JITSI : Jurnal Ilmiah Teknologi Sistem Informasi

Perancangan Ulang UI/UX Website E-Learning UNMUL Menggunakan Metode Design Thinking

2025-01-21T07:24:00+00:00

The rapid advancement of technology necessitates effective information systems in universities to enhance academic program quality. Mulawarman University addresses this through e-learning, yet users, especially students and lecturers, encounter challenges with the interface. This research aims to redesign the UNMUL e-learning website for better usability. Using the Design Thinking method, the study focuses on user issues and translates them into feature requirements. Data were collected through interviews and usability testing with students and lecturers. The findings reveal that the redesigned application supports various teaching and learning activities while reflecting Mulawarman University's identity. Usability testing showed high scores: 86 for the lecturer prototype and 80 for the student prototype. Additionally, the User Experience Questionnaire results are classified as excellent according to UEQ benchmarks.

Development of South Solok PNP PSDKU Computer Network Infrastructure Using the Network Development Life Cycle (NDLC) Method

2025-01-21T07:24:16+00:00

This research aims to analyze and design the computer network infrastructure at the Politeknik Negeri Padang (PNP) Program Studi Di luar Kampus Utama (PSDKU) South Solok in order to improve network performance. Currently there are 4 Optical Network Terminal (ONT) units from ISP Indihome with bandwidth for 2 ONTs of 100 Mbps and 1 ONT of 300 Mbps and 1 ONT specifically as a Wifi ID access point to meet the internet needs of lecturers, students and educational staff. However, there are problems identified, namely bandwidth management is not optimal, which results in a bottleneck on one of the ISP lines and not optimal use of the available bandwidth capacity and there is no back up if one of the ONTs has a problem. This research uses the Network Development Life Cycle (NDLC) method which consists of analysis, design, simulation, implementation, monitoring and management stages. In the initial stage, network requirements analysis and network topology design with the addition of a router are carried out. Network testing is carried out at the final stage to ensure that the new network infrastructure is able to work properly. The results of this research provide better internet network optimization in PNP PSDKU South Solok

Object Detection for Retail Products with TensorFlow 2

2025-01-21T07:23:28+00:00

On-shelf availability is a crucial aspect in the retail industry, directly impacting customer satisfaction and sales. Artificial intelligence-based object detection technology can enhance efficiency in monitoring product availability. This study examines the implementation of TensorFlow 2 for detecting retail products on shelves, using the SSD MobileNetV2 FPNLite architecture. Three model variations were developed based on input image sizes: 320x320, 640x640, and 1024x1024. The models were trained using transfer learning with a dataset containing 128 retail product classes. Evaluation results show that the 640x640 model achieved the best performance in terms of the trade-off between precision and speed, with a mAP of 0.72049 and an inference time of 0.283 seconds. The 320x320 model had the fastest inference time of 0.073 seconds, making it suitable for real-time applications. This study offers a solution to improve retail stock management through automatic object detection, aiming to reduce the risk of out-of-stock situations.

Risk Analysis of Using the ESPK Program PT Konimex Sukoharjo Using the Octave Allegro Method

2025-01-21T07:23:45+00:00

This study analyzes the risks associated with the ESPK (Electronic Calibration Request) Program at PT Konimex Sukoharjo using the Octave Allegro method. The ESPK program is utilized for calibration processes, and the research aims to determine whether the program poses potential risks to the company. The Octave Allegro method is used to evaluate threats and information security risks, enabling the organization to make decisions based on risks to the confidentiality, integrity, and availability of critical information assets. Data obtained indicate a Relative Risk Score of 28, meaning the risks can be mitigated or postponed. The findings involve users of the ESPK program, such as calibration admins, validation officers, calibration technicians, information system managers, and the owners of calibrated equipment. Key risks identified include data input errors, server downtime or maintenance during working hours, and incomplete program features. All these risks can either be mitigated or postponed. In conclusion, PT Konimex has not previously conducted a risk analysis on the ESPK program, and the Octave Allegro method identifies threats and risks for better protection of information assets.

