JURNAL MEDIA INFORMATIKA BUDIDARMA
Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer science)
Articles
1,182 Documents
<![CDATA[Comparative Analysis of Personality Detection using Random Forest and Multinomial Naive Bayes ]]>
<![CDATA[Azka Zainur Azifa]]>;
<![CDATA[Warih Maharani]]>;
<![CDATA[Prati Hutari Gani]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i1.5592
<![CDATA[Personality is a difference that is owned by each individual in thinking, feeling, and behaving. Personality is an individual characteristic that is formed based on biological parents and environmental influences. Personality type is one of the determinants of the type of work performed. The Big Five personality is a method used to detect personality. This theory divides characteristics into five dimensions, namely Openness, Conscientiousness, Extraversion, Neuroticism, and Agreeableness. Several studies have shown that personality identification can be done through social media, one of which is by using Twitter. Much research related to personality detection has been carried out using machine learning, but only focuses on one machine learning model. In the case of text detection, multinomial naive bayes have a more stable performance than random forest, while random forest has better accuracy than multinomial naive bayes. therefore this study focuses on conducting a comparative analysis using random forest and multinomial naive Bayes. the best accuracy is produced by a system with a random forest model of 60.71% and a precision value of 62% for openness personality and 57% for agreeableness personality.]]>
<![CDATA[Improvement Ranking Accuracy of Weighted Aggregated Sum Product Assessment With Lambda Variable ]]>
<![CDATA[Muhadi M. Ilyas Gultom]]>;
<![CDATA[Erna Budhiarti Nababan]]>;
<![CDATA[Zakarias Situmorang]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i1.5280
<![CDATA[Conventional methods are still used in selecting the best students in the various institutions depending on the subjectivity of each member of the assigned committee. In order to make an objective decision, it is necessary to have a method that can consider the criteria used to select the candidates to be elected. The decision-making method used in this study is Weighted Aggregated Sum Product Assessment(WASPAS). This study aims to analyze the increase in accuracy of the WASPAS method that occurs in the implementation of the lambda variable in the process of combining the Weight Product Method(WPM) and Weight Sum Method(WSM). This method is use because it is suitable for the case studied where the application of this method focuses on weighting criteria with a dynamic number of alternatives and low computational complexity providing good performance in handling large amounts of data.The application of this method uses data from students from Engineering Faculty of Universitas Islam Sumatera Utara which is tested on 10 students with criteria adapted from student data attributes that can be used as parameters for decision making. The results of this study show an increase for each alternative with an average value of 23.6% for each alternative. From this study it can be concluded that accuracy is highly dependent on variations in lambda values which are affected by the determinant operator in the equation used. Therefore it is possible to find an absolute equation to give optimal effect on a single value without variation by considering the bias of the effect of the WASPAS method on the lambda variable in future research.TRANSLATE with x EnglishArabicHebrewPolishBulgarianHindiPortugueseCatalanHmong DawRomanianChinese SimplifiedHungarianRussianChinese TraditionalIndonesianSlovakCzechItalianSlovenianDanishJapaneseSpanishDutchKlingonSwedishEnglishKoreanThaiEstonianLatvianTurkishFinnishLithuanianUkrainianFrenchMalayUrduGermanMalteseVietnameseGreekNorwegianWelshHaitian CreolePersian // TRANSLATE with COPY THE URL BELOW Back EMBED THE SNIPPET BELOW IN YOUR SITE Enable collaborative features and customize widget: Bing Webmaster PortalBack//]]>
<![CDATA[Analisis Optimasi Pada Algoritma Long ShortTerm Memory Untuk Memprediksi Harga Saham ]]>
<![CDATA[Nur Faridah]]>;
<![CDATA[Bambang Sugiantoro]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i1.5421
<![CDATA[Stocks are the most popular financial market instrument at the moment, indicated by an increase in investors' shares of 27.15% from the previous year. The biggest risk for stock investors in investing is the risk of falling prices (capital loss) and the risk of liquidation. To minimize this risk, before investing, you should do an analysis first, one of which is by predicting stock price movements. The best method for predicting stock prices is to use Long Short Term Memory (LSTM). In order to predict optimally, it is important to select an optimization algorithm before creating a model. Of the eight optimization algorithms studied, namely SGD, RMSProp, Adam, AdaGrad, AdaMax, AdaDelta, Nadam, and Ftrl. Adam's optimization has the highest level of accuracy in predicting stock prices, where the accuracy value between predicted stock prices and actual stock prices is 98.88% with the average difference between the predicted price and the actual price of IDR 46. This research is expected to provide benefits in predicting stock prices as accurately as possible using the Long Short Term Memory (LSTM) model with the selection of the right optimization algorithm.]]>
<![CDATA[Aspect-Based Sentiment Analysis on Twitter Using Long Short-Term Memory Method ]]>
<![CDATA[Siti Inayah Putri]]>;
<![CDATA[Erwin Budi Setiawan]]>;
<![CDATA[Yuliant Sibaroni]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.5637
