InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan
Not a member yet
304 research outputs found
Sort by
STARTUP E-COMPLAINT DENGAN INTEGRASI API UNTUK AKSES TANPA UNDUH PADA ONLINE SHOP
Full text linkThe development of the times that demands everything to be more efficient and effective has prompted various companies to develop their online systems. Along with global trends, online shopping in Indonesia is also becoming more popular. Customer satisfaction in online shopping is a determining factor in their decision to make a repeat purchase. Dissatisfaction can increase customer turnover and the cost of acquiring new customers. A common problem faced by businesses is the quality of customer service, especially in handling complaints manually which is no longer relevant in the midst of technological developments. This research aims to create an online customer complaint system that facilitates the handling of complaints efficiently, and simplifies the administration of reports and documentation. The system uses API technology to ensure an effective interface for admins and customers. The Waterfall method is used in the development of this application to minimize bugs and detect errors. The results of the study show that a web-based complaint application that is connected to a mobile application in real-time can provide ease of access and increase customer trust in online shop services
Early Detection of Diabetes Using a Machine Learning Model Based on Laboratory Data
Full text linkDiabetes mellitus is a chronic disease whose prevalence continues to increase worldwide, with a projected number of sufferers reaching 643 million by 2030. Early detection of diabetes is crucial to prevent serious complications such as cardiovascular disease, kidney failure, and nerve damage. This study aims to compare the performance of four machine learning algorithms (Random Forest, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors) in detecting diabetes based on clinical parameters, and to identify the most significant predictor variables. The study uses the Pima Indians Diabetes dataset consisting of 768 samples with 8 predictor variables (number of pregnancies, glucose, blood pressure, skin thickness, insulin, BMI, diabetes pedigree function, and age). Data is divided into a training set (70%) and a testing set (30%) using stratified sampling. Data preprocessing includes handling missing values, feature scaling using StandardScaler, and handling imbalanced data using the SMOTE technique. Performance evaluation uses accuracy, precision, recall, F1-score, and Area Under Curve (AUC-ROC) metrics. Results show that the Random Forest model achieves the best performance with an accuracy of 81.8%, precision of 79.2%, recall of 78.5%, F1-score of 78.8%, and AUC of 0.88. Support Vector Machine achieves an accuracy of 78.0%, Logistic Regression 76.0%, and K-Nearest Neighbors 74.5%. Feature importance analysis identifies glucose (28.5%), BMI (19.8%), and age (16.5%) as the most significant predictors in diabetes detection. The Random Forest model produces 17 false negatives and 12 false positives from 231 testing samples. The study concludes that Random Forest is the most effective algorithm for early diabetes detection with good accuracy and superior interpretability through feature importance
Penerapan Algoritma Boyer-Moore pada Aplikasi Glosarium Kesehatan
Full text linkPencarian istilah medis dalam glosarium kesehatan merupakan kebutuhan penting bagi mahasiswa, tenaga medis, dan masyarakat umum untuk memahami terminologi kesehatan. Namun, proses pencarian yang kurang efisien dapat memperlambat akses informasi. Penelitian ini membahas penerapan algoritma Boyer-Moore dalam aplikasi glosarium kesehatan guna meningkatkan efisiensi pencarian istilah medis. Metode penelitian meliputi studi literatur, analisis kebutuhan, perancangan sistem, implementasi, serta pengujian performa pencarian. Hasil implementasi menunjukkan bahwa algoritma Boyer-Moore lebih cepat dibandingkan metode pencarian sederhana (naïve search), dengan pengurangan jumlah perbandingan karakter dan waktu eksekusi hingga 50% pada dataset uji berisi 1000 istilah medis. Kesimpulan dari penelitian ini adalah bahwa algoritma Boyer-Moore efektif digunakan dalam aplikasi glosarium kesehatan karena mampu mempercepat proses pencarian istilah medis dan meningkatkan pengalaman pengguna
