Rules-based Algorithm Research Articles

Verb Form Recognition and Error Detection in English Articles Using Long Short-Term Memory and Grammar Checks

Error checking of verb forms in English articles is beneficial for learning English and improving the fluency of English texts. In this study, long shortterm memory (LSTM) was used to recognize the types of errors in verb forms. To maximize the utilization of textual context information, a bidirectional LSTM algorithm was employed. Simulation experiments were then conducted, and the algorithm was evaluated against the support vector machine (SVM) algorithm and the grammar rules-based algorithm. The bidirectional LSTM method demonstrated higher accuracy in recognizing the parts of speech of words and the types of verb form errors in the text. Additionally, the accuracy was more stable when faced with different types of verb form errors.

Evaluation of a Multi-Component Phenotype Algorithm for Systemic Lupus Erythematosus across the PCORnet, OMOP, and i2b2 Common Data Models

The aim of this study was to evaluate the performance of a computable phenotype for systemic lupus erythematosus (SLE) patients when it is ported from a local data warehouse to the i2b2, OMOP, and PCORnet CDMs. We adapted the SLE phenotype to the Northwestern Medicine (NM) Enterprise Data Warehouse (EDW) and NU i2b2, OMOP, and PCORnet instances. Each of the phenotype’s 17 components were determined by a rules-based algorithm built on diagnosis, medication, lab, and procedure codes. We assessed the phenotype over 168 clinician-confirmed SLE patients and 100 healthy controls and calculated agreement between the EDW and CDMs for overall SLE classification, individual SLICC criteria membership, and individual code occurrence level aggregates - count, first and last date, lab values using Cohen’s kappa (Cκ) and intraclass correlation coefficients (ICC). For overall SLE classification, agreement of the OMOP and PCORnet datamarts with the EDW was high (Cκ 0.928, 0.802, respectively) while that of i2b2 was low (Cκ 0.328). For the panel of SLICC criteria, OMOP had high agreement for 14/17 SLICC criteria (Cκ 0.792-1.000). PCORnet had high agreement for 13/17 criteria (Cκ 0.708-1.000). i2b2 had high agreement for 10/17 criteria (Cκ 0.813-1.000) with the exception of lab-based criteria. While agreement between the EDW and CDMs at the level of individual codes was relatively poor, agreement at the levels of overall SLE classification and individual SLICC criteria were reasonably high for OMOP and PCORnet, suggesting that inconsistencies at a micro, code level become less apparent at the macro, phenotype level.

Power system event detection using Teager Kaiser Energy Operator and autoencoder based algorithm

As the global demand for electricity increases, modern power systems are operating closer to their stability limits. This increases power system events that vary in intensity. It is essential to detect these power system events as early as possible and to take the necessary control actions to prevent escalation. This paper proposes a power system event detection method based on the Teager Kaiser Energy Operator (TKEO) and Autoencoder. In the proposed method, the rules-based algorithm performs primary detection, and the detected events are confirmed using the TKEO and autoencoder-based algorithms. The effectiveness of the proposed method was tested using test signals, simulated power system signals, and real-time power system data obtained from an actual power system. The results reveal the robustness and accuracy of the proposed method in detecting single and multiple power system events in the PMU data.

Bringing Care Close to Home: Remote Management of Heart Failure In Partnership with Indigenous Communities In Northern Ontario, Canada

BackgroundThe Weeneebayko Area Health Authority (WAHA) is a regional, community-based Indigenous health authority in Northern Ontario, Canada. From September 2022 to March 2023, the WAHA and University Health Network engaged in a partnership that designed a collaborative model of care to address inequities in cardiology specialist access in Northern Ontario. This model implemented a digital therapeutic for heart failure, (the Medly program) and in-person cardiology clinics in the region. MethodsA WAHA-based Medly program clinical coordinator worked closely with the University Health Network team to deliver care and support patient self-management of HF. The use and effectiveness of the Medly program were tracked through app usage and rules-based algorithm alerts, based on patient self-reported data. Distribution of relevant equipment (a scale, a blood pressure cuff, and a mobile device) for the Medly program was recorded. Surveys to assess patient and provider satisfaction with the Medly program also were administered. A retrospective chart audit of electronic medical records and administrative databases was conducted. ResultsA total of 33 patients in the WAHA were enrolled in the Medly program during a 7-month period, surpassing the enrollment goal of 25 patients. A total of 93% of eligible patients were on optimized guideline-directed medical therapy or were being titrated for it. Of 15 surveyed patients, 100% agreed or strongly agreed that the Medly program facilitated delivery of care close to home, and 86% of surveyed clinicians (n = 7) agreed or strongly agreed that the Medly program addresses a gap in available care in the region. ConclusionsThe implementation of the Medly program in partnership with the WAHA has demonstrated success in terms of the volume of referrals, the quality of care, adherence to evidence-based best-practice guidelines, and satisfaction with the program.

