13197 research outputs found
Sort by
Cryptoeconomic - Blockchains, Game Theory and Artificial Intelligence
No full textvideo/mp4Robots and autonomous vehicles increasingly rely on models of human behavior. However, models commonly used in robotics often lack in accuracy, transparency, and generalization. In this lecture, I will demonstrate how established models from cognitive science can help address these issues. I will illustrate how these models can be translated to human-robot interaction in traffic, which challenges need to be addressed in doing so, and how such modeling can contribute to development and assessment of autonomous vehicles.講演日: 2024年6月11日講演場所: 情報科学中講義室(L2), Middle lecture room (L2) in Information Sciencevide
キギョウカ シコウ アントレプレナーシップ オ マナブ
No full textvideo/mp4講演日: 2024年11月29日講演場所: ミレニアムホール講演者所属: 株式会社メルカリ取締役President講演者所属: 生駒市講演者所属: 奈良先端科学技術大学院大学vide
Overview of #SMM4H 2024 $2013 Task 2: Cross-Lingual Few-Shot Relation Extraction for Pharmacovigilance in French, German, and Japanese
No full textThis paper provides an overview of Task 2 from the Social Media Mining for Health 2024 shared task (#SMM4H 2024), which focused on Named Entity Recognition (NER, Subtask 2a) and the joint task of NER and Relation Extraction (RE, Subtask 2b) for detecting adverse drug reactions (ADRs) in German, Japanese, and French texts written by patients. Participants were challenged with a few-shot learning scenario, necessitating models that can effectively generalize from limited annotated examples. Despite the diverse strategies employed by the participants, the overall performance across submissions from three teams highlighted significant challenges. The results underscored the complexity of extracting entities and relations in multi-lingual contexts, especially from the noisy and informal nature of user-generated content. Further research is required to develop robust systems capable of accurately identifying and associating ADR-related information in low-resource and multilingual settings.conference pape
FedFusion: Adaptive Model Fusion for Addressing Feature Discrepancies in Federated Credit Card Fraud Detection
No full textThe digitization of financial transactions has led to a rise in credit card fraud, necessitating robust measures to secure digital financial systems from fraudsters. Nevertheless, traditional centralized approaches for detecting such frauds, despite their effectiveness, often do not maintain the confidentiality of financial data. Consequently, Federated Learning (FL) has emerged as a promising solution, enabling the secure and private training of models across organizations. However, the practical implementation of FL is challenged by data heterogeneity among institutions, complicating model convergence. To address this issue, we propose FedFusion, which leverages the fusion of local and global models to harness the strengths of both, ensuring convergence even with heterogeneous data with total feature discrepancy. Our approach involves three distinct datasets with completely different feature sets assigned to separate federated clients. Prior to FL training, datasets are preprocessed to select significant features across three deep learning models. The Multilayer Perceptron (MLP), identified as the best-performing model, undergoes personalized training for each dataset. These trained MLP models serve as local models, while the main MLP architecture acts as the global model. FedFusion then adaptively trains all clients, optimizing fusion proportions. Experimental results demonstrate the approach’s superiority, achieving detection rates of 99.74%, 99.70%, and 96.61% for clients 1, 2, and 3, respectively. This highlights the effectiveness of FedFusion in addressing data heterogeneity challenges, thereby paving the way for more secure and efficient fraud detection systems in digital finance.journal articl
Exposure Time Control Method for Higher Intermediate Frequency in Optical Heterodyne Imaging and Its Application to Electric-Field Imaging Based on Electro-Optic Effect
No full textjournal articl
Dynamic Object Concealment Processing Methods for Autonomous Vehicle Stress Reduction and Situational Awareness
Get PDFPassengers in autonomous vehicles need to perceive information about the position and size of external objects. This study investigates how hiding external object information can help reduce passenger stress. We propose four image processing patterns, including semi-transparent, bounding box, shadow, and fully concealed, to reduce the amount of visual information while preserving object position and size information to reduce stress and improve situational understanding. We categorized external stressors according to passengers’ stress levels and the need for an immediate understanding of the stressors using a VR-HMD simulator. This was done through subjective evaluations based on stress reduction and situation awareness questionnaires. The results from 20 subjects showed that the compatibility index was lower in the group with a higher need for immediate situation awareness compared to the group that prioritized confidentiality. This supports the idea that stressors requiring immediate awareness require both information reduction and situation awareness.conference pape
