Pub Date : 2021-12-01DOI: 10.1109/CSCI54926.2021.00117
Oyeyemi Osho, Sungbum Hong, T. Kwembe
Network Intrusion Detection Systems (IDS) have become expedient for network security and ensures the safety of all connected devices. Network Intrusion Detection System (IDS) alludes to observing network data information swiftly, detecting any intrusion pattern and preventing any harmful effect of anomaly intrusion that will cost the network. To combat this issue, we present in this concept paper an IDS based on the Principal Component Analysis (PCA) and Decision Tree Classifier algorithm, a supervised machine learning model to detect intrusion in the Network.
{"title":"Network Intrusion Detection System Using Principal Component Analysis Algorithm and Decision Tree Classifier","authors":"Oyeyemi Osho, Sungbum Hong, T. Kwembe","doi":"10.1109/CSCI54926.2021.00117","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00117","url":null,"abstract":"Network Intrusion Detection Systems (IDS) have become expedient for network security and ensures the safety of all connected devices. Network Intrusion Detection System (IDS) alludes to observing network data information swiftly, detecting any intrusion pattern and preventing any harmful effect of anomaly intrusion that will cost the network. To combat this issue, we present in this concept paper an IDS based on the Principal Component Analysis (PCA) and Decision Tree Classifier algorithm, a supervised machine learning model to detect intrusion in the Network.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131314811","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00100
Phillip Roshon, Feng-Jen Yang
In this study, we focus on a problem domain, construction problems, for reinforcement learning systems to optimize. We relate our approach to existing research in the field of automated theorem proving and other related techniques to optimize the solutions in this domain. We expect this study can inspire more interest in the adoption of and improve the efficiency of existing production systems.
{"title":"A Study on Deep Learning Approach to Optimize Solving Construction Problems","authors":"Phillip Roshon, Feng-Jen Yang","doi":"10.1109/CSCI54926.2021.00100","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00100","url":null,"abstract":"In this study, we focus on a problem domain, construction problems, for reinforcement learning systems to optimize. We relate our approach to existing research in the field of automated theorem proving and other related techniques to optimize the solutions in this domain. We expect this study can inspire more interest in the adoption of and improve the efficiency of existing production systems.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133803161","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00270
Javier Jose Diaz Rivera, Talha Ahmed Khan, Waleed Akbar, Muhammad Afaq, Wang-Cheol Song
Due to the advancements in machine learning and artificial intelligence applied fields, network anomaly detection systems have experienced an evolution from traditional signature-based methods for intrusion detection. Nonetheless, as security measures evolve, more sophisticated attacks are also constantly being developed by hackers. Not only a robust anomaly detection algorithm is needed, but also a real-time data feeding mechanism for minimizing the reaction-time impact is required. Moreover, DDoS attacks can flood the network data channels with more than thousands of packets per second with the latent effect of overloading most traditional monitoring systems that rely on data storage. Due to this, the research presented in this paper focuses its efforts on implementing a real-time data streaming system for network anomaly detection that can operate during a high volume of traffic data. The solution includes the deployment of a flow collector platform connected to Apache Kafka for receiving NetFlow data from network switches. Also, real-time big data processing techniques are applied through Apache Spark, where the ML anomaly detection is triggered. The detection of anomalies is performed by a combination of the unsupervised learning clustering algorithm k-means and the supervised learning classifier KNN (k- nearest neighbors). Finally, a monitoring system consisting of an ELK stack collects historical data for further evolution of the ML algorithms.
