Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00224
Noa Kaplan, R. Loveland, L. Denneau
The ”Asteroid Terrestrial-impact Last Alert System” (ATLAS) currently uses a two stage binary classifier to filter moving astronomical objects from electronic and optical artifacts, in order to detect asteroids that may eventually pass close to, or impact, Earth. Any detections that pass ATLAS’s filter are examined by human analysts. The results of the current filter contains more false positives than true positives, so that the majority of detections are classified as bogus by the analysts. These bogus tracklets cause unnecessary work for the analysts, and increase the time it takes to classify a detection as a real near Earth object, potentially decreasing warning time for a collision. In order to reduce this unnecessary effort, we extend the current classifier to incorporate dynamic motion data. We develop two engineered features which are combined with the output of the original classifier as the input features of a deep neural network. This network generates the probability of a detected object being designated real (i.e. an actual, moving, astronomical object), as opposed to being classified as bogus (i.e. one of the vast majority of false detections resulting from optical or noise artifacts). The new classifier decreases false positives by 59%, while maintaining a low false negative rate at virtually zero.
{"title":"Deep Neural Networks for Detecting Asteroids in the ATLAS Data Pipeline","authors":"Noa Kaplan, R. Loveland, L. Denneau","doi":"10.1109/ICMLA52953.2021.00224","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00224","url":null,"abstract":"The ”Asteroid Terrestrial-impact Last Alert System” (ATLAS) currently uses a two stage binary classifier to filter moving astronomical objects from electronic and optical artifacts, in order to detect asteroids that may eventually pass close to, or impact, Earth. Any detections that pass ATLAS’s filter are examined by human analysts. The results of the current filter contains more false positives than true positives, so that the majority of detections are classified as bogus by the analysts. These bogus tracklets cause unnecessary work for the analysts, and increase the time it takes to classify a detection as a real near Earth object, potentially decreasing warning time for a collision. In order to reduce this unnecessary effort, we extend the current classifier to incorporate dynamic motion data. We develop two engineered features which are combined with the output of the original classifier as the input features of a deep neural network. This network generates the probability of a detected object being designated real (i.e. an actual, moving, astronomical object), as opposed to being classified as bogus (i.e. one of the vast majority of false detections resulting from optical or noise artifacts). The new classifier decreases false positives by 59%, while maintaining a low false negative rate at virtually zero.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"50 1","pages":"1387-1392"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84772376","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00211
F. Mandreoli, Federico Motta, P. Missier
COVID-19-related pneumonia requires different modalities of Intensive Care Unit (ICU) interventions at different times to facilitate breathing, depending on severity progression. The ability for clinical staff to predict how patients admitted to hospital will require more or less ICU treatment on a daily basis is critical to ICU management. For real datasets that are sparse and incomplete and where the most important state transitions (dismissal, death) are rare, a standard Hidden Markov Model (HMM) approach is insufficient, as it is prone to overfitting. In this paper we propose a more sophisticated ensemble–based approach that involves training multiple HMMs, each specialized in a subset of the state transitions, and then selecting the more plausible predictions either by selecting or combining the models. We have validated the approach on a live dataset of about 1,000 patients from a partner hospital. Our results show that rare events, as well as the transitions to the most severe treatments outperform state of the art approaches.
