Matching Network Research Articles

Research on efficient matching method of coal gangue recognition image and sorting image

When the coal gangue sorting robot sorts coal gangue, the position of the target coal gangue will change due to belt slippage, deviation, and speed fluctuations of the belt conveyor. This will cause the robotic to fail in grasping or miss grasping. We have developed a solution to this problem: the IMSSP-Net two-stage network gangue image fast matching method. This method will reacquire the target gangue position information and improve the robot’s grasping precision and efficiency. In the first stage, we use SuperPoint to guarantee the scene adaptability and credibility of feature point extraction. We have enhanced Superpoint’s ability to detect feature points further by using the improved Multi-scale Retinex with Color Restoration enhancement algorithm. In the second stage, we introduce SuperGlue for feature matching to improve the robustness of the matching network. We eliminated erroneous feature matching point pairs and improved the accuracy of image matching by adopting the PROSAC algorithm. We conducted image matching comparison experiments under different object distances, scales, rotation angles, and complex conditions. The experimental platform adopts the double-manipulator truss-type coal gangue sorting robot independently developed by the team. The matching precision, recall, and matching time of the method are 98.2%, 98.3%, and 84.6ms, respectively. The method can meet the requirements of efficient and accurate matching between coal gangue recognition images and sorting images.

Ultra-wideband GaN RF power amplifier based on low-pass ladder matching network

Ultra-wideband GaN RF power amplifier based on low-pass ladder matching network

Advancements and Challenges in Antenna Design and Rectifying Circuits for Radio Frequency Energy Harvesting

The proliferation of smart devices increases the demand for energy-efficient, battery-free technologies essential for sustaining IoT devices in Industry 4.0 and 5G networks, which require zero maintenance and sustainable operation. Integrating radio frequency (RF) energy harvesting with IoT and 5G technologies enables real-time data acquisition, reduces maintenance costs, and enhances productivity, supporting a carbon-free future. This survey reviews the challenges and advancements in RF energy harvesting, focusing on far-field wireless power transfer and powering low-energy devices. It examines miniaturization, circular polarization, fabrication challenges, and efficiency using the metamaterial-inspired antenna, concentrating on improving diode nonlinearity design. This study analyzes key components such as rectifiers, impedance matching networks, and antennas, and evaluates their applications in biomedical and IoT devices. The review concludes with future directions to increase bandwidth, improve power conversion efficiency, and optimize RF energy harvesting system designs.

Smith Chart-Based Design of High-Frequency Broadband Power Amplifiers

This paper presents a comprehensive study on the design and performance of a high-power amplifier (PA) covering a broad frequency band from 0.1 to 4.8 GHz. Leveraging a 10 W GaN device, the amplifier achieves output power levels surpassing 10 W across the entire frequency band. Furthermore, the power-added efficiency (PAE) of the amplifier ranges from 47% to 59%, indicating its energy-efficient operation. With consistent gain characteristics varying between 7 and 15 dB, the design ensures reliable signal amplification for diverse applications. Notably, the approach introduces a simplified output matching network based on an LC network, prioritizing practicality without sacrificing performance. Additionally, comprehensive guidance is provided on utilizing the Smith chart for streamlined amplifier design, enabling engineers with an accessible methodology. Through a meticulous analysis, this work contributes to advancing the field of high-power amplification, offering enhanced performance and usability for next-generation wireless communication systems.

TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matching.

This study tackles image matching in difficult scenarios, such as scenes with significant variations or limited texture, with a strong emphasis on computational efficiency. Previous studies have attempted to address this challenge by encoding global scene contexts using Transformers. However, these approaches have high computational costs and may not capture sufficient high-level contextual information, such as spatial structures or semantic shapes. To overcome these limitations, we propose a novel image-matching method that leverages a topic-modeling strategy to capture high-level contexts in images. Our method represents each image as a multinomial distribution over topics, where each topic represents semantic structures. By incorporating these topics, we can effectively capture comprehensive context information and obtain discriminative and high-quality features. Notably, our coarse-level matching network enhances efficiency by employing attention layers only to fixed-sized topics and small-sized features. Finally, we design a dynamic feature refinement network for precise results at a finer matching stage. Through extensive experiments, we have demonstrated the superiority of our method in challenging scenarios. Specifically, our method ranks in the top 9% in the Image Matching Challenge 2023 without using ensemble techniques. Additionally, we achieve an approximately 50% reduction in computational costs compared to other Transformer-based methods. Code is available at https://github.com/TruongKhang/TopicFM.

