Search results for: mortality prediction

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular diseases caused by hypertension are extremely threatening to human health, and early diagnosis of hypertension can save a large number of lives. Traditional hypertension detection methods require special equipment and are difficult to detect continuous blood pressure changes. In this regard, this paper first analyzes the principle of heart rate variability (HRV) and introduces sliding window and power spectral density (PSD) to analyze the time domain features and frequency domain features of HRV, and secondly, designs an HRV-based hypertension prediction network by combining Resnet, attention mechanism, and multilayer perceptron, which extracts the frequency domain through the improved ResNet18 features through a modified ResNet18, its fusion with time-domain features through an attention mechanism, and the auxiliary prediction of hypertension through a multilayer perceptron. Finally, the network was trained and tested using the publicly available SHAREE dataset on PhysioNet, and the test results showed that this network achieved 92.06% prediction accuracy for hypertension and outperformed K Near Neighbor(KNN), Bayes, Logistic, and traditional Convolutional Neural Network(CNN) models in prediction performance.

Keywords: feature extraction, heart rate variability, hypertension, residual networks

Procedia PDF Downloads 85

Authors: Nelson Rotimi Osungbemiro, Sanni Rafiu Olugbenga, Abayomi Olufemi Olajuyigbe

Abstract:

Ninety Fingerlings of Clarias gariepinus were exposed to the pathogenic Flavobacterium columnare a Gram Negative bacteria responsible for high mortality in fish pond raised young fish (fries and fingerlings) of Clarias sp. in Southwestern Nigeria. After feeding with 40% crude protein pelletized fish feed for 5 days, the fishes were divided into two groups, one group was treated with extracts from Calendula officinalis flowers, while the second group was not treated (control). The results indicated that, at day 5, colony formation had been manifesting and at day 7, skin lesion occurred and at the 8th day, first mortality of fish occurred, and this continued steadily on the 9th-12th day when all the fishes were dead. Whereas, in the group that was treated with Calendula sp., no single mortality was recorded. This research shows that plant extract from Calendula flowers is an effective antimicrobial agent against the virulent pathogenic Flavobacterium columnare disease.

Keywords: antimicrobial, Flavobacterium columnare, Clarias gariepinus, fish

Procedia PDF Downloads 593

Authors: Mo-Se Lee, Cheol-Hwi Ahn, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN (Convolutional Neural Network), which is known as effective solution for recognizing and classifying images, has been popularly applied to classification and prediction problems in various fields. In this study, we try to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. In specific, we propose to apply CNN as the binary classifier that predicts stock market direction (up or down) by using a graph as its input. That is, our proposal is to build a machine learning algorithm that mimics a person who looks at the graph and predicts whether the trend will go up or down. Our proposed model consists of four steps. In the first step, it divides the dataset into 5 days, 10 days, 15 days, and 20 days. And then, it creates graphs for each interval in step 2. In the next step, CNN classifiers are trained using the graphs generated in the previous step. In step 4, it optimizes the hyper parameters of the trained model by using the validation dataset. To validate our model, we will apply it to the prediction of KOSPI200 for 1,986 days in eight years (from 2009 to 2016). The experimental dataset will include 14 technical indicators such as CCI, Momentum, ROC and daily closing price of KOSPI200 of Korean stock market.

Keywords: convolutional neural network, deep learning, Korean stock market, stock market prediction

Procedia PDF Downloads 417

Authors: Afroze Ibrahim Baqapuri, Ilya Trofimov

Abstract:

Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE). Click-through-rate (CTR) estimation plays a crucial role for ads selection, and greatly affects the SE revenue, advertiser traffic and user experience. We propose a novel architecture of solving CTR prediction problem by combining artificial neural networks (ANN) with decision trees. First, we compare ANN with respect to other popular machine learning models being used for this task. Then we go on to combine ANN with MatrixNet (proprietary implementation of boosted trees) and evaluate the performance of the system as a whole. The results show that our approach provides a significant improvement over existing models.

Keywords: neural networks, sponsored search, web advertisement, click prediction, click-through rate

Procedia PDF Downloads 561

Authors: Akram Khaleghei, Ghosheh Balagh, Viliam Makis

Abstract:

In this paper, we investigate the residual life prediction problem for a partially observable system subject to two failure modes, namely a catastrophic failure and a failure due to the system degradation. The system is subject to condition monitoring and the degradation process is described by a hidden Markov model with unknown parameters. The parameter estimation procedure based on an EM algorithm is developed and the formulas for the conditional reliability function and the mean residual life are derived, illustrated by a numerical example.

