database including 341 publications. Accordingly, the main aim of the present review work is to present a systematic state-of-the-art by relying on PRISMA guidelines for the performance analysis of the DL in DR applications. The study has been shown in three main steps. The first step is to collect the database, the second step is to analyze the databases, and the last step is to conclude the study’s main findings. According to the results, most studies employed accuracy as the most reliable and general evaluation metric for analyzing the DL techniques in different DR applications. Also, CNN has the most share of applications compared to other DL techniques. On the other hand, the best performance is related to the ensemble and advanced DL techniques. We’ll also publish and regularly update the most recent discoveries in future studies to stay up with the quick technological improvements.
{"title":"Deep Learning for Diabetic Retinopathy in Fundus Images","authors":"Keyvan Rahimi, R. Rituraj, D. Ecker","doi":"10.1109/CINTI-MACRo57952.2022.10029554","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029554","url":null,"abstract":"Clinically, using fundus pictures for predicting and detecting blind illnesses such as diabetic retinopathy (DR) is crucial. Deep learning (DL) is becoming a more common and promising technique in the different applications of DR, such as prediction, detection, classification, and disease diagnosis. Developing a review paper to analyze the DL techniques and their performance in the field is essential. We prepared a standard systematic review database including 341 publications. Accordingly, the main aim of the present review work is to present a systematic state-of-the-art by relying on PRISMA guidelines for the performance analysis of the DL in DR applications. The study has been shown in three main steps. The first step is to collect the database, the second step is to analyze the databases, and the last step is to conclude the study’s main findings. According to the results, most studies employed accuracy as the most reliable and general evaluation metric for analyzing the DL techniques in different DR applications. Also, CNN has the most share of applications compared to other DL techniques. On the other hand, the best performance is related to the ensemble and advanced DL techniques. We’ll also publish and regularly update the most recent discoveries in future studies to stay up with the quick technological improvements.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"8 1","pages":"000351-000358"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75931455","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029540
C. Köllod, Nikomidisz Jorgosz Eftimiu, G. Márton, I. Ulbert
Accurate Multi-class EMG signal classification is one of the key aspects of EMG-based prosthesis control. The other is a sufficient database. In this article, the process and classification of EMG signals are presented, which were recorded with the lightweight, easy-to-setup, semi-dry, 8-channeled, wireless MindRove Armband electrode system. Individual finger movements were captured with depth cameras, while the corresponding EMG signal was recorded. The labels about the executed movements were generated with a semi-automated algorithm. On the generated dataset Multiple classifiers, namely Random Forest, Extra Trees, Support Vector Machine, Nu-SVM, EEGNet, Ensemble, and Voting methods were tested and compared. Moreover, parameter searches were conducted, to increase the accuracy levels. In the case of EEGNet, the effect of transfer learning was also investigated.
{"title":"Classification of Semi-Automated Labeled MindRove Armband Recorded EMG Data","authors":"C. Köllod, Nikomidisz Jorgosz Eftimiu, G. Márton, I. Ulbert","doi":"10.1109/CINTI-MACRo57952.2022.10029540","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029540","url":null,"abstract":"Accurate Multi-class EMG signal classification is one of the key aspects of EMG-based prosthesis control. The other is a sufficient database. In this article, the process and classification of EMG signals are presented, which were recorded with the lightweight, easy-to-setup, semi-dry, 8-channeled, wireless MindRove Armband electrode system. Individual finger movements were captured with depth cameras, while the corresponding EMG signal was recorded. The labels about the executed movements were generated with a semi-automated algorithm. On the generated dataset Multiple classifiers, namely Random Forest, Extra Trees, Support Vector Machine, Nu-SVM, EEGNet, Ensemble, and Voting methods were tested and compared. Moreover, parameter searches were conducted, to increase the accuracy levels. In the case of EEGNet, the effect of transfer learning was also investigated.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"14 1","pages":"000381-000386"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81682180","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029466
D. Wheeler, J. Olszewska
Current technological advances and the growth of smart applications and services require the development of multi-platform mobile applications. Writing software to run on multiple computing platforms can involve a large amount of duplicate effort. This duplicate effort can take the form of re-implementing the business logic in a different language, re-implementing the user interface or, in many cases, re-implementing both for each platform. There are many cross-platform frameworks to help reduce or eliminate this effort, but they make compromises on performance or user experience. Hence, this paper presents a cross-platform framework whose goal is to reduce this compromise by aiming to minimise platform-specific code, but not eliminate it. Using this method will allow all platforms to have a featurerich, native interface, with most of the code, including user interface code, contained in a cross-platform library used by all platforms. Hence, this work establishes a framework for developing cross-platform GUI applications, involving the design and development of a common library as well as translation libraries for iOS, Android, and Windows. This developed framework has been successfully applied to the implementation of a real-world application for smart lift services.
