Search

This study addresses the gap in the literature concerning the comparative performance of LLMs in interpreting different types of figurative language across multiple languages. By evaluating LLMs using two multilingual datasets on simile and idiom interpretation, we explore the effectiveness of various prompt engineering strategies, including chain-of-thought, few-shot, and English translation prompts. We extend the language of these datasets to Persian as well by building two new evaluation sets. Our comprehensive assessment involves both closed-source (GPT-3.5, GPT-4o mini, Gemini 1.5), and open-source models (Llama 3.1, Qwen2), highlighting significant differences in performance across languages and figurative types. Our findings reveal that while prompt engineering methods are generally effective, their success varies by figurative type, language, and model. We also observe that open-source models struggle particularly with low-resource languages in similes. Additionally, idiom interpretation is nearing saturation for many languages, necessitating more challenging evaluations., Comment: 22 pages, 4 figures

Chest X-rays (X-ray images) have been proven to be effective for the diagnosis of chest diseases, including Pneumonia, Lung Opacity, and COVID-19. However, relying on traditional medical methods for diagnosis from X-ray images is prone to delays and inaccuracies because the medical personnel who evaluate the X-ray images may have preconceived biases. For this reason, researchers have proposed the use of deep learning-based techniques to facilitate the diagnosis process. The preeminent method is the use of sophisticated Convolutional Neural Networks (CNNs). In this paper, we propose a novel detection model named \textbf{AttCDCNet} for the task of X-ray image diagnosis, enhancing the popular DenseNet121 model by adding an attention block to help the model focus on the most relevant regions, using focal loss as a loss function to overcome the imbalance of the dataset problem, and utilizing depth-wise convolution to reduce the parameters to make the model lighter. Through extensive experimental evaluations, the proposed model demonstrates exceptional performance, showing better results than the original DenseNet121. The proposed model achieved an accuracy, precision and recall of 94.94%, 95.14% and 94.53%, respectively, on the COVID-19 Radiography Dataset.

Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is crucial for improving the efficiency and interpretability of plan generation as LLMs become more central to automation and decision-making. We introduce a novel approach to skill learning in LLMs by integrating process mining techniques, leveraging process discovery for skill acquisition, process models for skill storage, and conformance checking for skill retrieval. Our methods enhance text-based plan generation by enabling flexible skill discovery, parallel execution, and improved interpretability. Experimental results suggest the effectiveness of our approach, with our skill retrieval method surpassing state-of-the-art accuracy baselines under specific conditions., Comment: 12 pages, 5 figures, 2 tables, accepted at ICPM 2024'

Language model pre-training benefits from diverse data to enhance performance across domains and languages. However, training on such heterogeneous corpora requires extensive and costly efforts. Since these data sources vary lexically, syntactically, and semantically, they cause negative interference or the ``curse of multilinguality''. We propose a novel pre-training framework to alleviate this curse. Our method, DEPT, decouples embeddings from the transformer body while simultaneously training the latter in multiple contexts. DEPT enables training without a shared global vocabulary and: (1) can train robustly and effectively under significant data heterogeneity, (2) reduces token embedding parameters by up to 80% and the communication costs by 675x for billion-scale models, (3) enhances model generalization and plasticity in adapting to new languages and domains, and (4) permits training with custom optimized vocabularies per data source. We demonstrate DEPT's potential via the first vocabulary-agnostic federated multilingual pre-training of a 1.3 billion-parameter model, limiting its embedding size to 102.4 million instead of 512 million.

The current cybersecurity landscape is increasingly complex, with traditional Static Application Security Testing (SAST) tools struggling to capture complex and emerging vulnerabilities due to their reliance on rule-based matching. Meanwhile, Large Language Models (LLMs) have demonstrated powerful code analysis capabilities, but their static training data and privacy risks limit their effectiveness. To overcome the limitations of both approaches, we propose LSAST, a novel approach that integrates LLMs with SAST scanners to enhance vulnerability detection. LSAST leverages a locally hostable LLM, combined with a state-of-the-art knowledge retrieval system, to provide up-to-date vulnerability insights without compromising data privacy. We set a new benchmark for static vulnerability analysis, offering a robust, privacy-conscious solution that bridges the gap between traditional scanners and advanced AI-driven analysis. Our evaluation demonstrates that incorporating SAST results into LLM analysis significantly improves detection accuracy, identifying vulnerabilities missed by conventional methods., Comment: Under Review of IEEE SaTML 2024

