检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hojun Chung Junseo Lee Minsoo Kim Dohyeong Kim Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Department of Electrical and Computer Engineering and ASRI Seoul National University Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University and Department of Electrical and Computer Engineering and ASRI Seoul National University

ISBN: (纸本)9798331314385

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Classification Through Speech Data Analysis

Emotion Classification Through Speech Data Analysis

引用

2023 Winter Simulation Conference, WSC 2023

作者： Marcos, Luzalen Mai, Kristiina Valter Abhari, Abdolreza Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering Resilience Engineering Lab 350 Victoria Street TorontoONM5B 2K3 Canada Lab Department of Computer Science 245 Church Street TorontoONM5B 1Z4 Canada

ISBN: (纸本)9798350369663

Good quality healthcare services require effective communication between the patient and the healthcare provider. This work will help improve the areas of healthcare systems automation and optimization by applying Speech Emotion Recognition (SER) in health consultations to prevent miscommunication between patients and healthcare providers. Crowd-Sourced Emotional Multimodal Actors Dataset (CREMA-D) was used to compare the performances of different machine learning models in classifying emotions. Before feeding the raw dataset to the models, exploratory data analysis was done to determine features that should be considered for future analysis. Our results showed that depending on the emotion, there are some syllables in the text that were emphasized or took time to be pronounced by the speaker. After data analysis, the dataset was fed into different models and determined that the Support Vector Machine (SVM) is a machine-learning model for SER. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-powered WiFi-connected monitoring stations for environmental pollution app-based control in urban and industrial areas 8

Self-powered WiFi-connected monitoring stations for environm...

引用

8th International Conference on Control, Instrumentation and Automation, ICCIA 2022

作者： Visconti, Paolo De Fazio, Roberto Velazquez, Ramiro Al-Naami, Bassam Ghavifekr, Amir Aminzadeh University of Salento Department of Innovation Engineering Lecce Italy Universidad Panamericana Facultad de Ingeniería Aguascalientes Mexico The Hashemite University Faculty of Engineering Department of Biomedical Engineering Zarqa Jordan University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran

ISBN: (纸本)9781665495691

This paper presents the design of a sensing device for monitoring and storing the atmospheric and noise pollution data, using technology with zero impact on the environment. The system consists of an eco-friendly sensor pitch equipped with a multi-sources harvesting system used to scavenge energy from renewable sources (wind and solar light), making it suitable to be accumulated into a storage device. The harvested energy is used to feed a sensing section, which samples the environmental parameters (i.e. PM2.5, PM10, NH3, CO2, NO2, CO) at regular intervals. The hardware and firmware development of the sensor node is discussed;this last is based on the Arduino Pro Micro microcontroller board, which acquires, processes and stores the data from sensors and manages their transmissions towards the cloud platform. Finally, the test results of the developed sensor pitch are presented, demonstrating the correct operation of all system sections. © 2022 IEEE.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability 40

On the Impact of Knowledge Distillation for Model Interpreta...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Understanding Acoustic Phenomena in Stenosed Coronary Arteries through Bond Graph Modeling of Sound Generation

Understanding Acoustic Phenomena in Stenosed Coronary Arteri...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Loreto Rojas Sandoval René Araya Ulloa Ana Karoline Almeida Da Silva Gustavo Adolfo Marcelino de Almeida Nunes Rafael Mendes Faria José Parra Sepúlveda Lindemberg Barreto Mota Da Costa Luca Rubilar Acevedo Mário Fabrício Fleury Rosa Esteban J. Pino Suélia de Siqueira Rodrigues Fleury Rosa Electrical Engineering Department Universidad de Concepción Chile Mechanical Engineering Department University of Brasilia Brasilia Brazil Postgraduate Program in Biomedical Engineering University of Brasilia Brasilia Brazil

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Coronary artery stenosis is characterized by the obstruction or narrowing of coronary arteries, impairing blood flow to the cardiac muscle. Cardiovascular diseases rank among the leading global causes of death. Understanding the mechanisms, risk factors, and impacts of coronary artery stenosis (CAD) is essential for developing effective strategies for prevention, early diagnosis, and treatment, aiming to enhance cardiovascular health and reduce adverse consequences associated with this condition. Previous studies explore the potential of acoustic devices in non-invasive CAD detection through the analysis of cardiac sounds. A theoretical model utilized a cardiac microphone and signal processing to generate sounds in partially obstructed coronary arteries. Emphasizing the model’s sensitivity to geometric and dynamic parameters, this article integrates Bond Graph (BG) models into the analog sound circuit, aiming to develop a dynamic representation of biological processes in complex systems like coronary arteries. This research seeks to construct a comprehensive mathematical model using a state-space approach to enhance understanding, diagnostics, and interventions in cardiovascular conditions. The utilization of BG demonstrated notable similarity to the pathology of the disease, providing an accurate representation of its effects. The model’s sensitivity to geometric and dynamic parameters allowed an in-depth understanding of the specific physiological characteristics of the disease, highlighting its ability to reproduce patterns observed in patients with CAD.

