Flight departure delays affect operational efficiency and the quality of air transportation services. This study compares the performance of the Artificial Neural Network (ANN), ANN optimized using Particle Swarm Optimization (ANN-PSO), and ANN optimized using Genetic Algorithm (ANN-GA) for flight delay classification using a two-class dataset, namely on-time and delayed flights, based on opera…
This research was conducted because departure delays on the Light Rail Transit can reduce passenger comfort and satisfaction. Therefore, a predictive model that can estimate delays accurately is needed. The purpose of this study is to implement, compare, and determine the best machine learning algorithm for predicting LRT departure delays in Canberra. The dataset used consists of static and rea…
Traffic accidents are a serious public safety issue that requires data-driven analytical approaches. This study aims to classify traffic accident severity into three classes, namely fatal, serious, and slight, using machine learning algorithms. Four algorithms are evaluated: Random Forest, Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). M…
The rapid adoption of Cyber-Physical Systems (CPS) has improved operational efficiency across critical sectors but has simultaneously increased exposure to cyber threats, particularly Man-in-the-Middle (MITM) attacks that covertly intercept and manipulate communication. In CPS environments, such attacks pose serious risks to system reliability and operational safety, thereby requiring security …
Cloud computing provides dynamic computing resources over a network. However, an increasing number of user requests can lead to higher server workloads and decreased service performance. This study aims to analyze the performance of load balancing using the Least Connection method with HAProxy as the load balancer. The system was implemented in a VMware-based virtual machine environment consist…
Accurate and efficient ship detection has become an urgent necessity amid increasing maritime activities, including security monitoring, law enforcement, and maritime traffic management. This study aims to implement the Faster R-CNN (Region-based Convolutional Neural Network) method for ship detection to improve efficiency and accuracy compared to conventional methods. The data used in this stu…
Penelitian ini bertujuan untuk menganalisis pola kecelakaan lalu lintas di Kota Palembang menggunakan pendekatan machine learning berbasis clustering. Data sekunder diperoleh dari catatan resmi Kepolisian Kota Palembang mencakup periode 2021–2024 dengan total 2.658 data dan 35 variabel awal. Setelah melalui proses prapemrosesan, dilakukan pembersihan data, penghapusan variabel yang tidak rele…
Penelitian ini bertujuan mengidentifikasi pola tingkat kerawanan kriminalitas pencurian kendaraan bermotor (curanmor) di Kabupaten Musi Banyuasin menggunakan pendekatan unsupervised learning. Empat algoritma clustering ini, yaitu K-Means, DBSCAN, Hierarchical Clustering, dan Gaussian Mixture Model digunakan untuk mengelompokkan data kejadian kriminal berdasarkan variabel jenis kendaraan, jumlah…
Botnets are a serious cyberattack threat that infects computer networks controlled by botmasters to carry out malicious activities. Various types of botnets have emerged over the years, posing a significant threat to cybersecurity. These botnets' malicious activities vary from executing instruction-based attacks such as DDoS attacks, flooding, and spamming. This study used the CICIoT2023 datase…
Denial of Service (DoS) attacks pose a serious threat to IPv6-based smart home networks, causing disruptions in device connectivity and significantly reducing system performance. This study aims to detect DoS attacks in IPv6 smart home networks using the Logistic Regression machine learning algorithm. The dataset was generated from network traffic captured using the THC-IPv6 tool, followed by f…
Supply Chain Management involves several parties who play a role in the process of delivering goods or services so it requires transparency regarding transaction records for all parties involved with the aim of avoiding falsification of transaction data. To overcome this problem, this research aims to build a security system using the Proof-of-Stake (poS) method. A collection of blocks containi…
The development of smart home technology provides convenience for users in managing household devices automatically and through internet connectivity; however, it also raises potential security threats, such as SSL Pinning Bypass, which allows attackers to intercept communications, and Distributed Denial of Service (DDoS) attacks, which can disrupt service availability. To address these issues,…
Maximal Extractable Value (MEV) bot activity on blockchain networks poses a significant challenge, as MEV bots exploit transaction-processing mechanisms to gain profit in ways that may hinder fairness, increase gas fees, and disrupt network stability. This study employs the Extreme Gradient Boosting (XGBoost) model to classify MEV bot activity in Ethereum blockchain transactions using numerical…
This study aims to detect and classify Distributed Denial of Service (DDoS) and Man-in-the-Middle (MiTM) attacks in smart home networks using the Light Gradient Boosting Machine (LightGBM) algorithm. With the rapid growth of Internet of Things (IoT) devices, cybersecurity challenges have become crucial due to vulnerabilities in smart home devices. This research utilizes the COMNETS SMARTHOME da…
The advancement of Internet of Things (IoT) technology has brought significant changes to everyday life, especially through the adoption of smart home devices. The use of smart homes is growing rapidly because it can help make housework easier. However, the increasing use of these devices also increases cyber threats. Some dangerous threats are SSL Pinning Bypass and MITM. In this study, we wil…
