Pub Date : 2023-08-25DOI: 10.1080/24751839.2023.2250123
Hamdi Eltaief, Ali El kamel, H. Youssef
{"title":"MSA-SDMN: multicast source authentication scheme for multi-domain software defined mobile networks","authors":"Hamdi Eltaief, Ali El kamel, H. Youssef","doi":"10.1080/24751839.2023.2250123","DOIUrl":"https://doi.org/10.1080/24751839.2023.2250123","url":null,"abstract":"","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43599465","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 : 2023-08-05DOI: 10.1080/24751839.2023.2235114
Hoang Hai Son, Vo Phuc Tinh, Duc Ngoc Minh Dang, Bui Thi Duyen, Duy-Dong Le, Thai-Thinh Dang, Q. Nguyen, Thanh-Qui Pham, Van-Luong Nguyen, Tran Anh Khoa, Nguyen Hoang Nam
{"title":"A novel solution for energy-saving and lifetime-maximizing of LoRa wireless mesh networks","authors":"Hoang Hai Son, Vo Phuc Tinh, Duc Ngoc Minh Dang, Bui Thi Duyen, Duy-Dong Le, Thai-Thinh Dang, Q. Nguyen, Thanh-Qui Pham, Van-Luong Nguyen, Tran Anh Khoa, Nguyen Hoang Nam","doi":"10.1080/24751839.2023.2235114","DOIUrl":"https://doi.org/10.1080/24751839.2023.2235114","url":null,"abstract":"","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47367923","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 : 2023-07-25DOI: 10.1080/24751839.2023.2239617
Ahlem Abid, F. Jemili, O. Korbaa
ABSTRACT Industry 4.0 refers to a new generation of connected and intelligent factories that is driven by the emergence of new technologies such as artificial intelligence, Cloud computing, Big Data and industrial control systems (ICS) in order to automate all phases of industrial operations. The presence of connected systems in industrial environments poses a considerable security challenge, moreover with the huge amount of data generated daily, there are complex attacks that occur in seconds and target production lines and their integrity. But, until now, factories do not have all the necessary tools to protect themselves, they mainly use traditional protection. In order to improve industrial control systems in terms of efficiency and response time, the present paper propose a new distributed intrusion detection approach using artificial intelligence methods, Big Data techniques and deployed in a cloud environment. A variety of Machine Learning and Deep Learning algorithms, basically convolutional neural networks (CNN), have been tested to compare performance and choose the most suitable model for the classification. We test the performance of our model by using the industrial dataset SWat.
{"title":"Distributed deep learning approach for intrusion detection system in industrial control systems based on big data technique and transfer learning","authors":"Ahlem Abid, F. Jemili, O. Korbaa","doi":"10.1080/24751839.2023.2239617","DOIUrl":"https://doi.org/10.1080/24751839.2023.2239617","url":null,"abstract":"ABSTRACT Industry 4.0 refers to a new generation of connected and intelligent factories that is driven by the emergence of new technologies such as artificial intelligence, Cloud computing, Big Data and industrial control systems (ICS) in order to automate all phases of industrial operations. The presence of connected systems in industrial environments poses a considerable security challenge, moreover with the huge amount of data generated daily, there are complex attacks that occur in seconds and target production lines and their integrity. But, until now, factories do not have all the necessary tools to protect themselves, they mainly use traditional protection. In order to improve industrial control systems in terms of efficiency and response time, the present paper propose a new distributed intrusion detection approach using artificial intelligence methods, Big Data techniques and deployed in a cloud environment. A variety of Machine Learning and Deep Learning algorithms, basically convolutional neural networks (CNN), have been tested to compare performance and choose the most suitable model for the classification. We test the performance of our model by using the industrial dataset SWat.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41982654","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 : 2023-07-07DOI: 10.1080/24751839.2023.2229700
H. Phan, N. Nguyen, D. Hwang, Yeong-Seok Seo
ABSTRACT People have more channels to express their opinions and feelings about events, products, and celebrities because of the development of social networks. They are becoming rich data sources, gaining attention for many practical applications and in the field of research. Sentiment analysis (SA) is one of the most common uses of this data source. Of the currently available SA datasets, most are only suitable for use in SA corresponding to a specific level, such as document, sentence, or aspect levels. This renders it difficult to develop practical systems that require a combination of sentiment analyzes at all three levels. Additionally, the previous datasets included opinions on only a single domain, although many people often mention multiple domains when expressing their views. This study introduces a new dataset called multi-level and multi-domain (M2SA) for SA. Each sample in M2SA contains a short text with at least two sentences and two aspects with different domains and sentiment polarities. The release of the M2SA dataset will contribute to the promotion of research in the field of SA, primarily by promoting the development and improvement of methods for multi-level SA or multi-aspect, multi-domain SA. The M2SA dataset was tested using state-of-the-art SA methods and was compared with other standard datasets. The results demonstrate that the M2SA dataset is better than the previous datasets in supporting to improve of the performance of SA methods.