Large Language Models (LLMs) have shown significant promise in plan generation. Yet, existing datasets often lack the complexity needed for advanced tool use scenarios - such as handling paraphrased query statements, supporting multiple languages, and managing actions that can be done in parallel. These scenarios are crucial for evaluating the evolving capabilities of LLMs in real-world applications. Moreover, current datasets don't enable the study of LLMs from a process perspective, particularly in scenarios where understanding typical behaviors and challenges in executing the same process under different conditions or formulations is crucial. To address these gaps, we present the ProcessTBench synthetic dataset, an extension of the TaskBench dataset specifically designed to evaluate LLMs within a process mining framework., Comment: 6 pages, 4 figures, dataset available at https://github.com/microsoft/ProcessTBench

The continuous flow of data collected by Internet of Things (IoT) devices, has revolutionised our ability to understand and interact with the world across various applications. However, this data must be prepared and transformed into event data before analysis can begin. In this paper, we shed light on the potential of leveraging Large Language Models (LLMs) in event abstraction and integration. Our approach aims to create event records from raw sensor readings and merge the logs from multiple IoT sources into a single event log suitable for further Process Mining applications. We demonstrate the capabilities of LLMs in event abstraction considering a case study for IoT application in elderly care and longitudinal health monitoring. The results, showing on average an accuracy of 90% in detecting high-level activities. These results highlight LLMs' promising potential in addressing event abstraction and integration challenges, effectively bridging the existing gap., Comment: 12 pages

Cardiac auscultation, an integral tool in diagnosing cardiovascular diseases (CVDs), often relies on the subjective interpretation of clinicians, presenting a limitation in consistency and accuracy. Addressing this, we introduce the BUET Multi-disease Heart Sound (BMD-HS) dataset - a comprehensive and meticulously curated collection of heart sound recordings. This dataset, encompassing 864 recordings across five distinct classes of common heart sounds, represents a broad spectrum of valvular heart diseases, with a focus on diagnostically challenging cases. The standout feature of the BMD-HS dataset is its innovative multi-label annotation system, which captures a diverse range of diseases and unique disease states. This system significantly enhances the dataset's utility for developing advanced machine learning models in automated heart sound classification and diagnosis. By bridging the gap between traditional auscultation practices and contemporary data-driven diagnostic methods, the BMD-HS dataset is poised to revolutionize CVD diagnosis and management, providing an invaluable resource for the advancement of cardiac health research. The dataset is publicly available at this link: https://github.com/mHealthBuet/BMD-HS-Dataset., Comment: 14 pages, 13 figures

Multimodal aspect-based sentiment analysis (MABSA) enhances sentiment detection by combining text with other data types like images. However, despite setting significant benchmarks, attention mechanisms exhibit limitations in efficiently modelling long-range dependencies between aspect and opinion targets within the text. They also face challenges in capturing global-context dependencies for visual representations. To this end, we propose Kolmogorov-Arnold Networks (KANs) and Selective State Space model (Mamba) transformer (DualKanbaFormer), a novel architecture to address the above issues. We leverage the power of Mamba to capture global context dependencies, Multi-head Attention (MHA) to capture local context dependencies, and KANs to capture non-linear modelling patterns for both textual representations (textual KanbaFormer) and visual representations (visual KanbaFormer). Furthermore, we fuse the textual KanbaFormer and visual KanbaFomer with a gated fusion layer to capture the inter-modality dynamics. According to extensive experimental results, our model outperforms some state-of-the-art (SOTA) studies on two public datasets., Comment: 10 pages, 2 figures, and 3 tables