Aplikasi Pendeteksi Kematangan Tanaman Menggunakan Metode Transformasi Ruang Warna HSI (Hue, Saturation, Intensity) dan K-NN (K- Nearest Neighbor)

2025-01-21T07:22:26+00:00

Tomatoes and chili peppers are essential commodities in the agricultural and food industry, playing a crucial role in nutritional diversity and flavor in human diets. Identifying the ripeness of these fruits is a critical step in the food supply chain, yet it is often done manually by directly observing the ripeness of chilies and tomatoes, which is time-consuming and susceptible to observer subjectivity. Therefore, a system that can identify the ripeness of tomatoes and chili peppers is needed. This system implements the HSI color space extraction method and the K-NN method. K-NN can classify plants based on colors extracted using the HSI color space, which includes three dimensions: Hue (H), Saturation (S), and Intensity (I). The research results in a model from the tomato and chili pepper dataset with an accuracy of 92% and a data split ratio of 80%:20%. This model is implemented in web and mobile formats, expected to efficiently and accurately identify the ripeness of tomatoes and chili peppers. This can help farmers determine the optimal harvest time, improve agricultural production and quality, and provide more reliable information in the food supply chain

Hoax News Detection in Indonesian Political Headlines Using Multinomial Naive Bayes

2025-01-21T07:24:47+00:00

Social media is a means of online social interaction on the Internet, where users can freely share information. Because of the freedom, it cannot be denied that some people will misuse social responsible for misusing social media as a place to spread false news. Based on a survey of 2,032 respondents conducted by DailySocial.id in 2018, it was concluded that the majority of Indonesians do not have the ability to detect hoax news. Therefore, the research aims to design and build a hoax news detection application using the Android-based Multinomial Naive Bayes algorithm. At the design stage, the application is designed to receive input in the form of textual political news headlines. It then uses the Multinomial Naive Bayes algorithm to detect hoaxes by comparing the resulting text with data sets. In the testing phase, the algorithm is tested on a confusion matrix and shows the degree of hoax detection. The accuracy of the hoax detection is 88.9%, the precision is 93.33%, the recall is 84%, the recall is 84%, and the F1 score is 88.4%. With a detection application, it is hoped that this hoax news will be able to contribute to the online environment of the Indonesian people by verifying the information before sharing it on social media.

Metode Profile Matching Sistem Pendukung Keputusan Untuk Menentukan Orang Dalam Gangguan Jiwa

2025-01-21T07:22:57+00:00

The Profile Matching method is a technique in decision support systems that is used to analyze the conformity of criteria with predetermined standards. In the context of determining mental disorder status, this method plays a role in identifying individuals based on certain mental health criteria. The process involves comparing an individual's profile with a standard profile that describes the characteristics of mental disorders. The criteria analyzed include aspects of the indicators, namely; Emotional, Physical, Behavioral and Psychological relevant to mental health. This method is able to provide objective recommendations because it uses weight-based calculations for each criterion. This Profile Matching-based decision support system can help health workers and decision makers at the village level to identify and group individuals with mental disorders, so that appropriate interventions can be determined. With this system, the process of evaluating people's mental health conditions can be carried out more accurately and efficiently. This method is one method of determining the indication that a person is classified as an ODGJ with the indicators, namely; Emotional, Physical, Behavioral and Psychological. Based on research results from 5 patients who were tested using the Profile Matching method, the following results are in the highest order; Patient F had the highest score, namely 3.7, patient R, namely 3.4, patient C, namely 3.3, patient S, namely 3.2 and the smallest was patient A, namely 3.0. It is hoped that it can increase early detection of mental disorders, as well as speed up follow-up treatment or referral to further mental health services.

A Performance of Generative Pre-Trained Transformers (GPT) in Answering Questions on Anatomy in The Turkish Dentistry Specialization Exam

2025-01-21T07:22:42+00:00

Artificial intelligence based programs are used in various fields of daily life, often without our awareness. With the increasing integration of artificial intelligence applications into the educational system, accessing information has become faster. As a result, chat programs that produce text-based answers similar to those of humans are being used as educational tools. The accuracy of the content generated by these programs has always been a topic of interest. In our study, we evaluated the success of ChatGPT, Gemini, and Copilot applications in answering dental specialty exam anatomy questions from 2012-2021. In the computer environment, free versions of ChatGpt-4, Google Gemini and Microsoft Copilot were accessed. The responses were recorded as either correct or incorrect. Out of 74 anatomy questions ChatGPT, Gemini and Copilot gave 2, 10, and 1 incorrect answers, respectively. Although the evaluated programs showed sufficient success in answering anatomy questions, their use was deemed limited due to errors in the supplementary information they provided.

