Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00059
Ge Hangli, Lifeng Lin, Renhe Jiang, Takashi Michikata, N. Koshizuka
In this study, a method of multi-weighted graphs learning for passenger count prediction in railway networks, is presented. Traffic prediction can provide significant insights for railway system optimization, urban planning, smart city development, etc. However, affected by various factors, including spatial, temporal, and other external ones, traffic prediction on railway networks remains a critical task because of the complexity of the railway networks. To achieve high learning performance of the models and discover the correlation between the models and features, we proposed various heterogenerous weighted graphs for the passenger count prediction. Six types of weight graphs, that is, connection graph, distance graph, correlation graph, and their fused weight graphs were proposed to fully construct the spatial and geometrical features within the entire railway network. Two representative types of graph neural networks, that is, the graph convolutional network (GCN) and graph attention network (GAT) were implemented for evaluation. The evaluation results demonstrate that the proposed GAT model learning on the correlation graph achieves the best performance, as it can reduce the metrics of mean absolute error (MAE), root mean square error (RSME), and mean absolute percentage error metrics (MAPE) on average by 19.7%, 6.9%, 27.9% respectively. Finally, the importance and effectiveness of the models with corresponding weight graphs were also investigated and explained. It also provides the interpretability of the traffic prediction tasks on the railway network.
{"title":"Multi-weighted Graphs Learning for Passenger Count Prediction on Railway Network","authors":"Ge Hangli, Lifeng Lin, Renhe Jiang, Takashi Michikata, N. Koshizuka","doi":"10.1109/COMPSAC54236.2022.00059","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00059","url":null,"abstract":"In this study, a method of multi-weighted graphs learning for passenger count prediction in railway networks, is presented. Traffic prediction can provide significant insights for railway system optimization, urban planning, smart city development, etc. However, affected by various factors, including spatial, temporal, and other external ones, traffic prediction on railway networks remains a critical task because of the complexity of the railway networks. To achieve high learning performance of the models and discover the correlation between the models and features, we proposed various heterogenerous weighted graphs for the passenger count prediction. Six types of weight graphs, that is, connection graph, distance graph, correlation graph, and their fused weight graphs were proposed to fully construct the spatial and geometrical features within the entire railway network. Two representative types of graph neural networks, that is, the graph convolutional network (GCN) and graph attention network (GAT) were implemented for evaluation. The evaluation results demonstrate that the proposed GAT model learning on the correlation graph achieves the best performance, as it can reduce the metrics of mean absolute error (MAE), root mean square error (RSME), and mean absolute percentage error metrics (MAPE) on average by 19.7%, 6.9%, 27.9% respectively. Finally, the importance and effectiveness of the models with corresponding weight graphs were also investigated and explained. It also provides the interpretability of the traffic prediction tasks on the railway network.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133825034","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00233
Amina Jandoubi, M. Bennani, A. E. Fazziki
Nowadays, the Internet of Things touches all areas of our daily life, such as industry, economy, energy and agriculture. If we extend these domains to solutions related to smart homes and cars, we will count more than 50 billion connected devices in 2020. These applications transmit a high amount of data on the internet through IoT communication protocols. In some cases, the security aspect is required as the exchanged data can be sensitive. Therefore, it is necessary to develop a means to assess the confidence we can assign to such transmission protocols. In this context, the fault injection characterization mechanism speeds up the fault introduction into a transmission protocol to observe its reaction and to assess its resilience to application conditions with risks of errors occurring. This paper presents a systematic approach to identifying the moment of fault injection in the messaging protocol Message Queuing Telemetry Transport (MQTT). MQTT protocol handles exchanged messages across a distributed system where the injection instant cannot be defined through a time value as the synchronization of the distributed components is not guaranteed. New algorithms are introduced: (1) extract the send/receive messages' pairs, (2) timestamp the communication events using the vector clock, (3) filter the sending events and (4) generate alternate sent messages sequences. Events models for the publisher/broker provided services are generated. These services are: connect, disconnect and publish, obeying some required properties for services' quality.