Algorithm development to improve intervention effectiveness for parents with mental health signs and symptoms.

In this study we aimed to describe and compare groups formed by a rules-based algorithm to prospectively identify clients at risk of poor outcomes in order to guide tailored public health nursing (PHN) intervention approaches. Data-driven methods using standardized Omaha System PHN documentation. Clients ages 13-40 who received PHN home visiting services for both the Caretaking/parenting and Mental health problems (N=4109). We applied a theory-based algorithm consisting of six rules using existing Omaha System data. We examined the groups formed by the algorithm using standard descriptive, inferential statistics, and Latent Class Analysis. Clients (N=4109) were 25.1 (SD=5.9) years old and had an average of 7.3 (SD=3.2) problems, 250 (SD=319) total interventions, and 32 (SD=44) Mental health interventions. Overall outcomes improved after PHN interventions (p<.001 for all) and having more Mental health signs/symptoms was negatively associated with outcome scores (p<.001 for all). This algorithm may be helpful in identifying high-risk clients during a baseline assessment who may benefit from more intensive mental health interventions. Findings show there is value using the Omaha System for PHN documentation and algorithm clinical decision support development. Future research should focus on algorithm implementation in PHN clinical practice.

Efficient control of connected and automated vehicles on a two-lane highway with a moving bottleneck

This paper investigates the traffic flow of connected and automated vehicles (CAVs) inducing by a moving bottleneck on a two-lane highway. A heuristic rules-based algorithm (HRA) has been used to control the traffic flow upstream of the moving bottleneck. In the HRA, some CAVs in the control zone are mapped onto the neighboring lane as virtual ones. To improve the driving comfort, the command acceleration caused by virtual vehicle is restricted. Comparing with the benchmark in which the CAVs change lane as soon as the lane changing condition is met, the HRA significantly improves the traffic flow: the overtaking throughput as well as the outflow rate increases, the travel delay and the fuel consumption decrease, the comfort level could also be improved.

Machine-Learning-Based Detection of Pressure-Induced Faults in Continuous Glucose Monitors

Continuous glucose monitors (CGMs) are prone to faults termed pressure-induced sensor attenuations (PISAs), particularly when the user rolls over on the sensor during sleep. PISAs result in false, low blood glucose readings, leading to undesirable pump shutoffs and an increased risk of hyperglycemia. Data from an outpatient trial with PISA glucose readings labeled for 1125 nights was used. Machine learning methods such as decision trees, support vector machines, neural networks, random forest, and gradient-boosted machine models are compared against each other and with a previously reported rules-based algorithm for PISA detection on the same data set. The best-performing gradient-boosted machine model is further improved using the developed start-PISA model. Model interpretation methods are used to confirm that PISA behavior is well-captured and provides insights into decision-making.

Traffic flow of connected and automated vehicles at lane drop on two-lane highway: An optimization-based control algorithm versus a heuristic rules-based algorithm

This paper investigates traffic flow of connected and automated vehicles at lane drop on two-lane highway. We evaluate and compare performance of an optimization-based control algorithm (OCA) with that of a heuristic rules-based algorithm (HRA). In the OCA, the average speed of each vehicle is maximized. In the HRA, virtual vehicle and restriction of the command acceleration caused by the virtual vehicle are introduced. It is found that (i) capacity under the HRA (denoted as C H) is smaller than capacity under the OCA; (ii) the travel delay is always smaller under the OCA, but driving is always much more comfortable under the HRA; (iii) when the inflow rate is smaller than C H, the HRA outperforms the OCA with respect to the fuel consumption and the monetary cost; (iv) when the inflow rate is larger than C H, the HRA initially performs better with respect to the fuel consumption and the monetary cost, but the OCA would become better after certain time. The spatiotemporal pattern and speed profile of traffic flow are presented, which explains the reason underlying the different performance. The study is expected to help for better understanding of the two different types of algorithm.

Reproducible disease phenotyping at scale: Example of coronary artery disease in UK Biobank.

