Gerald Onwujekwe, Manoj A. Thomas, Kweku-Muata A. Osei-Bryson
The Deloitte's report (2015) on cybersecurity trends states that emerging technologies, coupled with a shifting threat profile, are challenging organizations to deal more and more with sophisticated "bad actors" that are motivated, skilled, and adaptable [1]. There is little doubt that cybercrime is growing more rapidly than cybersecurity measures are able to deal with and businesses and governments have never been more at risk from cyberattacks. In this paper, we ask the question, 'what are some of the robust data governance practices that can be put in place to forestall cybercrime?' We also asked the question, 'are there some research papers that have been published to address this concern? We then took a deep into extant literature to find out. Furthermore, we proposed a cybercrime mitigation framework using robust data governance. Our literature synthesis revealed that there is little research that investigated the concept of data governance and cybercrime together, which leads us to propose research hypotheses for a future quantitative research.
{"title":"Using Robust Data Governance to Mitigate the Impact of Cybercrime","authors":"Gerald Onwujekwe, Manoj A. Thomas, Kweku-Muata A. Osei-Bryson","doi":"10.1145/3325917.3325923","DOIUrl":"https://doi.org/10.1145/3325917.3325923","url":null,"abstract":"The Deloitte's report (2015) on cybersecurity trends states that emerging technologies, coupled with a shifting threat profile, are challenging organizations to deal more and more with sophisticated \"bad actors\" that are motivated, skilled, and adaptable [1]. There is little doubt that cybercrime is growing more rapidly than cybersecurity measures are able to deal with and businesses and governments have never been more at risk from cyberattacks. In this paper, we ask the question, 'what are some of the robust data governance practices that can be put in place to forestall cybercrime?' We also asked the question, 'are there some research papers that have been published to address this concern? We then took a deep into extant literature to find out. Furthermore, we proposed a cybercrime mitigation framework using robust data governance. Our literature synthesis revealed that there is little research that investigated the concept of data governance and cybercrime together, which leads us to propose research hypotheses for a future quantitative research.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116411953","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}
The Internet in general and the web are considered the main medium of remote communication. They are important sources of information and services to all the users. Assistive technologies and tools facilitate web accessibility to help users with special needs by delivering the content of the webpages in a form that is understandable by these users. However, these assistive technologies and tools often face certain obstacles in delivering the information because of the confusion of web design elements caused by poor webpage design or carelessness in following the web accessibility guidelines. In this paper, we list the minimum required web accessibility guidelines formulated on the basis of a comprehensive review of WCAG 2.1 guidelines to be followed while developing webpages for visually impaired users. We then introduce a tool intended to enhance web accessibility for such users. We tested the tool on a few websites and observed that it significantly improved the webpage accessibility of these websites.
{"title":"Instant Adaptation Enrichment Technique to Improve Web Accessibility for Blind Users","authors":"Suliman K. Almasoud, H. Mathkour","doi":"10.1145/3325917.3325931","DOIUrl":"https://doi.org/10.1145/3325917.3325931","url":null,"abstract":"The Internet in general and the web are considered the main medium of remote communication. They are important sources of information and services to all the users. Assistive technologies and tools facilitate web accessibility to help users with special needs by delivering the content of the webpages in a form that is understandable by these users. However, these assistive technologies and tools often face certain obstacles in delivering the information because of the confusion of web design elements caused by poor webpage design or carelessness in following the web accessibility guidelines. In this paper, we list the minimum required web accessibility guidelines formulated on the basis of a comprehensive review of WCAG 2.1 guidelines to be followed while developing webpages for visually impaired users. We then introduce a tool intended to enhance web accessibility for such users. We tested the tool on a few websites and observed that it significantly improved the webpage accessibility of these websites.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114437168","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}
With the rapid development of the Internet, the network traffic shows an explosive growth trend. Although the Internet facilitates people's lives, it also brings a lot of security threats. Thus, the analysis of abnormal behavior of network traffic becomes a crucial factor for ensuring the quality of Internet services and preventing network intrusion. This paper proposes a deep learning method that combines CNN and LSTM to detect abnormal network traffic, especially unknown intrusions. In the field of machine learning, the choice of features is the key ingredient to the effect and accuracy of the model. Therefore, this paper also proposes a feature selection method based on Information Gain (IG), extracting more valuable features, which are fed into the model. We use CNN to extract the higher dimensional features of the input data, and then use LSTM to learn the timing characteristics of the network traffic. We applied our model on the KDD99 dataset and assessed its accuracy. When the epoch greater than 4, the training accuracy reaches 0.99 and testing accuracy reaches 0.925, which showed a certain improvement compared with the traditional model. In the era when information volume is becoming more and more dense, the analysis of network traffic will become more and more necessary, which also proves broader application prospects.