Lumped-element SNAIL parametric amplifier with two-pole matching network

Broadband impedance-matched Josephson parametric amplifiers are key components for high-fidelity single-shot multi-qubit readout. Nowadays, several types of impedance matched parametric amplifiers have been proposed: the first is an impedance-matched parametric amplifier based on a Klopfenstein taper, and the second is the impedance-matched parametric amplifier based on auxiliary resonators. Here, we present the quantum-limited 3-wave-mixing lumped-element SNAIL parametric amplifier with two-pole impedance matching transformer. A two-pole Chebyshev matching network with shunted resonators is based on parallel-plate capacitors and superconducting planar coil. Operating in a flux-pumped mode, we experimentally demonstrate an average gain of 15 dB across a 600 MHz bandwidth, along with an average saturation power of −107 dBm and quantum-limited noise temperature.

Retraction: A multi-objective optimization based doherty power amplifier and its matching network optimization method.

Retraction: A multi-objective optimization based doherty power amplifier and its matching network optimization method.

HAGMN-UQ: Hyper association graph matching network with uncertainty quantification for coronary artery semantic labeling

Coronary artery disease (CAD) is one of the leading causes of death worldwide. Accurate extraction of individual arterial branches from invasive coronary angiograms (ICA) is critical for CAD diagnosis and detection of stenosis. Generating semantic segmentation for coronary arteries through deep learning-based models presents challenges due to the morphological similarity among different types of coronary arteries, making it difficult to maintain high accuracy while keeping low computational complexity. To address this challenge, we propose an innovative approach using the hyper association graph-matching neural network with uncertainty quantification (HAGMN-UQ) for coronary artery semantic labeling on ICAs. The graph-matching procedure maps the arterial branches between two individual graphs, so that the unlabeled arterial segments are classified by the labeled segments, and the coronary artery semantic labeling is achieved. Leveraging hypergraphs not only extends representation capabilities beyond pairwise relationships, but also improves the robustness and accuracy of the graph matching by enabling the modeling of higher-order associations. In addition, employing the uncertainty quantification to determine the trustworthiness of graph matching reduces the required number of comparisons, so as to accelerate the inference speed. Consequently, our model achieved an accuracy of 0.9211 for coronary artery semantic labeling with a fast inference speed, leading to an effective and efficient prediction in real-time clinical decision-making scenarios.

A 2–36 GHz CMOS LNA with π-Network-Based wideband interstage matching technique for software-defined radio systems

With the advance in wireless communication, next-generation software-defined radio (SDR) systems require transceivers to operate in both sub-6GHz and millimeter-wave (mmWave) band and support multiple standards. However, bridging sub-6GHz frequencies with millimeter-wave bands exceeding 30 GHz remains a challenge for conventional wideband LNAs. To surmount this, a 2–36 GHz CMOS low-noise amplifier (LNA) designed for SDR systems is introduced in this paper. An innovative wideband input matching network capable of spanning both frequency domains is proposed. The methodology effectively mitigates the impact of vast parasitic capacitances, achieving wideband input matching against Electrostatic Discharge (ESD) and on-chip decoupling capacitor parasitic. In addition, a π-network-based wideband interstage matching technique is adopted to extend bandwidth of gain. A tri-stage prototype of the proposed LNA, designed using a 40-nm CMOS process, is designed to validate our design strategies. The post-simulation outcomes reveal a peak gain of 14 dB with a -3dB bandwidth ranging from 2 to 36 GHz, equating to a fractional bandwidth of 178 %. The Noise Figure (NF) is commendably uniform across the frequency spectrum, stabilizing at 5 dB. Furthermore, the third-order input intercept point (IIP3) is −4.2dBm to -3dBm across the bandwidth. The performance is achieved with a power of 19.4 mW and within a core area of 0.1 mm2.