{"title":"Faultload time model of the MQTT protocol publish service","authors":"Amina Jandoubi, M. Bennani, A. E. Fazziki","doi":"10.1109/COMPSAC54236.2022.00233","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00233","url":null,"abstract":"Nowadays, the Internet of Things touches all areas of our daily life, such as industry, economy, energy and agriculture. If we extend these domains to solutions related to smart homes and cars, we will count more than 50 billion connected devices in 2020. These applications transmit a high amount of data on the internet through IoT communication protocols. In some cases, the security aspect is required as the exchanged data can be sensitive. Therefore, it is necessary to develop a means to assess the confidence we can assign to such transmission protocols. In this context, the fault injection characterization mechanism speeds up the fault introduction into a transmission protocol to observe its reaction and to assess its resilience to application conditions with risks of errors occurring. This paper presents a systematic approach to identifying the moment of fault injection in the messaging protocol Message Queuing Telemetry Transport (MQTT). MQTT protocol handles exchanged messages across a distributed system where the injection instant cannot be defined through a time value as the synchronization of the distributed components is not guaranteed. New algorithms are introduced: (1) extract the send/receive messages' pairs, (2) timestamp the communication events using the vector clock, (3) filter the sending events and (4) generate alternate sent messages sequences. Events models for the publisher/broker provided services are generated. These services are: connect, disconnect and publish, obeying some required properties for services' quality.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132810592","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00159
Florian Hofer, Clemens Kuen
The growing popularity of cloud computing and the Internet of Things for private use increased the availability of off-the-shelf device solutions. This shift is particularly the case for widely distributed networks that allow community use like LoRa Wan. However, it is still unclear how mature these products are for use beyond hobbyist needs. Therefore, this paper examines selected off-the-shelf devices and gateways and explores their suitability through experimentation in a LoRaWAN community-enabled infrastructure. In addition, we extend lacking function-ality and report shortcomings and bug fixes.
{"title":"Off-the-shelf LoRaWAN: Experimenting on the prospect of a low-cost rapid prototyping solution","authors":"Florian Hofer, Clemens Kuen","doi":"10.1109/COMPSAC54236.2022.00159","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00159","url":null,"abstract":"The growing popularity of cloud computing and the Internet of Things for private use increased the availability of off-the-shelf device solutions. This shift is particularly the case for widely distributed networks that allow community use like LoRa Wan. However, it is still unclear how mature these products are for use beyond hobbyist needs. Therefore, this paper examines selected off-the-shelf devices and gateways and explores their suitability through experimentation in a LoRaWAN community-enabled infrastructure. In addition, we extend lacking function-ality and report shortcomings and bug fixes.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122423402","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00154
Wei Liu, Jiarui Zhang, Yijun Zhao
Deep learning has attracted a great amount of interest in recent years and has become a rapidly emerging field in artificial intelligence. In medical image analysis, deep learning methods have produced promising results comparable to and, in some cases, superior to human experts. Nevertheless, researchers have also noted the limitations and challenges of the deep learning approaches, especially in model selection and interpretability. This paper compares the efficacy of deep learning and traditional machine learning techniques in detecting cognitive impairment (CI) associated with Alzheimer's disease (AD) using brain MRI scans. We base our study on 894 brain MRI scans provided by the open access OASIS platform. In particular, we explore two deep learning approaches: 1) a 3D convolutional neural network (3D-CNN) and 2) a hybrid model with a CNN plus LSTM (CNN-LSTM) architecture. We further examine the performance of five traditional machine learning algorithms based on features extracted from the MRI images using the FreeSurfer software. Our experimental results demonstrate that the deep learning models achieve higher Precision and Recall, while the traditional machine learning methods deliver more stability and better performance in Specificity and overall accuracy. Our findings could serve as a case study to highlight the challenges in adopting deep learning-based approaches.
{"title":"A Comparison of Deep Learning and Traditional Machine Learning Approaches in Detecting Cognitive Impairment Using MRI Scans","authors":"Wei Liu, Jiarui Zhang, Yijun Zhao","doi":"10.1109/COMPSAC54236.2022.00154","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00154","url":null,"abstract":"Deep learning has attracted a great amount of interest in recent years and has become a rapidly emerging field in artificial intelligence. In medical image analysis, deep learning methods have produced promising results comparable to and, in some cases, superior to human experts. Nevertheless, researchers have also noted the limitations and challenges of the deep learning approaches, especially in model selection and interpretability. This paper compares the efficacy of deep learning and traditional machine learning techniques in detecting cognitive impairment (CI) associated with Alzheimer's disease (AD) using brain MRI scans. We base our study on 894 brain MRI scans provided by the open access OASIS platform. In particular, we explore two deep learning approaches: 1) a 3D convolutional neural network (3D-CNN) and 2) a hybrid model with a CNN plus LSTM (CNN-LSTM) architecture. We further examine the performance of five traditional machine learning algorithms based on features extracted from the MRI images using the FreeSurfer software. Our experimental results demonstrate that the deep learning models achieve higher Precision and Recall, while the traditional machine learning methods deliver more stability and better performance in Specificity and overall accuracy. Our findings could serve as a case study to highlight the challenges in adopting deep learning-based approaches.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117215111","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00016
Carlo Vitucci, Daniel Sundmark, Marcus Jägemar, Jakob Danielsson, Alf Larsson, Thomas Nolte
Fault management is an important function that impacts the design of any digital system, from the simple kiosk in a shop to a complex 6G network. It is common to classify fault conditions into different taxonomies using terms like fault or error. Fault taxonomies are often suitable for managing fault detection, fault reporting, and fault localization but often neglect to support all different functions required by a fault management process. A correctly implemented fault management process must be able to distinguish between defects and faults, decide upon ap-propriate actions to recover the system to an ideal state, and avoid an error condition. Fault management is a multi-disciplinary process where recovery actions are deployed promptly by com-bined hardware, firmware, and software orchestration. The importance of fault management processes significantly increases with modern nanometer technologies, which suffer the risk of so-called soft errors, a corruption of a bit cells that can happen due to spurious disturbance, like cosmic radiation. Modern fault management implementations must support recovery actions for soft errors to ensure a steady system. This paper describes an extended fault classification model that emphasizes fault management and recovery actions. We aim to show how the reliability-based fault taxonomy definition is more suitable for the overall fault management process.