Synchronizing Approach in Designing Annotation Guidelines for Multilingual Datasets: A COVID-19 Case Study Using English and Japanese Tweets
No full textThe difference in culture between the U.S. and Japan is a popular subject for Western vs. Eastern cultural comparison for researchers. One particular challenge is to obtain and annotate multilingual datasets. In this study, we utilized COVID-19 tweets from the two countries as a case study, focusing particularly on discussions concerning masks. The annotation task was designed to gain insights into societal attitudes toward the mask policies implemented in both countries. The aim of this study is to provide a practical approach for the annotation task by thoroughly documenting how we aligned the multilingual annotation guidelines to obtain a comparable dataset. We proceeded to document the effective practices during our annotation process to synchronize our multilingual guidelines. Furthermore, we discussed difficulties caused by differences in expression style and culture, and potential strategies that helped improve our agreement scores and reduce discrepancies between the annotation results in both languages. These findings offer an alternative method for synchronizing multilingual annotation guidelines and achieving feasible agreement scores for cross-cultural annotation tasks. This study resulted in a multilingual guideline in English and Japanese to annotate topics related to public discourses about COVID-19 masks in the U.S. and Japan.conference pape
Improving Self-training with Prototypical Learning for Source-Free Domain Adaptation on Clinical Text
No full textDomain adaptation is crucial in the clinical domain since the performance of a model trained on one domain (source) degrades seriously when applied to another domain (target). However, conventional domain adaptation methods often cannot be applied due to data sharing restrictions on source data. Source-Free Domain Adaptation (SFDA) addresses this issue by only utilizing a source model and unlabeled target data to adapt to the target domain. In SFDA, self-training is the most widely applied method involving retraining models with target data using predictions from the source model as pseudo-labels. Nevertheless, this approach is prone to contain substantial numbers of errors in pseudo-labeling and might limit model performance in the target domain. In this paper, we propose a Source-Free Prototype-based Self-training (SFPS) aiming to improve the performance of self-training. SFPS generates prototypes without accessing source data and utilizes them for prototypical learning, namely prototype-based pseudo-labeling and contrastive learning. Also, we compare entropy-based, centroid-based, and class-weights-based prototype generation methods to identify the most effective formulation of the proposed method. Experimental results across various datasets demonstrate the effectiveness of the proposed method, consistently outperforming vanilla self-training. The comparison of various prototype-generation methods identifies the most reliable generation method that improves the source model persistently. Additionally, our analysis illustrates SFPS can successfully alleviate errors in pseudo-labeling.conference pape
Arukikata Travelogue Dataset with Geographic Entity Mention, Coreference, and Link Annotation
No full textGeoparsing is a fundamental technique for analyzing geo-entity information in text, which is useful for geographic applications, e.g., tourist spot recommendation. We focus on document-level geoparsing that considers geographic relatedness among geo-entity mentions and present a Japanese travelogue dataset designed for training and evaluating document-level geoparsing systems. Our dataset comprises 200 travelogue documents with rich geo-entity information: 12,171 mentions, 6,339 coreference clusters, and 2,551 geo-entities linked to geo-database entries.conference pape
Laser-carbonized Electrodes on Implantable CMOS-based Imaging Device for Simultaneous Deep-brain Optical and Electrophysiological Measurements
No full textOptical and electrophysiological methods are widely used in neuroscience to study brain activity. Each technique has its own strengths and weaknesses that complement each other to provide a more comprehensive understanding of neuronal activity. To this end, we developed an implantable CMOS image sensor device with an integrated carbon electrode for the simultaneous measurement of fluorescence and extracellular signals. The device is composed of a 450 × 1660 00B5m2, comprising 120 × 90 pixels recording at 10 frames per second. An absorption filter film was placed on top of the imaging surface to block excitation light. The device was coated with parylene-C for waterproofing and, finally, the coating film was readily turned into carbon electrodes by laser carbonization. We characterized the laser-carbonized electrodes by cyclic voltammetry, electrochemical impedance spectroscopy, and X-ray photoelectron spectroscopy to confirm the electrode carbonization. We then demonstrated the simultaneous in vivo recording of fluorescence and extracellular signals in hippocampus CA1 using the device.journal articl