Design of a Microwave Lowpass – Bandpass Filter using Deep Learning and Artificial Intelligence

In this paper, a lowpass – bandpass dual band microwave filter is designed by using deep learning and artificial intelligence. The designed filter has compact size and desirable pass bands. In the proposed filter, the resonators with Z-shaped and T-shaped lines are used to design the low pass channel, while coupling lines, stepped impedance resonators and open ended stubs are utilized to design the bandpass channel. Artificial neural network (ANN) and deep learning (DL) technique has been utilized to extract the proposed filter transfer function, so the values of the transmission zeros can be located in the desired frequency. This technique can also be used for the other electrical devices. The lowpass channel cut off frequency is 1 GHz, with better than 0.2 dB insertion loss. Also, the bandpass channel main frequency is designed at 2.4 GHz with 0.5 dB insertion loss in the passband.

Download Full-text

Compact dual-mode microstrip bandpass filter based on slotted square patch resonator

Microelectronics International ◽

10.1108/mi-08-2021-0080 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Karthie S. ◽

Zuvairiya Parveen J. ◽

Yogeshwari D. ◽

Venkadeshwari E.

Keyword(s):

Bandpass Filter ◽

Filter Design ◽

Center Frequency ◽

Dual Mode ◽

Content Type ◽

Transmission Zeros ◽

Compact Size ◽

Mode Response ◽

Better Than ◽

Good Agreement

Purpose The purpose of this paper is to present the design of a compact microstrip bandpass filter (BPF) in dual-mode configuration loaded with cross-loop and square ring slots on a square patch resonator for C-band applications. Design/methodology/approach In the proposed design, the dual-mode response for the filter is realized with two transmission zeros (TZs) by the insertion of a perturbation element at the diagonal corner of the square patch resonator with orthogonal feed lines. Such TZs at the edges of the passband result in better selectivity for the proposed BPF. Moreover, the cross-loop and square ring slots are etched on a square patch resonator to obtain a miniaturized BPF. Findings The proposed dual-mode microstrip filter fabricated in RT/duroid 6010 substrate using PCB technology has a measured minimum insertion loss of 1.8 dB and return loss better than 24.5 dB with a fractional bandwidth (FBW) of 6.9%. A compact size of 7.35 × 7.35 mm2 is achieved for the slotted patch resonator-based dual-mode BPF at the center frequency of 4.76 GHz. As compared with the conventional square patch resonator, a size reduction of 61% is achieved with the proposed slotted design. The feasibility of the filter design is confirmed by the good agreement between the measured and simulated responses. The performance of the proposed filter structure is compared with other dual-mode filter works. Originality/value In the proposed work, a compact dual-mode BPF is reported with slotted structures. The conventional square patch resonator is deployed with cross-loop and square ring slots to design a dual-mode filter with a square perturbation element at its diagonal corner. The proposed filter exhibits compact size and favorable performance compared to other dual-mode filter works reported in literature. The aforementioned design of the dual-mode BPF at 4.76 GHz is suitable for applications in the lower part of the C-band.

Download Full-text

A Wideband Bandpass Filter Integrated Single-Pole Double-Throw Switch with Wide Stopband

Frequenz ◽

10.1515/freq-2018-0045 ◽

2018 ◽

Vol 72 (11-12) ◽

pp. 533-537 ◽

Cited By ~ 1

Author(s):

Jin Xu ◽

Qi-Hang Cai ◽

Zhi-Yu Chen

Keyword(s):

Insertion Loss ◽

Bandpass Filter ◽

Fractional Bandwidth ◽

Central Frequency ◽

Resonant Frequencies ◽

Capacitively Coupled ◽

Filter Theory ◽

Compact Size ◽

Better Than ◽

Coupled Resonator

Abstract This paper proposes a wideband bandpass filter (BPF) integrated single-pole double-throw (SPDT) switch by using the capacitively coupled LC resonators with loaded p-i-n diodes. The BPF-integrated on-state channel can be synthesized by using the coupled resonator filter theory, and the off-state channel with high suppression is built due to the misaligned resonant frequencies of LC resonators. As an example, a BPF-integrated SPDT switch is designed and fabricated with the central frequency of 1 GHz and the 3 dB fractional bandwidth of 29.7 %. The on-state channel has a measured insertion loss of 1.23 dB, and a 20 dB rejection wide stopband from 1.47 GHz to 8.6 GHz. The off state channel has a 43 dB suppression around 1 GHz. The isolation between two ports is better than 52.4 dB. The fabricated BPF-integrated SPDT switch size including bias circuits but excluding feeding lines has a compact size of 0.086 λg×0.096 λg.