We report the serendipitous discovery of a faint (M_UV > -12.2), low-metallicity (Z ~ 0.02 Zsun), ionizing source (dubbed T2c) with a spectroscopic redshift of z=6.146. T2c is part of a larger structure amplified by the Hubble Frontier Field galaxy cluster MACSJ0416, and was observed with JWST/NIRSpec IFU. Stacking the short-wavelength NIRCam data reveals no stellar continuum detection down to a magnitude limit of m_UV ~ 31.0 (3 sigma). However, prominent Hb, [OIII]4959,5007, and Ha emissions are detected, with equivalent widths exceeding 200A, 800A, and 1300A (3 sigma), respectively. The corresponding intrinsic (magnification-corrected x23 +/- 3) ultraviolet and optical rest-frame magnitudes exceed 34.4 and 33.9 (corresponding to M_uv and M_opt fainter than -12.2 and -12.8, at lambda_rest ~ 2000A and ~5000A, respectively), suggesting a stellar mass lower than a few 10^4 Msun under an instantaneous burst scenario. The inferred ionizing photon production efficiency (xi_ion) is high, xi_ion >~ 26.08(25.86) 3(5)sigma, assuming no dust attenuation and no Lyman continuum leakage, indicating the presence of massive stars despite the low mass of the object. The very poor sampling of the initial mass function at such low mass star-forming complex suggests that the formation of very massive stars might be favored in very low metallicity environments. T2c is surrounded by Balmer and weak oxygen emission on a spatial scale of a few hundred parsecs after correcting for lensing effects. This system resembles an HII region potentially powered by currently undetected, extremely efficient, low-metallicity star complexes or clusters. We propose that massive O-type stars populate this low-mass and metallicity high-redshift satellites, likely caught in an early and short formation phase, contributing to the ionization of the surrounding medium., Comment: 9 pages, 5 figures, 1 table. Submitted to A&A. Comments are welcome

The ROS 2 Navigation Stack (Nav2) has emerged as a widely used software component providing the underlying basis to develop a variety of high-level functionalities. However, when used in outdoor environments such as orchards and vineyards, its functionality is notably limited by the presence of obstacles and/or situations not commonly found in indoor settings. One such example is given by tall grass and weeds that can be safely traversed by a robot, but that can be perceived as obstacles by LiDAR sensors, and then force the robot to take longer paths to avoid them, or abort navigation altogether. To overcome these limitations, domain specific extensions must be developed and integrated into the software pipeline. This paper presents a new, lightweight approach to address this challenge and improve outdoor robot navigation. Leveraging the multi-scale nature of the costmaps supporting Nav2, we developed a system that using a depth camera performs pixel level classification on the images, and in real time injects corrections into the local cost map, thus enabling the robot to traverse areas that would otherwise be avoided by the Nav2. Our approach has been implemented and validated on a Clearpath Husky and we demonstrate that with this extension the robot is able to perform navigation tasks that would be otherwise not practical with the standard components., Comment: Published at ICRA 2024

The potential health risks of cement dust exposure are increasingly raising concern worldwide as the cement industry expands in response to rising cement demand. This necessitates the need to determine the nature of the risks in order to develop appropriate measures. This study determined the effects of cement dust exposure on the weight and blood glucose levels of people residing or working around a cement company in Sokoto, Nigeria. Demographic information was obtained using questionnaires from 72 participants, which included age, gender, educational level, exposure hours, occupation, and lifestyle. The blood glucose levels and body mass index (BMI) were measured using a Fine Test glucometer and a mechanical scale, respectively. The results showed that most of the people living or working around the cement company were middle-aged men (31-40; 42.06%) with a primary (33.33%) or secondary (45.83%) school education. It showed that 30 (41.69%) of the participants were overweight while 5 (6.94%) were obese. Additionally, 52.78% of the participants were diabetic while 31.94% were prediabetic. Participants that were exposed for long hours (> 15 hours per day) were the most diabetic (20% of the participants), followed by smokers (15%), and artisans (7%). It can be concluded that exposure to cement dust from the company increased the risk of overweight, obesity, and hyperglycemia among the participants. These health risks were worsened by daily long hours of exposure, smoking, and artisanal pollutant exposure. Human settlements and artisans should not be located near the cement company, and the company should minimize pollutant emissions., Comment: accept

Due to the increasing popularity of DC loads and the potential for higher efficiency, DC microgrids are gaining significant attention. DC microgrids utilize multiple parallel converters to deliver sufficient power to the load. However, a key challenge arises when connecting these converters to a common DC bus: maintaining voltage regulation and accurate current sharing. Unequal cable resistances can cause uneven power sharing and lead to power losses. Conventional droop control methods, which employ a virtual resistor to address this issue, have limitations in achieving good performance across the entire converter operating range. This paper proposes a modified droop control algorithm to address this issue. This method modifies the virtual resistor in a way that ensures power sharing aligns with each converter-rated capacity. The algorithm is simple to implement and uses local measurements to update the droop gain. This paper presents simulation studies and experimental tests to analyze the performance of the proposed method, considering scenarios with equal and unequal converter ratings. The results successfully validate the accuracy and effectiveness of this innovative approach.