A lack of internationally agreed standards for combining available data sources at scale risks inconsistent disease phenotyping limiting research reproducibility. To develop and then evaluate if a rules-based algorithm can identify coronary artery disease (CAD) sub-phenotypes using electronic health records (EHR) and questionnaire data from UK Biobank (UKB). Case-control and cohort study. Prospective cohort study of 502K individuals aged 40-69 years recruited between 2006-2010 into the UK Biobank with linked hospitalization and mortality data and genotyping. We included all individuals for phenotyping into 6 predefined CAD phenotypes using hospital admission and procedure codes, mortality records and baseline survey data. Of these, 408,470 unrelated individuals of European descent had a polygenic risk score (PRS) for CAD estimated. CAD Phenotypes. Association with baseline risk factors, mortality (n = 14,419 over 7.8 years median f/u), and a PRS for CAD. The algorithm classified individuals with CAD into prevalent MI (n = 4,900); incident MI (n = 4,621), prevalent CAD without MI (n = 10,910), incident CAD without MI (n = 8,668), prevalent self-reported MI (n = 2,754); prevalent self-reported CAD without MI (n = 5,623), yielding 37,476 individuals with any type of CAD. Risk factors were similar across the six CAD phenotypes, except for fewer men in the self-reported CAD without MI group (46.7% v 70.1% for the overall group). In age- and sex- adjusted survival analyses, mortality was highest following incident MI (HR 6.66, 95% CI 6.07-7.31) and lowest for prevalent self-reported CAD without MI at baseline (HR 1.31, 95% CI 1.15-1.50) compared to disease-free controls. There were similar graded associations across the six phenotypes per SD increase in PRS, with the strongest association for prevalent MI (OR 1.50, 95% CI 1.46-1.55) and the weakest for prevalent self-reported CAD without MI (OR 1.08, 95% CI 1.05-1.12). The algorithm is available in the open phenotype HDR UK phenotype library (https://portal.caliberresearch.org/). An algorithmic, EHR-based approach distinguished six phenotypes of CAD with distinct survival and PRS associations, supporting adoption of open approaches to help standardize CAD phenotyping and its wider potential value for reproducible research in other conditions.

Managing prior approval for site-of-service referrals: an algorithmic approach

ObjectivesMany payers and health care providers are either currently using or considering use of prior authorization schemes to redirect patient care away from hospital outpatient departments toward free-standing ambulatory surgical centers owing to the payment differential between these facilities. In this work we work with a medium size payer to develop and lay out a process for analysis of claims data that allows payers to conservatively estimate potential savings from such policies based on their specific case mix and provider network.Study DesignWe analyzed payment information for a medium-sized managed care organization to identify movable cases that can reduce costs, estimate potential savings, and recommend implementation policy alternatives.MethodsWe analyze payment data, including all professional and institutional fees over a 15-month period. A rules-based algorithm was developed to identify episodes of care with at least one alternate site for each episode, and potential savings from a site-of-service policy.ResultsData on 64,884 episodes of care were identified as possible instances that could be subject to the policy. Of those, 7,679 were found to be attractive candidates for movement. Total projected savings was approximately $8.2 million, or over $1,000 per case.ConclusionsInstituting a site-of-service policy can produce meaningful savings for small and medium payers. Tailoring the policy to the specific patient and provider population can increase the efficacy of such policies in comparison to policies previously established by other payers.

Rules Based Algorithm for AI game JADDWAL

The video game landscape is populated by games that rely on AI to make the player have a challenging and enjoyable experience, especially as games keep getting better and better in terms of performance and technology, soon it will be hard to ignore it as just a game and perceive it as a technological accomplishment, In this paper, we implemented a Rules-Based Algorithm to create an AI for a relatively simple game, We further analyze how the AI works and functions and if it would be the best suited for a simple video board game.&#x0D; :

Clinical insights into pulmonary hypertension in chronic obstructive pulmonary disease.

