Pub Date : 2021-12-21DOI: 10.1109/NICS54270.2021.9701494
Lien-dai Nguyen, Trang N. M. Cao, Lam Huynh-Anh, Hanh Dang-Ngoc
In this paper, an efficient embedded machine learning system is proposed to automatically detect face masks and measure human temperature in a real-time application. In particular, our system uses a Raspberry-Pi camera to collect realtime video and detect face masks by implementing a classification model on Raspberry Pi 3 in public places. The face mask detector is built based on MobileNetV2, with ImageNet pre-trained weights, to detect three cases of correctly wearing, incorrectly wearing and not wearing a mask. We also design a human temperature measurement framework by deploying a temperature sensor on the Raspberry Pi 3. The numerical results prove the practicality and effectiveness of our embedded systems compared to some state-of-the-art researches. The results of accuracy rate in detecting three cases of wearing a face mask are 98.61% based on the training results and 97.63% for validation results. Meanwhile, our proposed system needs a short time of 6 seconds for each person to be tested through the whole process of face mask detection and human forehead temperature measurement.
{"title":"An Embedded Machine Learning System For Real-time Face Mask Detection And Human Temperature Measurement","authors":"Lien-dai Nguyen, Trang N. M. Cao, Lam Huynh-Anh, Hanh Dang-Ngoc","doi":"10.1109/NICS54270.2021.9701494","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701494","url":null,"abstract":"In this paper, an efficient embedded machine learning system is proposed to automatically detect face masks and measure human temperature in a real-time application. In particular, our system uses a Raspberry-Pi camera to collect realtime video and detect face masks by implementing a classification model on Raspberry Pi 3 in public places. The face mask detector is built based on MobileNetV2, with ImageNet pre-trained weights, to detect three cases of correctly wearing, incorrectly wearing and not wearing a mask. We also design a human temperature measurement framework by deploying a temperature sensor on the Raspberry Pi 3. The numerical results prove the practicality and effectiveness of our embedded systems compared to some state-of-the-art researches. The results of accuracy rate in detecting three cases of wearing a face mask are 98.61% based on the training results and 97.63% for validation results. Meanwhile, our proposed system needs a short time of 6 seconds for each person to be tested through the whole process of face mask detection and human forehead temperature measurement.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127193006","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701499
M. Nguyen, Van-Su Tran, B. D. Nguyen
A simple and low-profile reconfigurable unit-cell design for Ka band reconfigurable reflectarray antennas is presented in this paper. The unit-cell is based on a single substrate and a ground plane that allows a simple fabrication process. One p-i-n diode is used to control the reflection phase shift with a step of 180°. The optimization of the unit-cell structure is carried out with full wave simulation software. Radiation characteristics of a 10x10-element reflectarray is also validated in Ka-frequency band. Simulation results show that the unit cell exhibits a good 1-bit phase control within a wide bandwidth and the array achieves an excellent beam-steering capability with low loss and wide scan angle.
{"title":"Ka-band Reflectarray Unit-cell with 1-bit Digital Phase Resolution","authors":"M. Nguyen, Van-Su Tran, B. D. Nguyen","doi":"10.1109/NICS54270.2021.9701499","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701499","url":null,"abstract":"A simple and low-profile reconfigurable unit-cell design for Ka band reconfigurable reflectarray antennas is presented in this paper. The unit-cell is based on a single substrate and a ground plane that allows a simple fabrication process. One p-i-n diode is used to control the reflection phase shift with a step of 180°. The optimization of the unit-cell structure is carried out with full wave simulation software. Radiation characteristics of a 10x10-element reflectarray is also validated in Ka-frequency band. Simulation results show that the unit cell exhibits a good 1-bit phase control within a wide bandwidth and the array achieves an excellent beam-steering capability with low loss and wide scan angle.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"60 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123305477","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701518
Tri Cong-Toan Tran, Thien Phu Nguyen, Thanh Le
Based Sentiment Analysis (ABSA), which aims to identify sentiment polarity towards specific aspects in customers’ comments or reviews, has been an attractive topic of research in social listening. In this paper, we construct a specialized model utilizing PhoBert’s top-level hidden layers integrated into a hierarchical classifier, taking advantage of these components to propose an effective classification method for ABSA task. We evaluated our model’s performance on two public datasets in Vietnamese and the results show that our implementation outperforms previous models on both datasets.