{"title":"A Reliability-oriented Faults Taxonomy and a Recovery-oriented Methodological Approach for Systems Resilience","authors":"Carlo Vitucci, Daniel Sundmark, Marcus Jägemar, Jakob Danielsson, Alf Larsson, Thomas Nolte","doi":"10.1109/COMPSAC54236.2022.00016","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00016","url":null,"abstract":"Fault management is an important function that impacts the design of any digital system, from the simple kiosk in a shop to a complex 6G network. It is common to classify fault conditions into different taxonomies using terms like fault or error. Fault taxonomies are often suitable for managing fault detection, fault reporting, and fault localization but often neglect to support all different functions required by a fault management process. A correctly implemented fault management process must be able to distinguish between defects and faults, decide upon ap-propriate actions to recover the system to an ideal state, and avoid an error condition. Fault management is a multi-disciplinary process where recovery actions are deployed promptly by com-bined hardware, firmware, and software orchestration. The importance of fault management processes significantly increases with modern nanometer technologies, which suffer the risk of so-called soft errors, a corruption of a bit cells that can happen due to spurious disturbance, like cosmic radiation. Modern fault management implementations must support recovery actions for soft errors to ensure a steady system. This paper describes an extended fault classification model that emphasizes fault management and recovery actions. We aim to show how the reliability-based fault taxonomy definition is more suitable for the overall fault management process.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117251144","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00132
Yan Huang, Xian Xu
Software defect prediction is an active topic in the field of software engineering. Cross-project defect prediction (CPDP) adopts the defect data set of the source project to predict the defects of the target project. However, the metrics of the source project and those of the target project are often different, and the traditional CPDP has certain limitations at this time. To address the inconsistency of source and target metrics, researchers propose heterogeneous cross-project defect prediction (HCPDP). To improve the performance of the HCPDP, we propose new Two-stage Cost-sensitive Local Models (TCLM). TCLM aims to improve on the problem of feature selection, linear inseparability of heterogeneous data, class imbalance and data adoption problems in HCPDP. Firstly, in the feature selection stage, we add cost information to improve the feature selection algorithm. Then, KCCA (Kernel Canonical Correlation Analysis) is used to project and map the heterogeneous data into a common feature space so as to mitigate the problem of inconsistent feature sets of the source and the target projects. Secondly, in the model training stage, we adopt local models to improve the performance, and introduce cost information to deal with the class imbalance problem. To verify the effectiveness of the TCLM method, we conduct large-scale empirical study on 24 projects in the AEEEM, PROMISE, NASA, and Relink datasets. Experimental results show that TCLM indeed outperforms the previous work. Therefore, we recommend using the TCLM method to build an HCPDP model.
