HOT aSAX: A Novel Adaptive Symbolic Representation for Time Series Discords Discovery

Pham, Ninh; Le, Quang Loc; Dang, Tran Khanh

doi:10.1007/978-3-642-12145-6_12

Cited by 17 publications

(19 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more sophisticated way of handling the non-Gaussian distribution with SAX representation is to use adaptive breakpoints. 46 However, we found that the optimal solution for our data was to set breakpoints to values that separated scores into equal-sized bins (quantiles), thus satisfying SAX's expectation that any arbitrary score has an equal probability of being assigned to any of the bins. Another limitation of this study regards the single-site origins of the dataset.…”

Section: Discussionmentioning

confidence: 92%

Characterizations of Temporal Postoperative Pain Signatures With Symbolic Aggregate Approximations

Tighe¹,

Nickerson

Fillingim

et al. 2017

The Clinical Journal of Pain

View full text Add to dashboard Cite

Objectives The primary aim was to characterize the temporal dynamics of postoperative pain intensity using symbolic aggregate approximation (SAX). The secondary aim was to explore the effects of sociodemographic and clinical factors on the SAX representations of postoperative pain intensity. Materials and Methods We applied SAX to a large-scale time series database of 226,808 acute postoperative pain intensity ratings. Pain scores were stratified by patient age, gender, type of surgery, home opioid use, and postoperative day (POD), and co-stratified by age and gender. Cosine similarity, a metric that measures distance using vector angle, was applied to these motif data to compare pain behavior similarities across strata. Results Across age groups, SAX clusters revealed a shift from low-to-low pain score transitions in older patients to high-to-high pain score transitions in younger patients, whereas analyses stratified by gender showed that males had a greater focus of pain score transitions among lower intensity pain scores compared to females. Surgical stratification, using cardiovascular surgery as a reference, demonstrated that pulmonary surgery had the highest cosine similarity at 0.855. With POD stratification, POD 7 carried the greatest cosine similarity to POD 0 (0.611) after POD 1 (0.765), with POD3 (0.419) and POD4 (0.441) carrying the lowest cosine similarities with POD 0. Discussion SAX offers a feasible and effective framework for characterizing large-scale postoperative pain within the time domain. Stratification of SAX representations demonstrate unique temporal dynamic profiles on the basis of age group, sex, type of surgery, preoperative opioid use, and across postoperative days 1-7.

show abstract

Section: Discussionmentioning

confidence: 92%

Characterizations of Temporal Postoperative Pain Signatures With Symbolic Aggregate Approximations

Tighe¹,

Nickerson

Fillingim

et al. 2017

The Clinical Journal of Pain

View full text Add to dashboard Cite

show abstract

“…They introduce an adaptive window discord discovery (AWDD) to detect the anomaly in ECG recordings. It was developed from a brute force discord discovery (BFDD) algorithm [85]. The algorithm finds candidates with an abnormal heartbeat by selecting the largest Euclidean distance when comparing the heartbeats to each other.…”

Section: Model Trainingmentioning

confidence: 99%

A Survey of Heart Anomaly Detection Using Ambulatory Electrocardiogram (ECG)

Boulanger

2020

Sensors

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) are the number one cause of death globally. An estimated 17.9 million people die from CVDs each year, representing 31% of all global deaths. Most cardiac patients require early detection and treatment. Therefore, many products to monitor patient’s heart conditions have been introduced on the market. Most of these devices can record a patient’s bio-metric signals both in resting and in exercising situations. However, reading the massive amount of raw electrocardiogram (ECG) signals from the sensors is very time-consuming. Automatic anomaly detection for the ECG signals could act as an assistant for doctors to diagnose a cardiac condition. This paper reviews the current state-of-the-art of this technology discusses the pros and cons of the devices and algorithms found in the literature and the possible research directions to develop the next generation of ambulatory monitoring systems.

show abstract

“…For instance, HOT SAX algorithm [ 21 ] bases itself on the representation of symbolic aggregate approximation (SAX). The algorithm has shown a great potential for extending and applying to many other works [ 39 , 40 ].…”

Section: Related Workmentioning

confidence: 99%

Robust and Accurate Anomaly Detection in ECG Artifacts Using Time Series Motif Discovery

Sivaraks

Ratanamahatana

2015

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Electrocardiogram (ECG) anomaly detection is an important technique for detecting dissimilar heartbeats which helps identify abnormal ECGs before the diagnosis process. Currently available ECG anomaly detection methods, ranging from academic research to commercial ECG machines, still suffer from a high false alarm rate because these methods are not able to differentiate ECG artifacts from real ECG signal, especially, in ECG artifacts that are similar to ECG signals in terms of shape and/or frequency. The problem leads to high vigilance for physicians and misinterpretation risk for nonspecialists. Therefore, this work proposes a novel anomaly detection technique that is highly robust and accurate in the presence of ECG artifacts which can effectively reduce the false alarm rate. Expert knowledge from cardiologists and motif discovery technique is utilized in our design. In addition, every step of the algorithm conforms to the interpretation of cardiologists. Our method can be utilized to both single-lead ECGs and multilead ECGs. Our experiment results on real ECG datasets are interpreted and evaluated by cardiologists. Our proposed algorithm can mostly achieve 100% of accuracy on detection (AoD), sensitivity, specificity, and positive predictive value with 0% false alarm rate. The results demonstrate that our proposed method is highly accurate and robust to artifacts, compared with competitive anomaly detection methods.

show abstract

HOT aSAX: A Novel Adaptive Symbolic Representation for Time Series Discords Discovery

Cited by 17 publications

References 6 publications

Characterizations of Temporal Postoperative Pain Signatures With Symbolic Aggregate Approximations

Characterizations of Temporal Postoperative Pain Signatures With Symbolic Aggregate Approximations

A Survey of Heart Anomaly Detection Using Ambulatory Electrocardiogram (ECG)

Robust and Accurate Anomaly Detection in ECG Artifacts Using Time Series Motif Discovery

Contact Info

Product

Resources

About