Keywords: partially observable system, hidden Markov model, competing risks, residual life prediction

Procedia PDF Downloads 404

Authors: Shabistana Nisar, Parvez Qamar Rizvi, Sheeraz Malik

Abstract:

The potential advantage of nanotechnology is comparably marginal due to its unclear benefits in agriculture and insufficiency in public opinion. The nanotech products might solve the pesticide problems of societal concern fairly at acceptable or low risk for consumers and environmental applications. The deleterious effect of chemicals used on crops can be compacted either by reducing the existing active ingredient to nanosize or by plummeting the metals into nanoform. Considering the above facts, an attempt was made to determine the efficacy of nanoelements viz., Silver, Copper Manganese and Neem seed kernel extract (NSKE) for effective management of gram pod borer, Helicoverpa armigera infesting chickpea, being the most damaging pest of large number of crops, gram pod borer was selected as test insect to ascertain the impact of nanoparticles under controlled conditions (25-27 ˚C, 60-80% RH). The respective nanoformulations (0.01, 0.005, 0.003, 0.0025, 0.002, 0.001) were topically applied on 4th instar larvae of pod borer. In general, nanochemicals (silver, copper, manganese, NSKE) produced relatively high mortality at low dilutions (0.01, 0.005, 0.003). The least mortality was however recorded at 0.001 concentration. Nanosilver proved most efficient producing significantly highest (f₄,₂₄=129.56, p < 0.05) mortality 63.13±1.77, 83.21±2.02 and 96.10±1.25 % at 0.01 concentration after 2nd, 4th and 6th day, respectively. The least mortality was however recorded with nanoNSKE. The mortality values obtained at respective days were 21.25±1.50%, 25.20±2.00%, and 56.20±2.25%. Nanocopper and nanomanganese showed slow rate of killing on 2nd day of exposure, but increased (79.20±3.25 and 65.33±1.25) at 0.01 dilution on 3rd day, followed by 83.00±3.50% and 70.20±2.20% mortality on 6thday. The sluggishness coupled with antifeedancy was noticed at early stage of exposure. The change in body colour to brown due to additional melanisation in copper, manganese, and silver treated larvae and demalinization in nanoNSKE exposed larvae was observed at later stage of treatment. Thus, all the nanochemicals applied, produced the significant lethal impact on Helicoverpa armigera and can be used as valuable tool for its effective management.

Keywords: chickpea, helicoverpa armigera, management, nanoparticles

Procedia PDF Downloads 344

Authors: Marek Kuźniewski, Magdalena B. Kaziuk , Danuta Fedak, Paulina Dumnicka, Ewa Stępień, Beata Kuśnierz-Cabala, Władysław Sułowicz

Abstract:

Background: The high prevalence of cardiovascular morbidity and mortality among patients with chronic kidney disease (CKD) is observed especially in those undergoing dialysis. Osteoprotegerin (OPG) and its ligands, receptor activator of nuclear factor kappa-B ligand (RANKL) and tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) have been associated with cardiovascular complications. Our aim was to study their role as cardiovascular risk factors in stage 5 CKD patients. Methods: OPG, RANKL and TRAIL concentrations were measured in 69 hemodialyzed CKD patients and 35 healthy volunteers. In CKD patients, cardiovascular dysfunction was assessed with aortic pulse wave velocity (AoPWV), carotid artery intima-media thickness (CCA-IMT), coronary artery calcium score (CaSc) and N-terminal pro-B-type natriuretic peptide (NT-proBNP) serum concentration. Cardiovascular and overall mortality data were collected during a 7-years follow-up. Results: OPG plasma concentrations were higher in CKD patients comparing to controls. Total soluble RANKL was lower and OPG/RANKL ratio higher in patients. Soluble TRAIL concentrations did not differ between the groups and OPG/TRAIL ratio was higher in CKD patients. OPG and OPG/TRAIL positively predicted long-term mortality (all-cause and cardiovascular) in CKD patients. OPG positively correlated with AoPWV, CCA-IMT and NT-proBNP whereas OPG/TRAIL with AoPWV and NT-proBNP. Described relationships were independent of classical and non-classical cardiovascular risk factors, with exception of age. Conclusions: Our study confirmed the role of OPG as a biomarker of cardiovascular dysfunction and a predictor of mortality in stage 5 CKD. OPG/TRAIL ratio can be proposed as a predictor of cardiovascular dysfunction and mortality.

Keywords: osteoprotegerin, tumor necrosis factor-related apoptosis-inducing ligand, receptor activator of nuclear factor kappa-B ligand, hemodialysis, chronic kidney disease, cardiovascular disease

Procedia PDF Downloads 326

Authors: Seun Mayowa Sunday

Abstract:

Loan prediction is one of the most significant and recognised fields of research in the banking, insurance, and the financial security industries. Some prediction systems on the market include the construction of static software. However, due to the fact that static software only operates with strictly regulated rules, they cannot aid customers beyond these limitations. Application of many machine learning (ML) techniques are required for loan prediction. Four separate machine learning models, random forest (RF), decision tree (DT), k-nearest neighbour (KNN), and logistic regression, are used to create the loan prediction model. Using the anaconda navigator and the required machine learning (ML) libraries, models are created and evaluated using the appropriate measuring metrics. From the finding, the random forest performs with the highest accuracy of 80.17% which was later implemented into the Django framework. For real-time testing, the web application is deployed on the Alibabacloud which is among the top 4 biggest cloud computing provider. Hence, to the best of our knowledge, this research will serve as the first academic paper which combines the model development and the Django framework, with the deployment into the Alibaba cloud computing application.

