Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: 1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. 2) Generative Intermediate Fusion (GIF) module, which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The remarkable results justify the efficacy of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA.

Existing learning-based arbitrary-scale point cloud upsampling methods are usually challenged with limited point cloud feature representation and noise-sensitive refinement of coarse point cloud. In this paper, we introduce GraphDAE-PU, a novel framework for point cloud upsampling that addresses the challenges associated with arbitrary-scale point cloud upsampling. Our approach integrates graph representation with a denoising auto-encoder architecture, harnessing the intrinsic structure of point clouds to enhance feature extraction and refine the upsampled points. Specifically, the use of a graph neural network enables our model to capture complex geometric relationships within the data, thereby improving the accuracy of the generated point clouds. Concurrently, the denoising auto-encoder refines coarse, midpoint-interpolated point clouds, resulting in surfaces that are not only accurate and uniform but also robust to noise. Experimental evaluations, both qualitative and quantitative, reveal that GraphDAE-PU consistently outperforms existing methods, demonstrating its accuracy and robustness in arbitrary-scale upsampling tasks.

Concept drift remains a critical challenge in non-stationary industrial fault diagnosis processes, where evolving operational conditions induce continuous distributional shifts and hinder model generalization. While existing continual learning approaches primarily focus on mitigating forgetting, they often lack explicit mechanisms to detect and quantify drift in a timely manner. To address this, this paper proposes a novel multi-scale feature-probability consistency-based drift detection (MFPC-DCD) framework. It comprises three core components: (1) a feature-level divergence module that leverages Maximum Mean Discrepancy (MMD) to measure latent representation shifts; (2) a probability-level divergence module utilizing Jensen–Shannon divergence to quantify predictive inconsistencies; and (3) a multi-scale consistency fusion strategy that aggregates drift signals across short-, mid-, and long-term temporal windows, thereby enhancing robustness and temporal granularity. The MFPC-DCD method can explicitly detect domain shifts by jointly capturing structural and semantic distributional variations through multi-resolution analysis and then the resulting unified drift coefficient provides precise quantification of domain shifts and can be seamlessly integrated into downstream continual learning fault diagnosis for adaptive regularization. Experiments conducted on two fault diagnosis datasets — CWRU, and our proprietary DPS — demonstrate that MFPC-DCD achieves state-of-the-art drift detection performance and adaptability under diverse drift scenarios.

Channel-spatial attention mechanisms have been extensively investigated in computer vision. However, it is still a difficult problem that how to efficiently utilize global and local contextual information laid in a feature tensor to generate an accurate 3D attention map. This paper proposes a novel attention module for convolutional neural networks named Dual Rank-1 Tensor Attention Module, which can reach a good balance between global and local contextual information utilization for attention map generation. In our module, given a feature tensor, we sequentially generate two rank-1 3D tensor attention maps, i.e., the initial rank-1 tensor attention map containing global contextual information, and the complement rank-1 tensor attention map containing partial local contextual information. Then, we obtain a 3D tensor attention map based on the combination of these two rank-1 tensor attention maps for feature recalibration. Experimental results on ImageNet-1K and PASCAL VOC datasets demonstrate that the proposed module can achieve competitive performance compared with other state-of-the-art attention modules. The source code will be available at https://github.com/KevinBHLin/.

Multi-agent collaborative Simultaneous Localization and Mapping (SLAM) is an effective way for large-scale mapping. However, this approach, which relies on Visual-Inertial Odometry(VIO) as input, suffers from limitations such as susceptibility to environmental influences and the difficulty in accurately constructing dense 3D maps. To address these challenges, this paper presents Multi-Estimation Robust SLAM System (MERSYS), a novel framework for three-dimensional dense mapping based on the fusion of Lidar-Inertial Odometry(LIO) and VIO. Benefiting from lower communication’s costs and dense information acquisition capability, the proposed framework aims to achieve compatibility in processing both LIO and VIO inputs, establish joint loop closure detection to enable multi-map fusion, and then create a comprehensive global 3D dense point cloud map. Furthermore, an efficient communication strategy has been proposed to enable bidirectional transmission of dense and voluminous data. Experimental evaluations conducted on the publicly available HILTI SLAM 2021 dataset [10] as well as a real world dataset. Experimental results show that MERSYS achieves better results than state-of-the-art methods. The source code is available on the GitHub1.