A Compact Broadband Rectifier Based on Coupled Transmission Line for Wireless Power Transfer

Wireless Power Transfer (WPT) can effectively solve the problem of autonomous power supply for low-power devices. Rectifier is the key component in WPT technology. In this paper, a novel impedance matching network for the broadband rectifier is proposed. This impedance matching network compensates for the diode impedance and reduces its impedance change when the frequency or input power changes. The passive boosting mechanism utilizing coupled transmission lines (CTLs) improves the power conversion efficiency (PCE) of the diode in the low power region. The structure is especially optimized for low-power device applications. For validation, a broadband rectifier operating at 1.9–3 GHz is fabricated and measured. The structure fabricated on the Rogers 4003 substrate with a thickness of 1.508 mm and the diode is HSMS2860. The DC voltage Vout on the load (RL=1300 Ω) was measured. The results show that at 0 dBm, the PCE keeps more than 60% at 1.98–3 GHz. The peak PCE of 79.6% is obtained at 4 dBm. The compact size of the broadband rectifier is 19 mm × 21 mm. This broadband rectifier for low input power ranges can be applied to WPT technology.

AP-Net: Attention-fused volume and progressive aggregation for accurate stereo matching

Stereo matching plays an important role in advancing substantial applications such as 3D reconstruction, autonomous driving, depth sensing, and has recently made tremendous progress. It still poses a significant challenge, however, in the extraction of disparities from a pair of rectified images to achieve accurate stereo matching. In this paper, we propose an attention-fused cost volume construction and progressive cost aggregation network, namely AP-Net, to elevate the accuracy of stereo matching. Specifically, we introduce attention fusion to learn feature similarity between corresponding points on the left and right images while capturing long-dependent contextual information to construct attention-fused cost volumes. Moreover, we propose progressive cost aggregation, which consists of two stages to fully exploit information from different cost volumes. Furthermore, to make more accurate adjustments to the initial disparity, we implement an information entropy-guided disparity refinement module, which leverages information entropy as an explicit confidence measure of the initial disparity estimation to guide the refinement module in calculating the disparity residual more accurately and improving the overall accuracy of disparity estimation. Our implemented disparity refinement module can also be seamlessly embedded into a variety of stereo matching networks, significantly improving the model’s performance with only a small increase in computation and parameters. Experimental results across various stereo datasets confirm that our proposed AP-Net consistently delivers competitive performance. The code is available at https://github.com/zhuys-bupt/AP-Net.

Design and development of dual-band superconducting filter with a novel structure

In this paper, a novel design structure of a dual-band filter is proposed. The core of the structure is to form a dual-band filter by connecting two sub-filters through a matching network. The matching network can not only improve the flexibility of the design, but also minimize the influence between the two sub-filters. Two sub-filters are designed separately, one of which is composed of interdigital resonators and the other is composed of hairpin resonators. The center frequency and bandwidth of the two passbands are flexible and controllable. Finally, a dual-band high-temperature superconducting (HTS) filter is designed and successfully fabricated on a DyBa2Cu3O7 (DyBCO) thin film on thickness of 0.5 mm LaAlO3 wafer, and the measured results are in good agreement with the simulation results.

Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network

Bearing fault diagnosis presents challenges, such as insufficient fault samples and significant fault data distribution variation in different bearing operating conditions. These problems cause traditional deep learning models to show poor generality and accuracy during bearing fault diagnosis. To address these challenges, this paper proposed a few-shot bearing fault diagnosis method based on an Ensemble Empirical Mode Decomposition (EEMD) parallel neural network and a relation network (RN). First, the original bearing fault vibration signal was decomposed by EEMD, while the decomposed signal components were processed via Short Time Fourier Transfor (STFT) to obtain a two-dimensional time-frequency feature map. Then, a parallel neural network was used for initial fault feature extraction, after which the extracted features were fused to construct a more accurate multi-dimensional fault feature map. A more precise fault feature vector was generated via the feature embedding module of the RN, and the fault features of the support and query sets were stitched to create a fault feature vector set. Finally, the relation module of the RN was used for the nonlinear distance determination of the fault feature vector set and to generate the relation score for the few-shot variable condition bearing fault diagnosis. In this paper, EEMD module is introduced into RN to construct multi-dimensional fault characteristics of the original fault signal. Original signal decomposition, STFT transformation and splicing effectively improve the randomness and blindness of convolution operations, improve the accuracy of fault feature extraction in RN, and thus improve the overall diagnostic performance of the model. The experimental results showed that the proposed model obtained higher diagnostic accuracy than the matching network (MN) and RN meta-learning fault diagnosis (MLFD) methods. The accuracy of fault diagnosis of the model in 5Way-Nshot is >80%, and the accuracy of fault diagnosis in 5Way-10shot is the highest at 95.2%.

A 28 GHz balun‐first LNA with db‐linear 32 db gain range for 5 G applications

AbstractThis letter presents a 28 GHz balun‐first low noise amplifier (LNA) featuring a wide dB‐linear variable gain range. The architecture of LNA includes three‐stage cascode amplifiers. An integrated balun at the input stage provides RF ESD protection and converts a single‐ended signal to a differential one (S‐to‐D). A transformer‐based dual‐resonant matching network is designed and analyzed to achieve wideband performance. To realize a continuous dB‐linear variable gain range and consistent input/output matching, gain control is implemented in the second stage using a 5‐bit digital‐to‐analog converter (DAC) for a 32 dB gain range. The DAC can generate a nonlinear analog voltage to control the gate of the common‐gate transistor in the second cascode stage, inversely compensating for the nonlinear gain variations of the cascode amplifier. The LNA is fabricated in 65‐nm CMOS process with a core size of 0.154 mm². Measurement results exhibit a maximum gain of 33.5 dB and a minimum noise figure (NF) of 3.65 dB with a 3‐dB bandwidth of 23–29.5 GHz. The measured variable gain range is approximately 32 dB across 32 different gain states, with a linear gain step of ~1 dB per state and an IP1dB ranging from −6.5 dBm to −35.25 dBm. The power consumption is 35.4–48 mW from a 1.2 V supply voltage.

A fully integrated GaAs HBT power amplifier for WLAN 802.11ax applications

AbstractA fully integrated gallium arsenide (GaAs) heterojunction bipolar transistor (HBT) power amplifier (PA) for wireless local area network 802.11ax applications is presented in this paper. The structure consists of two‐stage power cells. To satisfy the high linearity requirements of IEEE 802.11ax, we analyzed the distortion of amplitude‐to‐amplitude and amplitude‐to‐phase. Due to the thermal and voltage sensitivity of GaAs HBT, an adaptive bias circuit is designed to ensure linearity. Moreover, an efficient passive output matching network is designed by analyzing the efficiency of the passive network. The design electromagnetic structure is fabricated in a 2‐μm GaAs HBT process. Under continuous wave testing, the output power reaches 27.2 dBm and the maximum efficiency of 28% at 2.4 GHz. Under the excitation of a 40 MHz 1024‐quadratic amplitude modulation signal, the output power meeting error vector magnitude of −35 dB reaches 16.8–17.2 dBm from 2.4 to 2.5 GHz.

ROPGMN: Effective ROP and variants discovery using dynamic feature and graph matching network

Return Oriented Programming (ROP) is one of the most challenging threats to operating systems. Traditional detection and defense techniques for ROP such as stack protection, address randomization, compiler optimization, control flow integrity, and basic block thresholds have certain limitations in accuracy or efficiency. At the same time, they cannot effectively detect ROP variant attacks, such as COP, COOP, JOP. In this paper, we propose a novel ROP and its variants detection approach that first filters the normal execution flow according to four strategies provided and then adopts Graph Matching Network (GMN) to determine whether there is ROP or its variant attack. Moreover, we developed a prototype named ROPGMN with shared memory to solve cross-language and cross-process problems. Using real-world vulnerable programs and constructed programs with dangerous function calls, we conduct extensive experiments with 6 ROP detectors to evaluate ROPGMN. The experimental results demonstrate the effectiveness of ROPGMN in discovering ROPs and their variant attacks with low performance overhead.

