The Domain Name System (DNS) plays a critical role in the functioning of the Internet, providing essential resolution services for nearly all user activities. In this work, we examine the hypothesis that individual users exhibit recurrent and distinctive patterns in their DNS query behavior, which can be leveraged to create unique and robust user fingerprints. Building on a publicly available dataset of real DNS traffic collected from a large-scale network, we evaluate the feasibility of user identification solely based on these behavioral DNS traces, independent of IP address stability. We conducted a comparative study of several machine learning models - including Naive Bayes, Random Forests, XGBoost, Multilayer Perceptrons, and Convolutional Neural Networks - on their ability to classify users based on domain category frequencies and derived statistical features. After extensive data preprocessing, dimensionality reduction, and feature selection, our best-performing model (CNN) achieves a classification accuracy of 86.7% across 1727 classes (unique IP addresses). The results confirm the viability of DNS-based user fingerprinting, even in the presence of dynamic IP addresses. Our approach opens new avenues for applications in network forensics and anomaly detection, while also raising important questions about privacy and ethical use of passive traffic analysis.

A new flexible skewed bimodal distribution with multivariate extensions: Theory and application to traffic crash injury severity analysis

A vine copula-based analysis of spatial dependence of traffic conflict risk at highway ramp areas.

SQL injection is a common and dangerous attack vector in web applications that allows attackers to execute malicious SQL queries to gain unauthorized access to the database. We aim to develop a more adaptive and resilient system that can dynamically evolve and adapt to new attack patterns. SQL injection detection and prevention has the potential to significantly improve the security of web applications and provide better protection against SQL injection attacks. Intrusion detection and prevention systems (IDPS) play a critical role in safeguarding computer networks from malicious activities and security breaches. Traditional IDPS solutions often struggle to adapt to evolving threats and exhibit limitations in accurately detecting and preventing sophisticated attacks. This approach is for enhancing IDPS capabilities through the integration of a hybrid genetic algorithm (HGA). By combining the evolutionary search capabilities of genetic algorithms with the domain-specific knowledge and rules of intrusion detection systems, the proposed HGA offers a robust framework for improving detection accuracy and reducing false positives. The hybridization process involves incorporating genetic operators, such as crossover and mutation, into the rule-based detection mechanisms of IDPS. Additionally, the HGA dynamically adjusts detection thresholds and parameters based on real-time network traffic analysis, enabling adaptive and proactive defense mechanisms against emerging threats.

The increasing intensity of traffic object movement in urban areas has not been accompanied by adequate road infrastructure, resulting in traffic congestion, air pollution, and a higher risk of traffic accidents. One of the primary causes of accidents is traffic violations, particularly wrong-way driving behavior. This study develops a video-based automated traffic violation detection system using the YOLOv5 algorithm. A computer vision approach is employed to detect, classify traffic objects, and count wrong-way violations in real time. Due to limited access to real-world traffic violation footage, simulated traffic scenarios are used as testing data. The system is evaluated on four traffic object classes: motorcycles, cars, buses, and trucks. Experimental results demonstrate strong performance, achieving a precision of 90%, a recall of 92%, and an F1-score of 91%, while the traffic object counting accuracy reaches 89%. These findings indicate that the proposed system has significant potential to support traffic analysis and assist authorities in making more effective decisions to reduce congestion and traffic accidents.

This study aims to analyze the magnitude of the impact or influence caused by the Trading Market development activities, which can affect traffic performance in the surrounding area so as to minimize the impact on traffic disruption. This study uses initial calculations carried out to find the peak hour (pcu/hour), namely by changing the traffic volume data that is still in units of vehicles/hour, then multiplied by the passenger car equivalent factor (pcu). The value of the passenger car equivalent factor (pcu) refers to the Indonesian Road Capacity Guidelines (PKJI) 20223. The results show the degree of saturation of the new market road segment 2 at the highest peak hour of the existing condition is 0.55, during the construction period of 2024 is 0.60. During the operational period of 2025 is 0.57 and the prediction of 5 (five) years in 2030 is 0.67. The degree of saturation of the new market road segment 1 at the highest peak hour of the existing condition is 0.08, during the construction period of 2024 is 0.09. During the operational period of 2025 is 0.09 and the prediction of 5 (five) years in 2030 is 0.11. The degree of saturation of the Rajamin Purba road segment 1 at the highest peak hour of the existing condition is 0.86, during the construction period of 2024 is 0.88, During the operational period of 2025 is 0.89 and the prediction of 5 (five) years in 2030 is 1.05. The degree of saturation of Rajamin Purba road segment 2 during the highest peak hour in existing conditions is 0.86, during the construction period in 2024 it is 0.91, during the operational period in 2025 it is 0.88 and the 5 (five) year prediction in 2030 is 0.99.

