检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shin, Juhyeon Lee, Jonghyun Lee, Saehyung Park, Minjun Lee, Dongjun Hwang, Uiwon Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of

In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label. We developed a gradient alignment loss to precisely manage the adaptation process, ensuring that changes made for some data don’t negatively impact the model’s performance on other data. We introduce a prototype feature of a class as a proxy measure of the negative impact. To make GAP regularizer feasible under the TTA constraints, where model can only access test data without labels, we tailored its formula in two ways: approximating prototype features with weight vectors of the classifier, calculating gradient without back-propagation. We demonstrate GAP significantly improves TTA methods across various datasets, which proves its versatility and effectiveness. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

DAFA: DISTANCE-AWARE FAIR ADVERSARIAL TRAINING

arXiv

引用

arXiv 2024年

作者： Lee, Hyungyu Lee, Saehyung Jang, Hyemi Park, Junsung Bae, Ho Yoon, Sungroh Electrical and Computer Engineering Seoul National University Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem. Existing methodologies aimed to enhance robust fairness by sacrificing the model's performance on easier classes in order to improve its performance on harder ones. However, we observe that under adversarial attacks, the majority of the model's predictions for samples from the worst class are biased towards classes similar to the worst class, rather than towards the easy classes. Through theoretical and empirical analysis, we demonstrate that robust fairness deteriorates as the distance between classes decreases. Motivated by these insights, we introduce the Distance-Aware Fair Adversarial training (DAFA) methodology, which addresses robust fairness by taking into account the similarities between classes. Specifically, our method assigns distinct loss weights and adversarial margins to each class and adjusts them to encourage a trade-off in robustness among similar classes. Experimental results across various datasets demonstrate that our method not only maintains average robust accuracy but also significantly improves the worst robust accuracy, indicating a marked improvement in robust fairness compared to existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Q-Learning-Based Multi-Objective Global Path Planning for UGV Navigation*

Q-Learning-Based Multi-Objective Global Path Planning for UG...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Hiago O. B. Batista Thayron M. Hudson Kevin B. de Carvalho Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Núcleo de Especialização em Robótica (NERo) Universidade Federal de Viçosa Viçosa - MG Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

This paper presents an offline path planning strategy for unmanned ground vehicles (UGVs) using Q-learning. The proposed method addresses path optimization in warehouse-like environments, where tasks involve item pickup and delivery to specific locations. The Q-learning algorithm trains an agent to determine the most efficient routes, with validation conducted in an $8 \times 5$ meter workspace equipped with an Optitrack motion capture system. The workspace was discretized into a $16 \times 10$ grid, allowing the Q-learning to effectively navigate through complex obstacle-laden scenarios. Experimental results indicate that the Q-learning approach outperforms traditional methods such as Dijkstra, A-star, and Breadth-First Search in terms of path length, number of turns, planning time, and overall success rate; being up to 7 times faster to plan a path and reducing the number of bends by up to 41%. The Q-learning based paths feature more linear segments, which contribute to energy savings and improved navigational efficiency. Future work will explore applications in heterogeneous multi-agent systems and enhancements in training time and agent collaboration.

关键词： Training Meters Q-learning Navigation Path planning Motion capture Planning Robots Optimization Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

SF(DA)2: SOURCE-FREE DOMAIN ADAPTATION THROUGH THE LENS OF DATA AUGMENTATION

arXiv

引用

arXiv 2024年

作者： Hwang, Uiwon Lee, Jonghyun Shin, Juhyeon Yoon, Sungroh Division of Digital Healthcare Yonsei University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