{"title":"Two-stage cost-sensitive local models for heterogeneous cross-project defect prediction","authors":"Yan Huang, Xian Xu","doi":"10.1109/COMPSAC54236.2022.00132","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00132","url":null,"abstract":"Software defect prediction is an active topic in the field of software engineering. Cross-project defect prediction (CPDP) adopts the defect data set of the source project to predict the defects of the target project. However, the metrics of the source project and those of the target project are often different, and the traditional CPDP has certain limitations at this time. To address the inconsistency of source and target metrics, researchers propose heterogeneous cross-project defect prediction (HCPDP). To improve the performance of the HCPDP, we propose new Two-stage Cost-sensitive Local Models (TCLM). TCLM aims to improve on the problem of feature selection, linear inseparability of heterogeneous data, class imbalance and data adoption problems in HCPDP. Firstly, in the feature selection stage, we add cost information to improve the feature selection algorithm. Then, KCCA (Kernel Canonical Correlation Analysis) is used to project and map the heterogeneous data into a common feature space so as to mitigate the problem of inconsistent feature sets of the source and the target projects. Secondly, in the model training stage, we adopt local models to improve the performance, and introduce cost information to deal with the class imbalance problem. To verify the effectiveness of the TCLM method, we conduct large-scale empirical study on 24 projects in the AEEEM, PROMISE, NASA, and Relink datasets. Experimental results show that TCLM indeed outperforms the previous work. Therefore, we recommend using the TCLM method to build an HCPDP model.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117293783","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00048
Etienne Gael Tajeuna, M. Bouguessa, Shengrui Wang
We present a novel approach for studying evolving customer electricity load profiles. Based on the daily changes that may happen in a power grid, we devise a network-based method to identify and track the evolution of electricity consumption patterns over days. The tracking of these evolving patterns enables us to: (a) use Cox regression and LSTM recurrent neural network for modeling the lifetime of electricity consumption profiles and (b) trace the trajectories of customer electricity consumption behaviors to perform load forecasting.
{"title":"A Longitudinal Study of Customer Electricity Load Profiles","authors":"Etienne Gael Tajeuna, M. Bouguessa, Shengrui Wang","doi":"10.1109/COMPSAC54236.2022.00048","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00048","url":null,"abstract":"We present a novel approach for studying evolving customer electricity load profiles. Based on the daily changes that may happen in a power grid, we devise a network-based method to identify and track the evolution of electricity consumption patterns over days. The tracking of these evolving patterns enables us to: (a) use Cox regression and LSTM recurrent neural network for modeling the lifetime of electricity consumption profiles and (b) trace the trajectories of customer electricity consumption behaviors to perform load forecasting.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116223140","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00238
M. Menard, Tommy Nelson, Milan Shahi, Hugh Morton, Adam DeTavernier, Harvey P. Siy, Rui Zhao, Myoungkyu Song
Secure library reuse is critical for modern ap-plications to protect private information in software security engineering. Teaching secure programming is also more critical to tackle the challenges of new and evolving threats. However, novice students often make mistakes by API misuses due to a lack of understanding of secure libraries or a false sense of security. In this paper, we study the feasibility of applying code clone detection (CCD) for finding relevant examples to effectively teach secure programming to computer science students. CCD is an emerging new technology that extracts syntactically or semantically similar code fragments to support many software engineering tasks, such as program understanding, code quality analysis, software evolution analysis, and bug detection. We have developed a prototype implementation ExTUTOR that allows students to search for relevant examples as feedback when they want to fix their programming issues or vulnerabilities. In our evaluation, we applied ExTUTOR to open source subject applications in the security domain. Our approach should help novice students gain benefits from feedback and identify how to effectively make use of APIs, encouraging students to fix their own security violations in their own applications.
{"title":"A Feasibility Study of Using Code Clone Detection for Secure Programming Education","authors":"M. Menard, Tommy Nelson, Milan Shahi, Hugh Morton, Adam DeTavernier, Harvey P. Siy, Rui Zhao, Myoungkyu Song","doi":"10.1109/COMPSAC54236.2022.00238","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00238","url":null,"abstract":"Secure library reuse is critical for modern ap-plications to protect private information in software security engineering. Teaching secure programming is also more critical to tackle the challenges of new and evolving threats. However, novice students often make mistakes by API misuses due to a lack of understanding of secure libraries or a false sense of security. In this paper, we study the feasibility of applying code clone detection (CCD) for finding relevant examples to effectively teach secure programming to computer science students. CCD is an emerging new technology that extracts syntactically or semantically similar code fragments to support many software engineering tasks, such as program understanding, code quality analysis, software evolution analysis, and bug detection. We have developed a prototype implementation ExTUTOR that allows students to search for relevant examples as feedback when they want to fix their programming issues or vulnerabilities. In our evaluation, we applied ExTUTOR to open source subject applications in the security domain. Our approach should help novice students gain benefits from feedback and identify how to effectively make use of APIs, encouraging students to fix their own security violations in their own applications.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114834893","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00221
Zhipeng Cui, Qinyan Zhang, Jing-Wei Zhang, Xue Sun, Qing Wang, Yi Lei, Lin Zang, Li Zhao, Jijiang Yang
Gastroscopy is an important step in the diagnosis of early gastric cancer. However, because the morphological manifestations of early gastric cancer are not obvious, endoscopists need long-term specialized training and experience accumulation to correctly identify early cancer through magnification gastroscopy. In this paper, the data set of gastroscopy image is collected and enhanced, and target detection method is combined with gastroscopy image. The Mask R-CNN+BiFPN model was proposed to enhance the feature fusion and improve the detection effect of early gastric cancer lesions. Compared with Mask R-CNN, the improved Mask R-CNN model has better performance, with the sensitivity and specificity of 91.67% and 88.95% in accurately labeled gastroscopic datasets, respectively, showing a good segmentation effect for surface swelling lesions.
