IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
Not a member yet
480 research outputs found
Sort by
Effect of Sentence Length in Sentiment Analysis Using Support Vector Machine and Convolutional Neural Network Method
Get PDFBased on Article 10 paragraph 1 of Law No. 14 of 2005, a teacher must have four competencies: pedagogical, personality, social, and professional. ICT training at Sunan Kalijaga State Islamic University involves instructors as educators who must have such competencies. An instructor's performance is assessed through students' learning evaluation system by giving comments to the instructions. These comments contain positive and negative sentiments that can be reviewed by conducting sentiment analysis. Research related to sentiment analysis in recent years has been widely done, but researchers rarely pay attention to the effect of sentence length from the dataset on the method's performance. This study tried to analyze sentiment related to sentence length effect on ICT training student comments using Support Vector Machine and Convolutional Neural Network methods. This study concluded that the sentence length on the dataset would affect the SVM and CNN methods' performance when combined with Word2vec. While the SVM+TFIDF method performance is not affected by sentence length, this method has the fastest process time than other methods. The CNN+Word2vec method produced the best performance in this study with a value of 0.94% accuracy, 0.95% precision, 0.96% recall, and 0.95% f1-score
Steganographic Model for encrypted messages based on DNA Encoding
Get PDFInformation has become an inseparable part of human life. Some information that is considered important, such as state or company documents, require more security to ensure its confidentiality. One way of securing information is by hiding the information in certain media using steganography techniques. Steganography is a method of hiding information into other files to make it invisible. One of the most frequently used steganographic methods is Least Significant Bit (LSB).In this study, the LSB method will be modified using DNA Encoding and Chargaff's Rule. Chargaff's Rule or complementary base pairing rule is used to construct a complementary strand. The modification of the LSB method using DNA encoding and Chargaff's Rule is expected to increase the security of the information.The MSE test results show the average value of the LSB method is 0.000236368, while the average value for the DNA Encoding-based Steganography method is 0.000770917. The average PSNR value for the LSB method was 76.82 dB while the DNA Encoding-based Steganography method had an average value of 70.88 dB. The time of inserting and extracting messages using the Steganography method based on DNA Encoding is relatively longer than the LSB method because of its higher algorithmic complexity. The message security of the DNA Encoding-based Steganography method is better because there is encryption in the algorithm compared to the LSB method which does not have encryption
Analysis of classic assumption test and multiple linear regression coefficient test for employee structural office recommendation
Get PDFThe performance appraisal process in Religious High Court Bandar Lampung has not been carried out objectively, but rather a subjectivity element (relationship closeness). Some employees occupy structural positions but do not fulfil competence and promotion principles, so that it has an impact on providing promotion to a position in the judiciary. Multiple Linear Regression method can provide a predictive model for employee recommendations entitled to occupy positions in the agency. The method implementation using SPSS produces an equation Y = 74.177 + 0.035X1 + 0.020X2 - 0.026X3 + 0.045X4 + 0.001X5. This equation is applied to the employee performance values, and it is obtained from 40 employees 26 employees deserve to be given recommendations promotion. Regression performance testing results using 10-cross validation get the correlation coefficient value is 80.66% with MAE value of 2.24% and RMSE 3.88%, which mean has good performance
Aspect-Based Sentiment Analysis on Indonesian Restaurant Review Using a Combination of Convolutional Neural Network and Contextualized Word Embedding
Get PDFSomeone's opinion on a product or service that is poured through a review is something that is quite important for the owner or potential customer. However, the large number of reviews makes it difficult for them to analyze the information contained in the reviews. Aspect-based sentiment analysis is the process of determining the sentiment polarity of a sentence based on predetermined aspects.This study aims to analyze an Indonesian restaurant review using a combination of Convolutional Neural Network and Contextualized Word Embedding models. Then it will be compared with a combination of Convolutional Neural Network and Traditional Word Embedding models. The result of aspect-classification on three models; BERT-CNN, ELMo-CNN, and Word2vec-CNN give the best results on the ELMo-CNN model with micro-average precision of 0.88, micro-average recall of 0.84, and micro-average f1-score of 0.86. Meanwhile, the sentiment-classification gives the best results on the BERT-CNN model with a precision value of 0.89, a recall of 0.89, and an f1-score of 0.91. Classification using data without stemming have almost similar results, even better than using data with stemming
DSS for Keyboard Mechanical Selection Using AHP and Profile Matching Method
Get PDFMechanical keyboards are designed with various shapes, variations, and specifications that are different from other types of keyboards. The mechanical keyboard itself has an aesthetic function that allows users to customize it. There are various specifications on mechanical keyboards, causing various considerations, which can make it difficult for users to choose a mechanical keyboard that fits the desired criteria. Supported by observations in the Indonesia Mechanical Keyboard Group (IMKG), some users are still limited in their knowledge of mechanical keyboard products available in Indonesia, also, currently there is no solution that can handle this problem.Based on these problems, in this research, an DSS is built that can help overcome these problems, by providing recommendations for a mechanical keyboard according to the wishes of the user. DSS is implemented in web form using the AHP method for the weighting process and Profile Matching for the scoring process. The criteria used are determined by conducting a survey regarding the specifications that are the priority considerations in choosing a mechanical keyboard.At the end of the study, the DSS that was successfully built was able to provide mechanical keyboard priority recommendations according to user preferences and get an average evaluation result of 36.17 out of a total maximum value of 40
