International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Gradient Boosting Machine Based on PSO for prediction of Leukemia after a Breast Cancer Diagnosis
Get PDFThe purpose of this study is to develop an accurate risk predictive model for Chronic Myeloid Leukemia (CML) after an early diagnosis of Breast Cancer (BC). Gradient Boosting Machine (GBM) classification algorithm has been applied to the SEER breast cancer dataset for females diagnosed with BC from 2010 to 2016. A practical Swarm optimizer (PSO) was utilized to optimize the GBM algorithm's hyperparameters to find the SEER dataset's best attributes. Nine attributes were carefully selected to study the growth of CML after a lag time of 6 months following BC's diagnosis. The results revealed that the predictive model could classify patients with breast cancer only and patients with breast cancer with Leukemia by an achieved Accuracy, Sensitivity, and Speciï¬city rates of 98.5 %, 99 %, 97.85 %, respectively. To verify the performance of the proposed algorithm, the accuracy of the suggested GBM classifier model was compared with another state-of-the-art model classifiers KNN (k-Nearest Neighbor), SVM (Support Vector Machine), and RF (Random Forest), which are commonly applied algorithms in most of the existing literature. The results also proved the superior ability of the implemented GBM model Classifier in the classification of breast cancer disease and prediction of patients having Leukemia developed after having breast cancer. These results are promising as they show the integral role of the GBM classifier to classify and predict the tumor with high accuracy and efficiency, which will further help in better cancer diagnosis and treatment of the disease
Multi-Stage Statistical Approach to Wind Power Forecast Errors Evaluation: A Southern Sulawesi Case Study
Get PDFWind Power Plant (WPP) is part of renewable energy sources, with rapid expansion worldwide. It has the advantages of clean and green energy, but its uncertainty leads to an additional grid integration cost. The uncertainty of wind power output is much dependent on the accuracy of the wind power forecast (WPF) result. Since there is no perfect wind power forecast, understanding the current system's forecast accuracy characteristics is essential in expecting typical errors faced in the future. This paper proposed a new algorithm of the statistical approach method to evaluate characteristics of wind power forecast errors (WPFE) from an observed power system with high-penetration WPP. This method combined the approach of scatter diagram, statistical distribution, standard error performance, and score weighting in a multi-stage algorithm. It consists of serial and parallel processes to check the consistency of the results. In this study, a comprehensive analysis was made of various scenarios based on location and timescale. This proposed algorithm has been successfully tested on statistical data of Sidrap WPP and Jeneponto WPP in the Southern Sulawesi power system. The result showed that the scenario with the aggregation of both WPPs in hour-ahead timescale has the most accurate and consistent performance among all scenarios. It demonstrated specific characteristics of WPFE in the observed power system that can be used as an essential starting point in conducting future wind integration expansion studies
Genetic Diversity and Sequences Analysis from Elaeis guineensis Jacq. Infected with Ganoderma boninense
Get PDFEarly screening tests on the seedling phase of Elaeis guineensis would have a significant effect on diminishing the time and the resources needed to increase variations in the oil palm breeding program to resistance Ganoderma. This research was conducted to evaluate the genetic diversity and heterozygosity among eight populations of E. guineensis Jacq. Seedlings and matures using the molecular of variant loci analysis to an early screening. PCR and GenAlEx studied the method of genetic diversity and oil palm resistance genes. The results showed the microsatellite markers (EgIFR, Eg001, Eg002, and Eg003) pattern in the DNA and protein-encoding in the oil palm seedlings' root tissue to Ganoderma resistance played a potential early screening role in material planting. The polymorphic information content (PIC) values were identified as 0.655-0.998. The means number of allele distribution in each population and loci showed Ho = 0.48. The mean of heterozygosity was found in 0.67 level. The analysis molecular of variance (AMOVA) showed a significant variability by 45% among individuals and 53% within individuals in the population. A total of 92 data sequences were identified and available on the NCBI database. They have a similarity from proteins, i.e., isoflavone reductase, polyadenylated, heat shock cognate, and thaumatin. The highest total score was showed 117, and the similarity was identified at 100%. Furthermore, the phylogenetic clusters were distinct between the seedling and mature based on the same gene and protein. This study suggested the markers and proteins important to E. guineensis against Ganoderma boninense
Application of 60/70 Grade Bitumen with Layer Variations on Ballast Structures
