The research on visual analytics for software maintenance has noticeabily advanced in the past few years. For many software projects, software maintenance needs an effective and efficient path from data to decision. Visual analytics (VA) creates such a path that enables the user to extract insights by interacting with the relevant information. This paper focuses on VA in software maintenance and has the following goals: investigate the VA adoption and suggest important implications for practice, and identify current research trends, open problems, and areas for improvement. To achieve these goals we conducted a systematic literature review with three research questions and assessed 51 studies published in the past two decades. The results indicate that there is a lack of collaboration between academic researchers and industry practitioners. This impedes the credibility of the proposed tools and methods due to lack of confidence in industry adoption. Furthermore, in this study we identified the need to expand VA support to other programming languages and software maintenance tasks.
{"title":"Visual Analytics in Software Maintenance: A Systematic Literature Review","authors":"Kaihua Liu, S. Reddivari","doi":"10.1145/3564746.3587022","DOIUrl":"https://doi.org/10.1145/3564746.3587022","url":null,"abstract":"The research on visual analytics for software maintenance has noticeabily advanced in the past few years. For many software projects, software maintenance needs an effective and efficient path from data to decision. Visual analytics (VA) creates such a path that enables the user to extract insights by interacting with the relevant information. This paper focuses on VA in software maintenance and has the following goals: investigate the VA adoption and suggest important implications for practice, and identify current research trends, open problems, and areas for improvement. To achieve these goals we conducted a systematic literature review with three research questions and assessed 51 studies published in the past two decades. The results indicate that there is a lack of collaboration between academic researchers and industry practitioners. This impedes the credibility of the proposed tools and methods due to lack of confidence in industry adoption. Furthermore, in this study we identified the need to expand VA support to other programming languages and software maintenance tasks.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122186694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the area of research and the process of being innovative, researchers know that sometimes the tools that are needed are something other than what can be attained off the shelf. During research conducted in the selection and composition of cyberattack models, a prototype application was built to assist in searching for cyberattack information against specific systems. This process of selection is only one step towards learning more about cyberattacks and how organizations can defend against them. An initial prototype web application was developed, and this project has expanded the functionality of that web application to not only allow the selection of cyberattack models but also to compose them. The composition is based on two approaches, sequential or parallel. The application has also been expanded to automate the process of assembling models. A description of the design specifications of the application and additional development plans are shown.
{"title":"Cyberattack Repository: A Web Application for the Selection and Composition of Cyberattack Models","authors":"Katia P. Maxwell, Levi Seibert","doi":"10.1145/3564746.3587012","DOIUrl":"https://doi.org/10.1145/3564746.3587012","url":null,"abstract":"In the area of research and the process of being innovative, researchers know that sometimes the tools that are needed are something other than what can be attained off the shelf. During research conducted in the selection and composition of cyberattack models, a prototype application was built to assist in searching for cyberattack information against specific systems. This process of selection is only one step towards learning more about cyberattacks and how organizations can defend against them. An initial prototype web application was developed, and this project has expanded the functionality of that web application to not only allow the selection of cyberattack models but also to compose them. The composition is based on two approaches, sequential or parallel. The application has also been expanded to automate the process of assembling models. A description of the design specifications of the application and additional development plans are shown.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131200744","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}
Since 1999, the National Science Foundation has supported a program that provides scholarships to low income students who pursue degrees in computer science, engineering, or mathematics. Originally, this program was called "Computer Science, Engineering, and Mathematics Scholarships" (CSEMS). In 2004, the program was renamed "Scholarships for Science, Technology, Engineering, and Mathematics" (S-STEM) and modified to include students from physical and life sciences. Appalachian State University (App State) has been the recipient of five CSEMS/S-STEM awards since 2001. Nearly all of the students in these programs experienced high levels of financial need and the majority were first generation college students. Our CSEMS and S-STEM programs have consistently maintained high rates of retention, significantly higher than national retention rates for these majors. Our current S-STEM program incorporates students from chemistry, geology, and physics and astronomy in addition to computer science and mathematics. We have also been able to maintain high rates of retention, over 88 percent, for this more diverse group of majors. We attribute this success to addressing financial, academic, and social barriers to success in STEM. This paper discusses the components of our current S-STEM program, The Appalachian High Achievers in STEM.
