检索结果-内蒙古大学图书馆

IEEE International Conference on Robotic computing (IRC)

作者： Joshua Ho Chien-Min Wang Chung-Ta King Chi-Wei Feng Shih-Yun Sunkuan Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan

ISBN: (数字)9798331521554

ISBN: (纸本)9798331521561

The ability of robots to imitate human learning strategies-rapidly adapting to new tasks without large datasets-has garnered significant attention in meta-learning. Meta-reinforcement learning seeks to enhance robotic agent flexibility across diverse tasks and contexts, offering promise where single-task learning often fails. Despite advancements like multi-task diffusion models and task-weighted optimization mechanisms, effectively training tasks with varying complexities simultaneously remains a major challenge. This paper introduces a novel meta-reinforcement learning method that addresses this issue by clustering the training tasks of robotic arms based on semantic and trajectory similarities, while leveraging adaptive learning rates and task-specific weights proposed by the multitask optimization techniques. Our approach, TEAM, emphasizes performance-driven semantic clustering, optimizing based on robotic task similarity, complexity, and convergence objectives. We also integrate fast adaptive and multi-task optimization of the diffusion model to enhance computational efficiency and adaptability. More specifically, we introduce a cluster-specific optimization technique, using specialized parameters for each group to allow more refined task handling. The experimental validation demonstrates the effectiveness of this scalable method in improving performance, adaptability, and efficiency in real-world, heterogeneous robotic tasks, further advancing robotic computing in meta-reinforcement learning.

关键词： Training Metalearning program processors Semantics Multitasking Diffusion models Complexity theory Trajectory Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

SR-BigGAN: lightweight image super-resolution with priors

引用

Machine Vision and Applications 2025年第4期36卷 1-18页

作者： Kumar, Deepak Srinivas Rao, Harshitha Kumar, Chetan Shao, Ming Department of Computer Science Worcester Polytechnic Institute Worcester USA Program of Data Science University of Massachusetts Dartmouth USA Old Dominion University - Thomas Jefferson National Accelerator Facility Joint Institute on Advanced Computing for Environmental Studies Portsmouth USA Miner School of Computer and Information Sciences University of Massachusetts Lowell Lowell USA

Recent progress in the field of high-fidelity image synthesis using GANs has shown appealing outcomes, which motivates a series of successful image super-resolution (SR) works. However, most GAN-based SR models apply plain GAN models and are cumbersome compared to CNN-based SR models. In addition, the very advantage of conditional GAN has not yet been explored under the context of SR. In this paper, we develop a lightweight SR-BigGAN with priors for single-image super-resolution (SISR). First, our new model is an extension of BigGAN tailored to deep SR pipeline, retaining both generator and discriminator architectures, but with modifications to accommodate SR tasks. Second, prior knowledge defined as class labels from the low-resolution images, is fully leveraged through the conditional generative model to refine the SR process. Third, the lightweight nature of the model is achieved through knowledge distillation, focusing on reduced computational complexity and memory usage, making it the first practice of this kind in GAN-based SISR modeling. Extensive experiments on DIV2K, Pascal, mini-ImageNet, and SR benchmarks including Set5 and Set14 in an attempt to compare the Structural Similarity (SSIM), Peak Signal-to-Noise Ratio (PSNR) with the state-of-the-art models have shown appealing results. Our model achieves an average PSNR of 34.99 and SSIM of 0.791 across these datasets, demonstrating quantitative improvements over existing methods. The generated high-resolution images offer both perceptual enhancement and improved classification results. Additionally, explicit comparisons with GAN-based SR techniques such as ESRGAN and SRGAN highlight the superiority of our approach in both fidelity and efficiency. In particular, we achieve an average of $$\hbox{PSNR}=34.99$$ and $$\hbox{SSIM}=0.791$$ on several testing datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HAAQI-Net: A Non-Intrusive Neural Music Audio Quality Assessment Model for Hearing Aids

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1877-1892页

作者： Dyah A. M. G. Wisnu Stefano Rini Ryandhimas E. Zezario Hsin-Min Wang Yu Tsao Taiwan International Graduate Program—Social Network and Human-Centered Computing Institute of Information Science Academia Sinica Taipei Taiwan College of Informatics National Chengchi University Taipei Taiwan Institute of Communications Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Electrical Engineering Chung Yuan Christian University Taiwan

