Mehdi Hamidkhani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mehdi Hamidkhani has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Hossein Malekpoor
Department of Electrical Engineering, Faculty of Engineering, Arak University, Arak, Iran
4 shared publications Homayoon Oraizi
Department of Electrical Engineering, Iran University of Science and Technology Narmak, Tehran, 16846-13114, Iran
3 shared publications- Farzad Mohajeri
School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran
2 shared publications - Rasool Sadeghi
Islamic Azad University, Isfahan, Iran
2 shared publications - Esmaeil Bagheri
Department of Engineering, Deh.C, Islamic Azad University, Isfahan, Iran
1 shared publication Farzad Mohajeri
Department of Electrical Engineering, Shiraz University, Shiraz, Iran
1 shared publication
Latest Publications
- Open Access
- 28 August 2026
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 32 (8) , 1173-1202
Energy-Efficient Cooperative Data Offloading in Cellular Networks Using Reinforcement Learning
To address the growing need for wireless communications energy efficiency, this paper proposes a new multi-agent reinforcement learning (MARL) approach to cooperative data offloading in heterogeneous cellular networks. This research is among the first to employ MARL to this extent, and it offers an end-to-end solution that combines cellular, Wi-Fi, and device-to-device (D2D) communications and considers practical network environments like user mobility and channel conditions. We formulate the offloading problem as a Markov Decision Process (MDP) with correct models of energy consumption and network conditions. The deep Q-network (DQN)-based MARL algorithm allows user equipment (UEs) to learn collaborative strategies for optimizing overall energy consumption and timely offloading of data. Simulations compare MARL against greedy, random, and independent Q-learning baselines in low and high mobility regimes. Experiments show that MARL saves energy by as much as 40% over random offloading and 16.6% over greedy offloading, as well as enhancing average delay, throughput, and fairness. Convergence of the learning rate of the algorithm is within 1000 episodes, and sensitivity analyses confirm its performance across a range of user density and data size settings. Furthermore, the MARL framework accommodates dynamic network conditions and provides an adaptable solution for network operators to maximize performance and sustainability for existing and future wireless networks. The suggested MARL framework still performs better in terms of delay, throughput, and fairness, while at the same time catapulting energy savings over the greedy offloading approach by 9.4% to 12.8% under the very realistic 3GPP-compliant HARQ, adaptive modulation, standardized power control, and urban SLAW mobility models settings. With the extended state/action spaces and realistic 3GPP+SLAW conditions, MARL has an energy savings of 11.7%–14.2% over greedy offloading while still having the leading delay, throughput, and fairness.
- 28 August 2026
- Published by Pensoft Publishers in JUCS - Journal of Universal Computer Science
- Vol. 32 (8) , 1173-1202
Open AccessEnergy-Efficient Cooperative Data Offloading in Cellular Networks Using Reinforcement Learning
To address the growing need for wireless communications energy efficiency, this paper proposes a new multi-agent reinforcement learning (MARL) approach to cooperative data offloading in heterogeneous cellular networks. This research is among the first to employ MARL to this extent, and it offers an end-to-end solution that combines cellular, Wi-Fi, and device-to-device (D2D) communications and considers practical network environments like user mobility and channel conditions. We formulate the offloading problem as a Markov Decision Process (MDP) with correct models of energy consumption and network conditions. The deep Q-network (DQN)-based MARL algorithm allows user equipment (UEs) to learn collaborative strategies for optimizing overall energy consumption and timely offloading of data. Simulations compare MARL against greedy, random, and independent Q-learning baselines in low and high mobility regimes. Experiments show that MARL saves energy by as much as 40% over random offloading and 16.6% over greedy offloading, as well as enhancing average delay, throughput, and fairness. Convergence of the learning rate of the algorithm is within 1000 episodes, and sensitivity analyses confirm its performance across a range of user density and data size settings. Furthermore, the MARL framework accommodates dynamic network conditions and provides an adaptable solution for network operators to maximize performance and sustainability for existing and future wireless networks. The suggested MARL framework still performs better in terms of delay, throughput, and fairness, while at the same time catapulting energy savings over the greedy offloading approach by 9.4% to 12.8% under the very realistic 3GPP-compliant HARQ, adaptive modulation, standardized power control, and urban SLAW mobility models settings. With the extended state/action spaces and realistic 3GPP+SLAW conditions, MARL has an energy savings of 11.7%–14.2% over greedy offloading while still having the leading delay, throughput, and fairness.
