This study aims to design and build a website-based employee attendance application using QR Code with PHP and MySQL at the Mediska Prabumulih Health Clinic. The manual attendance system that has been used so far is prone to data manipulation and is less effective in supporting employee discipline. With the Waterfall development method, this application is expected to facilitate real-time atten…
Instagram is one of the most popular social media platforms that is not only used to share pictures and videos, but also as a means of discussion on various social, political and cultural issues. One of the most active and influential accounts in Indonesia is the Mata Najwa account, which often triggers public discussion through the comments section. The large number of incoming comments create…
Administrative services at Plaju Darat Subdistrict are still carried out manually, often causing long queues and inefficiency. To address this issue, a web-based queuing application was developed using the prototype method and CodeIgniter framework. This application allows residents to take queue numbers online and helps staff manage queue data efficiently. Test results show that the system fun…
Eczema, or Atopic Dermatitis, is a skin condition often triggered by certain allergens in food. The increasing prevalence of eczema requires a solution to help individuals prone to allergies recognize potential allergens in packaged food products. This study aims to develop a food composition classification system to detect allergens that may trigger eczema using the Long Short-Term Memory (LST…
The abundance of digital information in today's era makes the extraction of relevant information a major challenge, especially in Indonesian, which has unique linguistic characteristics. As an effort to overcome this challenge, this study develops an extractive question-answering system for Indonesian text by fine-tuning the IndoBERT model, which enables the system to extract specific parts of …
Detection of plant diseases through visual observation of leaves manually has several limitations and takes a long time. This research develops an Android application-based plant disease detection system that can identify plant diseases through leaf images using the Convolutional Neural Network (CNN) algorithm. The dataset used in this research comes from Kaggle Disease Classification, which co…
Social media has become an important platform for users to interact, share opinions, and share information. However, it increases the risk of spreading harmful content such as hate speech and abusive language, which harms individuals and the online environment. This research aims to classify hate speech and abusive language using the Support Vector Machine method. The data used in this research…
Keyphrase play an important role in applications such as information retrieval, text summarization, recommendation systems, and indexing of scientific documents. However, the automated process of generating key phrases still faces major challenges, especially when faced with complex English scientific articles rich in technical terms. Transformer-based generative approaches often produce phrase…
Hoax news poses a serious threat in the current digital environment as it harms society by disseminating false and misleading information. Detecting hoax news is essential to maintain the integrity of information, prevent the spread of misinformation, and safeguard public safety. This research adopts a classification approach to hoax news based on LSTM (Long Short-Term Memory) with the utilizat…
Communication media such as SMS (Short Message Service) is now rarely used, but SMS is still needed because it can still be useful for users in receiving information. However, problems arise due to fraudulent messages. Thus, SMS classification becomes important by using the Synthetic Minority Oversampling Technique (SMOTE) method which can balance unbalanced data, Mutual Information (MI) which …
The era of globalization has driven intense competition among businesses, forcing them to become smarter in fulfilling customer demand. One strategy adopted by companies is using machine learning to predict customer demand. This study focuses on the use of the Prophet algorithm developed by Meta or Facebook and published in 2017. The Prophet algorithm is resilient to missing data, changes over …
This study aims to design and build a website-based booking application system in Plaju Darat Village, with the main objective of increasing efficiency in administration and service to the community. The problem currently faced is that the booking process is still done manually, so it requires a lot of time and energy. The proposed solution is the development of a website-based application that…
The transaction process currently used at the Pempek Ceria Rasa store still relies on a manual system, depending solely on handwritten records in transaction books. This often leads to errors in writing and calculation, including mistakes in order quantities and total costs. The purpose of this research is to develop an online-based ordering system. The benefits include assisting the ordering p…
Until now, the management of official letter administration has faced numerous shortcomings, due to the administrative processes for assignment letters, director's decrees, leave permits, internal memos, and circular letters being managed and stored in separate document files. This makes it difficult to search for and update information, and increases the risk of errors in data management. The …
The rapid growth of the film industry in recent years has created a need for an accurate age classification system to ensure that content is appropriate to its target audience. One approach that can be used to identify the age classification of a film is through analysis of the subtitle text, without relying on visual or audio elements. This study aims to compare the performance of two classifi…
