检索结果-内蒙古大学图书馆

ABFS: Natural Robustness Testing for LLM-based NLP software

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xiao, Mingxuan Xiao, Yan Ji, Shunhui Li, Yunhe Xue, Lei Zhang, Pengcheng Key Laboratory of Water Big Data Technology of Ministry of Water Resources the College of Computer Science and Software Engineering Hohai University No. 8 Focheng West Road Jiangning District Nanjing211100 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University No.66 Gongchang Road Xinhu Street Guangming District Shenzhen528406 China

Owing to the exceptional performance of Large Language Models (LLMs) in Natural Language Processing (NLP) tasks, LLM-based NLP software has rapidly gained traction across various domains, such as financial analysis and content moderation. However, these applications frequently exhibit robustness deficiencies, where slight perturbations in input (prompt+example) may lead to erroneous outputs. Current robustness testing methods face two main limitations: (1) low testing effectiveness, limiting the applicability of LLM-based software in safety-critical scenarios, and (2) insufficient naturalness of test cases, reducing the practical value of testing outcomes. To address these issues, this paper proposes ABFS, a straightforward yet effective automated testing method that, for the first time, treats the input prompts and examples as a unified whole for robustness testing. Specifically, ABFS formulates the testing process as a combinatorial optimization problem, employing Best-First Search to identify successful test cases within the perturbation space and designing a novel Adaptive control strategy to enhance test case naturalness. We evaluate the robustness testing performance of ABFS on three datasets across five threat models. On Llama2-13b, the traditional StressTest achieves only a 13.273% success rate, while ABFS attains a success rate of 98.064%, supporting a more comprehensive robustness assessment before software deployment. Compared to baseline methods, ABFS introduces fewer modifications to the original input and consistently generates test cases with superior naturalness. Furthermore, test cases generated by ABFS exhibit stronger transferability and higher testing efficiency, significantly reducing testing costs. © 2025, CC BY-NC-ND.

关键词： software testing

GRAPH ATTENTION-BASED DEEP NEURAL NETWORK FOR 3D POINT CLOUD PROCESSING

学校读者我要写书评

暂无评论

GRAPH ATTENTION-BASED DEEP NEURAL NETWORK FOR 3D POINT CLOUD...

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Li, Xun Xue, Feng Chen, Chao Yuan, Xiaohui Lu, Qiang Ministry of Education Hefei China School of Computer Science and Information Hefei University of Technology Hefei China Hefei China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei China School of Software Hefei University of Technology Hefei China Department of Science and Engineering University of North Texas DentonTX United States

ISBN: (纸本)9781665438643

Due to the increasing popularity of 3D sensors, it has become easier and easier to obtain point cloud data. In many fields such as autonomous driving, how to fully extract the features of point cloud to better understand and perceive 3D scenes requires further research. Therefore, this paper proposes a novel end-to-end deep learning network for the features of disorder and irregularity of 3D point cloud data. Our network uses an encoder-decoder network architecture, and a three-layer structure is used in both stages. Each encoder layer consists of graph attention convolution and graph attention pooling. Graph attention convolution reflects the spatial distribution relationship in the neighborhood area. And graph attention pooling merges the spatial distribution information in the neighborhood into the feature of the sampling point. The experimental results show that our method achieves the best results in shape classification and has competitive performance in other tasks. © 2021 IEEE

关键词： Deep neural networks

Multi-Objective Optimization Design for DC-Link Capacitor of Motor Driver

学校读者我要写书评

暂无评论

Multi-Objective Optimization Design for DC-Link Capacitor of...

