检索结果-内蒙古大学图书馆

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

作者： Shiva Shokouhmand Md Motiur Rahman Miad Faezipour Smriti Bhatt School of Engineering Technology Electrical & Computer Engineering Technology Purdue University West Lafayette IN USA Department of Computer and Information Technology Purdue University West Lafayette IN USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Pulmonary illnesses are annually reported as highly prevalent. Patient outcomes can, however, be improved through the aid of automated processes for early diagnoses. This study aims to develop an automated method with a comprehensive explanation for diagnosing underlying adventitious sounds in respiratory diseases. For this purpose, stethoscope audio signal recordings are initially segmented to merely include either normal or adventitious sounds such as wheezing and crackling. A comprehensive feature set representing the temporal and spectral dynamics in the respiratory events is extracted to identify the respiratory condition. An extreme gradient-based boosting (XGBoost) model is used and evaluated on the ICBHI 2017 dataset recordings based on a five-fold cross-validation approach. To further increase the model explainability, shapley values are calculated and analyzed. Our predictive method suggests specificity, sensitivity, and ICBHI scores of 94.57%, 77.96%, and 86.27%, respectively, demonstrating superior results, outperforming the state-of-the-art techniques. It is also concluded that Mel-frequency cepstral coefficients (MFCC), spectral centroid, zero crossing rate, and signal intensity are the most consistent discriminating features within the adventitious sounds. Clinical relevance— This work contributes to the development of advanced smart digital stethoscopes and respiratory monitoring systems that can be used in clinical, telemedicine and personalized healthcare settings for early detection of breathing disorders or pulmonary conditions.

关键词： Sensitivity Lungs Telemedicine Pulmonary diseases Stethoscope Feature extraction Boosting Recording Mel frequency cepstral coefficient Monitoring

来源：评论

学校读者我要写书评

暂无评论

Enhancing Research and Mentoring Skills in Engineering Education Through a Mentoring Triad Model

Enhancing Research and Mentoring Skills in Engineering Educa...

引用

Frontiers in Education (FIE) Conference

作者： Sakhi Aggrawal Aparajita Jaiswal Computer and Information Technology Purdue University West Lafayette USA CILMAR Purdue University West Lafayette USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice study submitted in the “Competencies Development” category is a multi-methods case study that aims to examine the impact of a unique Mentoring Triad Model on enhancing research skills in undergraduate students, mentoring skills in graduate students, and professional growth in faculty mentors. The Mentoring Triad consists of an undergraduate student, graduate student, and faculty member collaborating on a semester-long research project within the context of a large Midwestern research university. Data was collected from each participant through surveys, interviews, observations, and document analysis. Results indicate the Mentoring Triad Model facilitated significant growth in research skills, psychosocial development, and professional competencies for all participants. The undergraduate student developed research abilities, intercultural competence, communication skills, collaboration, and self-regulation. The graduate student enhanced their mentoring, research, empathy, project management, adaptability, and collaboration skills. The faculty mentor refined their team management, mentoring, time management, openness to feedback, and collaborative capacities. Findings support the Mentoring Triad as an effective model for integrating research and multilevel mentorship to advance the holistic development of aspiring researchers and professionals in higher education, with implications for replication across disciplines and institutions.

关键词： Surveys Cultural competence Adaptation models Text analysis Collaboration Project management Mentoring Interviews Engineering education

来源：评论

学校读者我要写书评

暂无评论

XAI-based Feature Selection for Improved Network Intrusion Detection Systems

arXiv

引用

arXiv 2024年

作者： Arreche, Osvaldo Guntur, Tanish Abdallah, Mustafa Purdue School of Engineering and Technology Purdue University IndianapolisIN United States Computer Science Department Purdue University IndianapolisIN United States Computer and Information Technology Department Purdue University IndianapolisIN United States

Explainability and evaluation of AI models are crucial parts of the security of modern intrusion detection systems (IDS) in the network security field, yet they are lacking. Accordingly, feature selection is essential for such parts in IDS because it identifies the most paramount features, enhancing attack detection and its description. In this work, we tackle the feature selection problem for IDS by suggesting new ways of applying eXplainable AI (XAI) methods for this problem. We identify the crucial attributes originated by distinct AI methods in tandem with the novel five attribute selection methods. We then compare many state-of-the-art feature selection strategies with our XAI-based feature selection methods, showing that most AI models perform better when using the XAI-based approach proposed in this work. By providing novel feature selection techniques and establishing the foundation for several XAI-based strategies, this research aids security analysts in the AI decision-making reasoning of IDS by providing them with a better grasp of critical intrusion traits. Furthermore, we make the source codes available so that the community may develop additional models on top of our foundational XAI-based feature selection framework. © 2024, CC BY.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Centralized Hierarchical Cybersecurity Monitoring Towards Securing the Defense Industrial Base Supply Chain