随着互联网的快速发展，网络流量呈现爆发式增长趋势。虽然互联网方便了人们的生活，但它也带来了很多安全威胁。因此，分析网络流量的异常行为成为保证互联网服务质量和防止网络入侵的关键因素。本文提出了一种结合CNN和LSTM的深度学习方法来检测异常网络流量，特别是未知入侵。在机器学习领域，特征的选择是影响模型效果和准确性的关键因素。因此，本文还提出了一种基于信息增益(Information Gain, IG)的特征选择方法，提取更多有价值的特征，并将其输入到模型中。我们使用CNN提取输入数据的高维特征，然后使用LSTM学习网络流量的时序特征。我们将我们的模型应用于KDD99数据集并评估了它的准确性。当epoch大于4时，训练精度达到0.99，测试精度达到0.925，与传统模型相比有一定的提高。在信息量越来越密集的时代，对网络流量的分析将越来越有必要，这也证明了更广阔的应用前景。
{"title":"Network Traffic Anomaly Detection Based on Information Gain and Deep Learning","authors":"Xianglin Lu, Pengju Liu, Jiayi Lin","doi":"10.1145/3325917.3325946","DOIUrl":"https://doi.org/10.1145/3325917.3325946","url":null,"abstract":"With the rapid development of the Internet, the network traffic shows an explosive growth trend. Although the Internet facilitates people's lives, it also brings a lot of security threats. Thus, the analysis of abnormal behavior of network traffic becomes a crucial factor for ensuring the quality of Internet services and preventing network intrusion. This paper proposes a deep learning method that combines CNN and LSTM to detect abnormal network traffic, especially unknown intrusions. In the field of machine learning, the choice of features is the key ingredient to the effect and accuracy of the model. Therefore, this paper also proposes a feature selection method based on Information Gain (IG), extracting more valuable features, which are fed into the model. We use CNN to extract the higher dimensional features of the input data, and then use LSTM to learn the timing characteristics of the network traffic. We applied our model on the KDD99 dataset and assessed its accuracy. When the epoch greater than 4, the training accuracy reaches 0.99 and testing accuracy reaches 0.925, which showed a certain improvement compared with the traditional model. In the era when information volume is becoming more and more dense, the analysis of network traffic will become more and more necessary, which also proves broader application prospects.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019594","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}
Ali Alqazzaz, Raed Alharthi, Ibrahim Alrashdi, E. Aloufi, M. Zohdy, Ming Hua
The smart parking system is a major component of the smart city concept, especially in the age of the Internet of Things (IoT). It attempts to take the stress out of finding a free parking space in crowded places, mostly during peak times. This paper focuses on implementing a secure smart parking solution based on the publish-subscribe communication model for exchanging a huge volume of data with a large number of clients while minimizing the power consumption. The Elliptic Curve Cryptography (ECC) was adopted in this paper as a promising substitution to traditional public key cryptography such as Rivest-Shamir-Adleman (RSA). The implemented system provides several functional services including parking vacancy detection, real-time information for drivers about parking availability, driver guidance, and parking reservation. Moreover, it provides security mechanisms for both network and application layers. Performance and power consumption experiments using a testbed show the efficiency and practicality of the implemented system, essentially with the IoT resource-constrained devices. Our findings demonstrate achieving energy consumption reductions of up to 54% and a CPU usage decrease of up to 55% compared to the existing solutions.