Development and Evaluation of Digital Image-Based Tomato Leaf Disease Classification Model Using Transfer Learning
Full text linkLeaf diseases in tomato plants (Solanum lycopersicum), including Early Blight, Late Blight, and Leaf Mold, can cause substantial reductions in crop yield if not detected at an early stage. Conventional manual detection methods are constrained by limitations in speed, consistency, and accuracy, particularly under field conditions. This study proposes a tomato leaf disease classification framework leveraging a transfer learning approach, in which the Inception V3 architecture functions as a feature extractor and the Random Forest algorithm serves as the classifier. The dataset employed comprises four categories of tomato leaf images—Early Blight, Late Blight, Leaf Mold, and Healthy—which were stratified into training (80%) and testing (20%) subsets. All images were resized to 299×299 pixels, normalized, and subjected to optional data augmentation. Feature representations were extracted from the Global Average Pooling layer of Inception V3 pretrained on the ImageNet dataset and subsequently input into a Random Forest classifier with hyperparameters optimized via grid search. Experimental evaluation demonstrated that the proposed model achieved an accuracy of 94.3%, surpassing the performance of a conventional CNN (89.2%) and a Random Forest classifier without transfer learning (76.5%). The confusion matrix analysis revealed the highest classification performance for the Healthy and Late Blight categories, whereas the Leaf Mold category exhibited a higher misclassification rate due to its visual symptom similarity to Early Blight. The findings of this research indicate that a hybrid methodology combining deep learning-based feature extraction and classical machine learning algorithms is highly effective for agricultural image classification in scenarios with limited datasets. Furthermore, the proposed approach holds significant potential for integration into web- or mobile-based decision support systems, enabling rapid and accurate plant disease detection in practical agricultural settings
Design of a Virtual Based English Learning Application System Reality and Augmented Reality
Full text linkTextbook-based learning media makes the learning atmosphere less attractive for students, especially for elementary school students. This causes the transfer of knowledge to be hampered. Advances in information technology have penetrated the world of education which applies information technology as a tool in teaching and learning activities such as visual animations including augmented reality technology. The augmented reality of technology in English learning applications is a solution to attract the interest of elementary school children. This application has two main features, namely learning and quizzes. First, students are given an introduction to objects around the house in English, then asked to work on questions in an augmented reality and virtual reality technology environment. This application carries out several processes which include reading marker symbols using a camera, then carrying out a pre-processing stage, namely the segmentation process for comparing marker symbols. If the marker symbol is an image that is similar to the reference data, the recognition image will be used to display the 3 dimensions of the object. The trial results show that the features of this application work well, and students perceive it as helpful to have this application for learning English
Decision Support System for Selecting Optimal Coconut Varieties for Coconut Milk Production: Integration of Analytic Hierarchy Process and Simple Additive Weighting Methods
