Publication Search

The integration of autonomous systems in traffic management has become increasingly important as urban populations and vehicle numbers continue to rise, leading to significant congestion. Traditional traffic signal control systems, which rely on fixed timing, are no longer sufficient to handle the dynamic and complex nature of urban traffic. To address these challenges, the proposed explainable Deep Reinforcement Learning (DRL) framework aims to optimize traffic signal control by dynamically adjusting traffic signals based on real-time data. This approach enhances traffic flow efficiency, reduces congestion, and improves overall system performance. The framework leverages Vehicle-to-Everything (V2X) communication, which enables real-time data exchange between vehicles, infrastructure, and other road users, extending the perception range of autonomous vehicles and providing valuable insights for traffic signal optimization. Additionally, the integration of smart infrastructure, such as smart intersections, plays a crucial role in enabling adaptive traffic management and facilitating better coordination across multiple intersections. One of the key advantages of the proposed system is its transparency, achieved through the implementation of explainable AI (XAI) techniques. These mechanisms provide clear insights into the decision-making processes, ensuring that traffic management authorities and system users can understand the rationale behind the system’s decisions. Although challenges such as data accuracy, scalability, and cybersecurity risks remain, the proposed DRL framework shows great promise in revolutionizing traffic management systems. Future research directions include enhancing data collection methods, improving the scalability of the system for larger cities, and further developing explainability features to improve trust and adoption in real-world applications.

The rapid increase in Ro-Ro (Roll-On/Roll-Off) vessel and vehicle traffic at Tanjung Perak Port, Surabaya, has exposed critical inefficiencies in port operations, particularly at key berths such as Jamrud Utara and Jamrud Selatan. These inefficiencies manifest as prolonged queuing times for Ro-Ro vessels and land-based vehicle congestion, leading to delays in cargo handling and increased operational costs. This study aims to evaluate the operational performance of Ro-Ro terminals based on queue time indicators for both Ro-Ro vessels and vehicles. Employing a quantitative descriptive approach, the research integrates the M/M/c queuing model and Fishbone Diagram analysis to identify systemic causes of operational delays and overcapacity. The study reveals that berth utilization rates exceed 75%, indicating saturation, while limited buffer zones and disorganized traffic flow exacerbate vehicle queues. As a case study, the findings offer data-driven insights and practical recommendations, including schedule optimization, dedicated traffic lanes, and infrastructural upgrades to mitigate congestion. The proposed framework not only enhances service efficiency at the port but also contributes to broader logistics performance in Eastern Indonesia. By combining classical queuing theory with root cause analysis, this research introduces a methodological synergy that can be replicated across other Ro-Ro terminals facing similar challenges. The findings underscore the urgent need for integrated port traffic management and infrastructural adaptability in response to growing maritime logistics demands.

The increasing number of devices connected to the network and the rapid growth of data traffic have posed challenges in managing conventional networks. Traditional networks often experience inefficiencies in handling high traffic loads due to static traffic management, leading to congestion in some network paths while others remain underutilized. Software-Defined Networking (SDN) has emerged as an innovative solution by separating the control plane and data plane, enabling more flexible, centralized, and programmable network management. This study evaluates the performance of OpenFlow-based SDN using the ONOS Controller and compares it with conventional home Wi-Fi networks based on the TIPHON standard. The simulation was conducted using Virtual Machines (VMWare) and Mininet, which were connected to the ONOS Controller via the OpenFlow protocol, while the conventional network testing was performed using the Command Prompt. The testing included three data transmission scenarios: 1 host to 1 host, 2 hosts to 1 host, and 2 hosts to 2 hosts simultaneously, with measured parameters including delay and packet loss. The results indicate that in the 1 host to 1 host scenario, both SDN and conventional networks had a delay of less than 150 ms and 0% packet loss. However, in the 2 hosts to 2 hosts scenario, the conventional network experienced an increase in delay and packet loss of up to 17%, whereas SDN remained stable with a delay below 150 ms and 0% packet loss. This confirms SDN's superior efficiency in handling high network traffic through more dynamic traffic distribution. Additionally, this study confirms that SDN's centralized control allows for more adaptive traffic management, reduces congestion, and improves overall network stability. These research demonstrate SDN's efficiency in handling high traffic loads, making it a superior solution for modern network demands.