- 2 October 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (15) , 1-36
Presenting a fuzzy hierarchical method based on the combination of optimal features and machine learning for load and energy management in the cloud environment
- 2 October 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (15) , 1-36
Presenting a fuzzy hierarchical method based on the combination of optimal features and machine learning for load and energy management in the cloud environment
- Open Access
- 19 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 112446-112460
Improving the Accuracy of Indoor Object Localization in the Internet of Things Using Recurrent Neural Networks (LSTM) in Challenging Environments
Indoor localization is an essential part of many applications of the Internet of Things, and to track an object within a building with the required precision and reliability one needs to give guarantee to accurate indoor location-based services. This study proposes a new mixture of latest deep learning with sparse feature selection to further increase accuracy in the localization of objects in complex indoor environments. The approach uses nearly all the standard techniques to find best signal processing concepts and classification methods, successfully merging them together. The process integrates. Fhor signal noise reduction, statistical, entropic, and stochastic differential modeling methods to identify the features, and then, selects the optimized features to correct the inputs. The Long Short-Term Memory (LSTM) neural network is then trained on the selected features and excels in location classification with an extremely high precision. The experimental results, however, show that the proposed new compact method achieved a higher classification accuracy at 97.5% which was better than that obtained by such classic approaches as CNNs, RNNs, and Random Forest classifiers. Increased optimization is a positive side-effect of harmonizing sparse autoencoders based on a feature selection process, and deep learning classifiers. The discovery must be the result of a cheap and deployable information technology, apart from crucial issues such as energy, noise, and the behavior of the moving objects, and actuators.
- 19 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 112446-112460
Open AccessImproving the Accuracy of Indoor Object Localization in the Internet of Things Using Recurrent Neural Networks (LSTM) in Challenging Environments
Indoor localization is an essential part of many applications of the Internet of Things, and to track an object within a building with the required precision and reliability one needs to give guarantee to accurate indoor location-based services. This study proposes a new mixture of latest deep learning with sparse feature selection to further increase accuracy in the localization of objects in complex indoor environments. The approach uses nearly all the standard techniques to find best signal processing concepts and classification methods, successfully merging them together. The process integrates. Fhor signal noise reduction, statistical, entropic, and stochastic differential modeling methods to identify the features, and then, selects the optimized features to correct the inputs. The Long Short-Term Memory (LSTM) neural network is then trained on the selected features and excels in location classification with an extremely high precision. The experimental results, however, show that the proposed new compact method achieved a higher classification accuracy at 97.5% which was better than that obtained by such classic approaches as CNNs, RNNs, and Random Forest classifiers. Increased optimization is a positive side-effect of harmonizing sparse autoencoders based on a feature selection process, and deep learning classifiers. The discovery must be the result of a cheap and deployable information technology, apart from crucial issues such as energy, noise, and the behavior of the moving objects, and actuators.