{"title":"Cross-Platform Mobile Application Development for Smart Services","authors":"D. Wheeler, J. Olszewska","doi":"10.1109/CINTI-MACRo57952.2022.10029466","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029466","url":null,"abstract":"Current technological advances and the growth of smart applications and services require the development of multi-platform mobile applications. Writing software to run on multiple computing platforms can involve a large amount of duplicate effort. This duplicate effort can take the form of re-implementing the business logic in a different language, re-implementing the user interface or, in many cases, re-implementing both for each platform. There are many cross-platform frameworks to help reduce or eliminate this effort, but they make compromises on performance or user experience. Hence, this paper presents a cross-platform framework whose goal is to reduce this compromise by aiming to minimise platform-specific code, but not eliminate it. Using this method will allow all platforms to have a featurerich, native interface, with most of the code, including user interface code, contained in a cross-platform library used by all platforms. Hence, this work establishes a framework for developing cross-platform GUI applications, involving the design and development of a common library as well as translation libraries for iOS, Android, and Windows. This developed framework has been successfully applied to the implementation of a real-world application for smart lift services.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87448334","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 : 2022-11-21DOI: 10.1109/CINTI-MACRo57952.2022.10029473
Kristóf Takács, R. Elek, T. Haidegger
Image processing techniques are having a huge impact on most fields of robotics and industrial automation. Real-time methods are usually employed in complex automation tasks, assisting with decision making or directly guiding robots and machinery, while post-processing is usually used for retrospective assessment of systems and processes. While artificial intelligence-based image processing algorithms (relying usually on neural networks) are more common nowadays, “classical” image processing methods can also be used effectively for most modern applications. This paper focuses on optical flow-based image processing, proving its efficiency by presenting optical flow-based solutions for modern challenges in different fields of robotics, such as robot-assisted surgery and food processing. The application domain introduced in this paper is based on a smart robotic gripper designed to support automated robot cells in the meat industry. The gripper is capable of slip detection and secure gripping of soft, slippery tissues with the help of the implemented real-time algorithm.
{"title":"Image Processing-Based Methods to Improve the Robustness of Robotic Gripping","authors":"Kristóf Takács, R. Elek, T. Haidegger","doi":"10.1109/CINTI-MACRo57952.2022.10029473","DOIUrl":"https://doi.org/10.1109/CINTI-MACRo57952.2022.10029473","url":null,"abstract":"Image processing techniques are having a huge impact on most fields of robotics and industrial automation. Real-time methods are usually employed in complex automation tasks, assisting with decision making or directly guiding robots and machinery, while post-processing is usually used for retrospective assessment of systems and processes. While artificial intelligence-based image processing algorithms (relying usually on neural networks) are more common nowadays, “classical” image processing methods can also be used effectively for most modern applications. This paper focuses on optical flow-based image processing, proving its efficiency by presenting optical flow-based solutions for modern challenges in different fields of robotics, such as robot-assisted surgery and food processing. The application domain introduced in this paper is based on a smart robotic gripper designed to support automated robot cells in the meat industry. The gripper is capable of slip detection and secure gripping of soft, slippery tissues with the help of the implemented real-time algorithm.","PeriodicalId":18535,"journal":{"name":"Micro","volume":"8 1","pages":"000345-000350"},"PeriodicalIF":0.0,"publicationDate":"2022-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75164961","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：