Unsignalized intersections are a major point of concern due to the increasing number of vehicles. Bima City is a city located on the eastern part of Sumbawa Island, West Nusa Tenggara Province. As a developing city, congestion and busy traffic often occur on roads or intersections of Mongosidi and Anggrek roads. Therefore, this study was conducted to determine the performance and level of service of unsignalized intersections at Mongosidi Street and Anggrek Street. The method used refers to the Indonesian Road Capacity Manual (MKJI) 1997. This study aims to determine the indicators of traffic behavior at unsignalized intersections. The results of the calculation obtained a total flow of 3147 smp / hour, a capacity value (C) of 4234 smp / hour and a degree of saturation (DS) of 0.74, Traffic Delay (DT) of 8.07 sec / smp, intersection delay (D) of 11.73 sec / smp and upper and lower limit queuing opportunities of 44.46% and 17.74% respectively. This condition occurs on Monday, March 17, 2025 at the peak hour of 06.45-07.45 WITA. For the level of service of the intersection pattern, the conditions on Monday, March 17, 2025 at the peak hour of 06.45-07.45 WITA are also categorized as type C, namely stable flow, but the speed and movement of vehicles are controlled.Drivers are limited in choosing speed, with saturation density (Ds) around 0.45 - 0.74.

This study investigates the impact of cashless payment technologies, specifically e-toll and Garda Total Objek (GTO), on customer satisfaction and travel efficiency on the Tangerang-Merak Toll Road. The research demonstrates that the implementation of these technologies significantly enhances travel time efficiency and overall user satisfaction, providing a more seamless and convenient toll payment experience. Despite these positive outcomes, the study identifies several technical challenges that hinder optimal performance. Notably, there is an 18% transaction failure rate, primarily caused by malfunctions in card reader devices and server disruptions, which negatively affect the customer experience. In addition to technological reliability, the quality of service delivered by field staff and the degree of customer loyalty emerge as critical factors influencing sustained use of the digital payment system and overall satisfaction levels.The study underscores the importance of time efficiency and customer loyalty as key drivers for improving service quality and encouraging the widespread adoption of cashless systems. To address these challenges, the study recommends enhancing the reliability of payment devices and network infrastructure through regular maintenance and upgrades. Furthermore, the adoption of Multi-Lane Free Flow (MLFF) technology is suggested to allow toll transactions without stopping, thereby reducing traffic congestion and waiting times at toll plazas. Continuous staff training is essential to improve service response and technical troubleshooting. Additionally, customer loyalty programs offering incentives like discounts and rewards could increase user engagement. The study also emphasizes the need for increased public education on cashless payment systems and their features to minimize resistance and misunderstandings. Finally, ongoing monitoring and evaluation based on user feedback are critical for promptly addressing issues and sustainably improving customer satisfaction.

Efficient management of aircraft parking stands is a critical element in maintaining flight safety at airports. As air traffic increases, the coordination and performance of the Apron Movement Control (AMC) team play a vital role in assigning parking positions to prevent operational delays and potential hazards. This study aims to evaluate the performance of the AMC team in managing parking stands at Yogyakarta International Airport using a descriptive qualitative approach. The assessment was based on five indicators proposed by Robbins & Judge: work quality, work quantity, timeliness, effectiveness, and independence. Data were collected through direct observation, semi-structured interviews, and documentation analysis. The findings indicate that the AMC team consistently performs its duties in accordance with established procedures, responds effectively to sudden operational changes, and demonstrates independent decision-making capabilities. These results highlight the crucial role of the AMC team in ensuring the safe movement of aircraft on the apron. However, challenges such as limited staffing and unanticipated schedule changes still require attention to improve overall operational efficiency.

