Pub Date : 2019-12-01DOI: 10.1109/ICMLA.2019.00110
Ryoya Yamasaki, Toshiyuki Tanaka
Modal linear regression (MLR) is a method for obtaining a conditional mode predictor as a linear model. We study kernel selection for MLR from two perspectives: "which kernel achieves smaller error?" and "which kernel is computationally efficient?". First, we show that a Biweight kernel is optimal in the sense of minimizing an asymptotic mean squared error of a resulting MLR parameter. This result is derived from our refined analysis of an asymptotic statistical behavior of MLR. Secondly, we provide a kernel class for which iteratively reweighted least-squares algorithm (IRLS) is guaranteed to converge, and especially prove that IRLS with an Epanechnikov kernel terminates in a finite number of iterations. Simulation studies empirically verified that using a Biweight kernel provides good estimation accuracy and that using an Epanechnikov kernel is computationally efficient. Our results improve MLR of which existing studies often stick to a Gaussian kernel and modal EM algorithm specialized for it, by providing guidelines of kernel selection.
{"title":"Kernel Selection for Modal Linear Regression: Optimal Kernel and IRLS Algorithm","authors":"Ryoya Yamasaki, Toshiyuki Tanaka","doi":"10.1109/ICMLA.2019.00110","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00110","url":null,"abstract":"Modal linear regression (MLR) is a method for obtaining a conditional mode predictor as a linear model. We study kernel selection for MLR from two perspectives: \"which kernel achieves smaller error?\" and \"which kernel is computationally efficient?\". First, we show that a Biweight kernel is optimal in the sense of minimizing an asymptotic mean squared error of a resulting MLR parameter. This result is derived from our refined analysis of an asymptotic statistical behavior of MLR. Secondly, we provide a kernel class for which iteratively reweighted least-squares algorithm (IRLS) is guaranteed to converge, and especially prove that IRLS with an Epanechnikov kernel terminates in a finite number of iterations. Simulation studies empirically verified that using a Biweight kernel provides good estimation accuracy and that using an Epanechnikov kernel is computationally efficient. Our results improve MLR of which existing studies often stick to a Gaussian kernel and modal EM algorithm specialized for it, by providing guidelines of kernel selection.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"11 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":"130355785","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.2019.00305
G. Delaney, D. Howard, K. D. Napoli
Granular materials, such as sands, soils, grains and powders, are ubiquitous in both natural and artificial systems. They are core to many industrial systems from mining and food production to pharmaceuticals and construction. Granular media display unique properties, including their ability to flow like a liquid at low densities and jam in to a solid state at high densities. Granular materials are used functionally in a number of industrial systems, where for example their insulating, energy absorption, filtration or vibration damping properties are variously exploited. A recent emerging industrial application is to utilise the jamming transition of granular matter (transition from a sold to a liquid) to create functional jammed systems such as universal grippers or soft robotic devices with potential broad impact across many industrial sectors. However, controlling the microscopic properties of such systems to elicit bespoke functional granular systems remains challenging due to the complex relationship between the individual particle morphologies and the related emergent behaviour of the bulk state. Here, we investigate the use of evolution to explore the functional landscapes of granular systems. We employ a superellipsoid representation of the particle shape which allows us to smoothly transition between a large variety of particle aspect ratios and angularities, and investigate the use of multi-component systems alongside homogenous granular arrangements. Results show the ability to successfully characterise a sample design space, and represents an important step towards the creation of bespoke jammed systems with a range of practical applications across broad swathes of industry.
