Pub Date : 2024-07-11DOI: 10.4108/eetinis.v11i3.5221
Pham Van Duong, T. Trinh, Minh-Tien Nguyen, Huy-The Vu, Minh Chuan Pham, Tran Manh Tuan, Le Hoang Son
Named entity recognition (NER) is one of the most important tasks in natural language processing, which identifies entity boundaries and classifies them into pre-defined categories. In literature, NER systems have been developed for various languages but limited works have been conducted for Vietnamese. This mainly comes from the limitation of available and high-quality annotated data, especially for specific domains such as medicine and healthcare. In this paper, we introduce a new medical NER dataset, named ViMedNER, for recognizing Vietnamese medical entities. Unlike existing works designed for common or too-specific entities, we focus on entity types that can be used in common diagnostic and treatment scenarios, including disease names, the symptoms of the diseases, the cause of the diseases, the diagnostic, and the treatment. These entities facilitate the diagnosis and treatment of doctors for common diseases. Our dataset is collected from four well-known Vietnamese websites that are professional in terms of drag selling and disease diagnostics and annotated by domain experts with high agreement scores. To create benchmark results, strong NER baselines based on pre-trained language models including PhoBERT, XLM-R, ViDeBERTa, ViPubMedDeBERTa, and ViHealthBERT are implemented and evaluated on the dataset. Experiment results show that the performance of XLM-R is consistently better than that of the other pre-trained language models. Furthermore, additional experiments are conducted to explore the behavior of the baselines and the characteristics of our dataset.
命名实体识别（NER）是自然语言处理中最重要的任务之一，它能识别实体边界并将其归入预定义的类别。在文献中，NER 系统已针对多种语言进行了开发，但针对越南语的工作还很有限。这主要是由于可用的高质量注释数据有限，尤其是在医学和医疗保健等特定领域。在本文中，我们介绍了一个新的医疗 NER 数据集，名为 ViMedNER，用于识别越南语医疗实体。与针对常见或过于特殊的实体设计的现有作品不同，我们专注于可用于常见诊断和治疗场景的实体类型，包括疾病名称、疾病症状、病因、诊断和治疗。这些实体有助于医生对常见疾病进行诊断和治疗。我们的数据集收集自四个知名的越南网站，这些网站在拖动销售和疾病诊断方面都很专业，并由领域专家注释，具有较高的一致性得分。为了创建基准结果，我们基于预先训练的语言模型（包括 PhoBERT、XLM-R、ViDeBERTa、ViPubMedDeBERTa 和 ViHealthBERT）实现了强大的 NER 基线，并在数据集上进行了评估。实验结果表明，XLM-R 的性能始终优于其他预训练语言模型。此外，我们还进行了其他实验，以探索基线的行为和我们数据集的特点。
{"title":"ViMedNER: A Medical Named Entity Recognition Dataset for Vietnamese","authors":"Pham Van Duong, T. Trinh, Minh-Tien Nguyen, Huy-The Vu, Minh Chuan Pham, Tran Manh Tuan, Le Hoang Son","doi":"10.4108/eetinis.v11i3.5221","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.5221","url":null,"abstract":"Named entity recognition (NER) is one of the most important tasks in natural language processing, which identifies entity boundaries and classifies them into pre-defined categories. In literature, NER systems have been developed for various languages but limited works have been conducted for Vietnamese. This mainly comes from the limitation of available and high-quality annotated data, especially for specific domains such as medicine and healthcare. In this paper, we introduce a new medical NER dataset, named ViMedNER, for recognizing Vietnamese medical entities. Unlike existing works designed for common or too-specific entities, we focus on entity types that can be used in common diagnostic and treatment scenarios, including disease names, the symptoms of the diseases, the cause of the diseases, the diagnostic, and the treatment. These entities facilitate the diagnosis and treatment of doctors for common diseases. Our dataset is collected from four well-known Vietnamese websites that are professional in terms of drag selling and disease diagnostics and annotated by domain experts with high agreement scores. To create benchmark results, strong NER baselines based on pre-trained language models including PhoBERT, XLM-R, ViDeBERTa, ViPubMedDeBERTa, and ViHealthBERT are implemented and evaluated on the dataset. Experiment results show that the performance of XLM-R is consistently better than that of the other pre-trained language models. Furthermore, additional experiments are conducted to explore the behavior of the baselines and the characteristics of our dataset.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141656122","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 : 2024-05-06DOI: 10.4108/eetinis.v11i3.5992
Yanqing Xu, Shuai Wang, Ruihong Jiang, Zhou Wang
This paper aims to develop a distributed channel estimation (CE) algorithm for spatially non-stationary (SNS) channels in extremely large aperture array systems, addressing the issues of high communication cost and computational complexity associated with traditional centralized algorithms. However, SNS channels differ from conventional spatially stationary channels, presenting new challenges such as varying sparsity patterns for different antennas. To overcome these challenges, we propose a novel distributed CE algorithm accompanied by a simple yet effective hard thresholding scheme. The proposed algorithm is not only suitable for uniform antenna arrays but also for irregularly deployed antennas. Simulation results demonstrate the advantages of the proposed algorithm in terms of estimation accuracy, communication cost, and computational complexity.