The threat of Distributed Denial of Service (DDoS) is increasing develop along with increasing use of the Internet of Things (IoT) and Software-Defined Networking (SDN) architecture . Although SDN provides convenience in management network , properties its centralized control make it prone to to flooding attacks that can paralyze controller performance . Detection method conventional , such as approach statistics and machine learning, still own limitations in matter accuracy , high false positive rate , and dependence on extracted features manually . To overcome problem said , research This propose a hybrid deep learning based DDoS detection and mitigation model that combines Convolutional Neural Network (CNN) to extraction feature spatial from RGB and Gated Recurrent Unit (GRU) images for understand temporal correlation between traffic data network . System tested through network test-bed Mininet based with Ryu/Floodlight controller, using simulation DDoS attacks (Hping3, LOIC) and normal traffic (video streaming, HTTP server). Traffic data cross recorded in PCAP format, processed become RGB image measuring 200×200 pixels, and labeled based on type traffic . Evaluation results with metric accuracy , precision, recall, F1-score, and MCC show that the CNN–GRU model has performance more superior compared to baseline approaches such as CNN-only, GRU-only, as well as classical ML methods such as SVM and Random Forest. In addition , the system capable apply mitigation adaptive through automatic flow rule creation on edge switches. Findings This confirm that effective deep learning- based spatial -temporal hybrid approach in increase detection early and response DDoS attacks on SDN networks adaptive and real-time.  

This lesson is to construct a durable and efficient form rigid pavement by utilizing the structural analysis and material performance approach. Rigid pavement is the main choice in highway construction because of its ability to bear heavy loads and its relatively long service life. The research methodology involves structural analysis to determine the optimal thickness and type of material for rigid pavement. This structural analysis considers various factors, including the estimated traffic load, subgrade characteristics, and local environmental conditions. In addition, material performance evaluation is also carried out to select materials that are appropriate to environmental conditions and meet technical requirements. The results of this study are recommendations for rigid pavement planning that include the right thickness, optimal material type, and construction specifications that are in accordance with applicable technical standards. The results of Rigid Pavement Thickness Planning using the Bina Marga 2003 Method on the Sumbermiri - Gudo Jombang Road case study produced a concrete slab thickness of  20 cm with K-300 concrete quality. In addition, the reinforcement used has a diameter of Ø 12 mm with a distance between reinforcements of  8,5 cm.

In an effort to reduce the number of work accidents, Satlantas members as the responsible party need to maintain their performance in the field. However, in reality, performance can be influenced by other variables such as work stress and OCB. This will affect the results and quality of performance carried out. The purpose of this study was to determine the relationship and influence between two variables, namely work stress (X1) and OCB (X2) on the performance (Y) of Satlantas Aceh Besar members in reducing traffic accidents. This study is a study with a quantitative approach using a survey method. Data collection was carried out by distributing questionnaires containing 50 statements to 44 respondents of Satlantas Aceh Besar. Data analysis in this study used multiple linear regression, which produced the equation Ŷ = a + b1X1 + b2X2 + e where work stress and performance have a negative relationship direction with a coefficient value of -0.247, while the tcount value> ttable (-2.020) which means H0 is rejected. Then the results of the OCB t-test on performance have a t-value of 7.465 which is greater than the t-table of 2.020 so that H0 is accepted and OCB has an effect on performance with an F-value of 52.182 greater than the Ftable of 3.226 meaning that H0 is accepted which means that work stress and OCB together have an effect on performance. Then the results of the determination coefficient are known to be 0.718 which means that work stress and OCB have an effect on performance of 71.8%. From these results it can be concluded that work stress does not have a significant effect on member performance, while OCB has a significant effect on member performance and OCB with work stress together affect member performance.