{"title":"An HMM–ensemble approach to predict severity progression of ICU treatment for hospitalized COVID–19 patients","authors":"F. Mandreoli, Federico Motta, P. Missier","doi":"10.1109/ICMLA52953.2021.00211","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00211","url":null,"abstract":"COVID-19-related pneumonia requires different modalities of Intensive Care Unit (ICU) interventions at different times to facilitate breathing, depending on severity progression. The ability for clinical staff to predict how patients admitted to hospital will require more or less ICU treatment on a daily basis is critical to ICU management. For real datasets that are sparse and incomplete and where the most important state transitions (dismissal, death) are rare, a standard Hidden Markov Model (HMM) approach is insufficient, as it is prone to overfitting. In this paper we propose a more sophisticated ensemble–based approach that involves training multiple HMMs, each specialized in a subset of the state transitions, and then selecting the more plausible predictions either by selecting or combining the models. We have validated the approach on a live dataset of about 1,000 patients from a partner hospital. Our results show that rare events, as well as the transitions to the most severe treatments outperform state of the art approaches.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"39 1","pages":"1299-1306"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88609744","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00120
Sabine Apfeld, A. Charlish, G. Ascheid
One of the challenges encountered when processing streaming data is a change of the data distribution, which is called concept drift. It has been shown that ensemble methods are effective in reacting to such a change. However, so far it has not been investigated how the architecture and configuration of the ensemble, as well as the properties of the scenario, influence the prediction accuracy if the ensemble members (experts) are Long Short-Term Memory networks with an internal state. This paper evaluates six ensemble architectures in several configurations with regards to their suitability for processing streaming data with sudden, recurring concept drift. The evaluation with a public dataset shows the impact of the architecture and configuration on the ensembles’ accuracies, as well as the influence of the concepts’ stability periods and the Long Short-Term Memory experts’ internal states under several conditions.
{"title":"Ensembles of Long Short-Term Memory Experts for Streaming Data with Sudden Concept Drift","authors":"Sabine Apfeld, A. Charlish, G. Ascheid","doi":"10.1109/ICMLA52953.2021.00120","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00120","url":null,"abstract":"One of the challenges encountered when processing streaming data is a change of the data distribution, which is called concept drift. It has been shown that ensemble methods are effective in reacting to such a change. However, so far it has not been investigated how the architecture and configuration of the ensemble, as well as the properties of the scenario, influence the prediction accuracy if the ensemble members (experts) are Long Short-Term Memory networks with an internal state. This paper evaluates six ensemble architectures in several configurations with regards to their suitability for processing streaming data with sudden, recurring concept drift. The evaluation with a public dataset shows the impact of the architecture and configuration on the ensembles’ accuracies, as well as the influence of the concepts’ stability periods and the Long Short-Term Memory experts’ internal states under several conditions.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"1 1","pages":"716-723"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89311452","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00116
S. Stieber, N. Schröter, E. Fauster, Alexander Schiendorfer, W. Reif
Carbon fiber reinforced polymers (CFRP) offer highly desirable properties such as weight-specific strength and stiffness. Liquid composite moulding (LCM) processes are prominent, economically efficient, out-of-autoclave manufacturing techniques and, in particular, resin transfer moulding (RTM), allows for a high level of automation. There, fibrous preforms are impregnated by a viscous polymer matrix in a closed mould. Impregnation quality is of crucial importance for the final part quality and is dominated by preform permeability. We propose to learn a map of permeability deviations based on a sequence of camera images acquired in flow experiments. Several ML models are investigated for this task, among which ConvLSTM networks achieve an accuracy of up to 96.56%, showing better performance than the Transformer or pure CNNs. Finally, we demonstrate that models, trained purely on simulated data, achieve qualitatively good results on real data.
