Pub Date : 2023-03-23DOI: 10.1080/24751839.2023.2183631
Hoang Hai Son, Tran Anh Khoa, Thanh Phong Doan, Huu Khoa Tran, Duc Ngoc Minh Dang, Hoang Nam Nguyen
ABSTRACT As digitization is integrated into daily life, media are increasingly transferred over the Internet. Voice-over-Internet Protocol (VoIP), the most popular media transfer technology, is attracting many researchers and investments. The application of Artificial Intelligence (AI) technology into the Private Branch Exchange (PBX) has played a pivotal role in enhancing the customer experience and is able to unite employees in any company. One technology application used to optimize customer experience in a call centre is the use of an automatic PBX integrated with a Virtual Assistant (VA), which interacts directly with the PBX through voice and in multiple languages without any keystrokes. The Interactive Voice Response (IVR) module forwards the customer’s call to an operator or supports automatic processing. This solution can help businesses to handle thousands of calls per day with optimal performance, thus creating a customer care campaign that quickly reaches many users. A PBX integrated with Vietnamese Virtual Assistants (VVA) on an AI technology platform will also help businesses to cut down on operator costs with automated calls. Through comparison with a traditional PBX, this article analyzes, evaluates and optimizes an automatic PBX system with integrated VVA, thereby offering efficient solutions for interest companies.
{"title":"Design and implementation of a VoIP PBX integrated Vietnamese virtual assistant: a case study","authors":"Hoang Hai Son, Tran Anh Khoa, Thanh Phong Doan, Huu Khoa Tran, Duc Ngoc Minh Dang, Hoang Nam Nguyen","doi":"10.1080/24751839.2023.2183631","DOIUrl":"https://doi.org/10.1080/24751839.2023.2183631","url":null,"abstract":"ABSTRACT As digitization is integrated into daily life, media are increasingly transferred over the Internet. Voice-over-Internet Protocol (VoIP), the most popular media transfer technology, is attracting many researchers and investments. The application of Artificial Intelligence (AI) technology into the Private Branch Exchange (PBX) has played a pivotal role in enhancing the customer experience and is able to unite employees in any company. One technology application used to optimize customer experience in a call centre is the use of an automatic PBX integrated with a Virtual Assistant (VA), which interacts directly with the PBX through voice and in multiple languages without any keystrokes. The Interactive Voice Response (IVR) module forwards the customer’s call to an operator or supports automatic processing. This solution can help businesses to handle thousands of calls per day with optimal performance, thus creating a customer care campaign that quickly reaches many users. A PBX integrated with Vietnamese Virtual Assistants (VVA) on an AI technology platform will also help businesses to cut down on operator costs with automated calls. Through comparison with a traditional PBX, this article analyzes, evaluates and optimizes an automatic PBX system with integrated VVA, thereby offering efficient solutions for interest companies.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"201 - 226"},"PeriodicalIF":2.7,"publicationDate":"2023-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46087612","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 : 2023-03-22DOI: 10.1080/24751839.2023.2186624
Long Ngo, Chieu Luong Xuan, H. M. Luong, Bình Ngô Thanh, Bui Ngoc Dung
ABSTRACT Crack detection is one of the crucial aspects of bridge evaluation and maintenance. Several existing image-based methods require capturing the bridge surface and extracting crack features to detect the crack. However, in some positions such as the space under the bridge and piers, it is difficult to capture crack images. This paper aims to apply a method to detect cracks on the bridge surface by using a drone that can capture images in challenging positions. The video recorded from the drone will be automatically identified the cracks by employing the deep learning method. Deep learning is designed for training and testing the dataset with 51.000 images, each image sized 244 × 244. The deep learning method shows the feasibility of detecting the cracks in the transport facility. This is supported by the high accuracy of the experimental results of 95.19%. In addition, the tool can assign an ID containing information to each crack from video so that these cracks can then be mounted on a 3D map of the bridge for research on crack development over time in the task of assessing the health of bridges.
