Diverse Traffic Patterns Research Articles

Object Detection and Classification Framework for Analysis of Video Data Acquired from Indian Roads

Object detection and classification in autonomous vehicles are crucial for ensuring safe and efficient navigation through complex environments. This paper addresses the need for robust detection and classification algorithms tailored specifically for Indian roads, which present unique challenges such as diverse traffic patterns, erratic driving behaviors, and varied weather conditions. Despite significant progress in object detection and classification for autonomous vehicles, existing methods often struggle to generalize effectively to the conditions encountered on Indian roads. This paper proposes a novel approach utilizing the YOLOv8 deep learning model, designed to be lightweight, scalable, and efficient for real-time implementation using onboard cameras. Experimental evaluations were conducted using real-life scenarios encompassing diverse weather and traffic conditions. Videos captured in various environments were utilized to assess the model’s performance, with particular emphasis on its accuracy and precision across 35 distinct object classes. The experiments demonstrate a precision of 0.65 for the detection of multiple classes, indicating the model’s efficacy in handling a wide range of objects. Moreover, real-time testing revealed an average accuracy exceeding 70% across all scenarios, with a peak accuracy of 95% achieved in optimal conditions. The parameters considered in the evaluation process encompassed not only traditional metrics but also factors pertinent to Indian road conditions, such as low lighting, occlusions, and unpredictable traffic patterns. The proposed method exhibits superiority over existing approaches by offering a balanced trade-off between model complexity and performance. By leveraging the YOLOv8 architecture, this solution achieved high accuracy while minimizing computational resources, making it well suited for deployment in autonomous vehicles operating on Indian roads.

Breaking On-Chip Communication Anonymity using Flow Correlation Attacks

Network-on-Chip (NoC) is widely used to facilitate communication between components in sophisticated System-on-Chip (SoC) designs. Security of the on-chip communication is crucial because exploiting any vulnerability in shared NoC would be a goldmine for an attacker that puts the entire computing infrastructure at risk. We investigate the security strength of existing anonymous routing protocols in NoC architectures, making two pivotal contributions. Firstly, we develop and perform a machine learning (ML)-based flow correlation attack on existing anonymous routing techniques in Network-on-Chip (NoC) systems, revealing that they provide only packet-level anonymity. Secondly, we propose a novel, lightweight anonymous routing protocol featuring outbound traffic tunneling and traffic obfuscation. This protocol is designed to provide robust defense against ML-based flow correlation attacks, ensuring both packet-level and flow-level anonymity. Experimental evaluation using both real and synthetic traffic demonstrates that our proposed attack successfully deanonymizes state-of-the-art anonymous routing in NoC architectures with high accuracy (up to 99%) for diverse traffic patterns. It also reveals that our lightweight anonymous routing protocol can defend against ML-based attacks with minor hardware and performance overhead.

Traffic prediction via clustering and deep transfer learning with limited data

AbstractThis paper proposes a method based on the clustering algorithm, deep learning, and transfer learning (TL) for short‐term traffic prediction with limited data. To address the challenges posed by limited data and the complex and diverse traffic patterns observed in traffic networks, we propose a profile model based on few‐shot learning to extract each detector's unique profiles. These profiles are then used to cluster detectors with similar patterns into distinct clusters, facilitating effective learning with limited data. A Convolutional Neural Network ‐ Long Short‐Term Memory (CNN‐LSTM)‐based predictive model is proposed to learn and predict traffic volumes for each detector within a cluster. The proposed method demonstrates resilience to detector failures and has been validated using the Performance Measurement System dataset. In scenarios with less than 2 months of training data and 10% failed detectors, the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) for station‐level traffic volume prediction increase from 12.7 vehs/5 min, 20.9 vehs/5 min, and 10.5% to 13.9 vehs/5 min, 24.2 vehs/5 min, and 11.7%, respectively. For lane‐level traffic volume prediction, the average MAE, RMSE, and MAPE increase from 4.7 vehs/5 min, 7.7 vehs/5 min, and 15% to 5.6 vehs/5 min, 9.6 vehs/5 min, and 16.8%. Furthermore, the proposed method extends its applicability to traffic speed and occupancy prediction tasks. TL is integrated to improve speed/occupancy prediction accuracy by leveraging knowledge obtained from traffic volume, considering the correlation between traffic flow, speed, and occupancy. When less than 1 month of traffic speed/occupancy data is available for learning, the proposed method achieves an MAE, RMSE, and MAPE of 0.7 km/h, 1.3 km/h, and 1.3% for station‐level traffic speed prediction and 0.5%, 1.1%, and 11% for station‐level traffic occupancy.