Keywords: k-nearest neighbor, random forest, logistic regression, decision tree, django, cloud computing, alibaba cloud

Procedia PDF Downloads 115

Authors: Maria Ines Azambuja

Abstract:

Graphic displays of Age-Period-Cohort (APC) mortality trends generally uses data aggregated within 5 or 10-year intervals. Technology allows one to increase the amount of processed data. Displaying occurrences by 1-year intervals is a logic first step in the direction of attaining higher quality landscapes of variations in temporal occurrences. Method: 1) Comparison of UK mortality trends plotted by 10-, 5- and 1-year intervals; 2) Comparison of UK and US mortality trends (period X age and cohort X age) displayed by 1-year intervals. Source: Mortality data (period, 1x1, males, 1933-1912) uploaded from the Human Mortality Database to Excel files, where Period X Age and Cohort X Age graphics were produced. The choice of transforming age-specific trends from calendar to birth-cohort years (cohort = period – age) (instead of using cohort 1x1 data available at the HMD resource) was taken to facilitate the comparison of age-specific trends when looking across calendar-years and birth-cohorts. Yearly live births, males, 1933 to 1912 (UK) were uploaded from the HFD. Influenza references are from the literature. Results: 1) The use of 1-year intervals unveiled previously unsuspected period, cohort and interacting period x cohort effects upon all-causes mortality. 2) The UK and US figures showed variations associated with particular calendar years (1936, 1940, 1951, 1957-68, 72) and, most surprisingly, with particular birth-cohorts (1889-90 in the US, and 1900, 1918-19, 1940-41 and 1946-47, in both countries. Also, the figures showed ups and downs in age-specific trends initiated at particular birth-cohorts (1900, 1918-19 and 1947-48) or a particular calendar-year (1968, 1972, 1977-78 in the US), variations at times restricted to just a range of ages (cohort x period interacting effects). Importantly, most of the identified “scars” (period and cohort) correlates with the record of occurrences of Influenza A epidemics since the late 19th Century. Conclusions: The use of 1-year intervals to describe APC mortality trends both increases the amount of information available, thus enhancing the opportunities for patterns’ recognition, and increases our capability of interpreting those patterns by describing trends across smaller intervals of time (period or birth-cohort). The US and the UK mortality landscapes share many but not all 'scars' and distortions suggested here to be associated with influenza epidemics. Different size-effects of wars are evident, both in mortality and in fertility. But it would also be realistic to suppose that the preponderant influenza A viruses circulating in UK and US at the beginning of the 20th Century might be different and the difference to have intergenerational long-term consequences. Compared with the live births trend (UK data), birth-cohort scars clearly depend on birth-cohort sizes relatives to neighbor ones, which, if causally associated with influenza, would result from influenza-related fetal outcomes/selection. Fetal selection could introduce continuing modifications on population patterns of immune-inflammatory phenotypes that might give rise to 'epidemic constitutions' favoring the occurrence of particular diseases. Comparative analysis of mortality landscapes may help us to straight our record of past circulation of Influenza viruses and document associations between influenza recycling and fertility changes.

Keywords: age-period-cohort trends, epidemic constitution, fertility, influenza, mortality

Procedia PDF Downloads 220

Authors: Edwaldo R. B. Monteiro, Patricia D. M. Plentz, Edson R. De Pieri

Abstract:

Mobile robotics is gaining an increasingly important role in modern society. Several potentially dangerous or laborious tasks for human are assigned to mobile robots, which are increasingly capable. Many of these tasks need to be performed within a specified period, i.e., meet a deadline. Missing the deadline can result in financial and/or material losses. Mechanisms for predicting the missing of deadlines are fundamental because corrective actions can be taken to avoid or minimize the losses resulting from missing the deadline. In this work we propose a simple but reliable deadline missing prediction mechanism for mobile robots through the use of historical data and we use the Pioneer 3-DX robot for experiments and simulations, one of the most popular robots in academia.

Keywords: deadline missing, historical data, mobile robots, prediction mechanism

Procedia PDF Downloads 391

Authors: Chang Su Woo, Hyun Sung Park

Abstract:

Useful lifetime evaluations of rail-pads were very important in design procedure to assure the safety and reliability. It is, therefore, necessary to establish a suitable criterion for the replacement period of rail pads. In this study, we performed properties and accelerated heat aging tests of rail pads considering degradation factors and all environmental conditions including operation, and then derived a lifetime prediction equation according to changes in hardness, thickness, and static spring constants in the Arrhenius plot to establish how to estimate the aging of rail pads. With the useful lifetime prediction equation, the lifetime of e-clip pads was 2.5 years when the change in hardness was 10% at 25°C; and that of f-clip pads was 1.7 years. When the change in thickness was 10%, the lifetime of e-clip pads and f-clip pads is 2.6 years respectively. The results obtained in this study to estimate the useful lifetime of rail pads for high speed trains can be used for determining the maintenance and replacement schedule for rail pads.

