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: This research is driven by the challenges faced by Universitas Lancang Kuning (UNILAK) in attracting applicants amidst intense competition, especially after the government's policy opened independent pathways to…
o State Universities (PTN) from 2022-2023, which impacted private university applicant numbers. To address this and support strategic planning, this study aims to predict the trend of prospective students applying to all study programs at UNILAK for the period 2025-2027. Two time series models were employed: ARIMA (AutoRegressive Integrated Moving Average) and LSTM (Long Short-Term Memory). Applicant data from 2019 to 2024 was used to build the model. The Augmented Dickey-Fuller (ADF) test confirmed the data's stationarity with a p-value of 0.0. ACF and PACF analyses determined the ARIMA parameters as p=1, d=1, q=1. The LSTM model was trained to capture more complex data patterns. ARIMA predictions for 2025, 2026, and 2027 are 3298.66, 3362.33, and 3371.30, respectively. LSTM predictions for the same years are 3335.64, 3476.52, and 3518.42. Evaluation using Root Mean Squared Error (RMSE) showed ARIMA (RMSE=588.72) to be more accurate than LSTM (RMSE=653.96). Nevertheless, LSTM provided a more optimistic prediction. This study concludes that ARIMA is better suited for short-term planning, while LSTM can be used for more ambitious long-term strategies.
Keywords: arima; LSTM; applicants; prediction; university
Abstrak: Penelitian ini didorong oleh tantangan Universitas Lancang Kuning (UNILAK) dalam menarik pendaftar di tengah persaingan ketat, khususnya setelah kebijakan pemerintah membuka jalur mandiri ke Perguruan Tinggi Negeri (PTN) sejak 2022-2023, yang menyebabkan penurunan jumlah pendaftar di universitas swasta. Untuk mendukung perencanaan strategis, studi ini bertujuan memprediksi tren jumlah calon mahasiswa yang mendaftar ke seluruh program studi di UNILAK untuk periode 2025-2027.Dua model deret waktu digunakan: ARIMA (AutoRegressive Integrated Moving Average) dan LSTM (Long Short-Term Memory). Data jumlah pendaftar dari 2019 hingga 2024 digunakan untuk membangun model. Uji Augmented Dickey-Fuller (ADF) menunjukkan data stasioner dengan p-value 0,0. Analisis ACF dan PACF menentukan parameter ARIMA sebagai p=1, d=1, q=1. Model LSTM dilatih untuk menangkap pola data yang lebih kompleks.Prediksi ARIMA untuk 2025, 2026, dan 2027 adalah 3298.66, 3362.33, dan 3371.30. Prediksi LSTM untuk tahun yang sama adalah 3335.64, 3476.52, dan 3518.42. Evaluasi menggunakan Root Mean Squared Error (RMSE) menunjukkan ARIMA (RMSE=588.72) lebih akurat daripada LSTM (RMSE=653.96). Meskipun demikian, LSTM memberikan prediksi yang lebih optimis. Studi ini menyimpulkan ARIMA lebih cocok untuk perencanaan jangka pendek, sementara LSTM dapat digunakan untuk strategi jangka panjang yang ambisius.
Kata kunci: arima; LSTM; pendaftar; prediksi; universitas
Abstract:Face recognition has become a common thing used in the field of surveillance and security in computer technology and image devices. This study aims to identify the usefulness of a person's face on 3 test images. This study…
dy examines the methods of cropping techniques, image enhancement through intensity measurement, and histogram analysis to improve the contrast and distribution of image intensity. In addition, the Viola-Jones algorithm is used to detect key facial features such as eyes, nose, and mouth. The results of the analysis are then applied in the feature evaluation stage, where usually between facial features are applied to measure the ratio of facial proportions. Furthermore, the comparison of proportional ratios of several images was analyzed using bar graphs and line graphs to evaluate the trend and stability of facial proportions. The results showed the best ratio stability with a smaller variation of the on-off ratio of image 2 which is 0.4762 pixels to 0.4983 pixels. Image 2 is the most ideal for face measurement systems based on geometric ratios because it provides more consistent and visible results.
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: 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: Gallery Parfume Shop is a business engaged in cosmetics located on Jalan Merdeka, Simpang Empat, Kec. Tanjung Tiram, Kab. Batu Bara, North Sumatra. In the procedures and management of sales management at Gallery…
y Parfume is still done manually, the reports are still recorded in notes the impact of this is that Gallery Parfume has difficulty in evaluating their sales performance, identifying market trends, and planning effective sales strategies and also difficulty building loyalty. Therefore, a system is needed, by implementing E-CRM at Gallery Parfume can get new customers, improve customer relationships, and retain customers, which will ultimately create customer loyalty and to measure the increase in profitability resulting from the use of E-CRM into a web-based application so that it will later facilitate increasing sales, customer loyalty, and saving operational costs. The method used to collect and analyze this research data is a qualitative method. It is expected that through this web application it can also build a database to make it easier for Gallery Parfume to search for data and reports.