Base saturation flow rate (BSFR) and its effect on performance of pretimed signalized intersection with non-lane based urban heterogeneous traffic.

Signalized intersections that are pretimed are commonly used in rapidly developing cities with diverse traffic patterns, including those found in Indonesia. These intersections are a common source of congestion and delays in road networks, particularly when there is non-lane based (NLB) traffic in urban areas. Accurate estimation of both the base saturation flow rate and capacity is essential for this type of facility, as an error in the prediction of the base saturation flow rate can result in significant bias in capacity evaluation and design at signalized intersections. The estimation of capacity at signalized intersections is critical for ensuring optimal signal timings, minimizing delay, and reducing congestion. Heterogeneous traffic, which refers to the presence of various types of vehicles with distinct static and dynamic characteristics, is a common phenomenon. To address this issue, this paper presents a modeling approach for the SFR that takes into account heterogeneous traffic and NLB movements. Indonesia, being an archipelago with 34 provinces, served as the focus of this study, which specifically concentrated on Banda Aceh, the capital province of Aceh province. Employing primary and observed data collected at a specific, predetermined signalized timing, this study aimed to investigate the impact of intersection geometry and heterogeneous traffic composition on the SFR. By adopting the modeling approach for NLB movements, the study formulated the BSFR model. To estimate the scale parameters of the BSFR, the multiple linear regression approach was utilized. The analysis results reveal that the existing BSFR based on the IHCM formula gives a substantially biased estimation because the PCEs from the Indonesian Highway Capacity Manual (IHCM) are underestimated. This source of error could be partially due to the heterogeneous (varied vehicle composition) traffic flow with NLB movements, unlike that observed under the prevailing conditions of IHCM 1997. The empirical results show that the existing IHCM should be improved to avoid overestimation, particularly for effective approach width (We) greater than 4.5 m. A comparison of the BSFR prediction model between IHCM's PCEs and new PCEs shows that the BSFR is predicted more accurately in the latter case. This finding demonstrates that the existing IHCM can be adjusted in two ways: adjusting PCEs or calibrating the BSFR formula. The proposed models can also enhance the accuracy of BSFR prediction, leading to better signalized intersection capacity estimation, providing support for designing traffic operation, alleviating traffic congestion, and reducing congestion delay within the city.

Optimizing VANET Communication through Realistic Traffic Simulation

This article explores the optimization of communication in Vehicular Ad-Hoc Networks (VANETs) through the use of realistic traffic simulation in Raipur City, located in the state of Chhattisgarh. VANETs are a specialized type of Mobile Ad-Hoc Networks (MANETs) that enable vehicles to communicate with each other and with roadside infrastructure, improving road safety, traffic efficiency, and providing additional services. However, VANETs encounter challenges due to the dynamic nature of vehicular environments, including high mobility, intermittent connectivity, and varying traffic conditions. To address these challenges, this study proposes the Integration to Message Exchange (IME) method, which incorporates realistic traffic simulation into VANET communication optimization strategies. Realistic traffic simulation models vehicle behavior and interactions with the road network, considering factors such as traffic flow, congestion, and road conditions. By integrating this simulation into VANET communication optimization algorithms, the performance of the proposed IME method and other routing strategies is evaluated under realistic traffic scenarios. The results demonstrate that the IME method significantly improves message delivery rates and reduces message latency compared to the D-LAR and AODV routing methods. In comparison to the DLAR method, the IME method increases the packet delivery ratio by 4.82%, reduces end-to-end delay by 4.0%, increases throughput by 4.85%, decreases routing overhead by 8.79%, and normalizes routing load by 7.71%. The city of Raipur in Chhattisgarh is the geographical context for this research. Raipur is a rapidly growing urban area with diverse traffic patterns and road conditions. By conducting experiments and simulations in this specific setting, the findings of this study can directly address the challenges faced by VANETs in Raipur City.

