Biomathematical Model Research Articles

Artificial Intelligence by Artificial Neural Networks to Simulate Oat (Avena sativa L.) Grain Yield Through the Growing Cycle

Artificial neural networks simulating oat grain yield throughout the crop cycle, can represent an innovative proposal regarding management and decision making, reducing costs and maximizing profits. The objective of the study is to develop biomathematical models via artificial neural networks, capable of predicting the productivity of oat grains by meteorological variables, nitrogen management and biomass obtained throughout the development cycle, making it possible to plan more efficient and sustainable managements. In each cultivation system (soybeans/oats; maize/oats), two experiments were carried out in 2017 and 2018, one for analyzing grain yield and the other for cutting every 30 days to obtain biomass. The experiments were conducted in a randomized block design with four replications for four levels of N-fertilizer (0, 30, 60 and 120 kg ha-1), applied in the stage of the 4th expanded leaf. The use of the artificial neural network makes it possible to predict grain yield by harvesting the biomass obtained at any stage of oat development, together with the handling of the nitrogen dose and meteorological information during cultivation. Therefore, a new tool to aid the simulation of oat productivity throughout the cycle, facilitating faster decision making for more efficient and sustainable management with the crop.

Dynamical Characteristics and Signal Flow Graph of Nonlinear Fractional Smoking Mathematical Model

Abstract In this article, we study approximate analytic solutions for one of the famous models in biomathematics, namely the nonlinear fractional mathematical smoking model. When alpha=1, we deduce the analytical solution using the Reduced differential transforms method (RDTM) for the nonlinear ordinary mathematical smoking model. The disease-free equilibrium point, the stability of the equilibrium point, and the reproduction number are all discussed for the fractional mathematical smoking model. We use mathematical software packages such as Mathematica to find more iteration when calculating the approximate solution. Results are presented graphically to illustrate the behavior of the obtained approximate solutions. The system is presented by a proposed novel signal flow graph and simulated via SIMULINK/MATLAB. The graph of signal flow is used to calculate some of the model invariants such as the adjacency matrix, model energy, and Estrada index. Also, the novelty and significance of the results are clear using a 3D plot.

Changes in performance and bio-mathematical model performance predictions during 45 days of sleep restriction in a simulated space mission

Lunar habitation and exploration of space beyond low-Earth orbit will require small crews to live in isolation and confinement while maintaining a high level of performance with limited support from mission control. Astronauts only achieve approximately 6 h of sleep per night, but few studies have linked sleep deficiency in space to performance impairment. We studied crewmembers over 45 days during a simulated space mission that included 5 h of sleep opportunity on weekdays and 8 h of sleep on weekends to characterize changes in performance on the psychomotor vigilance task (PVT) and subjective fatigue ratings. We further evaluated how well bio-mathematical models designed to predict performance changes due to sleep loss compared to objective performance. We studied 20 individuals during five missions and found that objective performance, but not subjective fatigue, declined from the beginning to the end of the mission. We found that bio-mathematical models were able to predict average changes across the mission but were less sensitive at predicting individual-level performance. Our findings suggest that sleep should be prioritized in lunar crews to minimize the potential for performance errors. Bio-mathematical models may be useful for aiding crews in schedule design but not for individual-level fitness-for-duty decisions.

Fatigue in surgical residents an analysis of duty-hours and the effect of hypothetical naps on predicted performance

PurposeSleep loss and fatigue, common in resident physicians, are related to increased medical errors and decreased physician wellbeing. Biomathematical modeling of fatigue can illuminate the relationship between surgical resident fatigue and work scheduling. MethodsGeneral surgery resident schedules were analyzed using the Sleep, Activity, Fatigue and Task Effectiveness model to predict resident performance during work hours. Hypothetical naps were built into the model to assess their effect on predicted performance and fatigue risk. Results12 months of duty-hours logged by 89 residents, ranging from post-graduate year (PGY) 1–5, were analyzed. Residents had moderate levels of fatigue risk over 12 month schedules, with at least an 8-h sleep debt during 24.36% of shifts. Performance scores decreased as shift lengths increased. The addition of hypothetical naps increased predicted performance and reduced shift time with fatigue risk. ConclusionsBiomathematical modeling of resident schedules and predicts a concerning level of fatigue and decreased effectiveness. Naps may improve performance without decreasing scheduled hours.