For$LCL$type grid-connected inverters, inverter-side current control (ICC) mode is more promising for industrial applications for the convenience in the protection of power switches, e.g., IGBTs. However, the time delay in digital control causes the limited stable region of single-loop ICC. To enhance the stability of the system, capacitor-current-feedback active damping (CCF-AD) has been widely used to achieve the dual-loop current control. However, most of the existing designs of CCF-AD are under grid-side current control, while the passivity-based design of CCF-AD for the ICC has yet to receive much attention. For achieving passive output admittance of the inverter, this paper reveals a small delay needs to be introduced into the CCF-AD loop for the ICC. The parameter design of CCF-AD is detailed in this paper. Finally, the experimental results verify the theoretical analysis.

Symmetrical six-phase motors offer superior fault-tolerant ability, particularly with neutral point connection (CNP) configuration. In the structure of CNP, non-negligible zero-sequence current (ZSC) is generated since zero-sequence loop has been formed between the dual inverters. This paper proposes a novel zero-sequence current elimination (ZSCE) pulsewidth modulation (PWM) scheme for S6-PMSM with CNP. The switching state combinations of dual inverter is mapped to three orthogonal sub-planes using decoupling coordinate transformation, and combinations of vectors with zero zero-sequence voltage (ZSV) are picked to generate the same common mode voltage (CMV) of two inverters in the synthesis process of reference vector. The two CMVs can cancel out each other to remove the modulated ZSV source and eliminate the ZSC. The superiority of the proposed ZSCE PWM method is demonstrated by the experiment.

The LCL-type grid-connected inverter (GCI) with inverter-side current control (ICC) has been extensively implemented for the advantages of its over-current protection ability and low cost. However, in the scenario of distorted grid voltage, due to indirect control of the grid-side current, ICC lacks relevant information about the grid current harmonics, thus, the harmonics can freely flow into the filter capacitor and distort the grid current. In this paper, a capacitor current compensation scheme with active damping and repetitive controller (RC) is proposed to enhance the grid current quality. Besides, the output admittance of the inverter is tuned to be passive below Nyquist frequency to ensure a sufficient stability condition. Finally, the effectiveness of the proposed method for the grid current quality enhancement is verified by experimental results.

Dual-dc-port inverter can directly connect photo-voltaic (PV) and battery to ac-grid without dc-dc converter, providing a low-cost, small-volume, and high-efficiency solution for PV-battery hybrid systems. However, it is challenging to design the modulation scheme for the dual-dc-port inverter due to the unbalanced dc-link and coupled port power control feature. To realize flexible power allocation and achieve satisfactory current quality under unbalanced dc-link voltage, this article proposes a hybrid modulation-based flexible power allocation strategy for the dual-dc-port inverter. In the proposed strategy, flexible active power allocation for each port is achieved by proportionally splitting the desired voltage vector, and the split voltage vector for each port is implemented by the hybrid modulation. With the hybrid modulation, challenges for modulation scheme design under unbalanced dc port voltage are also avoided. Experimental tests are conducted to verify the effectiveness of the proposed power allocation strategy. And experimental results indicate that the proposed strategy has beneficial steady-state and dynamic performance.

The battery-supercapacitor hybrid energy storage system (HESS) integrates high-energy-density units and high-power-density units together, which has been widely used in microgrids (MGs) applications. However, the conventional HESS has the disadvantages of low efficiency and large volume. To improve the system power density, the quasi single-stage con-verter is an attractive solution for HESS due to it offering direct power flows from dc-side to ac-side. To maximize the system efficiency, this article proposes a novel space vector modulation with its basic idea and implementation process. Finally, the effectiveness of the proposed modulation is verified by quasi-single-stage converter-based virtual synchronous generator (VSG) experimental tests.