- 28 July 2023
- Published by American Geophysical Union (AGU) in Radio Science
- Vol. 58 (8)
Miniaturized High Gain Broadband 16‐Element MIMO Array Using Planar Artificial Magnetic Conductor With Enhanced Isolation for WLAN/WiMAX Applications
A low‐profile 16‐element printed dipole antenna (PDA) array backed by a planar artificial magnetic conductor (AMC) is introduced for multiple‐input multiple‐output (MIMO) wireless communications. The proposed 16‐element MIMO array loaded by a 13 × 13 AMC reflector with various polarized directions exhibits a low‐profile wideband structure, which includes the broad measured bandwidths from 4.25 to 7.25 GHz with increased gains (>8 dBi) and high efficiency. The high isolation between the 16 elements with diverse polarizations is larger than 27 dB and reaches 67 dB over the operating band for MIMO systems. The suggested PDA with a microstrip V‐shaped dipole excited by a V‐shaped microstrip feedline is used to expand the broad simulated band spanning 5.34–6.70 GHz (S11 ≤ −10 dB). Moreover, the suggested 13 × 13 planar fractal AMC reflector is loaded into the PDA array to exhibit a reflection coefficient, S11, of less than −10 dB across the band of 4.26–6.90 GHz for wireless local area network and worldwide interoperability for microwave access applications. The proposed design with AMC compared to the design without AMC exhibits a size reduction of 50.3%, increased gain up to 8.2 dBi, and excellent impedance matching with unidirectional radiation patterns. The novel AMC unit cell is realized based on the planar patch with inserted slots to operate at 6.10 GHz with an AMC band spanning 5.15–7.10 GHz (32%).
- 28 July 2023
- Published by American Geophysical Union (AGU) in Radio Science
- Vol. 58 (8)
Miniaturized High Gain Broadband 16‐Element MIMO Array Using Planar Artificial Magnetic Conductor With Enhanced Isolation for WLAN/WiMAX Applications
A low‐profile 16‐element printed dipole antenna (PDA) array backed by a planar artificial magnetic conductor (AMC) is introduced for multiple‐input multiple‐output (MIMO) wireless communications. The proposed 16‐element MIMO array loaded by a 13 × 13 AMC reflector with various polarized directions exhibits a low‐profile wideband structure, which includes the broad measured bandwidths from 4.25 to 7.25 GHz with increased gains (>8 dBi) and high efficiency. The high isolation between the 16 elements with diverse polarizations is larger than 27 dB and reaches 67 dB over the operating band for MIMO systems. The suggested PDA with a microstrip V‐shaped dipole excited by a V‐shaped microstrip feedline is used to expand the broad simulated band spanning 5.34–6.70 GHz (S11 ≤ −10 dB). Moreover, the suggested 13 × 13 planar fractal AMC reflector is loaded into the PDA array to exhibit a reflection coefficient, S11, of less than −10 dB across the band of 4.26–6.90 GHz for wireless local area network and worldwide interoperability for microwave access applications. The proposed design with AMC compared to the design without AMC exhibits a size reduction of 50.3%, increased gain up to 8.2 dBi, and excellent impedance matching with unidirectional radiation patterns. The novel AMC unit cell is realized based on the planar patch with inserted slots to operate at 6.10 GHz with an AMC band spanning 5.15–7.10 GHz (32%).
- Open Access
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 59164-59173
Analysis of High Gain Wideband 2 × 2 Printed Slot Array With AMC Surface by Presenting Equivalent Transmission Line Model for C and X-Band Applications
A low-profile broadband 2×2 printed slot array with V-shaped slots by loading broadband artificial magnetic conductor (AMC) is demonstrated. A proposed wideband printed array with tapered V-shaped slots with the feeding of coplanar-waveguide (CPW) is measured in 8.24-11.13 GHz. Also, the proposed wideband planar AMC surface is embedded into the printed array to attain enhanced radiation properties. The printed slot array with the 7×7 AMC surface covers -10 dB measured bandwidth from 4.47 to 13.32 GHz (100%). The design loaded by AMC compared to the design without AMC introduces a reduced size of 109.4%, a bandwidth improvement of 70%, and good impedance matching. Moreover, by adding an AMC surface into the printed array, an enhanced gain of 12.3 dBi with uni-directional radiation patterns is attained. The measured gain over the wide bandwidth shows acceptable stability with an average gain of almost 11 dBi. The proposed AMC unit cell is proposed to resonate at 10.10 GHz with a bandwidth of 7.85-12.24 GHz (43.7%) for X-band applications. In addition, the proposed equivalent transmission line model of the antenna with AMC is presented with acceptable output results. This model forecasts the input impedance of the printed array with AMC at the frequency band of 4.50-13.30 GHz as well.
