2017 IEEE International Conference on Data Mining Workshops (ICDMW)最新文献

Deep Physiological Arousal Detection in a Driving Simulator Using Wearable Sensors 基于可穿戴传感器的驾驶模拟器深层生理唤醒检测

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-12-18 DOI: 10.1109/ICDMW.2017.69

Aaqib Saeed, S. Trajanovski, M. V. Keulen, J. V. Erp

{"title":"Deep Physiological Arousal Detection in a Driving Simulator Using Wearable Sensors","authors":"Aaqib Saeed, S. Trajanovski, M. V. Keulen, J. V. Erp","doi":"10.1109/ICDMW.2017.69","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.69","url":null,"abstract":"Driving is an activity that requires considerable alertness. Insufficient attention, imperfect perception, inadequate information processing, and sub-optimal arousal are possible causes of poor human performance. Understanding of these causes and the implementation of effective remedies is of key importance to increase traffic safety and improve driver's well-being. For this purpose, we used deep learning algorithms to detect arousal level, namely, under-aroused, normal and over-aroused for professional truck drivers in a simulated environment. The physiological signals are collected from 11 participants by wrist wearable devices. We presented a cost effective ground-truth generation scheme for arousal based on a subjective measure of sleepiness and score of stress stimuli. On this dataset, we evaluated a range of deep neural network models for representation learning as an alternative to handcrafted feature extraction. Our results show that a 7-layers convolutional neural network trained on raw physiological signals (such as heart rate, skin conductance and skin temperature) outperforms a baseline neural network and denoising autoencoder models with weighted F-score of 0.82 vs. 0.75 and Kappa of 0.64 vs. 0.53, respectively. The proposed convolutional model not only improves the overall results but also enhances the detection rate for every driver in the dataset as determined by leave-one-subject-out cross-validation.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116816808","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}

引用次数: 24

Spectral Keyboard Streams: Towards Effective and Continuous Authentication 频谱键盘流:迈向有效和持续的认证

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-12-18 DOI: 10.1109/ICDMW.2017.38

A. Alshehri, Frans Coenen, Danushka Bollegala

引用次数: 0

Predicting Dementia Screening and Staging Scores from Semantic Verbal Fluency Performance 从语义语言流畅性表现预测痴呆筛查和分期得分

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-12-18 DOI: 10.1109/ICDMW.2017.100

N. Linz, J. Tröger, Jan Alexandersson, Maria Wolters, A. König, Philippe H. Robert

引用次数: 24

Analyzing Informal Caregiving Expression in Social Media 社交媒体中的非正式关怀表达分析

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-12-15 DOI: 10.1109/ICDMW.2017.50

Reda Al-Bahrani, M. Danilovich, W. Liao, A. Choudhary, Ankit Agrawal

{"title":"Analyzing Informal Caregiving Expression in Social Media","authors":"Reda Al-Bahrani, M. Danilovich, W. Liao, A. Choudhary, Ankit Agrawal","doi":"10.1109/ICDMW.2017.50","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.50","url":null,"abstract":"Caregiving is the act of providing assistance to an individual unable to perfom some daily living activities. Caregiving can be either paid or unpaid. An informal caregiver is an unpaid caregiver to an older, sick, or disabled family member or friend on a daily basis. Informal caregiving is associated with increased physical, mental, and emotional stressors contributing to poor health outcomes, caregiver burnout, and increased risk for institutionalization of the older adult care recipient. Informal caregivers manage their stressors through supportive services such as support groups or respite care, but little is known about how they use social media to share their caregiving experience. No work to our knowledge has investigated caregiver use of Twitter to share the caregiving experience.We collect and analyze tweets related to Alzheimer’s and Dementia. We present some insights on sentiment of the tweets, statistics of United States geographical locations of the tweeters, and the relationships of the care recipients. In our analysis we found that the majority of tweet sentiment was negative. Moreover, female care recipients are mentioned at a higher frequency than male care recipients in the tweets.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"22 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134163636","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}

引用次数: 7

Pi-CEP: Predictive Complex Event Processing Using Range Queries over Historical Pattern Space Pi-CEP:在历史模式空间上使用范围查询的预测性复杂事件处理

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-18 DOI: 10.1109/ICDMW.2017.167

Syed Gillani, A. Kammoun, K. Singh, Julien Subercaze, C. Gravier, J. Fayolle, F. Laforest

{"title":"Pi-CEP: Predictive Complex Event Processing Using Range Queries over Historical Pattern Space","authors":"Syed Gillani, A. Kammoun, K. Singh, Julien Subercaze, C. Gravier, J. Fayolle, F. Laforest","doi":"10.1109/ICDMW.2017.167","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.167","url":null,"abstract":"Predictive Complex Event Processing (CEP) constitutes the next phase of CEP evolution and provides future predictive states of the partially matched complex sequences. In this paper, we demonstrate our novel predictive CEP system and show that this problem can be solved while leveraging existing data modelling, query execution and optimisation frameworks. We model the predictive detection of events over an N-dimensional historical matched sequence space. Hence, a predictive set of events can be determined by answering the range queries over the historical sequence space. In order to take advantage of range search over 1-dimensional data structures, we transform the N-dimensional space into 1-dimension using space filling z-order curve. We propose a compressed index structure to store 1- dimensional data and execute customised range query techniques. Furthermore, we propose an approximate summarisation technique, over the historical space of top-k most infrequent range queries, to cater catastrophic forgetting of older matches. Two real-world datasets are used to demonstrate the feasibility of our proposed techniques. We demonstrate that our system can efficiently predict complex events and it equips a user-friendly interface to fulfil the requirements of user-computer interaction in a real-time.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132088151","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}

