检索结果-内蒙古大学图书馆

10th International Conference on Digital Arts, Media and Technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2025

作者： Mekruksavanich, Sakorn Hnoohom, Narit Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798331543273

With the rise of wearable sensors and smart devices, human activity recognition (HAR) has become a vital research area in ubiquitous computing. Although many studies report high accuracy using k-fold cross-validation, these results often do not reflect actual generalization interpretation due to subject-dependent data leakage, where models test on activities from the subjects they were trained. This study compares traditional k-fold cross-validation with leave-one-subject-out (LOSO) validation using the WISDM dataset, highlighting the importance of proper validation techniques in HAR systems. We implemented and evaluated five advanced deep learning models - convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU) - on windowed raw sensor data. Our experiments showed significant differences between validation methods. The BiGRU model achieved 97.91% accuracy with k-fold cross-validation and 98.02% with LOSO validation, while the CNN model achieved only 92.55% and 93.44%, respectively. These results underscore the impact of both model architecture and validation approach on performance. Our findings stress the need for subject-independent validation strategies like LOSO to develop truly generalizable HAR systems. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using EEG Signals in Human Brain Waves and Deep Learning Approaches 10

Emotion Recognition Using EEG Signals in Human Brain Waves a...

引用

作者： Mekruksavanich, Sakorn Hnoohom, Narit Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798331543273

Emotion recognition using EEG signals has gained growing attention in recent years due to its promising applications in human-computer interaction, affective computing, and mental health assessment. This study investigates the performance of various deep learning architectures in classifying emotional states from EEG recordings. We utilize the Emotion EEG dataset as a benchmark and evaluate five prominent deep learning models. The classification task targets three emotion categories: neu-tral, positive, and negative. Experimental results reveal notable differences in model performance. Among the tested models, BiGRU achieves the highest classification accuracy of 97.70% (±0.69%), followed closely by BiLSTM with 97.37% (±0.17%). These bidirectional architectures significantly outperform the CNN model, which attains an accuracy of only 61.59% (±1.22%). The LSTM and GRU models yield intermediate results, nearing 92% accuracy. The findings highlight the effectiveness of bidirectional recurrent neural networks in modeling the temporal characteristics of EEG signals for emotion detection. This research contributes to advancing EEG-based emotion recognition by identifying the most suitable deep learning strategies, thus supporting the development of more intelligent and emotion-aware computing systems. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Spacecraft Using Dual Transformers and Efficient Bayesian Hyperparameter Optimization

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 629-644页

作者： Raja, N. Kannaiya Ramesh, Janjhyam Venkata Naga El-Ebiary, Yousef A. Baker Muniyandy, Elangovan Reddy, N. Konda Kumar, Vanipenta Ravi Devarasetty, Prasad School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal466114 India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Faculty of Informatics and Computing UniSZA University Malaysia Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Engineering Mathematics K L University Greenfields Guntur Dist Andhra Pradesh Vaddeswaram522302 India Department of Mathematics Annamacharya University New Boyanapalli Rajampet India Department of Computer Science and Engineering DVR & Dr HS MIC College of Technology Andhra Pradesh Kanchikacherla India

Spacecraft pose estimation is an essential contribution to facilitating central space mission activities like autonomous navigation, rendezvous, docking, and on-orbit servicing. Nonetheless, methods like Convolutional Neural Networks (CNNs), Simultaneous Localization and Mapping (SLAM), and Particle Filtering suffer significant drawbacks when implemented in space. Such techniques tend to have high computational complexity, low domain generalization capacity for varied or unknown conditions (domain generalization problem), and accuracy loss with noise from the space environment causes such as fluctuating lighting, sensor limitations, and background interference. In order to overcome these challenges, this study suggests a new solution through the combination of a Dual-Channel Transformer Network with Bayesian Optimization methods. The innovation is at the center with the utilization of EfficientNet, augmented with squeeze-and-excitation attention modules, to extract feature-rich representations without sacrificing computational efficiency. The dual-channel architecture dissects satellite pose estimation into two dedicated streams—translational data prediction and orientation estimation via quaternion-based activation functions for rotational precision. Activation maps are transformed into transformer-compatible sequences via 1×1 convolutions, allowing successful learning in the transformer's encoder-decoder system. To maximize model performance, Bayesian Optimization with Gaussian Process Regression and the Upper Confidence Bound (UCB) acquisition function makes the optimal hyperparameter selection with fewer queries, conserving time and resources. This entire framework, used here in Python and verified with the SLAB Satellite Pose Estimation Challenge dataset, had an outstanding Mean IOU of 0.9610, reflecting higher accuracy compared to standard models. In total, this research sets a new standard for spacecraft pose estimation, by marrying the versatility of deep le

