Abstract:Abstract: The implementation of dress code regulations in university environments is generally still carried out conventionally, requiring significant time and effort and potentially leading to subjective assessments. This…
is study develops an automatic student dress code compliance detection system using computer vision based on the YOLOv8 model. The dataset consists of 1,800 annotated images divided into eight clothing categories, split into 78% training (1,404 images), 14% validation (254 images), and 8% testing (143 images). All images underwent preprocessing and data augmentation before training the YOLOv8 model with an input size of 640×640 pixels for 50 epochs. During testing, the YOLOv8 model achieved an overall performance of Precision 0.844, Recall 0.773, F1-Score 0.802, and mAP@0.5 0.841, and was able to detect clothing objects with good accuracy and stable performance under various image conditions. The system was integrated with a Flask-based backend and a web-based frontend to enable real time detection and compliance classification, with a response time of less than 2 seconds, supporting automatic and consistent identification of student dress code compliance as “Compliant” or “Violation.”
Keywords: compliance detection; computer vision; dress code regulations; real time detection; YOLOv8.
Abstrak: Penerapan aturan berpakaian di lingkungan kampus umumnya masih dilakukan secara konvensional sehingga membutuhkan waktu dan tenaga yang relatif besar serta berpotensi menimbulkan subjektivitas penilaian. Penelitian ini bertujuan mengembangkan sistem pendeteksi kepatuhan berpakaian mahasiswa secara otomatis berbasis visi komputer menggunakan model YOLOv8. Dataset yang digunakan terdiri dari 1.800 citra beranotasi yang terbagi ke dalam 8 kategori pakaian, dengan pembagian data sebesar 78% data latih (1.404 citra), 14% data validasi (254 citra) dan 8% data uji (143 citra). Seluruh citra diproses melalui tahapan pre-processing dan data augmentation, kemudian digunakan untuk melatih model YOLOv8 dengan ukuran input 640×640 piksel selama 50 epoch. Pada tahap pengujian, model mencapai performa keseluruhan dengan Precision 0.844, Recall 0.773, F1-Score 0.802, dan mAP@0.5 0.841, serta mampu mendeteksi objek pakaian dengan akurasi baik dan performa stabil pada berbagai kondisi citra. Sistem kemudian diintegrasikan dengan backend berbasis Flask dan frontend web untuk mendukung proses deteksi waktu nyata dan klasifikasi kepatuhan, dengan waktu respons sistem kurang dari 2 detik, sehingga mampu mengidentifikasi status kepatuhan berpakaian mahasiswa ke dalam kategori “Aman” dan “Melanggar Aturan” secara otomatis dan konsisten.
Kata kunci: aturan berpakaian; deteksi waktu nyata; pendeteksi kepatuhan; visi komputer; YOLOv8.
Abstract:Abstract: Conventional semiconductor chip counting at PT Elektronik Indonesia relies on manual weighing, which is prone to human error and inefficiency. This study proposes a desktop-based counting system using a digital…
scanner and image processing. The novelty lies in integrating horizontal-vertical projection with probabilistic Hough transform to robustly detect grid lines, form square cells, and enable accurate unit estimation via average intensity analysis, eliminating the need for reference weighing. Experiments on 15 actual chip images yielded an error rate of 0.009519% and up to 73.674%time efficiency gains compared to the manual method. The system reduces operator dependency, minimizes errors, and accelerates counting, providing a practical machine vision solution for semiconductor production.
Keywords: chip counting; image processing; probabilistic hough transform; grid line detection; time effeciency.
Abstrak: Penghitungan chip semikonduktor konvensional di PT Elektronik Indonesia bergantung pada penimbangan manual, yang rentan terhadap kesalahan manusia dan kurang efisien. Penelitian ini mengusulkan sistem penghitungan berbasis desktop menggunakan scanner digital dan pengolahan citra. Kebaruan terletak pada integrasi proyeksi horizontal-vertikal dengan probabilistic Hough transform untuk mendeteksi garis grid secara kuat, membentuk sel persegi, serta memungkinkan estimasi unit akurat melalui analisis intensitas rata-rata, sehingga menghilangkan kebutuhan penimbangan referensi. Eksperimen pada 15 citra chip aktual menghasilkan tingkat kesalahan 0,009519% dan peningkatan efisiensi waktu hingga 73,674% dibandingkan metode manual. Sistem ini mengurangi ketergantungan operator, meminimalkan kesalahan, dan mempercepat penghitungan, menyediakan solusi machine vision praktis untuk produksi semikonduktor.