{"title":"Utilising Evolutionary Algorithms to Design Granular Materials for Industrial Applications","authors":"G. Delaney, D. Howard, K. D. Napoli","doi":"10.1109/ICMLA.2019.00305","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00305","url":null,"abstract":"Granular materials, such as sands, soils, grains and powders, are ubiquitous in both natural and artificial systems. They are core to many industrial systems from mining and food production to pharmaceuticals and construction. Granular media display unique properties, including their ability to flow like a liquid at low densities and jam in to a solid state at high densities. Granular materials are used functionally in a number of industrial systems, where for example their insulating, energy absorption, filtration or vibration damping properties are variously exploited. A recent emerging industrial application is to utilise the jamming transition of granular matter (transition from a sold to a liquid) to create functional jammed systems such as universal grippers or soft robotic devices with potential broad impact across many industrial sectors. However, controlling the microscopic properties of such systems to elicit bespoke functional granular systems remains challenging due to the complex relationship between the individual particle morphologies and the related emergent behaviour of the bulk state. Here, we investigate the use of evolution to explore the functional landscapes of granular systems. We employ a superellipsoid representation of the particle shape which allows us to smoothly transition between a large variety of particle aspect ratios and angularities, and investigate the use of multi-component systems alongside homogenous granular arrangements. Results show the ability to successfully characterise a sample design space, and represents an important step towards the creation of bespoke jammed systems with a range of practical applications across broad swathes of industry.","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":"129538419","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.2019.00098
Sayan Chakraborty, Smit Shah, Kiumars Soltani, A. Swigart
The recent increase in the scale and complexity of software systems has introduced new challenges to the time series monitoring and anomaly detection process. A major drawback of existing anomaly detection methods is that they lack contextual information to help stakeholders identify the cause of anomalies. This problem, known as root cause detection, is particularly challenging to undertake in today's complex distributed software systems since the metrics under consideration generally have multiple internal and external dependencies. Significant manual analysis and strong domain expertise is required to isolate the correct cause of the problem. In this paper, we propose a method that isolates the root cause of an anomaly by analyzing the patterns in time series fluctuations. Our method considers the time series as observations from an underlying process passing through a sequence of discretized hidden states. The idea is to track the propagation of the effect when a given problem causes unaligned but homogeneous shifts of the underlying states. We evaluate our approach by finding the root cause of anomalies in Zillow's clickstream data by identifying causal patterns among a set of observed fluctuations.
{"title":"Root Cause Detection Among Anomalous Time Series Using Temporal State Alignment","authors":"Sayan Chakraborty, Smit Shah, Kiumars Soltani, A. Swigart","doi":"10.1109/ICMLA.2019.00098","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00098","url":null,"abstract":"The recent increase in the scale and complexity of software systems has introduced new challenges to the time series monitoring and anomaly detection process. A major drawback of existing anomaly detection methods is that they lack contextual information to help stakeholders identify the cause of anomalies. This problem, known as root cause detection, is particularly challenging to undertake in today's complex distributed software systems since the metrics under consideration generally have multiple internal and external dependencies. Significant manual analysis and strong domain expertise is required to isolate the correct cause of the problem. In this paper, we propose a method that isolates the root cause of an anomaly by analyzing the patterns in time series fluctuations. Our method considers the time series as observations from an underlying process passing through a sequence of discretized hidden states. The idea is to track the propagation of the effect when a given problem causes unaligned but homogeneous shifts of the underlying states. We evaluate our approach by finding the root cause of anomalies in Zillow's clickstream data by identifying causal patterns among a set of observed fluctuations.","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":"129698002","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.2019.00022
Piyush Yadav, D. Das, E. Curry
Modelling complex events in unstructured data like videos not only requires detecting objects but also the spatiotemporal relationships among objects. Complex Event Processing (CEP) systems discretize continuous streams into fixed batches using windows and apply operators over these batches to detect patterns in real-time. To this end, we apply CEP techniques over video streams to identify spatiotemporal patterns by capturing window state. This work introduces a novel problem where an input video stream is converted to a stream of graphs which are aggregated to a single graph over a given state. Incoming video frames are converted to a timestamped Video Event Knowledge Graph (VEKG) [1] that maps objects to nodes and captures spatiotemporal relationships among object nodes. Objects coexist across multiple frames which leads to the creation of redundant nodes and edges at different time instances that results in high memory usage. There is a need for expressive and storage efficient graph model which can summarize graph streams in a single view. We propose Event Aggregated Graph (EAG), a summarized graph representation of VEKG streams over a given state. EAG captures different spatiotemporal relationships among objects using an Event Adjacency Matrix without replicating the nodes and edges across time instances. These enable the CEP system to process multiple continuous queries and perform frequent spatiotemporal pattern matching computations over a single summarised graph. Initial experiments show EAG takes 68.35% and 28.9% less space compared to baseline and state of the art graph summarization method respectively. EAG takes 5X less search time to detect pattern as compare to VEKG stream.