<![CDATA[Twitter is one of the most popular social media among Indonesian people. Due to the high number of users and the intensity of their use, Twitter can also be used to dig up information related to a topic or product with sentiment analysis. One of the most frequently discussed topics on Twitter is related to movie reviews. Everyone's opinion of movie reviews can refer to different aspects. So, aspect-based sentiment analysis can be applied to movie reviews to get more optimal results. Aspect-based sentiment analysis is a solution to find out the opinions of Twitter users on movie reviews based on the aspects. In this study, a system for aspect-based sentiment analysis was built with a dataset of Indonesian language movie reviews consisting of 3 aspects: plot, acting, and director. The classification model uses Long Short-Term Memory (LSTM) method with the application of TF-IDF feature extraction, fastText feature expansion, and handling of imbalanced data using SMOTE. The results of this study for the plot aspect obtained an accuracy score of 74.86% and F1-score of 74.74%, the acting aspect obtained an accuracy score of 94.80% and F1-score of 94.74%, and the director aspect obtained an accuracy score of 94.02% and F1-score of 93.89%.]]>
<![CDATA[Implementasi Metode Convolutional Neural Network Untuk Identifikasi Citra Digital Daun ]]>
<![CDATA[Asmaul Husnah Nasrullah]]>;
<![CDATA[Haditsah Annur]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.5962
<![CDATA[Convolutional Neural Network (CNN) is a deep learning algorithm that is widely used to identify and classify a digital image object. In this study the Convolutional Neural Network (CNN) is used as an algorithm that functions to identify leaf types (certain plants) based on images obtained from a public dataset provider named Daun Jamu Indonesia. The existence of image characteristics causes the assistance process to require a more detailed feature selection process. Therefore the CNN method is used in order to solve the problem. The Convolutional Neural Network (CNN) method is capable of performing image recognition by minimizing feature extraction. CNN is also reliable in processing unstructured data because it uses a multi-layered structure of artificial reasoning networks. The image recognition process is carried out by looking for the shape of the model that matches the processed data in order to get the best results. In this study, the augmentation process was carried out on the training data and validation data so that overfitting does not occur in the Convolutional Neural Network (CNN). The results obtained in this study indicate that the Convolutional Neural Network (CNN) method can identify leaf types with a measured accuracy rate of 92% using the Confusion Matrix evaluation method. It is hoped that this research can be used as a reference for the use of the Convolutional Neural Network (CNN) method for image data, especially plant leaf types.]]>
<![CDATA[Data Mining Penentuan Jurusan Siswa Menggunakan Metode Agglomerative Hierarchical Clustering (AHC ]]>
<![CDATA[Rima Tamara Aldisa]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.6092
<![CDATA[There are various students who experience problems during the learning process because the chosen major does not match their abilities because choosing a major is only influenced by other people so that it is not in accordance with their abilities and a teacher is also difficult to adjust the abilities of one student to other students. In order for these students to be grouped with students who have the same level of knowledge, a grouping is carried out using data mining techniques in order to obtain new information in a database that has a large size or large amount of data to make it easier for users to obtain this information. The method used is AHC which is utilized as clustering with the single linkage method, the single link method is considered more effective than other methods because the problem is very suitable where the grouping process is carried out based on each criterion of the distance between all alternatives. The criteria used were three criteria (Science Score, IPS Score, TPA Score) with a total of 121 students. The application of the AHC method is carried out by utilizing rapidminer so that the results obtained are more efficient and effective. The results that can be used by the school are cluster 0 totaling 93 students, cluster 1 totaling 10 students, cluster 2 totaling 10 students and cluster 3 totaling 8 students.]]>
<![CDATA[Penerapan Aplikasi Sistem Pakar Untuk Mendiagnosa Penyakit Kucing Berbasis Web Menggunakan Metode Forward Chaining Dan Certainty Factor ]]>
<![CDATA[Febrina Shanti Nurrachma]]>;
<![CDATA[Nuril Lutvi Azizah]]>;
<![CDATA[Metatia Intan Mauliana]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.6029
<![CDATA[Cats are animals that are loved and admired by the public because of their beautiful physical shape and adorable behavior. But most cat keepers do not know how to treat and do not know the disease experienced by their pets just by looking at the symptoms of the disease that occurs in cats. So many cat owners are not aware if their cat has a disease and is late in providing treatment. From these problems, an expert system is needed that can help in solving problems, an expert system application that adopts artificial intelligence in the field of veterinary medicine that can diagnose diseases in cats. The purpose of this research is to build an expert system that is useful as a tool for diagnosing diseases in cats based on the web using forward chaining and certainty factor methods. This system is built using PHP and MySQL programming languages and based on the results of system functional testing using black box testing which states that the system is running well and all components produce the expected results and are able to assist users in diagnosing cat diseases, the results of disease diagnosis and the confidence value is in accordance between manual calculations and calculations on the system by bringing up the results of certainty value calculations factor in each possible disease detected on the website. From the day of diagnostic testing, it was concluded that 33% of cats were diagnosed with feline calciirus, 33% of cats were diagnosed with feline panleuopenia, 40% of cats were diagnosed with feline rhinotracheitis, 37% of cats were diagnosed with helmathiasis, 80% of cats were diagnosed with otitis, 36% of cats were diagnosed with ringworm, 68% of cats were diagnosed with scabies.]]>
