Pub Date : 2019-12-01DOI: 10.1109/ICMLA.2019.00155
Akhil Mathur, Anton Isopoussu, F. Kawsar, N. Bianchi-Berthouze, N. Lane
Unsupervised domain adaptation is emerging as a powerful technique to improve the generalizability of deep learning models to new image domains without using any labeled data in the target domain. In the literature, solutions which perform cross-domain feature-matching (e.g., ADDA), pixel-matching (CycleGAN), and combination of the two (e.g., CyCADA) have been proposed for unsupervised domain adaptation. Many of these approaches make a strong assumption that the source and target label spaces are the same, however in the real-world, this assumption does not hold true. In this paper, we propose a novel solution, FlexAdapt, which extends the state-of-the-art unsupervised domain adaptation approach of CyCADA to scenarios where the label spaces in source and target domains are only partially overlapped. Our solution beats a number of state-of-the-art baseline approaches by as much as 29% in some scenarios, and represent a way forward for applying domain adaptation techniques in the real world.
{"title":"FlexAdapt: Flexible Cycle-Consistent Adversarial Domain Adaptation","authors":"Akhil Mathur, Anton Isopoussu, F. Kawsar, N. Bianchi-Berthouze, N. Lane","doi":"10.1109/ICMLA.2019.00155","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00155","url":null,"abstract":"Unsupervised domain adaptation is emerging as a powerful technique to improve the generalizability of deep learning models to new image domains without using any labeled data in the target domain. In the literature, solutions which perform cross-domain feature-matching (e.g., ADDA), pixel-matching (CycleGAN), and combination of the two (e.g., CyCADA) have been proposed for unsupervised domain adaptation. Many of these approaches make a strong assumption that the source and target label spaces are the same, however in the real-world, this assumption does not hold true. In this paper, we propose a novel solution, FlexAdapt, which extends the state-of-the-art unsupervised domain adaptation approach of CyCADA to scenarios where the label spaces in source and target domains are only partially overlapped. Our solution beats a number of state-of-the-art baseline approaches by as much as 29% in some scenarios, and represent a way forward for applying domain adaptation techniques in the real world.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131333586","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00193
S. Nõmm, Alejandro Guerra-Manzanares, Hayretdin Bahsi
The analysis of the interplay between the feature selection and the post-hoc local interpretation steps in a machine learning workflow followed for IoT botnet detection constitutes the research scope of the present paper. While the application of machine learning-based techniques has become a trend in cyber security, the main focus has been almost on detection accuracy. However, providing the relevant explanation for a detection decision is a vital requirement in a tiered incident handling processes of the contemporary security operations centers. Moreover, the design of intrusion detection systems in IoT networks has to take the limitations of the computational resources into consideration. Therefore, resource limitations in addition to human element of incident handling necessitate considering feature selection and interpretability at the same time in machine learning workflows. In this paper, first, we analyzed the selection of features and its implication on the data accuracy. Second, we investigated the impact of feature selection on the explanations generated at the post-hoc interpretation phase. We utilized a filter method, Fisher's Score and Local Interpretable Model-Agnostic Explanation (LIME) at feature selection and post-hoc interpretation phases, respectively. To evaluate the quality of explanations, we proposed a metric that reflects the need of the security analysts. It is demonstrated that the application of both steps for the particular case of IoT botnet detection may result in highly accurate and interpretable learning models induced by fewer features. Our metric enables us to evaluate the detection accuracy and interpretability in an integrated way.
