Pub Date : 2021-12-01DOI: 10.1109/CSCI54926.2021.00228
J. Weymouth, R. Karne, A. Wijesinha
The focus of Computer Science Education research has been innovation and increasing the learning experience. Knowledge has grown exponentially in all disciplines within computer science. Over the last decade, computer science education has been evolving from abstract subject matter to increased innovation. Studies show improved learning using automated and visual learning tools like simulations, virtualization, visualization, and video-like games. Recent research shows enhanced learning tools like visual automation, simulation, and video games are more beneficial than detrimental. This review will present some of the more innovative ways to give Computer Science Education.
{"title":"A Survey of Innovation in Undergraduate Computer Science Education","authors":"J. Weymouth, R. Karne, A. Wijesinha","doi":"10.1109/CSCI54926.2021.00228","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00228","url":null,"abstract":"The focus of Computer Science Education research has been innovation and increasing the learning experience. Knowledge has grown exponentially in all disciplines within computer science. Over the last decade, computer science education has been evolving from abstract subject matter to increased innovation. Studies show improved learning using automated and visual learning tools like simulations, virtualization, visualization, and video-like games. Recent research shows enhanced learning tools like visual automation, simulation, and video games are more beneficial than detrimental. This review will present some of the more innovative ways to give Computer Science Education.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126601624","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00129
Wenjuan Zhang, William Yang, J. Talburt, S. Weissman, Mary Q. Yang
The emergence of single-cell sequencing technologies has enabled the production of high-resolution data at the individual cell level, providing unprecedented opportunities to capture cell population diversity and dissect the cellular heterogeneity of complex diseases. At the same time, relatively high biological and technical noise poses new challenges for single-cell data analysis. The single-cell RNA sequencing (scRNA-seq) data often contains substantial missing values due to gene dropout events. Here, we developed a convolutional neural network based model to recover missing values for scRNA-seq data. We first calculated the probability of dropout employing gamma-normal expectation maximum algorithm. Unlike most existing approaches, our model only recovered the expression values that have a dropout probability larger than a threshold. The mean square error and Pearson correlation coefficient were used to assess the accuracy of predicted expression values. The purity and entropy were computed to measure the homogeneity of cell clusters using imputed gene expression profiles. Across various scRNAseq datasets, our model demonstrated robust performance and achieved comparable or better results compared to the other imputation methods.
{"title":"Missing Value Recovery for Single Cell RNA Sequencing Data","authors":"Wenjuan Zhang, William Yang, J. Talburt, S. Weissman, Mary Q. Yang","doi":"10.1109/CSCI54926.2021.00129","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00129","url":null,"abstract":"The emergence of single-cell sequencing technologies has enabled the production of high-resolution data at the individual cell level, providing unprecedented opportunities to capture cell population diversity and dissect the cellular heterogeneity of complex diseases. At the same time, relatively high biological and technical noise poses new challenges for single-cell data analysis. The single-cell RNA sequencing (scRNA-seq) data often contains substantial missing values due to gene dropout events. Here, we developed a convolutional neural network based model to recover missing values for scRNA-seq data. We first calculated the probability of dropout employing gamma-normal expectation maximum algorithm. Unlike most existing approaches, our model only recovered the expression values that have a dropout probability larger than a threshold. The mean square error and Pearson correlation coefficient were used to assess the accuracy of predicted expression values. The purity and entropy were computed to measure the homogeneity of cell clusters using imputed gene expression profiles. Across various scRNAseq datasets, our model demonstrated robust performance and achieved comparable or better results compared to the other imputation methods.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121234764","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00253
Delia Montero-Contreras, J. L. Quiroz-Fabián, Adriana Pérez-Espinosa, Rodrigo Rivera-Cerón
The COVID-19 pandemic took the world by surprise, its rapid spread and its death rate caused governments to make drastic decisions such as closing borders, establishing curfews, closing businesses, etc. in order to break the chains of infections. In many countries mobile apps were developed to have information on possible contagions and prevent their spread. This paper describes COVIUAM, a mobile app that collects information on suspected or confirmed cases of COVID-19 in members of the Metropolitan Autonomous University. Through the data collected by COVIUAM app, patterns can be identified in the information, for example in symptomatology data. The article highlights the design and architecture of COVIUAM app and presents two evaluations, one quantitative and one qualitative of the information collected and the use of the application.
