Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989562
D. Karunakaran, J. S. Berrio, Stewart Worrall, E. Nebot
With the advent of the autonomous vehicle, there is potential to reduce the accident rate to a minimum level. Modern automated vehicles will undoubtedly include machine learning (ML) and probabilistic techniques. These algorithms with a non-deterministic world significantly complicate the safety assessment process. In addition, the autonomous system handles the responsibility of safe navigation, so the vehicle has to ensure its safety by itself. Due to these reasons, it is essential to thoroughly assess the system before deploying it on public roads. However, there are many testing challenges for highly automated vehicles (HAVs) to overcome before the wide-scale deployment. In this paper, we conducted a semi-systematic literature review on several issues and challenges related to the testing of HAVs.
{"title":"Challenges Of Testing Highly Automated Vehicles: A Literature Review","authors":"D. Karunakaran, J. S. Berrio, Stewart Worrall, E. Nebot","doi":"10.1109/RASSE54974.2022.9989562","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989562","url":null,"abstract":"With the advent of the autonomous vehicle, there is potential to reduce the accident rate to a minimum level. Modern automated vehicles will undoubtedly include machine learning (ML) and probabilistic techniques. These algorithms with a non-deterministic world significantly complicate the safety assessment process. In addition, the autonomous system handles the responsibility of safe navigation, so the vehicle has to ensure its safety by itself. Due to these reasons, it is essential to thoroughly assess the system before deploying it on public roads. However, there are many testing challenges for highly automated vehicles (HAVs) to overcome before the wide-scale deployment. In this paper, we conducted a semi-systematic literature review on several issues and challenges related to the testing of HAVs.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126056579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989814
Ta-Chun Lo, Chun-Ying Tao, Jyh-Biau Chang, C. Shieh
The demand for large-volume database storage has become an essential issue with the rising trend of big data. Since the NoSQL database performs better than SQL databases when handling extensive data, many developers choose the NoSQL database as their first choice. Among all the NoSQL databases, HBase has become a popular choice due to its flexibility and high efficiency in the big data processing field. HBase is a column-oriented NoSQL database. It uses HDFS storage and is suitable for integrating with Hadoop ecosystem applications. However, deploying an HBase cluster on bare metal or virtual machines could be pretty complicated and time-consuming. The container technology can make HBase installation more convenient. Nevertheless, containerized HBase can be deployed in different ways. Deploying the HBase cluster in a proper approach can achieve higher performance. In this research, we propose two approaches, namely the Container-dedicated approach and the Container-shared approach, to containerize HBase on Kubernetes. Two benchmark tools are used to compare their performance under different workloads. According to experiment results, the Container-dedicated approach is suitable for writeheavy and read/write balanced applications. The container-shared approach shows a better performance in read-heavy applications. The test result will give future developers a reference when designing a containerized HBase cluster.
{"title":"Performance Comparison of Containerized HBase Clusters on Kubernetes","authors":"Ta-Chun Lo, Chun-Ying Tao, Jyh-Biau Chang, C. Shieh","doi":"10.1109/RASSE54974.2022.9989814","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989814","url":null,"abstract":"The demand for large-volume database storage has become an essential issue with the rising trend of big data. Since the NoSQL database performs better than SQL databases when handling extensive data, many developers choose the NoSQL database as their first choice. Among all the NoSQL databases, HBase has become a popular choice due to its flexibility and high efficiency in the big data processing field. HBase is a column-oriented NoSQL database. It uses HDFS storage and is suitable for integrating with Hadoop ecosystem applications. However, deploying an HBase cluster on bare metal or virtual machines could be pretty complicated and time-consuming. The container technology can make HBase installation more convenient. Nevertheless, containerized HBase can be deployed in different ways. Deploying the HBase cluster in a proper approach can achieve higher performance. In this research, we propose two approaches, namely the Container-dedicated approach and the Container-shared approach, to containerize HBase on Kubernetes. Two benchmark tools are used to compare their performance under different workloads. According to experiment results, the Container-dedicated approach is suitable for writeheavy and read/write balanced applications. The container-shared approach shows a better performance in read-heavy applications. The test result will give future developers a reference when designing a containerized HBase cluster.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129845288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989982
Chi-Kai Chang, Wei-Liang Lin
Gradually, unmanned vehicles are more popular and seen in some places, such as department stores or supermarkets with many people. In order to integrate into human daily life, they should be able to avoid crowd and follow pedestrian flow as human will do. It is not enough to only follow the shortest path for them.The purpose of this work is to implement a navigation algorithm in the real world that considers the flow and density of people. We use a cloud computer to receive fixed camera images, divide regions on the image, and then obtain pedestrian flow and density information through FairMOT[2] algorithm, and wirelessly transmit the information to the unmanned vehicle. Therefore, the unmanned vehicle can avoid high density or reverse flow, and better follow social etiquette.In our implementation, flow directions are with different colors, and shown in our experiments. Furthermore, the flow and density information is passed through WiFi, and affects the cost of a new created cost map layer, called people flow and density layer. The density information affects the navigation reliably. Due to the same area may have different directions of people flow, the following flow algorithm is more challenging.The fixed camera we used is a low-cost webcam, and the unmanned vehicle is with a single camera and a one-line lidar.