Pulmonary hypertension (PH) is a common complication of chronic obstructive pulmonary disease (COPD). Little is known about the prevalence and clinical profiles of patients with COPD-PH. We report the clinical characteristics, hemodynamic profiles, and prognosis in a large population of patients with COPD referred for right heart catheterization (RHC). We extracted data from all patients referred for RHC between 1997 and 2017 in Vanderbilt's deidentified medical record. PH was defined as mean pulmonary artery pressure >20 mmHg. Pre- and postcapillary PH were defined according to contemporary guidelines. COPD was identified using a validated rules-based algorithm requiring international classification of diseases codes relevant to COPD. We identified 6065 patients referred for RHC, of whom 1509 (24.9%) had COPD and 1213 had COPD and PH. Patients with COPD-PH had a higher prevalence of diabetes, atrial fibrillation, and heart failure compared with COPD without PH. Approximately 55% of patients with COPD-PH had elevated left ventricle(LV)filling pressure. Pulmonary function testing data from individuals with COPD-PH revealed subtype differences, with precapillary COPD-PH having lower diffusion capacity of the lungs for carbon monoxide (DLCO) values than the other COPD-PH subtypes. Patients with COPD-PH had significantly increased mortality compared with COPD alone (hazard ratio[HR]: 1.70, 95% confidence interval [CI]: 1.28-2.26) with the highest mortality among the combined pre- and postcapillary COPD-PH subgroup (HR: 2.39; 95% CI: 1.64-3.47). PH is common among patients with COPD referred for RHC. The etiology of PH in patients with COPD is often mixed due to multimorbidity and is associated with high mortality, which may have implications for risk factor management.

Development and Evaluation of a Rules-based Algorithm for Primary Open-Angle Glaucoma in the VA Million Veteran Program

ABSTRACT The availability of electronic health record (EHR)-linked biobank data for research presents opportunities to better understand complex ocular diseases. Developing accurate computable phenotypes for ocular diseases for which gold standard diagnosis includes imaging remains inaccessible in most biobank-linked EHRs. The objective of this study was to develop and validate a computable phenotype to identify primary open-angle glaucoma (POAG) through accessing the Department of Veterans Affairs (VA) Computerized Patient Record System (CPRS) and Million Veteran Program (MVP) biobank. Accessing CPRS clinical ophthalmology data from VA Medical Center Eye Clinic (VAMCEC) patients, we developed and iteratively refined POAG case and control algorithms based on clinical, prescription, and structured diagnosis data (ICD-CM codes). Refinement was performed via detailed chart review, initially at a single VAMCEC (n = 200) and validated at two additional VAMCECs (n = 100 each). Positive and negative predictive values (PPV, NPV) were computed as the proportion of CPRS patients correctly classified with POAG or without POAG, respectively, by the algorithms, validated by ophthalmologists and optometrists with access to gold-standard clinical diagnosis data. The final algorithms performed better than previously reported approaches in assuring the accuracy and reproducibility of POAG classification (PPV >83% and NPV >97%) with consistent performance in Black or African American and in White Veterans. Applied to the MVP to identify cases and controls, genetic analysis of a known POAG-associated locus further validated the algorithms. We conclude that ours is a viable approach to use combined EHR-genetic data to study patients with complex diseases that require imaging confirmation.

Enhanced Detection of Heart Valve Disease Using Integrated Artificial Intelligence at Scale

BackgroundUndertreatment of heart valve disease creates unnecessary patient risk. Poorly integrated healthcare data systems are unequipped to solve this problem. A software program using a rules-based algorithm to search the electronic health record for heart valve disease among patients treated by healthcare systems in the United States may provide a solution. MethodsA software interface allowed concurrent access to picture archiving communication systems, the electronic health record, and other sources. The software platform was created to programmatically run a rules engine to search structured and unstructured data for identification of moderate or severe heart valve disease using guideline-reported values. Incidence and progression of disease as well as compliance with a care pathway were assessed. ResultsIn 2 health institutions in the United States 60,145 patients had 77,215 echocardiograms. Moderate or severe aortic stenosis (AS) was identified at a rate of 9.1% of patients (5474 and 6910 echocardiograms) in this population. The precision and accuracy of the algorithm for the detection of moderate or severe AS was 92.9% and 98.6%, respectively. Thirty-five percent of patients (441/1265) with moderate stenosis and a subsequent echocardiogram progressed to severe stenosis (mean interval, 358 days). In 1 sample 70.3% of moderate AS patients lacked a 6-month echocardiogram or appointment. The platform enabled 100% accountability for all patients with severe AS. ConclusionsA rules-based software program enhances detection of heart valve disease and can be used to measures disease progression and care pathway compliance.