{"title":"State Summarization of Video Streams for Spatiotemporal Query Matching in Complex Event Processing","authors":"Piyush Yadav, D. Das, E. Curry","doi":"10.1109/ICMLA.2019.00022","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00022","url":null,"abstract":"Modelling complex events in unstructured data like videos not only requires detecting objects but also the spatiotemporal relationships among objects. Complex Event Processing (CEP) systems discretize continuous streams into fixed batches using windows and apply operators over these batches to detect patterns in real-time. To this end, we apply CEP techniques over video streams to identify spatiotemporal patterns by capturing window state. This work introduces a novel problem where an input video stream is converted to a stream of graphs which are aggregated to a single graph over a given state. Incoming video frames are converted to a timestamped Video Event Knowledge Graph (VEKG) [1] that maps objects to nodes and captures spatiotemporal relationships among object nodes. Objects coexist across multiple frames which leads to the creation of redundant nodes and edges at different time instances that results in high memory usage. There is a need for expressive and storage efficient graph model which can summarize graph streams in a single view. We propose Event Aggregated Graph (EAG), a summarized graph representation of VEKG streams over a given state. EAG captures different spatiotemporal relationships among objects using an Event Adjacency Matrix without replicating the nodes and edges across time instances. These enable the CEP system to process multiple continuous queries and perform frequent spatiotemporal pattern matching computations over a single summarised graph. Initial experiments show EAG takes 68.35% and 28.9% less space compared to baseline and state of the art graph summarization method respectively. EAG takes 5X less search time to detect pattern as compare to VEKG stream.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"52 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":"134428951","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.2019.00010
Xinjie Lan, K. Barner
In order to reduce overfitting for the image recognition application, this paper proposes a novel regularization learning algorithm for deep learning. Above all, we propose a novel probabilistic representation for explaining the architecture of Deep Neural Networks (DNNs), which demonstrates that the hidden layers close to the input formulate prior distributions, thus DNNs have an explicit regularization, namely the prior distributions. Furthermore, we show that the backpropagation learning algorithm is the reason for overfitting because it cannot guarantee precisely learning the prior distribution. Based on the proposed theoretical explanation for deep learning, we propose a novel regularization learning algorithm for DNNs. In contrast to most existing regularization methods reducing overfitting by decreasing the training complexity of DNNs, the proposed method reduces overfitting through training the corresponding prior distribution in a more efficient way, thereby deriving a more powerful regularization. Simulations demonstrate the proposed probabilistic representation on a synthetic dataset and validate the proposed regularization on the CIFAR-10 dataset.
{"title":"Regularization Learning for Image Recognition","authors":"Xinjie Lan, K. Barner","doi":"10.1109/ICMLA.2019.00010","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00010","url":null,"abstract":"In order to reduce overfitting for the image recognition application, this paper proposes a novel regularization learning algorithm for deep learning. Above all, we propose a novel probabilistic representation for explaining the architecture of Deep Neural Networks (DNNs), which demonstrates that the hidden layers close to the input formulate prior distributions, thus DNNs have an explicit regularization, namely the prior distributions. Furthermore, we show that the backpropagation learning algorithm is the reason for overfitting because it cannot guarantee precisely learning the prior distribution. Based on the proposed theoretical explanation for deep learning, we propose a novel regularization learning algorithm for DNNs. In contrast to most existing regularization methods reducing overfitting by decreasing the training complexity of DNNs, the proposed method reduces overfitting through training the corresponding prior distribution in a more efficient way, thereby deriving a more powerful regularization. Simulations demonstrate the proposed probabilistic representation on a synthetic dataset and validate the proposed regularization on the CIFAR-10 dataset.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"25 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":"134555506","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.2019.00313
Fabian Fallas-Moya, Manfred Gonzalez-Hernandez, L. Barboza-Barquero, Kenneth Obando, Ovidio Valerio, Andrea Holst, Ronald Arias
Circadian rhythm regulates many biological processes. In plants, it controls the expression of genes related to growth and development. Recently, the usage of digital image analysis allows monitoring the circadian rhythm in plants, since the circadian rhythm can be observed by the movement of the leaves of a plant during the day. This is important because it can be used as a growth marker to select plants in plant breeding processes and to conduct fundamental science on this topic. In this work, a new algorithm is proposed to classify sets of coordinates to indicate if they show a circadian rhythm movement. Most algorithms take a set of coordinates and produce plots of the circadian movement, however, some databases have sets of coordinates that must be classified before the movement plots. This research presents an algorithm that determines if a set corresponds to a circadian rhythm movement using statistical analysis of polynomial regressions. Results showed that the proposed algorithm is significantly better compared with a Lagrange interpolation and with a fixed degree approaches. The obtained results suggest that using statistical information from the polynomial regressions can improve results in a classification task of circadian rhythm data.
