H. Bashashati, R. Ward, A. Bashashati, Amr M. Mohamed
The task of classifying EEG signals for self-paced Brain Computer Interface (BCI) applications is extremely challenging. This difficulty in classification of self-paced data stems from the fact that the system has no clue about the start time of a control task and the data contains a large number of periods during which the user has no intention to control the BCI. Therefore, to improve the performance of the BCI, it is imperative to exploit the characteristics of the EEG data as much as possible. For motor imagery based self-paced BCIs, during motor imagery task the EEG signal of each subject goes through several internal state changes. Applying appropriate classifiers that can exploit the temporal correlation in EEG data can enhance the performance of the BCI. In this paper, we propose an algorithm which is able to capture the temporal correlation of the EEG signal. We compare the performance of our algorithm that is based on neural network conditional random fields to two well-known dynamic classifiers, the Hidden Markov Models and Conditional Random Fields and to the static classifier, Support Vector Machines. We compare these methods using the data from SM2 dataset, and we show that our algorithm yields results that are considerably superior to the other approaches in terms of the Area Under the Curve (AUC) of the BCI system.
{"title":"Neural Network Conditional Random Fields for Self-Paced Brain Computer Interfaces","authors":"H. Bashashati, R. Ward, A. Bashashati, Amr M. Mohamed","doi":"10.1109/ICMLA.2016.0169","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0169","url":null,"abstract":"The task of classifying EEG signals for self-paced Brain Computer Interface (BCI) applications is extremely challenging. This difficulty in classification of self-paced data stems from the fact that the system has no clue about the start time of a control task and the data contains a large number of periods during which the user has no intention to control the BCI. Therefore, to improve the performance of the BCI, it is imperative to exploit the characteristics of the EEG data as much as possible. For motor imagery based self-paced BCIs, during motor imagery task the EEG signal of each subject goes through several internal state changes. Applying appropriate classifiers that can exploit the temporal correlation in EEG data can enhance the performance of the BCI. In this paper, we propose an algorithm which is able to capture the temporal correlation of the EEG signal. We compare the performance of our algorithm that is based on neural network conditional random fields to two well-known dynamic classifiers, the Hidden Markov Models and Conditional Random Fields and to the static classifier, Support Vector Machines. We compare these methods using the data from SM2 dataset, and we show that our algorithm yields results that are considerably superior to the other approaches in terms of the Area Under the Curve (AUC) of the BCI system.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127387830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this work, we apply the idea of conditional computation to the gated recurrent unit (GRU), a type of recurrent activation function. With slight modifications to the GRU, the number of floating point operations required to calculate the feed-forward pass through the network may be significantly reduced. This allows for more rapid computation, enabling a trade-off between model accuracy and model speed. Such a trade-off may be useful in a scenario where real-time performance is required, allowing for powerful recurrent models to be deployed on compute-limited devices.
{"title":"Faster Gated Recurrent Units via Conditional Computation","authors":"Andrew S. Davis, I. Arel","doi":"10.1109/ICMLA.2016.0165","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0165","url":null,"abstract":"In this work, we apply the idea of conditional computation to the gated recurrent unit (GRU), a type of recurrent activation function. With slight modifications to the GRU, the number of floating point operations required to calculate the feed-forward pass through the network may be significantly reduced. This allows for more rapid computation, enabling a trade-off between model accuracy and model speed. Such a trade-off may be useful in a scenario where real-time performance is required, allowing for powerful recurrent models to be deployed on compute-limited devices.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115747245","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}
Panos P. Markopoulos, S. Kundu, Shubham Chamadia, D. Pados
The K L1-norm Principal Components (L1-PCs) of a data matrix X Ε RD × N can be found optimally with cost O(2NK), in the general case, and O(Nrank(X)K - K + 1), when rankX is a constant with respect to N [1],[2]. Certainly, in real-world applications where N is large, even the latter polynomial cost is prohibitive. In this work, we present L1-BF: a novel, near-optimal algorithm that calculates the K L1-PCs of X with cost O (NDmin{N, D} + N2(K4 + DK2) + DNK3), comparable to that of standard (L2-norm) Principal-Component Analysis. Our numerical studies illustrate that the proposed algorithm attains optimality with very high frequency while, at the same time, it outperforms on the L1-PCA metric any counterpart of comparable computational cost. The outlier-resistance of the L1-PCs calculated by L1-BF is documented with experiments on dimensionality reduction and genomic data classification for disease diagnosis.
