Pub Date : 2022-10-19DOI: 10.1109/KSE56063.2022.9953789
Tuan Le Xuan, Hang Pham Thi, Hai Nguyen Do
Detecting and recognizing text in images is a task that has received a lot of attention recently due to its high applicability in many fields such as digitization, storage, lookup, authentication However, most current research works and products are focusing on detecting and extracting text from images but not paying very much attention to analyzing and exploiting semantics and nuances of those extracted texts. In this study, we propose a three-in-one system to detect, recognize and classify Vietnamese text in images collected from social media to help authorities in monitoring tasks. The system receives as input images containing Vietnamese text, uses the Character-Region Awareness For Text detection (CRAFT) model to perform background processing to produce areas containing text in the image; these text containers will then be rearranged in the same order as in the original image, and the text in the image will also be extracted out according to the text container. Next, we use VietOCR model to convert these text images into text fragments. Finally, these texts will be classified using an ensemble of machine learning models. Preliminary results show that the proposed model has an accuracy of up to 88.0% in detecting and recognizing text and 94% in classifying text nuances on the collected data set.
{"title":"Vietnamese Text Detection, Recognition and Classification in Images","authors":"Tuan Le Xuan, Hang Pham Thi, Hai Nguyen Do","doi":"10.1109/KSE56063.2022.9953789","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953789","url":null,"abstract":"Detecting and recognizing text in images is a task that has received a lot of attention recently due to its high applicability in many fields such as digitization, storage, lookup, authentication However, most current research works and products are focusing on detecting and extracting text from images but not paying very much attention to analyzing and exploiting semantics and nuances of those extracted texts. In this study, we propose a three-in-one system to detect, recognize and classify Vietnamese text in images collected from social media to help authorities in monitoring tasks. The system receives as input images containing Vietnamese text, uses the Character-Region Awareness For Text detection (CRAFT) model to perform background processing to produce areas containing text in the image; these text containers will then be rearranged in the same order as in the original image, and the text in the image will also be extracted out according to the text container. Next, we use VietOCR model to convert these text images into text fragments. Finally, these texts will be classified using an ensemble of machine learning models. Preliminary results show that the proposed model has an accuracy of up to 88.0% in detecting and recognizing text and 94% in classifying text nuances on the collected data set.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126059871","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953758
Khai Dinh Lai, T. Le, T. T. Nguyen
In this research, in order to accurately diagnose lung nodules using the LUNA16 dataset, a deep learning model, ResNetl01, is analyzed and chosen. The paper includes: (1) demonstrating the efficiency of the ResNetl01 network on the LUNA16; (2) analyzing the benefits and drawbacks of Attention modules before selecting the best Attention module to integrate into the ResNetl01 model in the classification of lung nodules in CT scans challenge; (3) comparing the efficacy of the proposed model to prior outcomes to demonstrate the model’s feasibility.
{"title":"Image classification of lung nodules by requiring the integration of Attention Mechanism into ResNet model","authors":"Khai Dinh Lai, T. Le, T. T. Nguyen","doi":"10.1109/KSE56063.2022.9953758","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953758","url":null,"abstract":"In this research, in order to accurately diagnose lung nodules using the LUNA16 dataset, a deep learning model, ResNetl01, is analyzed and chosen. The paper includes: (1) demonstrating the efficiency of the ResNetl01 network on the LUNA16; (2) analyzing the benefits and drawbacks of Attention modules before selecting the best Attention module to integrate into the ResNetl01 model in the classification of lung nodules in CT scans challenge; (3) comparing the efficacy of the proposed model to prior outcomes to demonstrate the model’s feasibility.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122680700","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953776
N. Cao, R. Valášek, Stanislav Ožana
Severa1 fuzzy concepts are involved in relational databases such as the degree of fulfilment of a graded property, the level of importance (or of possibility) of a component in a query, grouping features, or the concept of fuzzy quantifiers. We have recently approached the concepts of excluding features and unavoidable features to construct the extensions of fuzzy relational compositions. The extended compositions include the employment of fuzzy quantifiers as well. In this work, we approach the concept of importance levels of considered features in a particular sense that is intuitively suitable to the classification tasks. Then we propose a direction of incorporating this concept into the existing fuzzy relational compositions. We provide various useful properties related to the new models of the compositions. Furthermore, a simple example of the classification of animals in biology is addressed for the behaviour illustration of the proposed models. Finally, we examine the applicability of the new models to the practical application of the Dragonfly classification, which has been considered previously.
