Abstract. Internet of things is a huge network of large number of devices with sensors. This group of devices is estimated to grow over 25 billion in 2020 as its growth since its evolution has been truly more than just rapid growth. With such a growth in network expansion and increase in number of connected devices, security always have been an issue to be improved and one of the weak areas in IoT environment. While applying security in IoT environment the main characteristics of IoT being heterogenetic and the number of IoT devices are the challenges that need to be dealt with some efficient and feasible approach. Therefore, to address this problem, we propose a method of securing IoT system using basic principles of machine learning. The system will analyze the data and detect the malicious packets received from the edge devices. The experimental study showed improved results with the dummy data sets in an IoT environment.
{"title":"Security Method for Internet of Things Using Machine Learning Against Cyber Attacks","authors":"T. Ahanger, A. Aljumah","doi":"10.1145/3440084.3441199","DOIUrl":"https://doi.org/10.1145/3440084.3441199","url":null,"abstract":"Abstract. Internet of things is a huge network of large number of devices with sensors. This group of devices is estimated to grow over 25 billion in 2020 as its growth since its evolution has been truly more than just rapid growth. With such a growth in network expansion and increase in number of connected devices, security always have been an issue to be improved and one of the weak areas in IoT environment. While applying security in IoT environment the main characteristics of IoT being heterogenetic and the number of IoT devices are the challenges that need to be dealt with some efficient and feasible approach. Therefore, to address this problem, we propose a method of securing IoT system using basic principles of machine learning. The system will analyze the data and detect the malicious packets received from the edge devices. The experimental study showed improved results with the dummy data sets in an IoT environment.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127441623","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}
Neural network model is a momentous method to calculate semantic similarity. Taking into account the complexity of document structure, introducing hierarchical structure and attention mechanism into neural network can calculate document semantic representation more precisely. In order to verify the validity of the model, LP50 dataset was tested. The experimental results reveal that accurate document representation can be obtained by using the attention mechanism at two levels of words and sentences. Since this method has taken both the influence of context information and the contribution of components to the document into consideration. Compared with several conventional methods, there is a significant improvement of performance in our model.
{"title":"Hierarchical Attention-based BiLSTM Network for Document Similarity Calculation","authors":"Jiang Zhang, Qun Zhu, Yanlin He","doi":"10.1145/3440084.3441188","DOIUrl":"https://doi.org/10.1145/3440084.3441188","url":null,"abstract":"Neural network model is a momentous method to calculate semantic similarity. Taking into account the complexity of document structure, introducing hierarchical structure and attention mechanism into neural network can calculate document semantic representation more precisely. In order to verify the validity of the model, LP50 dataset was tested. The experimental results reveal that accurate document representation can be obtained by using the attention mechanism at two levels of words and sentences. Since this method has taken both the influence of context information and the contribution of components to the document into consideration. Compared with several conventional methods, there is a significant improvement of performance in our model.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"2 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127019974","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}
For working out the problem of ownership rights of data in the Big Data era, this paper proposes an establishment method of data ownership rights based on data classification. By summarizing characteristics of big data and analyzing current main views of the data ownership rights, this proposed method is following the principles of protecting data confidentiality and acknowledging the greatest contributors. First, according to the different involvement degree of participants in data generation processes, the data is divided into two categories: participatory data and non-participatory data. The participatory data is subdivided into equal participatory data and non-equal participatory data based on different contributions of participants. Since the non-participatory data generally involves the private and confidential information of the recorded parties, it is proposed that the ownership rights of this kind of data should belong to the recorded parties. Following the principle of acknowledging the greatest contributors, this paper proposes that the ownership rights of the equal participatory data belongs to all participants and that of non-equal participatory data belongs to the active participants.