Keywords: rail pads, accelerated test, Arrhenius plot, useful lifetime prediction, mechanical engineering design

Procedia PDF Downloads 310

Authors: H. A. Mansour

Abstract:

The objective of this research work is studying the water use prediction, prediction technology for water use by action agencies, and others involved in conservation, planning, and environmental assessment of the Water Erosion Prediction Project (WEPP) simulation model. Models the important physical, processes governing erosion in Egypt (climate, infiltration, runoff, ET, detachment by raindrops, detachment by flowing water, deposition, etc.). Simulation of the non-uniform slope, soils, cropping/management., and Egyptian databases for climate, soils, and crops. The study included important parameters in Egyptian conditions as follows: Water Balance & Percolation, Soil Component (Tillage impacts), Plant Growth & Residue Decomposition, Overland Flow Hydraulics. It could be concluded that we can adapt the WEPP simulation model to determining the previous important parameters under Egyptian conditions.

Keywords: WEPP, adaptation, soil properties, tillage impacts, water balance, soil percolation

Procedia PDF Downloads 287

Authors: A. Dadda, D. Khelef, K. Ait-Oudia, R. Kaidi

Abstract:

Neonatal calf diarrhea is the most important disease of neonatal calves and results in the greatest economic losses due to disease in this age group in both dairy and beef calves. The objectives of the present study were to estimate the morbidity and the mortality of neonatal diarrhea in dairy calves also to determine aetiology and risk factors were caused diarrhea in dairy veal under 60 days old. A total of 324 claves, housed in 30 dairy breeding were followed during two velage season from January to Juan 2013. The total mortality was 5,9% and was significantly higher in calves had less than 15 days of age. The incidence rate of diarrhea was 31,5% and peaked in the first two weeks after velage. The main causes were breeding controls, defect of passive immunity, old of calf, production season, and nutrient of pregnant cattle, veal’s housing and infectious agents. ELISA test on 22 fecal samples revealed that the 31, 82% of dairy breeding were infected, by cryptosporidium parvum in 13, 6% of study population, E.Coli F5 in 9% and Rotavirus with rate of 4, 5%.

Keywords: diarrhoea, neonatal, mortality, aetiology, risk factors, incidence

Procedia PDF Downloads 625

Authors: Joseph C. Chen, Venkata Mohan Kudapa

Abstract:

Development of two real-time surface roughness (Ra) prediction systems for milling operations was attempted. The systems used not only cutting parameters, such as feed rate and spindle speed, but also the cutting current generated and corrected by a clamp type energy sensor. Two different approaches were developed. First, a fuzzy inference system (FIS), in which the fuzzy logic rules are generated by experts in the milling processes, was used to conduct prediction modeling using current cutting data. Second, a neuro-fuzzy system (ANFIS) was explored. Neuro-fuzzy systems are adaptive techniques in which data are collected on the network, processed, and rules are generated by the system. The inference system then uses these rules to predict Ra as the output. Experimental results showed that the parameters of spindle speed, feed rate, depth of cut, and input current variation could predict Ra. These two systems enable the prediction of Ra during the milling operation with an average of 91.83% and 94.48% accuracy by FIS and ANFIS systems, respectively. Statistically, the ANFIS system provided better prediction accuracy than that of the FIS system.

Keywords: surface roughness, input current, fuzzy logic, neuro-fuzzy, milling operations

Procedia PDF Downloads 127

Authors: Vuk M. Popovic, Dunja D. Popovic

Abstract:

Software maintenance phase is started once a software project has been developed and delivered. After that, any modification to it corresponds to maintenance. Software maintenance involves modifications to keep a software project usable in a changed or a changing environment, to correct discovered faults, and modifications, and to improve performance or maintainability. Software maintenance and management of software maintenance are recognized as two most important and most expensive processes in a life of a software product. This research is basing the prediction of maintenance, on risks and time evaluation, and using them as data sets for working with neural networks. The aim of this paper is to provide support to project maintenance managers. They will be able to pass the issues planned for the next software-service-patch to the experts, for risk and working time evaluation, and afterward to put all data to neural networks in order to get software maintenance prediction. This process will lead to the more accurate prediction of the working hours needed for the software-service-patch, which will eventually lead to better planning of budget for the software maintenance projects.

Keywords: laboratory information system, maintenance engineering, neural networks, software maintenance, software maintenance costs

Procedia PDF Downloads 337

Authors: Jeff Clarine, Chang-Shyh Peng, Daisy Sang

Abstract:

Bioassay is the measurement of the potency of a chemical substance by its effect on a living animal or plant tissue. Bioassay data and chemical structures from pharmacokinetic and drug metabolism screening are mined from and housed in multiple databases. Bioassay prediction is calculated accordingly to determine further advancement. This paper proposes a four-step preprocessing of datasets for improving the bioassay predictions. The first step is instance selection in which dataset is categorized into training, testing, and validation sets. The second step is discretization that partitions the data in consideration of accuracy vs. precision. The third step is normalization where data are normalized between 0 and 1 for subsequent machine learning processing. The fourth step is feature selection where key chemical properties and attributes are generated. The streamlined results are then analyzed for the prediction of effectiveness by various machine learning algorithms including Pipeline Pilot, R, Weka, and Excel. Experiments and evaluations reveal the effectiveness of various combination of preprocessing steps and machine learning algorithms in more consistent and accurate prediction.