{"title":"A Practical Evaluation of a Secure and Energy-Efficient Smart Parking System Using the MQTT Protocol","authors":"Ali Alqazzaz, Raed Alharthi, Ibrahim Alrashdi, E. Aloufi, M. Zohdy, Ming Hua","doi":"10.1145/3325917.3325937","DOIUrl":"https://doi.org/10.1145/3325917.3325937","url":null,"abstract":"The smart parking system is a major component of the smart city concept, especially in the age of the Internet of Things (IoT). It attempts to take the stress out of finding a free parking space in crowded places, mostly during peak times. This paper focuses on implementing a secure smart parking solution based on the publish-subscribe communication model for exchanging a huge volume of data with a large number of clients while minimizing the power consumption. The Elliptic Curve Cryptography (ECC) was adopted in this paper as a promising substitution to traditional public key cryptography such as Rivest-Shamir-Adleman (RSA). The implemented system provides several functional services including parking vacancy detection, real-time information for drivers about parking availability, driver guidance, and parking reservation. Moreover, it provides security mechanisms for both network and application layers. Performance and power consumption experiments using a testbed show the efficiency and practicality of the implemented system, essentially with the IoT resource-constrained devices. Our findings demonstrate achieving energy consumption reductions of up to 54% and a CPU usage decrease of up to 55% compared to the existing solutions.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125564795","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}
Sterling Ramroach, A. Dhanoo, B. Cockburn, A. Joshi
Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics processing unit (GPU). In this paper, we leveraged the power of Nvidia GPUs to parallelize all of the computation involved in training, to accelerate a backpropagation feed-forward neural network with one hidden layer using CUDA and C++. This optimized neural network was tasked with predicting the level of glycated hemoglobin (HbA1c) from non-invasive markers. The rate of increase in the prevalence of Diabetes Mellitus has resulted in an urgent need for early detection and accurate diagnosis. However, due to the invasiveness and limitations of conventional tests, alternate means are being considered. Limited Joint Mobility (LJM) has been reported as an indicator for poor glycemic control. LJM of the fingers is quantified and its link to HbA1c is investigated along with other potential non-invasive markers of HbA1c. We collected readings of 33 potential markers from 120 participants at a clinic in south Trinidad. Our neural network achieved 95.65% accuracy on the training and 86.67% accuracy on the testing set for male participants and 97.73% and 66.67% accuracy on the training and testing sets for female participants. Using 960 CUDA cores from a Nvidia GeForce GTX 660, our parallelized neural network was trained 50 times faster on both subsets, than its corresponding CPU implementation on an Intel® Core™ i7-3630QM 2.40 GHz CPU.
{"title":"CUDA Optimized Neural Network Predicts Blood Glucose Control from Quantified Joint Mobility and Anthropometrics","authors":"Sterling Ramroach, A. Dhanoo, B. Cockburn, A. Joshi","doi":"10.1145/3325917.3325940","DOIUrl":"https://doi.org/10.1145/3325917.3325940","url":null,"abstract":"Neural network training entails heavy computation with obvious bottlenecks. The Compute Unified Device Architecture (CUDA) programming model allows us to accelerate computation by passing the processing workload from the CPU to the graphics processing unit (GPU). In this paper, we leveraged the power of Nvidia GPUs to parallelize all of the computation involved in training, to accelerate a backpropagation feed-forward neural network with one hidden layer using CUDA and C++. This optimized neural network was tasked with predicting the level of glycated hemoglobin (HbA1c) from non-invasive markers. The rate of increase in the prevalence of Diabetes Mellitus has resulted in an urgent need for early detection and accurate diagnosis. However, due to the invasiveness and limitations of conventional tests, alternate means are being considered. Limited Joint Mobility (LJM) has been reported as an indicator for poor glycemic control. LJM of the fingers is quantified and its link to HbA1c is investigated along with other potential non-invasive markers of HbA1c. We collected readings of 33 potential markers from 120 participants at a clinic in south Trinidad. Our neural network achieved 95.65% accuracy on the training and 86.67% accuracy on the testing set for male participants and 97.73% and 66.67% accuracy on the training and testing sets for female participants. Using 960 CUDA cores from a Nvidia GeForce GTX 660, our parallelized neural network was trained 50 times faster on both subsets, than its corresponding CPU implementation on an Intel® Core™ i7-3630QM 2.40 GHz CPU.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126790916","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}
Economics of partial equilibrium and general equilibrium cannot analyse the balanced problem of Internet economy, a single price lever is not fit for a full analysis of the Internet economy equilibrium problem, which the Internet economy equilibrium with polymorphism.this paper from the perspective of balanced general understanding and criticism, analyzes the equilibrium problems in western economics, and studied the foundation and the condition of the Internet economy polymorphic equilibrium analysis.
