Average Mean Value Research Articles

A Comparative Evaluation of Search Engines on Finding Specific Domain Information on the Web

Recently search engines have provided a truly amazing search service, especially in finding general information on the Web. However, the question arises, does search engine perform the same when seeking domain specific information such as medical, geographical or agriculture information? Along with that issue, an experiment has been conducted to test the effectiveness of today’s search engines from the aspect of information searching in a specific domain. There were four search engines have been selected namely Google, Bing, Yahoo and DuckDuckGo for the experiment. While for the domain specific, we chose to test information about the popular fruit in Southeast Asia that is durian. Precision metric has been used to evaluate the retrieval effectiveness. The findings show that Google has outperformed the other three search engines. Nevertheless, the mean average precision value 0.51 given by Google is still low to be satisfied neither by the researcher nor the information seekers.

Promising black locust (Robinia pseudoacacia L.) cultivars in Hungary

In Hungary, black locust (Robinia pseudoacacia L.) is one of the most important exotic stand-forming tree species, growing mostly under unfavourable ecological conditions. Considering the climate change effects its importance is increasing in many other countries. As a result of a selection programme, several black locust cultivars have been improved for setting up cultivar trials. In the paper four black locust cultivars were evaluated in Central Hungary under arid hydrological and brown forest soil conditions. Significant differences (P<5%) were found in height, DBH, mean tree volume and average stem form value (SFV). At the age of 35 the cultivar ‘R.p. Jászkiséri’ appeared to be the most promising one for yield production and ‘R.p. Zalai’ for SFV.

Changes in Different Classes of Precipitation and the Impacts on Sediment Yield in the Hekouzhen-Longmen Region of the Yellow River Basin, China

The sediment yield of the Yellow River Basin has obviously decreased since the 1980s, and the impacts of precipitation on sediment yield changes have become increasingly important with the global climate change. The spatial and temporal variations in annual precipitation and different classes of precipitation in the Hekouzhen-Longmen region (HLR) in the middle reaches of the Yellow River Basin were investigated using data collected from 301 rainfall stations from 1966 to 2016. The impacts of precipitation variation on sediment yield were evaluated, and the hydrological modeling method was used to quantitatively assess the attribution of precipitation and other factors to sediment yield changes in the HLR. The results show that the annual precipitation and P10 increased from the northwest to the southeast of the HLR, suggesting it was drier in the northwest region of the HLR. P25 and P50 were mainly concentrated in the northwestern and southwestern parts of the HLR, reflecting that heavy rain was more likely to occur in these regions of the HLR. All of the annual precipitation and different classes of precipitation had no significant changing trends from 1966 to 2016, and the relationship between rainfall and sediment yield obviously changed in 2006. Compared with the average annual mean values from 1966 to 2016, both the annual precipitation and the different classes of precipitation were higher in the HLR during 2007–2016. The sediment yield decrease during 1990–1999 was mainly influenced by precipitation, while other factors were the main driving factor for the sediment yield decrease in the periods of 1980–1989, 2000–2009, and 2010–2016, and other factors have become the dominant driving factors of the sediment yield change in the HLR since 2000.

Experimental investigation of methanol dissociated gas addition to gasoline in a spark ignition engine

This work investigates the performances and emission characteristics of a spark ignition (SI) engine fuelled with methanol dissociated gas and gasoline mixtures. The dissociation system for methanol was designed, methanol dissociated gas was blended to the gasoline up to 20% by volume, and experiments were conducted within a four-cylinder, four-stroke and water-cooled spark ignition (SI) engine. Performance tests were carried out via measuring brake thermal efficiency, equivalent specific fuel consumption, and exhaust emissions (CO, HC, NOx) with a constant speed of 2000 rpm at stoichiometric condition. The results indicate that an increase in methanol substituted ratio has slightly lowered the engine torque. The addition of methanol dissociated gas decreases the equivalent specific fuel consumption and increases the effective thermal efficiency from the economical point of view. And the exhaust emissions decrease by about 33% and 28% of the mean average values of CO and HC emissions when the proportion of methanol substitution was 20% comparing to pure gasoline. However, nitrogen oxide emission values increased with the adding of methanol dissociated gas.