Download Full-text

Miniaturized Dual-Band Bandpass Filter Using Embedded Dual-Mode Resonator with Controllable Bandwidths

Frequenz ◽

10.1515/freq-2015-0195 ◽

2016 ◽

Vol 70 (9-10) ◽

Author(s):

Chuanming Zhu ◽

Jin Xu ◽

Wei Kang ◽

Zhenxin Hu ◽

Wen Wu

Keyword(s):

Insertion Loss ◽

Degrees Of Freedom ◽

Bandpass Filter ◽

The Other ◽

Dual Band ◽

Dual Mode ◽

Transmission Zeros ◽

Low Insertion Loss ◽

Multiple Transmission ◽

Mode Resonator

AbstractIn this paper, a miniaturized dual-band bandpass filter (DB-BPF) using embedded dual-mode resonator (DMR) with controllable bandwidths is proposed. Two passbands are generated by two sets of resonators operating at two different frequencies. One set of resonators is utilized not only as the resonant elements that yield the lower passband, but also as the feeding structures with source-load coupling to excite the other to produce the upper passband. Sufficient degrees of freedom are achieved to control the center frequencies and bandwidths of two passbands. Moreover, multiple transmission zeros (TZs) are created to improve the passband selectivity of the filter. The design of the filter has been demonstrated by the measurement. The filter features not only miniaturized circuit sizes, low insertion loss, independently controllable central frequencies, but also controllable bandwidths and TZs.

Download Full-text

Miniaturized Wideband Bandpass Filter based on Capacitor-loaded One-eighth Wavelength Coupled Line

Applied Computational Electromagnetics Society ◽

10.47037/2021.aces.j.360707 ◽

2021 ◽

Vol 36 (7) ◽

pp. 865-871

Author(s):

Jin Shi ◽

Jiancheng Dong ◽

Kai Xu ◽

Lingyan Zhang

Keyword(s):

Insertion Loss ◽

Simple Structure ◽

Bandpass Filter ◽

State Of The Art ◽

Center Frequency ◽

Fractional Bandwidth ◽

Coupled Line ◽

Transmission Zeros ◽

Compact Size ◽

Multiple Transmission

A novel miniaturized wideband bandpass filter (BPF) using capacitor-loaded microstrip coupled line is proposed. The capacitors are loaded in parallel and series to the coupled line, which makes the filter just require one one-eighth wavelength coupled line and achieve filtering response with multiple transmission poles (TPs) and transmission zeros (TZs). Compared with the state-of-the-art microstrip wideband BPFs, the proposed filter has the advantages of compact size and simple structure. A prototype centered at 1.47 GHz with the 3-dB fractional bandwidth of 86.5% is demonstrated, which exhibits the compact size of 0.003λ2 g (λg is the guided wavelength at the center frequency) and the minimum insertion loss of 0.37 dB.

Download Full-text

Design and Analysis of a Wide Stopband Microstrip Dual-band Bandpass Filter

ARO-The Scientific Journal of Koya University ◽

10.14500/aro.10908 ◽

2021 ◽

Vol 9 (2) ◽

pp. 83-90

Author(s):

Salah I. Yahya ◽

Abbas Rezaei ◽

Yazen A. Khaleel

Keyword(s):

Bandpass Filter ◽

Design Method ◽

Dual Band ◽

Equivalent Model ◽

Harmonic Suppression ◽

Coupled Resonators ◽

Transmission Zeros ◽

Novel Structure ◽

Compact Size ◽

Coupled Lines

A novel configuration of a dual-band bandpass filter (BPF) working as a harmonic attenuator is introduced and fabricated. The proposed filter operates at 3 GHz, for UHF and SHF applications, and 6.3 GHz, for wireless applications. The presented layout has a symmetric structure, which consists of coupled resonators. The designing of the proposed resonator is performed by introducing a new LC equivalent model of coupled lines. To verify the LC model of the coupled lines, the lumped elements are calculated. The introduced filter has a wide stopband up to 85 GHz with 28th harmonic suppression, for the first channel, and 13th harmonic suppression, for the second channel. The harmonics are attenuated using a novel structure. Also, the proposed BPF has a compact size of 0.056 λg2. Having several transmission zeros (TZs) that improve the performance of the presented BPF is another feature. The proposed dual-band BPF is fabricated and measured to verify the design method, where the measurement results confirm the simulations.

Download Full-text

A Geometric Deep Learning Approach to Predict Binding Conformations of Bioactive Molecules

10.26434/chemrxiv.14453106.v1 ◽

2021 ◽

Author(s):

Oscar Méndez-Lucio ◽

Mazen Ahmad ◽

Ehecatl Antonio del Rio-Chanona ◽

Jörg Kurt Wegner

Keyword(s):

Artificial Intelligence ◽

Deep Learning ◽

Molecular Target ◽

Bioactive Molecules ◽

Target Pair ◽

Learning Approach ◽

Scoring Functions ◽

Structure Based Drug Design ◽

Protein Targets ◽

Better Than

Understanding the interactions formed between a ligand and its molecular target is key to guide the optimization of molecules. Different experimental and computational methods have been key to understand better these intermolecular interactions. Herein, we report a method based on geometric deep learning that is capable of predicting the binding conformations of ligands to protein targets. Concretely, the model learns a statistical potential based on distance likelihood which is tailor-made for each ligand-target pair. This potential can be coupled with global optimization algorithms to reproduce experimental binding conformations of ligands. We show that the potential based on distance likelihood described in this paper performs similar or better than well-established scoring functions for docking and screening tasks. Overall, this method represents an example of how artificial intelligence can be used to improve structure-based drug design.