Keywords: consumers; e-crm; stores
Abstrak: Toko Gallery Parfume merupakan usaha yang bergerak dibidang kosmetik yang berada dijalan Merdeka, Simpang Empat, Kec. Tanjung Tiram, Kab. Batu Bara, Sumatera Utara. Dalam prosedur dan manajemen pengelolaan penjualan di Gallery Parfume masih dilakukan secara manual, laporan nya masih tercatat di notes dampak dari hal tersebut gallery Parfume kesulitan dalam mengevaluasi kinerja penjualan mereka, mengidentifikasi tren pasar, dan merencanakan strategi penjualan yang efektif juga kesulitan membangun loyalitas. Maka dengan hal itu diperlukan sebuah sistem, dengan menerapkan E-CRM di Gallery Parfume dapat memperoleh pelanggan baru, meningkatkan hubungan dengan pelanggan, dan mempertahankan pelanggan, yang pada akhirnya akan terciptanya loyalitas pelanggan dan untuk mengukur peningkatan profitabilitas yang dihasilkan dari penggunaan E-CRM kedalam bentuk aplikasi berbasis web agar nantinya memudahkan dalam peningkatan penjualan, loyalitas pelanggan, dan penghematan biaya operasional. Metode yang digunakan untuk mengumpulkan dan menganalisis data penelitian ini dengan metode kualitatif. Diharapankan melalui aplikasi web ini juga dapat membangun database guna memudahkan Gallery Parfume dalam mencari data dan laporan.
Kata Kunci: e-crm; konsumen; toko
Abstract:Abstract: The growth of information technology continues to grow rapidly, especially in the business sector in Indonesia. Every year the growth of business shops increases to 3.98 million business units in 2022 from the…
real industry and trade sectors. So, this makes the Tanjung Shoe Store have serious challenges that affect sales levels which gives rise to problems of decreasing sales levels because there is no effective communication media, the shop is unable to analyze customer needs and market trends, customer disappointment often arises with the shop because it still applies conventional sales, and damage or loss of store operational data. To overcome this problem, a website-based system is needed by implementing a superior CRM (Customer Relationship Management) strategy in increasing customer retention with operational data management features, discounts, chat, online ordering, so that customers get updated information. The CRM concept used is operational, analytical, and collaborative. The application of CRM in this research aims to make it easier for users and improve customer service and optimize marketing at the Tanjung Shoe Store. So, this CRM strategy is an effective solution in facing modern business challenges in improving store performance and competitiveness.
Keywords: customer relationship management; customer service; optimize marketing
Abstrak: Pertumbuhan teknologi informasi terus berkembang pesat terutama pada bidang bisnis di Indonesia. Setiap tahunnya pertumbuhan toko usaha semakin meningkat hingga 3,98 juta unit usaha pada tahun 2022 dari sektor rill industri dan perdagangan. Sehingga hal ini membuat Toko Sepatu Tanjung memiliki tantangan serius yang mempengaruhi tingkat penjualan yang menimbulkan permasalahan penurunan tingkat penjualan karena tidak ada media komunikasi yang efektif, toko tidak mampu menganalisis kebutuhan pelanggan dan tren pasar, sering timbul kekecewaan pelanggan terhadap toko karena masih menerapkan penjualan konvensional, dan kerusakan atau kehilangan data operasional toko. Untuk mengatasi masalah ini diperlukan sistem berbasis website dengan menerapkan strategi CRM (Customer Relationship Management) yang unggul dalam meningkatkan retensi pelanggan dengan fitur pengelolaan data operasional, diskon, chatting, pemesanan online, sehingga pelanggan mendapatkan informasi secara update. Konsep CRM yang digunakan operasional, analitis, dan kolaboratif. Penerapan CRM pada penelitian ini bertujuan untuk memudahkan pengguna dan meningkatkan pelayanan pelanggan serta mengoptimalkan pemasaran pada Toko Sepatu Tanjung. Maka strategi CRM ini menjadi solusi yang efektif dalam menghadapi tantangan bisnis modern dalam meningkatkan kinerja dan daya saing toko.