{"title":"M2SA: a novel dataset for multi-level and multi-domain sentiment analysis","authors":"H. Phan, N. Nguyen, D. Hwang, Yeong-Seok Seo","doi":"10.1080/24751839.2023.2229700","DOIUrl":"https://doi.org/10.1080/24751839.2023.2229700","url":null,"abstract":"ABSTRACT People have more channels to express their opinions and feelings about events, products, and celebrities because of the development of social networks. They are becoming rich data sources, gaining attention for many practical applications and in the field of research. Sentiment analysis (SA) is one of the most common uses of this data source. Of the currently available SA datasets, most are only suitable for use in SA corresponding to a specific level, such as document, sentence, or aspect levels. This renders it difficult to develop practical systems that require a combination of sentiment analyzes at all three levels. Additionally, the previous datasets included opinions on only a single domain, although many people often mention multiple domains when expressing their views. This study introduces a new dataset called multi-level and multi-domain (M2SA) for SA. Each sample in M2SA contains a short text with at least two sentences and two aspects with different domains and sentiment polarities. The release of the M2SA dataset will contribute to the promotion of research in the field of SA, primarily by promoting the development and improvement of methods for multi-level SA or multi-aspect, multi-domain SA. The M2SA dataset was tested using state-of-the-art SA methods and was compared with other standard datasets. The results demonstrate that the M2SA dataset is better than the previous datasets in supporting to improve of the performance of SA methods.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48290306","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 : 2023-06-21DOI: 10.1080/24751839.2023.2225254
L. Tu, T. N. Nguyen, Phuong T. Tran, Tran Trung Duy, Q.-S. Nguyen
ABSTRACT The performance of broadcasting networks employing Fountain codes with receiver diversity techniques is investigated in the present work. Particularly, we derive the closed-form expressions of the cumulative distribution function (CDF), the probability mass function (PMF), and the raw moments of the number of the needed time slots to deliver a common message to all users under two diversity schemes, namely, maximal ratio combining (MRC) and selection combining (SC). Numerical results are supplied to verify the accuracy of the considered networks and highlight the behaviours of these metrics as a function of some vital parameters such as the number of receivers, and the number of received antennae. Additionally, we also confirm the advantages of the MRC scheme compared with the SC scheme in the broadcasting networks.
{"title":"Performance statistics of broadcasting networks with receiver diversity and Fountain codes","authors":"L. Tu, T. N. Nguyen, Phuong T. Tran, Tran Trung Duy, Q.-S. Nguyen","doi":"10.1080/24751839.2023.2225254","DOIUrl":"https://doi.org/10.1080/24751839.2023.2225254","url":null,"abstract":"ABSTRACT The performance of broadcasting networks employing Fountain codes with receiver diversity techniques is investigated in the present work. Particularly, we derive the closed-form expressions of the cumulative distribution function (CDF), the probability mass function (PMF), and the raw moments of the number of the needed time slots to deliver a common message to all users under two diversity schemes, namely, maximal ratio combining (MRC) and selection combining (SC). Numerical results are supplied to verify the accuracy of the considered networks and highlight the behaviours of these metrics as a function of some vital parameters such as the number of receivers, and the number of received antennae. Additionally, we also confirm the advantages of the MRC scheme compared with the SC scheme in the broadcasting networks.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42503526","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 : 2023-06-03DOI: 10.1080/24751839.2023.2218046
Q.-S. Nguyen, T. N. Nguyen, L. Tu
ABSTRACT The performance of the simultaneous wireless information and power transfer (SWIPT) enabled full-duplex (FD) relaying in non-orthogonal multiple access (NOMA) networks is investigated in both reliability and security aspects. More precisely, for the viewpoint of reliability, we derive in the closed-form expression the outage probability (OP) at both end-users. On the other hand, intercept probability (IP) is considered a helpful metric to measure the security of the considered systems. Moreover, we derive the IP in the closed-form expression too. Numerical results are also given to confirm the correctness of the derived mathematical framework as well as to identify the insights of both metrics as a function of some key parameters such as the transmit power, the power-splitting (PS) ratio, and the power allocation ratio.