Automatic Identification System (AIS) is a communication technology that plays an important role in improving operational safety and efficiency in the shipping industry. AIS allows ships to exchange real-time data on identity, position, speed, and direction, which helps prevent collisions and facilitates maritime traffic management by port authorities. In addition, AIS functions in search and rescue operations by providing accurate information on the location of ships in trouble. In terms of security, AIS allows monitoring of suspicious ships, thus helping in preventing illegal activities in the waters. This study aims to design and develop a prototype AIS receiver based on LoRa, Arduino, and LCD HMI. The LoRa module was chosen because of its ability to transmit data over long distances with low power consumption, which is suitable for the maritime environment. Arduino is used as the main microcontroller to control the system, while the LCD HMI serves as the display interface for the received data. After the hardware and software design was completed, the system was tested through functional testing and performance measurements using a spectrum analyzer to evaluate the strength of the LoRa signal at various distances. The test results show that the AIS receiver is able to receive data well up to 15 meters on land and 13 meters at sea, with a delay of 100 milliseconds. System performance degrades at longer distances due to environmental interference and signal attenuation. These findings provide insight into the effective limits of LoRa communication in maritime applications and can be used as a reference for frequency testing and optimization of LoRa-based long-range communication systems.

Congestion in Pontianak City significantly impacts traffic flow, affecting both efficiency and comfort of road transit. The city's unsignalized intersections, crucial for managing vehicle flow from multiple directions, are under scrutiny for their performance. A study using the Indonesian Road Capacity Guidelines (IRCG) has assessed intersections, that the degree of saturation often exceeds acceptable limits, leading to congestion and increased delays. The research highlights that the current capacity of these intersections is insufficient to handle the growing traffic demand. For instance, under maximum traffic flow conditions, one intersection recorded a total traffic flow of 2,978.20 pcu/hour against a capacity of 2,716.40 pcu/hour, resulting in a degree of saturation of 1.096. This indicates a need for interventions like installing traffic signals or modifying road geometry to enhance flow efficiency. Despite these findings, the analysis of existing conditions specific unsignalized intersections showed a level of service value of E and F, suggesting that these intersections currently require immediate improvements. However, to further improve intersection performance, recommendations include reducing side obstacles, enhancing road geometry, and installing two-phase traffic signals, which offer the highest capacity with minimal delay. These measures aim to ensure that Pontianak City's transportation infrastructure can effectively.

Law enforcement of road transportation traffic is one of the important aspects in maintaining road safety and order. However, the effectiveness of monitoring and evaluating the performance of Civil Servant Investigators (PPNS) in law enforcement is often hampered by unstructured processes and lack of transparency in reporting. This research aims to analyze the role of information technology (IT)-based system development in improving transparency, efficiency, and accountability in monitoring and evaluating PPNS performance. This research uses a qualitative method with a case study approach, which involves analyzing the application of information systems in institutions that handle traffic law enforcement. The results showed that IT systems can improve transparency by providing clear and real-time data access, increase efficiency by speeding up data processing and analysis, and strengthen accountability through auditable digital records. The study concludes that the development and implementation of IT systems in the oversight of PPNS performance not only improves the effectiveness of traffic law enforcement, but also strengthens the integrity and public trust in the institutions that carry out these tasks. The implementation of IT systems is expected to be a strategic solution in improving the quality of public services in the field of traffic law.

This research aims to address the issue of uneven bandwidth distribution in large organizational networks by implementing Quality of Service (QoS) using FIFO and the Hierarchical Token Bucket (HTB) algorithm on Mikrotik routers. Uneven bandwidth distribution can disrupt productivity and operational efficiency. This study creates a fair and efficient traffic management system, allowing bandwidth allocation according to user needs. The methodology involves detailed configuration of Mikrotik RouterOS to optimize QoS with adjusted HTB settings. Testing was conducted using IPerf3 to measure bandwidth variations received by clients in different conditions, including scenarios with two and three active clients. The results indicate that the HTB method provides more stable and consistent bandwidth distribution compared to FIFO. In the two-active client scenario, the unused bandwidth by the third client is allocated to higher priority clients, demonstrating HTB's effectiveness in managing traffic priorities. This research is expected to enhance user satisfaction by providing a network that is both stable and responsive to the needs of various operational applications, and contribute significantly to the development of best practices for bandwidth management in complex organizational environments.

