IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Predictive Analysis of Rice Pest Distribution in Bali Province Using Backpropagation Neural Network
Full text linkThe distribution of pests in rice plants results in significant losses in production and damage to rice plants for farmers, seen from data on the area of rice borer attacks in the province of Bali in Tabanan district. Therefore, by predicting the distribution of rice pests, we can know the pattern of pest attacks so that we can anticipate them because predicting can provide accuracy and error values through the test results. One of the prediction models is BPNN, where BPNN's advantages for solving complex problems are very suitable for use where large amounts of data are involved and many input/output variables, BPNN is also capable of modeling nonlinear relationships between input and output variables, which may be difficult to capture by this type of predictive model. other. Backpropagation includes supervised learning, which means it can learn from labeled examples and can make accurate predictions on new, unlabeled data. Split data using K-fold cross-validation serves to assess the process performance of an algorithmic method by dividing random data samples and grouping the data as many as K k-fold values
SVEAuAdIR model of COVID-19 Transmission
Full text linkThe COVID-19 pandemic that has occurred has received worldwide attention due to the rapid rate of transmission of the outbreak and the large number of deaths that occurred. The aim of this study is to build the SVEAuAdIR model , determine the transmission of COVID-19 in Indonesia by forecast the spread of the disease, and determine the effect of vaccination by looking at the basic reproduction number of SVEAuAdIR model. The results obtained from MAPE on the model are 12%. So it can be said that the SVEAuAdIR model is good for prediction models for the spread of COVID-19. The situation where there are no more individuals infected with COVID-19 is called COVID-19 disease free, thus it is predicted that Indonesia will be free of COVID-19 on October 7, 2021. The target of the Indonesian Ministry of Health is that by the end of 2021 the spread of COVID-19 can be stopped . However, on October 7, 2021, judging from the actual data during this research, there were still new cases of COVID-19. On that day there were 1393 new cases infected with COVID-19. Thus, showing that Indonesia's target of being free of COVID-19 disease by the end of 2021 has not been achieved. The number of the SVEAuAdIR model is in the range of values , which means that the spread of disease is close to disease-free. Based on the results of the value of the SVEAuAdIR model, this study concluded that vaccination could reduce the spread of COVID-19 compared to those who did not vaccinat
The Tweetology of New and Renewable Energy in Indonesia
Full text linkThe amount of unstructured data is increasing annually, which is promising forgaining insights. Twitter, a platform producing unstructured data, is currently one of the mostpopular media platforms used for conducting research on a topic's trend. This study attempts toanalyze the topic of New and Renewable Energy (NRE) in Indonesia. The purpose of this studyis to gain insights into the NRE topic trend over the last ten years by modeling the topicsdiscussed on Twitter and examining the location distribution of users who post tweets about thetopic. Accordingly, this study employed descriptive analysis, geocoding analysis, and topicmodeling. The results of descriptive analysis show that the development of NRE has acceleratedin recent years, particularly in 2021. Geocoding analysis reveals that the distribution of peoplewho engage in NRE posting activities is dominated by DKI Jakarta province. Topic modelingyielding two topics that were discussed the most by Indonesians over a 10-year period. The twotopics are related to government policies that support the development of NRE and electricity,which is Indonesia's focus in NRE. This study highlights the importance of analyzing theTweetology of NRE
Inverse Kinematic Algorithm with Newton-Raphson Method iteration to Control Robot Position and Orientation based on R programming language
Full text link The homogeneous transform program is a function used to calculate the homogeneous transformation matrix at a specific position and orientation of a three-link manipulator. The homogeneous transformation matrix is a 4x4 matrix used to represent the position and orientation of an object in three-dimensional space. In the program, the rotation matrix R is calculated using the Euler formula and stored in a 4x4 matrix along with the position coordinates. The Jacobian matrix function calculates the Jacobian matrix at a specific position and orientation of a three-link manipulator using the homogeneous transformation matrix. The Euler formula used in the program is based on the rotation matrices for rotations around the x, y, and z-axes. The output of these functions can be useful for future research in developing advanced manipulators with improved accuracy and flexibility. Research gaps in exploring the limitations of these functions in real-world applications, particularly in scenarios involving complex manipulator configurations and environmental factors
Classification Of Maternal Health Risk Using Three Models Naive Bayes Method
Full text linkLack of information related to maternal health care during pregnancy and post-pregnancy, especially in rural areas, results in many cases of pregnancy complications. Risk analysis for pregnant women is really needed as a reference in handling pregnant women so that the risk to pregnant women can be minimized. To analyze the risk of pregnant women can use data mining techniques by classifying the risk of pregnant women. This study proposes to classify Maternal Health Risk using the Naive Bayes method with three models, namely Gaussian, Multinomial, and Bournolli. The data used is the health data of pregnant women based on risk intensity which is grouped into three classes, namely low, mid and high risk. while the attributes are Age, Systolic Blood Pressure as SystolicBP, Diastolic BP as DiastolicBP, Blood Sugar as BS, Body Temperature as BodyTemp, and HeartRate. The results show that among the three Naïve Bayes models that have the best performance are the Multinomial and Bournolli with an accuracy of 84.8% while the Gaussian produces an accuracy of 82.6%
The Implementation of Mobile Technology in The Process of Reporting Disasters and Events