Credit risk management

PurposeThis study aims to examine and compare the credit risk management (CRM) scenario of Islamic banks (IBs) and conventional banks (CBs) in Pakistan, keeping in view the phenomenal growth of Islamic banking and its future implications.Design/methodology/approachA sample of five CBs and four IBs was chosen out of the whole banking industry for the study. Secondary data obtained from the banks’ annual financial reports for 13 years, starting from 2004 to 2016, were analyzed. Multiple regression, correlation and descriptive analysis were used in the examination of the data.FindingsThe results show that loan quality (LQ) has a positive and significant impact on CRM for both IBs and CBs. Asset quality (AQ), on the other hand, has a negative impact on CRM in the case of IBs, but has a significantly positive relation with CRM in the case of CBs. The impact of 16 ratios measuring LQ and AQ have also been individually checked on CRM, by making use of a regression model using a dummy variable of financial crises for robust comparison among CBs and IBs. The model proved significant, and CRM performance of IBs was observed to be better than that of CBs. Moreover, the mean average value of financial ratios used as a measuring tool for these variables shows that the CRM performance of IBs operating in Pakistan was better than that of CBs over the period of the study.Practical implicationsThe research findings are expected to facilitate bankers, investors, academics and policy makers to build a better understanding of CRM practices as adopted by CBs and IBs. The findings would be useful in formulating policy measures for the progress of the banking industry in Pakistan.Originality/valueThis research is unique in terms of its approach toward analyzing and comparing CRM performance of CBs and IBs. Such work has not been carried out before in the Pakistani banking industry.

Multilevel Building Detection Framework in Remote Sensing Images Based on Convolutional Neural Networks

In this paper, we propose a hierarchical building detection framework based on deep learning model, which focuses on accurately detecting buildings from remote sensing images. To this end, we first construct the generation model of the multilevel training samples using the Gaussian pyramid technique to learn the features of building objects at different scales and spatial resolutions. Then, the building region proposal networks are put forward to quickly extract candidate building regions, thereby increasing the efficiency of the building object detection. Based on the candidate building regions, we establish the multilevel building detection model using the convolutional neural networks (CNNs), from which the generic image features of each building region proposal are calculated. Finally, the obtained features are provided as inputs for training CNNs model, and the learned model is further applied to test images for the detection of unknown buildings. Various experiments using the Datasets I and II (in Section V-A) show that the proposed framework increases the mean average precision values of building detection by 3.63%, 3.85%, and 3.77%, compared with the state-of-the-art methods, i.e., Method IV. Besides, the proposed method is robust to the buildings having different spatial textures and types.

HOUGH TRANSFORM GENERATED STRONG IMAGE HASHING SCHEME FOR COPY DETECTION

The rapid development of image editing software has resulted in widespread unauthorized duplication of original images. This has given rise to the need to develop robust image hashing technique which can easily identify duplicate copies of the original images apart from differentiating it from different images. In this paper, we have proposed an image hashing technique based on discrete wavelet transform and Hough transform, which is robust to large number of image processing attacks including shifting and shearing. The input image is initially pre-processed to remove any kind of minor effects. Discrete wavelet transform is then applied to the pre-processed image to produce different wavelet coefficients from which different edges are detected by using a canny edge detector. Hough transform is finally applied to the edge-detected image to generate an image hash which is used for image identification. Different experiments were conducted to show that the proposed hashing technique has better robustness and discrimination performance as compared to the state-of-the-art techniques. Normalized average mean value difference is also calculated to show the performance of the proposed technique towards various image processing attacks. The proposed copy detection scheme can perform copy detection over large databases and can be considered to be a prototype for developing online real-time copy detection system.

Early myocardial changes in normotensive children of hypertensive parents: a tissue Doppler study.

The aim of this study was to examine early left ventricular systolic and diastolic changes using tissue Doppler imaging (TDI) in normotensive children of hypertensive parents (NCHP), a risk group for cardiovascular diseases. Ninety-two children characterized as NCHP (age range: 6-18 years) and 90 age-, gender-, height-, weight-, and body mass index-matched children characterized as normotensive children of normotensive parents (NCNP) were included in the study. Left ventricular diastolic parameters were assessed using transmitral flow pulse wave Doppler echocardiography and mitral septal and lateral annular TDI. Left ventricular systolic and diastolic function was evaluated globally using the TDI-derived myocardial performance index (MPI'). Mean systolic, diastolic, and average blood pressure values were found to be higher in the NCHP group than in the NCNP group. Echocardiographic parameters in the NCHP group showed statistically significant differences, including increased interventricular septum end-diastolic wall thickness (p = 0.039), left ventricular end-diastolic posterior wall thickness (p = 0.011), relative wall thickness (p = 0.013), and transmitral flow A velocity (p = 0.003); parameters determined by TDI included a prolonged isovolumetric relaxation time (p < 0.001) and isovolumetric contraction time (p = 0.002), shortened ejection time (p = 0.001), and increased MPI' (p < 0.001) in the NCHP group. Early alterations in myocardial function, indicated by increased MPI' values, had a positive correlation with systolic blood pressure and myocardial thickness. Conversely, they were negatively correlated with the ejection fraction and E/A ratio, which decreases with diastolic dysfunction. The MPI' is considered a repeatable, non-invasive, and low-cost assessment method that can surpass conventional methods in the detection of early left ventricular systolic and diastolic functional changes in the subclinical period of hypertension in children with familial risk.