Optimal control, signal flow graph, and system electronic circuit realization for nonlinear Anopheles mosquito model

We study the estimated investigative answers for one of the popular models in biomathematics, in particular, the nonlinear Anopheles mosquito model numerically. The optimal control (OC) for nonlinear Anopheles mosquito model is examined. Important and adequate conditions to ensure the presence and singularity of the arrangements of the control issue are assumed. Two control factors are suggested to limit the normal measure of eggs laid per treated female every day. The signal stream chart and Simulink[Formula: see text]Matlab of this model are constructed. The framework is designed utilizing the MULTISIM simulation program. We utilize the homotopy disruption strategy (HPM) to examine the logical surmised answer for the nonlinear control issue. We utilize the mathematical programming bundles, for example, Maple, to emphasize while ascertaining the rough arrangement. Results are displayed graphically and introduced to delineate the conduct of obtained inexact arrangements.

Study on the ability of 3D gamma analysis and bio-mathematical model in detecting dose changes caused by dose-calculation-grid-size (DCGS)

ObjectiveTo explore the efficacy and sensitivity of 3D gamma analysis and bio-mathematical model for cervical cancer in detecting dose changes caused by dose-calculation-grid-size (DCGS).Methods17 patients’ plans for cervical cancer were enrolled (Pinnacle TPS, VMAT), and the DCGS was changed from 2.0 mm to 5.0 mm to calculate the planned dose respectively. The dose distribution calculated by DCGS = 2.0 mm as the “reference” data set (RDS), the dose distribution calculated by the rest DCGS as the“measurement”data set (MDS), the 3D gamma passing rates and the (N) TCPs of the all structures under different DCGS were obtained, and then analyze the ability of 3D gamma analysis and (N) TCP model in detecting dose changes and what factors affect this ability.ResultsThe effect of DCGS on planned dose was obvious. When the gamma standard was 1.0 mm, 1.0 and 10.0%, the difference of the results of the DCGS on dose-effect could be detected by 3D gamma analysis (all p value < 0.05). With the decline of the standard, 3D gamma analysis’ ability to detect this difference shows weaker. When the standard was 1.0 mm, 3.0 and 10.0%, the p value of > 0.05 accounted for the majority. With DCGS = 2.0 mm being RDS, ∆gamma-passing-rate presented the same trend with ∆(N) TCPs of all structures except for the femurs only when the 1.0 mm, 1.0 and 10.0% standards were adopted for the 3D gamma analysis.ConclusionsThe 3D gamma analysis and bio-mathematical model can be used to analyze the effect of DCGS on the planned dose. For comparison, the former’s detection ability has a lot to do with the designed standard, and the latter’s capability is related to the parameters and calculated accuracy instrinsically.

Volume-dependent dose–response of the intestinal stem cell niche and lymphoid tissue

Background and purposePlasticity of the intestinal stem cell compartment in response to radiation injury is regulated by a stem cell niche. We present here the first experimental observations of a dose-volume effect of the intestinal stem cell niche and of the solitary intestinal lymphoid tissues (SILT). Materials and methodsRegeneration of intestinal crypts in mice was studied following irradiation of millimetre-size jejunal sections with single doses of 6 to 24 Gy and compared to total body irradiation (TBI). The statistical distribution of cells per crypt was scored and regressed to a biomathematical model. The number of SILTs was scored for different doses and field sizes and crypt regeneration was correlated with SILT proximity. ResultsWe observed a differential dose–response of the intestinal stem cell niche at the centres of the irradiated sections, but only for field sizes below 10 mm. Irradiation of 5 mm jejunum results in an increase in crypt survival by up to an order of magnitude, compared to TBI. Distributions of cell-per-crypt numbers and comparison to biomathematical modelling suggest that these observations stem from a field size-dependent regeneration rate. The density of SILTs also exhibits a volume-dependent dose–response and increased crypt survival correlates with a proximity to SILTs. ConclusionOur findings present the first observation of a field-size dependent dose–response of the intestinal stem cell niche. Its regeneration process does apparently not rely on distant radiation-sensitive resources of the organism, such as the bone marrow. Yet, our observations suggest that the niche interacts with intact tissue in millimetres distance, leading to faster crypt regeneration. The field-size dependent dose–response of SILTs posits a role of the immune system on the dose-volume effect.