{"title":"Towards the Integration of a Post-Hoc Interpretation Step into the Machine Learning Workflow for IoT Botnet Detection","authors":"S. Nõmm, Alejandro Guerra-Manzanares, Hayretdin Bahsi","doi":"10.1109/ICMLA.2019.00193","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00193","url":null,"abstract":"The analysis of the interplay between the feature selection and the post-hoc local interpretation steps in a machine learning workflow followed for IoT botnet detection constitutes the research scope of the present paper. While the application of machine learning-based techniques has become a trend in cyber security, the main focus has been almost on detection accuracy. However, providing the relevant explanation for a detection decision is a vital requirement in a tiered incident handling processes of the contemporary security operations centers. Moreover, the design of intrusion detection systems in IoT networks has to take the limitations of the computational resources into consideration. Therefore, resource limitations in addition to human element of incident handling necessitate considering feature selection and interpretability at the same time in machine learning workflows. In this paper, first, we analyzed the selection of features and its implication on the data accuracy. Second, we investigated the impact of feature selection on the explanations generated at the post-hoc interpretation phase. We utilized a filter method, Fisher's Score and Local Interpretable Model-Agnostic Explanation (LIME) at feature selection and post-hoc interpretation phases, respectively. To evaluate the quality of explanations, we proposed a metric that reflects the need of the security analysts. It is demonstrated that the application of both steps for the particular case of IoT botnet detection may result in highly accurate and interpretable learning models induced by fewer features. Our metric enables us to evaluate the detection accuracy and interpretability in an integrated way.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"59 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131922812","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00212
Mayra Alexandra Macas Carrasco, Chunming Wu
Current Cyber-Physical Systems (CPSs) are sophisticated, complex, and equipped with networked sensors and actuators. As such, they have become further exposed to cyber-attacks. Recent catastrophic events have demonstrated that standard, human-based management of anomaly detection in complex systems is not efficient enough and have underlined the significance of automated detection, intelligent and rapid response. Nevertheless, existing anomaly detection frameworks usually are not capable of dealing with the dynamic and complicated nature of the CPSs. In this study, we introduce an unsupervised framework for anomaly detection based on an Attention-based Spatio-Temporal Autoencoder. In particular, we first construct statistical correlation matrices to characterize the system status across different time steps. Next, a 2D convolutional encoder is employed to encode the patterns of the correlation matrices, whereas an Attention-based Convolutional LSTM Encoder-Decoder (ConvLSTM-ED) is used to capture the temporal dependencies. More precisely, we introduce an input attention mechanism to adaptively select the most significant input features at each time step. Finally, the 2D convolutional decoder reconstructs the correlation matrices. The differences between the reconstructed correlation matrices and the original ones are used as indicators of anomalies. Extensive experimental analysis on data collected from all six stages of Secure Water Treatment (SWaT) testbed, a scaled-down version of a real-world industrial water treatment plant, demonstrates that the proposed model outperforms the state-of-the-art baseline techniques.
{"title":"An Unsupervised Framework for Anomaly Detection in a Water Treatment System","authors":"Mayra Alexandra Macas Carrasco, Chunming Wu","doi":"10.1109/ICMLA.2019.00212","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00212","url":null,"abstract":"Current Cyber-Physical Systems (CPSs) are sophisticated, complex, and equipped with networked sensors and actuators. As such, they have become further exposed to cyber-attacks. Recent catastrophic events have demonstrated that standard, human-based management of anomaly detection in complex systems is not efficient enough and have underlined the significance of automated detection, intelligent and rapid response. Nevertheless, existing anomaly detection frameworks usually are not capable of dealing with the dynamic and complicated nature of the CPSs. In this study, we introduce an unsupervised framework for anomaly detection based on an Attention-based Spatio-Temporal Autoencoder. In particular, we first construct statistical correlation matrices to characterize the system status across different time steps. Next, a 2D convolutional encoder is employed to encode the patterns of the correlation matrices, whereas an Attention-based Convolutional LSTM Encoder-Decoder (ConvLSTM-ED) is used to capture the temporal dependencies. More precisely, we introduce an input attention mechanism to adaptively select the most significant input features at each time step. Finally, the 2D convolutional decoder reconstructs the correlation matrices. The differences between the reconstructed correlation matrices and the original ones are used as indicators of anomalies. Extensive experimental analysis on data collected from all six stages of Secure Water Treatment (SWaT) testbed, a scaled-down version of a real-world industrial water treatment plant, demonstrates that the proposed model outperforms the state-of-the-art baseline techniques.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132605923","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00293
Azim Ahmadzadeh, Berkay Aydin, Dustin J. Kempton, Maxwell Hostetter, R. Angryk, M. Georgoulis, Sushant S. Mahajan
We present a case study for time series prediction models in extreme class-imbalance problems. We have extracted multiple properties from the Space Weather ANalytics for Solar Flares (SWAN-SF) benchmark dataset which comprises of magnetic features from over 4075 active regions over a period of 9 years to create the forecasting dataset used in this study. In the extracted dataset, the class-imbalance ratio is 1:60, where the minority class is formed by instances of strong solar flares (GOES M-and X-class). This ratio reaches to 1:800 if we only consider the strongest class of flares (GOES X-class). This case of extreme imbalance, along with the temporal coherence of the sliced time series, provides us with an interesting set of challenges in the forecasting of scarce real-life phenomena. We have explored remedies to tackle the class-imbalance issue such as undersampling, oversampling and misclassification weights. In the process, we elaborate on common mistakes and pitfalls caused by ignoring the side effects of these remedies, including how and why they weaken the robustness of the trained models while seemingly improving the performance.