This paper introduces HAAQI-Net, a non-intrusive music audio quality assessment model for hearing aid users. Unlike traditional methods such as Hearing Aid Audio Quality Index (HAAQI), which requires intrusive reference signal comparisons, HAAQI-Net offers a more accessible and computationally efficient alternative. Leveraging a bidirectional long short-term memory architecture with attention mechanisms and features extracted from a pre-trained BEATs model, it can predict HAAQI scores directly from music audio clips and hearing loss patterns. The experimental results demonstrate that, compared to the traditional HAAQI as the reference, HAAQI-Net achieves a linear correlation coefficient (LCC) of 0.9368, a Spearman's rank correlation coefficient (SRCC) of 0.9486, and a mean squared error (MSE) of 0.0064, while significantly reducing the inference time from 62.52 seconds to 2.54 seconds. Furthermore, a knowledge distillation strategy was applied, reducing the parameters by 75.85% and inference time by 96.46%, while maintaining strong performance (LCC: 0.9071, SRCC: 0.9307, MSE: 0.0091). To expand its capabilities, HAAQI-Net was adapted to predict subjective human scores, mean opinion score (MOS), by fine-tuning. This adaptation significantly improved the prediction accuracy. Furthermore, the robustness of HAAQI-Net was evaluated under varying sound pressure level (SPL) conditions, revealing optimal performance at a reference SPL of 65 dB, with the accuracy gradually decreasing as SPL deviated from this point. The advancements in subjective score prediction, SPL robustness, and computational efficiency position HAAQI-Net as a reliable solution for music audio quality assessment, significantly contributing to the development of efficient and accurate models in audio signal processing and hearing aid technology.

关键词： Hearing aids Quality assessment Training Feature extraction Speech processing Auditory system Computational modeling Adaptation models Transformers Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

SODIUM-ION BATTERY CYCLE LIFE PREDICTION USING MACHINE LEARNING

SODIUM-ION BATTERY CYCLE LIFE PREDICTION USING MACHINE LEARN...

引用

International Conference on Green Energy, computing and Intelligent Technology 2024, GEn-CITy 2024

作者： Liu, Linfeng Juwono, Filbert H. Wong, W.K. Purwanto, Erick Jin, Tingyan Zhen, Yuyang Sustainable Energy Technology Program Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Electronic Engineering Xi'an Jiaotong-Liverpool University Suzhou China Department of Electrical and Computer Engineering Curtin University Malaysia Miri Malaysia Department of Computing Xi'an Jiaotong-Liverpool University Suzhou China School of Mechanical and Electrical Engineering Beijing Information Science and Technology University Beijing China School of Instrument Science and Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781837242689

In this study, we explore the classification and prediction capabilities of three models-Genetic programming (GP), Logistic Regression (LR), and the Kolmogorov-Arnold Network (KAN)-on the task of sodium-ion battery life prediction. By leveraging a dataset composed of multiple battery characteristics, we aim to determine the remaining power of sodium-ion batteries using these machine learning models. The KAN model, being a novel approach, demonstrates superior performance across various metrics, including accuracy, precision, recall, and F1 score, when compared to the other two models. This highlights the potential of KAN as a robust model for complex classification tasks in the field of battery life prediction. © The Institution of Engineering & Technology 2024.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Analysis of Shopping Mall Tourist Satisfaction in Bangkok Using Word Cloud of Online Reviews

Analysis of Shopping Mall Tourist Satisfaction in Bangkok Us...

引用

2023 International Conference on Cyber Management and Engineering, CyMaEn 2023

作者： Ladkoom, Kobthong Tarigan, Emiya Fefayosa Br Yasirandi, Rahmat Suwastika, Novian Anggis Anom, Rahmat Indra Pratama Makky, Muhammad Al Chandrakasem Rajabhat University Faculty of Science Bangkok Thailand Telkom University School of Computing Bandung Indonesia King Mongkut's Institute of Technology Ladkrabang Faculty of Information Technology Bangkok Thailand Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Kuala Lumpur Malaysia Doctoral Program of Tourism Trisakti School of Tourism Jakarta Indonesia