Energy Storage and Conversion (ISESC), CPSS & IEEE International Symposium on

作者： Qian Liu Kangxing Huang Xueliang Wei Yihong Zheng Hao Xiang School of Automation Wuhan University of Technology Wuhan China Department of Electronic & Computer Engineering Hong Kong University of Science and Technology Hongkong China College of Artificial Intelligence China University of Petroleum-Beijing Beijing China Software Development Department Wuhan iActuator Robotics Co. Ltd Wuhan China

ISBN: (数字)9798350380514

ISBN: (纸本)9798350380521

The capacitor is a common weak point in motor drive system design, necessitating targeted selection, design, and optimization of capacitor banks within these systems. Traditional capacitor design often relies on engineering experience, usually meeting specific capacitance and voltage requirements through simple parallel or series connections of capacitors. This approach often fails to fully optimize volume, cost, and reliability. This paper uses comprehensive theoretical modeling to optimize capacitor module design, effectively balancing capacitor lifespan, cost, and volume. For the design and selection of DC-link capacitors in a 1kW permanent magnet synchronous motor drive system, a multi-objective optimization design method for capacitor banks is proposed. The study treats the individual capacitance values of parallel capacitors as variables, significantly enhancing the overall performance of the capacitor module through precise optimization and the introduction of necessary constraints in the selection design. The proposed method is validated with a 1kW permanent magnet synchronous motor drive system. The optimization results show that under the guidance of a multi-objective optimization framework, the designed DC-link capacitor module meets physical size requirements while achieving overall optimization in terms of volume, cost, and lifespan, significantly improving system reliability.

关键词： Solid modeling Costs Capacitors Voltage Permanent magnet motors Capacitance Stability analysis Optimization Thermal stability System analysis and design

Learning Weighting Map for Bit-Depth Expansion within a Rational Range

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yuqing Jia, Qi Zhang, Jian Fan, Xin Wang, Shanshe Ma, Siwei Gao, Wen The School of Software Dalian University of Technology Dalian116620 China International School of Information Science and Engineering Dalian University of Technology Dalian116620 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China The School of Electronics Engineering and Computer Science Institute of Digital Media Peking University Beijing100871 China

Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth. In this paper, we design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range, invoking an accurate solution without modifying the given high-order bit information. To make the network adaptive for any bit-depth degradation, we investigate the issue in an optimization perspective and train the network under progressive training strategy for better performance. Moreover, we employ Wasserstein distance as a visual quality indicator to evaluate the difference of color distribution between restored image and the ground truth. Experimental results show our method can restore colorful images with fewer artifacts and false contours, and outperforms state-of-the-art methods with higher PSNR/SSIM results and lower Wasserstein distance. The source code will be made available at https://***/yuqing-liu-dut/ bit-depth-expansion Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

FireXnet: an explainable AI-based tailored deep learning model for wildfire detection on resource-constrained devices

学校读者我要写书评

暂无评论

Fire Ecology 2023年第1期19卷 1-19页

作者： Ahmad, Khubab Khan, Muhammad Shahbaz Ahmed, Fawad Driss, Maha Boulila, Wadii Alazeb, Abdulwahab Alsulami, Mohammad Alshehri, Mohammed S. Ghadi, Yazeed Yasin Ahmad, Jawad Faculty of Engineering and Technology Multimedia University Melaka Malaysia School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh UK Department of Cyber Security Pakistan Navy Engineering College NUST Karachi Pakistan Robotics and Internet of Things Laboratory Prince Sultan University Riyadh Saudi Arabia RIADI Laboratory National School of Computer Sciences University of Manouba Manouba Tunisia Department of Computer Science College of Computer Science and Information Systems Najran University Najran Saudi Arabia Department of Software Engineering Computer Science Al Ain University Abu Dhabi United Arab Emirates

Forests cover nearly one-third of the Earth’s land and are some of our most biodiverse ecosystems. Due to climate change, these essential habitats are endangered by increasing wildfires. Wildfires are not just a risk to the environment, but they also pose public health risks. Given these issues, there is an indispensable need for efficient and early detection methods. Conventional detection approaches fall short due to spatial limitations and manual feature engineering, which calls for the exploration and development of data-driven deep learning solutions. This paper, in this regard, proposes 'FireXnet', a tailored deep learning model designed for improved efficiency and accuracy in wildfire detection. FireXnet is tailored to have a lightweight architecture that exhibits high accuracy with significantly less training and testing time. It contains considerably reduced trainable and non-trainable parameters, which makes it suitable for resource-constrained devices. To make the FireXnet model visually explainable and trustable, a powerful explainable artificial intelligence (AI) tool, SHAP (SHapley Additive exPlanations) has been incorporated. It interprets FireXnet’s decisions by computing the contribution of each feature to the prediction. Furthermore, the performance of FireXnet is compared against five pre-trained models — VGG16, InceptionResNetV2, InceptionV3, DenseNet201, and MobileNetV2 — to benchmark its efficiency. For a fair comparison, transfer learning and fine-tuning have been applied to the aforementioned models to retrain the models on our dataset. The test accuracy of the proposed FireXnet model is 98.42%, which is greater than all other models used for comparison. Furthermore, results of reliability parameters confirm the model’s reliability, i.e., a confidence interval of [0.97, 1.00] validates the certainty of the proposed model’s estimates and a Cohen’s kappa coefficient of 0.98 proves that decisions of FireXnet are in considerable accordance with t

