Jurnal Teknik Informatika dan Sistem Informasi
Not a member yet
499 research outputs found
Sort by
Otomatisasi Proses Online Stock Opname pada Aplikasi Inventaris Barang untuk Multi Lokasi Pergudangan
Get PDFThe process of stock opname of goods in a business is something that must be done regularly to control the business assets. The stock opname process generally requires a lot of money and time, especially in businesses that have many branch locations. During the implementation of stock opname, sales transactions are usually stopped so that the stock does not change. As a result, the longer the time for this process is required, the greater the loss. In addition, extra costs are also incurred when the implementing manager is sent to each branch location where the stock opname will be carried out. Due to the high costs and losses incurred, this stock opname is usually only done a few times a year. On the other hand, the low frequency of stock opname has an impact on increasing business losses due to loss of assets that cannot be detected early. This study aims to increase the effectiveness of the stock opname process to minimize losses that occur during the stocktaking process or losses due to delays in handling the loss of goods assets. The results of this study indicate that the new system design allows the stock opname process to be carried out remotely without the presence of a manager and without stopping sales transactions, so as to reduce operational costs. The frequency of stock opname can also be carried out more frequently so that if there is a loss of assets, it can be immediately identified and action is taken to avoid high business losses. The result of software testing using the Blackbox Testing method shows that the application can run well and the result of User Acceptance Testing shows the acceptance of respondents at 87%, which means that respondents accept the solutions offered well
Pengaruh Preprocessing Terhadap Klasifikasi Diabetic Retinopathy dengan Pendekatan Transfer Learning Convolutional Neural Network
Get PDFDiabetic retinopathy (DR) is eye diseases caused by diabetic mellitus or sugar diseases. If DR is detected in early stage, the blindness that follow can be prevented. Ophthalmologist or eye clinician usually decide the stage of DR from retinal fundus images. Careful examination of retinal fundus images is time consuming task and require experienced clinicians or ophthalmologist but a computer which has been trained to recognize the DR stages can diagnose and give result in real-time manner. One approach of algorithm to train a computer to recognize an image is deep learning Convolutional Neural Network (CNN). CNN allows a computer to learn the features of an image, in our case is retinal fundus image, automatically. Preprocessing is usually done before a CNN model is trained. In this study, four preprocessing were carried out. Of the four preprocessing tested, preprocessing with CLAHE and unsharp masking on the green channel of the retinal fundus image give the best results with an accuracy of 79.79%, 82.97% precision, 74.64% recall, and 95.81% AUC. The CNN architecture used is Inception v3
Aplikasi Edukasi Pemecahan Masalah pada Vulnerability Server Berbasis Web
Get PDFThis research is purpose to design a virtual machine to simulate cyber attacks and find out how to design and build a virtual machine with a security gap that has been designed, so that it is used as education for web and server developers. The method used in building this system is the waterfall method which starts from designing a system to make it easier to build a system and then collecting data using observations to students of informatics engineering and computer engineering. The results of this system show that the system is able to run well, the guide for working on questions can be understood by the player, the player can inputs flags without problems, the clues provided are understandable and the educational videos provided are easy to understand. From the explanation aboce, the researchers concluded that this system can provide questions and education wel
Analisis Cluster Data Interkomparasi Anak Timbangan dengan Algoritma Self Organizing Maps
Get PDFIntercomparison was conducted to determine the ability and the performance of the laboratory. Intercomparison results are usually expressed in the range of En ratio values (En ?|1|) which express the equivalence of one laboratory with other laboratories. If the laboratory is declared unequal, then it needs to identify the source of the problem by itself. To make it easier, it can be done by Clustering which is one of the data mining techniques. Clustering is done by applying a self organizing map algorithm on the KNIME (Konstanz Information Miner) analytic tools. Several experiments were carried out with different layer size and data normalization status from one experiment to another experiment. The results were analyzed through pseudo F statistical test and icdrate test. The largest pseudo F statistic value was obtained from the 8th experiment (setting the layer size 2x2 without data normalization) with a pseudo F statistic value of 167.53 for 1kg artifacts and a Pseudo F statistic value of 104.86 for 200 g artifacts where the optimum number of clusters are 4. The smallest icdrate value was obtained from the 5th experiment (setting the 2x3 layer size without data normalization) with an icdrate value of 0.0713 for 1kg artifacts and icdrate value of 0.2889 for 200g artifacts with the best number of clusters being 6. From 12 laboratories can be grouped into 6 groups where each group has the same identification. There are groups 1, 3 and 6 have 1 member, while groups 2, 4 and 5 have 3 members
Penerapan Decision Support System Beasiswa Berprestasi pada Sekolah Menengah Kejuruan
Get PDFEvery educational institution provides scholarships that are offered to its students with specified requirements, as well as at SMK Negeri 1 Sukawati. Students who receive scholarships are students who meet the requirements and criteria that have been determined. The criteria determined are report cards, absenteeism, achievement, organizational involvement, and violations. However, some problems arise when determining the prospective recipients of achievement scholarships at SMKN 1 Sukawati, particularly many students who have achievements outside of school activities or non-academic achievements do not get scholarships. One of the criteria-set is to have achievement, which means achievement is not only academic achievement but also non-academic. The design of a system that can provide recommendations to decision makers is needed, so that it is right on target in providing opportunities for students who meet the criteria considered. The Simple Additive Weighting (SAW) method is used in this study because it can choose the best alternative from several alternatives. The results obtained in this study in the form of ranking and then make a recommendation to receiving a scholarship