{"title":"COVIUAM: A mobile app to get information about COVID-19 cases","authors":"Delia Montero-Contreras, J. L. Quiroz-Fabián, Adriana Pérez-Espinosa, Rodrigo Rivera-Cerón","doi":"10.1109/CSCI54926.2021.00253","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00253","url":null,"abstract":"The COVID-19 pandemic took the world by surprise, its rapid spread and its death rate caused governments to make drastic decisions such as closing borders, establishing curfews, closing businesses, etc. in order to break the chains of infections. In many countries mobile apps were developed to have information on possible contagions and prevent their spread. This paper describes COVIUAM, a mobile app that collects information on suspected or confirmed cases of COVID-19 in members of the Metropolitan Autonomous University. Through the data collected by COVIUAM app, patterns can be identified in the information, for example in symptomatology data. The article highlights the design and architecture of COVIUAM app and presents two evaluations, one quantitative and one qualitative of the information collected and the use of the application.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116763420","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00084
Korn Sooksatra, P. Rivas
With the rise of generative adversarial networks (GANs), many areas have seen remarkable improvements, e.g., computer vision, natural language processing, and the medical field. Notably, cryptography has been fueled by GANs producing adversarial neural cryptography (ANC). However, in these five years, ANC has little documented experimentation and applications that can be used in the real world. This paper aims to perform experiments on ANC to verify if the current status of ANC is ready for practical implementations of symmetric-key encryption. In our investigation, we assess several entities in ANC during training, encryption, and decryption of an ANC model, including decryption accuracy analysis. Furthermore, we study the resources required for deployment using different quantization techniques to reduce the size of an ANC model and its impact on performance and decryption accuracy. Our study provides enough data for offering practical advice for using and implementing ANC models.
{"title":"On the Practical Uses of Experimental Adversarial Neural Cryptography","authors":"Korn Sooksatra, P. Rivas","doi":"10.1109/CSCI54926.2021.00084","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00084","url":null,"abstract":"With the rise of generative adversarial networks (GANs), many areas have seen remarkable improvements, e.g., computer vision, natural language processing, and the medical field. Notably, cryptography has been fueled by GANs producing adversarial neural cryptography (ANC). However, in these five years, ANC has little documented experimentation and applications that can be used in the real world. This paper aims to perform experiments on ANC to verify if the current status of ANC is ready for practical implementations of symmetric-key encryption. In our investigation, we assess several entities in ANC during training, encryption, and decryption of an ANC model, including decryption accuracy analysis. Furthermore, we study the resources required for deployment using different quantization techniques to reduce the size of an ANC model and its impact on performance and decryption accuracy. Our study provides enough data for offering practical advice for using and implementing ANC models.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125219906","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00115
R. Hashemi, Omid M. Ardakani, Jeffrey A. Young, Chanchal Tamrakar
Establishing the relationship between stock price changes of a fortune 500 company and events (such as political, social, and/or business) is a multi-dimensional complex problem. However, such events change the social mood, which manifests itself in social media communications. Therefore, we collected time-series high frequency financial (HFF) data alongside corresponding time-series tweets about the same company for six months in 2019. Five months of data was used to (a) mine impactful tweets (nuggets) on minute-by-minute stock price changes, (b) discover and validate the nuggets profile, (c) predict future impactful tweets prior to their effects on the stock price using the HFF data and tweets for the sixth month as a test set, and (d) maintain an up-to-date nuggets profile. The results revealed successful detection of nuggets of tweets with a certainty factor close to 80%. Such prediction may greatly affect the decisions regarding market analytics.