- 13 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 59164-59173
Open AccessAnalysis of High Gain Wideband 2 × 2 Printed Slot Array With AMC Surface by Presenting Equivalent Transmission Line Model for C and X-Band Applications
A low-profile broadband 2×2 printed slot array with V-shaped slots by loading broadband artificial magnetic conductor (AMC) is demonstrated. A proposed wideband printed array with tapered V-shaped slots with the feeding of coplanar-waveguide (CPW) is measured in 8.24-11.13 GHz. Also, the proposed wideband planar AMC surface is embedded into the printed array to attain enhanced radiation properties. The printed slot array with the 7×7 AMC surface covers -10 dB measured bandwidth from 4.47 to 13.32 GHz (100%). The design loaded by AMC compared to the design without AMC introduces a reduced size of 109.4%, a bandwidth improvement of 70%, and good impedance matching. Moreover, by adding an AMC surface into the printed array, an enhanced gain of 12.3 dBi with uni-directional radiation patterns is attained. The measured gain over the wide bandwidth shows acceptable stability with an average gain of almost 11 dBi. The proposed AMC unit cell is proposed to resonate at 10.10 GHz with a bandwidth of 7.85-12.24 GHz (43.7%) for X-band applications. In addition, the proposed equivalent transmission line model of the antenna with AMC is presented with acceptable output results. This model forecasts the input impedance of the printed array with AMC at the frequency band of 4.50-13.30 GHz as well.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2977 (1)
A survey on optimal indoor objects localization in internet of things based on deep learning
Internet of Things (IoT) has connected millions of devices. IoT has enabled the use of smart services in all parts of daily life. Determining the position of objects in their internal environments is a challenge. Locating indoor environments is one of the concerns in using IoT. Several methods have been provided for locating in indoor environments. Methods based on deep learning are among the successful methods in determining the location of objects on the internet in indoor locations. The methods based on deep learning with advantages such as the ability to generalize and make decisions and high accuracy in determining the location of the object are desired. The main goal of this paper is to introduce deep learning methods in determining the internal location of objects.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2977 (1)
A survey on optimal indoor objects localization in internet of things based on deep learning
Internet of Things (IoT) has connected millions of devices. IoT has enabled the use of smart services in all parts of daily life. Determining the position of objects in their internal environments is a challenge. Locating indoor environments is one of the concerns in using IoT. Several methods have been provided for locating in indoor environments. Methods based on deep learning are among the successful methods in determining the location of objects on the internet in indoor locations. The methods based on deep learning with advantages such as the ability to generalize and make decisions and high accuracy in determining the location of the object are desired. The main goal of this paper is to introduce deep learning methods in determining the internal location of objects.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2977 (1)
Lessons from optimal localization of telecommunications drones in fifth generation networks based on unsupervised machine learning methods
Fifth generation mobile 5G networks are used in many countries. Despite the advantages such as high speed, low delay, high security and privacy, there are still challenges such as lack of full coverage, especially in remote areas. Drones with the ability to fly to any possible place have been a way to overcome the challenge of not having complete coverage in the fifth generation. But in order to provide proper coverage in fifth generation networks, the position of these drones should be determined optimally. In such a way that the maximum coverage in the network occurs with the lowest energy consumption. Choosing the right place for the optimal localization of UAVs is one of the important activities in strategic planning for the maximum coverage of fifth generation networks. The positioning of UAVs is a multi-criteria decision, which includes quantitative and qualitative localization criteria. Due to the complexity of positioning in fifth generation networks, traditional positioning methods cannot be used effectively. Using methods based on machine learning can help in this field. Methods based on machine learning have shown their superiority in many research fields. The main goal of this research is to investigate the methods based on machine learning in the optimal localization of drones in order to provide optimal coverage with the least energy consumption.