The single-stage multiport inverter (SSMPI)-fed motor drives enable direct connection from the dc-side energy sources to the ac motor without utilizing any dc/dc converters, which feature high power density and high efficiency of the overall system. However, the output power of each source is highly coupled with the motor control in this topology, which provides poor flexibility of power control. To address this problem, a decoupling control strategy is proposed in this paper. First, an asymmetrical carrier-based modulation strategy is adopted to ensure the high performance of the motor control by fully considering the voltage variation of sources. Then, injecting different values of the zero-sequence voltage adds a degree of freedom for controlling the output power of sources. With the proposed method, the flexible power control is realized without affecting the performance of the motor control. Finally, the effectiveness of the proposed control scheme is verified through experiments on a permanent magnet synchronous motor (PMSM)-based laboratory prototype.

In high-power applications, output filters are essential components of grid-connected inverters (GCIs) for filtering switching ripples. These filters are closely related to the electrical indexes and control performance of the GCI, including power density, efficiency, stability, etc. Therefore, they are often co-designed with constraints on electrical indexes and damping coefficients. However, damping coefficients can not provide sufficient stability conditions. To overcome it, this paper proposes a passivity-based multi-objective LTCL-RC filter design method. The proposed method can achieve passive output admittance at the full-frequency range to maintain a sufficient stability condition. To be specific, the Pareto optimization with respect to power density, efficiency and passivity is introduced to select parameters. Furthermore, a 4MW-GCI filter design example is provided to highlight its superiority over other state-of-the-art design methods, and the effectiveness of the proposed filter design approach in ensuring system stability is also verified on a scaled-down 1.4kW-VSI experimental prototype.

This paper proposes a dead time compensation method based on current ripple prediction (CRP) for three-level inverters. First, the dead time effect in three-level inverters is analyzed, including the influence of dead time freewheeling and switching process caused by parasitic capacitors, and the time delay variation curves of the phase voltage switching edges with the phase current are obtained. Then, the actual phase current is reconstructed using the CRP method and the sampled low-frequency current. Thus, the compensation time of the switching edges can be accurately calculated. Simulation and experimental results are provided to validate the effectiveness of the proposed method in both reducing phase current distortion and improving the common-mode voltage elimination effect.

The Internal-Parallel Multilevel Converter (IPMC) with reduced device count is implemented to drive the dual three-phase permanent magnet synchronous motor (DTP-PMSM) forming multilevel multiphase motor drives. However, due to the restriction of the low switching frequency (LSF) module sharing, only the parallel high switching frequency (HSF) switching states can keep interleaving operation, whereas the proportional-integral (PI) control, the resulting voltage reference, and the LSF switching state remain simultaneous, which leads to asymmetric pulse width modulation (PWM) waveform and significant harmonics. In this paper, the effect of asymmetric PWM waveform on current and torque harmonics is investigated. Meanwhile, a decoupled modulation strategy with optimized interleaved PWM is proposed to solve the problem, thus achieving the reduction of the corresponding order and switching frequency torque harmonics with a certain improvement in the current ripple. The experimental results with the IPMC-fed DTP-PMSM drive prototype are provided to verify the validity and superiority of the proposed modulation strategy compared to the traditional interleaving scheme and the non-interleaving technique.

This paper proposes a passivity-based design method of 6k±1-order harmonic repetitive control (6k±1 RC) for LCL-type grid-connected inverters (GCIs). According to the proposed design method, the output admittance of the 6k±1 RC-RC-controlled inverters is tuned to be passive at all frequencies so that it can be plug-and-play connected to the grid regardless of the grid impedance variations. Meanwhile, compared with the traditional repetitive control (CRC), 6k±1 RC has a faster error convergence rate and can produce low THD and high tracking accuracy even in distorted grid conditions. Experimental results verify the effectiveness of the proposed method.