Full text linkTelecommunications have an important role in facilitating communication and information exchange, especially in emergency situations such as natural disasters and unexpected community events. Implementing mobile technology is a promising solution to improve the response and handling of in-kind problems. Mobile technology allows the public to quickly report incidents of disaster or security issues through applications or short message services. The implementation of mobile technology facilitates real-time communication between the community and Babinsa. The public can send reports quickly, convey important information, and share photos or videos as evidence of events. Babinsa, on the other hand, can respond more efficiently to these reports and take necessary actions based on the information received. Apart from that, mobile technology also supports two-way communication between Babinsa and the community. The public can also get the latest information about emergencies, efforts handling, or evacuation via app or direct message notification. Thus, the implementation of mobile technology can make a significant contribution to improving communication, response, and handling of disasters and community events
Backward Elimination for Feature Selection on Breast Cancer Classification Using Logistic Regression and Support Vector Machine Algorithms
Full text linkBreast cancer is a prevalent form of cancer that afflicts women across all nations globally. One of the ways that can be done as a prevention to reduce elevated fatality due to breast cancer is with a detection system that can determine whether a cancer is benign or malignant. Logistic Regression and Support Vector Machine (SVM) classification algorithms are often used to detect this disease, but the use of these two algorithms often doesn’t give optimal results when applied to datasets that have many features, so additional algorithm is needed to improve classification performance by using Backward Elimination feature selection. The comparison of Logistic Regression and SVM algorithms was carried out by applying feature selection to breast cancer data to see the best model. The breast cancer dataset has 30 features and two classes, Benign and Malignant. Backward Elimination has reduced features from 30 features to 13 features, thereby increasing the performance of both classification models. The best classification was obtained by using the Backward Elimination feature selection and linear kernel SVM with an increase in accuracy value from 96.14% to 97.02%, precision from 98.06% to 99.49%, recall from 90.48% to 92.38%, and the AUC from 0.95 to 0.96
The Effect of Data Augmentation in Deep Learning with Drone Object Detection
Full text link Drone object detection is one of the main applications of image processing technology and pattern recognition using deep learning. However, the limited drone image data that can be accessed for training detection algorithms is a challenge developing drone object detection technology. Therefore, many studies have been conducted to increase the amount of drone image data using data augmentation techniques. This study aims to evaluate the effect of data augmentation on deep learning accuracy in drone object detection using the YOLOv5 algorithm. The methods used in this research include collecting drone image data, augmenting data with rotate, crop, and cutout, training the YOLOv5 algorithm with and without data augmentation, as well as testing and analyzing training results.The results of the study show that data augmentation can't improve the accuracy of the YOLOv5 algorithm in drone object detection. Evidenced by the decreasing value of precision and [email protected] and the relatively constant value of recall and F-1 score. This is caused by too much augmentation, which can cause a loss of important information in the data and cause noise or distortion
Improving Cardiovascular Disease Prediction by Integrating Imputation, Imbalance Resampling, and Feature Selection Techniques into Machine Learning Model
Full text linkCardiovascular disease (CVD) is the leading cause of death worldwide. Primary prevention is by early prediction of the disease onset. Using laboratory data from the National Health and Nutrition Examination Survey (NHANES) in 2017-2020 timeframe (N= 7.974), we tested the ability of machine learning (ML) algorithms to classify individuals at risk. The ML models were evaluated based on their classification performances after comparing four imputation, three imbalance resampling, and three feature selection techniques.Due to its popularity, we utilized decision tree (DT) as the baseline. Integration of multiple imputation by chained equation (MICE) and synthetic minority oversampling with Tomek link down-sampling (SMOTETomek) into the model improved the area under the curve-receiver operating characteristics (AUC-ROC) from 57% to 83%. Applying simultaneous perturbation feature selection and ranking (spFSR) reduced the feature predictors from 144 to 30 features and the computational time by 22%. The best techniques were applied to six ML models, resulting in Xtreme gradient boosting (XGBoost) achieving the highest accuracy of 93% and AUC-ROC of 89%.The accuracy of our ML model in predicting CVD outperforms those from previous studies. We also highlight the important causes of CVD, which might be investigated further for potential effects on electronic health records.
Classification Methods Performance On Logistic Package State Recognition
Full text link In the distribution sector, logistic package experience activities, such as transport, distribution, storage, packaging, and handling. Even though those processes have reasonable operational procedures, sometimes the package experience mishandling. The mishandling is hard to identify because many packages run simultaneously, and not all processes are monitored. An Inertial Measurement Unit (IMU) is installed inside a package to collect three acceleration and rotation data. The data is then labeled manually into four classes: correct handling, vertical fall, and thrown and rotating fall. Then, using cross-validation, ten classifiers were used to generate a model to classify the logistic package status and evaluate the accuracy score. It is hard to differentiate between free-fall and thrown. The classification only uses the accelerometer data to minimize the running time. The correct handling classification gives a good result because the data pattern has few variations. However, the thrown, free-fall and rotating data give a lower result because the pattern resembles each other. The average accuracy of the ten classifications is 78.15, with a mean deviation of 4.31. The best classifier for this research is the Gaussian Process, with a mean accuracy of 94.4 % and a deviation of 3.5 %