Jurnal Teknologi Informasi Universitas Lambung Mangkurat (JTIULM)
Not a member yet
142 research outputs found
Sort by
IDENTIFYING AND FIXING UX-FRICTION EMPLOYEE DEVELOPMENT WEBSITE WITH MIXED APPROACH HEART FRAMEWORK AND USABILITY TESTING
Get PDFThe company website has an important role in the business processes that occur in the company, one of which is managing employee productivity. PT.XYZ utilizes the Kaizen website to improve the quality of its employees. Assessment of user experience while operating the website can be a form of evaluation between expectations and actual conditions related to website feasibility. In this study, the researcher intends to find out what indicators are obstacles in the operation of a web-based application called the Kaizen website at PT.XYZ so that there is inefficiency in its use. This research involved 54 respondents who were employees of PT.XYZ. The combination of HEART and Usability Testing methods is used to identify obstacles experienced by users and evaluate user experience when using the Kaizen website. The results of the analysis are then used to improve website performance in order to create a good user experience. The results showed that the HEART score increased by an average of 9% on each variable. Usability testing assessment also shows that the Kaizen website reaches the acceptable category with a score of 90.5 after improvements are made
OPTIMIZATION OF CNN + MOBILENETV3 FOR INSECT IDENTIFICATION: TOWARD HIGH ACCURACY
Get PDFDevelopments in the field of artificial intelligence and deep learning, particularly Convolutional Neural Networks (CNN) techniques, have expanded the research potential and applications in ecology, including efficient and accurate insect classification. However, there are challenges in achieving high levels of accuracy with similar computational efficiency. In response, the efficient MobileNetV3 architecture was investigated to improve the insect pest classification process. Through an analytical descriptive quantitative approach and insect datasets from Kaggle, this study tested the effectiveness of CNN models optimized with MobileNetV3. The results indicated that the optimized model achieved classification accuracy of up to 90%, with consistent performance between training and validation data and significant loss reduction. With high precision and processing efficiency, this discovery makes a substantial contribution to deep learning applications in the field of intelligent agriculture, promising methodological improvements for other classification problems. Despite offering a promising solution, this study recognizes the limitation in dataset diversity and suggests further exploration with more varied datasets to strengthen the model's application in actual agricultural practices
KRUSKAL WALLIS ANALYSIS TO FIND OUT THE IMPROVEMENT OF DESIGN THINKING SKILLS IN OBJECT-ORIENTED PROGRAMMING MATERIALS THROUGH EDUCATIONAL CONTENT
Get PDFEducation legislation in Indonesia currently requires Informatics subjects, which is closely related to programming-based material. However, many students in Indonesia still have difficulty learning about programming material. One of them is due to the background of students about the ability to think in the process of solving a program code. Seeing the phenomenon of today's students who are active on social media, it is a good step if social media is used as a learning media platform. This study aims to analyze the improvement of design thinking skills by using educational content-based learning media. The research method used was R&D with the ADDIE media development model and One Group Pretest-Posttest as the research design. The results showed an increase after students were given treatment in the form of educational content based learning media. The Kruskal Wallis test results showed a significant difference between the upper class, middle class, and lower class. The N-Gain obtained in the upper class is 0.560, in the middle class is 0.505, and in the lower class is 0.303. The average value of the results of student responses to learning media is 96.59 percent with the category "Very Good".  
MINE SLOPE DESIGN SIMULATIONS USING SLIDE 6.0 SOFTWARE OF POST-MINING SLOPE STABILITY
Get PDFPost-mining slopes are susceptible to landslides due to factors such as slope geometry, rock structure, physical and mechanical properties of rocks, and groundwater content. Monitoring of these slopes is essential to prevent broader environmental issues. This research aims to determine the stability of former mining slopes using soil samples from the Mataraman District, Banjar Regency. The technical analysis method focuses on the physical and mechanical properties of soil, supplemented with mine slope design simulations using Slide 6,0 software to ascertain the safety factors from various slope angles. Safety factor analysis considers the smallest cohesion and bulk density values to represent the material strength of the slope. Findings indicate that the post-mining slopes would remain stable and safe provided no additional destabilizing factors are introduced. The slopes maintain a safety factor greater than 2, implying stability even with a steepness up to 70Β°.
Keywords: mining slope stability, safety facto
Application of K-Means and K-Medoids Algorithms for Clustering Chili Commodity Trade Distribution in Indonesia
Get PDFChili is one of the important commodities in agriculture and food, which is a product of the capsicum plant that has significant economic value in international trade. This study aims to identify an effective distribution strategy for red chili commodities in Indonesia through the use of the K-means and K-medoids clustering algorithms. The data used comes from the Central Statistics Agency (BPS) in 2022, including parameters-production, consumption, surplus/deficit, trade margin, and the impact of market operations and natural disasters. The implementation of K-means and K-medoids uses the RapidMiner application to form six provincial clusters based on the characteristics of red chili distribution. The results of the analysis show that K-medoids consistently outperforms K-means in cluster formation, with lower Davies-Bouldin Index (DBI) values ββindicating better clusters. The conclusion of this study confirms that K-medoids is more effective in grouping red chili distribution areas in Indonesia, potentially providing a stronger foundation for strategic decision making in the distribution management of this commodity. Therefore, this study recommends the use of K-medoids as a more appropriate approach for planning and implementing red chili distribution strategies in Indonesia.
