Direct synthesis approach for designing high selectivity microstrip distributed bandpass filters combined with deep learning

Dai, Xinyue; Yang, Qian; Du, Hao; Li, Jianxing; Guo, Cheng; Zhang, Anxue

doi:10.1016/j.aeue.2020.153499

Cited by 11 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data integration and intelligent deep learning can help to analyze this information and make predictions about future traffic patterns. In addition, decision-making and training of intelligent processes can be used to adapt and improve the performance of the congestion control system [12].…”

Section: Introductionmentioning

confidence: 99%

“…Reinforcement learning [12,13] is an artificial learning approach that has proven outstanding results in recent applications of controlling complex systems that have high non-linearity and dynamic nature, such as driverless vehicles [14], unmanned aerial vehicle control [15], and other types of systems which involves sensor reading, data analysis, decision making, and re-training or adaptation. Intelligent traffic control is a suitable example of a highly complex and dynamic system that requires intelligent control and adaptation to external factors [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Al-Heety,

Zakaria,

Abu-Khadrah

et al. 2024

CMES

View full text Add to dashboard Cite

Intelligent traffic control requires accurate estimation of the road states and incorporation of adaptive or dynamically adjusted intelligent algorithms for making the decision. In this article, these issues are handled by proposing a novel framework for traffic control using vehicular communications and Internet of Things data. The framework integrates Kalman filtering and Q-learning. Unlike smoothing Kalman filtering, our data fusion Kalman filter incorporates a process-aware model which makes it superior in terms of the prediction error. Unlike traditional Q-learning, our Q-learning algorithm enables adaptive state quantization by changing the threshold of separating low traffic from high traffic on the road according to the maximum number of vehicles in the junction roads. For evaluation, the model has been simulated on a single intersection consisting of four roads: east, west, north, and south. A comparison of the developed adaptive quantized Q-learning (AQQL) framework with state-of-the-art and greedy approaches shows the superiority of AQQL with an improvement percentage in terms of the released number of vehicles of AQQL is 5% over the greedy approach and 340% over the state-of-the-art approach. Hence, AQQL provides an effective traffic control that can be applied in today's intelligent traffic system.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Al-Heety,

Zakaria,

Abu-Khadrah

et al. 2024

CMES

View full text Add to dashboard Cite

show abstract

“…This proposed filter excels in electrical performance and power handling, although concerns regarding circuit size persist. Numerous design techniques have been documented in the literature for the development of Wideband Bandpass Filters (UWB-BPF) [21][22][23][24][25]. Nevertheless, these approaches are often plagued by issues such as substantial circuit size, intricate fabrication processes, and elevated costs.…”

Section: Introductionmentioning

confidence: 99%

A Novel Synthesis of Quasi-Chebyshev Ultra-Wideband Bandpass Filter Using Nth Order Stub Loaded Coupled-Line Resonator

Abdul Rehman,

Khalid,

Mushtaq

et al. 2023

Micromachines

View full text Add to dashboard Cite

This paper presents a novel synthesis of a quasi-Chebyshev Nth order stub-loaded coupled-line ultra-wideband bandpass filter. A unit element of a proposed filter topology consists of two short-circuited stubs loaded at the edges of coupled lines. A distributed equivalent circuit model of a proposed topology is extracted and used to acquire a generalized filtering function. The extracted filtering function is of rational form. The denominator of the filtering function causes a mismatch with Chebyshev type-I polynomials. For conventional narrowband filters, the denominator term can be neglected because of the close vicinity of band-edge frequencies; however, for the ultra-wideband filter response, the factor in the denominator cannot be neglected and hence requires a new mathematical procedure to compensate for the effect of the frequency-dependent term in the denominator. The electrical parameters are calculated using the proposed synthesis and used to design an ideal filter topology on ADS. To validate the proposed design procedure, fabrication is performed on a high-frequency substrate. The proposed filter is miniaturized in size and has good out-of-band performance. The simulated and measured results provide good agreement.

show abstract

Realization of superhuman intelligence in microstrip filter design based on clustering-reinforcement learning

et al. 2023

View full text Add to dashboard Cite

Direct synthesis approach for designing high selectivity microstrip distributed bandpass filters combined with deep learning

Cited by 11 publications

References 17 publications

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

Traffic Control Based on Integrated Kalman Filtering and Adaptive Quantized Q-Learning Framework for Internet of Vehicles

A Novel Synthesis of Quasi-Chebyshev Ultra-Wideband Bandpass Filter Using Nth Order Stub Loaded Coupled-Line Resonator

Realization of superhuman intelligence in microstrip filter design based on clustering-reinforcement learning

Contact Info

Product

Resources

About