Evaluating the Efficacy of Deep Learning Architectures in Predicting Traffic Patterns for Smart City Development

Smart city development necessitates the implementation of effective traffic management strategies. In this vein, various deep learning architectures, including VGG16Net, VGG19Net, GoogLeNet, ResNet-50, and AlexNet, are employed to predict diverse traffic patterns extracted from a comprehensive dataset. Evaluating performance metrics such as accuracy, sensitivity, and specificity reveals discernible variations among models, with ResNet-50 and AlexNet demonstrating superior predictive capabilities. Descriptive statistics and statistical analyses, including ANOVA and the Wilcoxon Signed Rank Test, provide nuanced insights into model differences and significance. The findings bear significant implications for urban planners and policymakers transforming cities into intelligent ecosystems, offering valuable insights for informed decision-making in innovative city development. Improved traffic predictions enhance daily commuting experiences and contribute to the informed development of sustainable urban infrastructure, aligning seamlessly with the ongoing evolution of smart cities toward a more connected and efficient future. Notably, AlexNet exhibits a significant accuracy of 0.931780366 in the context of traffic pattern prediction.

SecureNoC: A Learning-Enabled, High-Performance, Energy-Efficient, and Secure On-Chip Communication Framework Design

We propose SecureNoC, a learning-based framework to enhance NoC security against Hardware Trojan (HT) attacks while holistically improving performance and power. The proposed framework enhances NoC security with several architectural innovations, namely a per-router HT detector, multi-function bypass channels (MBCs), and a lightweight data encryption design. Specifically, the threat detector uses an artificial neural network for runtime HT detection with high accuracy. The MBCs consist of a router bypass route and reconfigurable channel buffers which can efficiently isolate malicious nodes and reduce power consumption. The proposed data encryption design adapts to diverse traffic patterns and dynamically deploys novel lightweight encryption techniques for desired security goals with improved latency. Additionally, to balance the trade-offs and handle the dynamic interactions of the proposed dynamic designs, a proactive deep-Q-learning (DQL) control policy is proposed to simultaneously provide optimized NoC security, performance, and power consumption. Simulation studies using PARSEC benchmarks show that the proposed SecureNoC achieves 36% higher HT detection accuracy over state-of-the-art NoC security techniques while reducing network latency by 39% and energy consumption by 46%.

Meta-STMF: Meta-Learning Based Spatial Temporal Prediction Model Fusion Approach

Traffic prediction is one of the core technology of intelligent transportation systems and is of great importance in traffic management. Among the existing methods, deep learning-based traffic prediction models are the mainstream methods and have achieved decent performance. However, when faced with traffic data with diverse traffic patterns, one model has to divide its attention to account for the prediction performance in different patterns, thus degrading the overall performance. To overcome the limitation, this paper proposes a meta-learning-based spatial-temporal deep learning model fusion approach, called Meta-STMF. The main idea is to assemble a group of sub-models so that each sub-model can focus on the patterns it specializes in. The method first trains each sub-model separately. Then, it extracts meta-knowledge from the input traffic data and utilizes a meta-learner to generate adaptive combination weights for each sub-model. Finally, the combination weights are used in the fusion of every sub-model prediction to obtain the final prediction. Extensive experiments on two large-scale real-world datasets show that our proposed approach consistently outperforms all competing baseline models with a large margin.

IoT Provisioning QoS based on Cloud and Fog Computing

The wide-spread Internet of Things (IoT) utilization in almost every scope of our life made it possible to automate daily life tasks with no human intervention. This promising technology has immense potential for making life much easier and open new opportunities for newly developed applications to emerge. However, meeting the diverse Quality of Service (QoS) demands of different applications remains a formidable topic due to diverse traffic patterns, unpredictable network traffic, and resource-limited nature of IoT devices. In this context, application-tailored QoS provisioning mechanisms have been the primary focus of academic research. This paper presents a literature review on QoS techniques developed in academia for IoT applications and investigates current research trends. Background knowledge on IoT, QoS metrics, and critical enabling technologies will be given beforehand, delving into the literature review. According to the comparison presented in this work, the commonly considered QoS metrics are Latency, Reliability, Throughput, and Network Usage. The reviewed studies considered the metrics that fit their provisioning solutions.