{"title":"Analysis of Data Ownership Rights in the Big Data Era","authors":"Wei Xiao, Yaqing Tu, Ping Wan, Ming Li, J. Ma","doi":"10.1145/3440084.3441210","DOIUrl":"https://doi.org/10.1145/3440084.3441210","url":null,"abstract":"For working out the problem of ownership rights of data in the Big Data era, this paper proposes an establishment method of data ownership rights based on data classification. By summarizing characteristics of big data and analyzing current main views of the data ownership rights, this proposed method is following the principles of protecting data confidentiality and acknowledging the greatest contributors. First, according to the different involvement degree of participants in data generation processes, the data is divided into two categories: participatory data and non-participatory data. The participatory data is subdivided into equal participatory data and non-equal participatory data based on different contributions of participants. Since the non-participatory data generally involves the private and confidential information of the recorded parties, it is proposed that the ownership rights of this kind of data should belong to the recorded parties. Following the principle of acknowledging the greatest contributors, this paper proposes that the ownership rights of the equal participatory data belongs to all participants and that of non-equal participatory data belongs to the active participants.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121607591","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}
Bekkouch Imad Eddine Ibrahim, D. C. Nicolae, A. Khan, Syed Imran Ali, A. Khattak
Outlier detection is one of the main fields in machine learning and it has been growing rapidly due to its wide range of applications. In the last few years, deep learning-based methods have outperformed machine learning and handcrafted outlier detection techniques, and our method is no different. We present a new twist to generative models which leverages variational autoencoders as a source for uniform distributions which can be used to separate the inliers from the outliers. Both the generative and adversarial parts of the model are used to obtain three main losses (Reconstruction loss, KL-divergence, Discriminative loss) which in return are wrapped with a one-class SVM which is used to make the predictions. We evaluated our method against several datasets both for images and tabular data and it has shown great results for the zero-shot outlier detection problem and was able to easily generalize it for supervised outlier detection tasks on which the performance has increased. For comparison, we evaluated our method against several of the common outlier detection techniques such as DBSCAN-based outlier detection, GMM, K-means and one class SVM directly, and we have outperformed all of them on all datasets.
{"title":"VAE-GAN Based Zero-shot Outlier Detection","authors":"Bekkouch Imad Eddine Ibrahim, D. C. Nicolae, A. Khan, Syed Imran Ali, A. Khattak","doi":"10.1145/3440084.3441180","DOIUrl":"https://doi.org/10.1145/3440084.3441180","url":null,"abstract":"Outlier detection is one of the main fields in machine learning and it has been growing rapidly due to its wide range of applications. In the last few years, deep learning-based methods have outperformed machine learning and handcrafted outlier detection techniques, and our method is no different. We present a new twist to generative models which leverages variational autoencoders as a source for uniform distributions which can be used to separate the inliers from the outliers. Both the generative and adversarial parts of the model are used to obtain three main losses (Reconstruction loss, KL-divergence, Discriminative loss) which in return are wrapped with a one-class SVM which is used to make the predictions. We evaluated our method against several datasets both for images and tabular data and it has shown great results for the zero-shot outlier detection problem and was able to easily generalize it for supervised outlier detection tasks on which the performance has increased. For comparison, we evaluated our method against several of the common outlier detection techniques such as DBSCAN-based outlier detection, GMM, K-means and one class SVM directly, and we have outperformed all of them on all datasets.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130024732","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. Carvalho, Niall O' Mahony, L. Krpalkova, S. Campbell, Joseph Walsh, P. Doody
Due to the increasing availability of internet connection both industrial and agricultural environments have experienced an expressive increase in the number of IoT devices for the last few years. This paper exposes an extensive architecture investigation looking for an optimal edge solution to cope with existing, and future applications. This paper presents an introduction to the proposed solution in terms of architecture, including local user interface, MQTT broker, machine learning edge engine, some existing management software, local databases, actual software used for hardware communication, the edge agent and aspects of the hardware used during tests. It also presents some results obtained from experiments under heavy load in terms of data and a small number of devices in terms of distribution. Together the paper brings some important findings on edge computing, compare main architectural aspects and will provide a broad view of how edge solutions might be built for this particular scenario. Having discussed how the ideal architecture works and having provided an overview of how it may be applied to industrial and agricultural environments, the conclusion points to the next steps for the current research.