Kata kunci: customer relationship management; optimalisasi pemasaran; pelayanan pelanggan
Abstract:Student development includes conduct as a key component. Student behavior becomes crucial in deciding how successful students will be in different spheres of life. The variety of student behavior can hinder the learning…
process and personal development of students. Through the development of an expert system-based counseling model based on backward chaining, this study seeks to discover trends in student behavior. The research process starts with problem analysis, goal setting, literature study, data collection, system design and implementation, and results analysis. It then moves on to counseling model development and implementation in the school setting. To determine the reasons for the unruly behavior of the kids, data were analyzed using a backward chaining methodology. UML Usecase diagrams are used in system design to define the roles of actors and users. The established counseling model, which consists of 14 behaviors, 67 phenomena/symptoms, and 14 rules, focuses on goals and methods to modify student behavior. Three students underwent system testing based on previously achieved goals from therapy. The findings revealed "Smoking," "Emotional Problems," and "Fighting" among the student behaviors. When the Backward Chaining-based counseling model is used, it is simpler for homeroom teachers to gather information about students' conduct from them and to offer remedies based on the transfer of professional knowledge without having to wait for the counselor guidance procedure
Abstract:Abstract: Unemployment is a global economic issue that directly impacts human life in both developed and developing countries, especially in Indonesia, which, if ignored, will severely impact society's social dynamics. To…
o overcome this problem, forecasts are made so that later, the government can take policies to control and suppress the unemployment growth rate. This research aims to predict unemployment in Indonesia in 2023 using the Weighted Moving Average method, widely used to determine the trend of a time series, which is part of one of the Time Series methods that gives different weights. The dataset used was obtained from the Central Statistics Agency (BPS) relating to unemployment data from 2000 to 2022 (23 years). To analyze the level of accuracy of the results of this unemployment forecast using the MAD, MSE, and MAPE methods. This research concludes that the Weighted Moving Average method can be applied in predicting unemployment in Indonesia in 2023. The results of this research are a prediction of the number of unemployed in Indonesia, as many as 8,874,942 people at a weight value of 3 (three) where the accuracy of the MAD value is 745786.1833, the MSE value is 948402050986.3 and MAPE is 8.28%.
Keywords: forecasting; unemployment; weigth moving average; indonesia
Abstrak: Pengangguran menjadi isu ekonomi global yang berdampak secara langsung terhadap tingkat kehidupan manusia di negara-negara yang sudah maju maupun yang sedang berkembang khususnya di negara Indonesia, yang jika diabaikan akan berdampak serius terhadap dinamika sosial masyarakat. Untuk mengatasi permasalahan tersebut dibuatlah peramalan agar nantinya pemerinta dapat mengambil kebijakan dalam mengendalikan dan menekan angka pertumbuhan pengangguran tersebut. Penelitian ini bertujuan untuk memprediksi pengangguran di Indonesia pada tahun 2023 menggunakan metode Weighted Moving Average dimana metode ini banyak digunakan untuk menentukan trend dari suatu deret waktu yang merupakan bagian dari salah satu metode Time Series yang memberikan bobot yang berbeda-beda. Adapun dataset yang digunakan diperoleh dari Badan Pusat Satatistik (BPS) berkaitan dengan data pengangguran dari tahun 2000 sampai dengan tahun 2022 (selama 23 tahun). Untuk menganalisa tingkat akurasi dari hasil peramalan pengangguran ini memakai metode MAD, MSE, dan MAPE. Kesimpulan dari penelitian ini yaitu dapat diterapkannya metode Weighted Moving Average dalam memprediksi pengangguran di Indonesia pada tahun 2023. hasil dari penelitian ini berupa prediksi jumlah pengangguran di Indonesia sebanyak 8.874.942 orang pada nilai bobot 3 (tiga) dimana akurasi nilai MAD sebesar 745786,1833, nilai MSE sebesar 948402050986,3 dan MAPE sebesar 8,28 %.
Kata kunci: peramalan; pengangguran; weigth moving average; indonesia
Abstract:Abstract: crime mapping, namely by examining various spatial data factors that can be integrated to be able to produce a variety of information for security officers and the government in an effort to realize security in…
an area by utilizing geographic information systems by mapping, visualizing and analyzing crime incidents so that Various patterns and trends of spatial and temporal crime are generated using the main concept of cryptography, namely the encryption or encryption process where the plaintext encoding process becomes ciphertext and the decryption or description process, which is the process of returning the ciphertext to the original plaintext using the Electronic Code Book (ECB) algorithm and the ECB algorithm vigenere
Keywords: criminal patterns, geographic information systems, network system
Abstrak: pemetaan kriminalitas yaitu dengan mengkaji berbagai macam faktor data spasial yang dapat terintegrasi untuk dapat menghasilkan keanekaragaman informasi bagi aparat keamanan dan pemerintah dalam upaya mewujudkan kemanan di suatu area dengan memanfaatkan sistem informasi geografis dengan cara dilakukan memetakan, memvisualkan dan menganalisis insiden kriminalitas sehingga dihasilkan beragam pola maupun trend kriminalitas secara spasial temporal dengan menggunakan konsep utama dari kriptografi yaitu proses enkripsi atau enkription dimana proses penyandian plainteks menjadi cipherteks dan proses dekripsi atau description yaitu proses mengembalikan cipherteks menjadi plainteks semula menggunakan algoritma Elektronic Code Book (ECB) dan algoritma Vigenere.
Kata kunci: pola kriminalitas, sistem informasi geografis, sistem keamanan