Jurnal Teknik Informatika dan Sistem Informasi

Usability Evaluation and Development of the Online Library Information System Using Think Aloud

2024-02-23T08:15:24+00:00

Usability refers to the quality of the user experience when interacting with a product or system, including websites, software, devices or applications. Usability is about effectiveness, efficiency and overall user satisfaction. OLIS (Online Library Information System) is an information system that functions as a catalog for managing the Del Institute of Technology library. Based on the usability value measurement results, the OLIS website has an SUS value of 41.25 or a “poor” level of usability. This shows that the usability aspect of the website must be improved. To achieve good usability, a usability evaluation is carried out using the think aloud method. This evaluation is carried out for at least 2 iterations until the OLIS usability value reaches a minimum value of 80. The results of the first iteration evaluation are 18 problem findings which are then analyzed to make the first iteration improvement design. Furthermore, the second iteration identifies problems from the first evaluation and produces 17 usability problems which will then be analyzed to make a second iteration improvement design that will be made into the final high fidelity prototype. The SUS measurement results on the OLIS website which have been evaluated by think aloud is 85.25 or the usability level is "excellent".

Success Analysis of Sistem Seleksi Mahasiswa Berprestasi with DeLone McLean Success Model

2024-08-14T03:48:29+00:00

Education is a very important thing where education can improve the quality and competitiveness of a person. Wonogiri Regency is one of the regions in Central Java that is currently struggling to improve the quality of human resources by increasing the interest in education of its people to the Higher Education level so that the Outstanding Student Scholarship program was launched. This study will analyze the success of the SIMAPRES website used for registration and selection of the scholarship program. The sample of this research is the applicants of the scholarship program who use the SIMAPRES website. The research model used is the DeLone & McLean IS Succes Model 2003 with 6 hypotheses and data processing using Partial Least Square-SEM which will show the correlation between variables from the model. This study tested a sample of 423 students applying for scholarship programs from various universities in Indonesia. From this sample, it was found that the six hypotheses showed a significant influence between variables with a T-Statistic value above 1.96, which also means that system quality, information quality, service quality have a good impact on the use and user satisfaction variables. From the results of the study it can be concluded that the SIMAPRES website has been quite successful in its use for registration and selection of the scholarship program.

K-Means Implementation for Customer Segmentation in Aluminium and Glass Business by Purchasing Behavior

2025-06-03T02:00:55+00:00

— Mulia Jasa Aluminium dan Kaca is a business in the retail and service sector, offering Aluminium and glass materials and services for manufacturing, installation, and repair. Currently, competition in this field is quite intense, leading the business owner to admit difficulties in increasing sales. Therefore, the business owner needs to implement marketing and service strategies to boost sales. However, the diversity of customers with varying characteristics and behaviors makes it challenging to establish effective marketing and service strategies. Thus, this study conducts customer segmentation based on purchasing behavior. The aim is to understand customer behavior and loyalty using sales report data from the business. The variables used to assess a customer's value are Length, Recency, Frequency, and Monetary (LRFM). These variables are grouped using the K-means clustering algorithm. The objective of this study is to group customers based on their purchasing behavior, thereby assisting the business in developing more effective marketing and service strategies, enhancing customer satisfaction, and ultimately increasing sales and loyalty. Using the Silhouette method to determine the optimal number of clusters, three customer groups were identified, with the highest coefficient value of 0.663063. Cluster 0 is the “Lost Customer Group”, Cluster 1 is the “New Customer Group”, and Cluster 2 is the “Core Customer Group”.

Comparison of Multifactor Evaluation and Fuzzy AHP on Coffee Bean Quality

2025-01-22T03:15:34+00:00

The development of information technology in the agricultural sector is crucial, including in determining coffee bean quality. This research implements a comparison of decision support systems (DSS) using the Multifactor Evaluation Process (MFEP) and Fuzzy Analytic Hierarchy Process (FAHP) methods to assess coffee bean quality based on moisture content, Trase, defects, color, aroma, and bean size. The results show that FAHP has an accuracy of 77%, higher than MFEP with an accuracy of 71%. Thus, FAHP is more effective in determining the farmers with the best coffee beans, thereby helping to improve the economic well-being of farmers and cooperatives.

