Pub Date : 2017-12-01DOI: 10.1109/ICMLA.2017.00-79
N. Klausner, M. Azimi-Sadjadi
This paper introduces a kernel machine for multiclass discrimination where the scoring function for each class is constructed using a linear combination over a predefined diverse library of kernel functions. The scoring function is built using an expanded set of the kernel library hence increasing the number of degrees of freedom to analyze the information content of each data sample. To choose the smallest set of kernels that best match desirable first-order moment properties of the class-conditional distribution a regularized linear least-squares problem is solved. The proposed multi-kernel machine is then demonstrated and benchmarked against similar techniques which rely on the use of a single kernel using a satellite imagery dataset for the purposes of discriminating among several vegetation and soil types.
{"title":"Multiple Kernel Learning Using Sparse Representation","authors":"N. Klausner, M. Azimi-Sadjadi","doi":"10.1109/ICMLA.2017.00-79","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-79","url":null,"abstract":"This paper introduces a kernel machine for multiclass discrimination where the scoring function for each class is constructed using a linear combination over a predefined diverse library of kernel functions. The scoring function is built using an expanded set of the kernel library hence increasing the number of degrees of freedom to analyze the information content of each data sample. To choose the smallest set of kernels that best match desirable first-order moment properties of the class-conditional distribution a regularized linear least-squares problem is solved. The proposed multi-kernel machine is then demonstrated and benchmarked against similar techniques which rely on the use of a single kernel using a satellite imagery dataset for the purposes of discriminating among several vegetation and soil types.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"78 1","pages":"695-700"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78218681","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00-48
Richard A. Bauder, T. Khoshgoftaar
Healthcare is an integral component in people’s lives, especially for the rising elderly population, and must be affordable. Medicare is one such healthcare program. Claims fraud is a major contributor to increased healthcare costs, but its impact can be lessened through fraud detection. In this paper, we compare several machine learning methods to detect Medicare fraud. We perform a comparative study with supervised, unsupervised, and hybrid machine learning approaches using four performance metrics and class imbalance reduction via oversampling and an 80-20 undersampling method. We group the 2015 Medicare data into provider types, with fraud labels from the List of Excluded Individuals/Entities database. Our results show that the successful detection of fraudulent providers is possible, with the 80-20 sampling method demonstrating the best performance across the learners. Furthermore, supervised methods performed better than unsupervised or hybrid methods, but these results varied based on the class imbalance sampling technique and provider type.
{"title":"Medicare Fraud Detection Using Machine Learning Methods","authors":"Richard A. Bauder, T. Khoshgoftaar","doi":"10.1109/ICMLA.2017.00-48","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-48","url":null,"abstract":"Healthcare is an integral component in people’s lives, especially for the rising elderly population, and must be affordable. Medicare is one such healthcare program. Claims fraud is a major contributor to increased healthcare costs, but its impact can be lessened through fraud detection. In this paper, we compare several machine learning methods to detect Medicare fraud. We perform a comparative study with supervised, unsupervised, and hybrid machine learning approaches using four performance metrics and class imbalance reduction via oversampling and an 80-20 undersampling method. We group the 2015 Medicare data into provider types, with fraud labels from the List of Excluded Individuals/Entities database. Our results show that the successful detection of fraudulent providers is possible, with the 80-20 sampling method demonstrating the best performance across the learners. Furthermore, supervised methods performed better than unsupervised or hybrid methods, but these results varied based on the class imbalance sampling technique and provider type.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"83 1","pages":"858-865"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77642549","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00-19
Edmar R. S. Rezende, Guilherme C. S. Ruppert, T. Carvalho, F. Ramos, Paulo Lício de Geus
Malicious software (malware) has been extensively used for illegal activity and new malware variants are discovered at an alarmingly high rate. The ability to group malware variants into families with similar characteristics makes possible to create mitigation strategies that work for a whole class of programs. In this paper, we present a malware family classification approach using a deep neural network based on the ResNet-50 architecture. Malware samples are represented as byteplot grayscale images and a deep neural network is trained freezing the convolutional layers of ResNet-50 pre-trained on the ImageNet dataset and adapting the last layer to malware family classification. The experimental results on a dataset comprising 9,339 samples from 25 different families showed that our approach can effectively be used to classify malware families with an accuracy of 98.62%.