Short-Term Traffic Prediction Based on DeepCluster in Large-Scale Road Networks

Short-term traffic prediction (STTP) is one of the most critical capabilities in Intelligent Transportation Systems (ITS), which can be used to support driving decisions, alleviate traffic congestion and improve transportation efficiency. However, STTP of large-scale road networks remains challenging due to the difficulties of effectively modeling the diverse traffic patterns by high-dimensional time series. Therefore, this paper proposes a framework that involves a deep clustering method for STTP in large-scale road networks. The deep clustering method is employed to supervise the representation learning in a visualized way from the large unlabeled dataset. More specifically, to fully exploit the traffic periodicity, the raw series is first divided into a number of sub-series for triplet generation. The convolutional neural networks (CNNs) with triplet loss are utilized to extract the features of shape by transforming the series into visual images. The shape-based representations are then used to cluster road segments into groups. Thereafter, a model sharing strategy is further proposed to build recurrent NNs-based predictions through group-based models (GBMs). GBM is built for a type of traffic patterns, instead of one road segment exclusively or all road segments uniformly. Our framework can not only significantly reduce the number of prediction models, but also improve their generalization by virtue of being trained on more diverse examples. Furthermore, the proposed framework over a selected road network in Beijing is evaluated. Experiment results show that the deep clustering method can effectively cluster the road segments and GBM can achieve comparable prediction accuracy against the IBM with less number of prediction models.

Data Science and Artificial Intelligence for Communications

The five articles in this special section focus on data science and artificial intelligence (AI) for communications. The innovation in AI, machine learning (ML), and network data analytics provides a huge opportunity to revolutionize the world’s communications systems and user experience. Through gathering, processing, learning, and controlling the vast amounts of information in an intelligent manner, these analytics tools enable the possibility to automate and optimize systems in a way that was not previously possible. This is particularly important as the communications infrastructures evolve to support increasingly more complex human type as well as machine type communications and enable, through the connectedness of meters, sensors, and things, a plethora of new services. Supporting such immensely diverse traffic patterns and applications will require dynamic, highly adaptive network environments, all the while ensuring highly reliable, secure, and ultra-low-latency service performance guarantees.

In Compute/Memory Dynamic Packet/Circuit Switch Placement for Optically Disaggregated Data Centers

Network function services on conventional hybrid data center (DC) architectures such as HELIOS arehard-wiredanddedicatedto specificnetworkresources. This limits flexibility and performance to handle diverse traffic patterns. Furthermore, disaggregation of server resources has shown promising potential to improve resource utilization, which has been a limitation of conventional server-centric DCs. This paper presents a reconfigurable hybrid disaggregated DC (dRedBox) architecture that combines the concept of server resource disaggregation with cutting-edge software and electronic and optical technologies. ThedRedBoxarchitecture provides a remarkable amount of flexibility and connectivity through hardware-based multilayer network function service programmability. This allows for multilayer network services to be dynamically deployed at runtime to network resources and, in turn, handle diverse traffic patterns. Furthermore, this study proposes algorithms and strategies for selecting and deploying electronic packet switching and optical circuit switching function services to implement virtual machine network requests across dRedBox and conventional hybrid disaggregated architectures under different traffic patterns. Finally, the performance of the various strategies on the dRedBox and conventional hybrid disaggregated DC architectures is evaluated in terms of blocking probability, energy efficiency, network utilization, and cost. Extensive results show that, at 10% blocking probability, dRedBox architecture achieves 100% gain on VM placement and 92% energy savings compared with conventional hybrid disaggregated architectures.