{"title":"Mining the Impact of Social Media on High-Frequency Financial data","authors":"R. Hashemi, Omid M. Ardakani, Jeffrey A. Young, Chanchal Tamrakar","doi":"10.1109/CSCI54926.2021.00115","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00115","url":null,"abstract":"Establishing the relationship between stock price changes of a fortune 500 company and events (such as political, social, and/or business) is a multi-dimensional complex problem. However, such events change the social mood, which manifests itself in social media communications. Therefore, we collected time-series high frequency financial (HFF) data alongside corresponding time-series tweets about the same company for six months in 2019. Five months of data was used to (a) mine impactful tweets (nuggets) on minute-by-minute stock price changes, (b) discover and validate the nuggets profile, (c) predict future impactful tweets prior to their effects on the stock price using the HFF data and tweets for the sixth month as a test set, and (d) maintain an up-to-date nuggets profile. The results revealed successful detection of nuggets of tweets with a certainty factor close to 80%. Such prediction may greatly affect the decisions regarding market analytics.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115170579","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00044
Andrew T. Park, Richard Dill, D. Hodson, Wayne C. Henry
Data Distribution Service (DDS) is a publish-subscribe middleware used to distribute data between real-time systems, production environments, and small embedded plat-forms. In DDS, Nodes have at least one Publisher or Subscriber. Publishers and Subscribers use unique Topics to send and receive messages. Each Subscriber has permission to read the Publisher’s message if it references the same Topic sent from the Publisher. This capability supports real-time communication, sacrificing security, such as impersonation attacks.This paper details, tests, and evaluates DDS-Cerberus (DDS-C), a novel distributed communication protocol integrating Ker-beros ticketing system with DDS. DDS-C integrates Kerberos au-thentication and Ticket retrieval with Publishers and Subscribers. Experiments have six parameters each with a 2:1 Publisher to Subscriber ratio. Performance tests modify the message byte size to emulate .txt and .mp3 files: 10 KB, 100 KB, 1 MB, 5 MB, 10 MB, and 20 MB. Experiment metrics for functionality and performance are the messages per second and latency in a wired environment. Experiments utilize ROS 2 (Robot Operating System) as a testbed. Initial tests for a baseline are conducted without DDS modifications and subsequent tests with DDS-C modifications. The results reveal that due to the ticketing compo-nent, DDS-C increases DDS security by preventing impersonation attacks while negligibly increasing average processing compared to baseline results.
{"title":"DDS-Cerberus: Ticketing Performance Experiments and Analysis","authors":"Andrew T. Park, Richard Dill, D. Hodson, Wayne C. Henry","doi":"10.1109/CSCI54926.2021.00044","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00044","url":null,"abstract":"Data Distribution Service (DDS) is a publish-subscribe middleware used to distribute data between real-time systems, production environments, and small embedded plat-forms. In DDS, Nodes have at least one Publisher or Subscriber. Publishers and Subscribers use unique Topics to send and receive messages. Each Subscriber has permission to read the Publisher’s message if it references the same Topic sent from the Publisher. This capability supports real-time communication, sacrificing security, such as impersonation attacks.This paper details, tests, and evaluates DDS-Cerberus (DDS-C), a novel distributed communication protocol integrating Ker-beros ticketing system with DDS. DDS-C integrates Kerberos au-thentication and Ticket retrieval with Publishers and Subscribers. Experiments have six parameters each with a 2:1 Publisher to Subscriber ratio. Performance tests modify the message byte size to emulate .txt and .mp3 files: 10 KB, 100 KB, 1 MB, 5 MB, 10 MB, and 20 MB. Experiment metrics for functionality and performance are the messages per second and latency in a wired environment. Experiments utilize ROS 2 (Robot Operating System) as a testbed. Initial tests for a baseline are conducted without DDS modifications and subsequent tests with DDS-C modifications. The results reveal that due to the ticketing compo-nent, DDS-C increases DDS security by preventing impersonation attacks while negligibly increasing average processing compared to baseline results.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115180133","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00354
R. Hendricks, L. Altherr
The following work gives an overview of a special type of neural networks, autoencoders, that can be of great interest to researchers and practitioners in the field of smart city, due to their numerous application possibilities in this context. Given the fact that these networks can be trained in an unsupervised fashion, autoencoders are immediately applicable to practically collected data sets that often lack labels, not requiring the tedious process of data labeling. In addition to the classical autoencoder, we present two other types, and highlight their differences in architecture and in areas of application. In doing so, the benefits of the respective autoencoders and their possible application, especially in the context of smart cities, are presented.