Dynamic Simulation of Single Qubit and Multi Qubit: A Python Approach

2025-02-14T09:23:46+00:00

This study developed a dynamic simulation system for single qubit and multi qubit using a Python-based approach, leveraging quantum computing libraries such as Qiskit, NumPy, and Matplotlib. The system is designed to simulate various quantum operations, including Hadamard, Pauli-X, Pauli-Y, Pauli-Z, CNOT, and Toffoli, with integration into a Flask-based web interface for easy user interaction. The simulation results show a high level of accuracy, with a difference of only 0.2% in measurement probabilities for single qubit operations like Hadamard and less than 0.4% for multi qubit operations like CNOT and Toffoli. The tests also demonstrated efficient execution times, ranging from 12 to 25 milliseconds, even for complex quantum operations. Validation against established literature confirms that the system is accurate, efficient, and reliable, making it a valuable tool for supporting learning and research in quantum computing.

Implementation of Regularized Singular Value Decomposition in Collaborative Filtering Book Recommendation System

2025-02-14T09:26:10+00:00

At the school level, time is limited by the system of lesson hours. This makes students have to use their time wisely before changing lesson. However, choosing appropriate reading material often requires more time which results in wasted class hours. The development of a recommendation system using the Collaborative Filtering (CF) and Regularized Singular Value Decomposition (SVD) methods was chosen to solve the problem of students having difficulty finding books in the library. The data used is student interaction data with books in the form of ratings which are collected directly and processed to provide recommendations. The results of applying SVD in predicting ratings and looking for appropriate latent features to describe the characteristics of students and books produce MAE and RMSE values of 0.478 and 0.686. The research conducted also shows that the appropriate number of latent factors or features and the addition of regularization have an effect on increasing prediction accuracy. The predicted value of the rating is then used to provide personal book recommendations and the latent feature values of the books found are used in calculating cosine similarity to provide non-personal recommendations.

Comparison of Kernel Convolutional Neural Network in Lampung Script Word Recognition and Transliteration

2025-05-04T04:59:43+00:00

The study aims to create a system that can recognize and transliterate Lampung script image data and compare the
Convolutional Neural Network (CNN) kernel to the Lampung script word recognition and transliteration system. The Lampung
script recognition and transliteration system with the CNN learning model is implemented using the python 3.9.4 64 bit programming language, with a stride of 1 for convolution and 2 for pooling, the kernel size variations used are 2x2, 3x3 and 5x5 which are applied crosswise for feature extraction of the convolution and pooling processes. The 3x3 convolution kernel type and 3x3 pooling kernel showed the best performance in transliterating and recognizing Lampung script words with a test accuracy of
0.9 and a small test result data inequality, which is 2/10 or 0.2. The 3x3 Kernel Size shows ideal conditions for use, especially
when the image features used have very few differences in features.

Mango Ripeness Detection Based on Color Features Using Digital Image Processing

2025-04-30T11:21:37+00:00

The classification of mango Golek ripeness is crucial for ensuring product quality and its economic value, especially in industrial applications. Manual and subjective ripeness determination often leads to inconsistency, resulting in decreased harvest quality and market value. This study aims to classify the ripeness of Golek mangoes into three categories: unripe, semi-ripe, and ripe, using digital image processing based on HSV and LAB color features combined with the K-Nearest Neighbor (KNN) algorithm. The dataset consists of 300 images, split into 80% training data and 20% testing data. The proposed method includes image acquisition, preprocessing, segmentation, morphological operations, feature extraction, and classification. The results show that the combination of HSV and LAB color features is effective in distinguishing ripeness levels, with an accuracy of 81.67% on the testing data and an average precision, recall, and F1-Score of 82%. Consistent color patterns in the unripe and semi-ripe categories enhance accuracy, while fluctuations in color intensity in the ripe category pose challenges. This approach shows potential for implementation in automatic sorting systems in industry.