Keywords: bioassay, machine learning, preprocessing, virtual screen

Procedia PDF Downloads 262

Authors: Abdelmanie Suleimat, Nagham Abu Shaqra, Sawsan Majali, Issam Adawi, Heba Abo Shindi, Anas Al Mohtaseb

Abstract:

The Government of Jordan recognizes that maternal mortality constitutes a grave public health problem. Over the past two decades, there has been significant progress in improving the quality of maternal health services, resulting in improved maternal and child health outcomes. Despite these efforts, measurement and analysis of maternal mortality remained a challenge, with significant discrepancies from previous national surveys that inhibited accuracy. In response with support from USAID, the Jordan Maternal Mortality Surveillance Response (JMMSR) System was established to collect, analyze, and equip policymakers with data for decision-making guided by interdisciplinary multi-levelled advisory groups aiming to eliminate preventable maternal deaths, A 2016 Public Health Bylaw required the notification of deaths among women of reproductive age. The JMMSR system was launched in 2018 and continues annually, analyzing data received from health facilities, to guide policy to prevent avoidable deaths. To date, there have been four annual national maternal mortality reports (2018-2021). Data is collected, reviewed by advisory groups, and then consolidated in an annual report to inform and guide the Ministry of Health (MOH); JMMSR collects the necessary information to calculate an accurate maternal mortality ratio and assists in identifying leading causes and contributing factors for each maternal death. Based on this data, national response plans are created. A monitoring and evaluation plan was designed to define, track, and improve implementation through indicators. Over the past four years, one of these indicators, ‘percent of facilities notifying respective health directorates of all deaths of women of reproductive age,’ increased annually from 82.16%, 92.95%, and 92.50% to 97.02%, respectively. The Government of Jordan demonstrated commitment to the JMMSR system by designating the MOH to primarily host the system and lead the development and dissemination of policies and procedures to standardize implementation. The data was translated into practical and evidence-based recommendations. The successful impact of results deepened the understanding of maternal mortality in Jordan, which convinced the MOH to amend the Bylaw now mandating electronic reporting of all births and neonatal deaths from health facilities to empower the JMMSR system, by developing a stillbirths and neonatal mortality surveillance and response system.

Keywords: maternal health, maternal mortality, preventable maternal deaths, maternal morbidity

Procedia PDF Downloads 21

Authors: Anne-Lena Kampen, Øivind Kure

Abstract:

Machine learning (ML) can be implemented in Wireless Sensor Networks (WSNs) as a central solution or distributed solution where the ML is embedded in the nodes. Embedding improves privacy and may reduce prediction delay. In addition, the number of transmissions is reduced. However, quality factors such as prediction accuracy, fault detection efficiency and coordinated control of the overall system suffer. Here, we discuss and highlight the trade-offs that should be considered when choosing between embedding and centralized ML, especially for multihop networks. In addition, we present estimations that demonstrate the energy trade-offs between embedded and centralized ML. Although the total network energy consumption is lower with central prediction, it makes the network more prone for partitioning due to the high forwarding load on the one-hop nodes. Moreover, the continuous improvements in the number of operations per joule for embedded devices will move the energy balance toward embedded prediction.

Keywords: central machine learning, embedded machine learning, energy consumption, local machine learning, wireless sensor networks, WSN

Procedia PDF Downloads 136

Authors: Mansoureh Naderipour, Susan Bastani, Mohammad Fazel Zarandi

Abstract:

Predicting links that may occur in the future and missing links in social networks is an attractive problem in social network analysis. Granular computing can help us to model the relationships between human-based system and social sciences in this field. In this paper, we present a model based on granular computing approach and Type-2 fuzzy logic to predict links regarding nodes’ activity and the relationship between two nodes. Our model is tested on collaboration networks. It is found that the accuracy of prediction is significantly higher than the Type-1 fuzzy and crisp approach.

Keywords: social network, link prediction, granular computing, type-2 fuzzy sets

Procedia PDF Downloads 311

Authors: Gunasekaran Raja, Rajakumar Arul, Kottilingam Kottursamy, Ramkumar Jayaraman, Sathya Pavithra, Swaminathan Venkatraman

Abstract:

Wireless Interoperability for Microwave Access (WiMAX) utilizes the IEEE 802.1X mechanism for authentication. However, this mechanism incurs considerable delay during handoffs. This delay during handoffs results in service disruption which becomes a severe bottleneck. To overcome this delay, our article proposes a key caching mechanism based on user path prediction. If the user mobility follows that path, the user bypasses the normal IEEE 802.1X mechanism and establishes the necessary authentication keys directly. Through analytical and simulation modeling, we have proved that our mechanism effectively decreases the handoff delay thereby achieving fast authentication.