 
Comparison of Arima Model with The Addition of Linear Quadratic Estimation Algorithm for Prediction The Spread of Covid-19 in Kotabaru District
Get PDFCoronavirus disease 2019 (Covid-19) has been declared by WHO as a pro-longed global pandemic which has caused signif- icant public health problems, deaths and economic losses, therefore it is necessary to carry out prevention and control ef- forts to break the chain of transmission of Covid-19. One effort that can be done is to estimate the additional number of posi- tive cases of Covid-19, so that the number of isolation rooms and the need for medical personnel can be estimated. In this study the prediction of an increase in the number of positive cases of Covid-19 was carried out using the Linear Quadratic Estimation (Kalman Filter) approach based on the state space model formed from the ARIMA model (0,1,4). Based on train- ing data from March 23, 2020 to April 4, 2023, the best time series model is the ARIMA model (0,1,4) which was chosen based on the smallest AIC value and satisfies the residual test hypothesi
Examining IT Service Management Service Operations Utilizing The ITIL V3 Framework: A Case Study of Dana
Get PDFThis paper presents a comprehensive analysis of IT service management (ITSM) service operations within the context of the ITIL v3 framework, focusing on a case study of Dana, a digital wallet company. Employing a quantitative research approach through a questionnaire, the study delves into Dana's implementation of ITIL v3 practices in managing its IT services. It investigates various aspects of IT service operations, encompassing event management, incident management, problem management, request fulfillment, and access management, within the framework of ITIL v3 and maturity model. By scrutinizing Dana's ITSM service operations, this study aims to offer insights into the effectiveness and challenges of applying the ITIL v3 framework in real-world organizational settings. The research findings contribute to the existing knowledge on IT service management practices and provide practical recommendations for organizations striving to optimize their IT service operations using ITIL v3 principles
IoT-Based Door Security System as A Countermeasure and Theft Prevention
Get PDFA security system is very necessary when creating a system. One of them is a door lock system. There are several security systems that can be used when creating an automatic door locking system, namely using alarms and application notifications. A good security system also requires how quickly the tool or system works to give signs that someone is breaking in. By applying IoT (Internet of Things) and also the ESP32 microcontroller, we can monitor an event in real-time. With IoT-based security systems, the system can continuously operate with just stable internet and electricity. The ESP32 microcontroller is also widely used in IoT projects due to its ease of operation and affordable price. An alarm that is responsive can help us prevent criminal activities. An alarm functions to alert us of something or a situation. By combining the concepts of the ESP32 microcontroller and alarm notifications in the form of messages on Telegram, we can create a reliable system. This becomes an effective solution for securing properties and the safety of its occupants
Classification of Mental Disorders Using Modified Balanced Random Forest And Feature Selection
Get PDFThis study employs the Modified Balanced Random Forest (MBRF) algorithm and Correlation-based Feature Selector (CfsSubsetEval) for mental disorder classification. The "Mental Disorder Classification" dataset from Kaggle was used with the aim of improving accuracy, evaluating feature selection, and assessing MBRF's performance in handling data imbalance. The study compares the performance of Random Forest (RF) and MBRF, and examines the impact of feature selection using CFS on mental disorder classification. The results indicate that MBRF outperforms RF with an 8.33% improvement in accuracy, 8.61% in precision, 8.33% in recall, and 9.08% in F1-Score. Additionally, the comparison between MBRF and MBRF with CFS reveals that while accuracy and recall remain the same, MBRF achieves 0.23% higher precision and 0.81% higher F1-Score than MBRF with CFS. In conclusion, the use of MBRF proves to be superior to the standard RF in addressing data imbalance for mental disorder classification, significantly improving accuracy, precision, recall, and F1-Score. However, feature selection with CFS does not significantly enhance performance. While accuracy and recall remain unchanged, MBRF without CFS demonstrates higher precision and F1-Score, indicating that the model performs better without feature selection in maintaining the balance between precision and recall
Analysis of Internet Network Quality of Service (QoS) on ULM Hotspot at Universitas Lambung Mangkurat Banjarmasin
Get PDFWith the internet, the technique of having information or records will become quicker and extra efficient. present day college students are very dependent on the internet in phrases of gaining knowledge of, doing assignments, accumulating assignments, even within the studying method using the internet. the present facility at Lambung Mangkurat university is ULM HOTSPOT to facilitate college students to get entry to the internet without cost, however at certain times ULM HOTSPOT regularly decreases its network speed. The intention of the research became to analyze the quality of the ULM HOTSPOT network in five faculties of Lambung Mangkurat university, Banjarmasin, specifically the faculty of Engineering ULM, faculty of Eco- nomics and business ULM (FEB ULM), faculty of teacher training and education ULM (FKIP ULM), faculty of Social and Political Sciences ULM (FISIP ULM), in addition to the ULM faculty of law, by using searching out parameter calculations for quality of provider, particularly Throughput, Jitter, delay, and Packet Loss primarily based on TIHPON standardization and in order to be able to discover what factors impact the parameter values of quality of service. The research turned into accomplished by collecting parameter data from quality of service using the network Protocol Analyzer software, specifically Wireshark in five faculties of Lambung Mangkurat university, Banjarmasin through getting access to the ULM HOTSPOT network in each faculty and establishing Simari, Gmeet, and Zoom as substances for accumulating quality of service parameter records. . The outcomes of this observe obtained a quality of service rating based on standards from TIHPON, faculty of Engineering with a rating of 2.75 (Unsatisfactory), FEB-ULM with a rating of 3 (excellent), FKIP-ULM with a value of 2.75 (Unsatisfactory), FISIP-ULM with a value of 3 (excellent), and the faculty of law with a value of 3 (excellent). The factors that have an effect on the decrease within the quality of service rating based on the ULM HOTSPOT internet network consumer capability exceeds the limit