Investigation of hydrogen addition to methanol-gasoline blends in an SI engine

In this study, effects of hydrogen-addition on the performance and emission characteristics of Methanol-Gasoline blends in a spark ignition (SI) engine were investigated. Experiments were conducted with a four-cylinder and four stroke spark ignition engine. Performance tests were performed via measuring brake thermal efficiency, brake specific fuel consumption, cylinder pressure and exhaust emissions (CO, CO2, HC, NOx). These performance metrics were analyzed under three engine load conditions (no load, 50% and 100%) with a constant speed of 2000 rpm. Methanol was added to the gasoline up to 15% by volume (5%, 10% and 15%). Besides, hydrogen was added to methanol-gasoline mixtures up to 15% by volume (3%, 6%, 9% and 15%). Results of this study showed that methanol addition increases BSFC by 26% and decreases thermal efficiency by 10.5% compared to the gasoline. By adding hydrogen to the methanol - gasoline mixtures, the BSFC decreased by 4% and the thermal efficiency increased by 2% compared to the gasoline. Hydrogen addition to methanol – gasoline mixtures reduces exhaust emissions by about 16%, 75% and 15% of the mean average values of HC, CO and CO2 emissions, respectively. Lastly, ıt was concluded that hydrogen addition improves combustion process; CO and HC emissions reduce as a result of the leaning effect caused by the methanol addition; and CO2 and NOx emission increases because of the improved combustion.

Saturday, September 29, 2018 9:00 am–10:00 am Impact of Adult Deformity Correction: 263. Development of deployable predictive models for MCID of 2-year outcomes across all commonly used HRQOL instruments in adult spinal deformity surgery: results in 570 patients from 17 hospitals

BACKGROUND CONTEXT Adult spinal deformity (ASD) surgery is costly with variable outcomes; in some series only 50% of patients achieve clinically important (MCID) improvements. Predictive modeling with machine learning is a relatively unexplored area of patient-reported outcomes research. These methods may be useful in shared-decision making, surgical planning, and postoperative patient counseling. PURPOSE To use predictive analytics to model health-related quality of life (HRQOL) outcomes at 1 year and 2 years after ASD surgery; including predicting the likelihood of achieving MCID. STUDY DESIGN/SETTING Data from two unique, multicenter, prospective observational cohort studies PATIENT SAMPLE Patients 18 years or older and treated for ASD with surgery. OUTCOME MEASURES Scoliosis Research Society-22, Oswestry Disability Index, Short Form-36v2. METHODS Two multi-center, prospective observational cohorts of ASD patients were queried to identify patients with complete enrollment, 1 and 2-year follow-up SRS-22, ODI and SF-36v2 data. Standard demographic and radiographic variables were collected. Modifiable surgical data (eg, 3-Column Osteotomy Yes or No), intraoperative and postoperative complications were collected. A total of 75 variables were used in the training of the models. Eight different prediction algorithms were trained with 3-time horizons: baseline to 1 year, baseline to 2 years, and 1 year to 2 years. External validation was accomplished via an 80/20 data split for training and testing each model, respectively. Five-fold cross validation within the training sample was performed. Accuracy was measured as the mean average error (MAE; smaller is better) and R² values. Models were created to predict HRQOL values at 2 years and to predict the likelihood of achieving MCID thresholds at 2 years postoperatively. RESULTS A total of 570 patients were included in the analysis. Models with the lowest MAE for each of the 5-time points were selected, achieving 82.4% predictive power. Patients with lower enrollment HRQOL were likely to achieve the greatest improvements and enrollment HRQOL values were the most important variables included. Age at enrollment was the most important demographic variable. Addition of surgeon and site to preoperative data increased the predictive power 1.8%. Site and surgeon fixed-effects played a crucial role in explaining outcome variance. Levels fused and enrollment curve magnitude were less important. CONCLUSIONS Predictive modeling from a large cohort of ASD patients was able to model 2-year outcomes scores, including the likelihood of achieving clinically relevant improvements. Patients with the lowest HRQOL scores were likely to appreciate the greatest improvements at 2 years postoperatively. Surgeon and site were important covariates, explaining variance in outcomes measures. These data may be used in informed decision making and patient counseling before and after ASD surgery. FDA DEVICE/DRUG STATUS This abstract does not discuss or include any applicable devices or drugs.

