Articles
<![CDATA[Identifikasi Tanda Tangan menggunakan Metode Fitur Ekstrasi Biner dan K Nearest Neighbor ]]>
<![CDATA[Simanjuntak, Mutiara Sarahwaty]]>;
<![CDATA[Rosnelly, Rika]]>;
<![CDATA[Wanayumini, Wanayumini]]>
<![CDATA[ CSRID (Computer Science Research and Its Development Journal) Vol 12, No 3 (2020): CSRID OKTOBER 2020 ]]>
Publisher : <![CDATA[Universitas Potensi Utama ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.22303/csrid.12.3.2020.191-200
<![CDATA[Tanda tangan mempunya pola yang unik berdasarkan fitur yang ditinjau. Penelitian ini mengindentifikasi tanda tangan secara otomatis dengan menggunakan fitur biner dari hasil tanda tangan scanner. Identifikasi tanda tangan penting dilakukan otentifikasi dokumen administrasi dan resmi dimana nilai akurasi hal yang diperlukan. Dalam pendekatan yang dilakukan, fitur tanda tangan diekstrak dengan menggunakan dua descriptor yaitu binary statistical image features (BSIF) dan local binary patterns (LBP). Penilaian menggunakan metode ini dengan melakukan percobaan dengan dua dataset yang sudah tersedia untuk umum yaitu database MCYT-75 dan GPDS-100. Dengan menggunakan metode klasifikasi KNN, mendapatkan nilai tertinggi masing-masing 96,7% dan 93,9%. Dalam verifikasi identifikasi tanda tangan akurasi klasifikasi diukur berdasarkan equal error rate (EER)yaitu 4.2% dan 5.33% pada GPDS-200 dan GPSD-150. Sehingga EER untuk database MCYT-75 sudah mencapau 7,78%. Nilai akurasi tersebut sudah dapat diketegorikan unggul.]]>
<![CDATA[APLIKASI PENCARIAN GAMBAR DENGANALGORITMA CONTENT-BASED IMAGE RETRIEVAL ]]>
<![CDATA[Mutiara S. Simanjuntak]]>;
<![CDATA[Allwine Allwine]]>;
<![CDATA[Rico Wijaya]]>
<![CDATA[ Jurnal Mantik Penusa Vol. 3 No. 3 (19): COmputer Science ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (311.284 KB)
<![CDATA[Image retrieval system is a method used to extract image features and provides rules for comparing two images based on these characteristics. Several methods that can be used are Image Meta Search and Content-Based Image Retrieval (CBIR) methods. CBIR is an image search based on information contained in the image, for example searching for duck images, then entering the characteristics of the duck image and then based on these characteristics look for another image with similar features. Characteristics commonly used to help search for images include color, shape and texture features. In the design of this image retrieval application program, the characteristic used is the color feature. One method that can be used to calculate image characteristics is the Color Histogram Peaks Indexing. This method will compare the image to be searched (query image) with the database image (image stored in the database) to produce color features that will be used as feature vectors for query images and database images. The Color Histogram Peaks Indexing method is a new method designed to overcome the problem of scaling changes in image search. Based on the test results, it is known that the conversion process from HSV image to RGB image requires a long calculation process because it has to do repetition for each pixel, the scale difference of an image will not greatly affect the location of the peak on the HSV Histogram image and image retrieval algorithm can be used to perform Image search process based on the color characteristics of the image.]]>
<![CDATA[SISTEM PAKAR MENDETEKSI TINGKAT RESIKO PENYAKIT MELALUI GEJALA DAN POLA HIDUP MENGGUNAKAN METODE FUZZY MAMDANI ]]>
<![CDATA[Allwine Allwine]]>;
<![CDATA[Mutiara S. Simanjuntak]]>;
<![CDATA[Rico Wijaya]]>
<![CDATA[ Jurnal Mantik Penusa Vol. 3 No. 3 (19): COmputer Science ]]>
