56 research outputs found
Development of Cardiovascular Disease Prediction System
No full textThis work presents the intelligent Cardiovascular Disease (CVD) prediction system based on machine learning, which uses Quantum Neural Network for machine learning. Early medical diagnosis of Heart disease is very important and should be performed accurately and efficiently. Unfortunately, the physicians don’t have the
enough time to analyze past history of patient in depth. This Intelligent system would enhance the medical care and reduce costs, by quick analysis of past data of patients with percentage of risk prediction. The accuracy of this intelligent system is significantly higher than other existing prognostic systems. All available Physical, Physiological, Clinical parameters have been considered in this study. The data of 815 Patients suffering with the symptoms of Heart disease has been collected from hospital and used for training and evaluation. Furthermore, the dataset of famous Framingham study consisting 5209 CVD patients’ data has been used for validation purpose. All the patients’ reports have been diagnosed and analysed by medical practitioner previously.
This system uses the Quantum Neural Network for machine learning. The results obtained have high degree of sensitivity and specificity that matches with the expert’s opinion with 98.5% accuracy. Such an expert system would be very useful when incorporated with other systems to provide diagnostic and predictive medical opinions in a timely manner. This system will work as an aid to physician for prognosis of heart disease. Using this system, medical practitioners may plan better medication and treatment strategy. The overall accuracy of this intelligent heart disease prognostic system is 98.5%, which is significantly higher than other existing approaches
Dynamics of Network Formation Processes in the Co-Author Model
No full textThis article studies the dynamics in the formation processes of a mutual consent network in game theory setting: the Co-Author Model. In this article, a limited observation is applied and analytical results are derived. Then, 2 parameters are varied: the number of individuals in the network and the initial probability of the links in the network in its initial state. A simulation result shows a finding that is consistent with an analytical result for a state of equilibrium while it also shows different possible equilibria.Dynamics, Network, Game Theory, Model,Simulation, Equilibrium, Complexity
A Novel Heart Disease Prediction System Based on Quantum Neural Network Using Clinical Parameters
No full textAims: The diagnosis of Heart disease at earliest possible stage is very crucial to increase the chance of successful treatment and to reduce the mortality rate. The interpretation of cardiovascular disease is time-consuming and requires analysis by an expert physician. Thus there is a need of expert system which may provide quick and accurate prediction of Heart disease at early possible stage, without the help of physician.
Place and Duration of Study: The study was carried out during 2010 to 2013 in the vicinity of Yamuna Nagar, Haryana, India.
Methodology: The data used for this study consists of clinical values (Diabetes Mellitus, Low Density Lipoprotein, Triglycerides and High Density Lipoprotein) and has been collected from various Hospitals of 689 patients, who have symptoms of heart disease. All these cases are analyzed after careful scrutiny with the help of the Physicians. For training and evaluation purpose we have carefully predicted the level of heart disease by taking the help of Cardiologist/ Physician. The data consists of patients’ record with doctor’s predictions/ diagnosis.
Results: The obtained result of Heart disease prediction match with the expert physician’s opinion with 96.97% accuracy and shows high degrees of sensitivity and specificity.
Conclusion: The proposed Heart Disease Prediction System based on Quantum Neural Network gives the high degrees of accuracy in predicting the risk of cardiovascular diseases, are also the best results based on clinical factors. The result generated by this system has been evaluated and validated on data of patients with the Doctor’s diagnosis. This system will help the doctors to plan for a better medication and provide the patient with early diagnosis as it performs reasonably well even without retraining. Such an expert system may also prove useful in combination with other systems to providing diagnostic and predictive medical opinions in a timely manner
Tracking JavaScript dependencies on the web
No full textThesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.Title as it appears in MIT Commencement Exercises program, June 5, 2015: Dependency tracking. Cataloged from student-submitted PDF version of thesis.Includes bibliographical references (pages 49-50).Identifying the performance bottlenecks of Web pages is often the first step in reducing page load times. Existing models of Web pages (dependency graphs) ignore the dynamic interactions of JavaScript objects along these critical paths. Current dependency graphs solely include the dependencies that arise from a Web object triggering a new HTTP request. This thesis presents DepTracker, a tool that captures dynamically generated dependencies between JavaScript objects on a Web page. These JavaScript dependencies give a more accurate picture of the network and computational resources contributing to the critical path. DepTracker works in conjunction with an HTTP record-and-replay framework, Mahimahi [17], to track reads and writes to the JavaScript global namespace during actual page loads. We classify dependencies into three categories: write-read, read-write, and write-write. Preserving each of these dependencies maintains the consistency of JavaScript execution on Web pages. For each dependency tracked, DepTracker provides developers with relevant line numbers in the source code, variable names, and values that are assigned and read. This information is particularly useful to Web developers seeking to speed up accesses to their websites by reordering individual objects. We use DepTracker, along with Mahimahi, to expose dependencies on 10 popular Web pages. We find that each Web page includes dependencies between JavaScript objects that are not captured by existing dependency graphs. For our corpus of test sites, we find that graphs that include JavaScript dependencies tracked by DepTracker include 32% and 73% more edges than default dependency graphs, at the median and 95th percentile, respectively.by Ameesh Kumar Goyal.M. Eng