- 1 January 2023
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2977 (1)
Lessons from optimal localization of telecommunications drones in fifth generation networks based on unsupervised machine learning methods
Fifth generation mobile 5G networks are used in many countries. Despite the advantages such as high speed, low delay, high security and privacy, there are still challenges such as lack of full coverage, especially in remote areas. Drones with the ability to fly to any possible place have been a way to overcome the challenge of not having complete coverage in the fifth generation. But in order to provide proper coverage in fifth generation networks, the position of these drones should be determined optimally. In such a way that the maximum coverage in the network occurs with the lowest energy consumption. Choosing the right place for the optimal localization of UAVs is one of the important activities in strategic planning for the maximum coverage of fifth generation networks. The positioning of UAVs is a multi-criteria decision, which includes quantitative and qualitative localization criteria. Due to the complexity of positioning in fifth generation networks, traditional positioning methods cannot be used effectively. Using methods based on machine learning can help in this field. Methods based on machine learning have shown their superiority in many research fields. The main goal of this research is to investigate the methods based on machine learning in the optimal localization of drones in order to provide optimal coverage with the least energy consumption.
- Open Access
- 13 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 166206-166222
Performance Enhancement of Low-Profile Wideband Multi-Element MIMO Arrays Backed by AMC Surface for Vehicular Wireless Communications
A low-profile printed dipole antenna (PDA) backed by broadband rhomboid artificial magnetic conductor (AMC) is introduced for vehicular wireless communications. Firstly, a suggested PDA with a pair of the microstrip E-shaped dipoles is fed by an E-shaped microstrip feedline to expand the bandwidth in the measured range of 5.5-6.96 GHz (S11≤ -10 dB). Then, the suggested rhomboid AMC reflector is inserted into the PDA to gain improved radiation efficiency up to more than 90%. The PDA loaded by the 3×3 rhomboid AMC array with the size of 48 mm×48 mm×6.8 mm exhibits -10 dB measured impedance bandwidth from 4.48 to 7 GHz (almost 44%) for wireless local area network (WLAN) and worldwide interoperability for microwave access (WiMAX) applications. The suggested PDA with AMC compared to the PDA without AMC exhibits a size reduction of 42.3%, enhanced gain up to 8.4 dBi, and excellent impedance matching (at least -20 dB) with uni-directional radiation patterns. The novel AMC unit cell is realized based on the recognized method as rhomboid coupled parasitic patches. The rhomboid AMC design operates at 6.20 GHz with an AMC bandwidth of 5.10-7.18 GHz (34%). Also, by loading 3×4 and 5×5 AMC reflectors into the two-element and four-element array of PDA, low-profile wideband structures with enhanced radiation properties are achieved. The measured S-parameters show the broad bandwidth from 4.48 to 7.12 GHz in C-band with enhanced gains and efficiencies (more than 90%) of multiple elements. Besides, the suitable isolation between the array elements of more than 30 dB for multiple-input multiple-output (MIMO) systems is achieved by applying various polarized directions of PDAs and loading periodic AMC reflectors.
- 13 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 166206-166222
Open AccessPerformance Enhancement of Low-Profile Wideband Multi-Element MIMO Arrays Backed by AMC Surface for Vehicular Wireless Communications
A low-profile printed dipole antenna (PDA) backed by broadband rhomboid artificial magnetic conductor (AMC) is introduced for vehicular wireless communications. Firstly, a suggested PDA with a pair of the microstrip E-shaped dipoles is fed by an E-shaped microstrip feedline to expand the bandwidth in the measured range of 5.5-6.96 GHz (S11≤ -10 dB). Then, the suggested rhomboid AMC reflector is inserted into the PDA to gain improved radiation efficiency up to more than 90%. The PDA loaded by the 3×3 rhomboid AMC array with the size of 48 mm×48 mm×6.8 mm exhibits -10 dB measured impedance bandwidth from 4.48 to 7 GHz (almost 44%) for wireless local area network (WLAN) and worldwide interoperability for microwave access (WiMAX) applications. The suggested PDA with AMC compared to the PDA without AMC exhibits a size reduction of 42.3%, enhanced gain up to 8.4 dBi, and excellent impedance matching (at least -20 dB) with uni-directional radiation patterns. The novel AMC unit cell is realized based on the recognized method as rhomboid coupled parasitic patches. The rhomboid AMC design operates at 6.20 GHz with an AMC bandwidth of 5.10-7.18 GHz (34%). Also, by loading 3×4 and 5×5 AMC reflectors into the two-element and four-element array of PDA, low-profile wideband structures with enhanced radiation properties are achieved. The measured S-parameters show the broad bandwidth from 4.48 to 7.12 GHz in C-band with enhanced gains and efficiencies (more than 90%) of multiple elements. Besides, the suitable isolation between the array elements of more than 30 dB for multiple-input multiple-output (MIMO) systems is achieved by applying various polarized directions of PDAs and loading periodic AMC reflectors.
