2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)最新文献

{"title":"Machine Learning Model for Frailty Detectxion using Electric Power Consumption Data from Smart Meter","authors":"Kijung Kim, Shimpei Ohsugi, N. Koshizuka","doi":"10.1109/DSAA53316.2021.9564127","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564127","url":null,"abstract":"With the increase of the number of the elderly, healthcare systems to support the daily life and wellbeing of the elderly attracted attention. Especially, frailty syndrome is one of the most significant challenges faced by many countries because of its high association with mortality and hospitalization. Recently, with the progress of ICT (Information and Communication Technology), many frailty detection models which use sensors were proposed. However, many of them require very high costs caused by the installation and management of sensors. Therefore, the objective of this study is to propose a machine learning-based frailty detection model using only electric power consumption data from smart meter, which uses no other devices such as sensors. Also, we examined the feasibility of our model through a case study, in which we have conducted on 24 elderly people. As a result of a cast study, we could detect frailty with 82% accuracy, 77% precision, 84% recall, and 80% f-score for a 2-class classification problem (frailty or non-frailty). The results of our study show that more elderly people can receive frailty diagnoses through smart meters. Moreover, since frailty is a reversible condition that could be restored to a healthy status with early and appropriate intervention, our model has potential to extend the healthy expectancy of the elderly.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114805289","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}

{"title":"3M-Transformers for Event Coding on Organized Crime Domain","authors":"Eric Parolin, L. Khan, Javier Osorio, Patrick T. Brandt, Vito D'Orazio, J. Holmes","doi":"10.1109/DSAA53316.2021.9564232","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564232","url":null,"abstract":"Political scientists and security agencies increasingly rely on computerized event data generation to track conflict processes and violence around the world. However, most of these approaches rely on pattern-matching techniques constrained by large dictionaries that are too costly to develop, update, or expand to emerging domains or additional languages. In this paper, we provide an effective solution to those challenges. Here we develop the 3M-Transformers (Multilingual, Multi-label, Multitask) approach for Event Coding from domain specific multilingual corpora, dispensing external large repositories for such task, and expanding the substantive focus of analysis to organized crime, an emerging concern for security research. Our results indicate that our 3M-Transformers configurations outperform state-of-the-art usual Transformers models (BERT and XLM-RoBERTa) for coding events on actors, actions and locations in English, Spanish, and Portuguese languages.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131985919","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}

{"title":"Interpretable Prediction of Diabetes from Tabular Health Screening Records Using an Attentional Neural Network","authors":"Yuki Oba, Taro Tezuka, Masaru Sanuki, Y. Wagatsuma","doi":"10.1109/DSAA53316.2021.9564151","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564151","url":null,"abstract":"Health screening is conducted in numerous countries to observe general health conditions. Machine learning has been applied to health screening records to predict asymptomatic patients' future medical states. However, for medical researchers and physicians, it is crucial to know why machine learning methods made such predictions to understand the underlying mechanism of the disease and prescribe treatments; therefore, predictions must be interpretable. We investigated the ability of an attentional neural network that processes tabular data, namely TabNet, to determine attributes that contribute to making predictions of the aggravation of type 2 diabetes. We used both model-agnostic and model-specific interpretation methods. For the former, we tested SHapley Additive exPlanations (SHAP). For the latter, we used model-specific feature importance and the mask in the attentive transformer of TabNet. We found that this mask provides useful information regarding which items in a biochemical analysis affect the aggravation of type 2 diabetes. The results from model-agnostic and model-specific methods were consistent.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130158272","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}

{"title":"Online Ensemble Aggregation using Deep Reinforcement Learning for Time Series Forecasting","authors":"A. Saadallah, K. Morik","doi":"10.1109/DSAA53316.2021.9564132","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564132","url":null,"abstract":"Both complex and evolving nature of time series structure make forecasting among one of the most important and challenging tasks in time series analysis. Typical methods for forecasting are designed to model time-evolving dependencies between data observations. However, it is generally accepted that none of them is universally valid for every application. Therefore, methods for learning heterogeneous ensembles by combining a diverse set of forecasts together appear as a promising solution to tackle this task. Several approaches, ranging from simple and enhanced averaging tactics to applying meta-learning methods, have been proposed to learn how to combine individual models in an ensemble. However, finding the optimal strategy for ensemble aggregation remains an open research question, particularly, when the ensemble needs to be adapted in real time. In this paper, we leverage a deep reinforcement learning framework for learning linearly weighted ensembles as a meta-learning method. In this framework, the combination policy in ensembles is modelled as a sequential decision making process, and an actor-critic model aims at learning the optimal weights in a continuous action space. The policy is updated following a drift detection mechanism for tracking performance shifts of the ensemble model. An extensive empirical study on many real-world datasets demonstrates that our method achieves excellent or on par results in comparison to the state-of-the-art approaches as well as several baselines.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134308369","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}

{"title":"Constructing Global Coherence Representations: Identifying Interpretability and Coherences of Transformer Attention in Time Series Data","authors":"Leonid Schwenke, Martin Atzmueller","doi":"10.1109/DSAA53316.2021.9564126","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564126","url":null,"abstract":"Transformer models have shown significant advances recently based on the general concept of Attention — to focus on specifically important and relevant parts of the input data. However, methods for enhancing their interpretability and explainability are still lacking. This is the problem which we tackle in this paper, to make Multi-Headed Attention more interpretable and explainable for time series classification. We present a method for constructing global coherence representations from Multi-Headed Attention of Transformer architectures. Accordingly, we present abstraction and interpretation methods, leading to intuitive visualizations of the respective attention patterns. We evaluate our proposed approach and the presented methods on several datasets demonstrating their efficacy.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129901241","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}

