Telematika
Not a member yet
319 research outputs found
Sort by
Implementasi Algoritma Base64 Pada Sistem Antrian Pasien Berbasis Website (Studi Kasus Puskesmas Bangunsari Kec.Dolopo Kab.Madiun
Full text linkBangunsari Health Center in providing services implements various stages of the process that must be passed. Among them is the registration process, where many patients often do not get a queue number because there are restrictions in certain poles every day. In the registration process, patients must submit identities such as Name, NIK, Date of birth, address and telephone number. This data is sensitive information that must be kept confidential, especially since the data is increasing every day. Therefore, to overcome these problems, namely through the development of a website-based patient queuing system by applying an encryption algorithm. With the aim that it will be useful to simplify the queuing process and secure the private data to avoid misuse and data leakage, by going through the data encryption or cryptography process. Cryptography is the science and art of maintaining the confidentiality of messages by encoding them into a form that is no longer understandable in meaning. Data encryption has several algorithms that can be used, one of which is the Base64 algorithm, the Base64 algorithm can be useful in encoding binary data so that it turns into a format that can be printed normally into ASCII format based on the number 64. To ensure that the website-based patient queuing system runs according to the flow that has been made, it is tested using the black box method with the results of the entire system functioning and running according to the source code that has been designed. Meanwhile, the results of implementing base64 run according to the rules that have been tested using the whitebox method and the base64 decode web site, with the results of whitebox and base64 site testing, it is known that the data results are encrypted in the database. So that if there are intruders who enter the database, they cannot read the data that has been encrypted in the form of random text in it
Strawberry Fruit Disease Identification Using Digital Image Processing Using GLCM With Artificial Neural Network Method
Full text linkPurpose: This research aims to identify strawberry fruit diseases using digital image processing using GLCM with the backpropagation artificial neural network method.Design/methodology/approach: Using images that have been preprocessed grayscale, crop, and resize and then processed using GLCM for traning using backpropagation artificial neural networks.Findings/result: Based on 250 image data that is processed by GLCM and classified using a backpropagation artificial neural network, it can be concluded that the best accuracy rate is obtained from ReLU activation with a traning data accuracy value of 95% and test data accuracy of 54%.Originality/value/state of the art: This research uses a combination of primary data with kaggle data by using a comparison of several experiments by changing the loss, optimizer and activation parameters
Classification of Indonesian Tale Categories using Support Vector Machine and FastText Feature Extraction
Full text linkThe purpose of this work is to develop a model to classify the various kinds of Indonesian folktales and to assess how well the support vector machine (SVM) approach and fastText feature extraction perform. The first phase of the study process is the gathering of data, namely the fairy tale dataset that has been annotated with categorizations for each genre of fairy tale. Following the collection of data, the pre-processing step is conducted. The purpose of the pre-processing step is to prepare the data for further processing in the subsequent stage. Following the completion of the preprocessing step, the training data and testing data are segregated. The subsequent step involves doing feature extraction using fastText. Moreover, the classification process is conducted using the Support Vector Machine (SVM) approach in order to get the ultimate outcome of the modeling process. The last phase involves assessing the performance of the constructed model. The categorization model for Indonesian fairy tales has a commendable accuracy rate of 85%, indicating its effectiveness. The aforementioned findings are substantiated by an accuracy metric of 85%, a recall metric of 85%, and an F1-score of 86%, indicating favorable outcomes.Previous researchs have not conducted any studies on the categorization of types of Indonesian fairy tales
Implementation of Histogram Equalization for Image Enhancement in The Classification of Spices Using K-Nearest Neighbor
Full text linkPurpose: To determine the effect of implementing Histogram equalization (HE) at the image preprocessing stage to improve image quality in rhizome spice classification using the K-Nearest Neighbor classification method.Design/Method/Approach: Rhizome spice data was taken directly using a camera with a total of 600 images divided by a ratio of 80:20 for training and testing data. Preprocessing is done starting from resize to 512x512 pixels, then remove background to remove background objects that are not needed, then histogram equalization and also grayscale conversion. Glcm texture feature modeling, rgb color feature and hsv color feature are used as classification parameters. Classification is done using the K-Nearest Neighbor (KNN) method.Findings/result: The test results of this study can be concluded that the application of HE at the image preprocessing stage succeeded in improving classification performance as seen from the accuracy evaluation value. In KNN classification without preprocessing histogram equalization gets an accuracy of 73.8%. When implementing histogram equalization the classification accuracy increases to 76.1%.From the two accuracy results obtained, it can be seen that the implementation of histogram equalization has a good effect in increasing the accuracy of classification.Originality/value/state of the art: The application of Histogram equalization (HE) in image preprocessing is able to improve image quality so that classification accuracy can increase compared to without using histogram equalization preprocessing
