Child heart image segmentation is a crucial step in medical analysis for the diagnosis of heart diseases. In this study, we utilize the You Only Look Once (YOLO) method for the segmentation of child heart images. YOLO is a well known deep learning model in object detection due to its ability to perform real time detection with high accuracy. We collected a dataset of child heart images, perform…
This research aims to compare two methods, namely 1 Dimension Convolutional Neural Networks (1DCNN) and Decision Tree, in detecting traffic violation rates in the city of Palembang. This study also uses You Only Look Once version 8 (YOLOv8) to count the number of vehicles to be detected based on video recordings, resulting in a model and obtaining an F-1 confidence score of 82%. The 1 Dimension…
Support Vector Machine (SVM) is a machine learning algorithm that falls into the category of supervised learning. SVM works by constructing an optimal hyperplane that separates two classes in a feature space. This hyperplane is chosen in such a way that it has a maximum margin, which is the largest distance between data points from both classes. In addition to the hyperplane, hyperparameters ar…
Skripsi yang berjudul: Perlindungan Hukum Terhadap Anak Yang LahirDari Perkawinan Beda Agama Pasca Diberlakukannya Surat Edaran Mahkamah Agung Nomor 2 Tahun 2023. Terhitung hingga tahun 2023 total ada 188 kasus perkawinan beda agama yang dimohonkan di Pengadilan Negeri dan telah diputuskan untuk didaftarkan di Kantor Catatan Sipil. Kondisi ini menjadi persoalan ketika diterbitkannya Surat Edara…
Between 20 and 50 million people suffer non-fatal injuries in road accidents every year, while more than a million of these incidents cause death. Road traffic crashes are a significant menace not only to the economy but also to public health. The numbers obtained are objective statistics not subject of personal opinion. This research aims to develop a clustering model using a machine learning …
This research aims to predict the types of school buses in Jakarta using machine learning methods. Data from 2017 to 2019 includes the number of passengers, the number of schools, and bus types. Exploratory data analysis identified patterns and trends, with feature engineering generating three main variables. We tested seven machine learning models, including SVM, Logistic Regression, KNN, Gaus…
The delineation of ECG signals is often hindered by noise, such as baseline wandering and electrode motion. This study presents a robust model for ECG signal denoising and delineation into four classes: baseline, P wave, QRS complex, and T wave, using data from multiple sources. The denoising model, based on a Multibranch LANLD architecture, was trained with noisy signals from NSTDB and clean l…
Di era digital saat ini, teknologi merupakan bagian penting dalam kehidupan sehari-hari, yang juga meningkatkan risiko kejahatan siber. Trojan Horse adalah jenis malware yang menyamar sebagai program sah sehingga dapat diunduh ke komputer atau perangkat seluler. Dalam penelitian ini, penulis mengusulkan metode Gated Recurrent Unit (GRU) untuk mengklasifikasi malware dengan menggunakan dataset C…
A botnet is a collection of devices infected with malware and controlled externally by an attacker to carry out network attacks, such as DDoS attacks, data theft, or spreading spam. This research uses a dataset from CICIoT2023 which consists of three types of classes, namely, tame traffic, mirai greip flood, and mirai udpplain to detect botnet malware attacks using the Support Vector Machine me…
A Mirai Botnet is a computer network consisting of thousands or millions of internet connected devices that have been hacked by the mirai malware. The purpose of the Mirai Botnet is to control Internet of Things (IoT) devices with weak security to infect the device and turn it into a botnet that can target other devices through Distributed Denial of Service (DDoS) attacks that can paralyze web …
The Gumay Mountains area topographically, it is in the elevation range of 200 to >1000 meters above sea level, with various types of slopes that vary. This landslide analysis observation uses two methods, namely NDVI and relief diversity. NDVI stands for Normalized Difference Vegetation Indices, an analysis that uses vegetation as its main index or parameter. In this case, the presence of veget…
In this growing modern era, IoT (Internet of Thing) networks have become a new era in IoT networks aimed at expanding the utilization of internet connectivity that is connected continuously. Low Power Lossy Network is part of the IoT network but has limited power and data packets are often lost, short transmission range and low bandwidth can cause waste of power that occurs. Therefore, this res…
In the era of rapidly developing technology, the Internet of Things (IoT) Network is one of the main applications driving the evolution of the Internet towards the Internet of the Future. LLN (Low Power Lossy Network) is an IoT network that has limited power and also has a low bandwidth which can make excessive energy usage and inappropriate data packet delivery a problem that often occurs on t…
Routing Protocols for low-power networks such as Wireless Sensor Networks suffer from decreased depth, increased control overhead, longer latency and higher energy usage. Path selection suffers from the problem of less stability as packet delivery failures are more frequent as nodes are very close to each other in dense networks. Laplacian Routing Protocol low power lossy network (L-RPL) is a p…
This research will discuss about energy consumption and usage intensity in Smarthome lighting system and efficiency in its application to evaluate the effectiveness with optimization. The purpose of this research is power transition, measurement and evaluation of efficiency effectiveness. This research uses the Optimization method with Load Monitoring (NILM) and Energy Consumption Analysis to m…