本文旨在为超大孔径阵列系统中的空间非静止（SNS）信道开发一种分布式信道估计（CE）算法，以解决与传统集中式算法相关的高通信成本和计算复杂性问题。然而，SNS 信道不同于传统的空间静止信道，它带来了新的挑战，例如不同天线的稀疏性模式各不相同。为了克服这些挑战，我们提出了一种新型分布式 CE 算法，并辅以简单有效的硬阈值方案。所提出的算法不仅适用于均匀天线阵列，也适用于不规则部署的天线。仿真结果证明了所提算法在估计精度、通信成本和计算复杂度方面的优势。
{"title":"Distributed Spatially Non-Stationary Channel Estimation for Extremely-Large Antenna Systems","authors":"Yanqing Xu, Shuai Wang, Ruihong Jiang, Zhou Wang","doi":"10.4108/eetinis.v11i3.5992","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.5992","url":null,"abstract":"This paper aims to develop a distributed channel estimation (CE) algorithm for spatially non-stationary (SNS) channels in extremely large aperture array systems, addressing the issues of high communication cost and computational complexity associated with traditional centralized algorithms. However, SNS channels differ from conventional spatially stationary channels, presenting new challenges such as varying sparsity patterns for different antennas. To overcome these challenges, we propose a novel distributed CE algorithm accompanied by a simple yet effective hard thresholding scheme. The proposed algorithm is not only suitable for uniform antenna arrays but also for irregularly deployed antennas. Simulation results demonstrate the advantages of the proposed algorithm in terms of estimation accuracy, communication cost, and computational complexity.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141007127","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 : 2024-05-02DOI: 10.4108/eetinis.v11i3.4728
Pham Minh Nam, Phong Ngo Dinh, Nguyen Luong Nhat, Tu Lam-Thanh, T. Le-Tien
The performance of multi-hop cluster-based wireless networks under multiple eavesdroppers is investigated in the present work. More precisely, we derive the outage probability (OP) of the considered networks under two relay selection schemes: the channel-gain-based scheme and the random scheme. Although equally correlated Rayleigh fading is taken into consideration, the derived mathematical framework remains tractable. Specifically, we represent the exact expression of the OP under the channel-based scheme in series form, while the OP under the random scheme is computed in a closed-form expression. Additionally, we propose a novel power allocation for each transmitter that strictly satisfies the given intercept probability. Numerical results based on the Monte Carlo method are provided to verify the correctness of the derived framework. These results are also used to identify the influences of various parameters, such as the number of clusters, the number of relays per cluster, and the transmit power.