Cellular Network Traffic Scheduling With Deep Reinforcement Learning

Modern mobile networks are facing unprecedented growth in demand due to a new class of traffic from Internet of Things (IoT) devices such as smart wearables and autonomous cars. Future networks must schedule delay-tolerant software updates, data backup, and other transfers from IoT devices while maintaining strict service guarantees for conventional real-time applications such as voice-calling and video. This problem is extremely challenging because conventional traffic is highly dynamic across space and time, so its performance is significantly impacted if all IoT traffic is scheduled immediately when it originates. In this paper, we present a reinforcement learning (RL) based scheduler that can dynamically adapt to traffic variation, and to various reward functions set by network operators, to optimally schedule IoT traffic. Using 4 weeks of real network data from downtown Melbourne, Australia spanning diverse traffic patterns, we demonstrate that our RL scheduler can enable mobile networks to carry 14.7% more data with minimal impact on existing traffic, and outpeforms heuristic schedulers by more than 2x. Our work is a valuable step towards designing autonomous, "self-driving" networks that learn to manage themselves from past data.

Rescue‐Sink: Dynamic sink augmentation for RPL in the Internet of Things

AbstractThe Internet of Things (IoT) is largely built on the interconnection of low‐power networked devices, generally referred to as low‐power and lossy networks (LLNs). The prime routing protocol designed over IPv6, named routing protocol for LLNs (RPL), presents the main effort to standardize an IPv6‐based routing protocol for all LLNs. Routing protocol for LLNs has gained significant prominence in IoT research due to its flexibility in adapting to different topologies and could run in agnostic replicas over the same network to serve different applications. However, as RPL is based on virtualizing a tree topology, many challenges ensue in scaling with network traffic and diverse traffic patterns in the IoT. The current RPL standard focus on operation under a single sink, toward which all traffic flows, and thereby its survivability determines the lifetime of the IoT network. However, it mentions briefly in its RFC6550, the using of multiple roots. However, it does not study when, where, and how deploying multiple roots. In this paper, we propose a dynamic Rescue Sink protocol, which actively monitors the performance of IoT nodes in a given RPL network and introduces a dynamic mechanism for mitigating RPL performance by introducing new sinks when needed. We define a suffering index computed over intervals by RPL nodes in a decentralized approach, which monitors their tendency to yield high traffic load without inducing control overhead. Furthermore, our Rescue Sink protocol is designed in line with the RPL standard, and we elaborate on all the components to integrate with the standard. We present a thorough evaluation of our Sink Rescue protocol, using the Cooja simulator over the Contiki OS, most prevalently used in IoT devices. We demonstrate the performance improvements in terms of energy consumption and data delivery.

A Virtual Channel Allocation Algorithm for NoC

Virtual channel (VC) flow control proves to be an alternative way to promote network performance, but uniform VC allocation in the network may be at the cost of chip area and power consumption. We propose a novel VC number allocation algorithm customizing the VCs in network based on the characteristic of the target application. Given the characteristic of target application and total VC number budget, the block probability for each port of nodes in the network can be obtained with an analytical model. Then VCs are added to the port with the highest block probability one by one. The simulation results indicate that the proposed algorithm reduces buffer consumption by 14.58%–51.04% under diverse traffic patterns and VC depth, while keeping similar network performance.

DT-RPL: Diverse bidirectional traffic delivery through RPL routing protocol in low power and lossy networks

As part of Internet of Things, low-power lossy network (LLN) applications are being diversified, which requires LLNs to support diverse traffic patterns. In this paper, we address performance issues of IPv6 routing protocol for LLNs (RPL) when delivering various traffic patterns. Specifically, we show that RPL was designed to mainly support upward traffic, and thus cannot construct reliable multi-hop routes for downward traffic-centric applications. To solve the problem effectively, we provide an improved RPL implementation, termed DT-RPL, which fast updates wireless link quality through both upward and downward traffic to support Diverse Traffic patterns. It is enabled to update routes in dynamic link environments regardless of traffic patterns. Our results in a multi-hop testbed over IEEE 802.15.4 links reveal that our scheme significantly improves RPL’s performance in various traffic scenarios, in terms of packet delivery ratio, control overhead and radio energy consumption.