Affect-Adaptive Activities in a Personalised Ubiquitous Learning System

Many literatures have shown the importance of emotion in learning because of their effect on learner’s performances thereby giving reasons why learners’ affective states are crucial to learning. In this light, this research work aims to identify affect-adaptive activities that would improve learning in a personalised ubiquitous learning system by detecting learning style and affective states through some patterns of  behaviours. In the study, learners’ preference are determined, learners affective states such as confidence, effort, independence and confusion are investigated. The ant colony clustering algorithm is used to determine learners’ activities. The four affective states are determined from the learners’ forum threads, content activities, assessment, timing, and discussion through learners’ engagement. The result of this research on two separate courses, Course A (Affect) and Course B (Non-Affect) shows that the four affective states influence learning. The average mean and standard deviation (SD) value for Course A (Mean=276.23, SD=272.27) over Course B (Mean=200.58, SD=210.51) showed an improvement in learning performance and the t-Test carried out between the courses suggested that students’ performance is dependent on their affective states. https://doi.org/10.26803/ijlter.17.7.3

Pencarian Question-Answer Menggunakan Convolutional Neural Network Pada Topik Agama Berbahasa Indonesia

Community-based question answering (CQA) is formed to help people who search information that they need through a community. One condition that may occurs in CQA is when people cannot obtain the information that they need, thus they will post a new question. This condition can cause CQA archive increased because of duplicated questions. Therefore, it becomes important problems to find semantically similar questions from CQA archive towards a new question. In this study, we use convolutional neural network methods for semantic modeling of sentence to obtain words that they represent the content of documents and new question. The result for the process of finding the same question semantically to a new question (query) from the question-answer documents archive using the convolutional neural network method, obtained the mean average precision value is 0,422. Whereas by using vector space model, as a comparison, obtained mean average precision value is 0,282.&#x0D; Index Terms—community-based question answering, convolutional neural network, question retrieval

Continuous Blood Pressure Monitoring Algorithm using Laser Doppler Flowmetry.

A novel machine learning algorithm is introduced to estimate continuous blood pressure monitoring using Laser Doppler Flowmetry (LDF). LDF provides instantaneous, continuous, and noninvasive measurements of blood flow in a small tissue sample. The proposed algorithm segments the continuous blood flow profile based on heartbeat cycles to subsequently extract multiple features. The beat-to-beat blood pressure was estimated from a multi-layer neural network algorithm using the extracted features. The algorithm was also validated with clinically proven cuff based continuous blood pressure sensors. Mean average error values of 4.54 \sim5.37 mmHg were observed, which conform to a Grade B/C category per the IEEE standard 1708-2014 for cuffless blood pressure measuring devices.

PENINGKATAN KEMAMPUAN REPRESENTASI MATEMATIS MELALUI PEMBELAJARAN KONTEKSTUAL SISWA KELAS VIII SMP

This research is an experimental research with the aim to know: (1) improvement of the average of mathematical representation skills of class VIII student of SMP Negeri 2 Uluiwoi before getting learning with contextual approach; (2) improvement of the average of mathematical representation skills of grade VIII student of SMP Negeri 2 Uluiwoi before getting learning with conventional approach; (3) an average increase in student representation skills taught by a contextual learning approach is better than an increase in the average of mathematical representation skills taught by conventional learning. The population in this study is all students of class VIII SMP Negeri 2 Uluiwoi academic year 2016/2017 spread in 2 parallel classes with the number of 46 people. The population consists of two classes, then the sample is chosen by specifying the first class as the experimental class and the second class as the control class, assuming that the two classes are statistically homogeneous. This data collection technique uses test and observation techniques. Data analysis techniques use descriptive statistics and inferential statistics. The results of empirical research indicate that; (1) Improvement of mathematical representation skills of class VIIIA students taught by using contextual learning model consisting of 24 students showed average value 46,25 and deviation standard 7,409 with mean increase or average N-Gain value 0, 42 is in the medium category. The improvement of the mathematical representation skills of VIIIB class students taught by using conventional learning model which consist of 22 students shows the average value 49,09 and deviation standard 15,402 with mean increase or average of N-Gain value equal to 0,25 is at low category. Inferential statistical analysis shows that (1) there is an increase in the average ability of students 'mathematical representation after having contextual learning, (2) There is an increase in the average ability of students' mathematical representation after conventional learning, and (3) students' mathematical representation with the application of contextual approach is higher than the conventional learning model in Grade VIII students of SMP Negeri 2 Uluiwoi.&#x0D; Keywords: Improved, Contextual, Conventional, N-Gain, mathematical representation skills.