{"title":"Realization of Unmanned Vehicle Navigation Considering Density and Pedestrian Flow with Cloud Information","authors":"Chi-Kai Chang, Wei-Liang Lin","doi":"10.1109/RASSE54974.2022.9989982","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989982","url":null,"abstract":"Gradually, unmanned vehicles are more popular and seen in some places, such as department stores or supermarkets with many people. In order to integrate into human daily life, they should be able to avoid crowd and follow pedestrian flow as human will do. It is not enough to only follow the shortest path for them.The purpose of this work is to implement a navigation algorithm in the real world that considers the flow and density of people. We use a cloud computer to receive fixed camera images, divide regions on the image, and then obtain pedestrian flow and density information through FairMOT[2] algorithm, and wirelessly transmit the information to the unmanned vehicle. Therefore, the unmanned vehicle can avoid high density or reverse flow, and better follow social etiquette.In our implementation, flow directions are with different colors, and shown in our experiments. Furthermore, the flow and density information is passed through WiFi, and affects the cost of a new created cost map layer, called people flow and density layer. The density information affects the navigation reliably. Due to the same area may have different directions of people flow, the following flow algorithm is more challenging.The fixed camera we used is a low-cost webcam, and the unmanned vehicle is with a single camera and a one-line lidar.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123902801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989871
Shih-Yang Huang, Chien-Yu Chiou, Yi-Siang Tan, Chih-Yang Chen, P. Chung
About 650,000 new cases of oral cavity cancer occur every year in the world, and cause more than 330,000 deaths. If oral cancer is diagnosed at an early stage, the overall 5-year survival rate is over 70%, while it drops to less than 40% if detected at a late stage. Thus, early detection of oral cancer is important. Visual non-invasive examination is an efficient and feasible approach for performing a preliminary diagnosis of oral cancer. In this paper, we propose a fully convolutional network (FCN) based model to segment cancer and precancer lesion regions in the oral cavity. In addition to the RGB channels of the input image, we append features of Gabor filter and wavelet filter that show strong response at cancer and precancer regions. We also propose a refine stage before the decision layer of FCN to preventing weight dominating problem when reducing high dimension features to small number of classes. In the experiments on oral cancer dataset, the IOU, sensitivity, and specificity of the proposed network achieves 0.586, 0.883, 0.726 respectively. The experimental results show the effectiveness of our method.