Kata kunci: penghitungan chip; pengolahan citra; probabilistic Hough transform; deteksi garis grid; efisiensi waktu.
Abstract:Abstract: In the era of the Internet of Things (IoT), cyber threats are increasingly complex and dynamic, thus demanding an adaptive and intelligent network security system. This study proposes a Convolutional Neural Network…
work (CNN)-based Intrusion Detection System (IDS) implemented through a Federated Learning (FL) approach in a Non-Independent and Identically Distributed (Non-IID) data environment. This approach allows the model to be trained in a distributed manner across multiple IoT devices without having to collect sensitive data to a central server, thereby maintaining data privacy while increasing the efficiency of the training process. The experiment used the CIC IoT 2023 dataset, which represents various modern IoT network traffic patterns. The results show that the proposed CNN–FL model achieves an overall accuracy of 0.99, with excellent performance in detecting various types of network traffic. The model obtains a perfect recall value (1.00) for normal traffic (Benign), as well as a very high F1-score for DDoS (0.99) and DoS (0.99) attacks. Stable and consistent performance across all five federation rounds demonstrates that this approach is a reliable, efficient, and accurate solution for detecting threats in distributed and privacy-preserving IoT networks.
Keywords: cnn; federated_learning; ids; non-iid; ciciot2023
Abstrak: Dalam era Internet of Things (IoT), ancaman siber semakin kompleks dan dinamis, sehingga menuntut sistem keamanan jaringan yang adaptif dan cerdas. Penelitian ini mengusulkan Intrusion Detection System (IDS) berbasis Convolutional Neural Network (CNN) yang diterapkan melalui pendekatan Federated Learning (FL) pada lingkungan data yang bersifat Non-Independent and Identically Distributed (Non-IID). Pendekatan ini memungkinkan model dilatih secara terdistribusi di berbagai perangkat IoT tanpa harus mengumpulkan data sensitif ke server pusat, sehingga mampu menjaga privasi data sekaligus meningkatkan efisiensi proses pelatihan. Eksperimen menggunakan dataset CIC IoT 2023, yang merepresentasikan berbagai pola lalu lintas jaringan IoT modern. Hasil penelitian menunjukkan bahwa model CNN–FL yang diusulkan mencapai akurasi keseluruhan sebesar 0.99, dengan performa yang sangat baik dalam mendeteksi berbagai jenis lalu lintas jaringan. Model memperoleh nilai recall sempurna (1.00) untuk lalu lintas normal (Benign), serta nilai F1-score yang sangat tinggi untuk serangan DDoS (0.99) dan DoS (0.99). Kinerja yang stabil dan konsisten di seluruh lima putaran federasi membuktikan bahwa pendekatan ini merupakan solusi yang andal, efisien, dan akurat untuk mendeteksi ancaman pada jaringan IoT yang bersifat terdistribusi dan menjaga privasi (privacy-preserving).
Kata kunci: cnn; federated_learning; ids; non-iid; ciciot2023
Abstract:Abstract: This study aims to develop a Deep Learning-based Traffic Flow Detector to automatically and accurately observe traffic flow. Conventional traffic observation is often conducted manually or via CCTV, but it is prone…
rone to human error and difficult to use for real-time trend analysis. In this study, the YOLOv4 method is used to detect four types of vehicles (cars, motorcycles, buses, trucks). To continuously track vehicle movement and address occlusion issues, the Deep SORT algorithm is implemented. The YOLOv4 model used is a pre-trained model and was tested on seven CCTV video recordings obtained from the official website of the Pekanbaru City Transportation Department. The system was implemented on a limited device, the Nvidia Jetson Nano, as a simulation of direct CCTV integration. Test results showed a highest precision of 98%, but the maximum accuracy achieved was only 26%. This low accuracy is influenced by several factors, including video resolution, detection model quality, and lighting conditions. Nevertheless, the system demonstrates potential to support future traffic management and engineering decisions but still requires further optimization, including improving video resolution and quality, retraining the model with a more representative local dataset, using lighter and more accurate detection models, and optimizing the tracking algorithm.