ISBN: (纸本)9781665493291

The tourism industry is very important to prioritize, especially for developing countries like Thailand. The increase in tourist visits to Bangkok also triggers the potential for a rise in Bangkok tourism during the pandemic. In this study, shopping malls are one of the attractive attractions for a capital city like Bangkok. Tourist expectations of attraction must be realized so that satisfaction can be realized and created revisit. In the digitalization era, the internet's use to find and disseminate information has become commonplace. *** is one of the leading review sites, which already has many reviewers, and is the case study in this research. Using Word Cloud as an analysis technique and clustering of data reviews, several important factors influence tourist satisfaction. Based on the 1186 clustered reviewers, several factors were produced, such as Place Quality, Location Access, Support Facilities, Price, and Seller Attitude. These factors can influence the decision to visit shopping malls in Bangkok because they represent tourist satisfaction. © 2023 IEEE.

关键词： Shopping centers

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Strawberry Disease Detection With Wall-Mounted Monitoring Cameras

引用

IEEE Internet of Things Journal 2024年第1期11卷 1439-1451页

作者： Lin, Yi-Bing Liu, Chun-You Chen, Wen-Liang Chang, Chia-Hui Ng, Fung-Ling Yang, Krista Hsung, Jerry Department of Computer Science National Yang Ming Chiao Tung University Hsinchu30010 Taiwan China Medical University College of Humanities and Sciences Taichung404 Taiwan National Cheng Kung University MiinWu School of Computing Tainan701 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei115 Taiwan National Yang Ming Chiao Tung University College of Biological Science and Technology Hsinchu30010 Taiwan National Yang Ming Chiao Tung University Industrial Development Graduate Program College of Biological Science and Technology Hsinchu30010 Taiwan Proto Solution System Company Ltd. Hsinchu302052 Taiwan

This article proposes StrawberryTalk, an Internet of Things (IoT) platform for image-based strawberry disease detection. StrawberryTalk reuses the wall-mounted monitoring cameras without extra hardware cost. The contributions of StrawberryTalk are the utilization of IoT for automatic photo shoot and the wind detection mechanism to eliminate the obscure photos due to the wind effects. Also, the data preprocessing and the infection detection models are manipulated as IoT devices to simplify the implementation of the multicascade artificial intelligence (AI) models. We derive the relationship between the camera zoom factor and the distance between the camera and the strawberries for optimal disease detection. Accuracy of detection may be affected by obscure photos. In terms of eliminating obscure photos due to wind effect, we analytically derive the relationship between the wind alert delay and the number of obscure photos that must be retaken. For the greenhouses in the Bao Mountain, we only need to retake one photo. Based on the experiments, the mean average precision (mAP) of StrawberryTalk (to detect exact spots in a leaf) can be up to 92.37%, which is better than the previous approaches. To detect if a pot has infected leaves, the accuracy of StrawberryTalk can be up to 97.92% at the zoom factor 30×. In commercial operation, it is important to detect all infected strawberry pots. StrawberryTalk is able to detect all infected pots (i.e., recall is 100%) with a camera of zoom factor of 12× . The accuracy is 96.88%. © 2014 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Defect Detection and Classification in Printed Circuit Boards using Convolutional Neural Networks

Defect Detection and Classification in Printed Circuit Board...

引用

International Conference on Edge computing and Applications (ICECAA)

作者： Yolanda D. Austria Arnel C. Fajardo Graduate School Program Technological Institute of the Philippines Quezon City Philippines College of Computing Science Information and Communication Technology Isabela State University Cauay an City Isabela Philippines

PCB defect detection and classification is vital in electronics manufacturing to ensure high-quality and safe products. Manual inspection is time-consuming, costly, and prone to errors. To address this, automated methods using deep learning models have gained preference. These models learn from diverse datasets of defect images or videos. In this study, a deep learning model was developed and trained using a dataset containing various defect classes, including breakout, copper, crack, cut, excessive conductor, missing conductor, mouse bite, pinhole, spur, and scratch. The model showed promising results in detecting defects across all classes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Defect Recognition on Single Layer Bare Printed Circuit Boards for Quality Control and Visual Inspection: A Low-Sample-Size Deep Transfer Learning Approach

Defect Recognition on Single Layer Bare Printed Circuit Boar...

