Time Series Decomposition using Automatic Learning Techniques for Predictive Models
Cast your vote
You can rate an item by clicking the amount of stars they wish to award to this item.
When enough users have cast their vote on this item, the average rating will also be shown.
Your vote was cast
Thank you for your feedback
Thank you for your feedback
Time series decomposition
MetadataShow full item record
PublisherInstitute of Physics Publishing
JournalJournal of Physics: Conference Series
AbstractThis paper proposes an innovative way to address real cases of production prediction. This approach consists in the decomposition of original time series into time sub-series according to a group of factors in order to generate a predictive model from the partial predictive models of the sub-series. The adjustment of the models is carried out by means of a set of statistic techniques and Automatic Learning. This method was compared to an intuitive method consisting of a direct prediction of time series. The results show that this approach achieves better predictive performance than the direct way, so applying a decomposition method is more appropriate for this problem than non-decomposition.
Attribution-NonCommercial-ShareAlike 4.0 International
The following license files are associated with this item:
- Creative Commons
Showing items related by title, author, creator and subject.
Performance of clinical prediction rules for diagnosis of pleural tuberculosis in a high-incidence settingSolari, Lely; Soto, Alonso; Van der Stuyft, Patrick; Unit of General Epidemiology and Disease Control; Institute of Tropical Medicine of Antwerp; Antwerp Belgium; Escuela de Medicina; Universidad Peruana de Ciencias Aplicadas; Lima Peru; Unit of General Epidemiology and Disease Control; Institute of Tropical Medicine of Antwerp; Antwerp Belgium; firstname.lastname@example.org (John Wiley & Sons Ltd, 2017-10)Objectives: Diagnosis of pleural tuberculosis (PT) is still a challenge, particularly in resource-constrained settings. Alternative diagnostic tools are needed. We aimed at evaluating the utility of Clinical Prediction Rules (CPRs) for diagnosis of pleural tuberculosis in Peru. Methods: We identified CPRs for diagnosis of PT through a structured literature search. CPRs using high-complexity tests, as defined by the FDA, were excluded. We applied the identified CPRs to patients with pleural exudates attending two third-level hospitals in Lima, Peru, a setting with high incidence of tuberculosis. Besides pleural fluid analysis, patients underwent closed pleural biopsy for reaching a final diagnosis through combining microbiological and histopathological criteria. We evaluated the performance of the CPRs against this composite reference standard using classic indicators of diagnostic test validity. Results: We found 15 eligible CPRs, of which 12 could be validated. Most included ADA, age, lymphocyte proportion and protein in pleural fluid as predictive findings. A total of 259 patients were included for their validation, of which 176 (67%) had PT and 50 (19%) malignant pleural effusion. The overall accuracy of the CPRs varied from 41% to 86%. Two had a positive likelihood ratio (LR) above 10, but none a negative LR below 0.1. ADA alone at a cut-off of ≥40 IU attained 87% diagnostic accuracy and had a positive LR of 6.6 and a negative LR of 0.2. Conclusion: Many CPRs for PT are available. In addition to ADA alone, none of them contributes significantly to diagnosis of PT.Acceso abierto
Predictive modeling for presumptive diagnosis of type 2 diabetes mellitus based on symptomatic analysisBarrios, Ordonez; Alberto, Diego; Infantes, Vizcarra; Raphael, Erick; Aguirre, Armas; Alexander, Jimmy (Institute of Electrical and Electronics Engineers Inc., 2017-08)The purpose of using Predictive Modeling for presumptive diagnosis of Type 2 Diabetes Mellitus based on symptomatic analysis is the optimization of the diagnosis phase of the disease through the process of evaluating symptomatic characteristics and daily habits, allowing the forecasting of T2DM without the need of medical exams through predictive analysis. The tool used was SAP Predictive Analytics and in order to identify the most suitable algorithm for the prediction, we evaluated them based on precision and false positive/negative relations, having found the Auto Classification algorithm as the most accurate with a 91.7% precision and a better correlation between false positives (8) and false negatives (3).
Factors predicting incremental administration of antihypertensive boluses during deep brain stimulator placement for Parkinson’s diseaseRajan, Shobana; Deogaonkar, Milind; Kaw, Roop; Nada, Eman MS; Hernández, Adrian V.; Ebrahim, Zeyd; Avitsian, Rafi (Elsevier B.V., 2014-11-28)Hypertension is common in deep brain stimulator (DBS) placement predisposing to intracranial hemorrhage. This retrospective review evaluates factors predicting incremental antihypertensive use intraoperatively. Medical records of Parkinson’s disease (PD) patients undergoing DBS procedure between 2008–2011 were reviewed after Institutional Review Board approval. Anesthesia medication, preoperative levodopa dose, age, preoperative use of antihypertensive medications, diabetes mellitus, anxiety, motor part of the Unified Parkinson’s Disease Rating Scale score and PD duration were collected. Univariate and multivariate analysis was done between each patient characteristic and the number of antihypertensive boluses. From the 136 patients included 60 were hypertensive, of whom 32 were on angiotensin converting enzyme inhibitors (ACEI) or angiotensin receptor blockers (ARB), told to hold on the morning of surgery. Antihypertensive medications were given to 130 patients intraoperatively. Age (relative risk [RR] 1.01; 95% confidence interval [CI] 1.00–1.02; p = 0.005), high Joint National Committee (JNC) class (p < 0.0001), diabetes mellitus (RR 1.4; 95%CI 1.2–17; p < 0.0001) and duration of PD >10 years (RR 1.2; 95%CI 1.1–1.3; p = 0.001) were independent predictors for antihypertensive use. No difference was noted in the mean dose of levodopa (p = 0.1) and levodopa equivalent dose (p = 0.4) between the low (I/II) and high severity (III/IV) JNC groups. Addition of dexmedetomidine to propofol did not influence antihypertensive boluses required (p = 0.38). Intraoperative hypertension during DBS surgery is associated with higher age group, hypertensive, diabetic patients and longer duration of PD. Withholding ACEI or ARB is an independent predictor of hypertension requiring more aggressive therapy. Levodopa withdrawal and choice of anesthetic agent is not associated with higher intraoperative antihypertensive medications.Acceso abierto