Keywords: authentication, authorization, and accounting (AAA), handoff, mobile, user path prediction (UPP) and user pattern

Procedia PDF Downloads 382

Authors: Christos E. Lampropoulos, Maria Konsta, Tamta Sirbilatze, Ifigenia Apostolou, Vicky Dradaki, Konstantina Panouria, Irini Dri, Christina Kordali, Vaggelis Lambas, Georgios Mavras

Abstract:

Objectives: Full Mini Nutritional Assessment (MNA) questionnaire is one of the most useful tools in diagnosis of malnutrition in hospitalized patients, which is related to increased morbidity and mortality. The purpose of our study was to assess the nutritional status of elderly, hospitalized patients and examine the hypothesis that MNA may predict mortality and extension of hospitalization. Methods: One hundred fifty patients (78 men, 72 women, mean age 80±8.2) were included in this cross-sectional study. The following data were taken into account in analysis: anthropometric and laboratory data, physical activity (International Physical Activity Questionnaires, IPAQ), smoking status, dietary habits, cause and duration of current admission, medical history (co-morbidities, previous admissions). Primary endpoints were mortality (from admission until 6 months afterwards) and duration of admission. The latter was compared to national guidelines for closed consolidated medical expenses. Logistic regression and linear regression analysis were performed in order to identify independent predictors for mortality and extended hospitalization respectively. Results: According to MNA, nutrition was normal in 54/150 (36%) of patients, 46/150 (30.7%) of them were at risk of malnutrition and the rest 50/150 (33.3%) were malnourished. After performing multivariate logistic regression analysis we found that the odds of death decreased 20% per each unit increase of full MNA score (OR=0.8, 95% CI 0.74-0.89, p < 0.0001). Patients who admitted due to cancer were 23 times more likely to die, compared to those with infection (OR=23, 95% CI 3.8-141.6, p=0.001). Similarly, patients who admitted due to stroke were 7 times more likely to die (OR=7, 95% CI 1.4-34.5, p=0.02), while these with all other causes of admission were less likely (OR=0.2, 95% CI 0.06-0.8, p=0.03), compared to patients with infection. According to multivariate linear regression analysis, each increase of unit of full MNA, decreased the admission duration on average 0.3 days (b:-0.3, 95% CI -0.45 - -0.15, p < 0.0001). Patients admitted due to cancer had on average 6.8 days higher extension of hospitalization, compared to those admitted for infection (b:6.8, 95% CI 3.2-10.3, p < 0.0001). Conclusion: Mortality and extension of hospitalization is significantly increased in elderly, malnourished patients. Full MNA score is a useful diagnostic tool of malnutrition.

Keywords: duration of admission, malnutrition, mini nutritional assessment score, prognostic factors for mortality

Procedia PDF Downloads 303

Authors: Kajori Banerjee, Laxmi Kant Dwivedi

Abstract:

“Health transition” is defined to be “a process through which high levels of mortality, morbidity and disability are reduced to low levels by influencing cultural, social and behavioural factors”. Life expectancy in India has been on the rise and parallel the burden of disease and disability has also risen noticeably. Borrowing data from Indian Census (2001, 2011), this study identifies the gender-wise burden of disability by calculating disability free life expectancy (DFLE) and life lived with disability (LWD). Sullivan’s method of calculating DFLE using proportion of disabled is used for this purpose. The change in person years lived with disability in the decade 2001-11 is further decomposed using Arriaga’s method into mortality and disability effects (ME and DE) to check the magnitude and direction of contribution of mortality and disability. Nationally, along with DFLE, LWD has amplified too. Despite having the highest life expectancy and DFLE, LWD in Kerala, was highest for both sexes in 2001. But in 2011, the LWD was highest among the males of Orissa and females of Rajasthan. For the overall population, DE is positive for the prime working age groups of 20-40years indicating that there has been an increase in the disability proportion holding mortality constant for 2001-2011. Females exhibit higher positive DE implying greater loss of healthy years due to disability than males. The findings call for an immediate attention to the causes of rising disability burden among the working population, especially females, as this might heavily effect the availability of quality labour force and its relative economic output in the Indian labour market. This also hints at the degrading quality of the elongated life and needs to be given the required attention to enhance the quality of life lead in the Nation.

Keywords: disability-free life expectancy, disability effect, life expectancy, mortality effect

Procedia PDF Downloads 382

Authors: Indrajeet Kumar, Jayanta Bhattacharya

Abstract:

This study was evaluated for the potential use of nanosilver (nAg) as a disinfectant and antimicrobial growth promoter supplement for the poultry. The experiments were conducted in the Kangsabati river basin region, in West Medinipur district, West Bengal, India for six months. Two poultry farms were adopted for the experiment. The rural economy of this region from Jhargram to Barkola is heavily dependent on contract poultry farming. The water samples were collected from the water source of poultry farm which has been used for poultry drinking purpose. The bacteriological analysis of water sample revealed that the total bacterial count (total coliform and E. coli) were higher than the acceptable standards. The bacterial loads badly affected the growth performance and health of the poultry. For disinfection, a number of chemical compounds (like formaldehyde, calcium hypochloride, sodium hypochloride, and sodium bicarbonate) have been used in typical commercial formulations. However, the effects of all these chemical compounds have not been significant over time. As a part of our research-to-market initiative, we used nanosilver (nAg) formulation as a disinfectant. The nAg formulation was synthesized by hydrothermal technique and characterized by UV-visible, TEM, SEM, and EDX. The obtained results revealed that the mortality rate of poultry was reduced due to nAg formulation compared to the mortality rate of the negative control. Moreover, the income of the farmer family was increased by 10-20% due to less mortality and better health of the poultry.