{"title":"Malicious Software Classification Using Transfer Learning of ResNet-50 Deep Neural Network","authors":"Edmar R. S. Rezende, Guilherme C. S. Ruppert, T. Carvalho, F. Ramos, Paulo Lício de Geus","doi":"10.1109/ICMLA.2017.00-19","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-19","url":null,"abstract":"Malicious software (malware) has been extensively used for illegal activity and new malware variants are discovered at an alarmingly high rate. The ability to group malware variants into families with similar characteristics makes possible to create mitigation strategies that work for a whole class of programs. In this paper, we present a malware family classification approach using a deep neural network based on the ResNet-50 architecture. Malware samples are represented as byteplot grayscale images and a deep neural network is trained freezing the convolutional layers of ResNet-50 pre-trained on the ImageNet dataset and adapting the last layer to malware family classification. The experimental results on a dataset comprising 9,339 samples from 25 different families showed that our approach can effectively be used to classify malware families with an accuracy of 98.62%.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"61 26 1","pages":"1011-1014"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78856722","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00-26
Bo Liu, Shuo Yan, Huanling You, Yan Dong, Jianqiang Li, Yong Li, Jianlei Lang, Rentao Gu
At present, high road surface temperature (RST) is threatening the safety of expressway transportation. It can lead to accidents and damages to road, accordingly, people have paid more attention to RST forecasting. Numerical methods on RST prediction are often hard to obtain precise parameters, whereas statistical methods cannot achieve desired accuracy. To address these problems, this paper proposes GBELM-RBF method that utilizes gradient boosting to ensemble Radial Basis Function Extreme Learning Machine. To evaluate the performance of the proposed method, GBELM-RBF is compared with other ELM algorithms on the datasets of airport expressway and Badaling expressway during November 2012 and September 2014. The root mean squared error (RMSE), accuracy and Pearson Correlation Coefficient (PCC) of these methods are analyzed. The experimental results show that GBELM-RBF has the best performance. For airport expressway dataset, the RMSE is less than 3, the accuracy is 78.8% and PCC is 0.94. For Badaling expressway dataset, the RMSE is less than 3, the accuracy is 81.2% and PCC is 0.921.
{"title":"An Ensembled RBF Extreme Learning Machine to Forecast Road Surface Temperature","authors":"Bo Liu, Shuo Yan, Huanling You, Yan Dong, Jianqiang Li, Yong Li, Jianlei Lang, Rentao Gu","doi":"10.1109/ICMLA.2017.00-26","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-26","url":null,"abstract":"At present, high road surface temperature (RST) is threatening the safety of expressway transportation. It can lead to accidents and damages to road, accordingly, people have paid more attention to RST forecasting. Numerical methods on RST prediction are often hard to obtain precise parameters, whereas statistical methods cannot achieve desired accuracy. To address these problems, this paper proposes GBELM-RBF method that utilizes gradient boosting to ensemble Radial Basis Function Extreme Learning Machine. To evaluate the performance of the proposed method, GBELM-RBF is compared with other ELM algorithms on the datasets of airport expressway and Badaling expressway during November 2012 and September 2014. The root mean squared error (RMSE), accuracy and Pearson Correlation Coefficient (PCC) of these methods are analyzed. The experimental results show that GBELM-RBF has the best performance. For airport expressway dataset, the RMSE is less than 3, the accuracy is 78.8% and PCC is 0.94. For Badaling expressway dataset, the RMSE is less than 3, the accuracy is 81.2% and PCC is 0.921.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"65 1","pages":"977-980"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87002288","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00-54
Michael Walton, M. Ayache, Logan Straatemeier, Daniel Gebhardt, Benjamin Migliori
We present a novel method of unsupervised anomaly detection using long-short-term memory mixture density networks (LSTM-MDN), applied to timeseries data of digital radio transmissions. The modern radio frequency (RF) environment is a dynamic and ever-changing complex milieu of signals, environmental effects, unintentional interference, and intentional jamming. A consequence of this complex mix is that RF receivers must become better and better at rejecting anomalous signals in order to recover the transmitted information. However, it is not always possible to know a priori what constitutes a valid signal and what constitutes an anomaly (intentional or otherwise), especially with the adoption of cognitive radio techniques. We show that an LSTM-MDN model is able to rapidly learn the training set and produce probability distribution functions for the expected signal as a function of time. We then demonstrate that the negative log likelihood of an incoming test transmission, conditioned on the training set, provides a metric that allows anomalous signals to be detected and labeled. We demonstrate this method for eight popular modulations and for three different anomaly types. By applying unsupervised learning in the temporal domain, we report a fully-generalizable anomaly detection method that may be applied to signals for which the transmission parameters may be unknown or obscured.