Sayurbox is an e-commerce application that provides fresh products directly from farmers to consumers. To understand user perception namely how users express their evaluations of the services and experiences when using the application this study conducts sentiment analysis on user reviews of Sayurbox from the Google Play Store using three classification algorithms: Naïve Bayes, Support Vector …
The Palembang City Environmental Agency is still using a conventional system, so it is not optimal in retrieving information data to assess service satisfaction surveys. The purpose of this research is to build a service satisfaction survey application that can help facilitate filling out surveys, managing survey data, and analyzing survey data. This application is designed to have three types …
This study aims to develop a website as an information and promotion medium for the QLC Musthofaynal Akhyar Tahfidz Boarding School in Palembang. The website replaces the previously manual and verbal method of information sharing. Development used the Waterfall method, covering analysis, design, implementation, and testing stages. Built with PHP and MySQL, the site includes an admin dashboard t…
Al Amalul Khair Islamic Boarding School still uses conventional methods in scheduling lessons, which often causes errors and delays in information. This research aims to build a website-based scheduling application to facilitate schedule management. This application has three types of users, namely admins as schedule compilers, teachers, and students as recipients of information. Development us…
A website-based information system for community service repository and publication was built to support the Informatics Management Study Program at Sriwijaya University in managing and disseminating information related to community service activities. This system aims to simplify data management for administrators and provide easy access to information for users. It was developed using the Wat…
The implementation of teacher-on-duty tasks at SMK Bina Cipta Palembang is still carried out manually, especially in recording student permissions to leave or go home during school hours. This manual process is prone to data loss, recording errors, and makes it difficult to search and generate reports. To address this issue, a web-based teacher-on-duty application was developed using the protot…
The Informatics Management Study Program currently does not have an integrated system for managing accreditation documents. Until now, data management has been carried out manually, making the process of searching for and storing documents less effective and efficient. To address this issue, the author developed a web-based accreditation document management system by leveraging information tech…
Keyphrase Generation is a task in Natural Language Processing that aims to extract keyphrases that represent the main content of a document. The increase in the number of scientific publications has made the manual annotation process inefficient and prone to subjectivity. Therefore, Automated Keyphrase Generation (AKG) has become a relevant approach to support more efficient scientific informat…
Text pre-processing is increasingly important in the era of rapidly growing digital information One of the important stages in text processing is stemming, which aims to convert words to their basic form by cutting off certain prefixes or suffixes. The Indonesian stemming algorithm that is often used is Sastrawi. To improve the accuracy and efficiency of the stemming process, this research modi…
Penelitian ini menerapkan algoritma FP-Growth untuk menganalisis Pola Pembelian Konsumen di Tamken Resto & Cafe di Palembang. Dengan fokus pada FP-Tree dan Association Rules, analisis dilakukan pada 9.371 data transaksi, menghasilkan 341 pola pembelian dengan minimum support 0,25% dan minimum confidence 50%. Pentingnya FP-Tree dan Association Rules terlihat dalam kemampuannya memberikan keterka…
Diabetes is a chronic disease with a continuously increasing global prevalence. Early detection poses a major challenge because symptoms often appear only when the condition is already severe. The classification of diabetes plays a crucial role in recognizing the disease early to allow for faster and more accurate interventions. According to data from the World Health Organization in 2020, over…
Detection, is an action or process of identifying the presence of something that is concealed. This research aim to develop a software that can be used to detect the similarity between thesis using the K-Means Clustering method, which is one of the simplest and popular unsupervised machine learning algorithms. In this research the detection is done on 56 documents using the silhouette method to…
The problem of vehicle scheduling and route optimization in food product distribution is a complex logistical challenge, especially when considering customer time window constraints and vehicle capacity. This study aims to implement a combination of Ant Colony Optimization (ACO) and Nearest Neighbor (NN) to solve the Vehicle Routing Problem with Time Windows (VRPTW) in the distribution system o…
Product distribution is an important part of the supply chain, as the timeliness of delivery has a significant impact on customer satisfaction and operational efficiency. This study aims to optimize delivery routes in the context of the Vehicle Routing Problem With Time Windows (VRPTW) problem, which is a distribution scheduling problem that considers the customer service deadline and the maxim…
Information about services at PT Asabri is still less touched by participants. This is due to the lack of human resources, especially customer service in serving participants. To overcome these problems, a question and answer system is needed to get more interactive information in order to help customer service in carrying out their duties. In this research, the system developed uses the rule- …