- Open Access
- 9 September 2019
- Published by Hindawi Limited in Journal of Electrical and Computer Engineering
- Vol. 2019, 1-11
Dual-Band High Q-Factor Complementary Split-Ring Resonators Using Substrate Integrated Waveguide Method and Their Applications
In modern microwave telecommunication systems, especially in low phase noise oscillators, there is a need for resonators with low insertion losses and high Q-factor. More specifically, it is of high interest to design resonators with high group delay. In this paper, three novel dual-band complementary split-ring resonators (CSRRs) featuring high group delay etched on the waveguide surface by using substrate integrated waveguides are investigated and proposed. They are designed for a frequency range of 4.5–5.5 GHz. Group delay rates for the first, second, and third resonators were approximated as much as 23 ns, 293 ns, and 90 ns, respectively. We also proposed a new practical method to develop a wide tuning range SIW CSRR cavity resonator with a small tuning voltage in the second resonator, which leads to about 19% and 1% of tuning frequency band in the first and second bands, respectively. Finally, some of their applications in the design of filter, diplexer, and low phase noise oscillator will be investigated.
- 9 September 2019
- Published by Hindawi Limited in Journal of Electrical and Computer Engineering
- Vol. 2019, 1-11
Open AccessDual-Band High Q-Factor Complementary Split-Ring Resonators Using Substrate Integrated Waveguide Method and Their Applications
In modern microwave telecommunication systems, especially in low phase noise oscillators, there is a need for resonators with low insertion losses and high Q-factor. More specifically, it is of high interest to design resonators with high group delay. In this paper, three novel dual-band complementary split-ring resonators (CSRRs) featuring high group delay etched on the waveguide surface by using substrate integrated waveguides are investigated and proposed. They are designed for a frequency range of 4.5–5.5 GHz. Group delay rates for the first, second, and third resonators were approximated as much as 23 ns, 293 ns, and 90 ns, respectively. We also proposed a new practical method to develop a wide tuning range SIW CSRR cavity resonator with a small tuning voltage in the second resonator, which leads to about 19% and 1% of tuning frequency band in the first and second bands, respectively. Finally, some of their applications in the design of filter, diplexer, and low phase noise oscillator will be investigated.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Smart Traffic Light Scheduling in Smart City Using Image and Video Processing
The growing population and increased vehicles lead to the main challenges in urban life. Therefore, the role of traffic management will save time and fuel consumption and reduce environmental pollution. In recent years, Internet of Things (IoT) and smart cities drive a new field of intelligent traffic management. In this paper, a new method for traffic light control is presented by using the combination of IoT and image and video processing techniques. In the proposed models, traffic light scheduling is determined based on the density and the number of passing vehicles. Moreover, it is implemented by Raspberry-Pi board and OpenCV tool. The analytical and experimental results indicate the efficiency provided by the proposed models in intelligent traffic management.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Smart Traffic Light Scheduling in Smart City Using Image and Video Processing
The growing population and increased vehicles lead to the main challenges in urban life. Therefore, the role of traffic management will save time and fuel consumption and reduce environmental pollution. In recent years, Internet of Things (IoT) and smart cities drive a new field of intelligent traffic management. In this paper, a new method for traffic light control is presented by using the combination of IoT and image and video processing techniques. In the proposed models, traffic light scheduling is determined based on the density and the number of passing vehicles. Moreover, it is implemented by Raspberry-Pi board and OpenCV tool. The analytical and experimental results indicate the efficiency provided by the proposed models in intelligent traffic management.