关键词： Solid modeling Analytical models Pathology Sensitivity Biological system modeling Prevention and mitigation Signal processing Predictive models Mathematical models Arteries

来源：评论

学校读者我要写书评

暂无评论

CONGENITAL HEART DISEASE CLASSIFICATION USING PHONOCARDIOGRAMS: A SCALABLE SCREENING TOOL FOR DIVERSE ENVIRONMENTS

arXiv

引用

arXiv 2025年

作者： Jabbar, Abdul Grooby, Ethan Crozier, Jack Gallon, Alexander Pham, Vivian Ahmad, Khawza I. Hassanuzzaman, Md Mostafa, Raqibul Khandoker, Ahsan H. Marzbanrad, Faezeh Department of Electrical and Computer System Engineering Monash University ClaytonVIC3800 Australia Department of Biomedical Engineering McGill University Quebec Canada Department of Electrical and Electronic Engineering United International University Dhaka Bangladesh School of Engineering Duke University United States Department of Biomedical Engineering Khalifa University Abu Dhabi127788 United Arab Emirates

Congenital heart disease (CHD) is a critical condition that demands early detection, particularly in infancy and childhood. This study presents a deep learning model designed to detect CHD using phonocardiogram (PCG) signals, with a focus on its application in global health. We evaluated our model on several datasets, including the primary dataset from Bangladesh, achieving a high accuracy of 94.1%, sensitivity of 92.7%, specificity of 96.3%. The model also demonstrated robust performance on the public PhysioNet Challenge 2022 and 2016 datasets, underscoring its generalizability to diverse populations and data sources. We assessed the performance of the algorithm for single and multiple auscultation sites on the chest, demonstrating that the model maintains over 85% accuracy even when using a single location. Furthermore, our algorithm was able to achieve an accuracy of 80% on low-quality recordings, which cardiologists deemed non-diagnostic. This research suggests that an AI-driven digital stethoscope could serve as a cost-effective screening tool for CHD in resource-limited settings, enhancing clinical decision support and ultimately improving patient outcomes. © 2025, CC BY.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Downstream Task Performance of Pre-Trained Model For Outdoor Audio Event Classification 9

Downstream Task Performance of Pre-Trained Model For Outdoor...

引用

9th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2023

作者： Rochadiani, Theresia Herlina Heryadi, Yaya Sonata, Ilvico Lukas Suparta, Wawan Bina Nusantara University Binus Graduate Program- Computer Science Jakarta Indonesia Universitas Katolik Indonesia Atma Jaya Cognitive Engineering Research Group Jakarta Indonesia Institut Teknologi Nasional Yogyakarta Department of Electrical Engineering Yogyakarta Indonesia

ISBN: (纸本)9798350369922

Our surroundings' auditory landscapes are a wealth of knowledge, providing insights into a range of outdoor pursuits. The automatic classification of these actions using audio event detection and classification (AEDC) systems has a great deal of potential applications in environmental monitoring, security, surveillance, and driverless cars. Even though AEDC has advanced significantly in indoor settings, difficulties still exist outside because of the variable and changing acoustic conditions brought on by elements like the weather, different sound sources, and ambient noise from traffic and industry. This study suggests an outdoor audio event categorization model based on convolutional neural networks (CNNs). The suggested model shows passable accuracy by utilizing adaptation to the downstream task using the ESC-50 dataset and transfer learning from a pre-trained model. The effectiveness of multi-class audio classification models in downstream tasks is analyzed in this paper, with an emphasis on the effect of an increasing number of output classes on accuracy. Three models - three, four, and five classes - with different output class configurations are used in the study, and their training and validation accuracies are assessed. Although the accuracy scores above 80% are commendable, the data show a discernible reduction in performance as the number of classes rises. Notably, the three-class model attains a validation accuracy exceeding 90%, whereas the four-class and five-class models exhibit reduced accuracies, falling below 90% and 85%, respectively. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a Healthy AI Tradition: Lessons from Biology and biomedical Science

arXiv

引用

arXiv 2024年

作者： Kasif, Simon Department of Biomedical Engineering Bioinformatics Graduate Program Department of Computer Science Boston University United States Department of Computer Science Tel Aviv University