{"title":"HSUM-HC: Integrating Bert-based hidden aggregation to hierarchical classifier for Vietnamese aspect-based sentiment analysis","authors":"Tri Cong-Toan Tran, Thien Phu Nguyen, Thanh Le","doi":"10.1109/NICS54270.2021.9701518","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701518","url":null,"abstract":"Based Sentiment Analysis (ABSA), which aims to identify sentiment polarity towards specific aspects in customers’ comments or reviews, has been an attractive topic of research in social listening. In this paper, we construct a specialized model utilizing PhoBert’s top-level hidden layers integrated into a hierarchical classifier, taking advantage of these components to propose an effective classification method for ABSA task. We evaluated our model’s performance on two public datasets in Vietnamese and the results show that our implementation outperforms previous models on both datasets.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116162170","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701569
Dinh Thang Hoang, Trung Kien Thai, Thanh Nguyen Chi, Long Quoc Trany
Trackers based on Siamese have demonstrated more remarkable performance in visual tracking. The majority of existing trackers typically compute target template and search image features independently, then utilize cross-correlation to predict the possibility of an object appearing at each spatial position in the search image for target localization. This paper proposes a Siamese network for feature enhancement and aggregation between the target template and the search image by utilizing a lightweight transformer with several linear self- and cross-attention layers. With anchor-free head prediction, the suggested framework is simple and effective. Extensive experiments on visual tracking benchmarks such as VOT2018, UAV123, and OTB100 demonstrates that our tracker achieves state-of-the-art performance and operates at a real-time frame rate of 39 fps.
{"title":"Real-Time Siamese Visual Tracking with Lightweight Transformer","authors":"Dinh Thang Hoang, Trung Kien Thai, Thanh Nguyen Chi, Long Quoc Trany","doi":"10.1109/NICS54270.2021.9701569","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701569","url":null,"abstract":"Trackers based on Siamese have demonstrated more remarkable performance in visual tracking. The majority of existing trackers typically compute target template and search image features independently, then utilize cross-correlation to predict the possibility of an object appearing at each spatial position in the search image for target localization. This paper proposes a Siamese network for feature enhancement and aggregation between the target template and the search image by utilizing a lightweight transformer with several linear self- and cross-attention layers. With anchor-free head prediction, the suggested framework is simple and effective. Extensive experiments on visual tracking benchmarks such as VOT2018, UAV123, and OTB100 demonstrates that our tracker achieves state-of-the-art performance and operates at a real-time frame rate of 39 fps.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122376839","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701572
Tuan Phong Tran, Van Cuong Nguyen, Ly Vu, Quang Uy Nguyen
Intrusion detection systems (IDSs) play a critical role in many computer networks to combat attacks from external environments. However, due to the rapid spread of various new attacks, developing a robust IDS that can effectively detect novel attacks and prevent them from devastating network systems is a challenging task. Recently, deep neural networks (DNNs) have been widely used to enhance the accuracy of IDSs in detecting network intrusions. Nevertheless, the performance of DNN highly depends on the representation of the input data. In this paper, we introduce a novel method called DeepInsight-Convolutional Neural Network-Intrusion Detection System (DC-IDS). In CD-IDS, the DeepInsight technique is used to transform the network traffic data into a new representation in the form of an image. This new representation of the traffic data is then used as the input of a Convolutional Neural Network (CNN). We evaluate our proposed technique using an extensive experiment on five IDS datasets. The experimental results show that the proposed model enhances the performance of IDSs in detecting various network attacks compared to different popular machine learning algorithms.