Download Full-text

Is Artificial Intelligence Better Than Human Clinicians in Predicting Patient Outcomes? (Preprint)

10.2196/preprints.19918 ◽

2020 ◽

Author(s):

Joon Lee

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Patient Outcome ◽

Deep Learning ◽

Patient Outcomes ◽

Outcome Prediction ◽

Prediction Models ◽

Challenging Problem ◽

Imaging Diagnostics ◽

Better Than

UNSTRUCTURED In contrast with medical imaging diagnostics powered by artificial intelligence (AI), in which deep learning has led to breakthroughs in recent years, patient outcome prediction poses an inherently challenging problem because it focuses on events that have not yet occurred. Interestingly, the performance of machine learning–based patient outcome prediction models has rarely been compared with that of human clinicians in the literature. Human intuition and insight may be sources of underused predictive information that AI will not be able to identify in electronic data. Both human and AI predictions should be investigated together with the aim of achieving a human-AI symbiosis that synergistically and complementarily combines AI with the predictive abilities of clinicians.

Download Full-text

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

Nature Communications ◽

10.1038/s41467-021-26643-8 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Gang Yu ◽

Kai Sun ◽

Chao Xu ◽

Xing-Hua Shi ◽

Chong Wu ◽

...

Keyword(s):

Artificial Intelligence ◽

Colorectal Cancer ◽

Deep Learning ◽

Supervised Learning ◽

Area Under The Curve ◽

Patient Level ◽

Significant Difference ◽

The Mean ◽

Whole Slide Images ◽

Better Than

AbstractMachine-assisted pathological recognition has been focused on supervised learning (SL) that suffers from a significant annotation bottleneck. We propose a semi-supervised learning (SSL) method based on the mean teacher architecture using 13,111 whole slide images of colorectal cancer from 8803 subjects from 13 independent centers. SSL (~3150 labeled, ~40,950 unlabeled; ~6300 labeled, ~37,800 unlabeled patches) performs significantly better than the SL. No significant difference is found between SSL (~6300 labeled, ~37,800 unlabeled) and SL (~44,100 labeled) at patch-level diagnoses (area under the curve (AUC): 0.980 ± 0.014 vs. 0.987 ± 0.008, P value = 0.134) and patient-level diagnoses (AUC: 0.974 ± 0.013 vs. 0.980 ± 0.010, P value = 0.117), which is close to human pathologists (average AUC: 0.969). The evaluation on 15,000 lung and 294,912 lymph node images also confirm SSL can achieve similar performance as that of SL with massive annotations. SSL dramatically reduces the annotations, which has great potential to effectively build expert-level pathological artificial intelligence platforms in practice.

Download Full-text

A Compact Lowpass Filter with Four Transmission Zeros Using Single-Sided Compact Microstrip Resonator Cells

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.487.125 ◽

2012 ◽

Vol 487 ◽

pp. 125-129

Author(s):

Kai Yu Zhao ◽

Lin Li

Keyword(s):

Insertion Loss ◽

Return Loss ◽

Cutoff Frequency ◽

Lowpass Filter ◽

Sharp Transition ◽

Microstrip Resonator ◽

Broad Bandwidth ◽

Transmission Zeros ◽

Compact Size ◽

Low Insertion Loss

A compact lowpass filter using two single-sided compact microstrip resonator cells （CMRCs）with low insertion loss and broad bandwidth is presented. The cutoff frequency is about 1.4 GHz, the insertion loss is less than 0.6 dB and the 20dB bandwidth is up to the range from 2.1 GHz to 9.8 GHz by means of introducing four transmission zeros through two CMRCs. In addition, the simulated results demonstrate that the proposed filter is characterized by a compact size, low insertion loss, sharp transition, low return loss and wide bandwidth.

Download Full-text

Compact Dual-Band Bandpass Filter Using Stubs Loaded Ring Resonator

Frequenz ◽

10.1515/freq-2015-0109 ◽

2016 ◽

Vol 70 (1-2) ◽

Author(s):

Jin Xu

Keyword(s):

Bandpass Filter ◽

Ring Resonator ◽

Design Guidelines ◽

Second Order ◽

Dual Band ◽

Compact Size ◽

Mode Method ◽

Resonant Characteristic ◽

Better Than ◽

Good Agreement

AbstractThis paper presents a novel second-order dual-band bandpass filter (BPF) by using proposed stubs loaded ring resonator. The resonant behavior of proposed stubs loaded ring resonator is analyzed by even-/odd-mode method, which shows its multiple-mode resonant characteristic. Parameters sweep is done so as to give the design guidelines. As an example, a second-order dual-band BPF operating at 1.8/5.2 GHz for GSM and WLAN applications is designed, fabricated and measured. The fabricated filter has a very compact size of 0.05λg×0.15λg. Measured results also show that the proposed dual-band BPF has a better than 20 dB rejection upper stopband from 5.47 GHz to 12.56 GHz. Good agreement is shown between the simulated and measured results.

Download Full-text