Keywords: farm water, nanosilver, field application, and poultry performance

Procedia PDF Downloads 147

Authors: Mostafa Najim, Alaa Rahhal, Fadi Khir, Safae Abu Yousef, Amer Aljundi, Feryal Ibrahim, Aliaa Amer, Ahmed Soliman Mohamed, Samira Saleh, Dekra Alfaridi, Ahmed Mahfouz, Sumaya Al-Yafei, Faraj Howady, Mohamad Yahya Khatib, Samar Alemadi

Abstract:

Background: Coronavirus disease 2019 (COVID-19) increases the risk of coagulopathy among critically ill patients. Although the presence of antiphospholipid antibodies (aPLs) has been proposed as a possible mechanism of COVID-19 induced coagulopathy, their clinical significance among critically ill patients with COVID-19 remains uncertain. Methods: This prospective observational study included patients with COVID-19 admitted to intensive care units (ICU) to evaluate the prevalence and clinical significance of aPLs, including anticardiolipin IgG/IgM, anti-β2-glycoprotein IgG/IgM, and lupus anticoagulant. The study outcomes included the prevalence of aPLs, a primary composite outcome of all-cause mortality, and arterial or venous thrombosis among aPLs positive patients versus aPLs negative patients during their ICU stay. Multiple logistic regression was used to assess the influence of aPLs on the primary composite outcome of mortality and thrombosis. Results: A total of 60 critically ill patients were enrolled. Of whom, 57 (95%) were male, with a mean age of 52.8 ± 12.2 years, and the majority were from Asia (68%). Twenty-two patients (37%) were found to have positive aPLs; of whom 21 patients were positive for lupus anticoagulant, whereas one patient was positive for anti-β2-glycoprotein IgG/IgM. The composite outcome of mortality and thrombosis during ICU did not differ among patients with positive aPLs compared to those with negative aPLs (4 (18%) vs. 6 (16%), aOR= 0.98, 95% CI 0.1-6.7; p-value= 0.986). Likewise, the secondary outcomes, including all-cause mortality, venous thrombosis, arterial thrombosis, discharge from ICU, time to mortality, and time to discharge from ICU, did not differ between those with positive aPLs upon ICU admission in comparison to patients with negative aPLs. Conclusion: The presence of aPLs does not seem to affect the outcomes of critically ill patients with COVID-19 in terms of all-cause mortality and thrombosis. Therefore, clinicians may not screen critically ill patients with COVID-19 for aPLs unless deemed clinically appropriate.

Keywords: antiphospholipid antibodies, critically ill patients, coagulopathy, coronavirus

Procedia PDF Downloads 150

Authors: Kiyoumars Roushangar, Saeid Sadaghian

Abstract:

Although accurate sediment load prediction is very important in planning, designing, operating and maintenance of water resources structures, the transport mechanism is complex, and the deterministic transport models are based on simplifying assumptions often lead to large prediction errors. In this research, firstly, two intelligent ANN methods, Radial Basis and General Regression Neural Networks, are adopted to model of total sediment load transport into Madani Dam reservoir (north of Iran) using the measured data and then applicability of the sediment transport methods developed by Engelund and Hansen, Ackers and White, Yang, and Toffaleti for predicting of sediment load discharge are evaluated. Based on comparison of the results, it is found that the GRNN model gives better estimates than the sediment rating curve and mentioned classic methods.

Keywords: sediment transport, dam reservoir, RBF, GRNN, prediction

Procedia PDF Downloads 483

Authors: Alexandre Barbosa de Almeida, Telma Woerle de Lima Soares

Abstract:

Protein structure prediction is a challenging task in the bioinformatics field. The biological function of all proteins majorly relies on the shape of their three-dimensional conformational structure, but less than 1% of all known proteins in the world have their structure solved. This work proposes a deep learning model to address this problem, attempting to predict some aspects of the protein conformations. Throughout a process of multiobjective dominance, a recurrent neural network was trained to abstract the particular bias of each individual multiobjective algorithm, generating a heuristic that could be useful to predict some of the relevant aspects of the three-dimensional conformation process formation, known as protein folding.