{"title":"An ML Based Anomaly Detection System in real-time data streams","authors":"Javier Jose Diaz Rivera, Talha Ahmed Khan, Waleed Akbar, Muhammad Afaq, Wang-Cheol Song","doi":"10.1109/CSCI54926.2021.00270","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00270","url":null,"abstract":"Due to the advancements in machine learning and artificial intelligence applied fields, network anomaly detection systems have experienced an evolution from traditional signature-based methods for intrusion detection. Nonetheless, as security measures evolve, more sophisticated attacks are also constantly being developed by hackers. Not only a robust anomaly detection algorithm is needed, but also a real-time data feeding mechanism for minimizing the reaction-time impact is required. Moreover, DDoS attacks can flood the network data channels with more than thousands of packets per second with the latent effect of overloading most traditional monitoring systems that rely on data storage. Due to this, the research presented in this paper focuses its efforts on implementing a real-time data streaming system for network anomaly detection that can operate during a high volume of traffic data. The solution includes the deployment of a flow collector platform connected to Apache Kafka for receiving NetFlow data from network switches. Also, real-time big data processing techniques are applied through Apache Spark, where the ML anomaly detection is triggered. The detection of anomalies is performed by a combination of the unsupervised learning clustering algorithm k-means and the supervised learning classifier KNN (k- nearest neighbors). Finally, a monitoring system consisting of an ELK stack collects historical data for further evolution of the ML algorithms.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114594104","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00027
Logan Crandall, M. Roberts, En Cheng
Whether it be classes, work, or social gatherings, the global pandemic has shown that the world can operate in a virtual space. The growing popularity of working from home saw a steady rise in video conferencing. In a virtual space, it is often necessary that participants have a webcam to have a meaningful connection with others. However, some participants may not own a webcam. Mimic is a software solution to allow the use of a webcam-enabled device, such as a smartphone, as a webcam on a computer that does not have a camera. The goal of Mimic is to provide the capacity to use a secondary device as a webcam input without the need to install any additional software on that mobile device. Mimic can accomplish this by building a web client that leverages the power of modern web browsers and WebRTC to stream the webcam video feed from a mobile device to another computer.
{"title":"Mimic: A Remote Webcam Device Over WebRTC","authors":"Logan Crandall, M. Roberts, En Cheng","doi":"10.1109/CSCI54926.2021.00027","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00027","url":null,"abstract":"Whether it be classes, work, or social gatherings, the global pandemic has shown that the world can operate in a virtual space. The growing popularity of working from home saw a steady rise in video conferencing. In a virtual space, it is often necessary that participants have a webcam to have a meaningful connection with others. However, some participants may not own a webcam. Mimic is a software solution to allow the use of a webcam-enabled device, such as a smartphone, as a webcam on a computer that does not have a camera. The goal of Mimic is to provide the capacity to use a secondary device as a webcam input without the need to install any additional software on that mobile device. Mimic can accomplish this by building a web client that leverages the power of modern web browsers and WebRTC to stream the webcam video feed from a mobile device to another computer.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114603775","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00025
T. Shi, Longshi Wu, Changhong Zhong, Ruixuan Wang, Hongmei Liu
In automatic histopathology and microscopy image analysis, due to high patient-level variability, the model trained based on the images from a set of patients may not perform well on the images from another set of patients. To overcome this issue, motivated by transductive learning and ensemble learning, we propose an iterative framework to train ensemble transductive models using pseudo-labels of test data. In each iteration, a number of individual models are first trained by combining the training set with part of randomly selected test data which have high prediction confidence, and then ensembled to predict the labels of test set for the next iteration. In this way, the latent information in test set would be exposed to the model such that the model can directly learn from the test data. Experimental evaluation on the white blood cancer microscopic image set and the breast histopathology image set shows that the proposed approach significantly outperforms the traditional ensemble models.
{"title":"Iterative Ensemble Transductive Learning for Microscopy Image Analysis","authors":"T. Shi, Longshi Wu, Changhong Zhong, Ruixuan Wang, Hongmei Liu","doi":"10.1109/CSCI54926.2021.00025","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00025","url":null,"abstract":"In automatic histopathology and microscopy image analysis, due to high patient-level variability, the model trained based on the images from a set of patients may not perform well on the images from another set of patients. To overcome this issue, motivated by transductive learning and ensemble learning, we propose an iterative framework to train ensemble transductive models using pseudo-labels of test data. In each iteration, a number of individual models are first trained by combining the training set with part of randomly selected test data which have high prediction confidence, and then ensembled to predict the labels of test set for the next iteration. In this way, the latent information in test set would be exposed to the model such that the model can directly learn from the test data. Experimental evaluation on the white blood cancer microscopic image set and the breast histopathology image set shows that the proposed approach significantly outperforms the traditional ensemble models.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114907040","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00323
Tiyani Christopher Hlongwane, Topside E. Mathonsi, D. D. du Plessis, Tonderai Muchenje
Facial recognition is a biological biometric feature that allows a person to be identified from a digital image. The face is known as the most recognizable aspect of human anatomy and acts like a human being’s first distinguishing feature. There are different techniques that can be used for the classification of data, two widely used techniques for data classification and dimension reduction are Principle Components Analysis (PCA) and Linear Discriminant Analysis (LDA). Facial recognition techniques have been comprehensively studied and applied in e-business. To reduce the False Rejection Rate (FRR) and False Acceptance Rate (FAR) during the recognition process, this review looks at the methods and the parameters that affect the facial recognition. Furthermore, we outline the strengths and challenges of these techniques. This comprehensive study serves as a starting point and a guide for everyone interested in exploring facial recognition techniques research area. The paper presents the conclusion and future work.