Full text linkSelection of optimal coconut varieties for coconut milk production is a crucial step in the food industry, considering that the quality and quantity of coconut milk are greatly influenced by the type of coconut used. This study aims to determine the best coconut varieties for coconut milk production by integrating two multicriteria decision-making methods, namely the Analytic Hierarchy Process (AHP) and Simple Additive Weighting (SAW). The AHP method is used to determine the weight of each influential criterion, such as oil content, taste, price, and availability. Meanwhile, the SAW method is applied to rank various coconut varieties based on the weight of the criteria that have been obtained. The data used in this study were collected from various sources, including scientific literature, as well as field observation data. The results of the analysis indicate that certain coconut varieties have significant advantages in terms of quality and efficiency of coconut milk production. The coconut varieties selected through the combined AHP and SAW methods are expected to provide practical guidance for coconut milk producers in selecting optimal coconut varieties, so that they can improve the quality of the coconut milk produced. Thus, this study provides an important contribution in the field of agribusiness, especially in the selection of coconut varieties for coconut milk production, as well as implementing the use of AHP and SAW methods in complex and multi-criteria decision making
Implementasi Penjadwalan CPU Menggunakan Algoritma First Come First Served (FCFS)
Full text linkPenerapan sistem operasi dengan multitasking dengan pemrosesan pekerjaan secara simultan memberi konsekuensi terhadap pemberian beban kepada prosesor semakin besar. Untuk melakukan pemrosesan CPU lebih optimal dilakukan penjadwalan terhadap job. Salah satu penjadwalan yang dipakai dengan algortima First Come First Served (FCFS
Analisis Penerapan Digital Signature sebagai Otentikasi dan Pengamanan Data
Full text linkKemajuan teknologi informasi semakin mempermudah proses pertukaran informasi, dan kemajuan tersebut tidak terlepas dari adanya komputer dan internet. Akan tetapi disamping kemajuan teknologi tersebut muncul masalah baru yakni ancaman terhadap keamanan data. Saat pertukaran informasi berlangsung informasi yang dikirimkan merupakan data plainteks dan hal ini sangat beresiko ketika ada pihak yang berhasil menyadap informasi, maka pihak tersebut akan dengan mudah mengubah informasi tersebut sebelum sampai pada penerima sebenarnya. Penerapan Digital Siganture dalam proses pengiriman data merupakan solusi untuk masalah tersebut. Dikarenakan digital signature merupakan suatu cara matematis untuk menunjukkan keotentikan suatu data. Dari beberapa penelitian yanng pernah dilakukan digital signature telah banyak dipakai dan mampu membangun suatu sistem yang aman dengan mengkombinasikan digital signature dengan berbagai algoritma seperti LSB Embedding , SHA-256, CRC32, Kurva Elpitik, dll., akan sangat mendukung dalam pembangkitan sistem yang mampu mengamankan data khusus dalam proses otentikasi data
Kombinasi Algoritma Simetri dan ECC untuk Meningkatkan Keamanan Pesan
No full textPengiriman atau pertukaran data adalah hal yang sering terjadi dalam dunia teknologi informasi. Apalagi pengiriman data dilakukan melalui layanan komunikasi dunia maya, ancaman kejahatan sangat banyak terjadi didalamnya. Untuk menjaga keamanan data, dapat dilakukan dengan menggunakan teknik kriptografi.Banyak algoritma kriptografi yang digunakan untuk melakukan pengamankan pesan, tetapi kekuatan dari keamanan pesan tersebut masih lemah. Peningkatan keamanan pesan dan kunci dilakukan dengan algoritma hybrid. Metode hybrid dilakukan dengan mengkombinasikan algoritma simetri AES dengan OTP dengan algoritma ECC (Elliptic Curve Cryptograpy) yaitu ECDH (Elliptic Curve Diffie-Hellman). Algoritma AES dan OTP digunakan untuk enkripsi dan dekripsi pesan sedangkan ECDH digunakan untuk menentukan dan pertukaran kunci nya sehingga akan semakin meningkatkan keamanan dari pesan
Analisis Kerusakan Laptop Mati Total Dengan Menggunakan Metode Sistem Pakar
Full text linkSangatlah menjengkelkan pada saat-saat penting laptop kita bermasalah tiba-tiba mati tidak bisa di hidupkan, padahal tugas kuliah atau pekerjaan kantor sudah menumpuk dan harus secepatnya selesai, untuk masalah ini tidak perlu terlalu panik, yang di butuhkan disini kita harus perlu tenang dan berpikir jernih dan mulai menganalisa, Hal yang perlu dilakukan pertama sekali adalah membuka batere laptop dan pasang kembali, mengukur adaptor tegangan 19 volt pada jarum adaptor. Membuka casing dan memperhatikan apakah ada yang terbakar, mengukur pin-pin penting setiap laptop dan membersihkan part-part dari debu menggunakan tiner. Langkah tersebut merupakan satu teknik perbaikan laptop mati total, Sangatlah menyenangkan laptop yang mati bisa beroperasi lagi