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Provable algorithms for multi-reference alignment over SO(2)

arXiv

引用

arXiv 2025年

作者： Drozatz, Gil Bendory, Tamir Sharon, Nir School of Electrical and Computer Engineering Tel Aviv University Israel Department of Applied Mathematics Tel Aviv University Israel

The multi-reference alignment (MRA) problem involves reconstructing a signal from multiple noisy observations, each transformed by a random group element. In this paper, we focus on the group SO(2) of in-plane rotations and propose two computationally efficient algorithms with theoretical guarantees for accurate signal recovery under a non-uniform distribution over the group. The first algorithm exploits the spectral properties of the second moment of the data, while the second utilizes the frequency matching principle. Both algorithms achieve the optimal estimation rate in high-noise regimes, marking a significant advancement in the development of computationally efficient and statistically optimal methods for estimation problems over groups. © 2025, CC BY-NC-ND.

关键词： Method of moments

来源：评论

学校读者我要写书评

暂无评论

Child Tracking and Prediction of Violence on Children In Social Media Using Natural Language Processing and Machine Learning 1

引用

22nd International Conference on Artificial Intelligence and Soft Computing, ICAISC 2023

作者： Nallakaruppan, M.K. Srivastava, Gautam Gadekallu, Thippa Reddy Reddy, Praveen Kumar Krishnan, Sivarama Polap, Dawid School of Information Technology and Engineering Vellore Institute of Technology Vellore India Department of Mathematics and Computer Science Brandon University Brandon Canada School of Information Technology and Engineering Vellore Institute of Technology Department of Electrical and Computer Engineering Lebanese American University Lebanon Zhongda Group Zhejiang Jiaxing314312 China Faculty of Applied Mathematics Silesian University of Technology Kaszubska 23 Gliwice44-100 Poland

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

Crimes against children are a direct threat to the world of tomorrow. The future of the world is in the hands of children who are the real wealth of mankind. The challenge for society is to address and handle challenges against children such as sexual abuse, trafficking, child labour, and harassment. Even though measures are taken by several governments globally, violence against children is an evident day-to-day process. This becomes the most challenging issue in the post-Internet era, where organized crime against children takes place around the world through a targeted group of people through virtual private networks and the dark web. What comes next is the emergence of social media, which provides an opportunity for these criminals to harm children globally through powerful social networks [15]. The existing methods focus on classifiers that do not work across multiple keywords [6] to look for sentiment analysis regarding a single classifier. There are only a few works that address the issue and these methods do not employ the multi-classification model [2]. In this paper, we propose a model which includes the Twitter API, the APIFY web scraper framework, as well as the VADER semantic analyzer in Python which possesses Decision tree analysis of sentiment prediction. The proposed work provides 99.6904% accuracy and predicts the classification of sentiment analysis. Our work has novelty in attribute selection, child trade, and violence analysis in social media and prediction of classification accuracy using the Decision Tree algorithm. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuclei Instance Segmentation in Histology Images

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuc...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wu, Xuening Shen, Yiqing Zhao, Qing Kang, Yanlan Hu, Ruiqi Zhang, Wenqiang Fudan University Shanghai Engineering Research Center of Ai & Robotics Academy for Engineering & Technology Shanghai China Johns Hopkins University Department of Computer Science BaltimoreMD United States Hong Kong Polytechnic University Department of Applied Mathematics Hong Kong Fudan University Engineering Research Center of Ai & Robotics Ministry of Education Academy for Engineering & Technology School of Computer Science Shanghai China