{"title":"An Overview of Selected Autoencoders and Their Potential Application in Smart Cities","authors":"R. Hendricks, L. Altherr","doi":"10.1109/CSCI54926.2021.00354","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00354","url":null,"abstract":"The following work gives an overview of a special type of neural networks, autoencoders, that can be of great interest to researchers and practitioners in the field of smart city, due to their numerous application possibilities in this context. Given the fact that these networks can be trained in an unsupervised fashion, autoencoders are immediately applicable to practically collected data sets that often lack labels, not requiring the tedious process of data labeling. In addition to the classical autoencoder, we present two other types, and highlight their differences in architecture and in areas of application. In doing so, the benefits of the respective autoencoders and their possible application, especially in the context of smart cities, are presented.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122944821","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00125
Seema Singh Saharan, P. Nagar, K. Creasy, E. Stock, James Feng, M. Malloy, J. Kane
Presently, the role of cytokines in severe illness like COPD, cancer, cardiac disease associated with smoking is being explored to enable preemptive diagnosis and delivery of treatment interventions. We are investigating the connection between the elevation of inflammatory plasma cytokine in smokers versus nonsmokers. Disease indicator cytokines can be used to monitor the progression of disease which can help in the crucial task of prognosis and definitive diagnosis.Powerful and versatile Machine Learning algorithms can be leveraged to extract insights that cannot be obtained manually. We have applied Support Vector Machine (SVM) on 65 plasma cytokines and other traditional biomarkers to differentiate smokers and nonsmokers. To optimize the classification separability, we have used the following techniques: Principal component analysis (PCA), 10-fold cross validation and variable importance. The primary metric of evaluation is Area Under Receiver Operating Curve (AUROC), though we have additionally recorded and compared prediction accuracy across classifiers.The results are very promising. The AUROC classification accuracy achieved by SVM using the selected predictor feature variables is 89.2% with a 95%CI (85.4%,93.1%). The most prominent cytokines, contributing to the classification, in the order of importance are: I-TAC, Age, TG, G-CSF-CSF-3, MDCCCL22, Eotaxin-3, LIF, IL-2, Eotaxin-2, MIP-3alpha. The AUROC classification accuracy improved to 93% with a 95% CI (90.1%,99.5%) upon choosing the five most prominent cytokines.The versatile prowess of Machine Learning algorithms such as Support Vector Machine can translate pioneering molecular discoveries into actionable insights that can be applied in the field of translational and precision medicine to save life.
{"title":"Implementation of PCA enabled Support Vector Machine using cytokines to differentiate smokers versus nonsmokers.","authors":"Seema Singh Saharan, P. Nagar, K. Creasy, E. Stock, James Feng, M. Malloy, J. Kane","doi":"10.1109/CSCI54926.2021.00125","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00125","url":null,"abstract":"Presently, the role of cytokines in severe illness like COPD, cancer, cardiac disease associated with smoking is being explored to enable preemptive diagnosis and delivery of treatment interventions. We are investigating the connection between the elevation of inflammatory plasma cytokine in smokers versus nonsmokers. Disease indicator cytokines can be used to monitor the progression of disease which can help in the crucial task of prognosis and definitive diagnosis.Powerful and versatile Machine Learning algorithms can be leveraged to extract insights that cannot be obtained manually. We have applied Support Vector Machine (SVM) on 65 plasma cytokines and other traditional biomarkers to differentiate smokers and nonsmokers. To optimize the classification separability, we have used the following techniques: Principal component analysis (PCA), 10-fold cross validation and variable importance. The primary metric of evaluation is Area Under Receiver Operating Curve (AUROC), though we have additionally recorded and compared prediction accuracy across classifiers.The results are very promising. The AUROC classification accuracy achieved by SVM using the selected predictor feature variables is 89.2% with a 95%CI (85.4%,93.1%). The most prominent cytokines, contributing to the classification, in the order of importance are: I-TAC, Age, TG, G-CSF-CSF-3, MDCCCL22, Eotaxin-3, LIF, IL-2, Eotaxin-2, MIP-3alpha. The AUROC classification accuracy improved to 93% with a 95% CI (90.1%,99.5%) upon choosing the five most prominent cytokines.The versatile prowess of Machine Learning algorithms such as Support Vector Machine can translate pioneering molecular discoveries into actionable insights that can be applied in the field of translational and precision medicine to save life.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126994338","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 : 2021-12-01DOI: 10.1109/CSCI54926.2021.00200
Fadi Al-Ayed
To address future cybersecurity challenges, this paper proposes a real-time three-factor authentication scheme (RT3FA). The proposed model integrates the characteristics of multi-factor authentication and real-time actual information. The additional layer of protection raises the obstacles for data access; face biometric is needed in addition to two-factor authentication. Facial biometric is accomplished by synchronizing real-time information with feature recognition via an instantaneous live feed from the user’s camera. However, the improved protection may cause efficiency issues and thus, require higher capacities for both the user’s device and the database system.