Get PDFThe conventional track application dominates the Indonesian rail track type. The rail track deterioration due to the overloading train becomes a crucial issue since it leads to high maintenance costs. Damage to the rail track can reduce its service life and carrying capacity. This research utilized the 60/70 grade bitumen as a binding material and stabilization of ballast structure. The aim is to analyze the mechanical behavior of new-ballast and poor-ballast structures, with 4% of the 60/70 grade bitumen in one layer (ballast surface layer) and three layers. The specimen’s weight, vertical deformation, elastic modulus, and ballast material abrasion have been analyzed using a UTM compressive strength test. The most obvious finding to appear from this research is that the new-ballast-based specimen, as for being free of mud and dust, was lighter in weight than the poor-ballast-based sample. Furthermore, the new-ballast and poor-ballast-based specimens added with 4% of the 60/70 grade bitumen had a lower vertical deformation than the baseline specimen. The position of 4% of the 60/70 grade bitumen on the ballast surface layer produced an optimum load distribution to the overall ballast layer. Also, the specimens consisting of new-ballast produced a higher elastic modulus compared to the specimens comprising poor-ballast. Lastly, the presence of the well-distributed asphalt on three layers of ballast structure could produce the minimum abrasion value due to the possibility that asphalt materials could protect ballast materials from abrasion
Land Use and Land Cover Change Detection for Water Yield Estimation using Remote Sensing Data in Batu Pahat, Johor
Get PDFGlobally, the accelerating urbanization led by industrialization and population growth causes severe environmental degradation. The urban expansion particularly to the conversion of land activities affects the ecosystem services critically. This study helps to fill in the gap of determining water yield in the urban area to reduce water stress due to the spatial land use change. The research objectives are to quantify the spatial land use change in Batu Pahat, Johor in the year 1999, 2010, and 2018. Second, to identify the water yield of Batu Pahat in the years 1999, 2010, and 2018. Third, to determine the relationship between water yield, vegetation, and urban expansion. The methods used are landscape change, water yield simulation, and statistical analysis by using the software included ENVI, ArcGIS, FRAGSTAT, Annual Water Yield InVEST Model, and Microsoft Excel. Raw satellite images were extracted for the year 1999, 2010, and 2018. The supervised classification of LULC (Land Use and Land Cover) was done based on the region created which are built-up area, cleared land, vegetation, and water bodies. This study generates results for the changes in percentage area for each LULC class. The highest percentage of area in Batu Pahat is vegetation while the cleared land ranked lowest. In conclusion, this study will aid in understanding and provided empirical data result for the urban expansion and water yield in Batu Pahat, Johor by using GIS and remote sensing applications to produce land use and water yield map as final output
The Geoelectric Resistivity Methods to Determine the Presence or Position of Layers and the Aquifer Type in Transition and Inland Tropical Peatlands of Central Kalimantan, Indonesia
Get PDFThe decreasing groundwater level (GWL) in degraded tropical peatland areas during the dry season has been one source of annual peat fire disasters in Central Kalimantan. After the severe peatland fire in 2015, Peatland Restoration Agency's strategies' peatland restoration efforts enhance peat moisture and increase the groundwater level of the hundreds of deep wells and canal blocking in the burned area of 2015. This study examines the use of geoelectric resistivity methods in determining the attachment or position of layers and types of aquifers in transition and inland tropical peatland. The research was conducted on transitional peatlands in Sidodadi Village with 19 estimate points of resistivity geoelectric, nine estimate points in the inland swamp in Taruna Jaya Village, and 18 estimate points Kalampangan Village. This research used the quantitative approach is a one-dimensional (1 D) resistivity geoelectric, which using the Schlumberger array. While the qualitative process verified the result of sequences observation with two drill wells in Sidodadi, two drill wells in Taruna Jaya, 18 hand drill wells in Kalampangan, and geological stratigraphy. The research results obtained 4 (four) layers of composition with resistivities ranging from 1.224 - 661.1 Ωm in Sidodadi, ranging from 3.37 – 7,950 Ωm in Taruna Jaya Kalampangan ranging from 5.36 - 16719 Ωm. The geoelectric data and field verification interpretation show that the soil/lithology layer consists of 4 (four) layers: peat, sand, sandy clay, and clay. The type of aquifer is an unconfined aquifer. The type of aquifer is an unconfined aquifer
Steroid Profiles of Wild Terror Green (Andinoacara rivulatus) Associated with Gonadal Histology in the Baba River, Ecuador