{"title":"Success with S-STEM: The Appalachian High Achievers in STEM","authors":"R. Tashakkori, Cindy Norris, Jennifer R. McGee","doi":"10.1145/3564746.3587017","DOIUrl":"https://doi.org/10.1145/3564746.3587017","url":null,"abstract":"Since 1999, the National Science Foundation has supported a program that provides scholarships to low income students who pursue degrees in computer science, engineering, or mathematics. Originally, this program was called \"Computer Science, Engineering, and Mathematics Scholarships\" (CSEMS). In 2004, the program was renamed \"Scholarships for Science, Technology, Engineering, and Mathematics\" (S-STEM) and modified to include students from physical and life sciences. Appalachian State University (App State) has been the recipient of five CSEMS/S-STEM awards since 2001. Nearly all of the students in these programs experienced high levels of financial need and the majority were first generation college students. Our CSEMS and S-STEM programs have consistently maintained high rates of retention, significantly higher than national retention rates for these majors. Our current S-STEM program incorporates students from chemistry, geology, and physics and astronomy in addition to computer science and mathematics. We have also been able to maintain high rates of retention, over 88 percent, for this more diverse group of majors. We attribute this success to addressing financial, academic, and social barriers to success in STEM. This paper discusses the components of our current S-STEM program, The Appalachian High Achievers in STEM.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128866938","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}
Our study uses the power of a graphics processing unit (GPU) to run malicious domain detection algorithms quickly and efficiently. We have developed a graphical user interface-based system that allows users to upload datasets (malicious domains) into a local database and then run tests with a list of domains to identify whether they are malicious. We have collected real malicious domain data from malicious domain websites and tested the five most widely used string-matching algorithms (Naïve, Levenshtein distance, Hamming distance, KMP and Rabin Karp), which allow users to compare the speeds of different string algorithms with varying time complexities against the number of domains both on the GPU (or the CPU) and our sample. On a CPU, this task becomes slower as our dataset grows. On a GPU, however, these algorithms can be run on any dataset size within the limit of the GPU's capacity with consistent performance.
{"title":"Developing a GUI Application: GPU-Accelerated Malicious Domain Detection","authors":"Trevor Rice, Dae Wook Kim, Mengkun Yang","doi":"10.1145/3564746.3587105","DOIUrl":"https://doi.org/10.1145/3564746.3587105","url":null,"abstract":"Our study uses the power of a graphics processing unit (GPU) to run malicious domain detection algorithms quickly and efficiently. We have developed a graphical user interface-based system that allows users to upload datasets (malicious domains) into a local database and then run tests with a list of domains to identify whether they are malicious. We have collected real malicious domain data from malicious domain websites and tested the five most widely used string-matching algorithms (Naïve, Levenshtein distance, Hamming distance, KMP and Rabin Karp), which allow users to compare the speeds of different string algorithms with varying time complexities against the number of domains both on the GPU (or the CPU) and our sample. On a CPU, this task becomes slower as our dataset grows. On a GPU, however, these algorithms can be run on any dataset size within the limit of the GPU's capacity with consistent performance.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124091443","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}
Mobile IoT is a collection of wireless moving nodes that function together to form a momentary network without centralized management or regular support services. Node moving at high mobility speed results in link failure and periodic topological variations in the network, often forcing nodes to restart the route discovery process. Existing multi-path routing that considers optimized hop count is the primary focus of the routing algorithm. Any connection interruption leads to packet loss, which increases delay and energy costs for retransmission. To mitigate these issues, we propose a mobility-based dynamic energy-efficient routing (DEER) through the link stability for mobile IoT nodes in software-defined wireless sensor networks (SDWSNs). The proposed DEER uses fuzzy logic to determine the link strength between nodes using an expected transmission count and path loss ratio. Then by assessing the residual energy of each node, the DEER system chooses relay nodes and decides on multipath routing while preserving link stability, reliability, and extended network lifetime.