{"title":"Composition Models of Fuzzy Relations Considering Importance Levels of Features*","authors":"N. Cao, R. Valášek, Stanislav Ožana","doi":"10.1109/KSE56063.2022.9953776","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953776","url":null,"abstract":"Severa1 fuzzy concepts are involved in relational databases such as the degree of fulfilment of a graded property, the level of importance (or of possibility) of a component in a query, grouping features, or the concept of fuzzy quantifiers. We have recently approached the concepts of excluding features and unavoidable features to construct the extensions of fuzzy relational compositions. The extended compositions include the employment of fuzzy quantifiers as well. In this work, we approach the concept of importance levels of considered features in a particular sense that is intuitively suitable to the classification tasks. Then we propose a direction of incorporating this concept into the existing fuzzy relational compositions. We provide various useful properties related to the new models of the compositions. Furthermore, a simple example of the classification of animals in biology is addressed for the behaviour illustration of the proposed models. Finally, we examine the applicability of the new models to the practical application of the Dragonfly classification, which has been considered previously.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128721148","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953766
N. Manh, D. V. Hang, D. Long, Le Quang Hung, P. C. Khanh, Nguyen Thi Oanh, N. T. Thuy, D. V. Sang
Endoscopy is one of the most effective methods for diagnosing diseases in the upper GI tract. This paper proposes a unified encoder-decoder model for dealing with three tasks simultaneously: anatomical site classification, lesion classification, and lesion segmentation. In addition, the model can learn from a training set comprised of data from multiple sources. We report results on our own large dataset of 8207 images obtained during routine upper GI endoscopic examinations. Experiments show that our model performs admirably in terms of classification accuracy and yields competitive segmentation results compared to the single-task model with the same architecture.
{"title":"EndoUNet: A Unified Model for Anatomical Site Classification, Lesion Categorization and Segmentation for Upper Gastrointestinal Endoscopy","authors":"N. Manh, D. V. Hang, D. Long, Le Quang Hung, P. C. Khanh, Nguyen Thi Oanh, N. T. Thuy, D. V. Sang","doi":"10.1109/KSE56063.2022.9953766","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953766","url":null,"abstract":"Endoscopy is one of the most effective methods for diagnosing diseases in the upper GI tract. This paper proposes a unified encoder-decoder model for dealing with three tasks simultaneously: anatomical site classification, lesion classification, and lesion segmentation. In addition, the model can learn from a training set comprised of data from multiple sources. We report results on our own large dataset of 8207 images obtained during routine upper GI endoscopic examinations. Experiments show that our model performs admirably in terms of classification accuracy and yields competitive segmentation results compared to the single-task model with the same architecture.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133668381","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953784
Tran Nguyen Huong, Le Huu Chung, Lam Nguyen Tung, Hoang-Viet Tran, Pham Ngoc Hung
Automated stubs generation is an important problem when testing units which contains calls to other uncompleted functions as testing and development phases are normally performed in parallel. This paper presents a fully automated method, named AS4UT, for generating stubs used in unit testing of C/C++ projects. The key idea of AS4UT is to consider each function call a mock variable. The idea is done by adding a Pre-process CFG (control flow graph) phase to concolic testing method. In this phase, all function calls in the CFG of a unit under test are replaced by their corresponding mock variables. Then, the updated CFG is used as an input for concolic testing method to generate the required test data set. We have implemented AS4UT in a tool, named AutoStubTesing, and performed experiments with some common functions which calls other units. Experimental results show that AS4UT can increase the code coverage of the generated test data set whilst reducing the number of test data and keeping the required time acceptable.
