DSpace collection: 會議論文

Heuristic Design for Humanoid Robots

title: Heuristic Design for Humanoid Robots

基於分軸變換提昇二維碼儲存技術

title: 基於分軸變換提昇二維碼儲存技術 abstract: 隨著物聯網和數位化應用的發展，二維碼作為一種重要的數據承載技術，已在行動支付、智慧物流等領域得到廣泛應用。然而，現有二維碼技術在數據容量與解碼穩定性方面仍面臨挑戰，特別是在高密度數據存儲和高損毀場景中。為了提升二維碼的儲存密度與解碼效率，本研究提出了一種基於分軸變換的創新技術，通過三維座標變換將數據嵌射至二維座標中，避免了傳統投影重疊問題，並顯著增強了數據存儲的可可靠性。研究結果表明，所提出的技術能顯著提高二維碼的儲存容量。此外，本研究的技術架構對未來高效、穩定的二維碼應用場景具有重要的理論價值和實際意義

AIの超進化に伴う日本語人材業界のトレンドを洞察するキャリアデザイン

title: AIの超進化に伴う日本語人材業界のトレンドを洞察するキャリアデザイン

「死の文学」と言われた村上春樹の1980年代までの創作群に築いた死生観―『ダンス・ダンス・ダンス』とその前の短篇集を中心に―

title: 「死の文学」と言われた村上春樹の1980年代までの創作群に築いた死生観―『ダンス・ダンス・ダンス』とその前の短篇集を中心に―

AI時代下のクリエイティブな日本文学授業への挑戦─AIと協働して村上春樹風動画制作の完成を目指して─

title: AI時代下のクリエイティブな日本文学授業への挑戦─AIと協働して村上春樹風動画制作の完成を目指して─

AI時代下の「不易流行」に相応しいクリエイティブな日本語授業を目指して

title: AI時代下の「不易流行」に相応しいクリエイティブな日本語授業を目指して

ChatGPT反證之人本精神需求下的在地永續與國際共融(共榮)：結合日語敘事力、AI、DX三把劍

title: ChatGPT反證之人本精神需求下的在地永續與國際共融(共榮)：結合日語敘事力、AI、DX三把劍

An Application of Deep Learning in the Zhuoshui River Basin for Multi-Station PM10 Forecast

title: An Application of Deep Learning in the Zhuoshui River Basin for Multi-Station PM10 Forecast

Image Regression Classification of Air Quality by Convolutional Neural Network

title: Image Regression Classification of Air Quality by Convolutional Neural Network

A study on spatiotemporal groundwater level forecasting by a hybridization of machine learning and physically-based models

title: A study on spatiotemporal groundwater level forecasting by a hybridization of machine learning and physically-based models

AI-Driven Hydro-Insights: Proactive Water Resource Management for Sustainable Agriculture in the Face of Climate Change

title: AI-Driven Hydro-Insights: Proactive Water Resource Management for Sustainable Agriculture in the Face of Climate Change

A Vision of Agriculture 4.0: Constructing Smart Agriculture through Artificial Intelligent

title: A Vision of Agriculture 4.0: Constructing Smart Agriculture through Artificial Intelligent

Feature Analysis and Anomaly Detection of Personal Protective Equipment in PCB Production Lines

title: Feature Analysis and Anomaly Detection of Personal Protective Equipment in PCB Production Lines

Siamese CNN-based Few-shot Learning for PCB Defect Detection

title: Siamese CNN-based Few-shot Learning for PCB Defect Detection abstract: Defect detection in mass production lines is often challenged by small and imbalanced datasets, making few-shot learning approaches particularly suitable. Traditional deep learning methods typically rely on large-scale datasets for training, which limit their applicability in real-world manufacturing environments. To address this limitation, this study proposes a few-shot learning model capable of identifying product defects using a limited amount of data, thereby enhancing generalization across multiple defect classes. Unlike conventional deep learning models that require extensive data, the proposed approach effectively performs defect detection with minimal samples. Specifically, we introduce a Siamese Convolutional Neural Network-based Few-Shot Learning (SCNN-FSL) framework. The Siamese network is constructed using CNN architecture and trained with a triplet loss function to optimize feature embedding. Furthermore, SCNN-FSL is integrated into an automated optical inspection (AOI) defect detection system, incorporating image preprocessing, data sampling, and object classification techniques tailored for detecting defects in electronic components on PCB production lines. Experimental results demonstrate that the proposed few-shot learning model outperforms traditional deep learning approaches, achieving higher accuracy and lower miss rates, thereby validating its effectiveness in practical industrial applications.

圓桌論壇「AI時代のFOMO（フォーモ)とJOMO(ジョーモ)の底力試し」

title: 圓桌論壇「AI時代のFOMO（フォーモ)とJOMO(ジョーモ)の底力試し」

圓桌論壇「2024 年度台湾日本語文学会国際学術シンポジウム―台湾における日本語文研究の持続可能性―」

title: 圓桌論壇「2024 年度台湾日本語文学会国際学術シンポジウム―台湾における日本語文研究の持続可能性―」

「パートナーシップの観点から見た『ノルウェイの森の』のキズキと「僕」との関係変容―「死は生の対極としてではなく、その⼀部として存在している」の言葉に注目して―」

title: 「パートナーシップの観点から見た『ノルウェイの森の』のキズキと「僕」との関係変容―「死は生の対極としてではなく、その⼀部として存在している」の言葉に注目して―」