{"title":"Deep Oral Cancer Lesion Segmentation with Heterogeneous Features","authors":"Shih-Yang Huang, Chien-Yu Chiou, Yi-Siang Tan, Chih-Yang Chen, P. Chung","doi":"10.1109/RASSE54974.2022.9989871","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989871","url":null,"abstract":"About 650,000 new cases of oral cavity cancer occur every year in the world, and cause more than 330,000 deaths. If oral cancer is diagnosed at an early stage, the overall 5-year survival rate is over 70%, while it drops to less than 40% if detected at a late stage. Thus, early detection of oral cancer is important. Visual non-invasive examination is an efficient and feasible approach for performing a preliminary diagnosis of oral cancer. In this paper, we propose a fully convolutional network (FCN) based model to segment cancer and precancer lesion regions in the oral cavity. In addition to the RGB channels of the input image, we append features of Gabor filter and wavelet filter that show strong response at cancer and precancer regions. We also propose a refine stage before the decision layer of FCN to preventing weight dominating problem when reducing high dimension features to small number of classes. In the experiments on oral cancer dataset, the IOU, sensitivity, and specificity of the proposed network achieves 0.586, 0.883, 0.726 respectively. The experimental results show the effectiveness of our method.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124510148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989605
Xiaoyue Ji, Zhekang Dong, Han Wang, C. S. Lai, Donglian Qi
Mental health problem is an increasingly common social issue leading to diseases such as depression, addiction, and heart attack. Facial expression is one of the most natural and universal signals for human beings to convey their emotional states and behavior intentions. Numerous studies have been conducted on automatic human emotion classification that can effectively establish the relationship between facial expression and mental health, while still suffer from intensive computation and low efficiency. Here, we present a memristive circuit design of Sequencer network for human emotion classification, which offers an environmentally friendly approach with low cost and easily deployable hardware. Specifically, a kind of eco-friendly memristor is fabricated using two-dimensional (2D) materials, and the corresponding testing performance is conducted to make sure its efficiency and stability. Then, the memristor-based Sequencer block, as a core component of Sequencer network, consisting of bidirectional long short-term memory (BiLSTM) circuit and some necessary function circuit modules is proposed. Based on this, the memristive Sequencer network can be achieved. Furthermore, the proposed memristive Sequencer network is applied for human emotion classification. The experimental results demonstrate that the proposed circuit has advantages in computational efficiency and cost, comparable to the main existing software-based methods.
{"title":"Memristive Circuit Design of Sequencer Network for Human Emotion Classification","authors":"Xiaoyue Ji, Zhekang Dong, Han Wang, C. S. Lai, Donglian Qi","doi":"10.1109/RASSE54974.2022.9989605","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989605","url":null,"abstract":"Mental health problem is an increasingly common social issue leading to diseases such as depression, addiction, and heart attack. Facial expression is one of the most natural and universal signals for human beings to convey their emotional states and behavior intentions. Numerous studies have been conducted on automatic human emotion classification that can effectively establish the relationship between facial expression and mental health, while still suffer from intensive computation and low efficiency. Here, we present a memristive circuit design of Sequencer network for human emotion classification, which offers an environmentally friendly approach with low cost and easily deployable hardware. Specifically, a kind of eco-friendly memristor is fabricated using two-dimensional (2D) materials, and the corresponding testing performance is conducted to make sure its efficiency and stability. Then, the memristor-based Sequencer block, as a core component of Sequencer network, consisting of bidirectional long short-term memory (BiLSTM) circuit and some necessary function circuit modules is proposed. Based on this, the memristive Sequencer network can be achieved. Furthermore, the proposed memristive Sequencer network is applied for human emotion classification. The experimental results demonstrate that the proposed circuit has advantages in computational efficiency and cost, comparable to the main existing software-based methods.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130697881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989657
S. M. Massa, Daniele Riboni, K. Nazarpour
Recently, high-density (HD) EMG electrodes have been proposed for improving amputees’ movement/grasping intention recognition, exploiting different machine learning techniques. HD EMG electrodes are composed of a large number of closely spaced channels that simultaneously acquire EMG signals from different parts of the muscle. Given the topological properties of these devices, it is important to fully exploit the spatiotemporal information provided by the electrodes to optimize recognition accuracy. In this work, we introduce the use of Graph Neural Networks (GNNs) to process HD EMG data for movement intention recognition of people with an amputation affecting the upper limbs and which use a robotic prosthesis. In this initial investigation of the approach, we conducted experiments using a real-world dataset consisting of EMG signals collected from 20 volunteers while performing 65 different gestures. We were able to detect 45 gestures with a classification error rate of less than 10%, and obtained an overall classification error rate of 8.75% with a standard deviation of 4.9. To the best of our knowledge, this is the first work in which GNNs are used for processing HD EMG data.