Development and Application of PP-CNT Composite for Hummingbird Inspired MAV Flapping Wings
No full textMicro Air Vehicles (MAVs) are small unmanned aircrafts which have a maximum size limit of 150 mm in any direction. They can be used for surveillance, reconnaissance, targeting, etc. To perform such missions, MAVs are required to hover. Hummingbirds, having excellent flight characteristics (such as hovering, ability to fly in any direction, ability to produce a reverse camber during upstroke for generating lift in both up-down strokes), have been chosen as the bio-inspiration for wing development. Wings are required to be light, strong and fatigue resistant, to be able to properly flap during flight. Therefore, wing-material becomes a crucial component. An optimization analysis, on the basis of density and fundamental frequency values obtained through Ansys, was done for selecting the wing material. Polypropylene (PP) was observed to have desired properties such as light weight, flexibility, strength, fatigue resistance, good heat and chemical resistance etc. Mixing Carbon Nano Tubes (CNTs) with PP can further increase the strength significantly, making it more suitable for large amplitude flapping. The PP-CNT composites were developed using solution casting method. The films were characterized mechanically (using UTM). The wings were characterized by their structural dynamic properties. The modal analysis of wings was done to obtain natural frequencies and mode shapes. The analysis was aimed to get the fundamental mode in the flapping range (8-15 Hz) of hummingbirds, as resonance increases efficiency. It was also done inside vacuum chamber to observe the effect of air on the natural frequency and modes. The Ansys results were compared with the experiments in vacuum for validation of experimental results. Damping coefficient of wings was also determined. In the end, bio-mimicking of hummingbird wing was also tried by doing some material and structural advancements in the wings
Neuropsychiatric co-morbidities in non-demented Parkinson′s disease
No full textObjective: To evaluate neuropsychiatric co-morbidities (depression, psychosis and anxiety) in non-demented patients with Parkinson′s disease (PD). Background: Non-motor symptoms like neuropsychiatric co-morbidities are common in Parkinson′s disease and may predate motor symptoms. Currently there is scarcity of data regarding neuropsychiatry manifestations in Indian patients with PD. Methods: In this cross-sectional study consecutive 126 non-demented patients with PD (MMSE ≥25) were enrolled. They were assessed using Unified Parkinson′s disease rating scale (UPDRS), Hoehn & Yahr (H&Y) stage, Schwab and England (S&E) scale of activity of daily life. Mini-international neuropsychiatric interview (MINI) was used for diagnosis of depression, psychosis and anxiety. Beck′s depression inventory (BDI), Brief psychiatric rating scale (BSRS) and Hamilton rating scale for anxiety (HAM-A) scales were used for assessment of severity of depression, psychosis and anxiety respectively. Results: Mean age and duration of disease was 57.9 ± 10.9 years and 7.3 ± 3.6 years respectively. At least one of the neuropsychiatric co-morbidity was present in 64% patients. Depression, suicidal risk, psychosis and anxiety were present in 43.7%, 31%, 23.8% and 35.7% respectively. Visual hallucinations (20.6%) were most frequent, followed by tactile (13.5%), auditory (7.2%) and olfactory hallucinations (1.6%). Patients with depression had higher motor disability (UPDRS-motor score 33.1 ± 14.0 vs 27.3 ± 13.3; and UPDRS-total 50.7 ± 21.8 vs 41.0 ± 20.3, all p values <0.05). Patients with psychosis were older (63.6 ± 8.0 years vs 56.1 ± 11.1 years, p < 0.05) and had longer duration of illness (8.6 ± 3.4 years vs 6.9 ± 3.5, p < 0.05). Conclusions: About two third patients with Parkinson′s disease have associated neuropsychiatric co-morbidities. Depression was more frequent in patients with higher disability and psychosis with longer duration of disease and older age. These co-morbidities need to be addressed during management of patients with PD
Cardiovascular risk prediction: a comparative study of Framingham and quantum neural network based approach
No full textRenu Narain,1 Sanjai Saxena,1 Achal Kumar Goyal2 1Department of Biotechnology, Thapar University, Punjab, India; 2University Computer Center, Gurukul Kangri University, Haridwar, Uttarakhand, India Purpose: Currently cardiovascular diseases (CVDs) are the main cause of death worldwide. Disease risk estimates can be used as prognostic information and support for treating CVDs. The commonly used Framingham risk score (FRS) for CVD prediction is outdated for the modern population, so FRS may not be accurate enough. In this paper, a novel CVD prediction system based on machine learning is proposed.Methods: This study has been conducted with the data of 689 patients showing symptoms of CVD. Furthermore, the dataset of 5,209 CVD patients of the famous Framingham study has been used for validation purposes. Each patient’s parameters have been analyzed by physicians in order to make a diagnosis. The proposed system uses the quantum neural network for machine learning. This system learns and recognizes the pattern of CVD. The proposed system has been experimentally evaluated and compared with FRS.Results: During testing, patients’ data in combination with the doctors’ diagnosis (predictions) are used for evaluation and validation. The proposed system achieved 98.57% accuracy in predicting the CVD risk. The CVD risk predictions by the proposed system, using the dataset of the Framingham study, confirmed the potential risk of death, deaths which actually occurred and had been recorded as due to myocardial infarction and coronary heart disease in the dataset of the Framingham study. The accuracy of the proposed system is significantly higher than FRS and other existing approaches.Conclusion: The proposed system will serve as an excellent tool for a medical practitioner in predicting the risk of CVD. This system will be serving as an aid to medical practitioners for planning better medication and treatment strategies. An early diagnosis may be effectively made by using this system. An overall accuracy of 98.57% has been achieved in predicting the risk level. The accuracy is considerably higher compared to the other existing approaches. Thus, this system must be used instead of the well-known FRS. Keywords: myocardial infarction, atherosclerosis, Framingham risk score, cardiovascular diseas
- …