{"title":"Unsupervised Anomaly Detection for Digital Radio Frequency Transmissions","authors":"Michael Walton, M. Ayache, Logan Straatemeier, Daniel Gebhardt, Benjamin Migliori","doi":"10.1109/ICMLA.2017.00-54","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-54","url":null,"abstract":"We present a novel method of unsupervised anomaly detection using long-short-term memory mixture density networks (LSTM-MDN), applied to timeseries data of digital radio transmissions. The modern radio frequency (RF) environment is a dynamic and ever-changing complex milieu of signals, environmental effects, unintentional interference, and intentional jamming. A consequence of this complex mix is that RF receivers must become better and better at rejecting anomalous signals in order to recover the transmitted information. However, it is not always possible to know a priori what constitutes a valid signal and what constitutes an anomaly (intentional or otherwise), especially with the adoption of cognitive radio techniques. We show that an LSTM-MDN model is able to rapidly learn the training set and produce probability distribution functions for the expected signal as a function of time. We then demonstrate that the negative log likelihood of an incoming test transmission, conditioned on the training set, provides a metric that allows anomalous signals to be detected and labeled. We demonstrate this method for eight popular modulations and for three different anomaly types. By applying unsupervised learning in the temporal domain, we report a fully-generalizable anomaly detection method that may be applied to signals for which the transmission parameters may be unknown or obscured.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"28 1","pages":"826-832"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86145491","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.0-125
Cristinel Codrescu
The finite impulse response multilayer perceptron (FIRMLP) is a multilayer perceptron where the static weights have been replaced by finite impulse response filters. Hereby, it represents a model for spatio-temporal processing. In this paper we present a temporal processing neural network which is based on the FIRMLP, but some layers have been replaced by temporal radial basis function (RBF) units. As training algorithm we used the temporal backpropagation not just for adapting the weights but also for finding the centers and widths of the RBF layers as well. The performance comparison have been done for the task of handwritten digit ecognition by using the MNIST and MNIST-Variations databases.
{"title":"RBF-FIRMLP Architecture for Digit Recognition","authors":"Cristinel Codrescu","doi":"10.1109/ICMLA.2017.0-125","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.0-125","url":null,"abstract":"The finite impulse response multilayer perceptron (FIRMLP) is a multilayer perceptron where the static weights have been replaced by finite impulse response filters. Hereby, it represents a model for spatio-temporal processing. In this paper we present a temporal processing neural network which is based on the FIRMLP, but some layers have been replaced by temporal radial basis function (RBF) units. As training algorithm we used the temporal backpropagation not just for adapting the weights but also for finding the centers and widths of the RBF layers as well. The performance comparison have been done for the task of handwritten digit ecognition by using the MNIST and MNIST-Variations databases.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"62 1","pages":"420-425"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76212335","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.0-166
Nuwan S. Ferdinand, Benjamin Gharachorloo, S. Draper
In this paper we propose an approach to parallelizing synchronous stochastic gradient descent (SGD) that we term “Anytime-Gradients”. The Anytime-Gradients is designed to exploit the work completed by slow compute nodes or “stragglers”. In many approaches work completed by these nodes, while only partial, is discarded completely. To maintain synchronization in our approach, each computational epoch is of fixed duration, and at the end of each epoch, workers send updated parameter vectors to a master mode for combination. The master weights each update by the amount of work done. The Anytime-Gradients scheme is robust to both persistent and non-persistent stragglers and requires no prior knowledge about processor abilities. We show that the scheme effectively exploits stragglers and outperforms existing methods.