Assessment of the quality of life in children and adolescents with asthma

Introduction: Asthma is a global health problem that negatively affects various aspects of the quality of a person's life. The aim of the study was to examine the quality of life in children and adolescents with asthma and the correlation between the degree of asthma control and the quality of life.Methods: The cross-sectional study included 100 children and adolescents with asthma over a six-month period in 2015. The study used: Standardized Pediatric Asthma Quality of Life Questionnaire (PAQLQ(S)) for the assessment quality of life and the questionnaires for the assessment of asthma control for two age groups: Asthma Control Test (ACT) for adolescents and Childhood Asthma Control Test (C-ACT).Results: 62 boys and 38 girls aged 7−17, whose average age was 11.2 (s = 2.7) years were included in the study. The overall PAQLQ(S) score ranged between 3.30 and 7.00 with an average mean value of 5.95. The findings have showed that most children with asthma estimated their overall PAQLQ(S) on the positive end of the scale. The children reported more impairment in the domain of 'Emotion' (x = 5.84) than in 'Activities' and 'Symptoms'. The percentage of adolescents in the category of poor control (12.5 %) was significantly lower than in the group of children (25.0 %). In both groups of children, the sub-scale 'Symptoms' was in highest correlation with the degree of asthma control (r = 0.915, p &lt; 0.01).Discussion and conclusion: In this study the children and adolescents with asthma showed an overall good quality of life. Control of asthma symptoms in children and adolescents positively influenced their quality of life.

Sedimentology and Depositional Environment of part of Lokoja Formation Exposed at Felele Junction, Southern Bida Basin

The exposed Campanian sedimentary sequence at Felele junction around Lokoja has been mapped, logged and sampled. The total thickness of the section is approximately 21.48m. The sediments consist of conglomeratic sandstones, coarse sandstones and mudstones. Grain size analysis performed on nineteen sandstone samples revealed the average values of mean, sorting, skewness and kurtosis as 0.6, 1.03, 0.53 and 0.76 respectively. These results show that the sandstones are coarse grained, poorly sorted, strongly fine skewed and platykurtic. This characteristic is typical of fluvial depositional environment. The plots of skewness against sorting, sorting versus kurtosis and mean against sorting suggest a fluvial depositional environment. Petrographic analysis of selected sandstones reveals the presence of quartz, feldspars (plagioclase and microcline) and mica (biotite and muscovite). Quartz (especially monocrystalline) dominates followed by feldspar with minor muscovite and biotite. Heavy mineral study revealed the presence of non-opaque mineral suites suggesting that the sediments are derived from the basement complex of igneous and metamorphic rocks. The heavy minerals observed include staurolite, rutile, kyanite, zircon and sphene. The samples are dominated by stauronite which signifies low grade metamorphism in the area. Integration of sedimentological and petrographical characteristics in this study suggest that the sandstone samples are derived from mixed origin and deposited in fluviatile environment under high energy setting not too far from the source. Hence it is a proximal deposit.

Retraction: Estimation of sediment accumulation rates using naturally occuring 210Pb models and heavy metal measurements in Gülbahçe Hydrothermal Vent Zone

In this study, sediment chronology was determined by using Lead-210 (210Pb) dating models in Gulbahce Bay. Sediment cores were obtained via a gravity core sampler from hydrothermal area and also from reference point and surficial distribution of Polonium-210 (210Po) was investigated in the study area. The average surficial 210Po concentration was relatively higher in hydrothermal area than the reference point. Sedimentation rates in Core reference point (RN) displayed an increase till the 1940’s and a decrease afterwards, sedimentation rates in any core from hydrothermal area did not exhibit regular continuous increase or decrease. The 210Pb fluxes measured from core inventories are close to each other but they are a bit higher than the average mediterranean and mean atmospheric 210Pb flux values. This situation indicates that there are outer contribution to the study area apart from atmospheric precipitation of 210Pb concentration. Average enrichment factors indicating that the sediments have not been co...