{"title":"L1-Norm Principal-Component Analysis via Bit Flipping","authors":"Panos P. Markopoulos, S. Kundu, Shubham Chamadia, D. Pados","doi":"10.1109/ICMLA.2016.0060","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0060","url":null,"abstract":"The K L1-norm Principal Components (L1-PCs) of a data matrix X Ε RD × N can be found optimally with cost O(2NK), in the general case, and O(Nrank(X)K - K + 1), when rankX is a constant with respect to N [1],[2]. Certainly, in real-world applications where N is large, even the latter polynomial cost is prohibitive. In this work, we present L1-BF: a novel, near-optimal algorithm that calculates the K L1-PCs of X with cost O (NDmin{N, D} + N2(K4 + DK2) + DNK3), comparable to that of standard (L2-norm) Principal-Component Analysis. Our numerical studies illustrate that the proposed algorithm attains optimality with very high frequency while, at the same time, it outperforms on the L1-PCA metric any counterpart of comparable computational cost. The outlier-resistance of the L1-PCs calculated by L1-BF is documented with experiments on dimensionality reduction and genomic data classification for disease diagnosis.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114962712","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}
This paper describes three metrics used to asses the filter diversity learned by convolutional neural networks during supervised classification. As our testbed we use four different data sets, including two subsets of ImageNet and two planktonic data sets collected by scientific instruments. We investigate the correlation between our devised metrics and accuracy, using normalization and regularization to alter filter diversity. We propose that these metrics could be used to improve training CNNs. Three potential applications are determining the best preprocessing method for non-standard data sets, diagnosing training efficacy, and predicting performance in cases where validation data is expensive or impossible to collect.
{"title":"Correlating Filter Diversity with Convolutional Neural Network Accuracy","authors":"Casey A. Graff, Jeffrey S. Ellen","doi":"10.1109/ICMLA.2016.0021","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0021","url":null,"abstract":"This paper describes three metrics used to asses the filter diversity learned by convolutional neural networks during supervised classification. As our testbed we use four different data sets, including two subsets of ImageNet and two planktonic data sets collected by scientific instruments. We investigate the correlation between our devised metrics and accuracy, using normalization and regularization to alter filter diversity. We propose that these metrics could be used to improve training CNNs. Three potential applications are determining the best preprocessing method for non-standard data sets, diagnosing training efficacy, and predicting performance in cases where validation data is expensive or impossible to collect.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"347 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122078885","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}
Arezou Moussavi Khalkhali, M. Jamshidi, Subhashie Wijemanne
Although there is no cure to date, Alzheimer's disease detection in early stages has a significant impact on the patient's life in terms of cost, the progress, and helping to plan in advance for an appropriate healthcare in the life ahead as well as providing clinical etiologies for further research. This paper discusses implementing a feature fusion method utilizing sparse and denoising autoencoders to reveal the stage of Alzheimer's disease. Four cohorts consisted of individuals with Alzheimer's disease, late mild cognitive impairment, early mild cognitive impairment, and normal control groups are classified using multinomial logistic regression fueled by the fusion of high-level and low-level features. The high-level features are extracted from the stacked autoencoders. The results show that feature fusion enhance the performance of typical autoencoders. However, the performance of feature fusion using denoising autoencoders is superior to that of the sparse training of autoencoders in terms of overall accuracy, precision, and recall.
{"title":"Feature Fusion for Denoising and Sparse Autoencoders: Application to Neuroimaging Data","authors":"Arezou Moussavi Khalkhali, M. Jamshidi, Subhashie Wijemanne","doi":"10.1109/ICMLA.2016.0106","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0106","url":null,"abstract":"Although there is no cure to date, Alzheimer's disease detection in early stages has a significant impact on the patient's life in terms of cost, the progress, and helping to plan in advance for an appropriate healthcare in the life ahead as well as providing clinical etiologies for further research. This paper discusses implementing a feature fusion method utilizing sparse and denoising autoencoders to reveal the stage of Alzheimer's disease. Four cohorts consisted of individuals with Alzheimer's disease, late mild cognitive impairment, early mild cognitive impairment, and normal control groups are classified using multinomial logistic regression fueled by the fusion of high-level and low-level features. The high-level features are extracted from the stacked autoencoders. The results show that feature fusion enhance the performance of typical autoencoders. However, the performance of feature fusion using denoising autoencoders is superior to that of the sparse training of autoencoders in terms of overall accuracy, precision, and recall.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122132060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which makes it very appealing for many fundamental tasks such as dimensionality reduction and semi-supervised learning. In this paper, we present a novel bimarginal pairwise encoding model, along with deep autoencoder, to learn nonlinear embedding for the aforementioned tasks. The new method learns powerful features that preserve critical pairwise information in a semi-supervised manner. It has achieved better performance on the well-known yet hard to make improvement benchmark MINIST compared with other methods in the same category, i.e. Autoencoder [4], Invariant Mapping for Dimensionality Reduction [1], Neighborhood Component Analysis [3], and Fixed Bi-Margin Pairwise Encoding [11].
与经典的监督学习方法需要预定义的类标签相比，两两编码或侧信息编码只需要两两相似信息来驱动特征学习，这使得它对于降维和半监督学习等许多基本任务非常有吸引力。在本文中，我们提出了一种新的双边缘成对编码模型，以及深度自编码器，以学习上述任务的非线性嵌入。新方法学习强大的特征，以半监督的方式保留关键的成对信息。与同类方法(Autoencoder[4]、Invariant Mapping for Dimensionality Reduction[1]、Neighborhood Component Analysis[3]、Fixed Bi-Margin Pairwise Encoding[11])相比，该方法在知名但难以改进的基准MINIST上取得了更好的性能。
{"title":"Semi-Supervised Learning with Bidirectional Adaptive Pairwise Encoding","authors":"Jiangbo Yuan, Jie Yu","doi":"10.1109/ICMLA.2016.0119","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0119","url":null,"abstract":"In contrast to classic supervised learning methods that demand pre-defined class labels, pairwise encoding or side-information encoding merely requires pairwise similarity information to drive feature learning, which makes it very appealing for many fundamental tasks such as dimensionality reduction and semi-supervised learning. In this paper, we present a novel bimarginal pairwise encoding model, along with deep autoencoder, to learn nonlinear embedding for the aforementioned tasks. The new method learns powerful features that preserve critical pairwise information in a semi-supervised manner. It has achieved better performance on the well-known yet hard to make improvement benchmark MINIST compared with other methods in the same category, i.e. Autoencoder [4], Invariant Mapping for Dimensionality Reduction [1], Neighborhood Component Analysis [3], and Fixed Bi-Margin Pairwise Encoding [11].","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124490275","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}
A. Sargolzaei, C. Crane, Alireza Abbaspour, S. Noei
A network of vehicular cyber-physical systems (VCPSs) can use wireless communications to interact with each other and the surrounding environment to improve transportation safety, mobility, and sustainability. However, cloud-oriented architectures are vulnerable to cyber attacks, which may endanger passenger and pedestrian safety and privacy, and cause severe property damage. For instance, a hacker can use message falsification attack to affect functionality of a particular application in a platoon of VCPSs. In this paper, a neural network-based fault detection technique is applied to detect and track fault data injection attacks on the cooperative adaptive cruise control layer of a platoon of connected vehicles in real time. A decision support system was developed to reduce the probability and severity of any consequent accident. A case study with its design specifications is demonstrated in detail. The simulation results show that the proposed method can improve system reliability, robustness, and safety.
{"title":"A Machine Learning Approach for Fault Detection in Vehicular Cyber-Physical Systems","authors":"A. Sargolzaei, C. Crane, Alireza Abbaspour, S. Noei","doi":"10.1109/ICMLA.2016.0112","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0112","url":null,"abstract":"A network of vehicular cyber-physical systems (VCPSs) can use wireless communications to interact with each other and the surrounding environment to improve transportation safety, mobility, and sustainability. However, cloud-oriented architectures are vulnerable to cyber attacks, which may endanger passenger and pedestrian safety and privacy, and cause severe property damage. For instance, a hacker can use message falsification attack to affect functionality of a particular application in a platoon of VCPSs. In this paper, a neural network-based fault detection technique is applied to detect and track fault data injection attacks on the cooperative adaptive cruise control layer of a platoon of connected vehicles in real time. A decision support system was developed to reduce the probability and severity of any consequent accident. A case study with its design specifications is demonstrated in detail. The simulation results show that the proposed method can improve system reliability, robustness, and safety.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"18 Suppl 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125734922","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}
If two fragments of source code are identical to each other, they are called code clones. Code clones introduce difficulties in software maintenance and cause bug propagation. In this paper, we present a machine learning framework to automatically detect clones in software, which is able to detect Types-3 and the most complicated kind of clones, Type-4 clones. Previously used traditional features are often weak in detecting the semantic clones The novel aspects of our approach are the extraction of features from abstract syntax trees (AST) and program dependency graphs (PDG), representation of a pair of code fragments as a vector and the use of classification algorithms. The key benefit of this approach is that our approach can find both syntactic and semantic clones extremely well. Our evaluation indicates that using our new AST and PDG features is a viable methodology, since they improve detecting clones on the IJaDataset 2.0.
{"title":"Semantic Clone Detection Using Machine Learning","authors":"Abdullah M. Sheneamer, J. Kalita","doi":"10.1109/ICMLA.2016.0185","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0185","url":null,"abstract":"If two fragments of source code are identical to each other, they are called code clones. Code clones introduce difficulties in software maintenance and cause bug propagation. In this paper, we present a machine learning framework to automatically detect clones in software, which is able to detect Types-3 and the most complicated kind of clones, Type-4 clones. Previously used traditional features are often weak in detecting the semantic clones The novel aspects of our approach are the extraction of features from abstract syntax trees (AST) and program dependency graphs (PDG), representation of a pair of code fragments as a vector and the use of classification algorithms. The key benefit of this approach is that our approach can find both syntactic and semantic clones extremely well. Our evaluation indicates that using our new AST and PDG features is a viable methodology, since they improve detecting clones on the IJaDataset 2.0.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128415853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, many financial sectors are evolving with huge numbers of web applications, which plays a crucial role in organizations to make important decisions. Considering this, the data has to be secured in order to prevent it from any attacks which lead to a huge loss. One of the topmost attacks in the database is SQL injection attack, is injecting some malicious query into the database causing serious threats. This paper proposes an enhanced approach to dynamic query matching technique by imposing a sanitizer for quick and easy detection of attack.
{"title":"Enhanced Approach to Detection of SQL Injection Attack","authors":"Raja Prasad Karuparthi, Bing Zhou","doi":"10.1109/ICMLA.2016.0082","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0082","url":null,"abstract":"In recent years, many financial sectors are evolving with huge numbers of web applications, which plays a crucial role in organizations to make important decisions. Considering this, the data has to be secured in order to prevent it from any attacks which lead to a huge loss. One of the topmost attacks in the database is SQL injection attack, is injecting some malicious query into the database causing serious threats. This paper proposes an enhanced approach to dynamic query matching technique by imposing a sanitizer for quick and easy detection of attack.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129342598","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}
Silvio L. Domingos, Rommel N. Carvalho, Ricardo Silva Carvalho, G. N. Ramos
The Department of Research and Strategic Information (DIE), from the Brazilian Office of the Comptroller General (CGU), is responsible for investigating potential problems related to federal expenditures. To pursue this goal, DIE regularly has to analyze large volumes of data to search for anomalies that can reveal suspicious activities. With the growing demand from the citizens for transparency and corruption prevention, DIE is constantly looking for new methods to automate these processes. In this work, we investigate IT purchases anomalies in the Federal Government Procurement System by using a deep learning algorithm to generate a predictive model. This model will be used to prioritize actions carried out by the office in its pursuit of problems related to this kind of purchases. The data mining process followed the CRISP-DM methodology and the modeling phase tested the parallel resources of the H2O tool. We evaluated the performance of twelve deep learning with auto-encoder models, each one generated under a different set of parameters, in order to find the best input data reconstruction model. The best model achieved a mean squared error (MSE) of 0.0012775 and was used to predict the anomalies over the test file samples.
{"title":"Identifying IT Purchases Anomalies in the Brazilian Government Procurement System Using Deep Learning","authors":"Silvio L. Domingos, Rommel N. Carvalho, Ricardo Silva Carvalho, G. N. Ramos","doi":"10.1109/ICMLA.2016.0129","DOIUrl":"https://doi.org/10.1109/ICMLA.2016.0129","url":null,"abstract":"The Department of Research and Strategic Information (DIE), from the Brazilian Office of the Comptroller General (CGU), is responsible for investigating potential problems related to federal expenditures. To pursue this goal, DIE regularly has to analyze large volumes of data to search for anomalies that can reveal suspicious activities. With the growing demand from the citizens for transparency and corruption prevention, DIE is constantly looking for new methods to automate these processes. In this work, we investigate IT purchases anomalies in the Federal Government Procurement System by using a deep learning algorithm to generate a predictive model. This model will be used to prioritize actions carried out by the office in its pursuit of problems related to this kind of purchases. The data mining process followed the CRISP-DM methodology and the modeling phase tested the parallel resources of the H2O tool. We evaluated the performance of twelve deep learning with auto-encoder models, each one generated under a different set of parameters, in order to find the best input data reconstruction model. The best model achieved a mean squared error (MSE) of 0.0012775 and was used to predict the anomalies over the test file samples.","PeriodicalId":356182,"journal":{"name":"2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"179 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130003660","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：