{"title":"A Review Paper on Facial Recognition Techniques in E-business","authors":"Tiyani Christopher Hlongwane, Topside E. Mathonsi, D. D. du Plessis, Tonderai Muchenje","doi":"10.1109/CSCI54926.2021.00323","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00323","url":null,"abstract":"Facial recognition is a biological biometric feature that allows a person to be identified from a digital image. The face is known as the most recognizable aspect of human anatomy and acts like a human being’s first distinguishing feature. There are different techniques that can be used for the classification of data, two widely used techniques for data classification and dimension reduction are Principle Components Analysis (PCA) and Linear Discriminant Analysis (LDA). Facial recognition techniques have been comprehensively studied and applied in e-business. To reduce the False Rejection Rate (FRR) and False Acceptance Rate (FAR) during the recognition process, this review looks at the methods and the parameters that affect the facial recognition. Furthermore, we outline the strengths and challenges of these techniques. This comprehensive study serves as a starting point and a guide for everyone interested in exploring facial recognition techniques research area. The paper presents the conclusion and future work.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117303417","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00192
S. Chaumette, Titien Cubilier
Drones and swarms of drones are now considered an additional tool for both civilian and military applications. As any computer-based system they can thus be (and are) the target of attacks and the consequences of such attacks can be dramatic for assets and people. We believe an approach based on honeypots that would attract the attention of attackers and would behave so that these attackers could not even understand they are in a honeypot and not in a real drone, would be a significant step towards the protection of these systems. Even though some prototypes exist, they do not fully address the fact of luring the attacker to believe he/she controls a real drone. In this paper we present our work to address this issue.
{"title":"aMDH and TWIN: Two original honeypot-based approaches to protect swarms of drones","authors":"S. Chaumette, Titien Cubilier","doi":"10.1109/CSCI54926.2021.00192","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00192","url":null,"abstract":"Drones and swarms of drones are now considered an additional tool for both civilian and military applications. As any computer-based system they can thus be (and are) the target of attacks and the consequences of such attacks can be dramatic for assets and people. We believe an approach based on honeypots that would attract the attention of attackers and would behave so that these attackers could not even understand they are in a honeypot and not in a real drone, would be a significant step towards the protection of these systems. Even though some prototypes exist, they do not fully address the fact of luring the attacker to believe he/she controls a real drone. In this paper we present our work to address this issue.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116167632","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00017
Philku Lee, Deyeon Kim, Seung Heon Lee, Seon-Hong Kim
Convolutional neural networks (CNNs) have become one of most powerful machine learning models; with enough data, their accuracy in tasks such as image-related classifications and natural language processing is unmatched. The drawback that many scientists have commented on is the fact that these networks, usually trained from randomly-initialized parameters, are black-boxes. This article introduces an innovative variant for CNNs, which incorporates principal components (PCs) derived from well-trained convolution kernels. The variant is called the principal component-incorporating CNN (PC-CNN), in which the PCs are employed either as a complete replacement for randomly-initialized convolution kernels or as an initialization for the convolution kernels to be re-trained. The objective is to help training processes converge to the global minimizer. The PC-CNN is applied for the MNIST handwritten digit dataset to prove its effectiveness.