APPLYING IMAGE PROCESSING TOOLS TO ANALYZE THE SURFACE CHARACTERISTICS OF NANO ALUMINA (NANOAL2O3) AND NANO TITANIUM (NANOTIO2)

Composite material is a material constructed of two or more materials that leads with different physical or chemical characteristics. Nano Alumina (NANO AL2O3) and Nano Titanium (NANO TIO2) are normally used to construct the composite material. The fundamental of texture analysis seeks to derive a general efficient and compact quantitative description of textures so that various mathematical operations can be used to achieve, compare and transform of texture characteristics. Many mechanical and physical methods are used to measure the surface characteristics. Some of these methods suffered from accurate description of material surface. In addition, the details of material surface are not clear via applying the traditional methods for surface analyzing. This work is concentrated on combining many functions and steps of image processing method to understand and analyze the surface characteristics of the composite material (Nano Alumina and Nano Titanium). The implemented approach including many steps: image enhancement, texture analysis, edge detection and contour analysis. This approach leads to explain, extract, analyze and evaluate the characteristics of surface texture of the composite material via measuring of mean values for original gray image, adjusted gray image, equalized gray image and adapted gray image. The average mean values of Nano Alumina are 103, 110, 128 and 134 for the applied method respectively. The average mean values of Nano titanium are 120, 123, 125 and 129 respectively. As a conclusion the implemented approach of surface texture analysis indicated that there is a significant improvement at the surface characteristics for both equalization and adaptive methods compared with the adjustment method.

Carbon dioxide capture by nitrogen containing organic materials – A density functional theory investigation

Abstract The present work deals with study and analysis of density functional theory (DFT) methods for carbon dioxide capture using nitrogen containing organic polymerix materials. Nitrogen containing organic materials as potential candidates for CO2 capture is examined by using various density functional methods. The performance of a set range of several density functionals from the representative families of pure generalized gradient approximation (GGA), meta-GGA, hybrid, long range corrected (LRC) and dispersion corrected functionals were considered for their assessment in calculating binding energies associated with gas molecules (CO2 and N2) with the nitrogen containing model systems. The theory behind the different classes of density functionals was discussed and the functionals were assessed using statistical parameters such as mean average binding energy values, mean absolute errors and root mean square deviations in calculating the binding energies with the gas molecules. A total of 80 method/basis set combinations were examined through the analysis of binding energies of the gas molecules (CO2 and N2) with various nitrogen containing aromatic frameworks. Unlike previosly reported DFt benchmarks, which calculate single point energies, in this work we have calculated binding energies for the geometries optmizied at each theoretical methods. For comparision the complexes were euavluated using Moller–Plesset perturbation method of second order MP2/aug-cc-pVDZ level theory to yield a best estimate of binding energies. We found that conventional functionals are not suitable for N-conatining model systems and tend to overestimate or understimate the binding energies. Considering both accuracy and efficiency the functionals we recommend are ωB97X-D, CAM-B3LYP and M06-2X. Also the functionals ωB97, ωB97X, PBE0 and M06-HF show relatively less errors and give reliable binding energies for the complexes. We have also discussed the mechanism for carbon dioxide interaction with polymer fragment anf functional groups in the model cluster systems. The conclusions obtained in the study would help in increasing awareness of the strengths and weaknesses of the DFT methods and assist the experimental researchers in efficient molecular engineering of porous covalent architectures for carbon dioxide capture.

Identification of Age-Related Macular Degeneration Using OCT Images

Age-related Macular Degeneration is the most leading retinal disease in the recent years. Macular degeneration occurs when the central portion of the retina, called macula deteriorates. As the deterioration occurs with the age, it is commonly referred as Age-related Macular Degeneration. This disease can be visualized by several imaging modalities such as Fundus imaging technique, Optical Coherence Tomography (OCT) technique and many other. Optical Coherence Tomography is the widely used technique for screening the Age-related Macular Degeneration disease, because it has an ability to detect the very minute changes in the retina. The Healthy and AMD affected OCT images are classified by extracting the Retinal Pigmented Epithelium (RPE) layer of the images using the image processing technique. The extracted layer is sampled, the no. of white pixels in each of the sample is counted and the mean value of the no. of pixels is calculated. The average mean value is calculated for both the Healthy and the AMD affected images and a threshold value is fixed and a decision rule is framed to classify the images of interest. The proposed method showed an accuracy of 75%.