Tweets Classification of Mental Health Disorder in Indonesia Using LDA and Cosine Similarity
Full text linkPurpose: Twitter related to mental health has great potential as a medium to provide important information to the public and health organizations on a large scale, but an evaluation of tweet data related to mental health disorders has not been carried out. This study aims to classify tweet data to determine the most common mental health disorders in Indonesia based on the symptoms experienced.Methodology: The classification process is carried out using cosine similarity calculations between tweets data and keywords which are compiled based on theoretical studies and optimization of the LDA topic modeling results.Findings/result:The classification results show that the most discussed issues on Twitter are depression, bipolar, schizophrenia, dementia, and PTSD. Based on these results it can be interpreted that the level of prevalence and public attention to depressive diorders is quite high compared to other disorders. From the results of the classification, it is also possible to identify the most discussed symptoms throughthe emergence of keywords from each category.Originality: Classification is calculated based on the cosine similarity between tweets and keywords compiled from human judgement and enriched using the results of LDA topic modeling to improve classification performanc
RECOGNITION OF HIRAGANA JAPANESE HANDWRITING CHARACTERS USING SUPPORT VECTOR MACHINE AND SCALE INVARIANT FEATURE TRANSFORM
Full text linkThe abundance of characters in Japanese Hiragana, the similarity in character shapes, and the lack of familiarity among the public with Hiragana in daily life make it difficult to learn. People tend to be more accustomed to romanized writing (alphabet) than specific characters, leading to difficulties in understanding Hiragana with its various sizes and shapes. This research aims to develop an effective and systematic Japanese Hiragana handwritten recognition system using Support Vector Machine (SVM) and Scale Invariant Feature Transform (SIFT) methods. The research methodology includes problem identification, literature review, data collection, data preprocessing, system design, implementation, and evaluation. The obtained data undergo augmentation and image preprocessing processes to create a larger variety and amount of data. Furthermore, feature extraction is performed on the data using the SIFT method before training the model using SVM. The research results show that the SVM-SIFT model achieves an accuracy of 0.928261, which is superior to the SVM model without SIFT with an accuracy of 0.389130. The best CV score for the SVM model without SIFT is 0.7746709410609622. Testing proves that the use of SVM SIFT is effective for classifying handwriting that varies in shape and size
Klasifikasi Suara Berdasarkan Range Frekuensi Menggunakan Metode Fast Fourier Transform Untuk Mengetahui Jenis Suara Manusia
Full text linkDalam penelitian ini dirancang sebuah sistem pengelompokan jenis suara seseorang berdasarkan rentang frekuensinya yang berdasar pada rentang frekuensi dominan tuts piano sebagai acuannya. Suara pada setiap manusia memiliki tipe yang berbeda-beda. Terdapat 7 tipe suara manusia yaitu, alto, mezzo-sopran, dan sopran untuk perempuan. Bass, bariton, countertenor, dan tenor untuk laki-laki. Sistem ini diperuntukkan untuk mengelompokkan setiap suara yang berbeda-beda baik laki-laki maupun perempuan agar dapat mengetahui jenis suara setiap individu karena setiap suara atau bunyi yang dikeluarkan pasti memiliki sebuah nada dan jenisnya masing-masing. Permasalahan ini muncul dikarenakan kualitas dan jenis suara setiap orang pasti berbeda-beda tidak lagi hanya berdasarkan tinggi rendah nya saja, melainkan karena setiap suara belum tentu mempunyai jenis suara tetapi setiap suara pasti memiliki frekuensi dari range vokal yang kemudian menghasilkan nada, lalu jika nada ini dipadukan dengan cara yang tepat, maka akan tercipta harmonisasi yang indah. Sistem yang dirancang terdiri dari masukan data awal berupa suara yang bereksistensi dengan format WAV dengan ukuran file tidak lebih dari 200 Mb, kemudian di ekstraksi menggunakan FFT (Fast Fourier Transform) pada software Python dan data suara akan di olah dari domain waktu ke domain frekuensi sehingga menghasilkan grafik dan jenis suaranya. Fast Fourier Transform (FFT) adalah suatu algoritma untuk menghitung transformasi Fourier diskrit (Discrete Fourier Transform, DFT) dengan cepat dan efisien. Transformasi Fourier cepat diterapkan dalam berbagai bidang, mulai dari pengolahan sinyal digital, memecahkan persamaan diferensial parsial, dan untuk algoritma untuk mengalikan bilangan bulat besar. Dalam penelitian ini sistem dapat mengklasifikasikan suara berdasarkan range frekuensi yang sama atau dominan dengan range vokalnya sehingga menghasilkan frekuensi suara, jenis dan nada suara serta grafiknya. Penelitian ini menghasilkan nada tertinggi oleh Titin dengan frekuensi sebesar 1374.523 Hz dan suara terendah dapat diperoleh oleh Ulfa dengan frekuensi 71.242 Hz
Analisis Suhu Permukaan Lahan dan Vegetasi untuk mengukur Urban Heat Island menggunakan Google Earth Engine.
