Time-Series Cross-Validation Parallel Programming using MPI

Mohammed, Abdulrahim; Khedr, Ahmed M.; AlHaj, Duaa; Khalifa, Reem Al; Alqaddoumi, Abdulla

doi:10.1109/icdabi53623.2021.9655795

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By adopting a non-realistic approach in which future data is used to evaluate the current test set, LOOCV tends to overestimate results. To overcome this problem, we adopt the TSCV approach [31], which is illustrated in figure 2. In the TSCV scheme, we guarantee that a minimum amount of data is used to train the very first model, which must include at least one seizure.…”

Section: Adopted Machine-learning Methodologymentioning

confidence: 99%

Approximate zero-crossing: a new interpretable, highly discriminative and low-complexity feature for EEG and iEEG seizure detection

et al. 2022

View full text Add to dashboard Cite

Objective: Long-term monitoring of people with epilepsy based on electroencephalography (EEG) and intracranial EEG (iEEG) has the potential to deliver key clinical information for personalised epilepsy treatment. More specifically, in outpatient settings, the available solutions are not satisfactory either due to poor classification performance or high complexity to be executed in resource-constrained devices (e.g., wearable systems). Therefore, we hypothesize that obtaining high discriminative features is the main avenue to improve low-complex seizure-detection algorithms. Approach: inspired by how neurologists recognize ictal EEG data, and to tackle this problem by targeting resource-constrained wearable devices, we introduce a new interpretable and highly discriminative feature for EEG and iEEG, namely approximate zero-crossing (AZC). We obtain AZC by applying a polygonal approximation to mimic how our brain selects prominent patterns among noisy data and then using a zero-crossing count as a measure of the dominating frequency. By employing Kullback-Leiber divergence, leveraging CHB-MIT and SWEC-ETHZ iEEG datasets, we compare the AZC discriminative power against a set of 56 classical literature features (CLF). Moreover, we assess the performances of a low-complex seizure detection method using only AZC features versus employing the CLF set. Main results: three AZC features obtained with different approximation thresholds are among the five with the highest median discriminative power. Moreover, seizure classification based on only AZC features outperforms an equivalent CLF-based method. The former detects 102 and 194 seizures against 99 and 161 for the latter (CHB-MIT and SWEC-ETHZ, respectively). Moreover, the AZC-based method keeps a similar false-alarm rate (i.e., an average of 2.1 and 1.0, against 2.0 and 0.5, per day). Significance: we propose a new feature and demonstrate its capability in seizure classification for scalp and intracranial EEG. We envision the use of such a feature to improve outpatient monitoring with resource-constrained devices.

show abstract

Section: Adopted Machine-learning Methodologymentioning

confidence: 99%

Approximate zero-crossing: a new interpretable, highly discriminative and low-complexity feature for EEG and iEEG seizure detection

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A common CV approach for personalized training is leave-one-seizureout, which means that data from one seizure is left out for testing, and seizures that come before but also after will be used for training. On the other hand, in the time series cross-validation (TSCV) approach [17], [18], only previously acquired data can be used for training. This means that if files are ordered in time, for the first CV fold only one file will be used for training and the one after it for testing.…”

Section: Respecting Temporal Data Dependenciesmentioning

confidence: 99%

Importance of methodological choices in data manipulation for validating epileptic seizure detection models

Pale,

Teijeiro,

Atienza

2023

2023 45th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Epilepsy is a chronic neurological disorder that affects a significant portion of the human population and imposes serious risks in the daily life. Despite advances in machine learning and IoT, small, non-stigmatizing wearable devices for continuous monitoring and detection in outpatient environments are not yet widely available. Part of the reason is the complexity of epilepsy itself, including highly imbalanced data, multimodal nature, and very subject-specific signatures. However, another problem is the heterogeneity of methodological approaches in research, leading to slower progress, difficulty in comparing results, and low reproducibility. Therefore, this article identifies a wide range of methodological decisions that must be made and reported when training and evaluating the performance of epilepsy detection systems. We characterize the influence of individual choices using a typical ensemble random-forest model and the publicly available CHB-MIT database, providing a broader picture of each decision and giving good-practice recommendations, based on our experience, where possible.

show abstract

Precipitated Handover Decision Detection in LTE Networks Through Recurrent Neural Networks

Reis,

Abularach Arnez,

De Souza

et al. 2023

2023 IEEE Latin-American Conference on Communications (LATINCOM)

View full text Add to dashboard Cite

Time-Series Cross-Validation Parallel Programming using MPI

Cited by 3 publications

References 7 publications

Approximate zero-crossing: a new interpretable, highly discriminative and low-complexity feature for EEG and iEEG seizure detection

Approximate zero-crossing: a new interpretable, highly discriminative and low-complexity feature for EEG and iEEG seizure detection

Importance of methodological choices in data manipulation for validating epileptic seizure detection models

Precipitated Handover Decision Detection in LTE Networks Through Recurrent Neural Networks

Contact Info

Product

Resources

About