ISBN: (纸本)9798350386226

Accurate nuclei segmentation is fundamental in histology image analysis, playing an essential role in cancer grading and diagnosis. However, this task remains challenging due to variations in staining protocols, heterogeneity among nuclei types, and the densely clustered nature of nuclei. While SAM exhibits zero-shot generalization capabilities in natural image segmentation, its performance degrades when applied to nuclei segmentation in histology images. Existing adaptations of SAM for medical imaging primarily focus on organ or lesion segmentation, which differs substantially from nuclei segmentation due to the unique characteristics of nuclei - specifically, their sparse distribution combined with dense clustering. To address these challenges, we propose Edge-SAN (Segment Any Nuclei with Edge Prompting), an interactive segmentation foundation model specifically designed for nuclei segmentation. Edge-SAN introduces a novel edge prompting method that enhances the delineation of nuclei boundaries, particularly among densely clustered nuclei, by leveraging edge information to improve segmentation accuracy. We evaluate Edge-SAN on 12 diverse datasets in both few-shot and zero-shot scenarios, demonstrating its effectiveness as a foundation model for nuclei segmentation, achieving 66.81% AJI and 73.13% DSC - improvements of 16.33% and 15.48% over SAM-Med2D, respectively. The code is available at https://***/deep-geo/Edge-SAN. © 2024 IEEE.

关键词： Deep Learning Digital Pathology Foundation Model Nuclei Segmentation Segment Anything Model

来源：评论

学校读者我要写书评

暂无评论

Analysis of Feature Parameters and Their Time-Transition for Shockable Arrhythmia and Prediction of the Effect of Electrical Defibrillation 3

Analysis of Feature Parameters and Their Time-Transition for...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Noguchi, Shunta Yoshikawa, Yuta Okai, Takayuki Oya, Hidetoshi Rahman, Md. Masudur Yoshida, Minoru Graduate School of Integrative Science and Engineering Tokyo City University Tokyo Japan Tokyo City University Department of Computer Science Tokyo Japan Noakhali Science and Technology University Department of Information and Communication Engineering Bangladesh Kanagawa University Department of Applied Systems and Mathematics Kanagawa Japan

ISBN: (纸本)9798331540319

In this paper, we propose a prediction system of the effect of electrical defibrillation. In order to develop the proposed system, we firstly analyze from pre-shock (immediately before defibrillation) ECGs (ElectroCardioGrams) by using Gabor Wavelet Transform, Poincaré plot analysis, Spectral entropy, and feature parameters are extracted by those extracted analysis results, we focus on time-transition feature parameter. Next, effective feature parameters are selected based on χ2 -test. Finally, 'Effective' and 'Ineffective' for electrical defibrillation are classified by using SVM (Support Vector Machine) with three kernels (Linear, Gaussian, and Polynomial) and regularization. In this way, we shows the effectiveness of the proposed feature extraction methods and prediction system. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Minimizing Maximum Tardiness in a Distributed Flow Shop Manufacturing Problem under No-Waiting and Sequence Dependent Setup Time Constraints 14

Minimizing Maximum Tardiness in a Distributed Flow Shop Manu...

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： Sayah, Achraf Aqil, Said Lahby, Mohamed Hassan Ii University of Casablanca Higher Normal School Laboratory of Applied Mathematics and Computer Sciences Morocco Hassan Ii University of Casablanca National Higher School of Arts and Crafts Laboratory Artificial Intelligence and Complex Systems Engineering Morocco