{"title":"Anytime Exploitation of Stragglers in Synchronous Stochastic Gradient Descent","authors":"Nuwan S. Ferdinand, Benjamin Gharachorloo, S. Draper","doi":"10.1109/ICMLA.2017.0-166","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.0-166","url":null,"abstract":"In this paper we propose an approach to parallelizing synchronous stochastic gradient descent (SGD) that we term “Anytime-Gradients”. The Anytime-Gradients is designed to exploit the work completed by slow compute nodes or “stragglers”. In many approaches work completed by these nodes, while only partial, is discarded completely. To maintain synchronization in our approach, each computational epoch is of fixed duration, and at the end of each epoch, workers send updated parameter vectors to a master mode for combination. The master weights each update by the amount of work done. The Anytime-Gradients scheme is robust to both persistent and non-persistent stragglers and requires no prior knowledge about processor abilities. We show that the scheme effectively exploits stragglers and outperforms existing methods.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"42 1","pages":"141-146"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77637100","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00010
Andrei Belcin, Sean L. A. Floyd, A. Asiri, H. Viktor
Healthcare practitioners agree that good oral health is a critical indicator of general health and wellness of a population. The lack of access to mandatory coverage for common issues such as cavities and non-surgical periodontal care often lead not only to medical problems, but also to loss of productivity. This trend is especially evident for older individuals and lower-income families. This paper discusses the results of our exploration of the annual Canadian Community Health Survey (CCHS), in order to further study the interplay between socio-economic factors and oral and dental health. To this end, we present the results when applying a number of machine learning algorithms to a CCHS data mart. Our results reaffirm that individuals' levels and sources of income are strong indicators of the number of dental visits per year. In addition, we found that younger adults and youth, who usually live in larger households, visit the dentist less frequently than all other survey respondents.
{"title":"An Exploratory Study of Oral and Dental Health in Canada","authors":"Andrei Belcin, Sean L. A. Floyd, A. Asiri, H. Viktor","doi":"10.1109/ICMLA.2017.00010","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00010","url":null,"abstract":"Healthcare practitioners agree that good oral health is a critical indicator of general health and wellness of a population. The lack of access to mandatory coverage for common issues such as cavities and non-surgical periodontal care often lead not only to medical problems, but also to loss of productivity. This trend is especially evident for older individuals and lower-income families. This paper discusses the results of our exploration of the annual Canadian Community Health Survey (CCHS), in order to further study the interplay between socio-economic factors and oral and dental health. To this end, we present the results when applying a number of machine learning algorithms to a CCHS data mart. Our results reaffirm that individuals' levels and sources of income are strong indicators of the number of dental visits per year. In addition, we found that younger adults and youth, who usually live in larger households, visit the dentist less frequently than all other survey respondents.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"24 1","pages":"1114-1119"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82551351","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.0-150
Ming Sun, A. Schwarz, Minhua Wu, N. Strom, S. Matsoukas, S. Vitaladevuni
This paper presents our work on building a small-footprint keyword spotting system for a resource-limited language, which requires low CPU, memory and latency. Our keyword spotting system consists of deep neural network (DNN) and hidden Markov model (HMM), which is a hybrid DNN-HMM decoder. We investigate different transfer learning techniques to leverage knowledge and data from a resource-abundant source language to improve the keyword DNN training for a target language which has limited in-domain data. The approaches employed in this paper include training a DNN using source language data to initialize the target language DNN training, mixing data from source and target languages together in a multi-task DNN training setup, using logits computed from a DNN trained on the source language data to regularize the keyword DNN training in the target language, as well as combinations of these techniques. Given different amounts of target language training data, our experimental results show that these transfer learning techniques successfully improve keyword spotting performance for the target language, measured by the area under the curve (AUC) of DNN-HMM decoding detection error tradeoff (DET) curves using a large in-house far-field test set.