{"title":"Rare-Event Time Series Prediction: A Case Study of Solar Flare Forecasting","authors":"Azim Ahmadzadeh, Berkay Aydin, Dustin J. Kempton, Maxwell Hostetter, R. Angryk, M. Georgoulis, Sushant S. Mahajan","doi":"10.1109/ICMLA.2019.00293","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00293","url":null,"abstract":"We present a case study for time series prediction models in extreme class-imbalance problems. We have extracted multiple properties from the Space Weather ANalytics for Solar Flares (SWAN-SF) benchmark dataset which comprises of magnetic features from over 4075 active regions over a period of 9 years to create the forecasting dataset used in this study. In the extracted dataset, the class-imbalance ratio is 1:60, where the minority class is formed by instances of strong solar flares (GOES M-and X-class). This ratio reaches to 1:800 if we only consider the strongest class of flares (GOES X-class). This case of extreme imbalance, along with the temporal coherence of the sliced time series, provides us with an interesting set of challenges in the forecasting of scarce real-life phenomena. We have explored remedies to tackle the class-imbalance issue such as undersampling, oversampling and misclassification weights. In the process, we elaborate on common mistakes and pitfalls caused by ignoring the side effects of these remedies, including how and why they weaken the robustness of the trained models while seemingly improving the performance.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130779122","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00135
Aaron N. Richter, T. Khoshgoftaar
Datasets for machine learning are constantly increasing in size, along with computational requirements for processing the data. A useful exercise for machine learning experiments is to approximate model performance as dataset size increases. This can inform application building and data collection efforts as well as improve computational efficiency by using subsets of the data. In this paper, we evaluate a learning curve estimation method on three large imbalanced datasets. Estimation is performed by fitting an inverse power law model to a learning curve created on a small amount of data. We then explore how well this estimated curve fits to the full learning curve of each dataset. The method has been previously evaluated for small datasets (hundreds or thousands of instances), and in this study we show that the method is indeed effective for larger datasets with millions of instances. This is beneficial because only a few thousand instances are required to accurately estimate the performance of models using millions of instances. To the best of our knowledge, this is the first study to systematically explore the use of an inverse power law curve fitting method for big data.
{"title":"Learning Curve Estimation with Large Imbalanced Datasets","authors":"Aaron N. Richter, T. Khoshgoftaar","doi":"10.1109/ICMLA.2019.00135","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00135","url":null,"abstract":"Datasets for machine learning are constantly increasing in size, along with computational requirements for processing the data. A useful exercise for machine learning experiments is to approximate model performance as dataset size increases. This can inform application building and data collection efforts as well as improve computational efficiency by using subsets of the data. In this paper, we evaluate a learning curve estimation method on three large imbalanced datasets. Estimation is performed by fitting an inverse power law model to a learning curve created on a small amount of data. We then explore how well this estimated curve fits to the full learning curve of each dataset. The method has been previously evaluated for small datasets (hundreds or thousands of instances), and in this study we show that the method is indeed effective for larger datasets with millions of instances. This is beneficial because only a few thousand instances are required to accurately estimate the performance of models using millions of instances. To the best of our knowledge, this is the first study to systematically explore the use of an inverse power law curve fitting method for big data.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131020403","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00228
Jingjing Wang, Fei Song, Kavita Walia, Jeffery Farber, R. Dara
Keywords and keyphrases are important for Natural Language Processing (NLP) applications such as document classification, information retrieval, and topic identification. They are also useful for capturing different classes of entities from content related to healthcare, biology, food science, and journalism fields. There are different approaches to extract keywords and keyphrases. Deep learning approaches have achieved high-performance results in terms of keywords and keyphrase extraction. However, among deep learning approaches, Convolutional Neural Network (CNN) potentials have not been fully explored as a technique for extracting keywords and keyphrases. In this work, we performed a comparative study using a benchmark dataset, the IEEE Xplore collection to test the CNN generalization ability in selecting keywords and keyphrases. In addition, we further collected a corpus in the field of foodborne illness outbreaks. We utilize this corpus to develop a CNN-based identification approach of keywords and keyphrases related to foodborne illnesses. Results were compared with several supervised (KEA, GuidedLDA) and unsupervised (LDA) machine learning algorithms. CNN outperformed these algorithms in selecting relevant keywords and keyphrases for foodborne illnesses. The findings of this study have also confirmed superiority of CNN-based algorithm for keyphrase extraction to other machine learning approaches.