Full text linkBanjarmasin, yang sering disebut sebagai kota seribu sungai, telah mengalami perkembangan perkotaan yang signifikan, yang mengarah pada intensifikasi efek Urban Heat Island (UHI). Studi ini menggunakan kuantitatif dengan analisis berbasis spasial memanfaatkan data satelit Landsat 8, dikombinasikan dengan kemampuan Google Earth Engine, untuk mengkaji interaksi antara Suhu Permukaan Lahan (LST) dan Indeks Vegetasi Ternormalisasi (NDVI) dari tahun 2013 hingga 2023. Pengamatan awal menunjukkan pola LST yang bervariasi, terutama di area sekitar sungai, serta variasi NDVI yang signifikan yang mencerminkan kondisi vegetasi. Analisis mendetail menunjukkan adanya hubungan yang jelas antara tutupan vegetasi dan suhu perkotaan, dengan fluktuasi suhu yang berkorelasi dengan perubahan vegetasi dan aktivitas antropogenik. Khususnya, pandemi COVID-19 global berperan dalam penurunan LST selama 2020-2021, meskipun cakupan vegetasi tetap relatif stabil. Temuan ini menekankan pentingnya perencanaan kota berkelanjutan, dengan penekanan pada pelestarian dan integrasi ruang hijau untuk mengurangi efek UHI dan mempromosikan keseimbangan lingkungan. Penelitian ini memberikan wawasan yang berharga tentang dinamika iklim perkotaan, kesehatan vegetasi, dan strategi pembangunan berkelanjutan untuk kota-kota yang mengalami urbanisasi cepat
Ensembled Voting Techniques for Advanced Breast Cancer Prediction
Full text linkBreast cancer is the most common type of cancer affecting women worldwide, with a significant increase in incidence rates each year. Information and Communication Technology (ICT) has made substantial contributions to the medical field, particularly through the use of Big Data and machine learning algorithms to enhance diagnostic accuracy and healthcare efficiency. This research aims to assess the performance of five breast cancer classification algorithms: Support Vector Machine (SVM), Decision Tree (C4.5), k-Nearest Neighbors (k-NN), Logistic Regression, and Ensembled Voting, using the Breast Cancer Wisconsin (Diagnostic) dataset. The study findings indicate that all models achieved high levels of accuracy, precision, recall, and F1-Score, with Ensembled Voting reaching the highest accuracy of 98.57%. This study confirms that machine learning algorithms, particularly Ensembled Voting, can be relied upon to improve breast cancer diagnosis accuracy, thereby significantly contributing to better healthcare outcomes
Design and Evaluation of Dental and Oral Health Education Using Design Thinking
No full textPurpose: To design a learning for dental and oral health by applying the Design thinking method.Design/method/approach: using the Design thinking method which has several processes such as Empathize, Define, Ideate, Prototype, and Test.Finding/Result: Design as a learning media for dental and oral health that is adapted to what is needed by users.Originality/state of the art: Designing a learning media website using the design thinking method and then evaluating to measure the quality of the system using the System Usability Scale method