引用次数: 6

Identifying Basketball Plays from Sensor Data; Towards a Low-Cost Automatic Extraction of Advanced Statistics 基于传感器数据的篮球动作识别迈向低成本的高级统计数据自动提取

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-17 DOI: 10.1109/ICDMW.2017.123

Adrià Arbués Sangüesa, T. Moeslund, C. Bahnsen, Raul Benitez Iglesias

引用次数: 14

An Experimental Evaluation of Prior Polarities in Sentiment Lexicons 情感词汇先验极性的实验评价

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.56

Ali Bugra Kanburoglu, E. Solak

引用次数: 0

Discovering Cooperative Structure Among Online Items for Attention Dynamics 注意动力学在线项目间的合作结构研究

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.146

Kanji Matsutani, Masahito Kumano, M. Kimura, Kazumi Saito, K. Ohara, H. Motoda

引用次数: 0

Dealing with Class Imbalance the Scalable Way: Evaluation of Various Techniques Based on Classification Grade and Computational Complexity 处理类不平衡的可扩展方法:基于分类等级和计算复杂度的各种技术评价

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.16

Bernhard Schlegel, B. Sick

{"title":"Dealing with Class Imbalance the Scalable Way: Evaluation of Various Techniques Based on Classification Grade and Computational Complexity","authors":"Bernhard Schlegel, B. Sick","doi":"10.1109/ICDMW.2017.16","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.16","url":null,"abstract":"Highly imbalanced datasets continue to be a challenge in many data mining applications. It is surprising that state-of-the-art techniques countering class imbalances are usually very computationally expensive and therefore unscalable. Most research effort has been directed into enhancing those techniques, e.g., by focusing on borderline examples or combining multiple techniques. This is usually accompanied by an increased computational complexity, reducing the scalability even further. This article has four major contributions: First, existing techniques to deal with imbalanced datasets are evaluated regarding their computational cost and influence on classification performance on a variety of publicly available datasets and classifiers. Second, a new, scalable technique, class specific scaling (CSS) is proposed as an alternative and compared to the existing techniques. Third, a parameter free class overlap and noise measure is introduced to complement the existing measures to assess the dataset's properties, such as the class balance ratio, and the number of features and samples. This enables a finer categorization of imbalanced datasets. Fourth, based on these measures and basic conditions such as scalability and the used classifier, general recommendations regarding the suitability of the different techniques are derived.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125672965","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}

引用次数: 3

Quantifying Seasonal Patterns in Disparate Environmental Variables Using the PolarMetrics R Package 使用PolarMetrics R软件包量化不同环境变量的季节模式

2017 IEEE International Conference on Data Mining Workshops (ICDMW) Pub Date : 2017-11-01 DOI: 10.1109/ICDMW.2017.45

B. G. Brooks, Danny C. Lee, Lars Y. Pomara, W. Hargrove, A. Desai

{"title":"Quantifying Seasonal Patterns in Disparate Environmental Variables Using the PolarMetrics R Package","authors":"B. G. Brooks, Danny C. Lee, Lars Y. Pomara, W. Hargrove, A. Desai","doi":"10.1109/ICDMW.2017.45","DOIUrl":"https://doi.org/10.1109/ICDMW.2017.45","url":null,"abstract":"Certain environmental processes, while influential, are inherently difficult to quantify and detect using traditional time series analyses, particularly among variables with different seasonal progressions. Disturbances that only manifest in part of a season (e.g., spring defoliation) or subtle climate shifts can pose detection challenges when they occur in the presence of other variability. Increasing sampling rates or even adding new sensors may not reveal the anticipated patterns. Eddy covariance tower data are a useful example for which various environmental drivers influence the overall signal, contributing noise and seemingly discordant variation. While eddy flux data are a rich representation of information, distinguishing expected seasonal responses within a signal can be challenging, especially where drivers may have either fast or lagged responses. A conventional solution might be to analyze and effectively smooth the data over daily to monthly intervals. However, such smoothed data will not exhibit the same variance, and subsequent regressions may not isolate relationships and anomalies to specific seasons. This paper introduces and demonstrates the use of a newly developed R software package, PolarMetrics, which is used to analyze 20 years of data from one AmeriFlux tower using a polar (circular) approach that reduces data volume to a smaller set of derived seasonal timing and magnitude metrics. Polar metrics quantify the annual cycle of input variables, and permit direct comparison of the strength and timing of seasonality. While performing the analysis over all years produces a synoptic result, analyzing year-by-year characterizes interannual variability.","PeriodicalId":389183,"journal":{"name":"2017 IEEE International Conference on Data Mining Workshops (ICDMW)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116558335","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}

引用次数: 1