MOTIVATION: Single-cell DNA methylation sequencing can assay DNA methylation at single-cell resolution. However, incomplete coverage compromises related downstream analyses, outlining the importance of imputation techniques. With a rising number of cell samples in recent large datasets, scalable and efficient imputation models are critical to addressing the sparsity for genome-wide analyses. RESULTS: We proposed a novel graph-based deep learning approach to impute methylation matrices based on locus-aware neighboring subgraphs with locus-aware encoding orienting on one cell type. Merely using the CpGs methylation matrix, the obtained GraphCpG outperforms previous methods on datasets containing more than hundreds of cells and achieves competitive performance on smaller datasets, with subgraphs of predicted sites visualized by retrievable bipartite graphs. Besides better imputation performance with increasing cell number, it significantly reduces computation time and demonstrates improvement in downstream analysis. AVAILABILITY AND IMPLEMENTATION: The source code is freely available at https://github.com/yuzhong-deng/graphcpg.git.

The dc-link current is an important indicator for the design and selection of dc-link capacitors for voltage source inverter (VSI). The traditional dc-link current analysis for two-level three-phase VSI based motor drive only considers ac fundamental phase current and neglect the ac high-frequency current ripple caused by the pulse width modulation (PWM) process. Thus, this paper introduces an accurate analytical method of the dc-link capacitor current by taking the real-time ac high-frequency current ripple into consideration. Moreover, the accurate calculation of rms current on the dc-link capacitor has been provided with the traditional PWM methods, and the time-domain comparison of dc-link current has been studied under the wide range of adjusting speed and power factor. Simulation and experimental results are both provided to validate the accuracy of the proposed method.

In low-voltage energy storage microgird systems, the quasi-single-stage architecture is a promising alternative to improve the efficiency, which contains a direct power flow path from the battery to the inverter, resulting in reduced power losses by dc/dc converter. However, the unbalanced dc-link voltage of two ports certainly generates asymmetric space vectors. Thus, how to design the modulation strategy under this scenario is the major challenge. Meanwhile, the power losses are not only determined by the topology, but the device material such as gallium nitride (GaN) also has a significant impact on it. Therefore, a novel hybrid Si/GaN-based quasi-single-stage converter (HSG-QSSC) is proposed in this paper. Furthermore, a simplified space-vector modulation (SVM) scheme is presented to concentrate all the high-frequency switching events on the GaN HEMTs while the Si IGBTs operate with low frequency and avoid complicated triangle functions. As a result, the total power losses are reduced due to the decoupled frequency switching, and the high efficiency of calculation is achieved. Islanded microgrid experimental results with a hybrid Si/GaN active-neutral-point converter (ANPC) prototype are provided to verify the feasibility and effectiveness of the presented modulation scheme.

The open winding permanent magnet synchronous machine (OW-PMSM) driven by dual two-level three–phase inverters with common dc bus have become common in variable speed applications due to the inherent advantages. This paper makes analysis of the characteristic of different modulation schemes for three-phase OW-PMSM, including the dc-link capacitor current which determines the lifetime of dc-link capacitor, and the conduction losses of the dual inverters which influence the temperature rise and thermal stress of each inverter. With the theoretical analysis and comparison, the proposed phase-shift sinusoidal pulse width modulation (PS-SPWM) is proved to have better performance than the conventional signal rotation space vector pulse width modulation (SVPWM) in some respect. Simulation and experimental results are both provided to validate the effect of the characteristic for the modulation schemes.