{"title":"Looking for the Best Fit of a Function over Circadian Rhythm Data","authors":"Fabian Fallas-Moya, Manfred Gonzalez-Hernandez, L. Barboza-Barquero, Kenneth Obando, Ovidio Valerio, Andrea Holst, Ronald Arias","doi":"10.1109/ICMLA.2019.00313","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00313","url":null,"abstract":"Circadian rhythm regulates many biological processes. In plants, it controls the expression of genes related to growth and development. Recently, the usage of digital image analysis allows monitoring the circadian rhythm in plants, since the circadian rhythm can be observed by the movement of the leaves of a plant during the day. This is important because it can be used as a growth marker to select plants in plant breeding processes and to conduct fundamental science on this topic. In this work, a new algorithm is proposed to classify sets of coordinates to indicate if they show a circadian rhythm movement. Most algorithms take a set of coordinates and produce plots of the circadian movement, however, some databases have sets of coordinates that must be classified before the movement plots. This research presents an algorithm that determines if a set corresponds to a circadian rhythm movement using statistical analysis of polynomial regressions. Results showed that the proposed algorithm is significantly better compared with a Lagrange interpolation and with a fixed degree approaches. The obtained results suggest that using statistical information from the polynomial regressions can improve results in a classification task of circadian rhythm data.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"248 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":"132620947","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.2019.00261
Abhijith Ragav, N. H. Krishna, Naveen Narayanan, Kevin Thelly, Vineeth Vijayaraghavan
Psychological stress in human beings has been on a meteoric rise over the last few years. Chronic stress can have fatal consequences such as heart disease, cancer, suicide and so on. It is thus imperative to detect stress early on to prevent health risks. In this work, we discuss efficient and accurate stress and affect detection using scalable Deep Learning methods, that can be used to monitor stress real-time on resource-constrained devices such as low-cost wearables. By making inferences on-device, we solve the issues of high latency and lack of privacy which are prevalent in cloud-based computation. Using the concept of Early Stopping - Multiple Instance Learning, we build specialized models for stress and affect detection for 3 popular datasets in the domain, that have very low inference times but high accuracy. We introduce a metric ηcomp to measure the computational savings from the use of these models. On average, our models show an absolute increase of 10% in overall accuracy over the benchmarks, computational savings of 95.39%, and an 18x reduction in inference times on a Raspberry Pi 3 Model B. This allows for efficient and accurate real-time monitoring of stress on low-cost resource-constrained devices.