引用

International Conference of Signal Processing and Intelligent Systems (ICSPIS)

Defect detection is a critical component in ensuring the highest quality of printed circuit board manufacture. The work investigates the application of transfer learning to identify YOLOv8 design flaws. The YOLOv8 model performs exceptionally well, with mean Average Precision (mAP) of 98.3%, Precision of 98.6%, and Recall of 96.0%. Numerous datasets provide high detection rates across a range of fault types following thorough testing and inference. This extensive evaluation demonstrates the robustness of the model by reliably identifying Fissure, Mousebite, EC-Short, MC-Spur, Breakout, Pinhole, and Copper defects. The study emphasizes how the YOLOv8 design can identify flaws, providing a dependable and effective way to guarantee the dependability and caliber of printed circuit boards throughout the production process. The foundation for utilizing YOLOv8 in industrial quality control is established by this study, which holds significant potential for improving defect detection and quality control in the manufacturing industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Syncretic Effect of Dual-Source Data on Affective computing in Online Learning Contexts: A Perspective From Convolutional Neural Network With Attention Mechanism

引用

Journal of Educational computing Research 2023年第2期61卷 466-493页

作者： Zhai, Xuesong Xu, Jiaqi Chen, Nian-Shing Shen, Jun Li, Yan Wang, Yonggu Chu, Xiaoyan Zhu, Yumeng College of Education Zhejiang University Zhejiang Hangzhou China Anhui Xinhua University Anhui Hefei China Anhui Jianzhu University Anhui Hefei China Program of Learning Sciences National Taiwan Normal University Yünlin Taiwan School of Computing and Information Technology University of Wollongong Wollongong NSW Australia College of Educational Science and Technology Zhejiang University of Technology Zhejiang Hangzhou China

Affective computing (AC) has been regarded as a relevant approach to identifying online learners’ mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners’ facial expression, to compute learners’ affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach based on the AC recognition accuracy between the two approaches (dual-source approach using Attention-AlexNet model 80.96%;single-source approach, facial expression 76.65% and head pose 64.34%). This study contributes to the theoretical construction of the dual-source data fusion approach, and the empirical validation of the effect of the Attention-AlexNet neural network approach on affective computing in online learning contexts. © The Author(s) 2022.

关键词： affective computing attention mechanism dual-source data fusion method multimodal

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Retention: A Comparative Study of Machine Learning Approach Utilizing Sociodemographic and Academic Factors

SSRN

引用

SSRN 2024年

作者： Delena, Reymark D. Dia, Nornina J. Sacayan, Redeemtor R. Sieras, Joseph C. Macatotong, Amer Hussien T. Casim, Suhaina K. Gulam, Sacaria B. Khalid, Suhaina A. Mindanao State University Philippines Department of Information Sciences College of Information and Computing Sciences Mindanao State University Main Campus Lanao Del Sur Marawi City9700 Philippines Undergraduate Program Department of Information Sciences College of Information and Computing Sciences Mindanao State University Main Campus Lanao Del Sur Marawi City9700 Philippines Department of Mathematics and Statistics College of Science and Mathematics Mindanao State University Iligan Institute of Technology Iligan City9200 Philippines Department of Computing Sciences College of Information and Computing Sciences Mindanao State University Main Campus Lanao Del Sur Marawi City9700 Philippines

Student retention at universities has been a longstanding concern among educators for many decades, mainly due to its impact on university rankings, institutional reputation, and financial stability. Seemingly, the College of information and computing sciences (CICS) of Mindanao State University in Marawi City has been facing the problem of student retention for many years. This research aims to perform predictive analysis to determine the sociodemographic and academic factors that highly influence a student’s decision to withdraw from their current program and to visualize the data using Python programming language in the Jupyter Notebook environment. The insights gained could enable decision-makers to determine areas needing improvement to mitigate attrition and assist students in attaining timely graduation. To identify the algorithm to be utilized for the prediction, ten (10) machine learning models were evaluated namely: Artificial Neural Network (ANN), Decision Tree, Extreme Gradient Boosting (XGBoost), Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Multi-Layer Perceptron (MLP), Naïve Bayes, Random Forest, and Support Vector Machine (SVM). These models were assessed using five (5) evaluation metrics: Accuracy score, F1 score, Mean Squared Error (MSE), Precision, and Recall. Findings reveal that the Extreme Gradient Boosting (XGBoost) demonstrated the highest prediction accuracy. Henceforth, the XGBoost model was identified that could accurately identify the probability of students’ withdrawal or retention from the program. © 2024, The Authors. All rights reserved.

关键词： Students

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：