{"title":"Designing image processing tools for testing concrete bridges by a drone based on deep learning","authors":"Long Ngo, Chieu Luong Xuan, H. M. Luong, Bình Ngô Thanh, Bui Ngoc Dung","doi":"10.1080/24751839.2023.2186624","DOIUrl":"https://doi.org/10.1080/24751839.2023.2186624","url":null,"abstract":"ABSTRACT Crack detection is one of the crucial aspects of bridge evaluation and maintenance. Several existing image-based methods require capturing the bridge surface and extracting crack features to detect the crack. However, in some positions such as the space under the bridge and piers, it is difficult to capture crack images. This paper aims to apply a method to detect cracks on the bridge surface by using a drone that can capture images in challenging positions. The video recorded from the drone will be automatically identified the cracks by employing the deep learning method. Deep learning is designed for training and testing the dataset with 51.000 images, each image sized 244 × 244. The deep learning method shows the feasibility of detecting the cracks in the transport facility. This is supported by the high accuracy of the experimental results of 95.19%. In addition, the tool can assign an ID containing information to each crack from video so that these cracks can then be mounted on a 3D map of the bridge for research on crack development over time in the task of assessing the health of bridges.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"227 - 240"},"PeriodicalIF":2.7,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41339914","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 : 2023-03-22DOI: 10.1080/24751839.2023.2183802
Kanaad Deshpande, Junaid Girkar, Ramchandra S. Mangrulkar
ABSTRACT This paper presents a novel approach for encrypting images using a Sudoku as its encryption key. This algorithm uses both symmetric and asymmetric key cryptography. It works with any type of data, Sudoku size, and keyspace. The image undergoes the process of modified thresholding, using a pseudo-random number generated from a Sudoku as the threshold. This image is then padded with zeros or the average pixel values to ensure the dimensions are multiples of the Sudoku's size and the image rows are shuffled randomly. For each iteration, the image rows are shuffled, followed by the columns, and finally, the image is rotated clockwise by 90 degrees. The resultant image is highly encrypted and resilient to brute-forcing methods. The algorithm requires roughly 25 milliseconds per iteration for a colored square image of dimensions and has an NPCR value of 99.60% and a UACI value of 35.65%. The gargantuan keyspace offered by the Sudoku keys ensures obedience of Kirchoff's principle and Shannon's maxim.
{"title":"Security enhancement and analysis of images using a novel Sudoku-based encryption algorithm","authors":"Kanaad Deshpande, Junaid Girkar, Ramchandra S. Mangrulkar","doi":"10.1080/24751839.2023.2183802","DOIUrl":"https://doi.org/10.1080/24751839.2023.2183802","url":null,"abstract":"ABSTRACT This paper presents a novel approach for encrypting images using a Sudoku as its encryption key. This algorithm uses both symmetric and asymmetric key cryptography. It works with any type of data, Sudoku size, and keyspace. The image undergoes the process of modified thresholding, using a pseudo-random number generated from a Sudoku as the threshold. This image is then padded with zeros or the average pixel values to ensure the dimensions are multiples of the Sudoku's size and the image rows are shuffled randomly. For each iteration, the image rows are shuffled, followed by the columns, and finally, the image is rotated clockwise by 90 degrees. The resultant image is highly encrypted and resilient to brute-forcing methods. The algorithm requires roughly 25 milliseconds per iteration for a colored square image of dimensions and has an NPCR value of 99.60% and a UACI value of 35.65%. The gargantuan keyspace offered by the Sudoku keys ensures obedience of Kirchoff's principle and Shannon's maxim.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"270 - 303"},"PeriodicalIF":2.7,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41480494","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 : 2023-03-19DOI: 10.1080/24751839.2023.2186625
Huan Vu, Ngoc-Dung Bui
ABSTRACT Neural Machine Translation (NMT) has constantly been shown to be a standard choice to build a translation system, in both academia and industry. For low-resource language pairs, data augmentation techniques have been widely used to tackle the data shortage problem in NMT. In this paper, we investigate the scaling behaviour of transformer-based NMT model to the increasing amount of synthetic data. Through the experiments, conducted in the Chinese-to-Vietnamese translation task, we aim to provide a guideline to the application of several methods such as back-translation, tagged back-translation, self-training and sentence concatenation in a low-resource, less-related language pair. Our results suggest that choosing the appropriate amount of synthetic data is a crucial task when building NMT systems. In addition, when combining methods, it is recommended to tag the data sources before training.