Cyberattack susceptibilities are introduced as the communication requirement increases with the incorporation of more renewable energy sources into DC microgrids. Parallel DC-DC converters are utilized to provide high current and supply the load. Nevertheless, these systems are susceptible to cyberattacks that have the potential to disrupt operations and jeopardize stability. Voltage instability may result from the manipulation of communication commands and low-layer control signals. Therefore, in this paper, a cyberattack that specifically targets parallel DC-DC converters is examined in a DC microgrid. A hybrid machine learning-based detection and mitigation strategy is suggested as a means to counteract this threat. The false data injection (FDI) attack targeting the converters is investigated within a DC microgrid. The efficacy of the suggested approach is verified via simulations executed for various scenarios within the MATLAB/Simulink environment. The technique successfully identifies and blocks FDI attacks, preventing cyberattacks and ensuring the safe operation of the DC microgrid.

Graph hypernetworks (GHNs), constructed by combining graph neural networks (GNNs) with hypernetworks (HNs), leverage relational data across various domains such as neural architecture search, molecular property prediction and federated learning. Despite GNNs and HNs being individually successful, we show that GHNs present problems compromising their performance, such as over-smoothing and heterophily. Moreover, we cannot apply GHNs directly to personalized federated learning (PFL) scenarios, where a priori client relation graph may be absent, private, or inaccessible. To mitigate these limitations in the context of PFL, we propose a novel class of HNs, sheaf hypernetworks (SHNs), which combine cellular sheaf theory with HNs to improve parameter sharing for PFL. We thoroughly evaluate SHNs across diverse PFL tasks, including multi-class classification, traffic and weather forecasting. Additionally, we provide a methodology for constructing client relation graphs in scenarios where such graphs are unavailable. We show that SHNs consistently outperform existing PFL solutions in complex non-IID scenarios. While the baselines' performance fluctuates depending on the task, SHNs show improvements of up to 2.7% in accuracy and 5.3% in lower mean squared error over the best-performing baseline., Comment: 25 pages, 12 figures, 7 tables, pre-print under review

The term 'active galactic nuclei' (AGN) subtends a huge variety of objects, classified on their properties at different wavelengths. Peaked sources (PS) represent a class of AGN at the first stage of evolution, characterised by a peaked radio spectrum. Among these radio sources, low-luminosity compact (LLC) sources can be identified as PS accreting with a high Eddington rate, harbouring low-power jets and hosting low-mass black holes. These properties are also shared by narrow-line Seyfert 1 galaxies (NLS1s). In 2016, LLCs were hypothesised to be the parent population of NLS1s with a flat radio spectrum (F-NLS1s), suggesting the former to be the same objects as the latter, seen at higher inclination. Based on radio luminosity functions and optical spectra analysis, 10 LLCs were identified as valid candidates for F-NLS1s. To account for the missing puzzle piece, verifying if these LLCs could be hosted in late-type galaxies as NLS1s, we performed the photometric decomposition of their Pan-STARRS1 images in all five filters. We used the 2D fitting algorithm GALFIT for the single-band analysis, and its extension GALFITM for the multi-band analysis. Considering that the morphological type and the structural parameters of the host can be dependent on the wavelength, we found six out of ten LLCs hosted in late-type galaxies, probably with pseudo-bulges, three point-like sources and one object of uncertain classification. Although this study is based on a small sample, it represents the first morphological analysis of LLC host galaxies. The results confirm the trend observed in NLS1s, indicating late-type/disc-like host galaxies for LLCs and supporting the validity of the parent population scenario., Comment: 15 pages, 21 figures, accepted for publication in A&A