AI is a magnificent field that directly and profoundly touches on numerous disciplines ranging from philosophy, computer science, engineering, mathematics, decision and data science and economics, to cognitive science, neuroscience and more. The number of applications and impact of AI is second to none and the potential of AI to broadly impact future science developments is particularly thrilling. While attempts to understand knowledge, reasoning, cognition and learning go back centuries, AI remains a relatively new field. In part due to the fact it has so many wide-ranging overlaps with other disparate fields it appears to have trouble developing a robust identity and culture. Here we suggest that contrasting the fast-moving AI culture to biological and biomedical sciences is both insightful and useful way to inaugurate a healthy tradition needed to envision and manage our ascent to AGI and beyond (independent of the AI Platforms used). After all, the human brain is a biological organ produced by evolution and human intelligence is a remarkable bi-product of nature and nurture and their complex interaction. In this perspective, we focus on traditions and culture, namely the commonly observed practices of evaluating, recognizing applauding, critiquing, debating and managing all progress including useful advances and discovery of challenging limitations. We are not discussing specific scientific exchanges between AI and Biology that include interdisciplinary cross fertilization of scientific methods, technology, ideas and applications that have been amply demonstrated and will continue to be transformative in the future. In a previous perspective, we suggested that biomedical laboratories or centers can usefully embrace logistic traditions in AI labs that will allow them to be highly collaborative, improve the reproducibility of research, reduce risk aversion and produce faster mentorship pathways for PhDs and fellows. This perspective focuses on the benefits of AI a

关键词： Biological organs

来源：评论

学校读者我要写书评

暂无评论

Evaluation of time-series database on microservice architecture for health monitoring system

Evaluation of time-series database on microservice architect...

引用

2022 International Symposium on Electronics and Smart Devices, ISESD 2022

作者： Simanjuntak, Eko Surantha, Nico Isa, Sani Muhamad Bina Nusantara University Binus Graduate Program-Master of Computer Science Computer Science Department Jakarta11480 Indonesia Tokyo City University Electronic and Communication Engineering Faculty of Engineering Department of Electrical Tokyo Japan

ISBN: (数字)9798350396607

ISBN: (纸本)9798350396607

Recently, the research on daily health monitoring using a wearable sensor has been continually evolving. In the future, when this system is actually implemented, a vast amount of data transmission will be conducted from multiple sensors to the cloud server. A system capable of transmitting, storing, processing, and visualizing massive volumes of data is necessary for health monitoring. This research aims to develop a health monitoring system that can accommodate a high amount of data with high performance. The proposed techniques include numerous modifications to system architecture and technology. In the system architecture, a multi-database is proposed to enhance the reliability of the system. As an enhancement to the technology aspect, a time series database and MQTT server are proposed. As the result, the proposed system achieves significantly better performance in terms of throughput, database-writing speed, and database-reading speed compared to the existing system. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Exploring RAG Solutions to Reduce Hallucinations in LLMs

Exploring RAG Solutions to Reduce Hallucinations in LLMs

引用

Annual IEEE Systems Conference

作者： Samar AboulEla Paria Zabihitari Nourhan Ibrahim Majid Afshar Rasha Kashef Electrical Computer and Biomedical Engineering Toronto Metropolitan University Toronto ON Canada Faculty of Engineering Alexandria University Alexandria Egypt Department of Electronics and Computer Engineering Technology Indiana State University Terre Haute USA

ISBN: (数字)9798331508180

ISBN: (纸本)9798331508197

Large Language Models (LLMs) often face challenges in generating accurate and reliable information, particularly in knowledge-intensive tasks. This limitation, referred to as hallucination, occurs when models produce content that is incorrect, irrelevant, or unsupported by evidence. Retrieval Augmented Generation (RAG) solutions provide a promising approach by integrating relevant external knowledge, enabling models to generate factually grounded responses. This study evaluates the performance of a base LLM model, a fine-tuned DistilBERT model, and two RAG architectures, Naïve RAG and Graph RAG, to study their impact on reducing hallucinations and enhancing contextual understanding. Using subsets of HaluEval, Squad-V2, and TriviaQA benchmark datasets, the base model achieved accuracies of 10.18%, 12.67%, and 5.46% respectively; Naive RAG resulted in 44.56%, 19.04%, and 35.32% accuracies; while the fine-tuned LLM model's accuracies were 72.5%, 72.31%, and 88.7% respectively. Graph RAG resulted in 8.85% and 15.12% accuracies using Squad-V2 and TriviaQA, respectively. Our findings show that while fine-tuned LLMs outperform baseline models, incorporating RAG solutions did not result in significant performance improvements, suggesting that the incorporation of external knowledge may not always align with the needs of the task. Experiments demonstrate that Graph RAG handles complex queries by leveraging relationships within structured knowledge graphs. Data organized as a knowledge graph may enable Graph RAG solutions reach their full potential by utilizing their capacity to efficiently retrieve contextually relevant information. Although computing complexity remains a restriction, this study shows that RAG topologies might not consistently enhance LLM reliability in practical situations.

关键词： Accuracy Scalability Large language models Retrieval augmented generation Memory Knowledge graphs Topology Reliability Optimization Context modeling

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：