Comparison of Long Short-Term Memory and Bidirectional Models for Fog Prediction

2025-04-30T11:24:12+00:00

Fog is a weather phenomenon that can significantly reduce visibility and impact transportation safety as well as public activities. The Citeko region in Bogor, located in a highland area, experiences a relatively high frequency of fog events, especially during the morning and rainy seasons. This study aims to develop and compare the performance of fog prediction models using Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) algorithms based on historical weather data from 2013 to 2023. The data, obtained from the Citeko Meteorological Station, includes weather parameters such as dry-bulb temperature, wet-bulb temperature, dew point, visibility, relative humidity, cloud cover, wind direction and speed, and hourly weather conditions. The data underwent several preprocessing steps, including missing value interpolation, fog classification based on weather parameters, normalization, and splitting into training and testing sets (80:20 ratio). The LSTM and BiLSTM models were then trained using a deep learning approach, both with and without early stopping. The results show that BiLSTM with early stopping achieved the best performance: 99.93% accuracy, 96.53% precision, 98.81% recall, and an F1-score of 97.66%, with only 9 false positives and 3 false negatives. This study contributes to the development of fog prediction systems based on artificial intelligence.

Eggplant Quality Classification Using Backpropagation Algorithm Based on Color and Texture Features

2025-05-02T07:54:32+00:00

Manual quality assessment of eggplant is often inconsistent, takes a long time, and is prone to errors due to worker fatigue. This research aims to develop an automated system based on digital image processing to assess eggplant quality efficiently and accurately. The stages begin with image capture using a mobile phone device designed to ensure stable lighting and uniform background. The acquired image is then processed through segmentation using the Otsu thresholding method as well as morphological operations to separate the main object from the background. Color and texture features are extracted through Gray-Level Co-occurrence Matrix (GLCM) analysis and RGB, HSV, and LAB color spaces. Training data amounting to 90% of the total dataset was used to train an artificial neural network-based classification model with a backpropagation algorithm, while the remaining 10% was used for testing. Experimental results showed that the combination of LAB, RGB, HSV, and texture features gave the best results, with a testing accuracy of 86%, recall of 85%, and precision of 92%. This model is very effective in detecting poor quality eggplants with 100% accuracy. This system can support the application of technology in the horticultural sector.

Laravel Middleware Implementation for Multi-User Access : Case Study Lecturer Minutes System

2025-03-11T11:39:13+00:00

One of the lecturers’ roles in Tridharma is teaching. There is a shift in the role of lecturers where lecturers are not only compiling and delivering materials but also guiding students in class so that they can think actively and independently. Universities must record teaching activities carried out by lecturers. Documentation of teaching activities is carried out using lecture minutes in either hardcopy or online form. There are problems faced in the digital recording process, namely data duplication due to the absence of data history, long data entry, and the difficulty of recapitulating required data. To solve the problem, a system is needed that can handle the data input process and share access so lecturers, vice deans, or faculty administrators can monitor the activities carried out. The system is built using the Laravel framework, which utilizes object-relational mapping (ORM) and middleware. ORM is used to simplify class attributes and relations between classes. The contents of classes designed with ORM are simpler than classes created conventionally. Middleware is a class that functions to process HTTP Requests. HTTP Requests can be validated for authentication processes and web access settings. The implementation has divided the user roles, namely lecturers, faculty vice deans, faculty/department level administrators, and administrators. Each role has its specific functions. Lecturers can only enter lecture minutes (BAP) for assigned courses and can monitor the data. The BAP input process also cannot be delegated to other parties. Faculty/department administrators and vice deans can monitor the BAP input process and confirm data according to the level given. Confirmed data can be exported in another form to facilitate the subsequent reporting process.

Designing Mobile Application for Sports Field Rental with Backend for Frontend Method

2025-06-06T06:29:50+00:00

This study aims to design a mobile-based sports field rental system by applying the Backend for Frontend (BFF) architectural approach. The main problem addressed is the limitation or manual systems in terms of efficiency, schedule transparency. And ease of booking. The research was conducted through several stages, including data collection, user interface design using Figma, backend development using Laravel, and API endpoint testing via Postman. The system evaluation was based on the ISO/IEC 25010 standard, particularly focusing on functional suitability, performance efficiency, reliability, and maintainability. The test results show that all endpoints responded correctly, with an average response time ranging from 200 to 600 ms, and no server errors were found. These findings indicate that the Backend for Frontend BFF approach is effective in supporting a modular and efficient digital rental system that is ready for integration into mobile applications.