{"title":"Ideal Edge Architecture to Scale IoT Devices","authors":"A. Carvalho, Niall O' Mahony, L. Krpalkova, S. Campbell, Joseph Walsh, P. Doody","doi":"10.1145/3440084.3441198","DOIUrl":"https://doi.org/10.1145/3440084.3441198","url":null,"abstract":"Due to the increasing availability of internet connection both industrial and agricultural environments have experienced an expressive increase in the number of IoT devices for the last few years. This paper exposes an extensive architecture investigation looking for an optimal edge solution to cope with existing, and future applications. This paper presents an introduction to the proposed solution in terms of architecture, including local user interface, MQTT broker, machine learning edge engine, some existing management software, local databases, actual software used for hardware communication, the edge agent and aspects of the hardware used during tests. It also presents some results obtained from experiments under heavy load in terms of data and a small number of devices in terms of distribution. Together the paper brings some important findings on edge computing, compare main architectural aspects and will provide a broad view of how edge solutions might be built for this particular scenario. Having discussed how the ideal architecture works and having provided an overview of how it may be applied to industrial and agricultural environments, the conclusion points to the next steps for the current research.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127164899","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}
Shuaifei Song, Deyuan Zhu, Yuncheng Song, Kun Yu, Huabin Feng, Hengchang Liu
With the development of low-cost, low-power sensing and communication technologies, there has been growing interest in the IoT for realizing smart cities, in order to maximize the productivity and reliability of urban infrastructure. One of the most representative examples is smart parking system, which consists of parking sensors and backend servers. In existing systems, parking sensors are placed in each parking spot to monitor the status of the parking spot, and then the sensing data is send to backend servers for further processing. Based on these sensor data, the smart parking system can provide some smart services, such as parking spot availability prediction, remote booking and parking guidance. The premise of all these smart services is that the sensor data is accurate and reliable. However, as the sensor ages, the sensor may produce some unreliable data, which brings great challenges to our smart services. In this paper, we present a novel anomaly detection and calibration system in "Suzhou Center", one of the largest most advanced urban complexes in China. Our system uses supervised machine learning algorithms, focusing on capturing spatio-temporal features. The experimental results show that our system can identify most anomalies and improve the accuracy of the sensor.
{"title":"Towards Real-time Anomaly Detection and Calibration for Large Parking Lot in Urban Complex","authors":"Shuaifei Song, Deyuan Zhu, Yuncheng Song, Kun Yu, Huabin Feng, Hengchang Liu","doi":"10.1145/3440084.3441177","DOIUrl":"https://doi.org/10.1145/3440084.3441177","url":null,"abstract":"With the development of low-cost, low-power sensing and communication technologies, there has been growing interest in the IoT for realizing smart cities, in order to maximize the productivity and reliability of urban infrastructure. One of the most representative examples is smart parking system, which consists of parking sensors and backend servers. In existing systems, parking sensors are placed in each parking spot to monitor the status of the parking spot, and then the sensing data is send to backend servers for further processing. Based on these sensor data, the smart parking system can provide some smart services, such as parking spot availability prediction, remote booking and parking guidance. The premise of all these smart services is that the sensor data is accurate and reliable. However, as the sensor ages, the sensor may produce some unreliable data, which brings great challenges to our smart services. In this paper, we present a novel anomaly detection and calibration system in \"Suzhou Center\", one of the largest most advanced urban complexes in China. Our system uses supervised machine learning algorithms, focusing on capturing spatio-temporal features. The experimental results show that our system can identify most anomalies and improve the accuracy of the sensor.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129975013","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}
Hao Song, Chao-Shih Liu, Qingling Liu, Yang Liu, Chun H. Wang, Mingxu Yi
The process of civil aircraft development is a complex system, where flight test is an extremely important process of the project. In the top-level planning of flight test, it is particularly important to determine the quantity of test aircraft, which is closely related to the total flight test period, cost, and resources. This paper analyzes and studies the number of test aircraft performing flight test missions, analyzes the related factors of the number of test aircraft, and proposes a reasonable calculation model with engineering operability based on flight test period and cost. It provides numerical data reference for overall planning of civil aircraft flight test during multi-objective optimization.