SSRN

引用

SSRN 2023年

作者： Sundararajan, Vijay Dietz, J. Eric Department of Computer & Information Technology CERIAS Purdue University United States Purdue Homeland Security Institute Department of Computer & Information Technology Purdue University United States

With the rise in cyberattacks by nation-state adversaries, the US Department of Defense (DoD) introduced mandatory cybersecurity compliance in December 2020 to fortify the Defense Industrial Base (DIB) supply chain and communication with its private partners. These private partners, obligated by Defense Federal Acquisition Regulations (DFARS), were required to conform to the latest standards in computer and data security. The Cybersecurity Maturity Model Certification (CMMC) is a compliance regulation built upon the existing DFARS 252.204-7012 and the NIST SP 800- 171 security controls. These private partners, also referred to as contractors, currently encounter challenges in implementing and monitoring these controls on their information systems, which store, process, and transmit Controlled Unclassified information (CUI). Safeguarding CUI and confidential communications throughout the supply chain, from the DoD to its contractors/sub-contractors, is imperative to mitigate cyber threats. This paper introduces a centralized hierarchical cybersecurity monitoring (CHCM) model for real-time compliance maintenance. Furthermore, this paper examines current work on centralized cybersecurity models, elucidates the security aspects, and addresses the benefits and challenges of implementing the CHCM model. © 2023, The Authors. All rights reserved.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Low Anisotropy Sense Retrofitting (LASeR): Towards Isotropic and Sense Enriched Representations 2

Low Anisotropy Sense Retrofitting (LASeR): Towards Isotropic...

引用

2nd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures: Deep Learning Inside Out, DeeLIO 2021

作者： Bihani, Geetanjali Rayz, Julia Taylor Department of Computer and Information Technology Purdue University

ISBN: (纸本)9781954085305

Contextual word representation models have shown massive improvements on a multitude of NLP tasks, yet their word sense disambiguation capabilities remain poorly explained. To address this gap, we assess whether contextual word representations extracted from deep pretrained language models create distinguishable representations for different senses of a given word. We analyze the representation geometry and find that most layers of deep pretrained language models create highly anisotropic representations, pointing towards the existence of representation degeneration problem in contextual word representations. After accounting for anisotropy, our study further reveals that there is variability in sense learning capabilities across different language models. Finally, we propose LASeR, a ‘Low Anisotropy Sense Retrofitting’ approach that renders off-the-shelf representations isotropic and semantically more meaningful, resolving the representation degeneration problem as a post-processing step, and conducting sense-enrichment of contextualized representations extracted from deep neural language models. © 2021 Association for Computational Linguistics.

关键词： Retrofitting

来源：评论

学校读者我要写书评

暂无评论

Taxonomy-based CHECKLIST for Large Language Model Evaluation

arXiv

引用

arXiv 2023年

作者： Zhang, Damin Purdue University Computer and Information Technology United States

As large language models (LLMs) have been used in many downstream tasks, the internal stereotypical representation may affect the fairness of the outputs. In this work, we introduce human knowledge into natural language interventions and study pre-trained language models' (LMs) behaviors within the context of gender bias. Inspired by CHECKLIST behavioral testing (Ribeiro et al. 2020), we present a checklist-style task that aims to probe and quantify LMs' unethical behaviors through question-answering (QA). We design three comparison studies to evaluate LMs from four aspects: consistency, biased tendency, model preference, and gender preference switch. We probe one transformer-based QA model trained on SQuAD-v2 (Rajpurkar et al. 2016) dataset and one autoregressive large language model. Our results indicate that transformer-based QA model's biased tendency positively correlates with its consistency, whereas LLM shows the opposite relation. Our proposed task provides the first dataset that involves human knowledge for LLM bias evaluation. © 2023, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Hire Me or Not? Examining Language Model’s Behavior with Occupation Attributes

arXiv

引用

arXiv 2024年

作者： Zhang, Damin Zhang, Yi Bihani, Geetanjali Rayz, Julia Department of Computer and Information Technology Purdue University West Lafayette United States

With the impressive performance in various downstream tasks, large language models (LLMs) have been widely integrated into production pipelines, such as recruitment and recommendation systems. A known issue of models trained on natural language data is the presence of human biases, which can impact the fairness of the system. This paper investigates LLMs’ behavior with respect to gender stereotypes in the context of occupation decision making. Our framework is designed to investigate and quantify the presence of gender stereotypes in LLMs’ behavior via multi-round question answering. Inspired by prior work, we constructed a dataset using a standard occupation classification knowledge base released by authoritative agencies. We tested it on three families of LMs (RoBERTa, GPT, and Llama) and found that all models exhibit gender stereotypes analogous to human biases, but with different preferences. The distinct preferences of GPT-3.5-turbo and Llama2-70b-chat, along with additional analysis indicating GPT-4o-mini favors female subjects, may imply that the current alignment methods are insufficient for debiasing and could introduce new biases contradicting the traditional gender stereotypes. Our contribution includes a 73,500 prompts dataset constructed with a taxonomy of real-world occupations and a multi-step verification framework to evaluate model’s behavior regarding gender stereotype. © 2024, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Property Induction Framework for Neural Language Models 44