{"title":"Mobility-based Optimal Relay Node Selection for IoT-oriented SDWSN","authors":"Poornima M R, Vimala H S, J Shreyas","doi":"10.1145/3564746.3587026","DOIUrl":"https://doi.org/10.1145/3564746.3587026","url":null,"abstract":"Mobile IoT is a collection of wireless moving nodes that function together to form a momentary network without centralized management or regular support services. Node moving at high mobility speed results in link failure and periodic topological variations in the network, often forcing nodes to restart the route discovery process. Existing multi-path routing that considers optimized hop count is the primary focus of the routing algorithm. Any connection interruption leads to packet loss, which increases delay and energy costs for retransmission. To mitigate these issues, we propose a mobility-based dynamic energy-efficient routing (DEER) through the link stability for mobile IoT nodes in software-defined wireless sensor networks (SDWSNs). The proposed DEER uses fuzzy logic to determine the link strength between nodes using an expected transmission count and path loss ratio. Then by assessing the residual energy of each node, the DEER system chooses relay nodes and decides on multipath routing while preserving link stability, reliability, and extended network lifetime.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115474008","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}
Md. Farhadul Islam, Sarah Zabeen, Fardin Bin Rahman, Md. Azharul Islam, Fahmid Bin Kibria, Meem Arafat Manab, Dewan Ziaul Karim, Annajiat Alim Rasel
In order to represent and investigate interconnected data, Graph Neural Networks (GNN) offer a robust framework that deftly combines Graph theory with Machine learning. Most of the studies focus on performance but uncertainty measurement does not get enough attention. In this study, we measure the predictive uncertainty of several GNN models, to show how high performance does not ensure reliable performance. We use dropouts during the inference phase to quantify the uncertainty of these transformer models. This method, often known as Monte Carlo Dropout (MCD), is an effective low-complexity approximation for calculating uncertainty. Benchmark dataset was used with five GNN models: Graph Convolutional Network (GCN), Graph Attention Network (GAT), Personalized Propagation of Neural Predictions (PPNP), PPNP's fast approximation (APPNP) and GraphSAGE in our investigation. GAT proved to be superior to all the other models in terms of accuracy and uncertainty both in node classification. Among the other models, some that fared better in accuracy fell behind when compared using classification uncertainty.
{"title":"Exploring Node Classification Uncertainty in Graph Neural Networks","authors":"Md. Farhadul Islam, Sarah Zabeen, Fardin Bin Rahman, Md. Azharul Islam, Fahmid Bin Kibria, Meem Arafat Manab, Dewan Ziaul Karim, Annajiat Alim Rasel","doi":"10.1145/3564746.3587019","DOIUrl":"https://doi.org/10.1145/3564746.3587019","url":null,"abstract":"In order to represent and investigate interconnected data, Graph Neural Networks (GNN) offer a robust framework that deftly combines Graph theory with Machine learning. Most of the studies focus on performance but uncertainty measurement does not get enough attention. In this study, we measure the predictive uncertainty of several GNN models, to show how high performance does not ensure reliable performance. We use dropouts during the inference phase to quantify the uncertainty of these transformer models. This method, often known as Monte Carlo Dropout (MCD), is an effective low-complexity approximation for calculating uncertainty. Benchmark dataset was used with five GNN models: Graph Convolutional Network (GCN), Graph Attention Network (GAT), Personalized Propagation of Neural Predictions (PPNP), PPNP's fast approximation (APPNP) and GraphSAGE in our investigation. GAT proved to be superior to all the other models in terms of accuracy and uncertainty both in node classification. Among the other models, some that fared better in accuracy fell behind when compared using classification uncertainty.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"13 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128987784","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}