本研究探讨了基于集群的多跳无线网络在多窃听器情况下的性能。更确切地说，我们推导了所考虑的网络在两种中继选择方案（基于信道增益的方案和随机方案）下的中断概率（OP）。虽然考虑到了等相关的瑞利衰落，但推导出的数学框架仍然是可行的。具体来说，我们用串联形式表示了基于信道的方案下 OP 的精确表达式，而随机方案下的 OP 则用闭式表达式计算。此外，我们还为每个发射机提出了严格满足给定截获概率的新型功率分配方案。我们提供了基于蒙特卡罗方法的数值结果，以验证推导框架的正确性。这些结果还用于确定各种参数的影响，如群集数、每个群集的中继数和发射功率。
{"title":"On the Performance of the Relay Selection in Multi-hop Cluster-based Wireless Networks with Multiple Eavesdroppers Under Equally Correlated Rayleigh Fading","authors":"Pham Minh Nam, Phong Ngo Dinh, Nguyen Luong Nhat, Tu Lam-Thanh, T. Le-Tien","doi":"10.4108/eetinis.v11i3.4728","DOIUrl":"https://doi.org/10.4108/eetinis.v11i3.4728","url":null,"abstract":"The performance of multi-hop cluster-based wireless networks under multiple eavesdroppers is investigated in the present work. More precisely, we derive the outage probability (OP) of the considered networks under two relay selection schemes: the channel-gain-based scheme and the random scheme. Although equally correlated Rayleigh fading is taken into consideration, the derived mathematical framework remains tractable. Specifically, we represent the exact expression of the OP under the channel-based scheme in series form, while the OP under the random scheme is computed in a closed-form expression. Additionally, we propose a novel power allocation for each transmitter that strictly satisfies the given intercept probability. Numerical results based on the Monte Carlo method are provided to verify the correctness of the derived framework. These results are also used to identify the influences of various parameters, such as the number of clusters, the number of relays per cluster, and the transmit power.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141020856","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}
In recent years, single-channel physiological recordings have gained popularity in portable health devices and research settings due to their convenience. However, the presence of electrooculogram (EOG) artifacts can significantly degrade the quality of the recorded data, impacting the accuracy of essential signal features. Consequently, artifact removal from physiological signals is a crucial step in signal processing pipelines. Current techniques often employ Independent Component Analysis (ICA) to efficiently separate signal and artifact sources in multichannel recordings. However, limitations arise when dealing with single or a few channel measurements in minimal instrumentation or portable devices, restricting the utility of ICA. To address this challenge, this paper introduces an innovative artifact removal algorithm utilizing enhanced empirical mode decomposition to extract the intrinsic mode functions (IMFs). Subsequently, the algorithm targets the removal of segments related to EOG by isolating them within these IMFs. The proposed method is compared with existing single-channel EEG artifact removal algorithms, demonstrating superior performance. The findings demonstrate the effectiveness of our approach in isolating artifact components, resulting in a reconstructed signal characterized by a strong correlation and a power spectrum closely resembling the ground-truth EEG signal. This outperforms the existing methods in terms of artifact removal. Additionally, the proposed algorithm exhibits significantly reduced execution time, enabling real-time online analysis.
{"title":"Real-time Single-Channel EOG removal based on Empirical Mode Decomposition","authors":"Kien Nguyen Trong, Nhat Nguyen Luong, Hanh Tan, Duy Tran Trung, Huong Ha Thi Thanh, Duy Pham The, Binh Nguyen Thanh","doi":"10.4108/eetinis.v11i2.4593","DOIUrl":"https://doi.org/10.4108/eetinis.v11i2.4593","url":null,"abstract":"In recent years, single-channel physiological recordings have gained popularity in portable health devices and research settings due to their convenience. However, the presence of electrooculogram (EOG) artifacts can significantly degrade the quality of the recorded data, impacting the accuracy of essential signal features. Consequently, artifact removal from physiological signals is a crucial step in signal processing pipelines. Current techniques often employ Independent Component Analysis (ICA) to efficiently separate signal and artifact sources in multichannel recordings. However, limitations arise when dealing with single or a few channel measurements in minimal instrumentation or portable devices, restricting the utility of ICA. To address this challenge, this paper introduces an innovative artifact removal algorithm utilizing enhanced empirical mode decomposition to extract the intrinsic mode functions (IMFs). Subsequently, the algorithm targets the removal of segments related to EOG by isolating them within these IMFs. The proposed method is compared with existing single-channel EEG artifact removal algorithms, demonstrating superior performance. The findings demonstrate the effectiveness of our approach in isolating artifact components, resulting in a reconstructed signal characterized by a strong correlation and a power spectrum closely resembling the ground-truth EEG signal. This outperforms the existing methods in terms of artifact removal. Additionally, the proposed algorithm exhibits significantly reduced execution time, enabling real-time online analysis.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140731868","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 : 2024-04-08DOI: 10.4108/eetinis.v11i2.5156
S. Lam, Xuan Nam Tran
INTRODUCTION: The beyond 5G millimeter wave cellular network system is expecting to provide the high quality of service in indoor areas. OBJECTIVES: Due to the high density of obstacles, the cooperative communication technique is employed to improve the user's desired signal power by finding more than one appropriate station to serve that user. METHODS: While the conventional system utilizes additional equipment such as Reconfigurable Intelligent Surfaces (RIS) and relays to enable the cooperative features, the paper introduces a new network paradigm that utilizes the second nearest Base Station (BS) of the typical user as the Decode and Forward (DF) relay. Thus, depends on the success of decoding the message from the user' serving BS of the second nearest BS, the typical user can work with and without assistance from the relay whose operation follows the discipline of the power-domain NOMA technique. In the case of with relay assistance, the Maximum Ratio Combining technique is utilized by the typical user to combine the desired signals. RESULTS: To examine the performance of the proposed system, the Nakagami-m and the newly developed path loss model, which considers the density of walls and their properties, are adopted to derive the coverage probability of the user with and without relay assistance. The closed-form expressions of this performance metric are derived by Gauss quadrature and Welch-Satterthwaite approximation.