{"title":"PCA Approaches for Optimal Convolution Kernels in Convolutional Neural Networks","authors":"Philku Lee, Deyeon Kim, Seung Heon Lee, Seon-Hong Kim","doi":"10.1109/CSCI54926.2021.00017","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00017","url":null,"abstract":"Convolutional neural networks (CNNs) have become one of most powerful machine learning models; with enough data, their accuracy in tasks such as image-related classifications and natural language processing is unmatched. The drawback that many scientists have commented on is the fact that these networks, usually trained from randomly-initialized parameters, are black-boxes. This article introduces an innovative variant for CNNs, which incorporates principal components (PCs) derived from well-trained convolution kernels. The variant is called the principal component-incorporating CNN (PC-CNN), in which the PCs are employed either as a complete replacement for randomly-initialized convolution kernels or as an initialization for the convolution kernels to be re-trained. The objective is to help training processes converge to the global minimizer. The PC-CNN is applied for the MNIST handwritten digit dataset to prove its effectiveness.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117285102","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00357
Ana María Campos Mora, Diego Sánchez Buitrago, Leonardo Juan Ramírez López
This study presents a new analysis method of physiological variables considered vital for the early diagnosis of COVID-19: Body Temperature, Heart Rate, and Blood Saturation. The applied method was the cross-analysis of variables to obtain triage-type criteria for classifying the individual in one of the three states: Prevention (yellow), Warning (Orange), and Alarm (Red) for each particular case. As a result, an automatic analysis algorithm was developed to support the physician in preventive treatment. It is possible to generate the warning states and classify the situation when making a report according to its condition by validating the results. The algorithms are published on Github to make them available to the scientific community in general and thus solve the early diagnosis.
{"title":"Crossed analysis of three-variable for early pre-diagnosis of COVID-19","authors":"Ana María Campos Mora, Diego Sánchez Buitrago, Leonardo Juan Ramírez López","doi":"10.1109/CSCI54926.2021.00357","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00357","url":null,"abstract":"This study presents a new analysis method of physiological variables considered vital for the early diagnosis of COVID-19: Body Temperature, Heart Rate, and Blood Saturation. The applied method was the cross-analysis of variables to obtain triage-type criteria for classifying the individual in one of the three states: Prevention (yellow), Warning (Orange), and Alarm (Red) for each particular case. As a result, an automatic analysis algorithm was developed to support the physician in preventive treatment. It is possible to generate the warning states and classify the situation when making a report according to its condition by validating the results. The algorithms are published on Github to make them available to the scientific community in general and thus solve the early diagnosis.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124519953","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00256
Subrata Kumar Das, Mohammad Zahidur Rahman
The health organizations store the patient data in different repositories and scattered in diverse locations. In the healthcare domain, the problem is that each hospital or even each department under a hospital maintains its own database having various data models (SQL, NoSQL, etc.). In this situation, existing or new applications require to grant healthcare actors to locate and share patient data from those pre-existing distributed databases (DDBs) remotely for the needs of patient quality treatment, daily operations of the health centers. However, data integration from distributed data sources is raising concern for data model variability. Therefore, it is significant to identify that how much an application like middleware is efficient to reconstruct and share patient data remotely from heterogeneous DDBs over the networks. The health organizations could also require to ensure whether their existing database model performs well or should replace by another one. So, this paper aims to design a system using different databases consisting of distinct data structures and an algorithm for middleware to integrate data from them with testing the system performance. The experimental results of this research work show that the patient data could be shared from various distributed data sources efficiently. Therefore the study could direct the healthcare organizations for sharing patient data from heterogeneous distributed databases without replacing the existing data model.
{"title":"Middleware to Integrate Patient Data from Heterogeneous Distributed Databases and Its Efficacy","authors":"Subrata Kumar Das, Mohammad Zahidur Rahman","doi":"10.1109/CSCI54926.2021.00256","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00256","url":null,"abstract":"The health organizations store the patient data in different repositories and scattered in diverse locations. In the healthcare domain, the problem is that each hospital or even each department under a hospital maintains its own database having various data models (SQL, NoSQL, etc.). In this situation, existing or new applications require to grant healthcare actors to locate and share patient data from those pre-existing distributed databases (DDBs) remotely for the needs of patient quality treatment, daily operations of the health centers. However, data integration from distributed data sources is raising concern for data model variability. Therefore, it is significant to identify that how much an application like middleware is efficient to reconstruct and share patient data remotely from heterogeneous DDBs over the networks. The health organizations could also require to ensure whether their existing database model performs well or should replace by another one. So, this paper aims to design a system using different databases consisting of distinct data structures and an algorithm for middleware to integrate data from them with testing the system performance. The experimental results of this research work show that the patient data could be shared from various distributed data sources efficiently. Therefore the study could direct the healthcare organizations for sharing patient data from heterogeneous distributed databases without replacing the existing data model.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125889016","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：