Single-Board Computers (SBCs) are increasingly being used due to their small form factor, reduced energy consumption, versatility, affordability, and increasing computational power. Therefore, they are now used in projects where they were not initially contemplated, such as running a Virtual Machine Manager (VMM). In this work, two ARM-based SBCs were selected (Raspberry Pi 4 Model B and ODROID-N2+) and an empirical evaluation was carried out to evaluate the network performance between two nodes running in the same SBC, or in different SBCs directly connected through WiFi or Ethernet. Although several hypervisors are suitable for these SBCs, Kernel-based Virtual Machine (KVM) was chosen since it seems to be the most active project that is developed for the ARM-based architecture. The metrics reported in this study include the TCP latency, UDP latency, TCP throughput, and HTTP latency. In general, the network performance of the ODROID-N2+ exceeded the Raspberry Pi 4 Model B. However, the latter has an indisputable advantage over the former with a much larger and more active community, making the development and deployment of applications much faster and straightforward. Hence, selecting the suitable SBCs should be done cautiously, considering the required software and additional hardware that the project is planning to connect to the SBCs.
单板计算机(sbc)由于其小尺寸、低能耗、多功能性、可负担性和不断提高的计算能力而越来越多地被使用。因此，它们现在被用于最初没有考虑到的项目中，例如运行虚拟机管理器(VMM)。本文选择了两个基于arm的SBC (Raspberry Pi 4 Model B和ODROID-N2+)，对运行在同一SBC中的两个节点，以及通过WiFi或以太网直接连接的不同SBC中的两个节点之间的网络性能进行了实证评估。尽管有几个管理程序适合这些sbc，但我们选择了基于内核的虚拟机(KVM)，因为它似乎是为基于arm的架构开发的最活跃的项目。本研究报告的指标包括TCP延迟、UDP延迟、TCP吞吐量和HTTP延迟。总的来说，ODROID-N2+的网络性能超过了Raspberry Pi 4 Model b。然而，后者比前者具有无可争辩的优势，因为它拥有更大、更活跃的社区，使得应用程序的开发和部署更快、更直接。因此，应该谨慎选择合适的sbc，考虑项目计划连接到sbc所需的软件和其他硬件。
{"title":"Network Performance Evaluation Between Virtual/Native Nodes Running on ARM-based SBCs Using KVM as Hypervisor","authors":"Eric Gamess","doi":"10.1145/3564746.3587015","DOIUrl":"https://doi.org/10.1145/3564746.3587015","url":null,"abstract":"Single-Board Computers (SBCs) are increasingly being used due to their small form factor, reduced energy consumption, versatility, affordability, and increasing computational power. Therefore, they are now used in projects where they were not initially contemplated, such as running a Virtual Machine Manager (VMM). In this work, two ARM-based SBCs were selected (Raspberry Pi 4 Model B and ODROID-N2+) and an empirical evaluation was carried out to evaluate the network performance between two nodes running in the same SBC, or in different SBCs directly connected through WiFi or Ethernet. Although several hypervisors are suitable for these SBCs, Kernel-based Virtual Machine (KVM) was chosen since it seems to be the most active project that is developed for the ARM-based architecture. The metrics reported in this study include the TCP latency, UDP latency, TCP throughput, and HTTP latency. In general, the network performance of the ODROID-N2+ exceeded the Raspberry Pi 4 Model B. However, the latter has an indisputable advantage over the former with a much larger and more active community, making the development and deployment of applications much faster and straightforward. Hence, selecting the suitable SBCs should be done cautiously, considering the required software and additional hardware that the project is planning to connect to the SBCs.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121892734","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, we present our findings with regard to teaching basic programming concepts at an Open Access Institution. The goal was to gather insight into how to best introduce programming to our students. We found that our students should start with block coding, as a means to slowly and easily introduce coding concepts. Then they are ready for text-based programming skills. This flow allows them to understand and be able to apply basic computing concepts and enjoy the process of learning. Also, introducing block coding should be done via a fun game or activity to entice them to want to learn programming.