{"title":"Study on Polymorphic Equilibrium of Internet Economy","authors":"Chenggang Li, Lu Ge","doi":"10.1145/3325917.3325950","DOIUrl":"https://doi.org/10.1145/3325917.3325950","url":null,"abstract":"Economics of partial equilibrium and general equilibrium cannot analyse the balanced problem of Internet economy, a single price lever is not fit for a full analysis of the Internet economy equilibrium problem, which the Internet economy equilibrium with polymorphism.this paper from the perspective of balanced general understanding and criticism, analyzes the equilibrium problems in western economics, and studied the foundation and the condition of the Internet economy polymorphic equilibrium analysis.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127713852","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}
Ruey-Shun Chen, Yeh-Cheng Chen, Jyh-haw Yeh, Yu-Xi Hu, N. Xiong, C-P Lee
The research combines two heuristic algorithms, COMSOAL and Priority rule-based algorithm, to design a production scheduling algorithm. Meanwhile it refers to dispatching rule and wafer start rule. Also base on the requirements and characters of wafer foundry companies, it designs proper capacity constraint model and wafer start rule to construct production planning system. Using simple, fast and flexible methods to generate reasonable and feasible production plans. The results of the research can give the wafer foundry companies several contributions. First, it shortens the execution time of generating a production plan. It improves the flexibility and efficiency of production planning. Second, the resolution of production plan is raised from the summary of manufacturing process and product type to full product name of order and demand allocation. It improves the resolution and accuracy of information analysis. Third, the planning period of wafer start plan is improved as well. Last, the frequency of production planning operation is improved from once a fortnight to once a week.
{"title":"Using Intelligent Algorithms to Construct a Wafer Foundry System in Manufacturing Industry","authors":"Ruey-Shun Chen, Yeh-Cheng Chen, Jyh-haw Yeh, Yu-Xi Hu, N. Xiong, C-P Lee","doi":"10.1145/3325917.3325918","DOIUrl":"https://doi.org/10.1145/3325917.3325918","url":null,"abstract":"The research combines two heuristic algorithms, COMSOAL and Priority rule-based algorithm, to design a production scheduling algorithm. Meanwhile it refers to dispatching rule and wafer start rule. Also base on the requirements and characters of wafer foundry companies, it designs proper capacity constraint model and wafer start rule to construct production planning system. Using simple, fast and flexible methods to generate reasonable and feasible production plans. The results of the research can give the wafer foundry companies several contributions. First, it shortens the execution time of generating a production plan. It improves the flexibility and efficiency of production planning. Second, the resolution of production plan is raised from the summary of manufacturing process and product type to full product name of order and demand allocation. It improves the resolution and accuracy of information analysis. Third, the planning period of wafer start plan is improved as well. Last, the frequency of production planning operation is improved from once a fortnight to once a week.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133930760","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}
Fish identification is a challenge to recreational anglers, but critically important to the management of fisheries. The state of Louisiana currently provides printed illustrations of species as the sole aid to anglers for the process of fish identification. This work describes the application of Google's TensorFlow machine learning library to the task of fish identification as a case study on the application of the image classification capabilities. We describe the implementation and results of the project.