Sleep health and predicted cognitive effectiveness of nurses working 12-hour shifts: an observational study

BackgroundDue to the 24hr nature of society, shift work has become an integral part of many industries. Within the literature there exists an abundance of evidence linking shift work-related sleep restriction and fatigue with errors, accidents, and adverse long-term health outcomes. ObjectiveThe study goal was to physiologically measure sleep patterns and predicted cognitive decline of nurses working both 12hr day and night shifts to address the growing concern about sleep restriction among healthcare workers. DesignThis study presents the results of a quasi-experimental, mixed between-within design where the sleep of 12hr day and night shift nurses was measured using ReadiBand wrist actigraphs. The between groups component was comprised of day v. night shift nurses. The within groups component was comprised of two separate measurement periods for each nurse—once for three consecutive days while they were working shifts (on duty) and once for three consecutive days off work (off duty). SettingParticipants wore the wrist actigraph at home and in the hospital, and were instructed to adhere to their regular sleep schedule. ParticipantsParticipants were recruited from two hospitals in Washington State (n=90). Participants were 48 night- and 42 day-shift nurses. All participants worked 12-hour shifts. MethodsSleep was measured using ReadiBand wrist actigraphs, which are licensed with the Sleep, Activity, Fatigue, and Task Effectiveness (SAFTEtm) Alertness Score model, a biomathematical model that predicts cognitive effectiveness based on sleep/wake schedule. ReadiBands also calculate sleep quantity, sleep efficiency, and sleep latency. Results were analysed in SPSS (v26) through multilevel modelling. ResultsDifferences were observed in sleep quantity, efficiency, and latency based on shift type (day vs. night) and shift duty (on vs. off). The most extreme differences, however, were noted in cognitive effectiveness (SAFTEtm), whereby night shift nurses experienced substantial decline—frequently into the “high risk” zone—throughout their shifts compared to day shift nurses. ConclusionsThe present study identifies sleep characteristics that differ between day and night nurses working 12-hour shifts using objective measurements of sleep. Biomathematical modelling can offer a novel method to estimate hours of greatest cognitive decline, and have implications for policy around shift duration, timing, and overtime allocation.

0218 Biomathematical Modeling Predicts Fatigue Risk in General Surgery Residents

Abstract Introduction Fatigue and its effects on performance have long been a concern in medicine. Evidence exists that current duty-hour restrictions for resident trainees have a limited impact on physician wellbeing and patient safety, prompting renewed efforts to address this threat. In this study, sleep patterns of general-surgery residents were used to optimize a biomathematical model of performance for use as a tool for fatigue risk management with residents. Methods General surgery residents based at a multi-hospital, general surgery residency program were approached for participation in this study. Enrolled residents wore actigraph devices for 8 weeks and completed subjective sleep assessments. Sleep data and shift schedules were then input into the Sleep, Activity, Fatigue and Task Effectiveness (SAFTE) Model to assess predicted cognitive performance. Performance was compared to an “effectiveness” level of 77 (equivalent to a blood-alcohol content of 0.05g/dL). Eight hours of sleep debt was considered “below reservoir criteria”. Results Sleep actigraphy data was collected from 22 general surgery residents. Modeling results showed that as shift lengths increased, effectiveness scores generally decreased, and the time spent below criterion (77) increased. Additionally, 11.13% of time on shift was below the effectiveness criterion and 42.7% of shifts included time spent below the reservoir criterion. Adjustments to the sleep prediction were made based on actual sleep, and performance predictions from actual sleep and the adjusted model were significantly correlated (p&amp;lt;.0001). Conclusion Despite adherence to national standards limiting work hours, current surgical resident sleep patterns and shift schedules create concerning levels of fatigue. This study illustrates how biomathematical fatigue models can predict resident physician sleep patterns and performance. Modeling represents a novel and important tool for medical educators seeking to create shift schedules that maintain physician preparedness and minimize fatigue risk. Support N/A

Sleepiness on the flight deck: Reported rates of occurrence and predicted fatigue risk exposure associated with UK airline pilot work schedules

Survey and field studies conducted with commercial airline pilots suggest that in-flight sleepiness and related involuntary sleep phenomena are experienced by pilots during their duties. However, for methodological, practical and commercial reasons, there is a lack of publicly available research data of per-flight hour rates of sleepiness experienced by pilots or predicted fatigue risk rates associated with pilots’ hours of work. This empirical field study sought to address this gap by collecting self-reported sleepiness/alertness ratings from pilots from 18 different UK airlines via a mobile phone app over the period of August 2017. In tandem, predicted sleepiness levels and sleep opportunities associated with participants’ flown rosters were investigated using biomathematical fatigue modelling. Findings indicated that a quarter of all flying duty periods were predicted to be preceded by a main sleep opportunity shorter than six hours, whilst 10% of all flying hours were associated with elevated fatigue risk levels. Pilots reported 7.3 reports of involuntary sleep on the flight deck per 1000 flying hours, which represents a rate far greater than that previously reported to the regulator. By comparison, the rates of predicted and recorded fatigue-related incapacitations greatly exceeded the target rate of medical incapacitation permissible under the medical incapacitation safety standard for commercial aviation of less than one occurrence per 1,000,000 h.