{"title":"An Automated Stub Method for Unit Testing C/C++ Projects","authors":"Tran Nguyen Huong, Le Huu Chung, Lam Nguyen Tung, Hoang-Viet Tran, Pham Ngoc Hung","doi":"10.1109/KSE56063.2022.9953784","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953784","url":null,"abstract":"Automated stubs generation is an important problem when testing units which contains calls to other uncompleted functions as testing and development phases are normally performed in parallel. This paper presents a fully automated method, named AS4UT, for generating stubs used in unit testing of C/C++ projects. The key idea of AS4UT is to consider each function call a mock variable. The idea is done by adding a Pre-process CFG (control flow graph) phase to concolic testing method. In this phase, all function calls in the CFG of a unit under test are replaced by their corresponding mock variables. Then, the updated CFG is used as an input for concolic testing method to generate the required test data set. We have implemented AS4UT in a tool, named AutoStubTesing, and performed experiments with some common functions which calls other units. Experimental results show that AS4UT can increase the code coverage of the generated test data set whilst reducing the number of test data and keeping the required time acceptable.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114999999","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}
Face anti-spoofing has become increasingly critical due to the widespread deployment of face recognition technology. Current approaches mostly focus on presentation attacks, where they rely on textual and spatio-temporal features in captured facial videos. However, in an environment where end-users manage their own devices, attackers can cheat by using virtual camera sensors and easily bypass sophisticated approaches for presentation attacks. In this paper, we propose a novel liveness detection protocol where users are required to read a random-generated sequence of words. Our proposed prediction model, LipBERT, a deep visual-linguistic alignment, is trained to detect if the captured facial stream conforms to the valid textual sequence. For the experiments, we introduce VNFaceTalking 1, an extensive dataset of 188,561 samples (around 130 hours in total). Each sample is at most 3 seconds video of frontal face talking Vietnamese. Experiments on the VNFaceTalking dataset demonstrate promising results.1https://github.com/tranvansanghust/VNFaceTalking
{"title":"A liveness detection protocol based on deep visual-linguistic alignment","authors":"Viet-Trung Tran, Van-Sang Tran, Xuan-Bang Nguyen, The-Trung Tran","doi":"10.1109/KSE56063.2022.9953623","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953623","url":null,"abstract":"Face anti-spoofing has become increasingly critical due to the widespread deployment of face recognition technology. Current approaches mostly focus on presentation attacks, where they rely on textual and spatio-temporal features in captured facial videos. However, in an environment where end-users manage their own devices, attackers can cheat by using virtual camera sensors and easily bypass sophisticated approaches for presentation attacks. In this paper, we propose a novel liveness detection protocol where users are required to read a random-generated sequence of words. Our proposed prediction model, LipBERT, a deep visual-linguistic alignment, is trained to detect if the captured facial stream conforms to the valid textual sequence. For the experiments, we introduce VNFaceTalking 1, an extensive dataset of 188,561 samples (around 130 hours in total). Each sample is at most 3 seconds video of frontal face talking Vietnamese. Experiments on the VNFaceTalking dataset demonstrate promising results.1https://github.com/tranvansanghust/VNFaceTalking","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115118484","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953756
Hau Nguyen Trung, S. N. Truong
Automated Legal Question Answering Competition is an annual competition to find the best solution to automatically answer legal questions based on well-known statute laws in the Vietnamese Language. In this paper, we will demonstrate how to solve the problems posed by ALQAC 2022, using BERT and its variants as a backbone network. In addition, we also study using tf-idf and BM-25 to rank the relevance of legal documents. At the same time, this publication also show how to enhance training data to solve the problem of limited training data.