{"title":"On the scalability of data augmentation techniques for low-resource machine translation between Chinese and Vietnamese","authors":"Huan Vu, Ngoc-Dung Bui","doi":"10.1080/24751839.2023.2186625","DOIUrl":"https://doi.org/10.1080/24751839.2023.2186625","url":null,"abstract":"ABSTRACT Neural Machine Translation (NMT) has constantly been shown to be a standard choice to build a translation system, in both academia and industry. For low-resource language pairs, data augmentation techniques have been widely used to tackle the data shortage problem in NMT. In this paper, we investigate the scaling behaviour of transformer-based NMT model to the increasing amount of synthetic data. Through the experiments, conducted in the Chinese-to-Vietnamese translation task, we aim to provide a guideline to the application of several methods such as back-translation, tagged back-translation, self-training and sentence concatenation in a low-resource, less-related language pair. Our results suggest that choosing the appropriate amount of synthetic data is a crucial task when building NMT systems. In addition, when combining methods, it is recommended to tag the data sources before training.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"241 - 253"},"PeriodicalIF":2.7,"publicationDate":"2023-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47242555","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 : 2023-03-17DOI: 10.1080/24751839.2023.2187278
Nhat Truong Pham, Sy Dzung Nguyen, Vu Song Thuy Nguyen, Bich Ngoc Hong Pham, Duc Ngoc Minh Dang
ABSTRACT Speech emotion recognition (SER) has several applications, such as e-learning, human-computer interaction, customer service, and healthcare systems. Although researchers have investigated lots of techniques to improve the accuracy of SER, it has been challenging with feature extraction, classifier schemes, and computational costs. To address the aforementioned problems, we propose a new set of 1D features extracted by using an overlapping sliding window (OSW) technique for SER in this study. In addition, a deep neural network-based classifier scheme called the deep Pattern Recognition Network (PRN) is designed to categorize emotional states from the new set of 1D features. We evaluate the proposed method on the Emo-DB and the AESSD datasets that contain several different emotional states. The experimental results show that the proposed method achieves an accuracy of 98.5% and 87.1% on the Emo-DB and AESSD datasets, respectively. It is also more comparable with accuracy to and better than the state-of-the-art and current approaches that use 1D features on the same datasets for SER. Furthermore, the SHAP (SHapley Additive exPlanations) analysis is employed for interpreting the prediction model to assist system developers in selecting the optimal features to integrate into the desired system.
{"title":"Speech emotion recognition using overlapping sliding window and Shapley additive explainable deep neural network","authors":"Nhat Truong Pham, Sy Dzung Nguyen, Vu Song Thuy Nguyen, Bich Ngoc Hong Pham, Duc Ngoc Minh Dang","doi":"10.1080/24751839.2023.2187278","DOIUrl":"https://doi.org/10.1080/24751839.2023.2187278","url":null,"abstract":"ABSTRACT Speech emotion recognition (SER) has several applications, such as e-learning, human-computer interaction, customer service, and healthcare systems. Although researchers have investigated lots of techniques to improve the accuracy of SER, it has been challenging with feature extraction, classifier schemes, and computational costs. To address the aforementioned problems, we propose a new set of 1D features extracted by using an overlapping sliding window (OSW) technique for SER in this study. In addition, a deep neural network-based classifier scheme called the deep Pattern Recognition Network (PRN) is designed to categorize emotional states from the new set of 1D features. We evaluate the proposed method on the Emo-DB and the AESSD datasets that contain several different emotional states. The experimental results show that the proposed method achieves an accuracy of 98.5% and 87.1% on the Emo-DB and AESSD datasets, respectively. It is also more comparable with accuracy to and better than the state-of-the-art and current approaches that use 1D features on the same datasets for SER. Furthermore, the SHAP (SHapley Additive exPlanations) analysis is employed for interpreting the prediction model to assist system developers in selecting the optimal features to integrate into the desired system.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"317 - 335"},"PeriodicalIF":2.7,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43058511","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 : 2023-03-15DOI: 10.1080/24751839.2023.2185448
B. Ngo, Chieu X. Luong, Long Ngo, H. M. Luong
ABSTRACT This study contributes an efficient method for assessing the structural integrity of concrete bridges by collecting images of surface cracks and defects with drones. The use of drones to gather crack samples reduces human error and is appropriate in adverse working conditions and short-duration examinations. This work introduces a new POI (Points of Interest) flying algorithm for typical flight paths, based on the drone flying criteria of safe viewing distance and the POI concept. In this research, the flight controller of the drone was combined with a Raspberry Pi4 to build and alter a typical flight path suitable for the mission, with the addition of interactive features that control flight mode switching, separation, and automatic return to the original orbit to meet expertly specified POIs. In other words, as drones approach a region requiring image capture, they automatically move to a safe distance to photograph cracks and then return to their predetermined orbit. An experiment at the Cau May bridge demonstrates that the path-planning algorithms created on an embedded computer can successfully coordinate with the flight controller switching three times to hover and zoom in on fractures during the inspection.