Keywords: deep learning; deepsort; NVIDIA Jetson NANO; traffic flow; YOLOv4
Abstrak: Penelitian ini bertujuan mengembangkan Traffic Flow Detector berbasis Deep Learning untuk mengobservasi arus lalu lintas secara otomatis dan akurat. Observasi lalu lintas konvensional sering dilakukan secara manual atau melalui CCTV, namun rentan terhadap human error dan sulit digunakan untuk menganalisis tren secara real-time. Pada penelitian ini digunakan metode YOLOv4 untuk mendeteksi empat jenis kendaraan (mobil, motor, bus, truk). Untuk melacak pergerakan kendaraan secara berkelanjutan dan mengatasi masalah occlusion, digunakan algoritma Deep SORT. Model YOLOv4 yang digunakan merupakan pre-trained model dan diujikan pada tujuh rekaman video CCTV yang diambil dari situs resmi Dinas Perhubungan Kota Pekanbaru. Sistem ini diimplementasikan pada perangkat terbatas Nvidia Jetson Nano sebagai simulasi penerapan langsung pada CCTV. Hasil pengujian menunjukkan presisi tertinggi mencapai 98%, namun akurasi tertingginya hanya sebesar 26%. Rendahnya akurasi dipengaruhi oleh beberapa faktor seperti resolusi video, kualitas model deteksi, serta kondisi pencahayaan. Meski demikian, sistem ini menunjukkan potensi untuk membantu pengambilan keputusan dalam manajemen dan rekayasa lalu lintas di masa depan, namun masih membutuhkan optimasi lebih lanjut, seperti peningkatan kualitas video input, pelatihan ulang model dengan dataset lokal, penggunaan model deteksi yang lebih ringan dan akurat serta pengoptimalan algoritma pelacakan.
Kata kunci: deep learning deepsort; Nvidia Jetson Nano; traffic flow; YOLOv4
Abstract:Abstract: The advancement of network security faces growing challenges as cyberattacks become more sophisticated. Traditional rule-based systems struggle with zero-day attacks and obfuscation techniques. This study examines…
nes the development trends of AI-based algo-rithms, particularly machine learning and deep learning, in threat detection. A literature review evaluates AI-driven approaches, including support vector machines, random for-est, deep neural networks, convolutional neural networks, and reinforcement learning. Findings show that AI enhances detection accuracy, adaptability, and reduces false posi-tives. Machine learning efficiently classifies known attacks, while deep learning excels in identifying complex patterns such as distributed denial-of-service and advanced persis-tent threats. Unsupervised learning improves anomaly detection without labeled data. However, AI models require high-quality data, substantial computational resources, and remain vulnerable to adversarial attacks. Despite these challenges, AI provides a dynam-ic and adaptive security solution, surpassing traditional systems. Future research should enhance AI scalability and resilience for evolving cybersecurity threats.
Keywords: anomaly detection; artificial intelligence; deep learning; machine learning; network security
Abstrak: Perkembangan keamanan jaringan menghadapi tantangan yang semakin besar seiring meningkatnya kompleksitas serangan siber. Sistem berbasis aturan tradisional kesulitan mendeteksi zero-day attack dan teknik penyamaran. Penelitian ini mengkaji tren pengembangan algoritma berbasis AI, khususnya machine learning dan deep learning, dalam deteksi ancaman. Literature review mengevaluasi pendekatan berbasis AI, termasuk support vector machines, random forest, deep neural networks, convolutional neural networks, dan reinforcement learning. Hasil penelitian menunjukkan bahwa AI meningkatkan akurasi deteksi, adaptabilitas terhadap ancaman baru, serta mengurangi false positive. Machine learning efektif mengklasifikasikan serangan yang telah diketahui, sementara deep learning unggul dalam mengenali pola kompleks seperti distributed denial-of-service dan advanced persistent threats. Unsupervised learning meningkatkan deteksi anomali tanpa memerlukan data berlabel. Namun, AI masih bergantung pada data berkualitas tinggi, sumber daya komputasi besar, dan rentan terhadap adversarial attack. Meskipun demikian, AI menawarkan solusi keamanan yang lebih dinamis dan adaptif dibandingkan sistem tradisional. Penelitian selanjutnya perlu difokuskan pada peningkatan skalabilitas dan ketahanan AI dalam menghadapi ancaman siber yang terus berkembang.