「死の文学」と言われた村上春樹文学と「グズグズした生」を肯定した村上春樹文学との距離―処女作『風の歌を聴け』から1980年代までの創作群から見て―

title: 「死の文学」と言われた村上春樹文学と「グズグズした生」を肯定した村上春樹文学との距離―処女作『風の歌を聴け』から1980年代までの創作群から見て―

「人文・社会科学の学生が持つ底力から問われる教師のスタンス ―「AIと外国語学習」、「日文翻訳」、「日文習作(二)」で実践した結果に鑑みてー」

title: 「人文・社会科学の学生が持つ底力から問われる教師のスタンス ―「AIと外国語学習」、「日文翻訳」、「日文習作(二)」で実践した結果に鑑みてー」

基於ShuffleNet的物聯網服裝圖像分類和屬性預測遷移學習方法

title: 基於ShuffleNet的物聯網服裝圖像分類和屬性預測遷移學習方法

Artificial Intelligence and Machine learning technique for student course recommendation system for higher education

title: Artificial Intelligence and Machine learning technique for student course recommendation system for higher education

Artificial intelligence and big data analytics for cancer classification and detection

title: Artificial intelligence and big data analytics for cancer classification and detection

Generative Extension Positive Pairs and Improving Sample Selection Based on Contrastive Learning for Unsupervised Person Re-identification

title: Generative Extension Positive Pairs and Improving Sample Selection Based on Contrastive Learning for Unsupervised Person Re-identification abstract: In this paper, we present Generative Extension Positive Pairs (GEPP), a novel approach to enhance unsupervised person re-identification (re-id) through contrastive learning. Data generation and pair selection methods significantly impact model performance in contrastive learning. To improve positive pair generation, we incorporate a Generative Adversarial Network (GAN) to create novel views as augmentation samples. We also introduce a sample selection scheme in the contrastive learning process to effectively choose GAN-augmented positive samples. Leveraging our sample selection results, we construct the GEPP framework and propose a unique loss function for contrastive learning. Experimental results showcase that our generative extension of positive pairs and sample selection method offer a versatile, automated, and diverse approach, achieving higher mean average precision (mAP) in re-id tasks than conventional data augmentation techniques. Additionally, our framework outperforms existing state-of-the-art methods on the Market-1501 and MSMT17 datasets.

Effect of Laser Welding Heat-Input on Re-passivation Characteristics during Pitting Corrosion Testing on 316L Orthopedic Cerclage-Wire

title: Effect of Laser Welding Heat-Input on Re-passivation Characteristics during Pitting Corrosion Testing on 316L Orthopedic Cerclage-Wire

Person Re-identification with AGW baseline using Polynomial Expansion of Cross Entropy Loss

title: Person Re-identification with AGW baseline using Polynomial Expansion of Cross Entropy Loss

CE-SQL: A Single-Table Chinese Text-to-SQL generation with BERT-Based Slot Filling Method

title: CE-SQL: A Single-Table Chinese Text-to-SQL generation with BERT-Based Slot Filling Method

BUAS: Joint Bottom-Up Article Selection for Quick Article Similarity Identification Based on NLP

title: BUAS: Joint Bottom-Up Article Selection for Quick Article Similarity Identification Based on NLP

An Energy Recharging Scheme for Perpetual Lifetime and Maximal Monitoring Quality in WRSNs

title: An Energy Recharging Scheme for Perpetual Lifetime and Maximal Monitoring Quality in WRSNs

Irregularity Detection of Daily Behavior Pattern Based on Regularity Feature Extraction for Home Elderly

title: Irregularity Detection of Daily Behavior Pattern Based on Regularity Feature Extraction for Home Elderly

Mobile Charger Recharge Scheduling Algorithm based on Data Quality in Wireless Sensor Networks

title: Mobile Charger Recharge Scheduling Algorithm based on Data Quality in Wireless Sensor Networks

On-Demand Recharge Scheduling Algorithm in Wireless Sensor Networks

title: On-Demand Recharge Scheduling Algorithm in Wireless Sensor Networks

Mobile Charger Scheduling Algorithm for Energy Recharging in Wireless Sensor Networks

title: Mobile Charger Scheduling Algorithm for Energy Recharging in Wireless Sensor Networks

Behavior Recognition Algorithm Using Unsupervised Learning for Home Elderly

title: Behavior Recognition Algorithm Using Unsupervised Learning for Home Elderly

FB-KEA: A Feature-Based Keyword Extraction Algorithm for Improving Hit Performance

title: FB-KEA: A Feature-Based Keyword Extraction Algorithm for Improving Hit Performance

An Energy Recharging Mechanism for Maximizing Surveillance Quality Using Mobile Charger in WSNs

title: An Energy Recharging Mechanism for Maximizing Surveillance Quality Using Mobile Charger in WSNs

An Energy Balanced Data Collection Mechanism for Maximizing Throughput using Uncontrolled Mobile Sink in WSNs

title: An Energy Balanced Data Collection Mechanism for Maximizing Throughput using Uncontrolled Mobile Sink in WSNs

Irregularity Detection of Daily Behavior Patterns Based on Unsupervised Learning

title: Irregularity Detection of Daily Behavior Patterns Based on Unsupervised Learning

Virtual Grid-Based Data Collection Using Mobile Sink in Wireless Sensor Networks

title: Virtual Grid-Based Data Collection Using Mobile Sink in Wireless Sensor Networks