A Property Induction Framework for Neural Language Models

引用

44th Annual Meeting of the Cognitive Science Society: Cognitive Diversity, CogSci 2022

作者： Misra, Kanishka Rayz, Julia Taylor Ettinger, Allyson Department of Computer and Information Technology Purdue University IN United States Department of Linguistics University of Chicago IL United States

To what extent can experience from language contribute to our conceptual knowledge? Computational explorations of this question have shed light on the ability of powerful neural language models (LMs)-informed solely through text input-to encode and elicit information about concepts and properties. To extend this line of research, we present a framework that uses neural-network language models (LMs) to perform property induction-a task in which humans generalize novel property knowledge (has sesamoid bones) from one or more concepts (robins) to others (sparrows, canaries). Patterns of property induction observed in humans have shed considerable light on the nature and organization of human conceptual knowledge. Inspired by this insight, we use our framework to explore the property inductions of LMs, and find that they show an inductive preference to generalize novel properties on the basis of category membership, suggesting the presence of a taxonomic bias in their representations. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Exploring Machine Learning Methods to Identify Patterns in Students' Solutions to Programming Assignments

Exploring Machine Learning Methods to Identify Patterns in S...

引用

Frontiers in Education (FIE) Conference

作者： Xiaojin Liu Hugo Castellanos Lucas Wiese Alejandra J. Magana Department of Computer Science Department of Computer and Information Technology Purdue University West Lafayette Indiana Department of Computer and Information Technology Purdue University West Lafayette Indiana Department of Computer and Information Technology School of Engineering Education Purdue University West Lafayette Indiana

technology and automation have become increasingly critical for organizations today, and programming has become an essential skill for all STEM majors to meet this demand. Graduates are expected to possess programming skills to meet the needs of the modern workforce. Acquiring programming skills is a challenging task, and institutions often struggle to provide adequate resources to meet the industry's demand for proficient computer programmers. To take steps toward better understanding programming challenges among undergraduate students in science disciplines, this study aims to characterize patterns in students' solutions to programming assignments over the course of a semester. With this, the goal is to characterize students' most common challenges and take steps toward providing automated feedback. Specifically, this study applies machine learning (ML) classification algorithms to analyze student artifacts from a college-level introductory Python programming course for science majors, including source code from labs, homework assignments, projects, and two live-coding exams. Data was collected as part of a semester-long course and pre-processed and de-identified. The researchers labeled the data, and relevant features were selected to prepare the data for training the ML algorithms. Various classification algorithms were trained, and the resulting ML models were evaluated for their accuracy. Then, the study deployed a quantitative research method to evaluate both the effectiveness of various ML models and the quality of the feedback the model could provide, such as efficiency and accuracy. The research results are expected to inform the development of machine-learning algorithms to provide higher-quality feedback mechanisms for students in introductory programming courses. In that manner, this study contributes to improving the quality of programming education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FocalSR: Revisiting image super-resolution transformers with fourier-transform cross attention layers for remote sensing image enhancement

引用

Geomatica 2025年第1期77卷

作者： Ou, Botong Shao, Gang Yang, Baijian Fei, Songlin Computer and Information Technology Purdue University West LafayetteIN47907 United States Libraries and School of Information Studies Purdue University West LafayetteIN47907 United States Forestry and Natural Resources Purdue University West LafayetteIN47907 United States

Transformer architecture has attained noteworthy performance achievements in recent image super-resolution research. However, current transformer-based methods still expose limitations in fully harnessing domain-specific information within images, particularly when applied to broader-scale remote sensing images that contain diverse landscape objects on one scene. Remote sensing images have relatively lower resolution compared to the common super-resolution training dataset and each landscape object covers a small area on the image. These natures of remote sensing images significantly reduced the attention pixels for image restoration in existing transformer-based methods. To address this challenge and enhance domain-specific multi-object image reconstruction, we introduce FocalSR, a Transformer model featuring FOurier-transform Cross Attention Layers for Super-Resolution. Drawing inspiration from state-of-the-art Transformer models like Hybrid Attention Transformer (HAT), FocalSR incorporates channel-focused and window-centric self-attention mechanisms. By integrating Fast Fourier Convolution into the cross-attention layer, FocalSR extends its capacity to capture image-wide information and intricate details in low-resolution images. Through unified task pretraining during model development, we validate the efficacy of these enhancements through extensive testing, resulting in substantial performance improvements. Notably, our experiments showcase FocalSR's superior performance in remote sensing datasets, demonstrating a notable 1 dB enhancement in the PSNR metric compared to other state-of-the-art methods. Additionally, significant improvements are observed in challenging scenarios such as pattern restoration and vegetation detail preservation, underscoring the transformative potential of FocalSR in advancing image processing and domain-specific vision tasks. © 2024 The Authors

关键词： Restoration

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：