Adaptive IoT Empowered Smart Road Traffic Congestion Control System Using Supervised Machine Learning Algorithm

Ata, Ayesha; Khan, Muhammad Adnan; Abbas, Sagheer; Ahmad, Gulzar

doi:10.1093/comjnl/bxz129

Cited by 39 publications

(18 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If LC is met, it passes that data into the cloud. Otherwise, it must be retrained [36]. e next step is to apply fuzzy logic to fuse the results of both techniques to improve the overall performance of the proposed technique.…”

Section: Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Brain Tumor Detection using Decision-Based Fusion Empowered with Fuzzy Logic

Tahir

Asif

Ahmad

et al. 2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Brain tumor is regarded as one of the fatal and dangerous diseases on the planet. It is present in the form of uncontrolled and irregular cells in the brain of an infected individual. Around 60% of glioblastomas turn into large tumors if it is not diagnosed earlier. Some valuable literature is available on tumor diagnosis, but there is room for improvement in overall performance. Machine Learning (ML)-based techniques have been widely used in the medical domain for early diagnostic diseases. The use of ML techniques in conjunction with improved image-guided technology may help in improving the performance of the brain tumor detection process. In this work, an ML-based brain tumor detection technique is presented. Adaptive Back Propagation Neural Network (ABPNN) and Support Vector Machine (SVM) algorithms are used along with fuzzy logic. The fuzzy logic is used to fuse the result of ABPNN and SVM. The proposed technique is developed using the BRATS dataset. Experimental results reveal that the ABPNN model achieved 98.67% accuracy in the training phase and 96.72% accuracy in the testing phase. On the other hand, the SVM model has attained 98.48% and 97.70% accuracy during the training and testing phases. After applying fuzzy logic for decision-based fusion, the overall accuracy of the proposed technique reaches 98.79% and 97.81% for the training and the testing phases, respectively. The comparative analysis with existing techniques shows the supremacy of the proposed technique.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

“…1128 samples are used for testing, i.e., 30% of the data samples [47,48]. To evaluate the proposed system, several performance measure metrics are used that are computed with the help of equations ( 27) to (36) [49].…”

Section: Experimental Analysismentioning

confidence: 99%

Brain Tumor Detection using Decision-Based Fusion Empowered with Fuzzy Logic

Tahir

Asif

Ahmad

et al. 2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…In particular, the convergence bound will decrease as the total number of iterations K increases, and it can be also declined by the model's better initial parameters θ0 . Taking into account the multi-agent parallel training paradigm, increasing the number of participating agents m in 1 The Supplemental Material is available at https://www.rongpeng.info/files/sup icc2022.pdf. the framework of FIRL can reduce the convergence bound, but this comes at the expense of more resource cost according to (4) and may lead to a reduction in the system's utility value according to (9).…”

Section: Consensus In Periodic Averaging Methodsmentioning

confidence: 99%

“…With the development of wireless communication and advanced machine learning technologies in the past few years, a large amount of data has been generated by smart devices and can enable a variety of multi-agent systems, such as smart road traffic control [1], smart home energy management [2], and the deployment of unmanned aerial vehicles (UAVs) [3]. Through deep reinforcement learning (DRL), an intelligent agent can gradually improve the performance of its parameterized policy via the trial-and-error interaction with the environment.…”

Section: Introductionmentioning

confidence: 99%

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

Xu¹,

Li²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.

show abstract

“…Also SVM is applied to analyzed traffic congestion analysis. Traffic congestion at particular point was also notified (7) . Duc-Binh Nguyen proposed fuzzy based traffic congestion algorithm based on velocity of the vehicle and congestion coefficient.…”

Section: Related Workmentioning

confidence: 99%

Intelligent signalling system to control traffic in vehicular ad hoc networks R

Lalitha¹,

Srinivas²,

Kumar³

et al. 2020

IJST

View full text Add to dashboard Cite

Traffic congestion problem persists more at junctions and causes inconvenience to public. Owing to this, people may not reach their destinations in time. Although there are alerts in mobile phones regarding arrival times of flight services and other journey related information due to sudden traffic jams at junctions these advanced technology innovations are being becoming fragile. Since long, many researchers have been putting their efforts to find remedies for reducing traffic congestion. Objectives: The key focus is on balancing forwarding time and waiting time at junctions based on the number of vehicles arrived at that junction. Methods: The proposed system uses Internet of Things (IoT) based monitoring to control signaling system. IR sensors are used to count number of vehicles passing over the lane by triggering clock for object detection. The signaling time can be changed dynamically based on the vehicle count, so that more time is allocated to the lanes which have more traffic and the remaining time is adjusted among other lanes. This reduces congestion at dense traffic lanes. Findings: There will be time variant setting of signal lights based on the density of the traffic. The dense traffic lanes will be allotted more time and will be cleared first. Expanding on this point, the time adjustment is done based on the vehicle count not on periodical fixation of intervals. Novelty: The ecosystem developed provides an ultimate solution to vehicle users for comfortable movement on the roads without being delayed.

show abstract

Adaptive IoT Empowered Smart Road Traffic Congestion Control System Using Supervised Machine Learning Algorithm

Cited by 39 publications

References 5 publications

Brain Tumor Detection using Decision-Based Fusion Empowered with Fuzzy Logic

Brain Tumor Detection using Decision-Based Fusion Empowered with Fuzzy Logic

Communication-Efficient Consensus Mechanism for Federated Reinforcement Learning

Intelligent signalling system to control traffic in vehicular ad hoc networks R

Contact Info

Product

Resources

About