{"title":"Improving Performance of the Typical User in the Indoor Cooperative NOMA Millimeter Wave Networks with Presence of Walls","authors":"S. Lam, Xuan Nam Tran","doi":"10.4108/eetinis.v11i2.5156","DOIUrl":"https://doi.org/10.4108/eetinis.v11i2.5156","url":null,"abstract":"INTRODUCTION: The beyond 5G millimeter wave cellular network system is expecting to provide the high quality of service in indoor areas. OBJECTIVES: Due to the high density of obstacles, the cooperative communication technique is employed to improve the user's desired signal power by finding more than one appropriate station to serve that user. METHODS: While the conventional system utilizes additional equipment such as Reconfigurable Intelligent Surfaces (RIS) and relays to enable the cooperative features, the paper introduces a new network paradigm that utilizes the second nearest Base Station (BS) of the typical user as the Decode and Forward (DF) relay. Thus, depends on the success of decoding the message from the user' serving BS of the second nearest BS, the typical user can work with and without assistance from the relay whose operation follows the discipline of the power-domain NOMA technique. In the case of with relay assistance, the Maximum Ratio Combining technique is utilized by the typical user to combine the desired signals. RESULTS: To examine the performance of the proposed system, the Nakagami-m and the newly developed path loss model, which considers the density of walls and their properties, are adopted to derive the coverage probability of the user with and without relay assistance. The closed-form expressions of this performance metric are derived by Gauss quadrature and Welch-Satterthwaite approximation.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140731650","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 : 2024-03-13DOI: 10.4108/eetinis.v11i2.4318
Mohamed Oulad-Kaddour, Hamid Haddadou, D. Palacios-Alonso, C. Conde, E. Cabello
The world has lived an exceptional time period caused by the Coronavirus pandemic. To limit Covid-19 propagation, governments required people to wear a facial mask outside. In facial data analysis, mask-wearing on the human face creates predominant occlusion hiding the important oral region and causing more challenges for human face recognition and categorisation. The appropriation of existing solutions by taking into consideration the masked context is indispensable for researchers. In this paper, we propose an approach for mask-wearing prediction and adaptive facial human-gender classification. The proposed approach is based on convolutional neural networks (CNNs). Both mask-wearing and gender information are crucial for various possible applications. Experimentation shows that mask-wearing is very well detectable by using CNNs and justifies its use as a prepossessing step. It also shows that retraining with masked faces is indispensable to keep up gender classification performances. In addition, experimentation proclaims that in a controlled face-pose with acceptable image quality' context, the gender attribute remains well detectable. Finally, we show empirically that the adaptive proposed approach improves global performance for gender prediction in a mixed context.