This research aims to compare the performance of the Random Forest and Support Vector Machine methods in analyzing Facebook data sentiment related to traffic congestion in Palembang City. Data was obtained through a web scraping process and labeled using a lexicon-based approach into three sentiment classes, namely positive, negative, and neutral. Feature representation was performed using the …
This study aims to analyze public sentiment toward traffic congestion in Palembang City based on Facebook social media comments using the Naïve Bayes algorithm. Data were collected through web scraping of Facebook comments related to traffic conditions in Palembang and labeled using a lexicon-based approach into three sentiment classes: positive, negative, and neutral. The dataset consists of …
The increasing number of APKs in mobile technology each year often coincides with the emergence of APKs containing malware. Through the Metasploit framework, threat actors are able to embed payloads into benign APKs. To address this issue, forensic investigation on mobile devices becomes crucial. This research aims to conduct forensic analysis on Android devices infected with Trojan APKs, apply…
Tanaman anggur merupakan komoditas hortikultura bernilai ekonomi tinggi yang rentan terhadap serangan hama belalang, sehingga diperlukan sistem identifikasi yang cepat dan akurat. Penelitian ini bertujuan untuk mengimplementasikan sistem klasifikasi hama belalang pada tanaman anggur berbasis Internet of Things (IoT) menggunakan metode machine learning. Sistem dikembangkan dengan mengombinasikan…
Kematangan buah anggur merupakan faktor utama dalam menentukan kualitas dan nilai jual buah karena berpengaruh langsung terhadap rasa, tekstur, dan tingkat kesegaran. Penilaian kematangan buah anggur secara manual masih memiliki keterbatasan karena bersifat subjektif dan bergantung pada pengalaman manusia. Penelitian ini bertujuan untuk merancang dan menganalisis sistem klasifikasi kematangan b…
Pertanian anggur di Indonesia menghadapi tantangan serius akibat serangan hama yang menurunkan kualitas dan kuantitas hasil panen, sehingga diperlukan sistem deteksi yang cepat dan akurat. Penelitian ini bertujuan mengimplementasikan metode Convolutional Neural Network (CNN) berbasis MobileNetV2 yang terintegrasi dengan Internet of Things (IoT) untuk mendeteksi dan mengklasifikasikan hama pada …
This research presents the implementation and evaluation of a LightWeight Vision Transformer (ViT) architecture for classifying seven different types of skin cancer using medical dermoscopic images from the HAM10000 dataset. The methodology includes data preprocessing, class balancing using Random Oversampling, and splitting the dataset into training and testing sets. Several hyperparameter con…
The rapid advancement of deepfake technology poses significant challenges, as it enables the generation of highly realistic synthetic facial images that are increasingly difficult to distinguish from authentic ones. This development raises substantial concerns regarding information verification and biometric security. This study aims to address these issues by implementing a deepfake detection …
Traffic congestion is a recurring issue in Palembang City and significantly affects the daily activities of its residents. Social media, particularly Facebook, serves as a platform for the public to express their opinions and complaints regarding traffic conditions. This study aims to analyze public sentiment toward traffic congestion in Palembang City using the Random Forest algorithm. The res…
This study aims to design and develop an Internet of Things (IoT)-based smart door system that integrates automatic door security and digital attendance. The system uses RFID technology for access authentication and NodeMCU as the main microcontroller that connects devices to the internet. By scanning a registered RFID card, users can automatically unlock the door, and attendance data is record…
Cities around the world, including the City of Palembang, are facing increasing challenges in terms of transportation management. Population growth, urbanization and continuous population mobility have led to increased traffic, congestion and challenges in achieving efficient mobility. So a research was carried out using various models and algorithms in the context of object recognition, vehicl…
Penggunaan layanan cloud telah menjadi semakin populer dalam beberapa tahun terakhir, memicu peningkatan permintaan terhadap sumber daya cloud computing yang lebih besar dan efisien. Hal ini menimbulkan tantangan baru dalam mengelola beban kerja yang semakin kompleks dan beragam. Penelitian ini bertujuan untuk memvalidasi efektivitas metode load balancing MTBLB (Multi-time Based Load Balancing)…
GrabFood, makes it easier for consumers to buy food and beverages without having to go to a restaurant. The competition between GrabFood and its competitors is currently growing rapidly. Therefore, GrabFood implements CRM activities by promoting various promotions and foods through social media platforms using the Instagram account @grabfood.id. This study focuses on examining whether activitie…
Pada masa kini semakin meningkat pengguna internet yang mengakses website pada waktu tertentu yang mana dapat menyebabkan kinerja web server menjadi buruk hingga mengalami downtime. Maka dari itu diperlukan sebuah sistem yang dapat aktif menjalankan web server secara terus menerus tanpa gangguan, yaitu Kubernetes. Kubernetes menerapkan cluster based yang terdiri dari satu node master dan bebera…
Proses labelisasi manual pada citra USG merupakan tugas yang menantang dikarenakan memerlukan ketelitian tinggi dan waktu yang lama. Sehingga labelisasi otomatis dengan deep learning dapat menjadi solusi. Penelitian ini bertujuan untuk mengetahui performa segmentasi dan labelisasi otomatis dengan menggunakan deep learning. Data dari penelitian menggunakan pemeriksaan USG pada jantung janin berj…