关键词：

A GNN-Based Learning Approach for Energy Optimization in Relay-Assisted IoT Networks

学校读者我要写书评

暂无评论

A GNN-Based Learning Approach for Energy Optimization in Rel...

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Yang, Huapeng Ji, Han Huang, Zhangqin Wu, Xiping College of Computer Science Beijing University of Technology Beijing Engineering Research Center for IoT Software and Systems Beijing100124 China School of Electrical and Electronic Engineering University College Dublin DublinD04 V1W8 Ireland School of Information Science and Engineering Southeast University The National Mobile Communications Research Laboratory Nanjing210096 China

ISBN: (纸本)9798350368369

Minimizing energy consumption is critical for the long-range (LoRa) Internet of Things (IoT) networks, to extend the battery lifetime of end devices (EDs) while reducing the maintenance cost. To overcome the excessive computational complexity required by the traditional optimization methods, learning approaches such as deep neural network (DNN) and reinforcement learning (RL) have been researched in wireless networks, where star topologies are widely employed. In contrast, LoRa usually deploys relays to assist the connection between the EDs and the gateway (GW), leading to a much more complex network topology. Consequently, DNN and RL would become less effective in LoRa, since those methods are difficult to learn the complex network topology constructed by LoRa. In this paper, we propose a learning method based on graph neural network (GNN), which is known for its prominent ability to capture and represent intricate graph-structural dependencies, to tackle the energy optimization problem for relay-assisted LoRa. Specifically, the multi-hop LoRa network is modeled as a directed graph, with channel state information (CSI) defined as node features, while the spreading factor and transmission power are deemed labels. A hierarchical message aggregation mechanism is proposed to effectively capture the multi-hop structural dependencies, followed by the process of inductive learning. Results show that against conventional optimization algorithms, the proposed method can achieve near-optimal energy consumption with a gap of 10% to 16%, while reducing the runtime by about six orders of magnitude. Compared to DNN, the GNN-based model can provide an energy saving of up to 32%, at a similar level of inference time. © 2025 IEEE.

关键词： Reinforcement learning

Microgrids-as-a-Service for Rural Electrification in Sub-Saharan Africa

学校读者我要写书评

暂无评论

computers, Materials & Continua 2020年第6期63卷 1249-1261页

作者： Qi Liu Kondwani Michael Kamoto Xiaodong Liu School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China School of Computing Edinburgh Napier UniversityEdinburghEH105DTUK

The majority of the population on the African continent is unable to access basic electricity services,this despite the abundance of renewable energy sources(RESs).The inability to adequately tap into these RESs has led to the continued dependence on non-renewable energy sources such as coal for electricity generation,and kerosene for cooking and lighting,the resulting use of which is poor health *** use of Microgrids(MGs)is being extensively researched as a feasible means of tackling the challenge of electrification,especially in rural and remote *** times have seen an increasing number of research works focusing on Sub-Saharan Africa(SSA),which is one of the regions with the lowest electrification rates in the *** provide the most suitable means to integrate RESs into the electricity generation process,paving the way towards clean energy for the African *** paper presents a review of recent literature on the usage of MG technology for rural electrification,with a specific focus on the applicability of MGs in the SSA *** paper additionally presents the challenges and opportunities to *** findings indicate that SSA has already begun the transition towards clean energy via implementation of RES-based ***,two resonating challenges in the literature are adequate support via policy,and proper planning of project *** two major barriers are needed to be overcome in order to fully utilize MGs for rural electrification in *** key methodology derived from this study is that any effort towards rural electrification requires a sufficient amount of investigation,incorporating both the technological and socio-economic aspects into a suitable design for the target location.