{"title":"PermeabilityNets: Comparing Neural Network Architectures on a Sequence-to-Instance Task in CFRP Manufacturing","authors":"S. Stieber, N. Schröter, E. Fauster, Alexander Schiendorfer, W. Reif","doi":"10.1109/ICMLA52953.2021.00116","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00116","url":null,"abstract":"Carbon fiber reinforced polymers (CFRP) offer highly desirable properties such as weight-specific strength and stiffness. Liquid composite moulding (LCM) processes are prominent, economically efficient, out-of-autoclave manufacturing techniques and, in particular, resin transfer moulding (RTM), allows for a high level of automation. There, fibrous preforms are impregnated by a viscous polymer matrix in a closed mould. Impregnation quality is of crucial importance for the final part quality and is dominated by preform permeability. We propose to learn a map of permeability deviations based on a sequence of camera images acquired in flow experiments. Several ML models are investigated for this task, among which ConvLSTM networks achieve an accuracy of up to 96.56%, showing better performance than the Transformer or pure CNNs. Finally, we demonstrate that models, trained purely on simulated data, achieve qualitatively good results on real data.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"61 1","pages":"694-697"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88153663","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00079
Daniel Fernández, F. Fernández, Javier García
Transfer in Reinforcement Learning (RL) aims to remedy the problem of learning complex RL tasks from scratch, which is impractical in most of the cases due to the huge sample requirements. To overcome this problem, transferring the knowledge acquired from a set of source tasks to a new target task is a core idea. This knowledge can be the policy, the model (state transition and/or reward function), or the value function learned in the source tasks. However, algorithms in transfer learning focus on transferring a single type of knowledge at a time, although intuitively it might be interesting to reuse several types of this knowledge. For this reason, in this paper we propose a multi-knowledge transfer RL algorithm which we call Probabilistic Transfer of Policies and Models (PTPM). PTPM, unlike single-knowledge transfer approaches, combines the transfer of two types of knowledge: policies and models. We show through different experiments on two well-known domains (Grid World and Mountain Car) how this novel multi-knowledge transfer algorithm improves the results of the two methods in which it is inspired separately. As an additional result, we show that sequential learning of multiple tasks is generally better than learning from a library of previously learned tasks from scratch.
强化学习中的迁移(Transfer in Reinforcement Learning, RL)旨在解决从头开始学习复杂强化学习任务的问题，由于样本需求巨大，这在大多数情况下是不切实际的。为了克服这一问题，将从一组源任务中获得的知识转移到新的目标任务中是一个核心思想。这些知识可以是策略、模型(状态转换和/或奖励函数)，或者在源任务中学习到的价值函数。然而，迁移学习中的算法专注于一次迁移一种类型的知识，尽管从直觉上讲，重用这种知识的几种类型可能会很有趣。为此，本文提出了一种多知识转移强化学习算法，我们称之为策略和模型的概率转移(PTPM)。PTPM与单一知识转移方法不同，它结合了两种类型的知识转移:政策和模型。我们通过在两个众所周知的领域(Grid World和Mountain Car)上的不同实验，展示了这种新颖的多知识转移算法是如何改进两种方法的结果的。作为一个额外的结果，我们表明对多个任务的顺序学习通常比从以前学习过的任务库中从头开始学习要好。
{"title":"Probabilistic Multi-knowledge Transfer in Reinforcement Learning","authors":"Daniel Fernández, F. Fernández, Javier García","doi":"10.1109/ICMLA52953.2021.00079","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00079","url":null,"abstract":"Transfer in Reinforcement Learning (RL) aims to remedy the problem of learning complex RL tasks from scratch, which is impractical in most of the cases due to the huge sample requirements. To overcome this problem, transferring the knowledge acquired from a set of source tasks to a new target task is a core idea. This knowledge can be the policy, the model (state transition and/or reward function), or the value function learned in the source tasks. However, algorithms in transfer learning focus on transferring a single type of knowledge at a time, although intuitively it might be interesting to reuse several types of this knowledge. For this reason, in this paper we propose a multi-knowledge transfer RL algorithm which we call Probabilistic Transfer of Policies and Models (PTPM). PTPM, unlike single-knowledge transfer approaches, combines the transfer of two types of knowledge: policies and models. We show through different experiments on two well-known domains (Grid World and Mountain Car) how this novel multi-knowledge transfer algorithm improves the results of the two methods in which it is inspired separately. As an additional result, we show that sequential learning of multiple tasks is generally better than learning from a library of previously learned tasks from scratch.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"574 1","pages":"471-476"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90421923","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00260
Pankaj Dikshit, B. Chandra, M. Gupta
Goods and Services Tax has been introduced for the first time in India in 2017 and it is a major tax reform. There have been a lot of queries posed by the users and response had to be given manually which was a very tedious task. There was a dire need to automate this Question/Answer process in an efficient manner. Embeddings e.g. BERT and ROBERTA have been used for converting the questions to make it efficient for clustering the questions. K-means and Hierarchical clustering techniques have been used for clustering the embeddings of questions, using different distance measures viz. Euclidean and Cosine. Three possible choices for answers for each query have been provided at first, and in the next step the best possible answer has been provided for each test question. Dataset of two months (October and November 2019) is used for automating the process. A high success rate in predicting the answers for the questions has been achieved.