Kata kunci: deteksi anomali; jaringan keamanan; kecerdasan buatan; pembelajaran dalam; pembelajaran mesin
Abstract:Abstract: Face detection remains a challenging task in computer vision due to real-world factors such as uneven lighting, varying viewpoints, distance, and occlusion. This study aims to develop and evaluate a real-time facial…
acial feature detection application (detecting face, eyes, nose, and mouth) using MATLAB and a webcam. Detection is performed using the Viola-Jones Cascade Classifier method through the vision.CascadeObjectDetector function. Key parameters that were adjusted include the MergeThreshold (ranging from 4 to 50 depending on the feature) and MinSize (based on estimated feature size within the frame). However, this study does not include tuning of other parameters such as FalseAlarmRate, which constitutes a limitation of the employed method. The adjustment of these parameters proved significant in improving detection accuracy and robustness under varying lighting conditions. Nevertheless, the system still encounters difficulties in detecting facial features in the presence of occlusion. This study also has the potential to serve as a foundation for further developments in face recognition, emotion detection, or biometric authentication.
Keywords: computer vision; haar cascade; MATLAB
Abstrak: Deteksi wajah merupakan tantangan dalam visi komputer karena dipengaruhi oleh kondisi nyata seperti pencahayaan tidak merata, sudut pandang, jarak, dan obstruksi. Penelitian ini bertujuan untuk mengembangkan dan menguji aplikasi deteksi fitur wajah secara real-time (wajah, mata, hidung, dan mulut) menggunakan MATLAB dan kamera webcam. Deteksi dilakukan dengan metode Viola-Jones Cascade Classifier melalui fungsi vision.CascadeObjectDetector. Parameter penting yang disesuaikan adalah MergeThreshold (antara 4 hingga 50 tergantung fitur), MinSize (mengikuti estimasi ukuran fitur dalam frame). Namun, penelitian ini tidak mencakup penyesuaian parameter lain seperti FalseAlarmRate, yang menjadi salah satu keterbatasan metode yang digunakan. Penyesuaian parameter ini terbukti signifikan dalam meningkatkan akurasi deteksi dan ketahanan terhadap variasi kondisi pencahayaan. Namun, sistem masih mengalami kesulitan mendeteksi fitur wajah jika terjadi obstruksi. Penelitian ini juga berpotensi menjadi dasar untuk pengembangan lebih lanjut dalam face recognition, emotion detection, atau biometric authentication.
Kata kunci: visi computer; haar cascade; MATLAB
Abstract:Abstract: Water irrigation is a crucial aspect of agriculture that often becomes the primary concern for farmers, especially because suboptimal management can lead to decreased crop yields and reduced income. So far, farmers…
mers have been practicing irrigation manually, where plants are watered twice a day, in the morning and evening, based on weather conditions without considering soil temperature or moisture levels. Based on the observations conducted, it was found that excessive water application increases water accumulation, resulting in nutrient loss from the soil and even root diseases. The objective of this study is to develop a system utilizing an ESP32 microcontroller and sensors to detect soil moisture, with a machine learning-based K-Nearest Neighbor (KNN) model, enabling farmers to remotely monitor and control their crops using an Android device. The testing results showed that with input data of 32°C temperature, 40% soil moisture, and 60% air humidity, the system produced a nearest distance of 0.000 and 0.541 from the closest k-nearest neighbors, with a status label of "needs water." As a result, the relay activates the water pump to irrigate the field. Meanwhile, for data with a nearest distance of 0.897, the system identified the status as "does not need water," indicating that the soil remains wet or moist. This study is expected to help reduce farmers' workloads by optimizing water usage according to plant needs and improving crop quality and yield.