{"title":"Facial mask-wearing prediction and adaptive gender classification using convolutional neural networks","authors":"Mohamed Oulad-Kaddour, Hamid Haddadou, D. Palacios-Alonso, C. Conde, E. Cabello","doi":"10.4108/eetinis.v11i2.4318","DOIUrl":"https://doi.org/10.4108/eetinis.v11i2.4318","url":null,"abstract":"The world has lived an exceptional time period caused by the Coronavirus pandemic. To limit Covid-19 propagation, governments required people to wear a facial mask outside. In facial data analysis, mask-wearing on the human face creates predominant occlusion hiding the important oral region and causing more challenges for human face recognition and categorisation. The appropriation of existing solutions by taking into consideration the masked context is indispensable for researchers. In this paper, we propose an approach for mask-wearing prediction and adaptive facial human-gender classification. The proposed approach is based on convolutional neural networks (CNNs). Both mask-wearing and gender information are crucial for various possible applications. Experimentation shows that mask-wearing is very well detectable by using CNNs and justifies its use as a prepossessing step. It also shows that retraining with masked faces is indispensable to keep up gender classification performances. In addition, experimentation proclaims that in a controlled face-pose with acceptable image quality' context, the gender attribute remains well detectable. Finally, we show empirically that the adaptive proposed approach improves global performance for gender prediction in a mixed context.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140247678","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 : 2024-03-07DOI: 10.4108/eetinis.v11i2.4678
Quang-Tu Pham, Dinh-Dat Pham, Khanh-Ly Can, Hieu Dao To, Hoang-Dieu Vu
This study delves into the application of deep learning training techniques using a restricted dataset, encompassing around 400 vehicle images sourced from Kaggle. Faced with the challenges of limited data, the impracticality of training models from scratch becomes apparent, advocating instead for the utilization of pre-trained models with pre-trained weights. The investigation considers three prominent models—EfficientNetB0, ResNetB0, and MobileNetV2—with EfficientNetB0 emerging as the most proficient choice. Employing the gradually unfreeze layer technique over a specified number of epochs, EfficientNetB0 exhibits remarkable accuracy, reaching 99.5% on the training dataset and 97% on the validation dataset. In contrast, training models from scratch results in notably lower accuracy. In this context, knowledge distillation proves pivotal, overcoming this limitation and significantly improving accuracy from 29.5% in training and 20.5% in validation to 54% and 45%, respectively. This study uniquely contributes by exploring transfer learning with gradually unfreeze layers and elucidates the potential of knowledge distillation. It highlights their effectiveness in robustly enhancing model performance under data scarcity, thus addressing challenges associated with training deep learning models on limited datasets. The findings underscore the practical significance of these techniques in achieving superior results when confronted with data constraints in real-world scenarios
{"title":"Vehicle Type Classification with Small Dataset and Transfer Learning Techniques","authors":"Quang-Tu Pham, Dinh-Dat Pham, Khanh-Ly Can, Hieu Dao To, Hoang-Dieu Vu","doi":"10.4108/eetinis.v11i2.4678","DOIUrl":"https://doi.org/10.4108/eetinis.v11i2.4678","url":null,"abstract":"This study delves into the application of deep learning training techniques using a restricted dataset, encompassing around 400 vehicle images sourced from Kaggle. Faced with the challenges of limited data, the impracticality of training models from scratch becomes apparent, advocating instead for the utilization of pre-trained models with pre-trained weights. The investigation considers three prominent models—EfficientNetB0, ResNetB0, and MobileNetV2—with EfficientNetB0 emerging as the most proficient choice. Employing the gradually unfreeze layer technique over a specified number of epochs, EfficientNetB0 exhibits remarkable accuracy, reaching 99.5% on the training dataset and 97% on the validation dataset. In contrast, training models from scratch results in notably lower accuracy. In this context, knowledge distillation proves pivotal, overcoming this limitation and significantly improving accuracy from 29.5% in training and 20.5% in validation to 54% and 45%, respectively. This study uniquely contributes by exploring transfer learning with gradually unfreeze layers and elucidates the potential of knowledge distillation. It highlights their effectiveness in robustly enhancing model performance under data scarcity, thus addressing challenges associated with training deep learning models on limited datasets. The findings underscore the practical significance of these techniques in achieving superior results when confronted with data constraints in real-world scenarios","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140077575","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 : 2024-02-22DOI: 10.4108/eetinis.v11i1.4703
Khalid Saifullah, Muhammad Ibrahim Khan, Suhaima Jamal, Iqbal H. Sarker
In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The intelligent BullyFilterNeT system devised overcomes Out-of-Vocabulary (OOV) challenges associated with non-contextual embeddings and addresses the limitations of context-aware feature representations. To facilitate a comprehensive understanding, three non-contextual embedding models GloVe, FastText, and Word2Vec are developed for feature extraction in Bengali. These embedding models are utilized in the classification models, employing three statistical models (SVM, SGD, Libsvm), and four deep learning models (CNN, VDCNN, LSTM, GRU). Additionally, the study employs six transformer-based language models: mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT, respectively to overcome the limitations of earlier models. Remarkably, BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, underscoring its effectiveness in cyberbullying text identification in the Bengali language.