在过去的几年里，人类的心理压力一直在迅速上升。慢性压力会导致致命的后果，比如心脏病、癌症、自杀等等。因此，必须及早发现压力，以预防健康风险。在这项工作中，我们讨论了使用可扩展的深度学习方法进行有效和准确的压力和影响检测，该方法可用于实时监测资源受限设备(如低成本可穿戴设备)的压力。通过在设备上进行推断，我们解决了在基于云的计算中普遍存在的高延迟和缺乏隐私的问题。利用早期停止-多实例学习的概念，我们为该领域的3个流行数据集建立了专门的压力和影响检测模型，这些模型具有非常低的推理时间但精度很高。我们引入了一个度量η比较来衡量使用这些模型所节省的计算量。平均而言，我们的模型显示，与基准测试相比，总体精度绝对提高了10%，计算节省了95.39%，在Raspberry Pi 3 Model b上的推理时间减少了18倍。这允许在低成本资源受限的设备上高效、准确地实时监测压力。
{"title":"Scalable Deep Learning for Stress and Affect Detection on Resource-Constrained Devices","authors":"Abhijith Ragav, N. H. Krishna, Naveen Narayanan, Kevin Thelly, Vineeth Vijayaraghavan","doi":"10.1109/ICMLA.2019.00261","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00261","url":null,"abstract":"Psychological stress in human beings has been on a meteoric rise over the last few years. Chronic stress can have fatal consequences such as heart disease, cancer, suicide and so on. It is thus imperative to detect stress early on to prevent health risks. In this work, we discuss efficient and accurate stress and affect detection using scalable Deep Learning methods, that can be used to monitor stress real-time on resource-constrained devices such as low-cost wearables. By making inferences on-device, we solve the issues of high latency and lack of privacy which are prevalent in cloud-based computation. Using the concept of Early Stopping - Multiple Instance Learning, we build specialized models for stress and affect detection for 3 popular datasets in the domain, that have very low inference times but high accuracy. We introduce a metric ηcomp to measure the computational savings from the use of these models. On average, our models show an absolute increase of 10% in overall accuracy over the benchmarks, computational savings of 95.39%, and an 18x reduction in inference times on a Raspberry Pi 3 Model B. This allows for efficient and accurate real-time monitoring of stress on low-cost resource-constrained devices.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"63 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":"115168102","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.2019.00088
S. Sharifi, Sofia Brown, I. Novikova, E. Mikhailov, G. Veronis, J. Dowling, Y. Banadaki, Elisha Siddiqui, Savannah Cuzzo, N. Bhusal, L. Cohen, Austin T. Kalasky, N. Prajapati, Rachel Soto-Garcia
An automated determination of Laguerre-Gaussian (LG) modes benefits cavity tuning and optical communication. In this paper, we employ machine learning techniques to automatically detect the lowest sixteen LG modes of a laser beam. Convolutional neural networks (CNN) are trained by collecting the experimental and simulated datasets of LG modes that relies only on the intensity images of their unique patterns. We demonstrate that the trained CNN model can detect LG modes with the maximum accuracy greater than 96% after 60 epochs. The study evaluates the CNN's ability to generalize to new data and adapt to experimental conditions.
{"title":"Identifying Laguerre-Gaussian Modes using Convolutional Neural Network","authors":"S. Sharifi, Sofia Brown, I. Novikova, E. Mikhailov, G. Veronis, J. Dowling, Y. Banadaki, Elisha Siddiqui, Savannah Cuzzo, N. Bhusal, L. Cohen, Austin T. Kalasky, N. Prajapati, Rachel Soto-Garcia","doi":"10.1109/ICMLA.2019.00088","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00088","url":null,"abstract":"An automated determination of Laguerre-Gaussian (LG) modes benefits cavity tuning and optical communication. In this paper, we employ machine learning techniques to automatically detect the lowest sixteen LG modes of a laser beam. Convolutional neural networks (CNN) are trained by collecting the experimental and simulated datasets of LG modes that relies only on the intensity images of their unique patterns. We demonstrate that the trained CNN model can detect LG modes with the maximum accuracy greater than 96% after 60 epochs. The study evaluates the CNN's ability to generalize to new data and adapt to experimental conditions.","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":"114768197","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.2019.00046
Christopher G. Harris, Y. Trisyono
The brown planthopper (BPH), Nilaparvata lugens (Stål), is a pest responsible for widespread damage to rice plants throughout South, Southeast, and East Asia. It is estimated that 10-30% of yield loss in rice crops is attributable to the BPH. In this paper, we develop a method to detect and classify the forms of BPH using CNNs and then model the infestation migration patterns of BPH in several rice-growing regions by using a CNN-LSTMs learning model. This prediction model considers inputs such as wind speed and direction, humidity, ambient temperature, the use of pesticides, the form of BPH, strain of rice, and spacing between rice seedlings to make predictions on the spread of BPH infestations over time. The detection and classification model outperformed other known BPH classification models, providing accuracy rates of 89.33%. Our prediction model accurately modeled the BPH-affected area 82.65% of the time (as determined by lamp trap counts). These models can help detect, classify, and model the infestations of other agricultural pests, improving food security for rice, the staple crop that 900 million of the world's poor depend on for most of their calorie intake.