{"title":"Research on Test Aircraft Quantitative Analysis Model during Flight Test Planning","authors":"Hao Song, Chao-Shih Liu, Qingling Liu, Yang Liu, Chun H. Wang, Mingxu Yi","doi":"10.1145/3440084.3441205","DOIUrl":"https://doi.org/10.1145/3440084.3441205","url":null,"abstract":"The process of civil aircraft development is a complex system, where flight test is an extremely important process of the project. In the top-level planning of flight test, it is particularly important to determine the quantity of test aircraft, which is closely related to the total flight test period, cost, and resources. This paper analyzes and studies the number of test aircraft performing flight test missions, analyzes the related factors of the number of test aircraft, and proposes a reasonable calculation model with engineering operability based on flight test period and cost. It provides numerical data reference for overall planning of civil aircraft flight test during multi-objective optimization.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130888729","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 presents a long range process fault prognosis system using long short-term memory (LSTM) network. Data from historical process operation with faults present are used to train LSTM networks. During process monitoring, a principal component analysis (PCA) model developed from normal historical process operation data is used to detect the presence of a fault. Once a fault is detected, reconstruction based fault diagnosis is used to diagnosis the detected fault. Then the trained LSTM network corresponding the diagnosed fault is use to provide long range fault magnitude forecast. The proposed method is applied to a simulated continuous stirred tank reactor (CSTR) and is compared with fault prognosis using extreme learning machine (ELM). The results show that the proposed fault prognosis method based on LSTM network can achieve excellent long range prognosis performance.
{"title":"Fault Magnitude Prognosis in Chemical Process Based on Long Short-Term Memory Network","authors":"Ruosen Qi, Jie Zhang","doi":"10.1145/3440084.3441212","DOIUrl":"https://doi.org/10.1145/3440084.3441212","url":null,"abstract":"This paper presents a long range process fault prognosis system using long short-term memory (LSTM) network. Data from historical process operation with faults present are used to train LSTM networks. During process monitoring, a principal component analysis (PCA) model developed from normal historical process operation data is used to detect the presence of a fault. Once a fault is detected, reconstruction based fault diagnosis is used to diagnosis the detected fault. Then the trained LSTM network corresponding the diagnosed fault is use to provide long range fault magnitude forecast. The proposed method is applied to a simulated continuous stirred tank reactor (CSTR) and is compared with fault prognosis using extreme learning machine (ELM). The results show that the proposed fault prognosis method based on LSTM network can achieve excellent long range prognosis performance.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126723951","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}
Recurrent neural networks (RNNs) have been used prevalently to capture long-term dependencies of sequential inputs. In particular, for question answering systems, variants of RNNs, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), allow the positional, ordering or contextual information to be encoded into latent contextual representations. While applying RNNs for encoding this information is intuitively reasonable, no specific research has been conducted to investigate how effective is their use in such systems when the sequence of sentences is unimportant. In this paper we conduct a case study on the effectiveness of using RNNs to generate context representations using the DMN+ network. Our results based on a three-fact task in the bAbI dataset show that sequences of facts in the training dataset influence the predictive performance of the trained system. We propose two methods to resolve this problem, one is data augmentation and the other is the optimization of the DMN+ structure by replacing the GRU in the episodic memory module with a non-recurrent operation. The experimental results demonstrate that our proposed solutions can resolve the problem effectively.