A biomathematical model of human erythropoiesis and iron metabolism

Anaemia therapy or perisurgical support of erythropoiesis often require both, EPO and iron medication. However, excessive iron medication can result in iron overload and it is challenging to control haemoglobin levels in a desired range. To support this task, we develop a biomathematical model to simulate EPO- and iron medication in humans. We combine our previously established model of human erythropoiesis including comprehensive pharmacokinetic models of EPO applications with a newly developed model of iron metabolism including iron supplementation. Equations were derived by translating known biological mechanisms into ordinary differential equations. Qualitative model behaviour is studied in detail considering a variety of interventions such as bleeding, iron malnutrition and medication. The model can explain time courses of erythrocytes, reticulocytes, haemoglobin, haematocrit, red blood cells, EPO, serum iron, ferritin, transferrin saturation, and transferrin under a variety of scenarios including EPO and iron application into healthy volunteers or chemotherapy patients. Unknown model parameters were determined by fitting the predictions of the model to time series data from literature. We demonstrate how the model can be used to make predictions of untested therapy options such as cytotoxic chemotherapy supported by iron and EPO. Following our ultimate goal of establishing a model of anaemia treatment in chronic kidney disease, we aim at translating our model to this pathological condition in the near future.

Sex-specific impact of patterns of imageable tumor growth on survival of primary glioblastoma patients

BackgroundSex is recognized as a significant determinant of outcome among glioblastoma patients, but the relative prognostic importance of glioblastoma features has not been thoroughly explored for sex differences.MethodsCombining multi-modal MR images, biomathematical models, and patient clinical information, this investigation assesses which pretreatment variables have a sex-specific impact on the survival of glioblastoma patients (299 males and 195 females).ResultsAmong males, tumor (T1Gd) radius was a predictor of overall survival (HR = 1.027, p = 0.044). Among females, higher tumor cell net invasion rate was a significant detriment to overall survival (HR = 1.011, p < 0.001). Female extreme survivors had significantly smaller tumors (T1Gd) (p = 0.010 t-test), but tumor size was not correlated with female overall survival (p = 0.955 CPH). Both male and female extreme survivors had significantly lower tumor cell net proliferation rates than other patients (M p = 0.004, F p = 0.001, t-test).ConclusionDespite similar distributions of the MR imaging parameters between males and females, there was a sex-specific difference in how these parameters related to outcomes.

Fatigue and short-term unplanned absences among police officers

PurposeThe purpose of this paper is to assess whether shift work, sleep loss and fatigue are related to short-term unplanned absences in policing.Design/methodology/approachN = 367 police officers from the Buffalo Police Department were studied. Day-by-day work and sick leave data were obtained from the payroll. Absenteeism was defined as taking a single sick day on a regularly scheduled workday. Biomathematical models of fatigue (BMMF) predicted officers' sleep–wake behaviors and on-duty fatigue and sleepiness. Prior sleep, fatigue and sleepiness were tested as predictors of absenteeism during the next shift.FindingsA total of 513,666 shifts and 4,868 cases of absenteeism were studied. The odds of absenteeism increased as on-duty fatigue and sleepiness increased and prior sleep decreased. This was particularly evident for swing shift officers and night shift officers who were predicted by BMMF to obtain less sleep and have greater fatigue and sleepiness than day shift officers. The odds of absenteeism were higher for female officers than male officers; this finding was not due to a differential response to sleep loss, fatigue or sleepiness.Practical implicationsAbsenteeism may represent a self-management strategy for fatigue or compensatory behavior to reduced sleep opportunity. Long and irregular work hours that reduce sleep opportunity may be administratively controllable culprits of absenteeism.Originality/valuePolice fatigue has consequences for police officers, departments and communities. BMMF provide a potential tool for predicting and mitigating police fatigue. BMMF were used to investigate the effects of sleep and fatigue on absenteeism.