A Framework for Efficient Routing in MANET using Index Routing Tables-based Algorithms

Conventional network routing protocols rely on predefined numerical network unique node ID or group identifier for packet delivery, independent of semantic applications. This compels incorporation of resource/service discovery approaches in the design itself, at higher layers of network, causing additional overhead. This overhead, though tolerable in high speed wired networks, significantly restricts the performance in the infrastructure-less wireless ad hoc networks expending their limited battery resources, which are already consumed due to assigning unique identifiers to the naturally anonymous and high mobile nodes. This study proposes a single routing approach which facilitates descriptive and semantically-rich identification of network’s resources/services. This fusion of the discovery processes of the resources and the path based on their similarity in a single phase significantly reduces traffic load and latency of communication considering the generality too. Further, a framework capable of exploiting application-specific semantics of messages, adaptable to diverse traffic patterns is proposed. Analytical results amply illustrate the scalability and efficacy of the proposed method.

The performance of MIN-based switch fabrics

A new method for the performance analysis of multistage interconnection networks (MINs) is presented. It supports modelling and analysis of switch fabrics built on such switching networks. The method is based on the idea of a generalized traffic source outlined in the paper. Using the generalized traffic idea, the new method overcomes the problems and limitations encountered in existing MIN performance analysis methods and can capture a larger variety of switching networks. Application of the proposed method and its generalizability are discussed. A higher flexibility of this new method to consider diverse traffic patterns is also reported. Sample results of the analysis proposed in this contribution are compared with the results of earlier methods and found superior. Simulation validation is also provided. The method is simple yet powerful enough to help designers to find the optimal structure of switching network for building a scalable router.

A GPS Analysis for Urban Freight Distribution

Daily life in urban centers has led to increasing and more demanding freight requirements. Manufacturers, retailers and other urban agents have thus tended towards more frequent and smaller deliveries, resulting in a growing use of light freight vehicles (<3.5 ton). This paper characterizes and analyzes urban freight distribution in order to generate new ways of understanding the phenomenon. Based on a case study of two different-sized Spanish cities using data from GPS, a vehicle observation survey and complementary driver's interviews, the authors propose a categorization of urban freight distribution. The results confirm GPS as a useful tool that allows the integration of dynamic traffic assignment data and diverse traffic operation patterns during different day periods, thereby improving delivery performance.

도시교통정보시스템을 위한 분산 계층 경로탐색 기법 설계

본 논문은 새로운 도시 교통 정보 시스템의 교통정보에 맞는 경로탐색 비용 산출법을 제시하고, 이 시스템을 전국적으로 운용 하고자 할 때, 운전자에게 효율적인 경로탐색을 지원하는 시스템 및 알고리즘을 제안한다. 새로운 시스템은 차선별로 각기 제공되는 모든 구간속도를 고려하여 비용을 계산 하고, 교통정보의 단위 데이터 양 및 운전자의 생활 패턴에 맞게 교통정보를 처리하는 계층을 논리적으로 나누어서, 각 계층 별로 다른 레벨의 교통정보 서비스를 제공한다. 또한 제시된 알고리즘은 양방향 프로토콜에 맞게 사용자 맞춤형 교통 정보 서비스를 제공하고, 운전자가 선택한 출발지와 목적지의 지리적인 거리와 시스템의 계층에 따라 효율적인 경로 탐색 및 재탐색이 이루어지도록 한다. 또한 본 논문은 추가적으로 이루어질 연구와 현재 경찰청 주도로 이루어지는 단위 도시별 시스템의 상호 연동을 위한 여러 가지 필요한 요구사항을 제시한다. This paper suggests new route plan cost calculation and cost-effective route plan algorithm and architecture for the new city traffic information system when it is operated nationwide. New algorithm and architecture estimates cost with traffic speeds which is supported for all different lanes, stratifies logical layer which process different levels' traffic information with diverse traffic patterns and provides different traffic information in the few levels. Also suggested new algorithm supports drivers' customized traffic information through both-way communications and plans routes effectively based on the distance between drivers' start position and destination and different levels which start and end position located. It proposes additional research items and requirement for integration between different cities' traffic information system which the national police agency invested and led.