关键词： Microgrid rural electrification Sub-Saharan Africa

What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lei, Na Li, Zezeng Xu, Zebin Li, Ying Gu, Xianfeng The International Information and Software Institute Dalian University of Technology Dalian116620 China The School of Software Dalian University of Technology Dalian116620 China The College of Computer Science and Technology Jilin University Changchun130015 China The Department of Computer Science and Applied Mathematics State University of New York Stony BrookNY11794-2424 United States

Intelligent Mesh Generation (IMG) represents a novel and promising field of research, utilizing machine learning techniques to generate meshes. Despite its relative infancy, IMG has significantly broadened the adaptability and practicality of mesh generation techniques, delivering numerous breakthroughs and unveiling potential future pathways. However, a noticeable void exists in the contemporary literature concerning comprehensive surveys of IMG methods. This paper endeavors to fill this gap by providing a systematic and thorough survey of the current IMG landscape. With a focus on 113 preliminary IMG methods, we undertake a meticulous analysis from various angles, encompassing core algorithm techniques and their application scope, agent learning objectives, data types, targeted challenges, as well as advantages and limitations. We have curated and categorized the literature, proposing three unique taxonomies based on key techniques, output mesh unit elements, and relevant input data types. This paper also underscores several promising future research directions and challenges in IMG. To augment reader accessibility, a dedicated IMG project page is available at https://***/xzb030/IMG_Survey. Copyright © 2022, The Authors. All rights reserved.

关键词： Mesh generation

Efficient and Trustworthy Block Propagation for Blockchain-enabled Mobile Embodied AI Networks: A Graph Resfusion Approach

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kang, Jiawen Liao, Jiana Gao, Runquan Wen, Jinbo Huang, Huawei Zhang, Maomao Yi, Changyan Zhang, Tao Niyato, Dusit Zheng, Zibin Anhui Engineering Research Center for Agricultural Product Quality Safety Digital Intelligence Fuyang Normal University Fuyang236037 China School of Automation Guangdong University of Technology Guangzhou510006 China School of Software Engineering Sun Yat-Sen University Zhuhai519082 China School of Intelligent Systems Engineering Sun Yat-Sen University Shenzhen518107 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China College of Computing and Data Science Nanyang Technological University Singapore

By synergistically integrating mobile networks and embodied artificial intelligence (AI), Mobile Embodied AI Networks (MEANETs) represent an advanced paradigm that facilitates autonomous, context-aware, and interactive behaviors within dynamic environments. Nevertheless, the rapid development of MEANETs is accompanied by challenges in trustworthiness and operational efficiency. Fortunately, blockchain technology, with its decentralized and immutable characteristics, offers promising solutions for MEANETs. However, existing block propagation mechanisms suffer from challenges such as low propagation efficiency and weak security for block propagation, which results in delayed transmission of vehicular messages or vulnerability to malicious tampering, potentially causing severe traffic accidents in blockchain-enabled MEANETs. Moreover, current block propagation strategies cannot effectively adapt to real-time changes of dynamic topology in MEANETs. Therefore, in this paper, we propose a graph Resfusion model-based trustworthy block propagation optimization framework for consortium blockchain-enabled MEANETs. Specifically, we propose an innovative trust calculation mechanism based on the trust cloud model, which comprehensively accounts for randomness and fuzziness in the miner trust evaluation. Furthermore, by leveraging the strengths of graph neural networks and diffusion models, we develop a graph Resfusion model to effectively and adaptively generate the optimal block propagation trajectory. Simulation results demonstrate that the proposed model outperforms other routing mechanisms in terms of block propagation efficiency and trustworthiness. Additionally, the results highlight its strong adaptability to dynamic environments, making it particularly suitable for rapidly changing MEANETs. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks