Sriwijaya Journal of Informatics and Applications (SJIA)
Not a member yet
49 research outputs found
Sort by
Automatic Clustering and Fuzzy Logical Relationship to Predict the Volume of Indonesia Natural Rubber Export
Get PDFNatural rubber is one of the pillars of Indonesia's export commodities. However, over the last few years, the export value of natural rubber has decreased due to an oversupply of this commodity in the global market. To overcome this problem, it is possible to predict the volume of Indonesia natural rubber exports. Predicted values can also help the government to compile market intelligence for natural rubber commodities periodically. In this study, the prediction of the export volume of natural rubber was carried out using the Automatic Clustering as an interval maker in the Fuzzy Time Series or usually called Automatic Clustering and Fuzzy Logical Relationship (ACFLR). The data used is 51 data per year from 1970 to 2020. The purpose of this study is to predict the volume of Indonesia natural rubber exports and compare the prediction results between the Automatic Clustering and Fuzzy Logical Relationship (ACFLR) and Chen's Fuzzy Time Series. The results showed that there was a significant difference between the two methods, ACFLR got 0.5316% MAPE with and Chen's Fuzzy Time Series model got 8.009%. Show that the ACFLR method performs better than the pure Fuzzy Time Series in predicting volume of Indonesia natural rubber exports
Identification Types Of Student Learning Modalities In Physics Subjects With Expert Systems Using Bayes Theorem Method
Get PDFLearning modality is a person's way of absorbing and processing information effectively and efficiently. This study aims to determine the results of the identification types of student learning modalities in physics subjects with an expert system using the Bayes theorem method, and the accuracy of the Bayes theorem method in identifying types of student learning modalities in physics subjects. This study uses the Bayes theorem method because it can produce a parameter estimate by combining information from the sample and other information that has been previously available to determine the results of the learning modality. This study uses 21 characteristics of learning modalities, 3 types of learning modalities, and 30 test cases obtained from an expert physics teacher at SMA Sumsel Jaya Palembang. Based on the tests that have been carried out, the results show that the system has an accuracy of 90% in identifying types of student learning modalities in physics subjects. It can be concluded that the Bayes theorem method can be used to identify types of student learning modalities in physics subjects
CLASSIFICATION OF ATRIAL FIBRILLATION IN ECG SIGNAL USING DEEP LEARNING
Get PDFAtrial fibrillation is a type of heart rhythm disorder that most often occurs in the world and can cause death. Atrial fibrillation can be diagnosed by reading an Electrocardiograph (ECG) recording, however, an ECG reading takes a long time and requires specialists to analyze the type of signal pattern. The use of deep learning to classify Atrial Fibrillation in ECG signals was chosen because deep learning has 10% higher performance compared to machine learning methods. In this research, an application for classification of Atrial Fibrillation was developed using the 1-Dimentional Convolutional Neural Network (CNN 1D) method. There are 6 configurations of the 1D CNN model that were developed by varying the configuration on the learning rate and batch size. The best model obtained 100% accuracy, 100% precision, 100% recall, and 100% F1 Score
Sign Language A-Z Alphabet Introduction American Sign Language using Support Vector Machine
Get PDFDeafness is a condition where a person's hearing cannot functionnormally. As a result, these conditions affect ongoing interactions,making it difficult to understand and convey information.Communication problems for the deaf are handled through theintroduction of various forms of sign language, one of which isAmerican Sign Language. Computer Vision-based sign languagerecognition often takes a long time to develop, is less accurate, andcannot be done directly or in real-time. As a result, a solution isneeded to overcome this problem. In the system training process,using the Support Vector Machine method to classify data and testingis carried out using the RBF kernel function with C parameters,namely 10, 50, and 100. The results show that the Support VectorMachine method with a C parameter value of 100 has betterperformance. This is evidenced by the increased accuracy of the RBFC=100 kernel, which is 99%
BEST EMPLOYEE ASSESSMENT DECISION SUPPORT SYSTEM USING ANALYTICAL HIERARCHY PROCESS (AHP) AND ADDITIVE RATIO ASSESSMENT (ARAS) METHODS
Get PDFThe purpose of this research is to make it easier to solve the problem of evaluating the best employees in the company PT. ASA KARYA MULTIGUNA, therefore a decision support system is needed. The Analytical Hierarchy Process (AHP) method is used for weighting criteria and the Additive Ratio Assessment (ARAS) method is used for ranking alternatives. From the results of the weighting of the criteria obtained weights for ability (0.31), initiative (0.04), discipline (0.08), performance (0.21), responsibility (0.13), attendance (0.08), communication (0.04), attitude (0.08). From the results of the alternative rankings, for the November 2020 period, the first place was Hendri Gustian, the second was Eka Wingsati Sartono, and the third was Eva Maya Fadila. In the December 2020 period, the first place was Hariyadi, the second was Hendri Gustian, and the third was Deden Kurniawan. In the January 2021 period, the first rank was Deden Kurniawan, the second rank was Hilman Djuniarto, and the third rank was Nurhayati Natalia. From the data for 3 periods from November 2020 to January 2021, which were tested managed to the average confidence level is 84.1%
Prediction of the Number of New Cases of Covid-19 in Indonesia Using Fuzzy Time Series Model Chen
Get PDFCoronavirus Diseases 2019 (Covid-19) is a disease caused by a virus that originated in Wuhan, China. This virus infects people rapidly to the country of Indonesia. According to the latest Covid-19 Development Team in Indonesia, as of 09/08/2021, there were around 3,686,740 people who were confirmed positive for Covid-19. With the numbers continuing to grow, predictions of new cases of Covid-19 in Indonesia were made using the time series method. The method used by the researcher is Chen's Fuzzy Time Series. The purpose of the researcher is to forecast, to find out the prediction of the number of new cases of Covid-19 in Indonesia using the FTS Chen method into software. In addition, in order to provide information to predict, so that the government knows and can make decisions. To measure the performance of the method, the Mean Absolute Percentage Error (MAPE) is used as a measure of the level of accuracy of the forecasting performed. The test data used were 363 data with several variations of parameters & . From the results of the analysis that was tested by the researcher, with 50 trials of parameter input, better accuracy results were obtained at input = 135135 and = 2000 with MAPE is 35.55006797 (35%)
Cat Breeds Classification Using Convolutional Neural Network For Multi-Object Image
Get PDFCat is one of the most popular pets. There are many cat breeds with unique characteristic and treatment for each breed. A cat owner can have more than one cat, either the same breed or different breeds. But not all cat owners know the breeds of their cats. Computers can be trained to recognized cat breeds, but there are many challenges for computers because it limited by how much they have been trained and programmed. In recent years, a lot of research about image classification has been done before and got various result, but most of the data used in previous research were single object images. Therefore, this study of cat breeds classification would be conducted with Convolutional Neural Network (CNN) in the Multi-Object images. This method was chosen because it had good classification results in the previous studies. This study used 5 breeds of cats with every breed having 200-3200 images for training. The test results were measured using confusion matrix, obtaining the precision, recall, f1 score and accuracy of 100% on multi-object images with 2 objects and 3 objects. On images with 4 objects achieved the precision, recall, f1 score and accuracy value of 89%, 87%, 87% and 95%. While the value of precision, recall, f1 score and accuracy on images with 5 objects get 87%, 86%, 86% and 94%, respectively
MEMBER ELECTION DECISION SUPPORT SYSTEM SOUTH SUMATERA PASKIBRAKA USING TOPSIS-PROMETHEE METHOD
Get PDFPaskibraka is the best young generation selected through various selections to raise and lower the Heritage Flag on Indonesian Independence Day. However, in the enthusiasm of the students to take part, the Dispora of South Sumatra Province still uses a manual assessment system so that several obstacles were found in its implementation. done with Microsoft Excel, as well as a calculation system that can only be used for one period, while this selection is an annual event that is held every time to celebrate Indonesian Independence Day. Therefore we need a way that can help the Dispora of South Sumatra Province in determining the best alternative for paskibraka members. One algorithm that is useful in decision support is Topsis. Topsis is used in the application of values for each criterion and a different range of values. Then using the Promethee method can improve the Topsis method because the Promethee method is used to determine the order of priority in multi-criteria analysis. The data taken by 60 participants were then researched according to predetermined criteria including written test scores, interview tests, health tests, physical fitness, and posture. Produced the best participants according to the system as many as 15 data. The results of the research test have an accuracy of 80%
Real Time Detection Of Waste Type Using Single Shot Multibox Detector
Get PDFThe lack of human initiative to manage their own wastes is one of many reasons why waste management in residential area is not optimal. A system to detect waste type in real time is a necessity to support the waste management process to be faster and optimal. This research propose the waste type detection systems using 2 types of Single Shot Multibox Detector models, SSD300 and SSD512. Both models were compared based on the accuracy and speed of detection on TACO dataset dan Waste Classification Data. SSD512 achieves a better accuracy of 0.63 mAP compared to the accuracy of SSD300, which is 0.57 mAP. Both models can also be said to be real time, with the SSD300's detection speed being faster at 51 fps compared to the SSD512's detection speed at 28 fps
Text Similarity Detection Between Documents Using Case Based Reasoning Method with Cosine Similarity Measure (Case Study SIMNG LPPM Universitas Sriwijaya)
Get PDFLPPM Universitas Sriwijaya is an institution that coordinates academic research and community service inside Universitas Sriwijaya. In carrying out the duty, LPPM assesses every proposal’s originality which would be impossible to do manually in the future due to massive data growth. Thus, automatization for the proposal's originality check is needed. The Case Based Reasoning method is used in this research because it allows the system to reuse the information that has been obtained to find documents that are similar to the test document. In this study, the data is represented in the form of the Vector Space Model and uses Cosine Similarity to measure document to document similarity. The data is represented by giving weight for each part of the tested documents. In this study, four formulas from previous research will be used for term weighting then the final result will be compared. The process begins by extracting data, separating parts of the document, figuring the similarity value of the test document to the case base utilizing Cosine Similarity Measure, results filtering with a certain threshold, summarizing the calculation results, and finally preserving the results obtained to be reused in the next calculation. The results of this study indicate that the text-similarity detection between documents has been successfully carried out using the proposed method with the best sensitivity level and the fastest computation time achieved in configuration II