Get PDFNative cichlids in Ecuador are represented by Andionoacara rivulatus and Cichlasoma festae mainly. These aquatic species are a fundamental part of the food chain of rural communities in the western subtropical region of Ecuador. For the first time, a detailed study on the gonadal development in A. rivulatus males and females was carried out, and the characterization of sex hormones present in their blood plasma from May 2019 to January 2020. Fish samples were captured in the multipurpose Baba River dam upstream of the Guayas River, Ecuador. Gonad and blood samples were collected for histological analysis and assaying of steroidal hormones such as 17β-estradiol and 11-ketotestosterone. The sex steroids were quantified by enzyme immunoassay (ELISA). As a result, the fish samples have asynchronous characteristics and show all development stages in testes and ovaries. The serological fluctuations show statistical differences (p <0.05) between the development stages, with low concentrations of estradiol and 11-KT. These results are somewhat related to the hydrological period of capture, where the temperature, luminosity, and rainfall play a fundamental role in the oogenesis and spermatogenesis in the captured fishes. The highest concentration of E2 is detected in female vitellogenesis stages and the highest concentration of 11-KT in the male spermatogenesis stage. These results confirm the fundamental role of these hormones in the key periods of gonadal development. In future studies, it is important to monitor the maturational hormone 17α, 20β-DHP, and the vitellogenin concentrations and thus understand the reproductive physiology of A. rivulatus
A Crowdsourced Contact Tracing Model to Detect COVID-19 Patients using Smartphones
Get PDFMillions of people have died all across the world because of the COVID-19 outbreak. Researchers worldwide are working together and facing many challenges to bring out the proper vaccines to prevent this infectious virus. Therefore, in this study, a system has been designed which will be adequate to stop the outbreak of COVID-19 by spreading awareness of the COVID-19 infected patient situated area. The model has been formulated for Location base COVID-19 patient identification using mobile crowdsourcing. In this system, the government will update the information about inflected COVID-19 patients. It will notify other users in the vulnerable area to stay at 6 feet or 1.8-meter distance to remain safe. We utilized the Haversine formula and circle formula to generate the unsafe area. Ten thousand valid information has been collected to support the results of this research. The algorithm is tested for 10 test cases every time, and the datasets are increased by 1000. The run time of that algorithm is growing linearly. Thus, we can say that the proposed algorithm can run in polynomial time. The algorithm's correctness is also being tested where it is found that the proposed algorithm is correct and efficient. We also implement the system, and the application is evaluated by taking feedback from users. Thus, people can use our system to keep themselves in a safe area and decrease COVID patients' rate
Evaluation of Correlations of Flow Boiling Heat Transfer of R600a in a Flat-Plate Solar Collector/Evaporator
Get PDFIn the current research work, the behavior of the boiling heat transfer coefficient in a flat-plate solar collector/evaporator, component of a direct-expansion solar-assisted heat pump (DX-SAHP) was studied using a hydrocarbon refrigerant with zero Ozone Depletion Potential (ODP) and low Global Warming Potential (GWP). The main dimensions of the collector/evaporator are 0.8, 3.8, and 1000 mm of the fin thickness, internal diameter, and length, respectively. Five experimental tests were realized at different times of the day for obtaining the results, with mass velocities varying between 197.59 and 267.26 kg·m-2·s-1, and the heat flux having values between 72.83 and 488.27 W·m-2. The operating values in tests, such as refrigerant pressure and temperature, were taken in a built prototype. The numerical analysis was carried out considering different correlations proposed by Chen, Wojtan, and Kattan. The Wojtan mathematical model offered the best projection of the heat transfer effect for the different transition zones of a two-phase flow along the pipeline. The boiling heat transfer coefficients had approximate maximum values of 8.2, 8.5, 7.8, 6.7, and 5.8 kW·m-2·K-1 for the A, B, C, D, and E tests prediction by Wojtan. Moreover, the boiling heat transfer coefficients increased as the mass velocity enhanced and the rise of vapor quality as the mass velocity was fixed. In this study, the effect of solar radiation, vapor quality on the measured heat transfer coefficient was analyzed
A Novel Multi-Patient Mechanical Ventilator Drive System Using Continuously Variable Transmission and Reverse Gearbox
Get PDFIn the present study, a new model of multi-mechanical ventilator drive using a continuously variable transmission (CVT) cone was presented as the main driving force to control the pressure of the BVM Ambu bag, which can produce different airflow pressures for several patients, and using a worm gear to isolate the CVT cone so as not to get the load generated from the pressure of the Ambu bag. In addition, the reverse gear transmission system is used to control the direction of rotation, and the leadscrew is used to change the rotation according to the linear translational motion of the Ambu bag pushing arm. In this system, a DC motor is used as the main driver, and a flexible tuner cable that can be connected to other ventilators is utilized. This research shows that this CVT system can reduce rotation down to 60.35% and increase rotation up to 148.26% with constant rotation input. There are 23 points of change in the position of the belt, which causes variations in the pouch pressing. The system can produce the highest and lowest pressure value at 20.2 and 0.4 cm H2O. Simultaneously, the rotation of the flexible tuner cable showed no significant change. However, the weakness in the CVT system is the belt friction with the cone surface causing heat and slippage. In this case, the selection of the appropriate material and belt shape can cause belt displacement easiness that important in appropriate speed for applied pressure