UCARE Chem Suite and uCAREChemSuiteCLI: An online tool and a standalone R package for the prediction of drug resistome

Background: In the era of antibiotic resistance, the prediction of bacterial resistome profiles, likely to cause resistance against novel drugs is of utmost importance. Despite this, to the best of our knowledge, no tool exists for the same. Therefore, with the rationale that drugs with similar structures have similar resistome profiles, two algorithms were developed viz., the deterministic model and the stochastic model to predict bacterial resistome for uncharacterized, but potential chemical structures. Methods and materials: Two separate databases were developed for Escherichia coli and Pseudomonas aeruginosa through exhaustive manual curation of published literature. Prediction of drug classes and bacterial resistome was carried out by the rules-based algorithm in the deterministic model, whereas the nearest neighbor algorithm was utilized in the stochastic model. Results: The models have been implemented in both standalone R package and an online server i.e., uCAREChemSuiteCLI and uCARE Chem Suite. In addition to resistome prediction, the online version of the suite enables the user to visualize the chemical structure, classify compound in predefined 19 drug classes, perform pairwise alignment and cluster with database compounds using graphical user interface. uCARE Chem Suite can be browsed from http://ucare.chem.e-bioinformatics.net, whereas uCAREChemSuiteCLI can be installed from CRAN (https://cran.r-project.org/package=uCAREChemSuiteCLI) and GitHub (https://github.com/sauravbsaha/uCAREChemSuiteCLI). Conclusion: We envisage that the said tool will enable the acceleration of the traditional drug discovery pipeline.

Derivative Based Gait Event Detection Algorithm Using Unfiltered Accelerometer Signals.

Wearable sensors have been investigated for the purpose of gait analysis, namely gait event detection. Many types of algorithms have been developed specifically using inertial sensor data for detecting gait events. Though much attention has turned toward machine learning algorithms, most of these approaches suffer from large computational requirements and are not yet suitable for real-time applications such as in prostheses or for feedback control. Current rules-based algorithms for real-time use often require fusion of multiple sensor signals to achieve high accuracy, thus increasing complexity and decreasing usability of the instrument. We present our results of a novel, rules-based algorithm using a single accelerometer signal from the foot to reliably detect heel-strike and toe-off events. Using the derivative of the raw accelerometer signal and applying an optimizer and windowing approach, high performance was achieved with a sensitivity and specificity of 94.32% and 94.70% respectively, and a timing error of 6.52 ± 22.37 ms, including trials involving multiple speed transitions. This would enable development of a compact wearable system for robust gait analysis in real-world settings, providing key insights into gait quality with the capability for real-time system control.

Optimal design of a university campus micro-grid operating under unreliable grid considering PV and battery storage

This paper proposes a novel methodology for redesigning a micro-grid characterized by a heavy reliance on diesel generators due to receiving power supply from an unreliable grid. The new design aims at phasing out the diesel generators and replacing them with a hybrid energy system composed of photovoltaics and a battery storage system. Two optimization approaches are adopted, a heuristic genetic algorithm approach is used to achieve sub-optimal sizing of the hybrid system sources and a rules-based dynamic programming approach to ensure optimal power flow. In order to reduce the computation time, a novel combinational approach employing genetic algorithm, dynamic programming and rules-based algorithm is proposed. The intervention of the dynamic programming for optimal power flow is restricted to certain active hours within a given day, while the rules-based power flow algorithm runs only outside those hours. The study demonstrates that the application of the hybrid system yields minimal operational cost by almost entirely phasing out the diesel generators and significantly reducing the energy purchased from the grid during peak hours. The micro-grid of a university campus is used as a case study where energy and economic indicators are derived to prove the superiority of the proposed techniques.

A Mobile Phone-Based Telemonitoring Program for Heart Failure Patients After an Incidence of Acute Decompensation (Medly-AID): Protocol for a Randomized Controlled Trial.