{"title":"Cyberbullying Text Identification based on Deep Learning and Transformer-based Language Models","authors":"Khalid Saifullah, Muhammad Ibrahim Khan, Suhaima Jamal, Iqbal H. Sarker","doi":"10.4108/eetinis.v11i1.4703","DOIUrl":"https://doi.org/10.4108/eetinis.v11i1.4703","url":null,"abstract":"In the contemporary digital age, social media platforms like Facebook, Twitter, and YouTube serve as vital channels for individuals to express ideas and connect with others. Despite fostering increased connectivity, these platforms have inadvertently given rise to negative behaviors, particularly cyberbullying. While extensive research has been conducted on high-resource languages such as English, there is a notable scarcity of resources for low-resource languages like Bengali, Arabic, Tamil, etc., particularly in terms of language modeling. This study addresses this gap by developing a cyberbullying text identification system called BullyFilterNeT tailored for social media texts, considering Bengali as a test case. The intelligent BullyFilterNeT system devised overcomes Out-of-Vocabulary (OOV) challenges associated with non-contextual embeddings and addresses the limitations of context-aware feature representations. To facilitate a comprehensive understanding, three non-contextual embedding models GloVe, FastText, and Word2Vec are developed for feature extraction in Bengali. These embedding models are utilized in the classification models, employing three statistical models (SVM, SGD, Libsvm), and four deep learning models (CNN, VDCNN, LSTM, GRU). Additionally, the study employs six transformer-based language models: mBERT, bELECTRA, IndicBERT, XML-RoBERTa, DistilBERT, and BanglaBERT, respectively to overcome the limitations of earlier models. Remarkably, BanglaBERT-based BullyFilterNeT achieves the highest accuracy of 88.04% in our test set, underscoring its effectiveness in cyberbullying text identification in the Bengali language.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140440847","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 : 2024-02-13DOI: 10.4108/eetinis.v11i1.4369
Hữu Quý Trần, Ho Van Khuong
Reconfigurable intelligent surface (RIS) can serve as a passive relay to maintain communication between a transceiver in severe scenarios of no direct link between them. In addition, harvesting energy from radio frequency (RF) signals can meliorate significantly energy efficiency. In this research, we propose RIS-aided communication systems with energy harvesting (RISwEH) which combine both RIS and RF energy harvesting to improve energy efficiency as well as communication reliability. To evaluate realistically and quickly the performance of the RISwEH, we propose the explicit formulas of the system throughput and the outage probability under the realistic scenario of Nakagami-m fading and imperfect channel state information (CSI). Moreover, we propose an optimization algorithm relied upon a Golden section search to attain the optimum value of the time splitting factor of energy harvester to obtain the best system performance. Various results corroborate the theoretical derivations, confirm the efficacy of the proposed optimization algorithm, and illustrate the influence of innumerable system settings on the system performance. Particularly, the imperfect CSI deteriorates considerably the system performance. Nonetheless, the performance of the RISwEH can be enhanced by accreting the quantity of the elements of the RIS as well as with the lower fading severity. Furthermore, the time splitting factor also impacts dramatically the outage performance of the RISwEH and its optimal value mitigates significantly the outage probability.