This study investigates the operational characteristics of heterogeneous traffic flow on freeways comprising human-driven vehicles (HVs) and connected autonomous vehicles (CAVs) by developing an improved heterogeneous traffic flow model that integrates both car-following and lane-changing behaviors of HVs and CAVs. The car-following and lane-changing behaviors of HVs are modeled using the intelligent driver model (IDM) and the minimizing overall braking induced by the lane-changing (MOBIL) model. For CAV car-following behavior, the IDM is enhanced to incorporate complete state information from multiple leading vehicles. Furthermore, the MOBIL model is refined to develop an autonomous lane-changing model for CAVs, accounting for the influence of multiple following vehicles. Game theory models the competitive and cooperative interactions among multiple CAVs, leading to a cooperative lane-changing model. Simulations are conducted using MATLAB. The results demonstrate that, compared with existing combinations of the IDM and MOBIL models, the proposed model yields substantial improvements in traffic flow stability and safety. An increased CAV penetration rate further improves traffic capacity, with particularly pronounced effects observed when the CAV penetration rate exceeds 0.4. These findings provide valuable theoretical insights into research on traffic flow modeling, capacity analysis, and traffic management strategies.

Encrypted network traffic analysis using quantum machine learning

Traffic analysis for secure communication: robust DoH tunnel detection via temporal convolutional network with semantic modulation and ReLU attention

Objectives This study aims to identify stable factors associated with traffic conflict risk in expressway weaving segments, with a particular focus on addressing the challenge of unobserved data distribution bias between training and test datasets, which can compromise model reliability. Methods To mitigate distribution bias and enhance result robustness, a causally regularized logistic model (CRLM) with a global causal regularizer was employed. To validate the stability of the CRLM, multi-dataset validation and model parameter consistency tests were conducted using five datasets collected from the field and simulation in two weaving types. Meanwhile, classic logistic regression (LR) and eXtreme Gradient Boosting (XGBoost) were developed for comparison. Results In the multi-dataset validation test, the average area under receiver operating characteristic curve (AUC) of the CRLMs is close to that of the XGBoosts, but with a lower standard deviation, suggesting that the CRLM provides more stable predictive performance across different combinations of training and testing datasets. In the model parameter consistency test, the CRLM can identify more stable factors across heterogeneous traffic environments. Furthermore, the causal mechanisms underlying traffic conflict risk in Type A and Type B weaving segments are distinct. The hazardous traffic flow characteristics for each weaving type were discussed in detail. Conclusions These findings provide a novel and robust methodological framework for traffic conflict risk analysis. In addition, the model results have practical implications for developing proactive traffic control strategies and enhancing automated driving systems (ADS) to improve traffic safety in expressway weaving segments.

ABSTRACT Traffic crash analysis of mountainous freeways frequently relies on imbalanced data, hindering effective prediction of fatal crashes. Previous research has not fully explored performance improvement for fatal crash prediction, leading to insufficient model performance. This study proposes a two-stage prediction (TSP) framework based on Stacked Sparse Autoencoder (SSAE), which sequentially classifies each injury severity to enhance prediction performance. First, K-means is used for unsupervised clustering to improve data homogeneity. The Adaptive Synthetic Sampling Approach (ADASYN) balances the dataset by increasing sample size. Then, LightGBM with Partial Dependence Plot (PDP) analysis identifies key features and reveals their nonlinear relationships with injury severity. The TSP-SSAE model is compared with Support Vector Machine (SVM), LightGBM, and Deep Neural Network (DNN). Results show TSP-SSAE achieves higher accuracy, precision, recall, and F1-score. It effectively handles extreme data imbalance and improves predictive performance, particularly enhancing fatal crash prediction accuracy, thereby providing insights for traffic safety management.

Mobile messaging platforms are increasingly targeted by large-scale spam, phishing, and fraud campaigns. This paper presents a comprehensive, defense-in-depth approach for protecting SMS and modern chat platforms. It explores traffic analysis, machine learning–based detection, behavioral graph modeling, and enforcement mechanisms that collectively disrupt abuse at scale. The study discusses key trade-offs between accuracy, latency, and user experience, demonstrating how layered protections significantly reduce spam volume and limit the economic viability of messaging abuse.

Green lane is one of the green open space functioning to reduce pollution air in urban areas. The research aims to formulate directions development of green lanes on the collector roads in Surakarta. Method analysis used is descriptive quantitative, with utilize analysis spatial in the process of processing GIS data and translating results process data into informative. While quantitative analysis used technique scoring for determine development areas of green lanes. The process analysis carried out is traffic density analysis, comfort level analysis and density canopy analysis. This research shows that there is as many as 71 collectors roads section in Surakarta which classified the green lanes development in two classifications, specifically: Priority 1 (very need development) and Priority 2 (requires development). Analysis results show there are 4 sections of collector road which in priority 1 green lanes development, specifically Kapten Mulyadi Road, Komodor Yos Sudarso Road, S. Parman Road, and Sutan Syahrir Road.