Biomathematical model for gyrotactic free-forced bioconvection with oxygen diffusion in near-wall transport within a porous medium fuel cell

Bioconvection has shown significant promise for environmentally friendly, sustainable “green” fuel cell technologies. The improved design of such systems requires continuous refinements in biomathematical modeling in conjunction with laboratory and field testing. Motivated by exploring deeper the near-wall transport phenomena involved in bio-inspired fuel cells, in the present paper, we examine analytically and numerically the combined free-forced convective steady boundary layer flow from a solid vertical flat plate embedded in a Darcian porous medium containing gyrotactic microorganisms. Gyrotaxis is one of the many taxes exhibited in biological microscale transport, and other examples include magneto-taxis, photo-taxis, chemotaxis and geo-taxis (reflecting the response of microorganisms to magnetic field, light, chemical concentration or gravity, respectively). The bioconvection fuel cell also contains diffusing oxygen species which mimics the cathodic behavior in a proton exchange membrane (PEM) system. The vertical wall is maintained at iso-solutal (constant oxygen volume fraction and motile microorganism density) and iso-thermal conditions. Wall values of these quantities are sustained at higher values than the ambient temperature and concentration of oxygen and biological microorganism species. Similarity transformations are applied to render the governing partial differential equations for mass, momentum, energy, oxygen species and microorganism species density into a system of ordinary differential equations. The emerging eight order nonlinear coupled, ordinary differential boundary value problem features several important dimensionless control parameters, namely Lewis number (Le), buoyancy ratio parameter i.e. ratio of oxygen species buoyancy force to thermal buoyancy force (Nr), bioconvection Rayleigh number (Rb), bioconvection Lewis number (Lb), bioconvection Péclet number (Pe) and the mixed convection parameter ([Formula: see text] spanning the entire range of free and forced convection. The transformed nonlinear system of equations with boundary conditions is solved numerically by a finite difference method with central differencing, tridiagonal matrix manipulation and an iterative procedure. Computations are validated with the symbolic Maple 14.0 software. The influence of buoyancy and bioconvection parameters on the dimensionless temperature, velocity, oxygen concentration and motile microorganism density distribution, Nusselt, Sherwood and gradient of motile microorganism density are studied. The work clearly shows the benefit of utilizing biological organisms in fuel cell design and presents a logical biomathematical modeling framework for simulating such systems. In particular, the deployment of gyrotactic microorganisms is shown to stimulate improved transport characteristics in heat and momentum at the fuel cell wall.

Sleep-wake behaviors exhibited by shift workers in normal operations and predicted by a biomathematical model of fatigue.

To compare rail workers' actual sleep-wake behaviors in normal operations to those predicted by a biomathematical model of fatigue (BMMF). To determine whether there are group-level residual sources of error in sleep predictions that could be modeled to improve group-level sleep predictions. The sleep-wake behaviors of 354 rail workers were examined during 1,722 breaks that were 8-24 h in duration. Sleep-wake patterns were continuously monitored using wrist-actigraphy and predicted from the work-rest schedule using a BMMF. Rail workers' actual and predicted sleep-wake behaviors were defined as split-sleep (i.e. ≥2 sleep periods in a break) and consolidated-sleep (i.e. one sleep period in a break) behaviors. Sleepiness was predicted from the actual and predicted sleep-wake data. Consolidated-sleep behaviors were observed during 1,441 breaks and correctly predicted during 1,359 breaks. Split-sleep behaviors were observed during 280 breaks and correctly predicted during 182 breaks. Predicting the wrong type of sleep-wake behavior resulted in a misestimation of hours of sleep during a break. Relative to sleepiness predictions derived from actual sleep-wake data, predicting the wrong type of sleep-wake behavior resulted in a misestimation of sleepiness predictions during the subsequent shift. All workers with the same work-rest schedule have the same predicted sleep-wake behaviors; however, these workers do not all exhibit the same sleep-wake behaviors in real-world operations. Future models could account for this group-level residual variance with a new approach to modeling sleep, whereby sub-group(s) may be predicted to exhibit one of a number of sleep-wake behaviors.

Biomathematical modelling for managing worker fatigue in civil engineering

Worker fatigue is an important risk factor in civil engineering and construction projects, particularly when night-time shift working is required. It is a significant cause of accidents and negatively affects health and well-being. Biomathematical models can be used to assess and reduce fatigue risk. Research funded by Tideway, the company delivering London’s Thames Tideway Tunnel, was carried out to explore the current use and knowledge of such models in tunnelling, and to produce guidance on how the models can be used for fatigue management within the wider construction industry. The research identified limitations in how the tunnelling sector currently applies fatigue modelling. Knowledge and understanding of the models need to increase throughout construction for them to be effective and used appropriately. It is also important for an industry consensus on acceptable fatigue risk to be reached.