Increased activity in the airside area, especially on the apron, causes the emergence of foreign objects such as gravel and oil spills that can disrupt flight safety. Apron Movement Control (AMC) plays a crucial role in regulating aircraft traffic, monitoring the apron area, and maintaining cleanliness from Foreign Object Debris (FOD). This study aims to evaluate the effect of AMC performance in FOD supervision on flight safety at Sentani International Airport. The method used is a quantitative approach with a saturated sampling technique, involving airside officers from airlines, Ground Handling (GH), Ground Support Equipment (GSE), and Marshallers. Data were collected through a closed questionnaire with a 4-point Likert scale and analyzed using validity, reliability, simple linear regression, T-test, and coefficient of determination. The results of the analysis show that AMC performance has a positive and significant effect on flight safety, with a significance value of the T test <0.05. The coefficient of determination (R²) of 0.916 indicates that AMC contributes 91.6% to flight safety, while the rest is influenced by other factors. This finding emphasizes the importance of improving the professionalism and effectiveness of AMC officers' performance.

The detection of computer network attacks is becoming increasingly important as the complexity and frequency of cyber-attacks threatening information systems and network infrastructure continue to rise. These attacks may lead to severe consequences, including data breaches, service disruptions, and financial losses. To address these challenges, artificial intelligence techniques have become a major focus in the development of more effective, adaptive, and reliable intrusion detection systems. Among various classification algorithms, the C4.5 decision tree has demonstrated strong performance due to its simplicity, interpretability, and high classification accuracy. This study aims to apply the C4.5 algorithm for network attack detection using a comprehensive dataset that includes multiple categories of attacks and normal network activities. The proposed methodology consists of several stages, including data preprocessing, feature selection, decision tree model construction, and performance evaluation using standard metrics such as accuracy, precision, recall, and F1-score. Data preprocessing is performed to handle missing values, normalize data, and reduce noise, thereby improving the overall quality of the dataset and enhancing classification results. The experimental results indicate that the C4.5 decision tree algorithm effectively classifies network traffic into attack and normal categories with a satisfactory level of accuracy. The model successfully identifies attack-related patterns and highlights significant features that influence detection performance. Further analysis reveals that appropriate feature selection and parameter tuning significantly contribute to improving model reliability and robustness. This research provides a valuable contribution to the development of efficient, accurate, and practical network intrusion detection systems. The proposed approach is expected to strengthen information security frameworks and support proactive defense strategies against increasingly sophisticated cyber threats, thereby enhancing the protection of critical network infrastructures.

Image classification is widely used in everyday life such as in car steering, closed-circuit television (CCTV), traffic cameras, etc. The implementation of image classification can be done using several methods, including neural network and support vector machine models. The neural network method is able to find the right weights that allow the network to show the desired behaviour while the support vector machine method has many dimensions and can overcome linear and non-linear data. In this research, feature extraction was carried out using VGG16 to increase accuracy. This research aims to find out how to implement the neural network and SVM algorithms to classify images and determine the results of analyzing the performance of the two methods. The data used in this study is secondary data consisting of 10 types of large wild cats with a total of 2339 training image datasets and 50 testing image datasets. The research stages consist of data augmentation, model design, model training, and model evaluation. Classification with the neural network model produced an accuracy of 96% and the support vector machine model produced an accuracy of 96%, which means that in a consistent training environment, the two models have the same performance.