In the face of the deep learning model’s vulnerability to domain shift, source-free domain adaptation (SFDA) methods have been proposed to adapt models to new, unseen target domains without requiring access to source domain data. Although the potential benefits of applying data augmentation to SFDA are attractive, several challenges arise such as the dependence on prior knowledge of class-preserving transformations and the increase in memory and computational requirements. In this paper, we propose Source-free Domain Adaptation Through the Lens of Data Augmentation (SF(DA)2), a novel approach that leverages the benefits of data augmentation without suffering from these challenges. We construct an augmentation graph in the feature space of the pretrained model using the neighbor relationships between target features and propose spectral neighborhood clustering to identify partitions in the prediction space. Furthermore, we propose implicit feature augmentation and feature disentanglement as regularization loss functions that effectively utilize class semantic information within the feature space. These regularizers simulate the inclusion of an unlimited number of augmented target features into the augmentation graph while minimizing computational and memory demands. Our method shows superior adaptation performance in SFDA scenarios, including 2D image and 3D point cloud datasets and a highly imbalanced dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

On mitigating stability-plasticity dilemma in CLIP-guided image morphing via geodesic distillation loss

arXiv

引用

arXiv 2024年

作者： Oh, Yeongtak Lee, Saehyung Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of

Large-scale language-vision pre-training models, such as CLIP, have achieved remarkable text-guided image morphing results by leveraging several unconditional generative models. However, existing CLIP-guided image morphing methods encounter difficulties when morphing photorealistic images. Specifically, existing guidance fails to provide detailed explanations of the morphing regions within the image, leading to misguidance. In this paper, we observed that such misguidance could be effectively mitigated by simply using a proper regularization loss. Our approach comprises two key components: 1) a geodesic cosine similarity loss that minimizes inter-modality features (i.e., image and text) on a projected subspace of CLIP space, and 2) a latent regularization loss that minimizes intra-modality features (i.e., image and image) on the image manifold. By replacing the naïve directional CLIP loss in a drop-in replacement manner, our method achieves superior morphing results on both images and videos for various benchmarks, including CLIP-inversion. © 2024, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Density Based Spatial Clustering of Applications with Noise and Sentence Bert Embedding for Indonesian Utterance Clustering

Density Based Spatial Clustering of Applications with Noise ...

引用

computer Science, Information Technology and engineering (ICCoSITE), International Conference on

作者： Muhammad Fikri Hasani Yaya Heryadi Yulyani Arifin Lukas Wayan Suparta Computer Science Department BINUS Graduate Program Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance.

关键词： computer science Art Text categorization Clustering algorithms Oral communication Chatbots Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Low-Crosstalk in 2D Waveguide Crossings by Metaheuristic Optimization Methods

Low-Crosstalk in 2D Waveguide Crossings by Metaheuristic Opt...

引用

Optics and Photonics Conference (SBFoton IOPC), SBFoton International

作者： Luana da França Vieira C. E. Rubio-Mercedes Vitaly Felix Rodriguez Esquerre Department of Computer Science Federal University of Western Bahia Barreiras Brazil Physics Engineering Program State University of Mato Grosso do Sul Dourados Brazil Graduate School of Electrical Engineering Federal University of Bahia Salvador Brazil

ISBN: (数字)9798350388176

ISBN: (纸本)9798350388183

This work describes the investigation of planar waveguide crossings using metaheuristic methods associated with the two-dimensional finite element method (2D-FEM). An optimization and measurement process are performed on the power transmission and crosstalk of the waveguide crossings and then the values calculated are compared with other studies in the literature. The best performing adjusted crossing is optimally designed by applying the following metaheuristics: Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), and a hybrid algorithm combining the Greedy Randomized Adaptive Search Procedure and Simulated Annealing (GRASP-SA). Transmission efficiency results higher than 97% and crosstalk below the -50 dB over a wide wavelength range, with a footprint of $\mathbf{4.9}\times \mathbf{4.9}\ \boldsymbol{\mu} \mathbf{m}^{\mathbf{2}}$ .

关键词： Performance evaluation Power measurement Metaheuristics Crosstalk Power transmission Simulated annealing Silicon Planar waveguides Optical waveguides Photonics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Fault Detection and Diagnosis: Application to Photovoltaic System 19

Deep Learning for Fault Detection and Diagnosis: Application...