Reccomendations on Selecting The Topic of Student Thesis Concentration using Case Based Reasoning
Get PDFCase Based Reasoning (CBR) is a method that aims to resolve a new case by adapting the solutions contained in previous cases that are similar to the new case. The system built in this study is the CBR system to make recommendations on the topic of student thesis concentration. This study used data from undergraduate students of Informatics Engineering IST AKPRIND Yogyakarta with a total of 115 data consisting of 80 training data and 35 test data. This study aims to design and build a Case Based Reasoning system using the Nearest Neighbor and Manhattan Distance Similarity Methods, and to compare the results of the accuracy value using the Nearest Neighbor Similarity and Manhattan Distance Similarity methods. The recommendation process is carried out by calculating the value of closeness or similarity between new cases and old cases stored on a case basis using the Nearest Neighbor Method and Manhattan Distance. The features used in this study consisted of GPA and course grades. The case taken is the case with the highest similarity value. If a case doesnt get a topic recommendation or is less than the trashold value of 0.8, a case revision will be carried out by an expert. Successfully revised cases are stored in the system to be made new knowledge. The test results using the Nearest Neighbor Method get an accuracy value of 97.14% and Manhattan Distance Method 94.29%
CPU and eGPU Support System Based on Naive Bayes Classification
Get PDFCentral Processing Unit (CPU) and External Graphics Processing Unit (eGPU) technology are known as overclocks which aim to make the device exceed the benchmarks set by the device maker. Until now there is no determination to rank the two hardware within certain limits such as hardware price range and year-by-year. Therefore, it is necessary to process the ranking of the hardware using Simple Additive Weighting (SAW) to obtain a ranking range and determine the weight per type of hardware analyzed. It can be classified using Naïve Bayes to determine results of criteria combination between two hardware to determine possible criteria into "not good" and "good". This classification used to determine probability criteria of choosing a combination of CPU and eGPU hardware. The results of this study are getting the best CPU and eGPU every year using SAW and then classifying it for pricing. In testing conducted on application of Naïve Bayes using 80% of training data has 2776 data and 20% of testing data has 695 data that will be tested for accuracy, precision, recall, and F1-score. For results of tests that have been carried out get 0.78 accuracy results, precision 1, Recall 0.764, and F1-Score 0.866
Author Obfuscation on Indonesian News Articles Using Genetic Algorithms
Get PDFAuthorship attribution is a method for identifying the author of a text from a group of potential authors and can solve the anonymity of unknown authors. Such method threatens anyone’s privacy, especially those who wish to write anonymously. To address this issue, author obfuscation is proposed to modify a text to disguise its author.In this research, a genetic algorithm-based author obfuscation model was created to modify Indonesian news articles to avoid identification from authorship attribution while keeping its semantics. The model iteratively changed some words in the article using crossover and mutation techniques guided by a fitness function which involve identification probability and similarity to the original article.The model is evaluated based on safety, soundness, and sensibleness parameter. The model has good safety since it can reduce the given authorship attribution model's accuracy by 0.3018 but drops to 0.1179 when tested on different models. Its soundness is pretty good since the similarity of the modified to the original articles reaches 0.7817. The model obtained a score of 2.571 on a scale of 0 to 4 in terms of sensibleness which indicates that some articles are acceptable in terms of grammar, but not a few are messy
Comparison of Filter and Wrapper Based Feature Selection Methods on Spam Comment Classification
Get PDFThe continuous growth of the internet has led to the use of social media for various purposes increase. For instance, some irresponsible parties take advantage of the comment feature on social media platforms to harm others by providing spam comments on the shared object. Furthermore, variation of comments creates many features to be processed, thereby negatively impacting the performance of a classification algorithm. Therefore, this study aims to solve the problem associated with spam comments by comparing filter and wrapper based feature selection using text classification techniques. Data collected from training and test data of 4944 and 100 comments showed that the best accuracy, precision, recall, and f-measure of MNB are 96%, 100%, 92%, and 95.8%. The best accuracy is achieved using feature selection by combining Chi-Square and Sequential Forward Selection methods with a subset of 500 features. Furthermore, the accuracy increase in the MNB and SVM classifications are 8% and 4%. This research concludes that the combination of feature selection improves the classification performance of Indonesian language spam comments
Anomaly Detection in Hospital Claims Using K-Means and Linear Regression
Get PDF BPJS Kesehatan, which has been in existence for almost a decade, is still experiencing a deficit in the process of guaranteeing participants. One of the factors that causes this is a discrepancy in the claim process which tends to harm BPJS Kesehatan. For example, by increasing the diagnostic coding so that the claim becomes bigger, making double claims or even recording false claims. These actions are based on government regulations is including fraud. Fraud can be detected by looking at the anomalies that appear in the claim data.This research aims to determine the anomaly of hospital claim to BPJS Kesehatan. The data used is BPJS claim data for 2015-2016. While the algorithm used is a combination of K-Means algorithm and Linear Regression. For optimal clustering results, density canopy algorithm was used to determine the initial centroid.Evaluation using silhouete index resulted in value of 0.82 with number of clusters 5 and RMSE value from simple linear regression modeling of 0.49 for billing costs and 0.97 for length of stay. Based on that, there are 435 anomaly points out of 10,000 data or 4.35%. It is hoped that with the identification of these, more effective follow-up can be carried out