This study aims to analyze the Level of Service (LoS) at the international departure terminal facilities at I Gusti Ngurah Rai Airport, Bali, in accommodating the growth of passenger traffic. Referring to IATA standards, PM 178 of 2015, and PM 41 of 2023, this research evaluates the performance of facilities such as passenger and baggage screening, check-in, immigration, and waiting areas. The research method used is qualitative, with data collected through observation, interviews, and documentation. The results show that the international departure terminal facilities meet the established service standards and are capable of handling passenger congestion during holiday seasons (high season and peak season). Efforts made by airport management include terminal expansion, queue management, and the enhancement of security systems with the latest technology. In conclusion, the Level of Service at I Gusti Ngurah Rai Airport is categorized as good and complies with existing standards, but infrastructure development is still needed to accommodate future increases in passenger numbers.

This research aims to develop a network security system with AdGuard DNS on Debian Linux and control time-based internet access using the Microtik Routerboard. The main challenges are rising network security threats and the need for efficient internet access management in a variety of environments, including families,, education, and offices. The aim of this study is to improve network security and efficiency by blocking harmful content and advertisements, ining user privacy, and regulating internet access at a specific time. Technologies used include DNS AdGuard on Debian Linux to strengthen protection against network security threats and RouterOS Microtik devices to manage internet access based on time. These technologies include content filtering features, network traffic distribution (load balancing), and the ability to block unwanted sites to enhance network performance. Research results show that the combination of AdGuard DNS and   Microtik Routerboard is an effective solution to enhance network security and efficiency. The system is capable of blocking harmful content and advertising, improving user privacy, and adjusting internet access as needed, thus creating a more secure, controlled, and optimal network.

The Raya Blega Street intersection is one of the intersections with a relatively high vehicle volume in Bangkalan Regency. There is no APILL (Traffic Signaling Device) available at this intersection, so it has an impact on traffic flow at the intersection. The existence of the market causes many side obstacles which reduce the optimal performance of the intersection. This condition causes the intersection to experience traffic delays, especially during peak hours such as when leaving work or when leaving. In this research, researchers want to identify the problem of congestion at the Raya Blega street-Rajawali street intersection by calculating and analyzing the performance of the Raya Blega street-Rajawali street intersection using the PKJI 2023 method so that it can be used as a benchmark for assessing the performance of unsignalized intersections and assisting related parties in handle problems at the intersection and it is hoped that they can handle the problems that occur at the intersection so that it can create security and safety for passing users.In this study, the highest value was obtained for existing conditions on Monday, April 29 2024, at morning peak hours (07.00-08.00) at approach point A (east Raya Blega street) with an intersection capacity value of 2297,96 smp/hour and the value obtained The degree of saturation is 0,36 and the delay value is 8.44 sec/smp so it is included in Level of Service B. So the status of the Raya Blega street-Rajawali street Bangkalan Regency intersection is still suitable to be maintained.

The construction of the Parepare City Twin Bridges resulted in increasing vehicle volumes and the occurrence of traffic jams which resulted in obstruction of traffic flow or congestion. The aim of this research is to determine the existing conditions, performance of intersections and road sections and their handling. The type of research used is quantitative, with the data collection method carried out (survey) and the data analysis used is MKJI 1997. The results of this research show that the existing condition of the intersection and road sections in segment 1 is at level of service (LoS) B, segment 2 v/c ratio is at level of service (LoS) A, and segment 3 v/c ratio value is at level of service (LoS) A. The performance of intersections and roads in Segment 1, namely Jl. The peak hour for the Makassar-Parepare axis is 16.00-17.00 (afternoon) Monday, the traffic flow value (Qtot) is 1812.5 pcu/hour, the saturation degree (DS) value is 0.21. Segment 2 is Jl. Gen. M. Yusuf and Jl. Arung Mampi peak hours are 16.00-17.00 (afternoon) on Mondays. The traffic flow value (Qtot) is 262.7 pcu/hour, the degree of saturation (DS) value is 0.05. The handling is installing traffic signs; installation of warning lights or traffic lights.