{"title":"Using Convolutional Neural Networks to Extract Keywords and Keyphrases: A Case Study for Foodborne Illnesses","authors":"Jingjing Wang, Fei Song, Kavita Walia, Jeffery Farber, R. Dara","doi":"10.1109/ICMLA.2019.00228","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00228","url":null,"abstract":"Keywords and keyphrases are important for Natural Language Processing (NLP) applications such as document classification, information retrieval, and topic identification. They are also useful for capturing different classes of entities from content related to healthcare, biology, food science, and journalism fields. There are different approaches to extract keywords and keyphrases. Deep learning approaches have achieved high-performance results in terms of keywords and keyphrase extraction. However, among deep learning approaches, Convolutional Neural Network (CNN) potentials have not been fully explored as a technique for extracting keywords and keyphrases. In this work, we performed a comparative study using a benchmark dataset, the IEEE Xplore collection to test the CNN generalization ability in selecting keywords and keyphrases. In addition, we further collected a corpus in the field of foodborne illness outbreaks. We utilize this corpus to develop a CNN-based identification approach of keywords and keyphrases related to foodborne illnesses. Results were compared with several supervised (KEA, GuidedLDA) and unsupervised (LDA) machine learning algorithms. CNN outperformed these algorithms in selecting relevant keywords and keyphrases for foodborne illnesses. The findings of this study have also confirmed superiority of CNN-based algorithm for keyphrase extraction to other machine learning approaches.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127805578","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00227
Charalampos Karyotis, Tomasz Maniak, F. Doctor, R. Iqbal, V. Palade, Raymond Tang
This paper describes the core computational mechanisms used by an urban flood forecasting and monitoring platform developed as part of a UK Newton Fund project in Malaysia. FLUD-FLood monitoring and forecasting platform for Urban Deployment - is a novel system aiming to deliver an effective and low cost urban flood forecasting solution, which is able to accurately forecast flood risk at street level, and deliver optimized recommendations to the relevant authorities as well as an early warning alerts to members of the public. This platform is based on a hybrid Deep Learning and Fuzzy Logic based architecture. As demonstrated by the experimental results and the analysis presented in this paper, this architecture enables the proposed system to account for factors that are not included in other modern flood forecasting systems, and simultaneously process high volumes of data originating from diverse data sources, in order to deliver accurate predictions concerning urban flood events
{"title":"Deep Learning for Flood Forecasting and Monitoring in Urban Environments","authors":"Charalampos Karyotis, Tomasz Maniak, F. Doctor, R. Iqbal, V. Palade, Raymond Tang","doi":"10.1109/ICMLA.2019.00227","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00227","url":null,"abstract":"This paper describes the core computational mechanisms used by an urban flood forecasting and monitoring platform developed as part of a UK Newton Fund project in Malaysia. FLUD-FLood monitoring and forecasting platform for Urban Deployment - is a novel system aiming to deliver an effective and low cost urban flood forecasting solution, which is able to accurately forecast flood risk at street level, and deliver optimized recommendations to the relevant authorities as well as an early warning alerts to members of the public. This platform is based on a hybrid Deep Learning and Fuzzy Logic based architecture. As demonstrated by the experimental results and the analysis presented in this paper, this architecture enables the proposed system to account for factors that are not included in other modern flood forecasting systems, and simultaneously process high volumes of data originating from diverse data sources, in order to deliver accurate predictions concerning urban flood events","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134487447","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00053
R. Filipe, Filipe Araújo
Large online web sites are supported in the back-end by a cluster of servers behind a load balancer. Ensuring proper operation of the cluster with minimal monitoring efforts from the load balancer is necessary to ensure performance. Previous monitoring efforts require extensive data from the system and fail to include the client perspective. We monitor the cluster using machine learning techniques that process data collected and uploaded by web clients, an approach that might complement system-side information. To experiment our solution, we trained the machine learning algorithms in a cluster of 10 machines with a load balancer and evaluated the results of these algorithms when one of the machines is overloaded. While a fine-grained view of the state of the machines, may require much effort to accomplish, given the compensation effect of the remaining healthy machines, the results show that we can achieve a coarse grained view of the entire system, to produce relevant insight about the cluster.