{"title":"Development of a solution for collecting crack images on concrete surfaces to assess the structural health of bridges using drone","authors":"B. Ngo, Chieu X. Luong, Long Ngo, H. M. Luong","doi":"10.1080/24751839.2023.2185448","DOIUrl":"https://doi.org/10.1080/24751839.2023.2185448","url":null,"abstract":"ABSTRACT This study contributes an efficient method for assessing the structural integrity of concrete bridges by collecting images of surface cracks and defects with drones. The use of drones to gather crack samples reduces human error and is appropriate in adverse working conditions and short-duration examinations. This work introduces a new POI (Points of Interest) flying algorithm for typical flight paths, based on the drone flying criteria of safe viewing distance and the POI concept. In this research, the flight controller of the drone was combined with a Raspberry Pi4 to build and alter a typical flight path suitable for the mission, with the addition of interactive features that control flight mode switching, separation, and automatic return to the original orbit to meet expertly specified POIs. In other words, as drones approach a region requiring image capture, they automatically move to a safe distance to photograph cracks and then return to their predetermined orbit. An experiment at the Cau May bridge demonstrates that the path-planning algorithms created on an embedded computer can successfully coordinate with the flight controller switching three times to hover and zoom in on fractures during the inspection.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"304 - 316"},"PeriodicalIF":2.7,"publicationDate":"2023-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43554686","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 : 2023-03-07DOI: 10.1080/24751839.2023.2182174
N. Le
ABSTRACT In the last decade, agent-based modelling and simulation has emerged as a potential approach to study complex systems in the real world, such as traffic congestion. Complex systems could be modelled as a collection of autonomous agents, who observe the external environment, interact with each other and perform suitable actions. In addition, reinforcement learning, a branch of Machine Learning, that models the learning process of a single agent as a Markov decision process, has recently achieved remarkable results in several domains (e.g. Atari games, Dota 2, Go, Self-driving cars, Protein folding, etc.), especially with the invention of deep reinforcement learning. Multi-agent reinforcement learning, by taking advantage of these two approaches, is a new technique that can be used to further study complex systems. In this article, we present a multi-agent reinforcement learning model for traffic congestion on one-way multi-lane highways and experiment with six reinforcement learning algorithms in this setting.