{"title":"The Role of RNNs for Contextual Representations: A Case Study Using DMN-plus","authors":"Y. Shen, E. Lai, Mahsa Mohaghegh","doi":"10.1145/3440084.3441190","DOIUrl":"https://doi.org/10.1145/3440084.3441190","url":null,"abstract":"Recurrent neural networks (RNNs) have been used prevalently to capture long-term dependencies of sequential inputs. In particular, for question answering systems, variants of RNNs, such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), allow the positional, ordering or contextual information to be encoded into latent contextual representations. While applying RNNs for encoding this information is intuitively reasonable, no specific research has been conducted to investigate how effective is their use in such systems when the sequence of sentences is unimportant. In this paper we conduct a case study on the effectiveness of using RNNs to generate context representations using the DMN+ network. Our results based on a three-fact task in the bAbI dataset show that sequences of facts in the training dataset influence the predictive performance of the trained system. We propose two methods to resolve this problem, one is data augmentation and the other is the optimization of the DMN+ structure by replacing the GRU in the episodic memory module with a non-recurrent operation. The experimental results demonstrate that our proposed solutions can resolve the problem effectively.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126310524","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}
At present, the mining and analysis of teaching data is mainly aimed at the online courses data, but not mixed data, which is fused by the traditional offline-classroom and online teaching data. Meanwhile, the most evaluation models are constructed by the learning data to evaluate the teaching quality of teachers, but not to evaluate and grade the individual quality of students. In fact, the evaluation and grading of students' quality can effectively provide more targeted teaching intervention for students of different levels based on the data analysis. To address these issues, the online teaching data is fused by the students' learning behavior data of traditional course to form the mixed data in this paper, and then the sparse non-negative matrix factorization (SNMF) method is adopted to extract the feature clusters of mixed learning data. According to the weights of the extracted cluster features, the multi-level feature indicators are selected in turn to construct the hierarchical evaluation index system. Finally, the comprehensive weighting method is adopted to evaluate and grade the individual students. In this paper, the mixed teaching data of computer basic course of our school is formed, and then the weights of feature clusters are calculated by SNMF and an evaluation model is established to evaluate and grade the students. The grading results are in accordance with the normal distribution and basically consistent with the grading distribution of students' final examination scores. Thus the validity of the model and method proposed in this paper is proved.
{"title":"Research of Cluster Feature Extraction and Evaluation System Construction for Mixed Teaching Data","authors":"Jing Zhou, Jun Xiong, Ze Chen","doi":"10.1145/3440084.3441191","DOIUrl":"https://doi.org/10.1145/3440084.3441191","url":null,"abstract":"At present, the mining and analysis of teaching data is mainly aimed at the online courses data, but not mixed data, which is fused by the traditional offline-classroom and online teaching data. Meanwhile, the most evaluation models are constructed by the learning data to evaluate the teaching quality of teachers, but not to evaluate and grade the individual quality of students. In fact, the evaluation and grading of students' quality can effectively provide more targeted teaching intervention for students of different levels based on the data analysis. To address these issues, the online teaching data is fused by the students' learning behavior data of traditional course to form the mixed data in this paper, and then the sparse non-negative matrix factorization (SNMF) method is adopted to extract the feature clusters of mixed learning data. According to the weights of the extracted cluster features, the multi-level feature indicators are selected in turn to construct the hierarchical evaluation index system. Finally, the comprehensive weighting method is adopted to evaluate and grade the individual students. In this paper, the mixed teaching data of computer basic course of our school is formed, and then the weights of feature clusters are calculated by SNMF and an evaluation model is established to evaluate and grade the students. The grading results are in accordance with the normal distribution and basically consistent with the grading distribution of students' final examination scores. Thus the validity of the model and method proposed in this paper is proved.","PeriodicalId":250100,"journal":{"name":"Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115279206","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：