{"title":"Client-Side Monitoring of HTTP Clusters Using Machine Learning Techniques","authors":"R. Filipe, Filipe Araújo","doi":"10.1109/ICMLA.2019.00053","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00053","url":null,"abstract":"Large online web sites are supported in the back-end by a cluster of servers behind a load balancer. Ensuring proper operation of the cluster with minimal monitoring efforts from the load balancer is necessary to ensure performance. Previous monitoring efforts require extensive data from the system and fail to include the client perspective. We monitor the cluster using machine learning techniques that process data collected and uploaded by web clients, an approach that might complement system-side information. To experiment our solution, we trained the machine learning algorithms in a cluster of 10 machines with a load balancer and evaluated the results of these algorithms when one of the machines is overloaded. While a fine-grained view of the state of the machines, may require much effort to accomplish, given the compensation effect of the remaining healthy machines, the results show that we can achieve a coarse grained view of the entire system, to produce relevant insight about the cluster.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"461 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115868550","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00024
D. Lakmal, Kumaran Kugathasan, V. Nanayakkara, S. Jayasena, Amal Perera, Lasantha Fernando
Every year paddy cultivators lose a significant amount of crop yield due to diseases and pests. Brown Planthopper (BPH) is one of the most common diseases that affect paddy cultivation. Sri Lankan government is struggling to make appropriate estimations regarding Brown Planthopper prevalence due to the absence of accurate and timely data. To solve this issue, a machine learning approach is proposed based on optical and synthetic aperture radar remote sensing data in this study. However, there is no previous effort for detecting Brown Planthopper attacks using machine learning and satellite remote sensing data under field conditions. This study consists of two phases. A time series classification based on SAR imagery is implemented to identify cultivated paddy fields in the first phase. Ratio and standard difference indices derived from optical satellite images are used in the second phase to identify regions affected by BPH attacks in paddy fields. Convolution neural network that is used in the first phase reports an accuracy of 96.20% for identifying cultivated paddy regions. A Support Vector Machine is used to detect areas damaged by BPH attacks in the second phase. The Combined approach of the first and the second phases shows promising results with an accuracy of 96.31% for detecting Brown Planthopper attacks.
{"title":"Brown Planthopper Damage Detection using Remote Sensing and Machine Learning","authors":"D. Lakmal, Kumaran Kugathasan, V. Nanayakkara, S. Jayasena, Amal Perera, Lasantha Fernando","doi":"10.1109/ICMLA.2019.00024","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00024","url":null,"abstract":"Every year paddy cultivators lose a significant amount of crop yield due to diseases and pests. Brown Planthopper (BPH) is one of the most common diseases that affect paddy cultivation. Sri Lankan government is struggling to make appropriate estimations regarding Brown Planthopper prevalence due to the absence of accurate and timely data. To solve this issue, a machine learning approach is proposed based on optical and synthetic aperture radar remote sensing data in this study. However, there is no previous effort for detecting Brown Planthopper attacks using machine learning and satellite remote sensing data under field conditions. This study consists of two phases. A time series classification based on SAR imagery is implemented to identify cultivated paddy fields in the first phase. Ratio and standard difference indices derived from optical satellite images are used in the second phase to identify regions affected by BPH attacks in paddy fields. Convolution neural network that is used in the first phase reports an accuracy of 96.20% for identifying cultivated paddy regions. A Support Vector Machine is used to detect areas damaged by BPH attacks in the second phase. The Combined approach of the first and the second phases shows promising results with an accuracy of 96.31% for detecting Brown Planthopper attacks.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123429922","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 : 2019-12-01DOI: 10.1109/ICMLA.2019.00101
Gaddiel Desirena, Armando Diaz, Jalil Desirena, Ismael Moreno, Daniel Garcia
This paper proposes a recommender system based on two-stage neural network architecture that maximizes Customer Lifetime Value (CLV). The Stage-I neural network uses a self-attention mechanism and a Collaborative Metric Learning (CML) to generate product recommendations. The Stage-II neural network uses a neural network-based survival analysis to infer insurance product recommendations that maximize customer lifetime. The proposed stacked neural network model can be used as a generative model to explore different cross-sell scenarios. The applicability of the proposed recommendation system is evaluated using transactional data from an Australian insurance company. We validated our results against a state of the art self-attention recommendation system, successfully extending its functionality to include lifetime value.
{"title":"Maximizing Customer Lifetime Value using Stacked Neural Networks: An Insurance Industry Application","authors":"Gaddiel Desirena, Armando Diaz, Jalil Desirena, Ismael Moreno, Daniel Garcia","doi":"10.1109/ICMLA.2019.00101","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00101","url":null,"abstract":"This paper proposes a recommender system based on two-stage neural network architecture that maximizes Customer Lifetime Value (CLV). The Stage-I neural network uses a self-attention mechanism and a Collaborative Metric Learning (CML) to generate product recommendations. The Stage-II neural network uses a neural network-based survival analysis to infer insurance product recommendations that maximize customer lifetime. The proposed stacked neural network model can be used as a generative model to explore different cross-sell scenarios. The applicability of the proposed recommendation system is evaluated using transactional data from an Australian insurance company. We validated our results against a state of the art self-attention recommendation system, successfully extending its functionality to include lifetime value.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123653629","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：