{"title":"DeepInsight-Convolutional Neural Network for Intrusion Detection Systems","authors":"Tuan Phong Tran, Van Cuong Nguyen, Ly Vu, Quang Uy Nguyen","doi":"10.1109/NICS54270.2021.9701572","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701572","url":null,"abstract":"Intrusion detection systems (IDSs) play a critical role in many computer networks to combat attacks from external environments. However, due to the rapid spread of various new attacks, developing a robust IDS that can effectively detect novel attacks and prevent them from devastating network systems is a challenging task. Recently, deep neural networks (DNNs) have been widely used to enhance the accuracy of IDSs in detecting network intrusions. Nevertheless, the performance of DNN highly depends on the representation of the input data. In this paper, we introduce a novel method called DeepInsight-Convolutional Neural Network-Intrusion Detection System (DC-IDS). In CD-IDS, the DeepInsight technique is used to transform the network traffic data into a new representation in the form of an image. This new representation of the traffic data is then used as the input of a Convolutional Neural Network (CNN). We evaluate our proposed technique using an extensive experiment on five IDS datasets. The experimental results show that the proposed model enhances the performance of IDSs in detecting various network attacks compared to different popular machine learning algorithms.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126669144","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701495
An Hung Nguyen, P. Nguyen
Change detection in multiple-temporal Synthetic Aperture Radar images has been received great interests for recent decades. The basic principle of change detection is to analyse the difference images generated from two Synthetic Aperture Radar images captured in the same geographic area at two different times. The popular operators used to create difference images are traditional subtraction, ratio, logarithm based ones and modified versions of them, which can use pixel information in the local or global areas. A challenge in detecting changes is to reduce impacts of speckle noises inherently existing in Synthetic Aperture Radar images on the accuracy of the detection. This paper proposed a novel algorithm to create the difference images based on averaging heterogeneous factors of corresponding neighbourhood areas in the two images. The resultant difference image is then filtered by the average filter to reject remaining speckle noises.
{"title":"Change detection in multiple-temporal Synthetic Aperture Radar images based on averaged heterogeneous factors of neighbourhood areas","authors":"An Hung Nguyen, P. Nguyen","doi":"10.1109/NICS54270.2021.9701495","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701495","url":null,"abstract":"Change detection in multiple-temporal Synthetic Aperture Radar images has been received great interests for recent decades. The basic principle of change detection is to analyse the difference images generated from two Synthetic Aperture Radar images captured in the same geographic area at two different times. The popular operators used to create difference images are traditional subtraction, ratio, logarithm based ones and modified versions of them, which can use pixel information in the local or global areas. A challenge in detecting changes is to reduce impacts of speckle noises inherently existing in Synthetic Aperture Radar images on the accuracy of the detection. This paper proposed a novel algorithm to create the difference images based on averaging heterogeneous factors of corresponding neighbourhood areas in the two images. The resultant difference image is then filtered by the average filter to reject remaining speckle noises.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126787939","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701577
Phuoc-Cuong Nguyen, Quoc-Trung Nguyen, Kim-Hung Le
In recent years, we have witnessed the significant growth of the Internet along with emerging security threats. A machine learning-based Intrusion Detection System (IDS) is widely employed to detect cyber attacks by continuously monitoring network traffic. However, the diversity of network features considerably affected the accuracy and training time of the IDS model. In this paper, a lightweight and effective feature selection algorithm for IDS is proposed. This algorithm combines the advantages of both Random Forest and AdaBoost algorithms. The evaluation results on popular datasets (NSL- KDD, UNSW-NB15, and CICIDS-2017) show that our proposal outperforms existing feature selection algorithms regarding the detection accuracy and the number of selected features.
{"title":"An Ensemble Feature Selection Algorithm for Machine Learning based Intrusion Detection System","authors":"Phuoc-Cuong Nguyen, Quoc-Trung Nguyen, Kim-Hung Le","doi":"10.1109/NICS54270.2021.9701577","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701577","url":null,"abstract":"In recent years, we have witnessed the significant growth of the Internet along with emerging security threats. A machine learning-based Intrusion Detection System (IDS) is widely employed to detect cyber attacks by continuously monitoring network traffic. However, the diversity of network features considerably affected the accuracy and training time of the IDS model. In this paper, a lightweight and effective feature selection algorithm for IDS is proposed. This algorithm combines the advantages of both Random Forest and AdaBoost algorithms. The evaluation results on popular datasets (NSL- KDD, UNSW-NB15, and CICIDS-2017) show that our proposal outperforms existing feature selection algorithms regarding the detection accuracy and the number of selected features.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124118183","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 this paper, we propose a design diagram of a low noise amplifier using NP2500MS transistor 0.25 pm AlGaN/ GaN HEMT technology of WIN Semiconductor, Taiwan, consisting of 2 stages at center frequency 25.8 GHz, this is the frequency band used for the 5th Generation Mobile Communications and some other K/Ka-band applications. With this transistor, the LNA has achieved a noise Figure less than 1.65 dB and the average Gain is 13 dB in the whole bandwidth.