{"title":"On the security and reliability performance of SWIPT-enabled full-duplex relaying in the non-orthogonal multiple access networks","authors":"Q.-S. Nguyen, T. N. Nguyen, L. Tu","doi":"10.1080/24751839.2023.2218046","DOIUrl":"https://doi.org/10.1080/24751839.2023.2218046","url":null,"abstract":"ABSTRACT The performance of the simultaneous wireless information and power transfer (SWIPT) enabled full-duplex (FD) relaying in non-orthogonal multiple access (NOMA) networks is investigated in both reliability and security aspects. More precisely, for the viewpoint of reliability, we derive in the closed-form expression the outage probability (OP) at both end-users. On the other hand, intercept probability (IP) is considered a helpful metric to measure the security of the considered systems. Moreover, we derive the IP in the closed-form expression too. Numerical results are also given to confirm the correctness of the derived mathematical framework as well as to identify the insights of both metrics as a function of some key parameters such as the transmit power, the power-splitting (PS) ratio, and the power allocation ratio.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43875507","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 : 2023-05-24DOI: 10.1080/24751839.2023.2214976
F. Jemili
ABSTRACT Intrusion detection is seen as the most promising way for computer security. It is used to protect computer networks against different types of attacks. The major problem in the literature is the classification of data into two main classes: normal and intrusion. To solve this problem, several approaches have been proposed but the problem of false alarms is still present. To provide a solution to this problem, we have proposed a new intrusion detection approach based on data fusion. The main objective of this work is to suggest an approach of data fusion-based Big Data analytics to detect intrusions; It is to build one dataset which combines various datasets and contains all the attack types. This research consists in merging the heterogeneous datasets and removing redundancy information using Big Data analytics tools: Hadoop/MapReduce and Neo4j. In the next step, machine learning algorithms are implemented for learning. The first algorithm, called SSDM (Semantically Similar Data Miner), uses fuzzy logic to generate association rules between the different item sets. The second algorithm, called K2, is a score-based greedy search algorithm for learning Bayesian networks from data. Experimentation results prove that – in both cases – data fusion contributes to having very good results.
{"title":"Towards data fusion-based big data analytics for intrusion detection","authors":"F. Jemili","doi":"10.1080/24751839.2023.2214976","DOIUrl":"https://doi.org/10.1080/24751839.2023.2214976","url":null,"abstract":"ABSTRACT\u0000 Intrusion detection is seen as the most promising way for computer security. It is used to protect computer networks against different types of attacks. The major problem in the literature is the classification of data into two main classes: normal and intrusion. To solve this problem, several approaches have been proposed but the problem of false alarms is still present. To provide a solution to this problem, we have proposed a new intrusion detection approach based on data fusion. The main objective of this work is to suggest an approach of data fusion-based Big Data analytics to detect intrusions; It is to build one dataset which combines various datasets and contains all the attack types. This research consists in merging the heterogeneous datasets and removing redundancy information using Big Data analytics tools: Hadoop/MapReduce and Neo4j. In the next step, machine learning algorithms are implemented for learning. The first algorithm, called SSDM (Semantically Similar Data Miner), uses fuzzy logic to generate association rules between the different item sets. The second algorithm, called K2, is a score-based greedy search algorithm for learning Bayesian networks from data. Experimentation results prove that – in both cases – data fusion contributes to having very good results.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42759912","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 : 2023-05-23DOI: 10.1080/24751839.2023.2215135
Kha Van Nguyen, H. Nguyen, Thang Quyet Le, Quang Nhat Minh Truong
ABSTRACT Most devices are now connected through the Internet, so cybersecurity issues have raised concerns. This study proposes network services in a virtual environment to collect, analyze and identify network attacks with various techniques. Our contributions include multi-fold. First, we deployed Honeynet architecture to collect network packets, including actual cyber-attacks performed by real hackers and crackers. In the second contribution, we have leveraged some techniques to normalize data and extract header information with 29 features from 200,000 samples of many types of network attacks for abnormal packet identification with machine learning algorithms. Furthermore, we introduce an Adaptive Cybersecurity (AC) system to detect attacks and provide warnings. The system can automatically collect more data for further analysis to improve performance. Our proposed method performs better than Snort in detecting dangerous malicious attacks. Finally, we have experimented with different cyber-attack approaches to exploit the ten website security risks recommended by the Open Web Application Security Project (OWASP). From the research results, the system is expected to be able to detect cybercriminal attacks and provide early warnings to prevent a potential cyber-attack.
