International Journal on Advanced Science, Engineering and Information Technology
Not a member yet
2006 research outputs found
Sort by
Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine
Get PDFPigmented skin lesion identification is essential for detecting harmful pathologies related to this large organ, especially cancer. An analysis of the different methods and projects developed to diagnose these illnesses throughout the years showed that they had become very useful tools to identify melanoma, dermatofibroma, and basal cell carcinoma, among other types of cancer, are seen through the use of new computer-aided technologies. The most common diagnosis is based on dermoscopy and the dermatologist expertise that can improve accuracy with image detection techniques and classification by computer. Therefore, this study aims to develop software models able to detect and classify skin cancer. The following work is based on the use of dermoscopy images obtained from the HAM10000 dataset, a database with 10000 images previously tested and validated for research use. The main process is divided into three relevant parts: image segmentation, feature extraction (FE) using ten different pre-trained Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM) to establish a classification model. According to the results, the models of classification performed very well using the image segmentation step, showing average accuracies between 80.67% (Xception) and 90% (Alexnet). In contrast to the process without using image segmentation, where no method reached 60%. AlexNet plus SVM model showed the minor running time and presented the higher accuracy rate (90.34%) for the correct identification and classification of the seven categories of cutaneous lesions taken into account
Effect of Tillage and Crop Rotation on Cereal Crops Yield in the Urals of the Nonblack Earth Zone of Russia
Get PDFProper selection of tillage system is important to increase yields. The work purpose is to assess the effectiveness of three different crop rotation and tillage systems combined with the chemistries use and repetitive sowing methods on spring wheat productive capacity and technology properties of its grains under natural conditions of the Urals in the nonblack earth zone of Russia. The study's objectives included studying the effectiveness of tillage systems in the region's conditions, evaluating the need for the use of chemicals, assessing the impact of each of the factors: meteorological conditions, soil fertility, agrotechnology, and intensification methods on wheat yield indicators. A comprehensive approach is used throughout this work. The study was carried out in 2006-2019 in the forest-steppe region of the Southern Urals (Ural Federal District of the Russian Federation). An experiment involving three influencing factors was performed: Factor 1 – the tillage system in crop rotation; Factor 2 – the chemical methods use; Factor 3 – the preceding crop presence. An inverse relationship was found between spring wheat productivity and weed share (Pearson correlation -0.83). There was a negative correlation between the distance from fallow to the plants' proportion affected by fungal rot. Their number has multiplied by more than 1.7. Depending on the preceding crop, the average yield for fallow wheat was 2.94 t per 1 ha, and for the third wheat after fallow, 1.44 t per 1 ha. The study bridged the lack of knowledge in the established task of increasing wheat yields in the Urals steppe forest territories. The three most important factors influencing wheat grain yield and quality are: 1) combined use of chemicals and fertilizers (45% contribution), availability of the forecrop, meteorological and climatic conditions, and tillage system. Consequently, the yield of spring wheat is related to the level of modern agricultural technologies development, particularly on the level of intensification required. Future similar studies should create a unified spring wheat database and allow the ability to adjust performance indicators depending on areas with different climatic conditions
The Verification Significant Wave Height Technique in Indonesian Waters and Analysis of Low Air Pressure
Get PDFA limited number of marine meteorological instruments for making observations in Indonesian waters are problems in verifying the BMKG-OFS model. The satellite altimetry was selected as a verification tool due to its wide measurement range. The verification was carried out by adjusting the coordinates, time, and grid of SWH obtained and orbit of the satellite path from the satellite altimetry to the model and overlaying the models' results as a pattern analysis in July 2018 – June 2019. The next step was a statistical analysis to determine the performance of the model. The analysis obtained 43% maximum SWH formed due to the low-pressure centers in the Pacific Ocean. The remaining spreads across the South China Sea, Indian Ocean, Andaman Sea and the Gulf of Australia. This study revealed that the SWH values from satellites were higher than the model. On every three hourly and monthly bases, the SWH of the bias, RMSE, and correlation coefficient were equivalent. The lowest bias of 0.26 occurred at 9.00 UTC, the lowest RMSE of 0.48 occurred at 21:00 UTC, and the maximum correlation coefficient of 0.82 occurred at 18:00 UTC. Whereas on a monthly scale, the lowest bias and RMSE, and the maximum correlation coefficient occurred in November. Based on these results, the BMKG-OFS model can be used to predict SWH in Indonesian waters. Besides, this verification technique can be an alternative as a new tool to verify maritime weather in the operational of BMKG
The Biological Signal Visualization Algorithm for Heart Surgery Simulator
Get PDFThis paper introduces a bio-signal visualization algorithm for developing a cardiovascular medical virtual training simulator. It provides opportunities for practitioners and specialists who have complicated medical practice to perform enough training exercises. To reimplement the current study operation situation as much as possible, we implemented an algorithm that can easily identify each biological signal based on the patient monitoring system by visualized. In the future, combining physical engines with valid verification of whether they are suitable for actual medical staff and building simulations. That is identical to actual surgical conditions will enable more scenarios for patient diagnosis and more training programs in various healthcare fields. It produces talented individuals with specialized skills for medical personnel by training in multiple health care fields and more patients' conditions. In addition, for emergencies and emergencies in a real surgical environment, patterns through pulse rate/blood pressure changes were implemented when certain values were entered. Users could be given various situations through the WebSocket communication method as a shield to provide them with specific situations (sudden blood pressure reduction, pulse rate rise, and breathing anxiety) suitable for each training scenario. Also, our method interacts with the user in real-time, keeps the signal uninterrupted and continuous when it gives signals such as a particular situation
Object Searching on Real-Time Video Using Oriented FAST and Rotated BRIEF Algorithm
Get PDFThe pre-processing and feature extraction stages are the primary stages in object searching on video data. Processing video in all frames is inefficient. Frames that have the same information should only be once processed to the next stage. Then, the feature extraction algorithm that is often used to process video frames is SIFT and SURF. The SIFT algorithm is very accurate but slow. On the other hand, the SURF algorithm is fast but less accurate. Therefore, the requirement for keyframe selection and feature extraction methods is fast and accurate in object searching on real-time video. Video is pre-processed by extracting video into frames. Then, the mutual information entropy method is used for keyframe selection. Keyframes are extracted using the ORB algorithm. The multiple object detection in the video is done by clustering on features. The feature extraction results on each cluster are matched with the results of the feature from the query image. Matching results from keyframe on video with the query image is used to retrieve the video's frame information. The experiment shows that keyframe selection is beneficial in real-time video data processing because the keyframe selection speed is faster than feature extraction on each frame. Then, feature extraction using the ORB algorithm results 2 times faster speed results than SIFT and SURF algorithms with values not so different from SIFT algorithm. This study's results can be developed as a security warning system in public places, especially by security in providing evidence of criminal cases from videos
Landslide and Environmental Risk from Oil Spill due to the Rupture of SOTE and OCP Pipelines, San Rafael Falls, Amazon Basin, Ecuador
Get PDFA landslide generated an environmental risk due to a provoked oil spill on April 7, 2020, with the SOTE and OCP pipelines rupture. This research aims to determine the areas susceptible to landslides in the river basin Quijos of the Coca River and estimate the environmental risk from exposure to the oil spill. A water analysis of the Coca River was performed by using the Mora-Vahrson method and GIS tools. The subsequent water sampling was probabilistic in a simple random way, and the analyzed parameters were oils and grease, Ba, Cd, Cr, BOD, COD, TPH, OD, Pb, and SST. The results show that 61.17% (572.68 km2) of the total studied area (936.19 km2) is susceptible to landslide hazards. In detail, 0.25% (2.34 km2) of the area is considered to be of very high susceptibility, 26.72% (250.12 km2) of high susceptibility, 11.82% (110.66 km2) of moderate susceptibility, and 0.04 (0.37 km2) of low susceptibility. Four of them were within the permissible limits from the ten analyzed parameters, which correspond to Ba with 0.70 mg/L, OD with 7.4% of saturation, BOD5 with 2 mg/L, and COD with 25 mg/L. The other six parameters, including oils and fats, exhibited a significant increase in concentrations after the oil spill, yielding Cd 0.05 mg/L, total Cr 0.45 mg/L, TPH 0.20 mg/L, Pb 0.20 mg/L, and SST 20%. These results are outside the permissible limits, meaning that the river waters are contaminated
Morphometric Characteristics of Cipeles Watershed to Identify Flood Prone Area
Get PDFCipeles watershed is located on Sumedang Regency, West Java Province. This research aims to identify the flood-prone area in the Cipeles Watershed based on morphometric characteristics. This research was conducted through studio analysis using Map Info and Global Mapper software and mathematical calculations. The data used in this research are stream network and topography. Digital Elevation Model was used to analyze the slope of the research area. Morphometric aspects used in the mathematical calculations consist of Drainage density, Drainage texture, Ratio of circularity, Ratio of elongation, and Form factor. The research area is a hilly area with high relief and a very steep-slightly steep slope in the west and south, relatively gentle in the middle to the east of the research area. It consists of parallel, subparallel, subradial, rectangular, dendritic, and subdendritic drainage patterns. Cipeles watershed has 38 subwatersheds with predominantly very elongated-circular shape and very coarse-coarse texture. The research area has relatively high rainfall that potentially causes flooding, especially downstream of the Cpl_10, Cpl_11, Cpl_12, Cpl_13, Cpl_14, Cpl_15, Cpl_16, and Cpl_17 subwatersheds. The research area is classified into low and moderate risk levels of flood potential. The low-risk level is located in Tanjungsari and Rancakalong district. The moderate risk level is located in North Sumedang, South Sumedang, Situraja, and Cimalaka district. The results showed that quantitative research could be used to identify flood prone area. It is recommended that the Cipeles Watershed can be well maintained through integrated watershed management and land use management