The rapid growth of computer networks has increased demand for more sophisticated tools for network traffic analysis and monitoring. The increasing reliance on networks has amplified the need for robust security and intrusion detection mechanisms. Numerous studies have sought to develop efficient methods for fast and accurate intrusion detection, each addressing the challenge from different perspectives. A common limitation among these approaches is their reliance on expert-engineered features extracted from network traffic. This dependency makes them less adaptable to emerging attack techniques and changes in normal traffic patterns, often resulting in suboptimal performance. In this study, we propose a method leveraging recent advancements in artificial neural networks and deep learning, specifically using recurrent neural networks (RNNs), for network traffic analysis and intrusion detection. The key advantage of this approach is its ability to autonomously extract features from network traffic without human intervention. Trained on the ISCX IDS 2012 dataset, the proposed model achieved an accuracy of 0.99 in distinguishing between malicious and normal traffic.

The pulse of MQTT in the wild: A large-scale traffic analysis

TrafficLLM: LLMs for improved open-set encrypted traffic analysis

A domain-specific autonomous agent for network traffic analysis

Most freeway accidents do not cause complete traffic breakdowns but create bottlenecks that significantly compromise traffic safety and efficiency, making safe and efficient vehicle passage essential. This paper proposes a proactive emergency traffic control architecture based on deep reinforcement learning to optimize traffic flow in accident-induced bottlenecks. Based on the traffic flow mechanism analysis in bottlenecks, a combined control strategy, integrating hierarchical differential variable speed limits (HDVSL) and lane change guidance (LCG), is devised to improve both macroscopic traffic coordination and microscopic vehicle behavior. Furthermore, to overcome perceptual limitations under complex traffic dynamics, we developed the Recurrent Soft Actor-Critic (R-SAC) algorithm. The ability to capture temporal sequential dependencies is accomplished by embedding a recurrent temporal modeling module within the policy network. Additionally, the memory and state augmentation module further enhances the adaptability to dynamic traffic patterns. A simulation-based evaluation was conducted in high-accident frequency mainline scenarios, and the results demonstrate that the proposed approach significantly outperforms existing strategies and models in both safety and efficiency. Specifically, it improves safety by 38.6% (measured by speed standard deviation) and efficiency by 35.7% (measured by travel time through the bottleneck) compared to the no-control scenario, and further surpasses the soft actor-critic algorithm by 5.4% and 5.9%, respectively. Moreover, the systematic evaluations of state engineering and generalization establish a principled basis for effective state selection and verify the model’s robustness, providing theoretical insights and practical guidance for emergency traffic management.

This study aimed to develop a machine-learning-based predictive model for winter traffic-accident risk using meteorological variables and analyze the influence of weather factors on accident occurrence. The study area consisted of five cities in Gyeonggi-do, South Korea—Dongducheon, Paju, Yangpyeong, Icheon, and Suwon—where automated surface observing system (ASOS) stations are located. Winter traffic-accident data from 2015 to 2023 were collected from the traffic accident analysis system (TAAS), and meteorological observations were obtained from the Korea Meteorological Administration. The dependent variable was constructed based on accidentoccurrence levels; ten meteorological variables, including temperature, solar radiation, wind speed, humidity, and cloud cover, were the independent variables. Softmax Regression, Random Forest, and XGBoost models were employed for prediction, and their performances were compared in terms of prediction accuracy and feature importance. The results revealed that the Random Forest model demonstrated the highest predictive performance across all regions. In addition, solar radiation, wind speed, and cloud cover significantly influenced accident occurrence beyond the widely assumed impact of temperature alone. These findings highlight the potential of machine-learning models as decision-support tools for winter road-safety management and proactive accident-prevention policies.

Traffic congestion is a growing concern in rapidly urbanizing cities, particularly in Dhaka, where mixed traffic conditions and poor infrastructure exacerbate delays and reduce mobility. This study aims to evaluate traffic flow characteristics and volume along the corridor from Sony Square to Mirpur 10 and identify the key contributors to congestion. The research follows a systematic methodology involving manual traffic volume counts using tally counters and video recordings at strategic locations across four daily time slots over ten consecutive days. The collected data were categorized by vehicle type and analyzed through conversion to Passenger Car Units (PCU) to standardize heterogeneous traffic. Microsoft Excel was employed for data tabulation, graphical analysis, and service flow rate calculations. The Highway Capacity Manual (HCM) framework was used to evaluate the Level of Service (LOS) at different times of day. The findings reveal that evening peak hours exhibit the most critical congestion levels (LOS F), while morning peaks also approach capacity (LOS E). Midday and afternoon periods show relatively smoother flow (LOS B and LOS C/D, respectively). Contributing factors to congestion include excessive vehicular traffic, the absence of dedicated lanes, inefficient signal timings, unauthorized street parking, and a lack of traffic discipline among both pedestrians and drivers. Based on these insights, the study proposes practical recommendations, including the implementation of dedicated lanes, optimized signal coordination, strict enforcement of parking regulations, and enhanced public transportation operations. These strategies aim to alleviate congestion and support efficient traffic management in urban corridors, such as Mirpur 10