{"title":"Performance Analysis for Reconfigurable Intelligent Surface-aided Communication Systems with Energy Harvesting under Imperfect Nakagami-m Channel Information","authors":"Hữu Quý Trần, Ho Van Khuong","doi":"10.4108/eetinis.v11i1.4369","DOIUrl":"https://doi.org/10.4108/eetinis.v11i1.4369","url":null,"abstract":"Reconfigurable intelligent surface (RIS) can serve as a passive relay to maintain communication between a transceiver in severe scenarios of no direct link between them. In addition, harvesting energy from radio frequency (RF) signals can meliorate significantly energy efficiency. In this research, we propose RIS-aided communication systems with energy harvesting (RISwEH) which combine both RIS and RF energy harvesting to improve energy efficiency as well as communication reliability. To evaluate realistically and quickly the performance of the RISwEH, we propose the explicit formulas of the system throughput and the outage probability under the realistic scenario of Nakagami-m fading and imperfect channel state information (CSI). Moreover, we propose an optimization algorithm relied upon a Golden section search to attain the optimum value of the time splitting factor of energy harvester to obtain the best system performance. Various results corroborate the theoretical derivations, confirm the efficacy of the proposed optimization algorithm, and illustrate the influence of innumerable system settings on the system performance. Particularly, the imperfect CSI deteriorates considerably the system performance. Nonetheless, the performance of the RISwEH can be enhanced by accreting the quantity of the elements of the RIS as well as with the lower fading severity. Furthermore, the time splitting factor also impacts dramatically the outage performance of the RISwEH and its optimal value mitigates significantly the outage probability.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139781230","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 : 2024-02-13DOI: 10.4108/eetinis.v11i1.4369
Hữu Quý Trần, Ho Van Khuong
Reconfigurable intelligent surface (RIS) can serve as a passive relay to maintain communication between a transceiver in severe scenarios of no direct link between them. In addition, harvesting energy from radio frequency (RF) signals can meliorate significantly energy efficiency. In this research, we propose RIS-aided communication systems with energy harvesting (RISwEH) which combine both RIS and RF energy harvesting to improve energy efficiency as well as communication reliability. To evaluate realistically and quickly the performance of the RISwEH, we propose the explicit formulas of the system throughput and the outage probability under the realistic scenario of Nakagami-m fading and imperfect channel state information (CSI). Moreover, we propose an optimization algorithm relied upon a Golden section search to attain the optimum value of the time splitting factor of energy harvester to obtain the best system performance. Various results corroborate the theoretical derivations, confirm the efficacy of the proposed optimization algorithm, and illustrate the influence of innumerable system settings on the system performance. Particularly, the imperfect CSI deteriorates considerably the system performance. Nonetheless, the performance of the RISwEH can be enhanced by accreting the quantity of the elements of the RIS as well as with the lower fading severity. Furthermore, the time splitting factor also impacts dramatically the outage performance of the RISwEH and its optimal value mitigates significantly the outage probability.
{"title":"Performance Analysis for Reconfigurable Intelligent Surface-aided Communication Systems with Energy Harvesting under Imperfect Nakagami-m Channel Information","authors":"Hữu Quý Trần, Ho Van Khuong","doi":"10.4108/eetinis.v11i1.4369","DOIUrl":"https://doi.org/10.4108/eetinis.v11i1.4369","url":null,"abstract":"Reconfigurable intelligent surface (RIS) can serve as a passive relay to maintain communication between a transceiver in severe scenarios of no direct link between them. In addition, harvesting energy from radio frequency (RF) signals can meliorate significantly energy efficiency. In this research, we propose RIS-aided communication systems with energy harvesting (RISwEH) which combine both RIS and RF energy harvesting to improve energy efficiency as well as communication reliability. To evaluate realistically and quickly the performance of the RISwEH, we propose the explicit formulas of the system throughput and the outage probability under the realistic scenario of Nakagami-m fading and imperfect channel state information (CSI). Moreover, we propose an optimization algorithm relied upon a Golden section search to attain the optimum value of the time splitting factor of energy harvester to obtain the best system performance. Various results corroborate the theoretical derivations, confirm the efficacy of the proposed optimization algorithm, and illustrate the influence of innumerable system settings on the system performance. Particularly, the imperfect CSI deteriorates considerably the system performance. Nonetheless, the performance of the RISwEH can be enhanced by accreting the quantity of the elements of the RIS as well as with the lower fading severity. Furthermore, the time splitting factor also impacts dramatically the outage performance of the RISwEH and its optimal value mitigates significantly the outage probability.","PeriodicalId":33474,"journal":{"name":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139841123","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：