{"title":"Extracting Invariant Features for Predicting State of Health of Batteries in Hybrid Energy Buses","authors":"Mohammed Ghaith Altarabichi, Yuantao Fan, Sepideh Pashami, P. Mashhadi, Sławomir Nowaczyk","doi":"10.1109/DSAA53316.2021.9564184","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564184","url":null,"abstract":"Batteries are a safety-critical and the most expensive component for electric vehicles (EVs). To ensure the reliability of the EVs in operation, it is crucial to monitor the state of health of those batteries. Monitoring their deterioration is also relevant to the sustainability of the transport solutions, through creating an efficient strategy for utilizing the remaining capacity of the battery and its second life. Electric buses, similar to other EVs, come in many different variants, including different configurations and operating conditions. Developing new degradation models for each existing combination of settings can become challenging from different perspectives such as unavailability of failure data for novel settings, heterogeneity in data, low amount of data available for less popular configurations, and lack of sufficient engineering knowledge. Therefore, being able to automatically transfer a machine learning model to new settings is crucial. More concretely, the aim of this work is to extract features that are invariant across different settings. In this study, we propose an evolutionary method, called genetic algorithm for domain invariant features (GADIF), that selects a set of features to be used for training machine learning models, in such a way as to maximize the invariance across different settings. A Genetic Algorithm, with each chromosome being a binary vector signaling selection of features, is equipped with a specific fitness function encompassing both the task performance and domain shift. We contrast the performance, in migrating to unseen domains, of our method against a number of classical feature selection methods without any transfer learning mechanism. Moreover, in the experimental result section, we analyze how different features are selected under different settings. The results show that using invariant features leads to a better generalization of the machine learning models to an unseen domain.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128518407","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}

{"title":"Efficient Modeling of Digital Shadows for Production Processes: A Case Study for Quality Prediction in High Pressure Die Casting Processes","authors":"A. Chakrabarti, Ravi Prasanna Sukumar, M. Jarke, Maximilian Rudack, P. Buske, C. Holly","doi":"10.1109/DSAA53316.2021.9564113","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564113","url":null,"abstract":"The advent of Industry 4.0 has led a wide variety of engineering fields to incorporate more automation into their existing work processes. Various engineering sectors intend to imbibe aspects of Industry 4.0 technologies by leveraging Internet of Things coupled with Machine Learning and Artificial Intelligence for process optimization. This, in turn, has led to the surge of cross-domain data integration strategies which when enriched with domain specific knowledge creates dynamic models, termed as Digital Shadows. In this paper, we present the adaptation of the Digital Shadow modeling approach to die casting processes. We propose a generic pipeline for the creation of the model and test the efficacy of such an approach by transforming a predictive analytics model into a digital shadow model. For the predictive modeling, we present a novel approach of image based pixel classification which accurately predicts the occurrence as well as the location of damages on the cast object surfaces.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131004065","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}

{"title":"A Full-Stack Machine Learning Environment for Rapidly Evolving Industry Applications","authors":"Kayla Robinson, C. Billman, Muktesh Masih, Kevin Rose, Xi Wang, K. Hundman","doi":"10.1109/DSAA53316.2021.9564174","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564174","url":null,"abstract":"Developing, deploying, and maintaining machine learning models is a key function of many data science teams. We describe a framework built by American Family Insurance to model the risk profiles of properties. Through empirical experiments, we demonstrate that our automated, end-to-end framework provides a rapid platform for experimentation and productionalization in a business environment.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114243000","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}

{"title":"Bayesian Independence Test with Mixed-type Variables","authors":"A. Benavoli, Cassio P. de Campos","doi":"10.1109/DSAA53316.2021.9564124","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564124","url":null,"abstract":"A fundamental task in AI is to assess (in)dependence between mixed-type variables (text, image, sound). We propose a Bayesian kernelised correlation test of (in)dependence using a Dirichlet process model. The new measure of (in)dependence allows us to answer some fundamental questions: Based on data, are (mixed-type) variables independent? How likely is dependence/independence to hold? How high is the probability that two mixed-type variables are more than just weakly dependent? We theoretically show the properties of the approach, as well as algorithms for fast computation with it. We empirically demonstrate the effectiveness of the proposed method by analysing its performance and by comparing it with other frequentist and Bayesian approaches on a range of datasets and tasks with mixed-type variables.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128108770","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}

{"title":"Feature-Option-Action: A domain adaption transfer reinforcement learning framework","authors":"Yunxiao Zhang, Xiaochuan Zhang, Tianlong Shen, Yuan Zhou, Zhiyuan Wang","doi":"10.1109/DSAA53316.2021.9564185","DOIUrl":"https://doi.org/10.1109/DSAA53316.2021.9564185","url":null,"abstract":"Transfer reinforcement learning (TRL) algorithms have achieved success on alleviating the resource-consumption and sample-insufficiency problem in reinforcement learning (RL). Existing works of cross-domain TRL mainly focus on designing a mapping between the state-action space of source and target domains. We, however, propose a novel TRL framework, Feature-Option-Action (FOA), with novel neural network architecture in this work, to avoid the design of explicit mapping functions between source and target domain. FOA learner is normally trained in the source domain, and the parameters of the option components in the neural network would then be used to initialize the learners in target domain. Empirical evidences have shown that our technique could significantly improve the performance of learners in target domains. Meanwhile, we train FOA models with the model updating methods (in our works, we call it step-update) used in Option-Critic, and illustrate that this method can improve the exploration ability of FOA models by increasing the diversity of options. We also compare step-update with other model updating methods, and the results show that step-update method performs better for FOA model to make transfer training faster and smoother.","PeriodicalId":129612,"journal":{"name":"2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128128002","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}