A routing protocol (RPL) specifically designed for networks with low power and high loss, such as Wireless Sensor Networks. RPL can be optimized for Energy Efficiency, due to limited resources and weak connections, the probability of network disconnection is quite high.This will cause losses resulting in more amount of energy consumption at the nodes to retransmit the packets. In this regard, R…
Seiring berkembangnya teknologi, model deep learning kini dapat digunakan untuk mengimplementasikan proses segmentasi dan klasifikasi citra. Penelitian ini bertujuan untuk mengembangkan model segmentasi dan klasifikasi kanker serviks menggunakan arsitektur U-Net Convolutional Neural Network (CNN). Model U-Net dikembangkan untuk melakukan segmentasi jaringan serviks dan memisahkan area yang menc…
T Wave Alternans (TWA) dikaitkan dengan beberapa penyakit dan deteksi akuratnya yang dapat mengdiagnosis lebih dini mengenai komplikasi jantung. Penelitian ini menggunakan data dari QT Database (QTDB) dan T Wave Alternans Database (TWADB). QTDB digunakan untuk proses training untuk pengujian model sedangkan dataset TWA digunakan untuk proses pengujian. Delineasi terhadap sinyal EKG secara otoma…
Perbandingan dilakukan antara data media sosial terhadap data angka kendaraan dari kamera CCTV Dirlantas Polda Sumsel menggunakan algoritma Naïve Bayes. Data media sosial dikumpulkan dengan teknik scrapping menggunakan Tweet Harvest, kemudian melalui proses preprocessing dan metode TF-IDF lalu diklasifikasikan menggunakan Naïve Bayes. Sedangkan data angka kendaraan, dilatih menggunakan model …
Blockchain is a distributed database in which information sent by users is periodically verified and grouped into blocks, thus forming a chain. CITA (Cryptape Inter-enterprise Trust Automation) is a high-performance blockchain system for enterprises with 6 microservices (RPC, Auth, Consensus, Chain, Executor, Network) that exchange information via Message Bus. The process of data retrieval, dat…
Spyware is a type of malicious software that can collect information about a person or organization without permission. Typically, spyware is installed accidentally through malware or downloaded from the internet without the user's knowledge. Spyware is particularly dangerous because it targets computers and gadgets, posing serious risks to privacy and data integrity. Spyware can collect sensit…
Penelitian ini bertujuan untuk mengembangkan model klasifikasi yang akurat untuk mengidentifikasi dan mengkategorikan lalu lintas anonim pada jaringan Tor. Dataset yang digunakan adalah CIC-Darknet2020. Teknik Synthetic Minority Over-sampling Technique (SMOTE) diterapkan untuk menangani ketidakseimbangan kelas, sementara Mutual Information Classifier (MIC) digunakan untuk seleksi fitur. Model K…
Perkembangan teknologi internet yang pesat telah menyebabkan meningkatnya aktivitas judi online yang berpotensi mengancam keamanan data dan ketertiban digital. Penelitian ini bertujuan untuk mendeteksi pola akses terhadap situs judi online melalui analisis informasi Server Name Indication (SNI) pada protokol SSL/TLS menggunakan metode Support Vector Machine (SVM). Proses penelitian mencakup pem…
This study examines the implementation and analysis of Dynamic Traffic Management on Software Defined Network (SDN) networks with performance assessment through Quality of Service (QoS) parameters using the t-Test method. The aim is to assess the impact of implementing dynamic traffic management on network performance by comparing conditions before and after the use of intent based routing on t…
The development of the Internet of Things (IoT) has brought convenience to human life through the smart home concept, which enables various devices to be interconnected and controlled automatically. However, this increased connectivity also poses security threats, particularly cyberattacks such as Distributed Denial of Service (DDoS), Denial of Service (DoS), and Man-in-the-Middle (MiTM). This …
The development of smart home technology enables users to control and monitor household devices automatically through the Internet of Things (IoT). However, this high connectivity also increases the risk of cyberattacks such as Distributed Denial of Service (DDoS) and Man in The Middle (MITM), which can compromise system stability and security. This study aims to detect DDoS and MITM attacks in…
Penelitian ini bertujuan membangun model klasifikasi kondisi lalu lintas menggunakan data dari sosial media (Instagram dan Facebook) serta data ETLE dengan arsitektur Long Short-Term Memory (LSTM). Dari total 1.251 data sosial media yang dikumpulkan, sebanyak 932 data dipilih berdasarkan kemunculan kata kunci “macet”, “sedang”, dan “lancar”. Data ini kemudian dibagi menjadi data lat…
This study aims to implement the You Only Look Once (YOLOv8) method for detecting acne in acne vulgaris images. Automatic detection of acne types is essential to support rapid, accurate, and efficient dermatological diagnosis. The research involves designing a YOLOv8-based detection model, which includes the stages of collecting and annotating facial image datasets, preprocessing, model trainin…
The rapid growth of Internet of Things (IoT) devices in smart home environments increases convenience but also introduces various network security threats, such as Distributed Denial of Service (DDoS) and Man in The Middle (MITM) attacks. This study aims to implement and evaluate the performance of the Extreme Gradient Boosting (XGBoost) algorithm in detecting DDoS and MITM attacks on IoT netwo…
This study developed the YOLOv8 model to detect five object classes, with training results showing an accuracy of 95%, an f-1 score of 89%, and mAP@0.5 of 93.1%. In the testing phase, the model achieved an accuracy of 93.83%, an f-1 score of 83%, and mAP@0.5 of 86.7%. Vehicle counting using YOLOv8 and DeepSORT on 72 videos showed an average accuracy of 95.51% for motorcycles and 79.02% for cars…