{"title":"Zero-Trust Model of Cybersecurity: A Significant Challenge in the Future","authors":"Fadi Al-Ayed","doi":"10.1109/CSCI54926.2021.00200","DOIUrl":"https://doi.org/10.1109/CSCI54926.2021.00200","url":null,"abstract":"To address future cybersecurity challenges, this paper proposes a real-time three-factor authentication scheme (RT3FA). The proposed model integrates the characteristics of multi-factor authentication and real-time actual information. The additional layer of protection raises the obstacles for data access; face biometric is needed in addition to two-factor authentication. Facial biometric is accomplished by synchronizing real-time information with feature recognition via an instantaneous live feed from the user’s camera. However, the improved protection may cause efficiency issues and thus, require higher capacities for both the user’s device and the database system.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133092099","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 : 2021-12-01DOI: 10.1109/csci54926.2021.00242
F. Fathabadi, J. Grantner, Saad A. Shebrain, I. Abdel-Qader
In laparoscopic surgery, surgeons should acquire additional skills before carrying out real operative procedures. The manual skills component of the Fundamentals of Laparoscopic Surgery exam is essential to measure the trainees’ technical skills. The peg transfer task is a hands-on exam in the FLS program. In this paper, a multi-object detection method is proposed to improve the performance of a laparoscopic box¬trainer-based skill assessment system from the top, side, and front cameras. Based on experimental results, the trained model could identify each instrument at a high score of fidelity and the train¬validation total loss for the SSD ResNet50 v1 FPN was about 0.06. In addition, this method could correctly identify the peg transfer time, the move, the carry and dropped states of each object from the top, side, and front cameras. This improved intelligent laparoscopic surgical box-trainer system helps in enhancing surgery residents’ laparoscopic skills. This project is a collaborative research effort between the Department of Electrical and Computer Engineering and the Department of Surgery, at Western Michigan University.
{"title":"Surgical Skill Training and Evaluation for a Peg Transfer Task of a Three Camera-Based Laparoscopic Box-Trainer System","authors":"F. Fathabadi, J. Grantner, Saad A. Shebrain, I. Abdel-Qader","doi":"10.1109/csci54926.2021.00242","DOIUrl":"https://doi.org/10.1109/csci54926.2021.00242","url":null,"abstract":"In laparoscopic surgery, surgeons should acquire additional skills before carrying out real operative procedures. The manual skills component of the Fundamentals of Laparoscopic Surgery exam is essential to measure the trainees’ technical skills. The peg transfer task is a hands-on exam in the FLS program. In this paper, a multi-object detection method is proposed to improve the performance of a laparoscopic box¬trainer-based skill assessment system from the top, side, and front cameras. Based on experimental results, the trained model could identify each instrument at a high score of fidelity and the train¬validation total loss for the SSD ResNet50 v1 FPN was about 0.06. In addition, this method could correctly identify the peg transfer time, the move, the carry and dropped states of each object from the top, side, and front cameras. This improved intelligent laparoscopic surgical box-trainer system helps in enhancing surgery residents’ laparoscopic skills. This project is a collaborative research effort between the Department of Electrical and Computer Engineering and the Department of Surgery, at Western Michigan University.","PeriodicalId":206881,"journal":{"name":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134267862","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：