Keywords: k-nearest neighbor (KNN); mikrokontroller ESP32; machine learning; water irrigation
Abstrak: Irigasi air merupakan aspek penting dalam pertanian yang menjadi perhatian utama petani, terutama karena pengelolaan yang kurang optimal berdampak pada penurunan hasil panen dan pendapatan. Selama ini, praktik irigasi oleh petani dilakukan secara manual, di mana penyiraman tanaman dilakukan dua kali sehari pada pagi dan sore berdasarkan kondisi cuaca tanpa memperhatikan suhu atau kelembaban tanah. Berdasarkan hasil observasi yang dilakukan, ditemukan masalah yaitu pemberian air secara berlebih menyebabkan akumulasi air meningkat mengakibatkan kehilangan nutrisi tanah dan bahkan penyakit akar. Tujuan penelitian ini menciptakan sistem yang dirancang menggunakan mikrokontroler ESP32 dan sensor untuk mendeteksi kelembaban tanah, dengan model K-Nearest Neighbor (KNN) berbasis machine learning sehingga memudahkan petani untuk mengontrol tanaman mereka dari jarak jauh menggunakan android. Hasil pengujian yang dilakukan dengan data inputan berupa suhu 32°C, kelembaban tanah 40% dan kelembaban udara 60%, sistem menghasilkan jarak terdekat sebesar 0.000 dan 0.541 dari k-nearest terdekat dengan label status "butuh air". Maka relay akan mengaktifkan pompa air untuk mengairi lahan. Kemudian, pada data dengan jarak terdekat 0.897, sistem mengidentifikasi status "tidak butuh air", menunjukkan bahwa kondisi tanah masih basah atau lembab. Penelitian ini diharapkan dapat membantu meringankan beban kerja petani mengoptimalkan penggunaan air sesuai dengan kebutuhan tanaman dan meningkatkan kualitas hasil panen.
Kata kunci: irigasi air; k-nearest neighbor (KNN); mikrokontroller ESP32; machine learning
Abstract:Abstract: Stunting is a chronic or chronic malnutrition that can be seen in the height of toddlers shorter than toddlers their age. the prevalence of toddlers affected by stunting nationally was 37.6 percent (2007) and decreased…
ecreased to 35.8 percent (2010). However, it increased to 37.2 percent (2013) and decreased again to 29.9 percent (2018). The data shows an erratic stunting prevalence. Many factors influence stunting, especially parents' knowledge about balanced nutrition that prevents stunting. Prevention of stunting needs to be done by monitoring nutritional status regularly and fulfilling balanced nutrition for toddlers. For early detection of stunting, an expert system using the Dempster Shafer method is needed. The Dempster Shafer method allows decision making based on various possibilities based on symptoms in toddlers. The results of the expert system calculation show that the Dempster Shafer method can detect stunting in toddlers by more than 90%.
Keywords: dempster shafer; expert system; stunting
Abstrak: Stunting yaitu kekurangan gizi menahun atau kronis yang dapat terlihat pada tinggi badan balita lebih pendek dari balita seusianya. pravelensi balita yang terjangkit stunting secara nasional sebesar 37,6 persen (2007) dan mengalami penurunan menjadi 35,8 persen (2010). Namun meningkat menjadi 37,2 persen (2013) dan menurun kembali menjadi 29,9 persen (2018). Data tersebut menunjukkan pravelensi stunting yang tidak menentu. Banyak faktor yang mempengaruhi stunting khususnya pengetahuan orang tua mengenai gizi seimbang pencegah stunting. Pencegahan stunting perlu dilakukan dengan pemantauan status gizi secara berkala dan pemenuhan gizi seimbang Balita. Untuk deteksi stunting sejak dini dibutuhkan seuatu sistem pakar menggunakan metode dempster shafer. Metode dempster shafer memungkinkan pengambilan keputusan berdasarkan berbagai kemungkinan berdasarkan gejala pada balita. Hasil perhitungan sistem pakar menunjukkan bahwa metode dempster shafer dapat mendeteksi stunting balita lebih sebesar 90%.