Keywords: Ab initio heuristic modeling, multiobjective optimization, protein structure prediction, recurrent neural network

Procedia PDF Downloads 193

Authors: Danladi Ali, Abdullahi Mukaila

Abstract:

In this work, GSM signal strength (power) was monitored in an indoor environment. Samples of the GSM signal strength was measured on mobile equipment (ME). One-dimensional multilevel wavelet is used to predict the fading phenomenon of the GSM signal measured and neural network clustering to determine the average power received in the study area. The wavelet prediction revealed that the GSM signal is attenuated due to the fast fading phenomenon which fades about 7 times faster than the radio wavelength while the neural network clustering determined that -75dBm appeared more frequently followed by -85dBm. The work revealed that significant part of the signal measured is dominated by weak signal and the signal followed more of Rayleigh than Gaussian distribution. This confirmed the wavelet prediction.

Keywords: decomposition, clustering, propagation, model, wavelet, signal strength and spectral efficiency

Procedia PDF Downloads 438

Authors: Ciro Cursio, Giulia Cursio, Pio Luigi Cursio, Luigi Cursio

Abstract:

Communication between practitioner and patient is of the utmost importance in aesthetic medicine: as of today, images of previous treatments are the most common tool used by doctors to describe and anticipate future results for their patients. However, using photos of other people often reduces the engagement of the prospective patient and is further limited by the number and quality of pictures available to the practitioner. Pre-existing work solves this issue in two ways: 3D scanning of the area with manual editing of the 3D model by the doctor or automatic prediction of the treatment by warping the image with hand-written parameters. The first approach requires the manual intervention of the doctor, while the second approach always generates results that aren’t always realistic. Thus, in one case, there is significant manual work required by the doctor, and in the other case, the prediction looks artificial. We propose an AI-based algorithm that autonomously generates a realistic prediction of treatment results. For the purpose of this study, we focus on hyaluronic acid treatments in the facial area. Our approach takes into account the individual characteristics of each face, and furthermore, the prediction system allows the patient to decide which area of the face she wants to modify. We show that the predictions generated by our system are realistic: first, the quality of the generated images is on par with real images; second, the prediction matches the actual results obtained after the treatment is completed. In conclusion, the proposed approach provides a valid tool for doctors to show patients what they will look like before deciding on the treatment.

Keywords: prediction, hyaluronic acid, treatment, artificial intelligence

Procedia PDF Downloads 102

Authors: Etienne Alain Feukeu, L. W. Snyman

Abstract:

Water scarcity is becoming a real issue nowadays. Most countries in the world are facing it in their own way based on their own geographical coordinate and condition. Many countries are facing a challenge of a growing water demand as a result of not only an increased population, economic growth, but also as a pressure of the population dynamic and urbanization. In view to mitigate some of this related problem, an accurate method of water estimation and future prediction, forecast is essential to guarantee not only the sufficient quantity, but also a good water distribution and management system. Beside the fact that several works have been undertaken to address this concern, there is still a considerable disparity between different methods and standard used for water prediction and estimation. Hence this work contrast and compare two well-defined and established methods from two countries (USA and South Africa) to demonstrate the inconsistency when different method and standards are used interchangeably.

Keywords: water scarcity, water estimation, water prediction, water forecast.

Procedia PDF Downloads 186

Authors: Francis Mark A. Fernandez, Chelca Ubay, Armithan Suguitan

Abstract:

Regions or provinces in a definite state certainly contribute to the economy of their mainland. These regions or provinces are the ones supplying the mainland with different resources and assets. Thus, with a certain region separating from the mainland would indeed impinge the heart of an entire state to develop and expand. With these, the researchers decided to study on the effects of the separation of one’s region to its mainland and the consequences that will take place if the mainland would rule out the region to separate from them. The researchers wrote this paper to present the causes of the separation of Catalonia from Spain and the prediction regarding the pursuance of this region to revolt from its mainland, Spain. In conducting this research, the researchers utilized two analyses, namely: qualitative and quantitative. In qualitative, numerous of information regarding the existing experiences of the citizens of Catalonia were gathered by the authors to give certainty to the prediction of the researchers. Besides this undertaking, the researchers will also gather needed information and figures through books, journals and the published news and reports. In addition, to further support this prediction under qualitative analysis, the researchers intended to operate the Phenomenological research in which the examiners will exemplify the lived experiences of each citizen in Catalonia. Moreover, the researchers will utilize one of the types of Phenomenological research which is hermeneutical phenomenology by Van Manen. In quantitative analysis, the researchers utilized the regression analysis in which it will ascertain the causality in an underlying theory in understanding the relationship of the variables. The researchers assigned and identified different variables, wherein the dependent variable or the y which represents the prediction of the researchers, the independent variable however or the x represents the arising problems that grounds the partition of the region, the summation of the independent variable or the ∑x represents the sum of the problem and finally the summation of the dependent variable or the ∑y is the result of the prediction. With these variables, using the regression analysis, the researchers will be able to show the connections and how a single variable could affect the other variables. From these approaches, the prediction of the researchers will be specified. This research could help different states dealing with this kind of problem. It will further help certain states undergoing this problem by analyzing the causes of these insurgencies and the effects on it if it will obstruct its region to consign their full-pledge autonomy.

Keywords: autonomy, liberty, prediction, separation

Procedia PDF Downloads 238