{"title":"Abnormal network packets identification using header information collected from Honeywall architecture","authors":"Kha Van Nguyen, H. Nguyen, Thang Quyet Le, Quang Nhat Minh Truong","doi":"10.1080/24751839.2023.2215135","DOIUrl":"https://doi.org/10.1080/24751839.2023.2215135","url":null,"abstract":"ABSTRACT Most devices are now connected through the Internet, so cybersecurity issues have raised concerns. This study proposes network services in a virtual environment to collect, analyze and identify network attacks with various techniques. Our contributions include multi-fold. First, we deployed Honeynet architecture to collect network packets, including actual cyber-attacks performed by real hackers and crackers. In the second contribution, we have leveraged some techniques to normalize data and extract header information with 29 features from 200,000 samples of many types of network attacks for abnormal packet identification with machine learning algorithms. Furthermore, we introduce an Adaptive Cybersecurity (AC) system to detect attacks and provide warnings. The system can automatically collect more data for further analysis to improve performance. Our proposed method performs better than Snort in detecting dangerous malicious attacks. Finally, we have experimented with different cyber-attack approaches to exploit the ten website security risks recommended by the Open Web Application Security Project (OWASP). From the research results, the system is expected to be able to detect cybercriminal attacks and provide early warnings to prevent a potential cyber-attack.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45166454","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 : 2023-05-03DOI: 10.1080/24751839.2023.2207267
H. Do, D. Chau, S. Tran
ABSTRACT Most speech processing models begin with feature extraction and then pass the feature vector to the primary processing model. The solution's performance mainly depends on the quality of the feature representation and the model architecture. Much research focuses on designing robust deep network architecture and ignoring feature representation's important role during the deep neural network era. This work aims to exploit a new approach to design a speech signal representation in the time-frequency domain via Linear Chirplet Transform (LCT). The proposed method provides a feature vector sensitive to the frequency change inside human speech with a solid mathematical foundation. This is a potential direction for many applications. The experimental results show the improvement of the feature based on LCT compared to MFCC or Fourier Transform. In both speaker gender recognition, dialect recognition, and speech recognition, LCT significantly improved compared with MFCC and other features. This result also implies that the feature based on LCT is independent of language, so it can be used in various applications.
{"title":"Speech feature extraction using linear Chirplet transform and its applications*","authors":"H. Do, D. Chau, S. Tran","doi":"10.1080/24751839.2023.2207267","DOIUrl":"https://doi.org/10.1080/24751839.2023.2207267","url":null,"abstract":"ABSTRACT Most speech processing models begin with feature extraction and then pass the feature vector to the primary processing model. The solution's performance mainly depends on the quality of the feature representation and the model architecture. Much research focuses on designing robust deep network architecture and ignoring feature representation's important role during the deep neural network era. This work aims to exploit a new approach to design a speech signal representation in the time-frequency domain via Linear Chirplet Transform (LCT). The proposed method provides a feature vector sensitive to the frequency change inside human speech with a solid mathematical foundation. This is a potential direction for many applications. The experimental results show the improvement of the feature based on LCT compared to MFCC or Fourier Transform. In both speaker gender recognition, dialect recognition, and speech recognition, LCT significantly improved compared with MFCC and other features. This result also implies that the feature based on LCT is independent of language, so it can be used in various applications.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42322050","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 : 2023-04-19DOI: 10.1080/24751839.2023.2198820
Ilhem Salah, Khaled Jouini, O. Korbaa
ABSTRACT Data Augmentation (DA) aims at synthesizing new training instances by applying transformations to available ones. DA has several well-known benefits such as: (i) increasing generalization ability; (ii) preventing data scarcity; and (iii) helping resolve class imbalance issues. In this work, we investigate the use of DA for stance and fake news detection. In the first part of our work, we explore the effect of various DA techniques on the performance of common classification algorithms. Our study reveals that the motto ‘the more, the better’ is the wrong approach regarding text augmentation and that there is no one-size-fits-all text augmentation technique. The second part of our work leverages the results of our study to propose a novel augmentation-based, ensemble learning approach. The proposed approach leverages text augmentation to enhance base learners' diversity and accuracy, ergo the predictive performance of the ensemble. The third part of our work experimentally investigates the use of DA to cope with the class imbalance problem. Class imbalance is very common in stance and fake news detection and often results in biased models. In this work we show how and to what extent text augmentation can help resolving moderate and severe imbalance.
{"title":"On the use of text augmentation for stance and fake news detection","authors":"Ilhem Salah, Khaled Jouini, O. Korbaa","doi":"10.1080/24751839.2023.2198820","DOIUrl":"https://doi.org/10.1080/24751839.2023.2198820","url":null,"abstract":"ABSTRACT Data Augmentation (DA) aims at synthesizing new training instances by applying transformations to available ones. DA has several well-known benefits such as: (i) increasing generalization ability; (ii) preventing data scarcity; and (iii) helping resolve class imbalance issues. In this work, we investigate the use of DA for stance and fake news detection. In the first part of our work, we explore the effect of various DA techniques on the performance of common classification algorithms. Our study reveals that the motto ‘the more, the better’ is the wrong approach regarding text augmentation and that there is no one-size-fits-all text augmentation technique. The second part of our work leverages the results of our study to propose a novel augmentation-based, ensemble learning approach. The proposed approach leverages text augmentation to enhance base learners' diversity and accuracy, ergo the predictive performance of the ensemble. The third part of our work experimentally investigates the use of DA to cope with the class imbalance problem. Class imbalance is very common in stance and fake news detection and often results in biased models. In this work we show how and to what extent text augmentation can help resolving moderate and severe imbalance.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41249018","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}