{"title":"An Application of Image Classification to Saltwater Fish Identification in Louisiana Fisheries","authors":"Nibha Manandhar, John W. Burris","doi":"10.1145/3325917.3325934","DOIUrl":"https://doi.org/10.1145/3325917.3325934","url":null,"abstract":"Fish identification is a challenge to recreational anglers, but critically important to the management of fisheries. The state of Louisiana currently provides printed illustrations of species as the sole aid to anglers for the process of fish identification. This work describes the application of Google's TensorFlow machine learning library to the task of fish identification as a case study on the application of the image classification capabilities. We describe the implementation and results of the project.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128388744","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}
The concept, Knowledge Management (KM) visualizes the accessibility of the knowledge created by an organization by those who need it. It deals with both the Explicit (i.e. Documented) and Implicit (i.e. engrained in human minds as skills, thoughts, ethics etc) types of knowledge. KM though finds its usability and applicability in all types of organizations, but as witnessed from the literature, it is mostly found operational in business organizations. An overview of the literature available on Knowledge Management (KM) and Knowledge Management System (KMS) clearly shows certain research and development trends, the study of which is the primary focus of the present paper, that precisely appertains to the conceptual development of KM, KMS, KM Models, KM Tools, and KMS in Profit making and Non-profit making organizations.
{"title":"Research Trends in Knowledge Management: Past, Present and Future","authors":"Shabahat Husain, Rumman Gul","doi":"10.1145/3325917.3325949","DOIUrl":"https://doi.org/10.1145/3325917.3325949","url":null,"abstract":"The concept, Knowledge Management (KM) visualizes the accessibility of the knowledge created by an organization by those who need it. It deals with both the Explicit (i.e. Documented) and Implicit (i.e. engrained in human minds as skills, thoughts, ethics etc) types of knowledge. KM though finds its usability and applicability in all types of organizations, but as witnessed from the literature, it is mostly found operational in business organizations. An overview of the literature available on Knowledge Management (KM) and Knowledge Management System (KMS) clearly shows certain research and development trends, the study of which is the primary focus of the present paper, that precisely appertains to the conceptual development of KM, KMS, KM Models, KM Tools, and KMS in Profit making and Non-profit making organizations.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132350496","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}
Charles T. Soini, Sofiane Fellah, Muhammad R. Abid
The citrus greening infection detection algorithm is performed via computer vision techniques and deep learning for the purpose of extracting sub-images of fruit from a tree image and using a trained machine learning function to determine if the fruit shows signs of a citrus greening infection disease called Huanglongbing. We trained our deep learning inception model with 4000 iterations and achieved validation accuracy 93.3%. The computer vision fruit sub-image extraction resulted in at worst around 80% accuracy in tree images and was manually calibrated to detect a specific range of orange color values.
{"title":"Citrus Greening Infection Detection (CiGID) by Computer Vision and Deep Learning","authors":"Charles T. Soini, Sofiane Fellah, Muhammad R. Abid","doi":"10.1145/3325917.3325936","DOIUrl":"https://doi.org/10.1145/3325917.3325936","url":null,"abstract":"The citrus greening infection detection algorithm is performed via computer vision techniques and deep learning for the purpose of extracting sub-images of fruit from a tree image and using a trained machine learning function to determine if the fruit shows signs of a citrus greening infection disease called Huanglongbing. We trained our deep learning inception model with 4000 iterations and achieved validation accuracy 93.3%. The computer vision fruit sub-image extraction resulted in at worst around 80% accuracy in tree images and was manually calibrated to detect a specific range of orange color values.","PeriodicalId":249061,"journal":{"name":"Proceedings of the 2019 3rd International Conference on Information System and Data Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130452914","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：