The reliance of language model training on massive amounts of computation and vast datasets scraped from potentially low-quality, copyrighted, or sensitive data has come into question practically, legally, and ethically. Federated learning provides a plausible alternative by enabling previously untapped data to be voluntarily gathered from collaborating organizations. However, when scaled globally, federated learning requires collaboration across heterogeneous legal, security, and privacy regimes while accounting for the inherent locality of language data; this further exacerbates the established challenge of federated statistical heterogeneity. We propose a Worldwide Federated Language Model Training~(WorldLM) system based on federations of federations, where each federation has the autonomy to account for factors such as its industry, operating jurisdiction, or competitive environment. WorldLM enables such autonomy in the presence of statistical heterogeneity via partial model localization by allowing sub-federations to attentively aggregate key layers from their constituents. Furthermore, it can adaptively share information across federations via residual layer embeddings. Evaluations of language modeling on naturally heterogeneous datasets show that WorldLM outperforms standard federations by up to $1.91\times$, approaches the personalized performance of fully local models, and maintains these advantages under privacy-enhancing techniques., Comment: 19 pages, 8 figures, Under Review

Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a wide range of tasks, thanks to the unprecedented amount of data they have been trained on. As established scaling laws indicate, LLMs' future performance improvement depends on the amount of computing and data sources they can leverage for pre-training. Federated learning (FL) has the potential to unleash the majority of the planet's data and computational resources, which are underutilized by the data-center-focused training methodology of current LLM practice. Our work presents a robust, flexible, reproducible FL approach that enables large-scale collaboration across institutions to train LLMs. We propose a scalable deployment system called Photon to enable the investigation and development of this new training paradigm for LLM pre-training. We show that Photon can be used by organizations interested in collaborating with their private data sources and computational resources for pre-training LLMs with billions of parameters. This paradigm would mobilize more computational and data resources while matching or potentially exceeding centralized performance. We further show the effectiveness of the federated training scales with model size and present our approach for training billion-scale federated LLMs using limited resources. Thus far, we have used Photon to train LLM models to the size of 7B parameters and anticipate larger models being completed in the near future. Finally, we show that LLM training is highly resilient to the classical challenges of federated statistical and hardware heterogeneity. Furthermore, we show that convergence is robust to partial participation, opening the avenue for compute-efficient collaborative training. Photon will help data-rich actors to become the protagonists of LLMs pre-training instead of leaving the stage to compute-rich actors alone., Comment: 24 pages, 15 figures, pre-print

Numerous applications have resulted from the automation of agricultural disease segmentation using deep learning techniques. However, when applied to new conditions, these applications frequently face the difficulty of overfitting, resulting in lower segmentation performance. In the context of potato farming, where diseases have a large influence on yields, it is critical for the agricultural economy to quickly and properly identify these diseases. Traditional data augmentation approaches, such as rotation, flip, and translation, have limitations and frequently fail to provide strong generalization results. To address these issues, our research employs a novel approach termed as PotatoGANs. In this novel data augmentation approach, two types of Generative Adversarial Networks (GANs) are utilized to generate synthetic potato disease images from healthy potato images. This approach not only expands the dataset but also adds variety, which helps to enhance model generalization. Using the Inception score as a measure, our experiments show the better quality and realisticness of the images created by PotatoGANs, emphasizing their capacity to resemble real disease images closely. The CycleGAN model outperforms the Pix2Pix GAN model in terms of image quality, as evidenced by its higher IS scores CycleGAN achieves higher Inception scores (IS) of 1.2001 and 1.0900 for black scurf and common scab, respectively. This synthetic data can significantly improve the training of large neural networks. It also reduces data collection costs while enhancing data diversity and generalization capabilities. Our work improves interpretability by combining three gradient-based Explainable AI algorithms (GradCAM, GradCAM++, and ScoreCAM) with three distinct CNN architectures (DenseNet169, Resnet152 V2, InceptionResNet V2) for potato disease classification.