{"title":"Classifying, Detecting, and Predicting Infestation Patterns of the Brown Planthopper in Rice Paddies","authors":"Christopher G. Harris, Y. Trisyono","doi":"10.1109/ICMLA.2019.00046","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00046","url":null,"abstract":"The brown planthopper (BPH), Nilaparvata lugens (Stål), is a pest responsible for widespread damage to rice plants throughout South, Southeast, and East Asia. It is estimated that 10-30% of yield loss in rice crops is attributable to the BPH. In this paper, we develop a method to detect and classify the forms of BPH using CNNs and then model the infestation migration patterns of BPH in several rice-growing regions by using a CNN-LSTMs learning model. This prediction model considers inputs such as wind speed and direction, humidity, ambient temperature, the use of pesticides, the form of BPH, strain of rice, and spacing between rice seedlings to make predictions on the spread of BPH infestations over time. The detection and classification model outperformed other known BPH classification models, providing accuracy rates of 89.33%. Our prediction model accurately modeled the BPH-affected area 82.65% of the time (as determined by lamp trap counts). These models can help detect, classify, and model the infestations of other agricultural pests, improving food security for rice, the staple crop that 900 million of the world's poor depend on for most of their calorie intake.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"6 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":"134314860","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.2019.00217
Steven Yen, M. Moh, Teng-Sheng Moh
Computer systems utilize logging to record events of interest. These logs are a rich source of information, and can be analyzed to detect attacks, failures, and many other issues. Due to the automated generation of logs by computer processes, the volume and throughput of logs can be extremely large, limiting the effectiveness of manual analysis. Rule-based systems were introduced to automatically detect issues based on rules written by experts. However, these systems can only detect known issues for which related rules exist in the rule-set. On the other hand, anomaly detection (AD) approaches can detect unknown issues. This is achieved by looking for unusual behaviors significantly different from the norm. In this paper, we target the problem of semi-supervised log anomaly detection, where the only training data available are normal logs from a baseline period. We propose a novel hybrid model called "CausalConvLSTM" for modeling log sequences that takes advantage of Convolutional Neural Network's (CNN) ability to efficiently extract spatial features in a parallel fashion, and Long Short-Term Memory (LSTM) network's superior ability to capture sequential relationships. Another major challenge faced by anomaly detection systems is concept drift, which is the change in normal system behavior over time. We proposed and evaluated concrete strategies for retraining neural-network (NN) anomaly detection systems to adapt to concept drift.
{"title":"CausalConvLSTM: Semi-Supervised Log Anomaly Detection Through Sequence Modeling","authors":"Steven Yen, M. Moh, Teng-Sheng Moh","doi":"10.1109/ICMLA.2019.00217","DOIUrl":"https://doi.org/10.1109/ICMLA.2019.00217","url":null,"abstract":"Computer systems utilize logging to record events of interest. These logs are a rich source of information, and can be analyzed to detect attacks, failures, and many other issues. Due to the automated generation of logs by computer processes, the volume and throughput of logs can be extremely large, limiting the effectiveness of manual analysis. Rule-based systems were introduced to automatically detect issues based on rules written by experts. However, these systems can only detect known issues for which related rules exist in the rule-set. On the other hand, anomaly detection (AD) approaches can detect unknown issues. This is achieved by looking for unusual behaviors significantly different from the norm. In this paper, we target the problem of semi-supervised log anomaly detection, where the only training data available are normal logs from a baseline period. We propose a novel hybrid model called \"CausalConvLSTM\" for modeling log sequences that takes advantage of Convolutional Neural Network's (CNN) ability to efficiently extract spatial features in a parallel fashion, and Long Short-Term Memory (LSTM) network's superior ability to capture sequential relationships. Another major challenge faced by anomaly detection systems is concept drift, which is the change in normal system behavior over time. We proposed and evaluated concrete strategies for retraining neural-network (NN) anomaly detection systems to adapt to concept drift.","PeriodicalId":436714,"journal":{"name":"2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA)","volume":"87 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":"134318776","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：