A Researcher’s Journey from Traditional Qualitative Methods to Tech-Driven Insights

2025-01-21T07:23:13+00:00

The integration of technology into qualitative research has revolutionised traditional methods, providing researchers with new opportunities and challenges. This paper compares the effectiveness, strengths, and limitations of traditional versus technology-based methods for recruiting participants, conducting interviews, and transcribing data, based on the personal experiences of the researchers. The findings reveal that while traditional face-to-face interviews enable deeper personal interaction and richer data collection, they are often time-consuming and logistically challenging. In contrast, technology-based methods offer increased accessibility, efficiency, and flexibility, particularly when recruiting participants and conducting interviews among geographically dispersed populations. However, these methods may compromise the depth of data due to the challenges of maintaining non-verbal cues and transcription accuracy, particularly when using automated transcription tools. This paper recommends a hybrid approach that combines the strengths of both methods. Best practices for using technology in qualitative research are proposed to ensure the richness and contextual depth of the data while leveraging the benefits of modern tools.

Analisis User Experience Tiktok Shop Menggunakan Framework Heart dan Importance Performance Analysis

2025-01-21T07:22:10+00:00

The rapid evolution of social media usage in Indonesia, particularly on TikTok, has marked a significant shift in online interaction. Despite initial controversies over negative content, TikTok's popularity surged in 2019 due to features such as the For You Page (FYP), dance challenges, and the increased online activity during the COVID-19 pandemic. Expanding its scope, TikTok introduced e-commerce features, including TikTok Shop, positioning itself as one of Indonesia's leading social commerce platforms. This study analyzes the user experience (UX) of TikTok Shop using the HEART framework (Happiness, Engagement, Adoption, Retention, and Task Success) combined with Importance Performance Analysis (IPA). Data was collected through questionnaires distributed to TikTok Shop users to identify key indicators for enhancing user experience and correlating these with the user interface (UI) of the TikTok Shop menu. Results revealed significant findings in the Cartesian diagram, with key metrics in Quadrant II including H1 (3.767%), H3 (2.31%), A1 (3.767%), and T7 (1.856%). Redesign recommendations were implemented for items categorized as Action and positioned in Quadrants II and III. Post-redesign testing showed a notable improvement, with an average performance increase of 12.1% compared to the initial evaluation. These findings offer insights into optimizing the TikTok Shop interface to enhance user satisfaction and engagement.

Similarity Judul Tugas Akhir Menggunakan Metoda Cosine, Jaccard, Rabin-Karp Pada Jurusan TI

2025-01-21T07:24:31+00:00

Plagiarism can occur anywhere and can be committed by anyone. For example, plagiarism by students when creating college assignments, where they unintentionally use someone else’s writing or ideas and forget to cite the source. Based on the above explanation, it is necessary to develop an information system to assess the percentage of plagiarism for proposed titles. After conducting an implementation test to measure the similarity accuracy and processing speed, a comparison was made between the proposed titles and the existing data, totaling 940 titles. The results showed a similarity rate of 84.13% with the Rabin-Karp method, 61.24% with the Cosine method, and 42.86% with the Jaccard method. In terms of processing speed, the Rabin-Karp method ranked first with a time of 0.5023 seconds, followed by the Cosine method with 0.5095 seconds, and the Jaccard method with 0.5103 seconds. From the test results, Jaccard Similarity is more suitable for short texts with unique word sets, but it is less precise for longer texts with important word distributions. Meanwhile, the Rabin-Karp method is not designed to measure general text similarity; instead, it is intended for fast and precise substring searches in pattern matching contexts

Klasifikasi Citra Dalam Identifikasi Jeruk Nipis dan Jeruk Mandarin Menggunakan Convolutional Neural Network (CNN)

2025-01-21T07:25:03+00:00

With the rapid development of technology in the field of image processing, it really helps farmers in identifying types of citrus fruit. This research aims to identify the differences between limes (Citrus aurantiifolia) and mandarin oranges (Citrus reticulata) using image processing methods and morphological analysis. Image processing is carried out to analyze visual differences based on color, texture and fruit size. In addition, chemical analysis was carried out to differentiate the composition of the compounds contained in the two types of oranges. The research results show that this approach is able to identify the differences between limes and mandarins with a high level of accuracy, and can be applied in various industries, including agriculture and food processing.