{"title":"Graph Neural Networks for HD EMG-based Movement Intention Recognition: An Initial Investigation","authors":"S. M. Massa, Daniele Riboni, K. Nazarpour","doi":"10.1109/RASSE54974.2022.9989657","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989657","url":null,"abstract":"Recently, high-density (HD) EMG electrodes have been proposed for improving amputees’ movement/grasping intention recognition, exploiting different machine learning techniques. HD EMG electrodes are composed of a large number of closely spaced channels that simultaneously acquire EMG signals from different parts of the muscle. Given the topological properties of these devices, it is important to fully exploit the spatiotemporal information provided by the electrodes to optimize recognition accuracy. In this work, we introduce the use of Graph Neural Networks (GNNs) to process HD EMG data for movement intention recognition of people with an amputation affecting the upper limbs and which use a robotic prosthesis. In this initial investigation of the approach, we conducted experiments using a real-world dataset consisting of EMG signals collected from 20 volunteers while performing 65 different gestures. We were able to detect 45 gestures with a classification error rate of less than 10%, and obtained an overall classification error rate of 8.75% with a standard deviation of 4.9. To the best of our knowledge, this is the first work in which GNNs are used for processing HD EMG data.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116260768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989734
Che-Chih Hsu, Yuan-Hao Huang
In the fifth-generation communication, the hybrid precoding technique is used in the massive multiple-input multiple-output (MIMO) system to reduce the RF chain number for power reduction. In recent years, deep learning techniques have been widely used in the hybrid precoding design to improve spectrum efficiency. This paper proposes an alternating minimization-based deep learning precoding technique for the hybrid precoding. This technique includes the phase information of the channel matrix in the deep learning model to improve the spectral efficiency. In addition, an on-line training method is also designed to track the channel features of the time-varying channel. Thus, the deep-learning neural network model can adaptively track the time-varying channel characteristics with a better performance than its counterpart deep-learning-based hybrid beamforming (DLHB) technique even if the initial network model is not good. The simulation experiments also analyze and compare the spectral efficiency with different hyperparameters of the deep-learning neural network model. The proposed adaptive hybrid precoding technique can further reduce 51.54% of the trainable parameters in the time-invariant environment and 76.14% of trainable parameters can be reduced in the time-varying environment compared to the benchmark technique of the DLHB. With the reduced parameter size, the proposed technique can be 1.6 ms faster than the DLHB with better spectrum efficiency.
{"title":"Deep Learning Based Adaptive Hybrid Beamforming for mmWave MIMO Systems","authors":"Che-Chih Hsu, Yuan-Hao Huang","doi":"10.1109/RASSE54974.2022.9989734","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989734","url":null,"abstract":"In the fifth-generation communication, the hybrid precoding technique is used in the massive multiple-input multiple-output (MIMO) system to reduce the RF chain number for power reduction. In recent years, deep learning techniques have been widely used in the hybrid precoding design to improve spectrum efficiency. This paper proposes an alternating minimization-based deep learning precoding technique for the hybrid precoding. This technique includes the phase information of the channel matrix in the deep learning model to improve the spectral efficiency. In addition, an on-line training method is also designed to track the channel features of the time-varying channel. Thus, the deep-learning neural network model can adaptively track the time-varying channel characteristics with a better performance than its counterpart deep-learning-based hybrid beamforming (DLHB) technique even if the initial network model is not good. The simulation experiments also analyze and compare the spectral efficiency with different hyperparameters of the deep-learning neural network model. The proposed adaptive hybrid precoding technique can further reduce 51.54% of the trainable parameters in the time-invariant environment and 76.14% of trainable parameters can be reduced in the time-varying environment compared to the benchmark technique of the DLHB. With the reduced parameter size, the proposed technique can be 1.6 ms faster than the DLHB with better spectrum efficiency.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129269313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989637
You-Cheng Zhang, Y. Hwang
This paper presents an image feature points assisted scheme to accelerate the process of point cloud matching in Odometry Estimation (OE) equipped with a Lidar camera. To calculate the changes of position and orientation of a camera across successive frames accurately, the corresponding point pairs between two laser point clouds must be identified first, which calls for a time-consuming iterative process. Conventional approaches utilize the laser point cloud data only and do not leverage the information of camera image to expedite the matching process. The proposed scheme analyzes the image first to identify the regions rich of feature points. Compared to flat regions, these regions serve better in point cloud matching. The size of the point could can be largely reduced by pruning out the regions less significant in terms of feature points. This speeds up the process without noticeable compromise of the matching accuracy. We implement the scheme in the odometry estimation module of a Simultaneous Localization and Mapping (SLAM) system and evaluate possible performance enhancement from the proposed scheme. Experimental results show that the enhancement in OE is more significant in a more planar environment. the time saving can be up to 18.9% and the deviation in path trajectory estimation is negligible.