Publisher : <![CDATA[Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Currently the expert system is growing rapidly moving along with the development of computer technology which is getting more and more advanced from day to day. Humans always try to make it easier to solve every problem faced. One application to solve every problem is an expert system for a healthy lifestyle.The importance of health for everyone in order to be able to empower everything that they have and their environment to the fullest, health is very closely related to healthy living. So that the definition of healthy living can be elaborated by having health in life with no problems with disruption in life both physical in the form of illness in the body and non-physical related to the condition of one's soul, heart and mind in life both individually and socially. The making of this expert system is carried out in the following stages: designing a healthy living program on eating rules, so as to create an expert system design with a tracking model with the Fuzzy Logic method. The making of this expert system uses the Microsoft Visual Basic 2008 programming language.]]>
<![CDATA[The Activity Activation Function Of Multilayer Perceptron - Based Cardiac Abnormalities: The Activity Activation Function Of Multilayer Perceptron - Based Cardiac Abnormalities ]]>
<![CDATA[Mutiara S. Simanjuntak]]>;
<![CDATA[Wanayumini Wanayumini]]>;
<![CDATA[Rika Rosnelly]]>;
<![CDATA[Teddy Surya Gunawan]]>
<![CDATA[ Jurnal Mantik Vol. 4 No. 1 (2020): May: Manajemen, Teknologi Informatika dan Komunikasi (Mantik) ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1206.55 KB)
<![CDATA[Cardiac disorders refer to irregular activity at the heart. Cardiac abnormalities sometimes do not exhibit any and unreasonable symptoms that can lead to sudden death due to heart-cracking functions. This article is to develop a program capable to detect cardiac abnormalities activity through the application of Multilayer Perceptron (MLP). A certain number of heart rate signal data from an electrocardiogram (EKG) will be used in this paper to train and to test the network performance of the MLP. MLP is trained by several techniques that Backpropagation (BP), Bayesian regularity (BR), and Levenberg-Marquardt (LM).]]>
<![CDATA[Using Preprocessing Text Mining With Nazief-Adriani Algorithms Similarity Of Essay Final Exam Semester ]]>
<![CDATA[MUTIARA SIMANJUNTAK]]>;
<![CDATA[Joel Panjaitan]]>;
<![CDATA[Syofyan Anwar Syahputra]]>
<![CDATA[ Jurnal Mantik Vol. 5 No. 3 (2021): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik) ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[The test is one way to measure the level of student ability in participating in learning. One type of exam given to students is the type of essay exam. This research focuses on making automatic grading for essay-type tests using cosine similarity. This method has several stages such as tokenizing, filtering, stemming, analyzing, weighing words in documents with cosine similarity. The stemming process uses the Nazief & Adriani algorithm. The results of this study are concluded that the selection of words that are considered as keywords in the answer key greatly affects the results of the assessment of the system. This is evidenced by testing applying the cosine law of 89.5%. However, there are several types of questions that are significantly different because there are unique characters in the database and answer keys that do not contain keywords that match the correct answer.]]>
<![CDATA[Performance Analysis Of Support Vector Machine In Identifying Comments And Ratings On E-Commerce ]]>
<![CDATA[Mutiara S. Simanjuntak]]>;
<![CDATA[Nurafni Damanik]]>;
<![CDATA[Allwine]]>
<![CDATA[ International Journal of Basic and Applied Science Vol. 11 No. 1 (2022): June: Basic and Applied Science ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35335/ijobas.v11i1.79