{"title":"An Empirical Study of Cross-Lingual Transfer Learning Techniques for Small-Footprint Keyword Spotting","authors":"Ming Sun, A. Schwarz, Minhua Wu, N. Strom, S. Matsoukas, S. Vitaladevuni","doi":"10.1109/ICMLA.2017.0-150","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.0-150","url":null,"abstract":"This paper presents our work on building a small-footprint keyword spotting system for a resource-limited language, which requires low CPU, memory and latency. Our keyword spotting system consists of deep neural network (DNN) and hidden Markov model (HMM), which is a hybrid DNN-HMM decoder. We investigate different transfer learning techniques to leverage knowledge and data from a resource-abundant source language to improve the keyword DNN training for a target language which has limited in-domain data. The approaches employed in this paper include training a DNN using source language data to initialize the target language DNN training, mixing data from source and target languages together in a multi-task DNN training setup, using logits computed from a DNN trained on the source language data to regularize the keyword DNN training in the target language, as well as combinations of these techniques. Given different amounts of target language training data, our experimental results show that these transfer learning techniques successfully improve keyword spotting performance for the target language, measured by the area under the curve (AUC) of DNN-HMM decoding detection error tradeoff (DET) curves using a large in-house far-field test set.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"22 1","pages":"255-260"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84316817","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 : 2017-12-01DOI: 10.1109/ICMLA.2017.00-21
S. Hörmann, Martin Bach, K. Dietmayer
A major challenge in autonomous driving is the prediction of complex downtown scenarios with mutiple road users. This contribution tackles this challenge by combining,,,,,,,, a Bayesian filtering technique for environment representation and machine learning as long-term predictor. Therefore, a dynamic occupancy grid map representing the static and dynamic environment around the ego-vehicle is utilized as input to a deep convolutional neural network. This yields the advantage of using data from a single timestamp for prediction, rather than an entire time series. Furthermore, convolutional neural networks have the inherent characteristic of using context information, enabling the implicit modeling of road user interaction. One of the major advantages is the unsupervised learning character due to fully automatic label generation. The presented algorithm is trained and evaluated on multiple hours of recorded sensor data containing multiple road users, e.g., pedestrians, bikes and vehicles.
{"title":"Learning Long-Term Situation Prediction for Automated Driving","authors":"S. Hörmann, Martin Bach, K. Dietmayer","doi":"10.1109/ICMLA.2017.00-21","DOIUrl":"https://doi.org/10.1109/ICMLA.2017.00-21","url":null,"abstract":"A major challenge in autonomous driving is the prediction of complex downtown scenarios with mutiple road users. This contribution tackles this challenge by combining,,,,,,,, a Bayesian filtering technique for environment representation and machine learning as long-term predictor. Therefore, a dynamic occupancy grid map representing the static and dynamic environment around the ego-vehicle is utilized as input to a deep convolutional neural network. This yields the advantage of using data from a single timestamp for prediction, rather than an entire time series. Furthermore, convolutional neural networks have the inherent characteristic of using context information, enabling the implicit modeling of road user interaction. One of the major advantages is the unsupervised learning character due to fully automatic label generation. The presented algorithm is trained and evaluated on multiple hours of recorded sensor data containing multiple road users, e.g., pedestrians, bikes and vehicles.","PeriodicalId":6636,"journal":{"name":"2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"103 1","pages":"1000-1005"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80297256","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：