{"title":"Application of Improved Mask R-CNN Algorithm Based on Gastroscopic Image in Detection of Early Gastric Cancer","authors":"Zhipeng Cui, Qinyan Zhang, Jing-Wei Zhang, Xue Sun, Qing Wang, Yi Lei, Lin Zang, Li Zhao, Jijiang Yang","doi":"10.1109/COMPSAC54236.2022.00221","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00221","url":null,"abstract":"Gastroscopy is an important step in the diagnosis of early gastric cancer. However, because the morphological manifestations of early gastric cancer are not obvious, endoscopists need long-term specialized training and experience accumulation to correctly identify early cancer through magnification gastroscopy. In this paper, the data set of gastroscopy image is collected and enhanced, and target detection method is combined with gastroscopy image. The Mask R-CNN+BiFPN model was proposed to enhance the feature fusion and improve the detection effect of early gastric cancer lesions. Compared with Mask R-CNN, the improved Mask R-CNN model has better performance, with the sensitivity and specificity of 91.67% and 88.95% in accurately labeled gastroscopic datasets, respectively, showing a good segmentation effect for surface swelling lesions.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114847543","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 : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00088
Jamalia Sultana, Mahmuda Naznin
Voice based interactive system has numerous ap-plications including patient care system, robotics, interactive learning tool etc. Speech Emotion Recognition (SER) is a vital part of any voice based interactive system. Providing an efficient SER framework in multi-lingual domain is highly challenging due to the difficulties in feature extraction from noisy voice signals, language barrier, issues due to gender dependency, domain generalization problem etc. Therefore, all of these challenges have made multi-domain SER interesting to the researchers. In our study, we provide a multi-domain SER framework where popular benchmark corpora have been integrated and used together for training and testing with the goal of removing language barriers and the corpus dependency. Moreover, we have utilized the role of gender on acoustic signal features to improve the performance in multi-domain. We design a hierarchical Convolutional Neural Network (CNN) based framework that finds the influence of genders while recognizing emotions in multi-domain cross-corpus system. We have used Unweighted Average Recall (UAR) for measuring performance in the multi-domain corpus to address data imbalance problem. We validate our proposed framework by conducting extensive experiments with benchmark datasets. The results show that using the proposed gender-based SER model with multi-lingual cross-corpus performs better than the conventional SER models. Our novel multi-domain cross-corpus SER will be very helpful for designing different multi-lingual voice- based interactive applications.
{"title":"Breaking the Barrier with a Multi-Domain SER","authors":"Jamalia Sultana, Mahmuda Naznin","doi":"10.1109/COMPSAC54236.2022.00088","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00088","url":null,"abstract":"Voice based interactive system has numerous ap-plications including patient care system, robotics, interactive learning tool etc. Speech Emotion Recognition (SER) is a vital part of any voice based interactive system. Providing an efficient SER framework in multi-lingual domain is highly challenging due to the difficulties in feature extraction from noisy voice signals, language barrier, issues due to gender dependency, domain generalization problem etc. Therefore, all of these challenges have made multi-domain SER interesting to the researchers. In our study, we provide a multi-domain SER framework where popular benchmark corpora have been integrated and used together for training and testing with the goal of removing language barriers and the corpus dependency. Moreover, we have utilized the role of gender on acoustic signal features to improve the performance in multi-domain. We design a hierarchical Convolutional Neural Network (CNN) based framework that finds the influence of genders while recognizing emotions in multi-domain cross-corpus system. We have used Unweighted Average Recall (UAR) for measuring performance in the multi-domain corpus to address data imbalance problem. We validate our proposed framework by conducting extensive experiments with benchmark datasets. The results show that using the proposed gender-based SER model with multi-lingual cross-corpus performs better than the conventional SER models. Our novel multi-domain cross-corpus SER will be very helpful for designing different multi-lingual voice- based interactive applications.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115480580","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：