Advances in high throughput sequencing have enabled DNA methylation profiling at single-cell resolution. The generation of single-cell methylation sequencing (scM-Seq) data provides unprecedented opportunities for a comprehensive dissection of epigenetic heterogeneity. An important step of exploring epigenetic heterogeneity is clustering cells according to their single-cell methylation profiles. However, the inherent sparsity and stochastic measurement characteristic of the data make it challenging. To this end, we introduce SINCEF, using spectral embedding fusion to reconstruct cell-to-cell pairwise distance for clustering single-cell methylation data. SIN CEF first calculates multiple basic distance matrices to capture cell-to-cell methylation dissimilarity relationships according to the global methylation status. Then it adopts spectral embedding to transform these basic distance matrices into the latent representations, pooling information from the basic distance measures. Finally, it reconstructs a novel distance matrix and implements hierarchical clustering to yield cell partitions. Assessments on several public scM-Seq datasets demonstrated that SINCEF could generate a more appropriate distance matrix to measure the methylation distance between cells, which considerably improved the clustering performance. As an additional benefit, the reconstructed novel distance matrix could help to visually assess the heterogeneity across cell populations through presenting the block structures in the hierarchical clustering heat maps. SINCEF is freely available on GitHub at https://github.com/TQBio/SINCEF.

MOTIVATION: Single-cell DNA methylation sequencing detects methylation levels with single-cell resolution, while this technology is upgrading our understanding of the regulation of gene expression through epigenetic modifications. Meanwhile, almost all current technologies suffer from the inherent problem of detecting low coverage of the number of CpGs. Therefore, addressing the inherent sparsity of raw data is essential for quantitative analysis of the whole genome. RESULTS: Here, we reported CaMelia, a CatBoost gradient boosting method for predicting the missing methylation states based on the locally paired similarity of intercellular methylation patterns. On real single-cell methylation datasets, CaMelia yielded significant imputation performance gains over previous methods. Furthermore, applying the imputed data to the downstream analysis of cell-type identification, we found that CaMelia helped to discover more intercellular differentially methylated loci that were masked by the sparsity in raw data, and the clustering results demonstrated that CaMelia could preserve cell-cell relationships and improve the identification of cell types and cell subpopulations. AVAILABILITY AND IMPLEMENTATION: Python code is available at https://github.com/JxTang-bioinformatics/CaMelia. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This article proposes a Bayesian method to acquire the estimation of human impedance and motion intention in a human-robot collaborative task. Combining with the prior knowledge of human stiffness, estimated stiffness obeying Gaussian distribution is obtained by Bayesian estimation, and human motion intention can be also estimated. An adaptive impedance control strategy is employed to track a target impedance model and neural networks are used to compensate for uncertainties in robotic dynamics. Comparative simulation results are carried out to verify the effectiveness of estimation method and emphasize the advantages of the proposed control strategy. The experiment, performed on Baxter robot platform, illustrates a good system performance.

Repetitive controller (RC) has the merits of simple structure, small computational burden, and providing zero steady-state control error for the closed-loop at the zero frequency, fundamental frequency, and its multiples. However, for a distributed generation (DG) interfacing converter with the auxiliary harmonic compensation capability, its harmonic control loop often does not need to control the direct current (DC) and fundamental frequency components, thereof RC is inapplicable. To address this issue, this paper proposes a new harmonic RC (HRC) for DG interfacing converters. To construct the HRC, a digital second-order high pass filter and a notch filter are respectively used to cancel poles of the internal model of conventional RC at zero and fundamental frequencies. When implemented in the harmonic control loop of the DG converter, the proposed HRC only deals with harmonics, avoiding the extra harmonic extraction. Both the mathematic model derivation and the controller parameters design are given in detail in the paper. Finally, experiments are performed to validate the effectiveness of the proposed scheme.

The time delay of digital control would make the equivalent output admittance of voltage source converter(VSC) non-passive, which may lead to the resonant instable problem. In this paper, the Luenberger observer-based active damping method is researched to make the admittance passive. The method contains two part: firstly, the observer predicts the capacitor current of the LCL filter; secondly, carrying out the active damping by using the predicted current. It turns out that the passivity of VSC's equivalent admittance is affected by both the observer and active damping, and the passive equivalent admittance can be obtained by properly designing the observer and active damping parameters. In practical application, the observer-based active damping method can not only avoid using additional current sensors but also make the equivalent admittance passive below the Nyquist frequency. The simulation results verified the effectiveness of the proposed method for improving stability.