Kata kunci: dempster shafer; sistem pakar; stunting
Abstract:Abstract: The increasing number of students at STMIK Royal Kisaran has raised the risk of air pollution caused by vehicle emissions, cigarette smoke, and waste burning, particularly around the campus canteen. The campus's…
s location, which is close to a rubber factory and the Sumatra Crossroad, further exacerbates air quality and significantly impacts the health of individuals active at STMIK Royal. This study aims to develop a system that can measure air quality in real-time and detect pollutants in the campus environment. The system utilizes MQ-135 and MQ-2 sensors integrated with a microprocessor to process and transmit data to an IoT-based database. This research employs a qualitative descriptive method to describe the facts and trends based on the available data. The results indicate that air quality is good in the morning, worsens during the afternoon, and improves again in the evening, reflecting increased pollution during periods of heightened industrial and transportation activities. The implementation of this system is expected to contribute to the creation of a healthier environment and raise awareness about the importance of air quality.
Keywords: air quality; campus environment ; IoT; pollution.
Abstrak: Peningkatan jumlah mahasiswa di Kampus STMIK Royal Kisaran telah meningkatkan risiko polusi udara akibat asap kendaraan, rokok, dan pembakaran sampah, terutama di sekitar kantin kampus. Lokasi kampus yang dekat dengan pabrik karet dan jalan lintas Sumatera sehingga memperburuk kualitas udara dan sangat mempengaruhi kesehatan para individu yang beraktivitas di STMIK Royal. Penelitian ini bertujuan mengembangkan sistem yang dapat mengukur kualitas udara secara real-time dan mendeteksi polutan di lingkungan kampus. Sistem ini menggunakan sensor MQ-135 dan MQ-2 yang terintegrasi dengan mikroprosesor untuk mengolah dan mengirim data ke database berbasis IoT. Penelitian ini menggunakan metode deskriptif kualitatif untuk menggambarkan fakta dan kecenderungan dari data yang tersedia. Hasilnya menunjukkan bahwa kualitas udara baik di pagi hari, memburuk di siang hari, dan membaik lagi di sore hari, menunjukkan peningkatan polusi saat aktivitas pabrik dan transportasi meningkat. Implementasi sistem ini diharapkan dapat mendukung terciptanya lingkungan yang lebih sehat dan meningkatkan kesadaran akan pentingnya kualitas udara.
Kata kunci: IoT; lingkungan kampus; kualitas udara; polusi.
Abstract:Abstract: Since information and communication technology has become ingrained in our daily lives, it has become easier to access information. However, there are some concerns. One of them is about fake news. The aim of this…
his study is to develop an Indonesian system for detecting false news by utilizing news headlines. The methods used are linear kernel support vector ma- chine and n-gram. According to the findings of the performance test that was carried out, the linear kernel support vector machine model employing the term frequency inverse document frequency unigram feature performs better than utilizing bigram. The precision value generated from the model performance test is 1.00. This means that the degree of accuracy in matching the requested information regarding fake news detection with the answers provided by the system is very good. Then the recall value generated is 0.99. This means the linear kernel support vector machine model using unigram news features is very effective for detecting fake news according to the text classification approach.
Keywords: classification; fake news; n-gram; support vector machine
Abstrak: Dengan adanya integrasi teknologi informasi dan komunikasi dalam kehidupan mem- buat kemudahan dalam mengakses informasi. Walaupun demikian, terdapat kekhawatiran akan beberapa hal. Salah satu di antaranya adalah berita palsu. Tujuan penelitian ini adalah merancang sistem deteksi berita palsu berbahasa Indonesia berdasarkan judul berita. Metode yang digunakan adalah Support Vector Machine kernel linier dan n-gram. Berdasarkan hasil uji performa, model Support Vector Machine kernel linier yang menggunakan fitur term frequency inverse document frequency unigram menunjukkan kinerja yang lebih baik dibandingkan bi- gram. Nilai precision yang dihasilkan dari uji performa model sebesar 1,00. Ini berarti derajat akurasi dalam mencocokkan informasi yang diminta mengenai deteksi berita palsu dengan ja- waban yang diberikan oleh sistem sangat baik. Kemudian nilai recall yang dihasilkan sebesar 0,99. Ini berarti model Support Vector Machine kernel linier dengan menggunakan fitur berita unigram sangat efektif untuk mendeteksi berita palsu menurut pendekatan teks klasifikasi.
Kata kunci: klasifikasi; berita palsu; n-gram; support vector machine