100% inverter-based renewable units are becoming more prevalent, introducing new challenges in the protection of microgrids that incorporate these resources. This is particularly due to low fault currents and bidirectional flows. Previous work has studied the protection of microgrids with high penetration of inverter-interfaced distributed generators; however, very few have studied the protection of a 100% inverter-based microgrid. This work proposes machine learning (ML)-based protection solutions using local electrical measurements that consider implementation challenges and effectively combine short-circuit fault detection and type identification. A decision tree method is used to analyze a wide range of fault scenarios. PSCAD/EMTDC simulation environment is used to create a dataset for training and testing the proposed method. The effectiveness of the proposed methods is examined under seven distinct fault types, each featuring varying fault resistance, in a 100% inverter-based microgrid consisting of four inverters., Comment: Accepted for publication at 2024 IEEE 33rd International Symposium on Industrial Electronics (ISIE)

As the composition of the power grid evolves to integrate more renewable generation, its reliance on distributed energy resources (DER) is increasing. Existing DERs are often controlled with proportional integral (PI) controllers that, if not properly tuned or if system parameters change, exhibit sluggish performance or large overshoot. The use of set point automatic adjustment with correction-enabled (SPAACE) with a linear predictor improves the transient response of these DERs without the need to access the PI controller parameters. The limitation of the existing SPAACE method is the high sampling rate needed for improved performance, which is not always practical. This paper proposes the addition of a memory term to the SPAACE with a linear predictor. This memory term is the integral of the errors of previous samples, which adds another layer to the prediction to improve the response at lower sampling rates and further reduces the overshoot and settling time compared to the existing SPAACE method. Time-domain simulation studies are performed in PSCAD/EMTDC to show the effectiveness of the proposed controller., Comment: Accepted for publication at IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society

The number of installed remote terminal units (RTU) is on the rise, increasing the observability and control of the power system. RTUs enable sending data to and receiving data from a control center in the power system. A distribution grid control center runs distribution management system (DMS) algorithms, where the DMS takes control actions during transients and outages, such as tripping a circuit breaker and disconnecting a controllable load to increase the resiliency of the grid. Relying on communication-based devices makes the control center vulnerable to cyberattacks, and attackers can send falsified data to the control center to cause disturbances or power outages. Previous work has conducted research on developing ways to detect a cyberattack and ways to mitigate the adverse effects of the attack. This work studies false data injection (FDI) attacks on the DMS algorithm of a fully inverter-based microgrid in real time. The fully inverter-based microgrid is simulated using an RTDS, an amplifier, an electronic load, a server, a network switch, and a router. The DMS is integrated into the server codes and exchanges data with RTDS through TCP/IP protocols. Moreover, a recurrent neural network (RNN) algorithm is used to detect and mitigate the cyberattack. The effectiveness of the detection and mitigation algorithm is tested under various scenarios using the real-time testbed., Comment: Accepted for publication at IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society

Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical vulnerability, often succumbing to overfitting by excessively memorizing the limited information available. This work addresses the challenge mentioned above by improving the supervised contrastive learning method leveraging both image-level labels and domain-specific augmentations to enhance model robustness. This approach integrates self-supervised pre-training with a two-stage supervised contrastive learning strategy. In the first stage, we employ a modified supervised contrastive loss that not only focuses on reducing false negatives but also introduces an elimination effect to address false positives. In the second stage, a relaxing mechanism is introduced that refines positive and negative pairs based on similarity, ensuring that only relevant image representations are aligned. We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images, and demonstrate an increase in classification accuracy by 1.45% in the image level, compared to the state-of-the-art method. This improvement corresponds to 93.63% absolute accuracy, highlighting the effectiveness of our approach in leveraging properties of data to learn more appropriate representation space., Comment: This work has been accepted to the Medical & Biological Engineering & Computing (MBEC 2024) journal

An LCL filter offers superior attenuation for high-frequency harmonics for three-phase grid-following inverters compared to LC and L filters. However, it also introduces an inherent resonance peak, which can lead to power quality issues or even instability of the inverter control system. Active damping (AD) is widely employed to effectively mitigate this resonance. Capacitor voltage feedback (CVF) and capacitor current feedback (CCF) are effective AD methods for LCL resonance damping. CVF is preferred due to its lower sensor requirement compared to CCF. However, a derivative term appears in the active damping loop, which introduces high-frequency noise into the system. This paper proposes a noise-immune approach by replacing the derivative term with a discrete function suitable for digital implementation. The LCL resonance can be damped effectively, resulting in enhanced stability of the inverter control system. Simulation results verify the proposed effectiveness of the method with grid inductance variation and weak grid conditions, Comment: 5 pages, 9 figures, conference paper