This paper presents an online template update method with bidirectional consistency constraint for Siamese trackers. Due to continuously applying cross-correlation mechanism between template and the search region, the performance of Siamese trackers highly relies on the fidelity of template. Therefore, besides standard linear update, learning the template update methods attract attention. Inspired by this, in this paper we adopt a learning to update model called UpdateNet as our baseline. Different from it, we further propose a novel bi-directional consistency loss as a constraint to learn the template update more smoothly and stably. Our method considers both forward and backward information for each medium frame, thus introducing a multi-stage bidirectional simulated tracking training mechanism. We apply our model to a Siamese tracker, SiamRPN and demonstrate the effectiveness and robustness of our proposed method compared with traditional UpdateNet in the Large-scale Single Object Tracking (LaSOT) dataset.

Most traditional methods for solving the kinematic control problem of redundant manipulators are designed from a signal processing perspective. However, such a perspective may make the resultant design difficult for practitioners to understand. If the problem is addressed from an energy perspective, the resultant design may be more comprehensive, because energy is a universal concept and can be used to describe complex large-scale industrial systems. Passivity is a property of engineering systems, which is characterized through energy transformation. In this paper, a passivity-based approach is proposed for the kinematic control of redundant manipulators, where the joint velocity limit of manipulators is also considered. The performance of the approach is theoretically guaranteed. In addition, simulative examples are presented to validate the efficacy of the approach and the theoretical results.

Shunt active power filters (S-APF) are highly popular ways for harmonic compensation due to the high performance and simplicity of installation. S-APF is commonly controlled in current control mode with load harmonic current detection, which is not quite suitable for the distributed power generation system (DPGS) where the nonlinear loads are highly dispersed. Local harmonic voltage detection based Resistive-APF (R-APF) seems more suitable to be applied in the DPGS, however, R-APF suffers from poor compensation performance and difficulty of parameter tuning. In this paper, a direct harmonic voltage control strategy for the S-APF is proposed with local point of common coupling (PCC) voltage detection only. The control strategy design procedure is given in detail. Simulation is conducted in Matlab/Simulink to compare the performance between the R-APF and the proposed method. The results validate superiority of the proposed method.

The modular paralleled three-level T-Type Inverters (3LT2Is) have been widely used to extend the power capacity. However, zero-sequence circulating currents (ZSCCs) are generated due to the difference of parameters between the paralleled inverters. The ZSCCs will lead to various issues, such as output current distortion, unbalanced current distribution and system loss increasing, etc. The finite control set model predictive control (FCS-MPC) is an optimization control scheme which is suit for controlling the converters since it has the advantages of fast dynamic response, flexibility of control system constraints, etc. Thus, a FCS-MPC based ZSCCs elimination algorithm for the modular paralleled 3LT2Is system is presented in this paper. All the 27 switching states for the 3LT2Is are analyzed and divided into different groups by different contributions on the ZSCCs. Based on the switching state analysis, the cost function is designed to pick out the optimal vectors for each 3LT2Is to ensure the control requirements. Finally, all digital simulation have been carried out in Matlab/Simulink and the results validate the effectiveness of the proposed algorithm in current tracking, neutral point potentials (NPPs) balance and ZSCCs elimination.

Because of the low power losses and moderate cost, the magnetic powder cores are popular in producing the filtering inductors for the high efficient and cost-effective power converters. However, the soft magnetic property of the powder cores leads to the wide variation of inductance along with the changing of the inductor current in one cycle of the grid, which challenges the system stability and power quality. In this paper, the current-dependent small-signal model of a three-phase LCL-filtered inverter is derived for designing the corresponding controller. Based on the developed small-signal model, a capacitor current feedback based active damping loop and a fractional order repetitive control based compound current control loop are designed to stabilize the system and enhance the control accuracy in steady-state, respectively. The controller design procedure is given in detail. Finally, all-digital simulation has been conducted on a 3.7 kVA inverter system to verify the theoretical expectations.