Analysis of Vehicle-to-Vehicle Basic Safety Message Communication Using Connectivity Characteristic Matrix
Get PDFThis work investigates vehicular mobility and the main factors that impact Vehicle-to-Vehicle (V2V) connectivity using Basic Safety Message (BSM). MATLAB simulation used for Vehicular mobility and connectivity characterization under specific road traffic conditions. The simulation covers connectivity between traveling vehicles and a selected target vehicle to monitor communication interaction and establish an envelope within which reliable communication and BSM messages can occur. Another objective of this work is to use BSM exchanges to indicate the level of connectivity used to estimate traffic density, thus enabling congestion prediction. The obtained data contain information describing many vehicles, distance, connectivity time, and traffic density. The simulation results indicate an increase in the number of connected vehicles (connectivity level) as a function of both traffic density and communication range. Extending communication over fixed duration showed increased connectivity levels, allowing more vehicles to interact and exchange BSMs. The rate of change of connectivity per communication range is an indication of the state of traffic. Continuous connectivity proved to be less than general connectivity as vehicles exits through ramps and move from one cluster of vehicles to another. Varying duration per fixed communication range produced evidence of spatial domain change, and cluster variation as threshold values separate vehicles clusters in time and space. This work presented a model to help analyze the impact of vehicular mobility as a function of BSM communication range variation and connectivity duration variation correlated to traffic density. Â
Spatiotemporal Variability in Soil Water Content Profiles under Young and Mature Oil Palm Plantations in North Bengkulu Regency
Get PDFSoil water content (SWC) profile refers to the vertical distribution of volumetric SWC at a certain depth of soil concerning the plant water availability. The current study aimed to evaluate the vertically spatial distributions and temporal variations in SWC profiles under young and mature oil palm trees during the end period of the rainy season. Twenty couples of sensors were inserted into 5 cm soil depth intervals up to 100 cm. Each sensor pair was connected to the dielectric instrument to measure the electrical impedance (Z, in kΩ) at each soil layer. The measured Z was then converted to the gravimetric SWC (θg, in g.g-1) using an equation of θg = 0.62.Z-0.2 found in our previous study. The gravimetric SWC data were then multiplied by soil bulk density for corresponding layers to get volumetric SWC (θv, in cm3.cm-3). Results showed that soil water profiles' depths were 40 to 70 mm higher under mature than under young oil palm plantations during six weeks of measurements. The vertical distribution of soil bulk density could be why the spatiotemporal variability in water content profile. Looser layers throughout the young oil palm soil profile might cause a higher proportion of drainage pores and result in less water content compared to the denser layers under the mature oil palm
The Effect of Mixed Inoculum Addition Concentration and Fermentation Time on the Characteristics of Dry Cocoa Beans (Theobroma cacao L.)
Get PDFThe fermentation process has an important role in determining the quality of cocoa beans by forming taste, color, aroma, and appearance. The purpose of this study was to determine the effect of inoculum concentration and fermentation time on the characteristics of dry cocoa beans and determine the best conditions for both inoculum addition concentration and fermentation time to produce dry cocoa beans under Indonesian national standards. The research used completely randomized design with two factors; the first factor was the starter concentration consisting of controls (0%), 0.5%, 1%, 1.5%, and 2% (v/w). The second factor is the fermentation time, namely 1 day, 2 days, 3 days, 4 days, and 5 days. Treatment was repeated twice to get 50 units of the experiment. The results showed that the addition concentration of mixed inoculum (Saccharomyces cerevisiae and Lactobacillus plantarum) had a significant effect on changes in temperature and pH during fermentation, and it also had a significant effect on total unfermented beans. This study showed that time fermentation treatment had a very significant effect on all tests. The interaction of the two treatments had a significant effect on temperature changes during fermentation; it also significantly affected total unfermented beans. According to the Indonesian National Standard of cocoa beans, the best treatment, and the fastest fermentation time to produce the first quality standard (cut test) is a concentration of 1% mixed inoculum and fermentation in 3 days