{"title":"Understanding College Level Student Learning of Basic Programming at an Open Access Institution","authors":"Cindy Robertson, Anca Doloc-Mihu","doi":"10.1145/3564746.3587007","DOIUrl":"https://doi.org/10.1145/3564746.3587007","url":null,"abstract":"In this study, we present our findings with regard to teaching basic programming concepts at an Open Access Institution. The goal was to gather insight into how to best introduce programming to our students. We found that our students should start with block coding, as a means to slowly and easily introduce coding concepts. Then they are ready for text-based programming skills. This flow allows them to understand and be able to apply basic computing concepts and enjoy the process of learning. Also, introducing block coding should be done via a fun game or activity to entice them to want to learn programming.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131808516","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}
Bryson Phillip, Ethan Butler, Ben Ulrich, David Carroll
We show that a quantum version of a classical arithmetic-logic unit (ALU) can be implemented on a quantum circuit. It would perform the same functions as a classical ALU, with the possibility of adding quantum functions in conjunction. To create the quantum ALU, we utilized IBM's Python package Qiskit and JupyterLab. We believe that a quantum ALU has the potential to be faster than its classical counterpart and the ability to calculate quantum specific operations. The simple classical functions translated to a quantum circuit show a promising future for the development of a full quantum ALU with unique quantum operations.
{"title":"A Quantum Computing Arithmetic-logic Unit","authors":"Bryson Phillip, Ethan Butler, Ben Ulrich, David Carroll","doi":"10.1145/3564746.3587005","DOIUrl":"https://doi.org/10.1145/3564746.3587005","url":null,"abstract":"We show that a quantum version of a classical arithmetic-logic unit (ALU) can be implemented on a quantum circuit. It would perform the same functions as a classical ALU, with the possibility of adding quantum functions in conjunction. To create the quantum ALU, we utilized IBM's Python package Qiskit and JupyterLab. We believe that a quantum ALU has the potential to be faster than its classical counterpart and the ability to calculate quantum specific operations. The simple classical functions translated to a quantum circuit show a promising future for the development of a full quantum ALU with unique quantum operations.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131641857","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}
Current license plate recognition systems struggle with image noise reduction and license plate feature detecting processes. This paper presents an efficient and highly accurate license plate detection and character detection program based on the YOLO neural network, which is a simplified CNN-based neural network frame for robust image processing systems. Different than most approaches, the system we proposed simply requires a prioritized analysis of the dataset in order to evaluate potential noises inside images so that program implementations could be more effective and more targeted to design and optimize with YOLO neural network. With our presented system, the accuracy of license plate detection improves from 63% which is performed by traditional image processing methods to 90.3%.
{"title":"Robust Efficient License Plate and Character Detection System Based on Simplified CNN","authors":"Selena He, Tu N. Nguyen, Kun Suo","doi":"10.1145/3564746.3587108","DOIUrl":"https://doi.org/10.1145/3564746.3587108","url":null,"abstract":"Current license plate recognition systems struggle with image noise reduction and license plate feature detecting processes. This paper presents an efficient and highly accurate license plate detection and character detection program based on the YOLO neural network, which is a simplified CNN-based neural network frame for robust image processing systems. Different than most approaches, the system we proposed simply requires a prioritized analysis of the dataset in order to evaluate potential noises inside images so that program implementations could be more effective and more targeted to design and optimize with YOLO neural network. With our presented system, the accuracy of license plate detection improves from 63% which is performed by traditional image processing methods to 90.3%.","PeriodicalId":322431,"journal":{"name":"Proceedings of the 2023 ACM Southeast Conference","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133945422","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：