<![CDATA[Penerapaan Metode TOPSIS dengan Pembobotan ROC dalam Seleksi Penerimaan Auditor Internal Perusahaan ]]>
<![CDATA[Rima Tamara Aldisa]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.5899
<![CDATA[Cheating or fraud is a major problem that must continue to be routinely monitored at the company. Fraud is a form of fraud that is carried out intentionally by hiding a truth or fact so that it can incite other people to commit acts that are detrimental to the company. In preventing fraud at the company, routine audit activities must be carried out at the company with a fast and precise time. For the company's operational system to be better, the audit activity is carried out by an internal auditor. Internal auditors are someone who works in activities with confidence with the aim of being able to advance values and improve company operations in an objective and independent manner. In the selection of candidates for internal auditors, there are several criteria as an internal auditor that have been determined by the company, namely General Knowledge, Skills, Expertise Certificates, Personal Qualities, Traits and Education. Currently the company does not have a system that can carry out the selection of appropriate and objective internal auditor candidates. The selection of internal auditors is carried out objectively, so the authors use a decision support system (SPK). SPK is an information system that functions as an aid in decision making within an organization. This system is useful in solving problems encountered through the use of predetermined methods. In this study, the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method and the ROC (Rank Order Centroid) method were used to obtain the data needed in the selection of internal auditor candidates to get Ratih Budi with a score of 1.0000 in alternative A6 as an internal auditor. on the company.]]>
<![CDATA[Implementasi Metode Preference Selection Index (PSI) dalam Seleksi Penerimaan Content Creator Media Sosial ]]>
<![CDATA[Usanto S]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.5936
<![CDATA[Currently social media in the world of work has an important role and can also be a place of business competition. Social media is now being used as an easier and more efficient promotional platform designed to capture the attention of the audience so as to expand the target market for higher profits. Content creators have an important role for business actors, content creators are responsible for social media owned by business actors. The selection process for accepting content creators is still carried out conventionally so that the selection process is sometimes not appropriate in accepting the best content creators. So with that, business actors must choose quality content creators so that their social media continues to be active and get a wider target audience. In selecting content creators, several criteria have been determined, namely skills, work experience, number of followers, interviews and education. Because of these problems, a system is needed that can assist in obtaining reliable and targeted recommendations. The application of a decision support system in this study was used by implementing the PSI (Preference Selection Index) method in which this method is very helpful in producing the best weight and preference values from alternative data and criteria so that the final result is the recommendation for the best content creator in Medan city in the Alternative A3 is Andriana with a value of 0.9236.]]>
<![CDATA[Sistem Pakar Diagnosa Penyakit Guillain-Barre Syndrome dengan Menerapkan Algoritma Teorema Bayes ]]>
<![CDATA[Ita Arfyanti]]>;
<![CDATA[Muhammad Fahmi]]>
<![CDATA[ JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 2 (2023): April 2023 ]]>
Publisher : <![CDATA[Universitas Budi Darma ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.30865/mib.v7i2.6065
<![CDATA[One of the diseases of the peripheral nervous system is Guillain-Barre Syndrome, this disease usually affects adults aged 30 years and over but does not rule out the possibility of attacking at various ages. This disease usually occurs in someone who has a deficiency of vitamins including B1, B6, B12 and among those who are addicted to alcohol, exposed to poisons and do too many repetitive movements. There are various kinds of symptoms that mark a patient with Guillain-Barre Syndrome including muscle pain, tingling, difficulty swallowing, difficulty breathing, loss of response to motor movements, increased pulse, indigestion, excessive sweating, unstable blood pressure. Then a study was carried out that utilized an expert system with the Bayes theorem algorithm. This system can make it easier for an expert to diagnose the patient's disease easily and more efficiently with the advantage of not having to meet directly between the patient and the doctor. Based on these problems, the researcher applied the algorithm above to produce a diagnosis with a percentage of the possibility that the patient suffered from this disease based on existing symptom data of 77.2%.]]>