Evaluasi Penggunaan Learning Management System Sebagai Alat Bantu Pembelajaran Matematika Sekolah Dasar
Get PDFTeaching and learning activities need to be interactive to increase children’s interest in learning. With the utilization of technology, there are so many learning tools had been made. One of them is Moodle. Moodle is a learning management system (LMS) application to support learning activity on electronic based (e-learning). The purpose of this research is to implement Moodle as LMS for mathematics learning on primary school children. By using Moodle, the lessons are delivered interactively for children to learn. This research will find out the influence of using this application towards the test score before and after using the application. T-Test analysis will be applied to analyze the differences. Besides analyzing the test score, questionnaires for the children who test the application will be given to know the effect of using the application for them. Based on the evaluation result using T-Test analysis, there were not any significant differences, but there were enhancements in average, highest, and lowest scores, along with the decrease in standard deviation. The result of correlation coefficient calculation between exercise frequency and quiz result was 0.2162, which meant that the correlation was weak or almost no correlation. Based on the questionnaire result, this application is considered helping children in understanding the subject
Sentiment Analysis on the Ratification of Penghapusan Kekerasan Seksual Bill on Twitter
Get PDFRancangan Undang-Undang Penghapusan Kekerasan Seksual (RUU PKS), or the bill of the Republic of Indonesia on the Elimination of Sexual Violence, is a bill that discusses sexual violence, victim protection and its scope concern the matters related to sexual violence. Elimination of sexual violence according to the PKS Bill aims to prevent all forms of violence. These discussions and conversations also occur on social media, especially on Twitter. Taking public sentiment is significant in choosing the proper messages, interference, and policy. Sentiment analysis is a field of study that analyses opinions, sentiments, judgments, evaluations of a person attitudes and emotions regarding a particular topic, service, product, individual, organization or activity. This study used the method of crawling to get data from Twitter. Then data cleansing, data processing is carried out using Bernoulli, Logistic Regression, and Support Vector Classification (SVC) algorithm. The data is then evaluated using three methods: accuracy, classification report, and confusion matrix. Based on the three algorithms used, it is found that all methods are equally accurate with 0.65. This study found positive, negative, and neutral sentiments expressed to the bill of Elimination of Sexual Violence through comments. It is shown that most people using the keyword “RUU PKS” are positive to the bill of Elimination of Sexual Violence (RUU PKS) while most people’s sentiments using #RUUPKSBukanSolusi are negative to the bill
Aplikasi Pengelolaan Persediaan Bahan Pada Usaha Kecil Menengah Pakaian Jadi
Get PDFClothing is one of the basic or primary needs. With the influence of clothing fashion that continues to grow, many Small and Medium Enterprises (SMEs) have sprung up engaged in the clothing sector. SMEs are one of the driving forces of the Indonesian economy. SMEs engaged in the clothing sector are businesses that produce apparel. The materials used in the manufacture of clothing also vary, so that inventory management and material requirements planning are essential processes in the manufacture of clothing. In this study, a simple mobile application was developed that can be used for material inventory management for SMEs. The primary function of this application is to record materials (inventory) and plan production needs using the Reorder Point (ROP) method. The Reorder Point (ROP) method is an order limit point helpful in knowing when a company holds an order. Program development using Android Studio IDE with Flutter framework and Dart programminglanguage. The results of functional testing on this application are 90% achieved following the expected results. The user acceptance test concludes that this application has the potential to facilitate SMEs in managing the inventory of material
Perancangan Sistem E-Reporting Menggunakan ReactJS dan Firebase
Get PDFThe head office of west region of Seventh Day Adventist Indonesia in Indonesia is located in Jakarta. Every month employees must report every transaction they have made . The report can be in the form of proof of purchase, shopping receipt, notes and other proof of transactions. The reporting system of the office is done by submitting a hardcopy proof of the transaction to the finance department. The reporting process takes a long time and allows for inaccurate proof of transactions. Another problem that is often found is the unknown status of reports. Employees often do not know whether the reports that have been received by the financial department have been approved or not. The purpose of this study is to design an E-reporting system that will make it easier for employees to report to the financial department so that reporting can be done quickly and accurately. The system to be built uses ReactJS and Firebase using an Agile Software development method. The result of this research is the creation of an E-reporting application that can help to report on the financial department every month
Perbandingan Algoritma Machine Learning dalam Menilai Sebuah Lokasi Toko Ritel
Get PDFAbstract — The application of machine learning technology in various industrial fields is currently developing rapidly, including in the retail industry. This study aims to find the most accurate algorithmic model so that it can be used to help retailers choose a store location more precisely. By using several methods such as Pearson Correlation, Chi-Square Features, Recursive Feature Elimination and Tree-based to select features (predictive variables). These features are then used to train and build models using 6 different classification algorithms such as Logistic Regression, K Nearest Neighbor (KNN), Decision Tree, Random Forest, Support Vector Machine (SVM) and Neural Network to classify whether a location is recommended or not as a new store location.
Keywords— Application of Machine Learning, Pearson Correlation, Random Forest, Neural Network, Logistic Regression