{"title":"An Image Feature Points Assisted Point Cloud Matching Scheme in Odometry Estimation for SLAM Systems","authors":"You-Cheng Zhang, Y. Hwang","doi":"10.1109/RASSE54974.2022.9989637","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989637","url":null,"abstract":"This paper presents an image feature points assisted scheme to accelerate the process of point cloud matching in Odometry Estimation (OE) equipped with a Lidar camera. To calculate the changes of position and orientation of a camera across successive frames accurately, the corresponding point pairs between two laser point clouds must be identified first, which calls for a time-consuming iterative process. Conventional approaches utilize the laser point cloud data only and do not leverage the information of camera image to expedite the matching process. The proposed scheme analyzes the image first to identify the regions rich of feature points. Compared to flat regions, these regions serve better in point cloud matching. The size of the point could can be largely reduced by pruning out the regions less significant in terms of feature points. This speeds up the process without noticeable compromise of the matching accuracy. We implement the scheme in the odometry estimation module of a Simultaneous Localization and Mapping (SLAM) system and evaluate possible performance enhancement from the proposed scheme. Experimental results show that the enhancement in OE is more significant in a more planar environment. the time saving can be up to 18.9% and the deviation in path trajectory estimation is negligible.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122089272","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989941
Zong-Yu He, Wei-Liang Lin
This article uses BERT[1] algorithm to judge Chinese sentiment. The goal is to automatically censor short advertising words on advertising boards or message boards, and filter out some inappropriate speeches. The method is to collect various speeches on the internet, including online shopping reviews, meal reviews, store reviews, etc., as well as emotion dictionaries, and use these data to train the algorithm so that the algorithm can correctly identify the emotions of short sentences.
{"title":"Bert Based Chinese Sentiment Analysis for Automatic Censoring of Dynamic Electronic Scroll","authors":"Zong-Yu He, Wei-Liang Lin","doi":"10.1109/RASSE54974.2022.9989941","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989941","url":null,"abstract":"This article uses BERT[1] algorithm to judge Chinese sentiment. The goal is to automatically censor short advertising words on advertising boards or message boards, and filter out some inappropriate speeches. The method is to collect various speeches on the internet, including online shopping reviews, meal reviews, store reviews, etc., as well as emotion dictionaries, and use these data to train the algorithm so that the algorithm can correctly identify the emotions of short sentences.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116470906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.1109/RASSE54974.2022.9989681
Chen-Yu Wang, Wei-Jong Yang, Chien-Yu Chiou, Meng Chen, Chung Ming Wang, Yu-Jyh Wang, P. Chung
Stereo matching algorithm is used to estimating the depth value correspond with two frames taken from left and right cameras. Due to the movement of the objects, the output of depth map will easily vibrate without confidence. Moreover, surrounding information which cover by other objects may cause significant impacts and problems for the users. Therefore, the stability of depth maps is a crucial point for precisely outcomes. This paper proposes a new notion that considers the motion of objects, the frames in different time, and the relationship between left and right frames to propagate a new depth map. The regions of each objects are estimated using quadtree and contrast context histogram. The experimental results show the proposed method surpass conventional stereo matching methods.
{"title":"Stereo Video Depth Estimation Based on Disparity Map Propagation","authors":"Chen-Yu Wang, Wei-Jong Yang, Chien-Yu Chiou, Meng Chen, Chung Ming Wang, Yu-Jyh Wang, P. Chung","doi":"10.1109/RASSE54974.2022.9989681","DOIUrl":"https://doi.org/10.1109/RASSE54974.2022.9989681","url":null,"abstract":"Stereo matching algorithm is used to estimating the depth value correspond with two frames taken from left and right cameras. Due to the movement of the objects, the output of depth map will easily vibrate without confidence. Moreover, surrounding information which cover by other objects may cause significant impacts and problems for the users. Therefore, the stability of depth maps is a crucial point for precisely outcomes. This paper proposes a new notion that considers the motion of objects, the frames in different time, and the relationship between left and right frames to propagate a new depth map. The regions of each objects are estimated using quadtree and contrast context histogram. The experimental results show the proposed method surpass conventional stereo matching methods.","PeriodicalId":382440,"journal":{"name":"2022 IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127793348","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：