{"title":"Ensemble Learning Methods for Legal Processing Tasks in ALQAC 2022","authors":"Hau Nguyen Trung, S. N. Truong","doi":"10.1109/KSE56063.2022.9953756","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953756","url":null,"abstract":"Automated Legal Question Answering Competition is an annual competition to find the best solution to automatically answer legal questions based on well-known statute laws in the Vietnamese Language. In this paper, we will demonstrate how to solve the problems posed by ALQAC 2022, using BERT and its variants as a backbone network. In addition, we also study using tf-idf and BM-25 to rank the relevance of legal documents. At the same time, this publication also show how to enhance training data to solve the problem of limited training data.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123649051","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 : 2022-10-19DOI: 10.1109/kse56063.2022.9953775
{"title":"KSE 2022 Cover Page","authors":"","doi":"10.1109/kse56063.2022.9953775","DOIUrl":"https://doi.org/10.1109/kse56063.2022.9953775","url":null,"abstract":"","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116880118","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 : 2022-10-19DOI: 10.1109/KSE56063.2022.9953763
Van Quan Nguyen, V. H. Nguyen, T. Hoang, Nathan Shone
The role of semi-supervised network intrusion detection systems is becoming increasingly important in the ever-changing digital landscape. Despite the boom in commercial and research interest, there are still many concerns over accuracy yet to be addressed. Two of the major limitations contributing to this concern are reliably learning the underlying probability distribution of normal network data and the identification of the boundary between the normal and anomalous data regions in the latent space. Recent research has proposed many different ways to learn the latent representation of normal data in a semi-supervised manner, such as using Clustering-based Autoencoder (CAE) and hybridized approaches of Principal Component Analysis (PCA) and CAE. However, such approaches are still affected by these limitations, predominantly due to an overreliance on feature engineering, or the inability to handle the large data dimensionality. In this paper, we propose a novel Cluster Variational Autoencoder (CVAE) deep learning model to overcome the aforementioned limitations and increase the efficiency of network intrusion detection. This enables a more concise and dominant representation of the latent space to be learnt. The probability distribution learning capabilities of the VAE are fully exploited to learn the underlying probability distribution of the normal network data. This combination enables us to address the limitations discussed. The performance of the proposed model is evaluated using eight benchmark network intrusion datasets: NSL-KDD, UNSW-NB15, CICIDS2017 and five scenarios from CTU13 (CTU13-08, CTU-13-09, CTU13-10, CTU13-12 and CTU13-13). The experimental results achieved clearly demonstrate that the proposed method outperforms semi-supervised approaches from existing works.
{"title":"A Novel Deep Clustering Variational Auto-Encoder for Anomaly-based Network Intrusion Detection","authors":"Van Quan Nguyen, V. H. Nguyen, T. Hoang, Nathan Shone","doi":"10.1109/KSE56063.2022.9953763","DOIUrl":"https://doi.org/10.1109/KSE56063.2022.9953763","url":null,"abstract":"The role of semi-supervised network intrusion detection systems is becoming increasingly important in the ever-changing digital landscape. Despite the boom in commercial and research interest, there are still many concerns over accuracy yet to be addressed. Two of the major limitations contributing to this concern are reliably learning the underlying probability distribution of normal network data and the identification of the boundary between the normal and anomalous data regions in the latent space. Recent research has proposed many different ways to learn the latent representation of normal data in a semi-supervised manner, such as using Clustering-based Autoencoder (CAE) and hybridized approaches of Principal Component Analysis (PCA) and CAE. However, such approaches are still affected by these limitations, predominantly due to an overreliance on feature engineering, or the inability to handle the large data dimensionality. In this paper, we propose a novel Cluster Variational Autoencoder (CVAE) deep learning model to overcome the aforementioned limitations and increase the efficiency of network intrusion detection. This enables a more concise and dominant representation of the latent space to be learnt. The probability distribution learning capabilities of the VAE are fully exploited to learn the underlying probability distribution of the normal network data. This combination enables us to address the limitations discussed. The performance of the proposed model is evaluated using eight benchmark network intrusion datasets: NSL-KDD, UNSW-NB15, CICIDS2017 and five scenarios from CTU13 (CTU13-08, CTU-13-09, CTU13-10, CTU13-12 and CTU13-13). The experimental results achieved clearly demonstrate that the proposed method outperforms semi-supervised approaches from existing works.","PeriodicalId":330865,"journal":{"name":"2022 14th International Conference on Knowledge and Systems Engineering (KSE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077783","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：