Analysis of Factors Contributing to Employee Attrition Based on Self-Organizing Map Clustering

2025-06-02T19:31:51+00:00

Employee turnover can disrupt the organization's operations and more or less cause losses to the business. Therefore, it is important to understand the causal factors so that organizations can take anticipatory action. Identify reasons employees leave their jobs is crucial for both employers and policy makers, especially when the goal is to prevent this from happening. Data on the causes of employee turnover is complex data that can have many dimensions, so a certain method is needed to analyze it. In this research, an analysis of data on the causes of employee turnover with 10 dimensions will be carried out using the Self Organizing Map (SOM) method. The Self-Organizing Map (SOM) is a technique for clustering and visualizing high-dimensional data by mapping it to a two-dimensional space while preserving the data's topological structure. This neural network-based method ensures that similar data points remain close to each other in the resulting 2D representation. SOM will cluster the data into several uniform groups. The results of this SOM grouping will be assessed with the Silhouette score, Dunn index and Connectivity value to determine how uniform the grouping is. Hopefully that by using the results of this SOM grouping, it shows that the clusters formed are very good and the data is clearly grouped. Therefore, we can analyze these groups with more accurate results.

Operational Risk Management Planning for Electronic-Based Government Systems

2025-06-02T19:34:48+00:00

Risk management in Information Technology (IT) is a crucial element for every organization, including government institutions. Currently, the Department of Communication, Informatics, Encryption, and Statistics of Buleleng Regency (Diskominfosanti Kab. Buleleng) does not have a specific approach to systematically managing IT risks. The Electronic-Based Government System (SPBE) is a government initiative that optimizes the use of IT and communication to provide services to the public. Implementing risk management in SPBE presents an opportunity for government agencies to enhance operational efficiency and drive innovation. This study aims to develop an initial guideline for SPBE risk management at Diskominfosanti Kab. Buleleng, with the goal of improving the institution’s SPBE index. The guideline design refers to the provisions outlined in Presidential Regulation (Perpres) No. 95 of 2018 and Ministerial Regulation of PANRB No. 5 of 2020 concerning SPBE Risk Management Guidelines. The approach used in this guideline integrates the COBIT 5 for Risk framework to identify, analyze, and evaluate various potential risks. The research findings identify 30 risks, consisting of 2 positive risks and 28 negative risks. The risk mitigation strategy design covers aspects of human resources, technology, and operational processes. This study produces three key outputs: risk identification, risk assessment, and a risk mitigation strategy framework for SPBE services implemented at Diskominfosanti Buleleng.

Product Development Using Agile Scrum Method

2025-05-30T08:01:21+00:00

HiColleagues is an edutech startup company that focuses on IT services and education. With the increasing number of competitors in the edutech field, HiColleagues formed a Business Development division to ensure the business process runs well. One of the sub-divisions of Business Development is Product, which is in charge of developing HiColleagues products so that they can compete with competitors. The Product sub-division will develop HiColleagues products by creating documents as needed. All of these tasks will be done by implementing the Agile Scrum method where each task will be divided into several sprints and using Trello to document all tasks. By using the Agile Scrum method and utilizing Trello, all tasks can be completed according to the deadline and thoroughly documented.

Impact of Collaborative Learning and Motivation on Learning Performance in Learning Management System

2025-05-30T07:58:47+00:00

This study analyzes the influence of Collaborative Learning Object Materials (LOM) and learning motivation on student performance in an Internet of Things (IoT) course using blended learning. The research was conducted using the Maranatha Online Learning (MORNING) platform, a Moodle-based Learning Management System (LMS). A flipped classroom model was implemented, integrating synchronous and asynchronous learning strategies. Path analysis was used to evaluate the relationship between LOM interaction, learning motivation, and learning outcomes. The results indicate that LOM interaction (B=0.656, p=0.000003) and learning motivation (B=0.341, p=0.005318) have a significant influence on learning performance (R²=0.648). Thus, this study demonstrates the potential of collaborative and motivational strategies in enhancing student engagement and performance in blended learning.