Lockdown as an Intervention Measure to Mitigate the Spread of COVID-19: a modeling study.

INTRODUCTION: This work aims to develop a biomathematical transmission model of COVID-19, in the State of Sergipe, Brazil, to estimate the distribution of cases over time and project the impact on the spread of the epidemic outbreak due to interventions and control measures over the local population. METHODS: This is an epidemiological mathematical modeling study conducted to analyze the dynamics of the accumulated cases of COVID-19, which used a logistic growth model that adds a term of withdrawal of individuals as a control measure. Three possible COVID-19 propagation scenarios were simulated based on three different rates of withdrawal of individuals. They were adjusted with real data of the infected and measures of control over the population. RESULTS: The lockdown would be the best scenario, with a lower incidence of infected people, when compared to the other measures. The number of infected people would grow slowly over the months, and the number of symptomatic individuals in this scenario would be 40,265 cases. We noticed that the State of Sergipe is still in the initial stage of the disease in the scenarios. It was possible to observe that the peak of cases and the equilibrium, in the current situation of social isolation, will occur when reaching the new support capacity, at the end of August in approximately 1,171,353 infected individuals. CONCLUSIONS: We established that lockdown is the intervention with the highest ability to mitigate the spread of the virus among the population.

Vertebral Tumor Detection and Segmentation Using Analytical Transform Assisted Statistical Characteristic Decomposition Model

Recently, vertebral tumor prediction using image-based vertebral bio-mathematical modeling with accurate segmentation has been considered as a significant area of research. Further, precise lumbar spinal segmentation is essential to the clinicians for tumor analysis. Therefore, precise and reliable segmentation process is required to help radiologists and doctors to identify different vertebrae tumors with better prediction ratio. The exact vertebral disks segmentation of spinal bones from medical images is a complex process in dealing with different deformities and pathologies in accordance to the conventional techniques such as Deep Convolutional Neural Network (DCNN), Finite Element Analysis (FEA), Principal Component and Factor Analysis (PCFA), Multi-Parameter Ensemble Learning (MPEL), Hierarchical Conditional Random Forest (HCRF), and Deep Siamese Neural Network (DSNN). Therefore, to overcome the present drawbacks, Analytical Transform Assisted Statistical Characteristic Decomposition Model (ATS-CDM) is proposed in this paper for the accurate prediction of vertebral tumor detection and segmentation. This technique is used for the calibration of the segmentation procedures in vertebral tumor image prediction and Receiver Operating Curve (ROC) grading for the lumbar spines. The significant objective of the model-fitting algorithm iterates the tumor regions and measures the current region's variance for the accurate identification of tumor. The outcomes show potential and promising results at lab scale evaluation through analyzing the vertebral datasets with Intra-Discal Pressure (IDP) images for experimental validation with 98.7% bending and 98.88 % segmentation accuracy leads to 94.2 ± 0.2 % to 97.02 ± 0.2 % average ROCgrading.

On a delayed epidemic model with non-instantaneous impulses

We introduce a non-instantaneous pulse vaccination model. Non-instantaneous impulsive nonlinear differential equations provide an adequate biomathematical model of some medical problems. In this paper we study some basic properties such as the attractiveness of the infection-free periodic solution and the permanence of some sub-population for a vaccine model where a constant fraction of the susceptible population is vaccinated in some periodic way. Our model is a system of nonlinear differential equations with impulses.

Multimodal System to Detect Driver Fatigue Using EEG, Gyroscope, and Image Processing

Sleepiness detection system that evaluates driver’s sleepiness level has always been the primary interest of researchers. There are a number of systems like electroencephalography-based sleepiness detection system (ESDS), vehicle based sleepiness estimator system, image acquisition technology and bio-mathematical models to detect drowsiness of drivers. However there has been less research on hybrid of these systems that detect sleepiness of drivers. In order to overcome the above limitation we propose a neural network based hybrid multimodal system that detects driver fatigue using electroencephalography(EEG) data, gyroscope data and image processing data. It was found that the proposed hybrid system performed well with a detection accuracy of 93.91% in identifying the drowsiness state of the driver.