<![CDATA[Consumers who have shopped at E-Commerce will provide reviews/comments on products that have been purchased. Customer confidence in the rating is hampered due to inconsistency of answers such as reviews that have negative text with a positive rating value. For this reason, a technique is needed to adjust the rating with comments or reviews of purchased goods to make it easier for consumers when shopping to see the rating directly without reading the reviews/comments of previous buyers. purpose of this study is to classify comments and ratings and then obtain the results of the accuracy of the classification system so that the above problems can be answered.This study uses Support Vector Machine classification technique because this algorithm is better in classification’s terms. Data used are 1044 comment data and 1044 rating. Data are grouped into Good, Neutral, Less good categories using Python by Google Colab and divided into training and test data. To test capability of system, data that has been classified then analyzed using Confusion matrix. Results showed that SVM Algorithm was able to classify with an accuracy rate of 71.14%, 88% precision, and 79% recall.SVM algorithm is able to formulate training data with an accuracy of 91.3%.]]>
<![CDATA[Pelatihan Kewirausahaan bagi Pemuda & Remaja Gereja Pantekosta di Indonesia (GPdI) Jemaat Maranatha Desa Matiti Kecamatan Doloksanggul ]]>
<![CDATA[Joel Panjaitan]]>;
<![CDATA[Arnold Pakpahan]]>;
<![CDATA[Regina Sirait]]>;
<![CDATA[Pieter Leuvanggi Hutagalung]]>;
<![CDATA[Syofyan Anwarsyah Putra]]>;
<![CDATA[Mutiara S Simanjuntak]]>
<![CDATA[ KARYA UNGGUL - Jurnal Pengabdian Kepada Masyarakat Vol. 1 No. 2 (2022): Edisi Juni ]]>
Publisher : <![CDATA[KARYA UNGGUL - Jurnal Pengabdian Kepada Masyarakat ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
<![CDATA[Tujuan pelatihan ini adalah untuk memotivasi dan mengembangkan wawasan berpikir Pemuda dan Remaja di GPdI Jemaat Maranatha Desa Matiti tentang berwirausaha. Adapun kegiatan yang dilaksanakan adalah memberikan pelatihan tentang kewirausahaan, cara memulai usaha dan bagaimana mengembangkan usaha. Dari hasil kegiatan pengabdian ini diketahui bahwa tingkat pemahaman peserta semakin meningkat. Hal ini dilihat dari hasil kusioner yang diberikan sebelum dan sesudah kegiatan dilaksanakan. Berdasarkan hasil kuisioner diperoleh bahwa pemahaman peserta tentang Kewirausahaan mengalami peningkatan. Sebelum mengikuti kegiatan pelatihan nilai rata-rata adalah 50, namun setelah mengikuti kegiatan nilai rata-rata menjadi 85, maka persentase peningkatan sebesar 70%. Kegiatan ini memberikan dampak positif bagi seluruh peserta dan termotivasi untuk terjun ke di dunia usaha. Pemahaman peserta tentang perencanaan & memulai usaha juga mengalami peningkatan. Sebelum mengikuti kegiatan penyuluhan dan pelatihan nilai rata-rata adalah 60, namun setelah mengikuti kegiatan nilai rata-rata menjadi 80, maka persentase peningkatan sebesar 33,3%. Pemahaman peserta tentang mempertahankan dan mengembangkan usaha juga mengalami peningkatan. Sebelum mengikuti kegiatan penyuluhan dan pelatihan nilai rata-rata adalah 60, namun setelah mengikuti kegiatan nilai rata-rata menjadi 85, maka persentase peningkatan sebesar 41,6%. Setelah pelaksanaan pelatihan dilakukan, terlihat peningkatan pengetahuan para peserta secara signifikan. Para peserta juga sangat antusias untuk mengikuti kegiatan ini. Hal ini dilihat dari banyaknya pertanyaan yang disampaikan oleh peserta kepada pemateri.]]>
<![CDATA[Epoch in a neural network for brain stroke ]]>
<![CDATA[Mutiara Simanjuntak]]>;
<![CDATA[Juanto Simangunsong]]>;
<![CDATA[Hongjie Dai]]>
<![CDATA[ International Journal of Basic and Applied Science Vol. 11 No. 4 (2023): March: Basic and Applied Science ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35335/ijobas.v11i4.156
<![CDATA[A neural network is a data processing system consisting of a large number of simple and highly interconnected processing elements in an architecture inspired by the structure of the cortical regions of the brain. Therefore, neural networks can often do things that humans or animals can do, but traditional computers are often lousy. This research discusses brain tumors that can be detected by artificial intelligence. Stroke includes the sudden death of brain cells due to lack of oxygen, blockage of the circulatory system, or severance of flexible pathways to the brain. Therefore the need for action that must be faster to be able to detect this deadly disease. The method used is a Neural Network which can collect knowledge by detecting patterns and relationships between data and learning experiences. So that the detection process is carried out more quickly and the patient can be given medical action as soon as possible. In the study I conducted brain stroke from the number of strokes with a value of 0 4733 and 1 out of 248. This research has a test conducted by conducting epoch training from 1 to 300, the highest score accuracy is in epoch 1 and 2 with more high scores.]]>