本文提出了一种采用台湾WIN半导体公司的NP2500MS晶体管0.25 pm AlGaN/ GaN HEMT技术的低噪声放大器的设计方案，该放大器的中心频率为25.8 GHz，这是第五代移动通信和其他一些K/ ka波段应用所使用的频段。使用该晶体管，LNA在整个带宽内的噪声系数小于1.65 dB，平均增益为13 dB。
{"title":"Design of a Ka-band MMIC Low Noise Amplifier for 5G applications","authors":"Ngoc Nguyen Xuan, Hoang Nguyen Huy, Manh Luong Duy","doi":"10.1109/NICS54270.2021.9701480","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701480","url":null,"abstract":"In this paper, we propose a design diagram of a low noise amplifier using NP2500MS transistor 0.25 pm AlGaN/ GaN HEMT technology of WIN Semiconductor, Taiwan, consisting of 2 stages at center frequency 25.8 GHz, this is the frequency band used for the 5th Generation Mobile Communications and some other K/Ka-band applications. With this transistor, the LNA has achieved a noise Figure less than 1.65 dB and the average Gain is 13 dB in the whole bandwidth.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127968743","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701565
Minh-Canh Huynh, Cheng-Yuan Chang
This paper proposes a novel adaptive neural network controller which can operate effectively in both linear and nonlinear narrowband active noise control systems. The advantage of the proposed method is a simple structure with three network layers, which its adaptive coefficients are updated online. Algorithm analysis of the proposed method is presented in this paper. The improved performance is verified by computer simulations through comparison with the traditional method.
{"title":"A novel adaptive neural controller for narrowband active noise control systems","authors":"Minh-Canh Huynh, Cheng-Yuan Chang","doi":"10.1109/NICS54270.2021.9701565","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701565","url":null,"abstract":"This paper proposes a novel adaptive neural network controller which can operate effectively in both linear and nonlinear narrowband active noise control systems. The advantage of the proposed method is a simple structure with three network layers, which its adaptive coefficients are updated online. Algorithm analysis of the proposed method is presented in this paper. The improved performance is verified by computer simulations through comparison with the traditional method.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"1 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113959868","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 : 2021-12-21DOI: 10.1109/NICS54270.2021.9701564
Y. Takahashi, A. Ito
Recently, we introduced a new automata model, so-called colored finite automata (CFAs) whose accepting states are multi-colored (i.e., not conventional black-and-white acceptance) in order to classify their input strings into two or more languages, and solved the specific complexity problems concerning color-unmixedness of nondeterministic CFA. More precisely, so-called UV, UP, and UE problems were shown to be NLOG-complete, P, and NP-complete, respectively. In this paper, we apply the concept of colored accepting mechanism to pushdown automata and show that the corresponding versions of the above mentioned complexity problems are all undecidable.
{"title":"On the Unmixedness Problems of Colored Pushdown Automata","authors":"Y. Takahashi, A. Ito","doi":"10.1109/NICS54270.2021.9701564","DOIUrl":"https://doi.org/10.1109/NICS54270.2021.9701564","url":null,"abstract":"Recently, we introduced a new automata model, so-called colored finite automata (CFAs) whose accepting states are multi-colored (i.e., not conventional black-and-white acceptance) in order to classify their input strings into two or more languages, and solved the specific complexity problems concerning color-unmixedness of nondeterministic CFA. More precisely, so-called UV, UP, and UE problems were shown to be NLOG-complete, P, and NP-complete, respectively. In this paper, we apply the concept of colored accepting mechanism to pushdown automata and show that the corresponding versions of the above mentioned complexity problems are all undecidable.","PeriodicalId":296963,"journal":{"name":"2021 8th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131668755","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：