BackgroundPatients with heart failure (HF) are at the highest risk for hospital readmissions during the first few weeks after discharge when patients are transitioning from hospital to home. Telemonitoring (TM) for HF management has been found to reduce mortality risk and hospital readmissions if implemented appropriately; however, the impact of TM targeted for patients recently discharged from hospital, for whom TM might have the biggest benefit, is still unknown. Medly, a mobile phone–based TM system that is currently being used as a standard of care for HF at a large Canadian hospital, may be an effective tool for the management of HF in patients recently discharged from hospital.ObjectiveThe objective of the Medly-After an Incidence of acute Decompensation (Medly-AID) trial is to determine the effect of Medly on the self-care and quality of life of patients with HF who have been recently discharged from hospital after an HF-related decompensation.MethodsA multisite multimethod randomized controlled trial (RCT) will be conducted at 2 academic hospitals and at least one community hospital to evaluate the impact of Medly-enabled HF management on the outcomes of patients with HF who had been hospitalized for HF-related decompensation and discharged during the 2 weeks before recruitment. The trial will include 144 participants with HF (74 in each control and intervention groups). Control patients will receive standard of care, whereas patients in the intervention group will receive standard of care and Medly. Specifically, patients in the intervention group will record daily weight, blood pressure, and heart rate and answer symptom-related questions via the Medly app. Medly will generate automated patient self-care messages such as to adjust diuretic medications, based on the rules-based algorithm personalized to the individual patient, and send real-time alerts to their health care providers as necessary. All patients will be followed for 3 months. Primary outcome measures are self-care and quality of life as measured through the validated questionnaires Self-Care of Heart Failure Index, EQ-5D-5L, and the Kansas City Cardiomyopathy Questionnaire-12. Secondary outcome measures for this study include cost of health care services used and health outcomes.ResultsPatient recruitment began in November 2018 at the Sunnybrook Health Sciences Centre, with a total of 35 participants recruited by July 30, 2019 (17 in the intervention group and 18 in the control group). The final analysis is expected to occur in the fall of 2020.ConclusionsThis RCT will be the first to assess the effectiveness of the Medly TM system for use following discharge from hospital after a HF-related decompensation.Trial RegistrationClinicalTrials.gov NCT03358303; https://clinicaltrials.gov/ct2/show/NCT03358303International Registered Report Identifier (IRRID)DERR1-10.2196/15753

Investigating Asthma, Allergic Disease, Passive Smoke Exposure, and Risk of Rheumatoid Arthritis.

Rheumatoid arthritis (RA) is postulated to originate at mucosal surfaces, particularly the airway mucosa. To investigate this hypothesis, we determined the association between RA and asthma, passive smoke exposure, and age at start of smoking. For this case-control study, we identified 1,023 cases of RA (175 incident) within a single-center biobank population, using a rules-based algorithm that combined self-report with 2 diagnostic codes. Exposures were self-reported on biobank questionnaires. Logistic regression models were used to calculate the association of exposures with RA, adjusting for potential confounders. Odds ratios (ORs) with 95% confidence intervals (95% CIs) were calculated. After adjustment for allergies, urban environment, and passive smoke exposure, asthma was found to be associated with RA in the full cohort (OR 1.28 [95% CI 1.04-1.58; P = 0.02]) but not the incident RA cohort (OR 1.17 [95% CI 0.66-2.06; P = 0.60]). History of allergic disease was associated with RA in both the full cohort (OR 1.30 [95% CI 1.12-1.51; P < 0.001]) and the incident RA cohort (OR 1.61 [95% CI 1.11-2.33; P = 0.01]), especially food allergy, which was significantly associated with RA in the full cohort (OR 1.38 [95% CI 1.08-1.75; P = 0.01]) and showed a trend toward significance in the incident RA cohort (OR 1.83 [95% CI 0.97-3.45; P = 0.06]). Passive smoke exposure at home or work was not associated with RA. Finally, age at start of smoking was not associated with increased odds of developing RA in either the full cohort (OR 1.03 [95% CI 1.00-1.06; P = 0.03]) or the incident RA cohort (OR 1.00 [95% CI 0.92-1.08; P = 0.98]). Asthma and allergies may be associated with increased risk of RA. Passive smoke exposure and early age at start of smoking do not appear to influence risk of RA.

Implementation of energy management strategy of hybrid power source for electrical vehicle

Managing the energy is one of the most important issues for the efficiency of vehicular applications using hybrid electric power systems. This paper deals with an analysis of an energy management for hybrid power system, which consists of fuel cell, ultra-capacitor and battery and dedicated to electrical vehicles. Thus, an energy management method is applied in order to split the energy flow between the three used sources. This strategy is based on a combination of three control methods; a fuzzy logic control, a flatness control and rule-based algorithm. For the fuzzy logic, the main idea is inspired from rule-based algorithms except that it is more flexible and less aggressive. The second technic is an innovative control using the flatness property for a Fuel cell/ supercapacitor/ Battery hybrid power system. For the rules based algorithm, it uses a supercapacitor state-of-charge control principle. Then, an experimental validation is done for the energy management method to show the efficiency of the proposed control strategy in term of the well share of the energy between sources to satisfy the load demand. A dSpace real-time card is used for management algorithm implementation and data acquisition. The obtained experimental results prove the efficiency and the validity of the proposed supervisor.