<![CDATA[Etika Dan Tanggung Jawab Digital Bagi Siswa/I SMP Negeri 2 Sihotang Kabupaten Samosir ]]>
<![CDATA[Mutiara S. Simanjuntak]]>;
<![CDATA[Juanto Simangunsong]]>;
<![CDATA[Aprima Matondang]]>
<![CDATA[ Transformasi Masyarakat : Jurnal Inovasi Sosial dan Pengabdian Vol. 1 No. 1 (2024): Januari: Transformasi Masyarakat : Jurnal Inovasi Sosial dan Pengabdian ]]>
Publisher : <![CDATA[Lembaga Pengembangan Kinerja Dosen ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.62383/transformasi.v1i1.79
<![CDATA[SMP Negeri 2 Sihotang is located in Samosir Regency, which is one of the koban schools for flash floods that occur at the end of 2023. This PKM aims to increase awareness of ethics and digital responsibility among junior high school students. With the widespread use of digital technology, especially among teenagers, it is important to introduce the concept of ethics and responsibility in its use. This PKM will adopt an educative approach that involves students directly in the understanding of digital ethics and its impact on individuals and society. The method used with the Socialization method, as well as the creation of multimedia-based educational materials. The main target of this PKM is students of SMP Negeri 2 Sihotang in Samosir Regency. Through an approach that focuses on student participation, it is expected to create a better understanding of the importance of acting responsibly in a digital environment. The expected outcome of this PKM is an increase in students' awareness of ethical and responsible practices in the use of digital technology, as well as their ability to take wise decisions in online situations. Thus, this PKM is expected to make a positive contribution to the formation of good digital character and behavior among students of SMP Negeri 2 Sihotang and the wider community.]]>
<![CDATA[Mental disorder classification with exploratory data analysis (EDA) ]]>
<![CDATA[Juanto Simangunsong]]>;
<![CDATA[Mutiara S Simanjuntak]]>;
<![CDATA[Nurmala Dewi Simanjuntak]]>
<![CDATA[ Journal of Intelligent Decision Support System (IDSS) Vol 7 No 3 (2024): Intelligent Decision Support System (IDSS) ]]>
Publisher : <![CDATA[Institute of Computer Science (IOCS) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35335/idss.v7i3.252
<![CDATA[Classification of mental disorders is the process of grouping mental disorders into categories based on their symptoms, causes and consequences. EDA is a data analysis strategy that emphasizes open-mindedness, creativity and diverse perspectives. EDA aims to explore as much data as possible, without imposing previous assumptions or models, until a coherent, coherent story emerges. EDA can help generate new hypotheses, identify patterns and outliers, and uncover underlying structures and relationships in data. This paper shows how EDA can be used to analyze and understand mental disorders data from a variety of sources and perspectives. We used EDA methods to explore the characteristics, prevalence, and distribution of mental disorders, as well as the relationships and interactions between mental disorders and other variables. We also compared EDA results with mental disorder classification systems such as the Diagnostic and Statistical Manual of Mental Disorders (DSM). We show that EDA can provide a more comprehensive and nuanced understanding of mental disorder data, as well as highlight the challenges and limitations of mental disorder classification. We hope this paper will illustrate the potential and benefits of EDA for mental disorders research and practice]]>