{"title":"Multi-agent reinforcement learning for traffic congestion on one-way multi-lane highways","authors":"N. Le","doi":"10.1080/24751839.2023.2182174","DOIUrl":"https://doi.org/10.1080/24751839.2023.2182174","url":null,"abstract":"ABSTRACT In the last decade, agent-based modelling and simulation has emerged as a potential approach to study complex systems in the real world, such as traffic congestion. Complex systems could be modelled as a collection of autonomous agents, who observe the external environment, interact with each other and perform suitable actions. In addition, reinforcement learning, a branch of Machine Learning, that models the learning process of a single agent as a Markov decision process, has recently achieved remarkable results in several domains (e.g. Atari games, Dota 2, Go, Self-driving cars, Protein folding, etc.), especially with the invention of deep reinforcement learning. Multi-agent reinforcement learning, by taking advantage of these two approaches, is a new technique that can be used to further study complex systems. In this article, we present a multi-agent reinforcement learning model for traffic congestion on one-way multi-lane highways and experiment with six reinforcement learning algorithms in this setting.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"255 - 269"},"PeriodicalIF":2.7,"publicationDate":"2023-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46701229","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 : 2023-03-06DOI: 10.1080/24751839.2023.2179909
A. Hamdi, Amina Nahali, Mokhtar Harrabi, Rafik Brahem
ABSTRACT Over the past decade, the continuous development and the high level of maturity of wireless sensor networks resulted in new networks called wireless body area networks (WBANs), which are an emerging sector of biomedical technology. Moreover, this field has gained significant attention due to its applications which mainly are toward biomedical and healthcare applications. Nowadays, small sensors that can transfer data to other devices can now be implanted anywhere on the human body to record different physiological indicators and enable further actions to be conducted, such as processing, remote procedures and decision aided. Considering this recent hot subject, the intent of this work is to present a new approach of the optimized design and the performance analysis of WBAN specifically channel modelling between wearable wireless sensors. The behaviour of these sensors on the human body is theoretically and experimentally explored in detail along this paper. A good agreement is obtained between the theoretical and the experimental results, although the complexity of the physiological behaviour of human body.
{"title":"Optimized design and performance analysis of wearable antenna sensors for wireless body area network applications","authors":"A. Hamdi, Amina Nahali, Mokhtar Harrabi, Rafik Brahem","doi":"10.1080/24751839.2023.2179909","DOIUrl":"https://doi.org/10.1080/24751839.2023.2179909","url":null,"abstract":"ABSTRACT Over the past decade, the continuous development and the high level of maturity of wireless sensor networks resulted in new networks called wireless body area networks (WBANs), which are an emerging sector of biomedical technology. Moreover, this field has gained significant attention due to its applications which mainly are toward biomedical and healthcare applications. Nowadays, small sensors that can transfer data to other devices can now be implanted anywhere on the human body to record different physiological indicators and enable further actions to be conducted, such as processing, remote procedures and decision aided. Considering this recent hot subject, the intent of this work is to present a new approach of the optimized design and the performance analysis of WBAN specifically channel modelling between wearable wireless sensors. The behaviour of these sensors on the human body is theoretically and experimentally explored in detail along this paper. A good agreement is obtained between the theoretical and the experimental results, although the complexity of the physiological behaviour of human body.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"155 - 175"},"PeriodicalIF":2.7,"publicationDate":"2023-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"60140896","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 : 2023-02-18DOI: 10.1080/24751839.2023.2174646
T. N. Cao, Thi Quynh Hoa Nguyen, Thi Nha Nguyen, Ngoc Hieu Nguyen, D. T. Le
ABSTRACT In this paper, an antenna design method operating at 3.5 GHz for 5G system is presented to improve its performance. The antenna is designed using fractal geometry combined with an imperfectly structured ground plane. In which, the radiation surface has the form of a Minkowski island fractal geometry, and the removed part of the ground is a complementary split ring resonator unit cell. In this design, the substrate material is FR4-epoxy microwave laminates with dielectric constant ϵ = 4.4, loss tangent (tan δ) of 0.02, and h = 1.6 mm thickness used to design the antennas. HFSS software is used in the simulation with the feeding method with a microstrip line. The proposed antenna has a significant performance increase compared to the original microstrip antenna such as reduced about 56% reduction in total size, enhanced 207% bandwidth, increased peak gain to 4.66 dB, and improved radiated efficiency to 89.3%. The physical model of the antenna has been fabricated and measured to verify the correctness of the design.