引用

19th IEEE International Multi-Conference on Systems, Signals and Devices, SSD 2022

作者： Marweni, Manel Fezai, Radhia Hajji, Mansour Mansouri, Majdi National Engineering School of Monastir Research Laboratory of Automation Signal Processing and Im-age 5019 Tunisia Electrical and Computer Engineering Program Texas A&m University at Qatar Doha23874 Qatar Prince Sultan University Department of Mathematics and Sciences Riyadh11586 Saudi Arabia

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

With expanding requests for effectiveness and product quality and advancing integration of au-tomatic control systems in high-cost and safety-critical processes, Fault Detection and Diagnosis (FDD) in photo-voltaic (PV) have gained a very important role. However, PV systems can be subject to failures. These faults may include the distinctive system components such as PV modules, converters/inverters, connection lines, which can lead to a reduce in the operation performance. Thus, FDD is one of the key technologies to improve the efficiency of grid-connected PV performances. The most well-known data-driven based FDD methods are Deep Learning (DL)-basd approaches. The main advantages of DL algorithms, are that they can learn automatically high- level features from PV data in a high-order. This paper therefore presents the appli-cation of DL-based tools for fault diagnosis purposes and provides a comparative study using PV systems. These techniques include Convolutional Neural Network (CNN), Long-Short Term Memory (LSTM) and BIdirectional Long-Short Term Memory (BILSTM). The implemented FDD based frameworks are validated using an emulated Grid-Connected PV (GCPV) system. The results show that the DL-based diagnosis methods are able to detect and diagnose faults under different operating modes. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Picosecond optical-to-x-ray (Cd,Mg)Te radiation detectors

Picosecond optical-to-x-ray (Cd,Mg)Te radiation detectors

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Cheng, J. Komissarov, I. Chen, G. Chakraborty, D. Kutcher, S. Chen, H. Trivedi, S. Sobolewski, Roman Materials Science Graduate Program University of Rochester RochesterNY14627 United States Laboratory for Laser Energetics University of Rochester RochesterNY14623 United States Department of Electrical and Computer Engineering University of Rochester RochesterNY14627 United States Brimrose Technology Corp SparksMD21152 United States

We developed a dual optical/x-ray ultrafast photodetector based on in-house grown Cdo * Mg0.03Te single crystals. The detector is characterized by ~200 ps full-width-at-half-maximum, readout-electronics limited photor... 详细信息

ISBN: (纸本)9781957171258

关键词： X ray detectors

来源：评论

学校读者我要写书评

暂无评论

Coordinated Feeder Reconfiguration, Capacitor Placement and Allocation of Distributed Energy Resources for Loss Reduction Under Variable Loading Conditions

Coordinated Feeder Reconfiguration, Capacitor Placement and ...

引用

IEEE Kansas Power and Energy Conference

作者： Meisam Mahdavi Augustine Awaafo Sasa Z. Djokic Konrad Schmitt Manohar Chamana Department of Electrical Engineering University of Jaén Linares Jaén Spain School of Engineering The University of Edinburgh Edinburgh Scotland UK Electrical & Computer Engineering Department Texas Tech University Lubbock TX USA Renewable Energy Program Texas Tech University Lubbock USA

Reduction of active power losses in distribution networks is an important issue, which is usually addressed through a separate, sequential, or simultaneous feeder reconfiguration (FR), volt-var regulation (e.g., capacitor placement, CP), and control of distributed energy resources (DERs). However, finding optimal solution for a coordinated FR, CP, and DER control requires significant computational efforts, which are additionally increased when variations in loading conditions are considered. Therefore, load variations are usually neglected in related analysis, although changes in power flows influence changes in network losses and, consequently, optimal controls for FR, CP and DERs. This paper presents the analysis of both benefits and disadvantages of including not only the peak demands, but also different loading conditions for a coordinated implementation of FR, CP and DER controls for the reduction of losses. The analysis is illustrated on the several distribution test networks and using representative load patterns from the existing literature. The obtained results suggest that the inclusion of load variations requires significantly longer computational times, but in some cases affects optimal solutions for FR, CP and DER controls (their numbers, locations and settings).

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：