{"title":"Automating Questions and Answers of Good and Services Tax system using clustering and embeddings of queries","authors":"Pankaj Dikshit, B. Chandra, M. Gupta","doi":"10.1109/ICMLA52953.2021.00260","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00260","url":null,"abstract":"Goods and Services Tax has been introduced for the first time in India in 2017 and it is a major tax reform. There have been a lot of queries posed by the users and response had to be given manually which was a very tedious task. There was a dire need to automate this Question/Answer process in an efficient manner. Embeddings e.g. BERT and ROBERTA have been used for converting the questions to make it efficient for clustering the questions. K-means and Hierarchical clustering techniques have been used for clustering the embeddings of questions, using different distance measures viz. Euclidean and Cosine. Three possible choices for answers for each query have been provided at first, and in the next step the best possible answer has been provided for each test question. Dataset of two months (October and November 2019) is used for automating the process. A high success rate in predicting the answers for the questions has been achieved.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"1 1","pages":"1630-1633"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75198162","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00209
P. Rasouli, Ingrid Chieh Yu
Recent studies have revealed that Machine Learning (ML) models are vulnerable to adversarial perturbations. Such perturbations can be intentionally or accidentally added to the original inputs, evading the classifier’s behavior to misclassify the crafted samples. A widely-used solution is to retrain the model using data points generated by various attack strategies. However, this creates a classifier robust to some particular evasions and can not defend unknown or universal perturbations. Counterfactual explanations are a specific class of post-hoc explanation methods that provide minimal modification to the input features in order to obtain a particular outcome from the model. In addition to the resemblance of counterfactual explanations to the universal perturbations, the possibility of generating instances from specific classes makes such approaches suitable for analyzing and improving the model’s robustness. Rather than explaining the model’s decisions in the deployment phase, we utilize the distance information obtained from counterfactuals and propose novel metrics to analyze the robustness of tabular classifiers. Further, we introduce a decision boundary modification approach using customized counterfactual data points to improve the robustness of the models without compromising their accuracy. Our framework addresses the robustness of black-box classifiers in the tabular setting, which is considered an under-explored research area. Through several experiments and evaluations, we demonstrate the efficacy of our approach in analyzing and improving the robustness of black-box tabular classifiers.
{"title":"Analyzing and Improving the Robustness of Tabular Classifiers using Counterfactual Explanations","authors":"P. Rasouli, Ingrid Chieh Yu","doi":"10.1109/ICMLA52953.2021.00209","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00209","url":null,"abstract":"Recent studies have revealed that Machine Learning (ML) models are vulnerable to adversarial perturbations. Such perturbations can be intentionally or accidentally added to the original inputs, evading the classifier’s behavior to misclassify the crafted samples. A widely-used solution is to retrain the model using data points generated by various attack strategies. However, this creates a classifier robust to some particular evasions and can not defend unknown or universal perturbations. Counterfactual explanations are a specific class of post-hoc explanation methods that provide minimal modification to the input features in order to obtain a particular outcome from the model. In addition to the resemblance of counterfactual explanations to the universal perturbations, the possibility of generating instances from specific classes makes such approaches suitable for analyzing and improving the model’s robustness. Rather than explaining the model’s decisions in the deployment phase, we utilize the distance information obtained from counterfactuals and propose novel metrics to analyze the robustness of tabular classifiers. Further, we introduce a decision boundary modification approach using customized counterfactual data points to improve the robustness of the models without compromising their accuracy. Our framework addresses the robustness of black-box classifiers in the tabular setting, which is considered an under-explored research area. Through several experiments and evaluations, we demonstrate the efficacy of our approach in analyzing and improving the robustness of black-box tabular classifiers.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"8 1","pages":"1286-1293"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75449708","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00030
Chunchun Li, Manuel Günther, T. Boult
Clustering has a long history in the computer vision community with a myriad of applications. Clustering is a family of unsupervised machine learning techniques that group samples based on similarity. Multiple ad hoc techniques have been developed to combine or fuse clustering algorithms with dozens of different clustering techniques. This paper presents a new formalization of clustering fusion and introduces the novel Commonality Fusion (ComFu) technique to combine the advantages of different clustering algorithms by fusing their results on datasets. ComFu builds a pairwise commonality matrix of samples by computing how many clustering algorithms group each pair together. Using this matrix, ComFu builds initial clusters of points with high commonality and then assigns points with low commonality to clusters with the highest average commonality to those points with an automatic distance measure selection process. We start experiments by comparing ComFu with the prior state-of-the-art cluster fusion algorithms on eight UCI datasets. We then evaluate ComFu on practical vision clustering problems, advancing the state-of-the-art on a wide range of applications including clustering faces in the IJB-B dataset. We apply ComFu to fuse FINCH, the state-of-the-art ”parameter-free” approach, which returns multiple partitions and can use multiple distance metrics, and show that ComFu improves their result by fusing over metrics and partitions.
{"title":"ComFu: Improving Visual Clustering by Commonality Fusion","authors":"Chunchun Li, Manuel Günther, T. Boult","doi":"10.1109/ICMLA52953.2021.00030","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00030","url":null,"abstract":"Clustering has a long history in the computer vision community with a myriad of applications. Clustering is a family of unsupervised machine learning techniques that group samples based on similarity. Multiple ad hoc techniques have been developed to combine or fuse clustering algorithms with dozens of different clustering techniques. This paper presents a new formalization of clustering fusion and introduces the novel Commonality Fusion (ComFu) technique to combine the advantages of different clustering algorithms by fusing their results on datasets. ComFu builds a pairwise commonality matrix of samples by computing how many clustering algorithms group each pair together. Using this matrix, ComFu builds initial clusters of points with high commonality and then assigns points with low commonality to clusters with the highest average commonality to those points with an automatic distance measure selection process. We start experiments by comparing ComFu with the prior state-of-the-art cluster fusion algorithms on eight UCI datasets. We then evaluate ComFu on practical vision clustering problems, advancing the state-of-the-art on a wide range of applications including clustering faces in the IJB-B dataset. We apply ComFu to fuse FINCH, the state-of-the-art ”parameter-free” approach, which returns multiple partitions and can use multiple distance metrics, and show that ComFu improves their result by fusing over metrics and partitions.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"1 1","pages":"143-150"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75728483","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00244
Nikola Marković, D. Vahle, V. Staudt, D. Kolossa
We introduce a novel hybrid approach for the early detection of power converter faults, focusing on the use case of modular multilevel converters. The proposed method is based on training a deep one-class classifier, which learns the characteristics of the normal system operation and can hence recognize deviations even without any training on potential fault conditions of the system. In order to achieve robust and reliable performance, the diagnosis of the system state utilizes short sequences of observations, which are combined through a probabilistic model. The decision about the system state can then take the form of monitoring the T2 test statistics, which allows us to control the maximum classification error. This proposed method, Reliability-guided One-Class Classification (ROCC) was tested on data recorded from a Modular Multilevel Converter. The approach is shown to be effective in all test cases, leading to reliable diagnostics even though the classifier is applied to a wide range of unseen conditions.
{"title":"Condition Monitoring for Power Converters via Deep One-Class Classification","authors":"Nikola Marković, D. Vahle, V. Staudt, D. Kolossa","doi":"10.1109/ICMLA52953.2021.00244","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00244","url":null,"abstract":"We introduce a novel hybrid approach for the early detection of power converter faults, focusing on the use case of modular multilevel converters. The proposed method is based on training a deep one-class classifier, which learns the characteristics of the normal system operation and can hence recognize deviations even without any training on potential fault conditions of the system. In order to achieve robust and reliable performance, the diagnosis of the system state utilizes short sequences of observations, which are combined through a probabilistic model. The decision about the system state can then take the form of monitoring the T2 test statistics, which allows us to control the maximum classification error. This proposed method, Reliability-guided One-Class Classification (ROCC) was tested on data recorded from a Modular Multilevel Converter. The approach is shown to be effective in all test cases, leading to reliable diagnostics even though the classifier is applied to a wide range of unseen conditions.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"34 1","pages":"1513-1520"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72913480","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 : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00216
Khaled Mohammed Saifuddin, Esra Akbas, Max Khanov, J. Beaman
Opioid Use Disorder (OUD) is one of the most severe health care problems in the USA. People addicted to opioids need various treatments, including Medication-Assisted Treatment (MAT), proper counseling, and behavioral therapies. However, during the peak time of the COVID-19 pandemic, the supply of emergency medications was disrupted seriously. Patients faced severe medical care scarcity since many pharmaceutical companies, drugstores, and local pharmacies were closed. Import-export was also canceled to consent to the government emergency law, i.e., lockdown, quarantine, and isolation. These circumstances and their negative effects on OUD patient’s psychology could have led them to a drop out of MAT medications and persuaded to resume illicit opioid use. This project involves collecting and analyzing a large volume of Twitter data related to MAT medications for OUD patients. We discover the Active MAT Medicine Users (AMMUs) on twitter. For this, we build a seed dictionary of words related to OUD and MAT and apply association rules to expand it. Further, AMMUs’ tweet posts are studied ‘before the pandemic’ (BP) and ‘during the pandemic’ (DP) to understand how the drug behaviors and habits have changed due to COVID-19. We also perform sentiment analysis on Tweets to determine the impact of the COVID-19 pandemic on the psychology of AMMUs. Our analysis shows that the use of MAT medications has decreased around 30.54%, where the use of illicit drugs and other prescription opioids increased 18.06% and 12.12%, respectively, based on AMMUs’ tweets posted during the lockdown compared with before the lockdown statistics. The COVID-19 pandemic and lockdown may result in the resumption of illegal and prescription opioid abuse by OUD patients. Necessary steps and precautions should be taken by health care providers to ensure the emergency supply of medicines and also psychological support and thus prevent patients from illicit opioid use.
{"title":"Effects of COVID-19 on individuals in Opioid Addiction Recovery","authors":"Khaled Mohammed Saifuddin, Esra Akbas, Max Khanov, J. Beaman","doi":"10.1109/ICMLA52953.2021.00216","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00216","url":null,"abstract":"Opioid Use Disorder (OUD) is one of the most severe health care problems in the USA. People addicted to opioids need various treatments, including Medication-Assisted Treatment (MAT), proper counseling, and behavioral therapies. However, during the peak time of the COVID-19 pandemic, the supply of emergency medications was disrupted seriously. Patients faced severe medical care scarcity since many pharmaceutical companies, drugstores, and local pharmacies were closed. Import-export was also canceled to consent to the government emergency law, i.e., lockdown, quarantine, and isolation. These circumstances and their negative effects on OUD patient’s psychology could have led them to a drop out of MAT medications and persuaded to resume illicit opioid use. This project involves collecting and analyzing a large volume of Twitter data related to MAT medications for OUD patients. We discover the Active MAT Medicine Users (AMMUs) on twitter. For this, we build a seed dictionary of words related to OUD and MAT and apply association rules to expand it. Further, AMMUs’ tweet posts are studied ‘before the pandemic’ (BP) and ‘during the pandemic’ (DP) to understand how the drug behaviors and habits have changed due to COVID-19. We also perform sentiment analysis on Tweets to determine the impact of the COVID-19 pandemic on the psychology of AMMUs. Our analysis shows that the use of MAT medications has decreased around 30.54%, where the use of illicit drugs and other prescription opioids increased 18.06% and 12.12%, respectively, based on AMMUs’ tweets posted during the lockdown compared with before the lockdown statistics. The COVID-19 pandemic and lockdown may result in the resumption of illegal and prescription opioid abuse by OUD patients. Necessary steps and precautions should be taken by health care providers to ensure the emergency supply of medicines and also psychological support and thus prevent patients from illicit opioid use.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"2 2 1","pages":"1333-1340"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79473291","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：