ISBN: (纸本)9798350308211

The distributed no-wait flow-shop manufacturing problem with sequence dependent setup time (DNWFSMP-SDST) is a challenging optimization problem that arises in various industries, including manufacturing and logistics. This problem involves scheduling a set of jobs on multiple machines in a distributed environment, where each job has a specific processing time and requires setup time between different machine transitions. The objective is to minimize the maximum tardiness of all jobs, which represents the maximum delay in completing any job beyond its desired due date. This study addresses the DNWFSMP-SDST optimization problem by employing two algorithms: Nawaz-Enscore-Ham (NEH) and Greedy Randomized Adaptive Search Procedure (GRASP). The NEH is a constructive heuristic that constructs an initial solution by iteratively inserting jobs into a partially ordered sequence. In contrast, GRASP combines a greedy randomized construction phase with a local search procedure to iteratively enhance the initial solution. The simulation study compares NEH and GRASP algorithms for solving DNWFSMP-SDST using bench-marking instance. The results show the pros and cons of each algorithm, helping practitioners make better decisions. Where the NEH algorithm outperform for GRASP technique solving the kind of problem. Overall, this research has enabled us to improve our methods for solving scheduling problems in distributed environments. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Improvement artificial bee colony meta-heuristic for solving manufacturing flow-shop scheduling problem under blocking constraint 14

Improvement artificial bee colony meta-heuristic for solving...

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： Nejjarou, Omar Aqil, Said Lahby, Mohamed Hassan Ii University of Casablanca Laboratory of Applied Mathematics and Computer Sciences Higher Normal School Morocco Hassan Ii University of Casablanca Laboratory Artificial Intelligence and Complex Systems Engineering National Higher School of Arts and Crafts Morocco

ISBN: (纸本)9798350308211

Manufacturing flow-shop scheduling problem is a highly attractive optimization challenge in operations research. When there is limited space in a workshop or capacity queue of machine is null, a new problem called manufacturing blocking flow-shop scheduling problem (MBFSP) is investigated. This optimization problem is solved by considering that the job must be blocked during scheduling when the next machine is not available. The address this challenge effectively, we present two novel algorithms: the Iterative Local Search (ILS) with neighborhood solutions, and the Artificial Bee Colony (ABC) algorithm inspired by nature's meta-heuristics. These cutting-edge approaches are designed to address the problem from distinct and innovative perspectives, with a primary focus on optimizing the overall quality of the solution. By embracing these advanced techniques, we can effectively expand the scope of potential outcomes, opening up new avenues for achieving superior results. The target is to decrease the total weighted flow time (TWFT) , which represents the duration of completing all tasks. We provide a mathematical statement of the MBFSP optimization case and propose two solution meta-heuristics. In order to comprehensively assess the effectiveness of the proposed algorithms, we conducted a rigorous comparative study. This study involved an extensive set of instances, carefully curated to encompass a wide range of scenarios with varying numbers of jobs and machines. By testing the algorithms across diverse instances, we aimed to obtain a holistic understanding of their performance. Simulation results show that the ABC algorithm overcame the ILS algorithm, with a hit ratio 88% over the set of test instances and a minimum mean relative deviation in percent of 0.0154%. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Word2Minecraft: Generating 3D Game Levels through Large Language Models

arXiv

引用

arXiv 2025年

作者： Huang, Shuo Nasir, Muhammad Umair James, Steven Togelius, Julian Department of Computer Science and Engineering Tandon School of Engineering New York University New York10012 United States School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa

We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements—such as protagonist goals, antagonist challenges, and environmental settings—into game levels with both spatial and gameplay constraints. We introduce a flexible framework that allows for the customization of story complexity, enabling dynamic level generation. The system employs a scaling algorithm to maintain spatial consistency while adapting key game elements. We evaluate Word2Minecraft using both metric-based and human-based methods. Our results show that GPT-4Turbo outperforms GPT-4o-Mini in most areas, including story coherence and objective enjoyment, while the latter excels in aesthetic appeal. We also demonstrate the system’s ability to generate levels with high map enjoyment, offering a promising step forward in the intersection of story generation and game design. We open-source the code at https://***/JMZkk/Word2Minecraft/tree/word2mc_v0 Copyright © 2025, The Authors. All rights reserved.

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：