Innovative multi-stage matching for counting anything

Few-shot counting (FSC) is the task of counting the number of objects in an image that belong to the same category, by using a provided exemplar pattern. By replacing the exemplar, we can effectively count anything, even in cases where we have no prior knowledge of that category’s exemplar. However, due to the variations within the same category and the impact of inter-class similarity, it is challenging to achieve accurate intra-class similarity matching using conventional similarity comparison methods. To tackle these issues, we propose a novel few-shot counting method called Multi-stage Exemplar Attention Match Network (MEAMNet), which increases the accuracy of matching, reduces the impact of noise, and enhances similarity feature matching. Specifically, we propose a multi-stage matching strategy to obtain more stable and effective matching results by acquiring similar feature in different feature spaces. In addition, we propose a novel feature matching module called Exemplar Attention Match (EAM). With this module, the intra-class similarity representation in each stage will be enhanced to achieve a better matching of the key feature. Experimental results indicate that our method not only significantly surpasses the state-of-the-art (SOTA) methods in most evaluation metrics on the FSC-147 dataset but also achieves comprehensive superiority on the CARPK dataset. This highlights the outstanding accuracy and stability of our matching performance, as well as its exceptional transferability. We will release the code at https://github.com/hzg0505/MEAMNet.

A Temperature-Robust Envelope Detector Receiving OOK-Modulated Signals for Low-Power Applications

This paper presents a passive Envelope Detector (ED) to be used for reception of OOK-modulated signals, such as in Wake-Up Receivers employed within Wireless Sensor Networks, widely used in the IoT. The main goal is implementing a temperature compensation mechanism in order to keep the passive ED input resistance roughly constant over temperature, making it a constant load for the preceding matching network and ultimately keeping the overall receiving chain sensitivity constant over temperature. The proposed ED was designed using STMicroelectronics 90 nm CMOS technology to receive 1 kbps OOK-modulated packets with a 433 MHz carrier frequency and a 0.6 V supply. The use of a block featuring a Proportional-to-Absolute Temperature (PTAT) current yields a 5 dB reduction in sensitivity temperature variation across the −40 °C to 120 °C range. Moreover, two different implementations were compared, one targeting minimal mismatch and the other one targeting minimal area. The minimal area version appears to be better in terms of estimated overall chain sensitivity at all temperatures despite a higher sensitivity spread.

Deep spatial and discriminative feature enhancement network for stereo matching

Deep spatial and discriminative feature enhancement network for stereo matching

6 GHz lamb wave acoustic filters based on A1-mode lithium niobate thin film resonators with checker-shaped electrodes

The first-order antisymmetric (A1) mode lamb wave resonator (LWR) based on Z-cut LiNbO3 thin films has attracted significant attention and is widely believed to be a candidate for next-generation reconfigurable filters with high frequency and large bandwidth (BW). However, it is challenging for traditional interdigitated electrodes (IDTs) based LWR filters to meet the requirement of a clean frequency spectrum response and enough out-of-band (OoB) rejection. To solve the problem, we propose LWRs with checker-shaped IDTs for the design of filters that meet the Wi-Fi 6E standard. By taking advantage of checker-shaped IDTs with unparalleled boundaries, the fabricated 6-GHz resonators successfully suppress higher-order A1 spurious modes, demonstrating a spurious-free impedance response and a high figure-of-merit (FOM) up to 104. Based on the demonstrated checker-shaped electrode design, the filter features a center frequency (f0) of more than 6 GHz, a 3 dB BW exceeding 620 MHz, and an excellent OoB rejection >25 dB, consistent with the acoustic-electric-electromagnetic (EM) multi-physics simulations. Furthermore, through the capacitance-inductance matching network technology, the filter’s voltage standing wave ratio (VSWR) is successfully reduced below 2, showing an excellent 50 Ω impedance matching. This study lays a foundation for ultra-high-frequency and ultra-wideband filters for the Wi-Fi 6/6E application.