{"title":"Improved performance for antenna based on a combination of fractal geometry with CSRR","authors":"T. N. Cao, Thi Quynh Hoa Nguyen, Thi Nha Nguyen, Ngoc Hieu Nguyen, D. T. Le","doi":"10.1080/24751839.2023.2174646","DOIUrl":"https://doi.org/10.1080/24751839.2023.2174646","url":null,"abstract":"ABSTRACT In this paper, an antenna design method operating at 3.5 GHz for 5G system is presented to improve its performance. The antenna is designed using fractal geometry combined with an imperfectly structured ground plane. In which, the radiation surface has the form of a Minkowski island fractal geometry, and the removed part of the ground is a complementary split ring resonator unit cell. In this design, the substrate material is FR4-epoxy microwave laminates with dielectric constant ϵ = 4.4, loss tangent (tan δ) of 0.02, and h = 1.6 mm thickness used to design the antennas. HFSS software is used in the simulation with the feeding method with a microstrip line. The proposed antenna has a significant performance increase compared to the original microstrip antenna such as reduced about 56% reduction in total size, enhanced 207% bandwidth, increased peak gain to 4.66 dB, and improved radiated efficiency to 89.3%. The physical model of the antenna has been fabricated and measured to verify the correctness of the design.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"144 - 154"},"PeriodicalIF":2.7,"publicationDate":"2023-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45603799","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 : 2023-02-16DOI: 10.1080/24751839.2023.2173843
D. Thin, Hung Quoc Ngo, D. Hao, Ngan Luu-Thuy Nguyen
ABSTRACT Aspect-based sentiment analysis (ABSA) has attracted many researchers' attention in recent years. However, the lack of benchmark datasets for specific languages is a common challenge because of the prohibitive cost of manual annotation. The zero-shot cross-lingual strategy can be applied to solve this gap in research. Moreover, previous works mainly focus on improving the performance of supervised ABSA with pre-trained languages. Therefore, there are few to no systematic comparisons of the benefits of multilingual models in zero-shot and joint training cross-lingual for the ABSA task. In this paper, we focus on the zero-shot and joint training cross-lingual transfer task for the ABSA. We fine-tune the latest pre-trained multilingual language models on the source language, and then it is directly predicted in the target language. For the joint learning scenario, the models are trained on the combination of multiple source languages. Our experimental results show that (1) fine-tuning multilingual models achieve promising performances in the zero-shot cross-lingual scenario; (2) fine-tuning models on the combination training data of multiple source languages outperforms monolingual data in the joint training scenario. Furthermore, the experimental results indicated that choosing other languages instead of English as the source language can give promising results in the low-resource languages scenario.
{"title":"Exploring zero-shot and joint training cross-lingual strategies for aspect-based sentiment analysis based on contextualized multilingual language models","authors":"D. Thin, Hung Quoc Ngo, D. Hao, Ngan Luu-Thuy Nguyen","doi":"10.1080/24751839.2023.2173843","DOIUrl":"https://doi.org/10.1080/24751839.2023.2173843","url":null,"abstract":"ABSTRACT Aspect-based sentiment analysis (ABSA) has attracted many researchers' attention in recent years. However, the lack of benchmark datasets for specific languages is a common challenge because of the prohibitive cost of manual annotation. The zero-shot cross-lingual strategy can be applied to solve this gap in research. Moreover, previous works mainly focus on improving the performance of supervised ABSA with pre-trained languages. Therefore, there are few to no systematic comparisons of the benefits of multilingual models in zero-shot and joint training cross-lingual for the ABSA task. In this paper, we focus on the zero-shot and joint training cross-lingual transfer task for the ABSA. We fine-tune the latest pre-trained multilingual language models on the source language, and then it is directly predicted in the target language. For the joint learning scenario, the models are trained on the combination of multiple source languages. Our experimental results show that (1) fine-tuning multilingual models achieve promising performances in the zero-shot cross-lingual scenario; (2) fine-tuning models on the combination training data of multiple source languages outperforms monolingual data in the joint training scenario. Furthermore, the experimental results indicated that choosing other languages instead of English as the source language can give promising results in the low-resource languages scenario.","PeriodicalId":32180,"journal":{"name":"Journal of Information and Telecommunication","volume":"7 1","pages":"121 - 143"},"PeriodicalIF":2.7,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48167729","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：