检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Jiang, Keyuan Devendra, Valli Chavan, Soniya Bernard, Gordon R. Purdue University Northwest Computer Information Technology & Graphics HammondIN United States Vanderbilt University Department of Medicine NashvilleTN United States

ISBN: (纸本)9798350337488

Gathering the information pertaining to health evidence occurring on particular days can help understand the progression of a disease over time, and such evidence as symptoms was widely shared by the social media users during the COVID-19 pandemic. Identifying this type of evidence is challenging. In this work, we investigated pretrained large language models on their ability to identify the day-based COVID-19 symptom mentions in Twitter posts. Our results on a corpus of 635 tweets show that without any supervision and optimization both GPT-3.5 and GPT 4 models achieved impressive performance, much better than Web-based ChatGPT and Google Bard. In addition, we explored and utilized GPT-4's ability to determine the number of matches between a list of predicted symptom expressions and a list of annotated symptom expressions, reducing the effort of designing a sophisticated algorithm for finding the matches. © 2023 IEEE.

关键词： COVID-19 symptoms day-based evidence health evidence detection large language models Twitter

来源：评论

学校读者我要写书评

暂无评论

A Quantal Response Analysis of Defender-Attacker Sequential Security Games

A Quantal Response Analysis of Defender-Attacker Sequential ...

引用

IEEE Conference on Decision and Control

作者： Md Reya Shad Azim Mustafa Abdallah Electrical and Computer Engineering Department Purdue University Indianapolis Computer and Information Technology Department Purdue University in Indianapolis

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We explore a scenario involving two sites and a sequential game between a defender and an attacker, where the defender is responsible for securing the sites while the attacker aims to attack them. Each site holds a loss value for the defender when compromised, along with a probability of successful attack. The defender can reduce these probabilities through security investments at each site. The attacker’s objective is to target the site that maximizes the expected loss for the defender, taking into account the defender’s security investments. While previous studies have examined security investments in such scenarios, our work investigates the impact of bounded rationality exhibited by the defender, as identified in behavioral economics. Specifically, we consider quantal behavioral bias, where humans make errors in selecting efficient (pure) strategies. We demonstrate the existence of a quantal response equilibrium in our sequential game and analyze how this bias affects the defender’s choice of optimal security investments. Additionally, we quantify the inefficiency of equilibrium investments under quantal decision-making compared to an optimal solution devoid of behavioral biases. We provide numerical simulations to validate our main findings.

关键词： Measurement Economics Decision making Games Aerospace electronics Numerical simulation Security Investment

来源：评论

学校读者我要写书评

暂无评论

Audio-Based Classification of Insect Species Using Machine Learning Models: Cicada, Beetle, Termite, and Cricket

arXiv

引用

arXiv 2025年

作者： Shetty, Manas V. Kumar, Yoga Disha Sendhil Computer and Information Technology Department Purdue University IN47907 United States

This project addresses the challenge of classifying insect species—Cicada, Beetle, Termite, and Cricket—using sound recordings. Accurate species identification is crucial for ecological monitoring and pest management. We employ machine learning models such as XGBoost, Random Forest, and K-Nearest Neighbors (KNN) to analyze audio features, including Mel Frequency Cepstral Coefficients (MFCC). The potential novelty of this work lies in the combination of diverse audio features and machine learning models to tackle insect classification, specifically focusing on capturing subtle acoustic variations between species that have not been fully leveraged in previous research. The dataset is compiled from various open sources, and we anticipate achieving high classification accuracy, contributing to improved automated insect detection systems. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Fostering AI Literacy Through Simple Prompting Exercises Using Dall-E

Fostering AI Literacy Through Simple Prompting Exercises Usi...

引用

Frontiers in Education (FIE) Conference

作者： Tatiana Ringenberg Nidhi Bhardwaj Nathan Kim Paul J. Thomas Computer and Information Technology Purdue University West Lafayette USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice full paper describes an AI prompting exercise to enhance students' AI prompting skills by providing immediate visual *** exercise was executed within an introductory systems development and organizational security course, consisting of approximately 54 students who were enrolled in a cybersecurity program at a large Midwestern university. The exercise was conducted in the classroom setting, followed by a discussion of observed patterns in successful and unsuccessful prompts. This paper delves into the exercise's methodology, offering an in-depth exploration of the prompts generated by the cohort of 50 students, supplemented with a content analysis. Majority of students initiated their prompts with elaborate descriptions of the intended subject, showcasing a clear inclination towards a subject-centric approach. There was also variance around explicitly addressing the task of image generation, with only a minority of prompts articulating the core objective. Spatial details of background features were prevalent, particularly in terms of their positioning relative to the subject or within the overall image composition. Moreover, the comprehensive nature of subject descriptions encompassing elements such as gender, age, physical features, ethnicity, and clothing, was a ubiquitous trend observed across nearly every prompt. We also consider future directions for enhancing and extending the exercise in courses with larger enrollments.

关键词： Visualization Ethnicity Content management Image synthesis Clothing Market research Artificial intelligence computer security

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Collaborative Hyper-Parameter Tuning 20th

Hierarchical Collaborative Hyper-Parameter Tuning

引用

20th International Conference on Practical Applications of Agents and Multi-Agent Systems , PAAMS 2022

作者： Esmaeili, Ahmad Ghorrati, Zahra Matson, Eric T. Department of Computer and Information Technology Purdue University West LafayetteIN47907 United States

ISBN: (纸本)9783031181917

Hyper-parameter Tuning is among the most critical stages in building machine learning solutions. This paper demonstrates how multi-agent systems can be utilized to develop a distributed technique for determining near-optimal values for any arbitrary set of hyper-parameters in a machine learning model. The proposed method employs a distributedly formed hierarchical agent-based architecture for the cooperative searching procedure of tuning hyper-parameter values. The presented generic model is used to develop a guided randomized agent-based tuning technique, and its behavior is investigated in both machine learning and global function optimization applications. According the empirical results, the proposed model outperformed both of its underlying randomized tuning strategies in terms of classification error and function evaluations, notably in higher number of dimensions. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Identifying Media Storage Locations in Baby Camera Apps: A Mobile Forensic Approach

Identifying Media Storage Locations in Baby Camera Apps: A M...

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Vinicius Lima Umit Karabiyik Computer and Information Technology Purdue University West Lafayete USA

ISBN: (数字)9798350364910

ISBN: (纸本)9798350364927

With the proliferation of IoT and its integration with the internet, digital forensics has encountered a diverse array of potentially questioned devices. Baby cameras represent an example of such devices, characterized by a dearth of background information on forensic analysis and content storage mechanisms within devices and their associated applications. Given the potential for these devices to capture criminal behavior, notably instances of child abuse, there exists a compelling need to comprehensively understand the storage methodologies employed, particularly concerning media content. This study aims to bridge this gap by conducting forensic analyses on two popular baby cameras, with a focus on identifying potential data sources pertinent to investigators. Our investigation prioritized photos and video content, leading to the identification of seven distinct locations where media may be stored. These locations were meticulously detailed, with a particular emphasis on determining those capable of retaining deliberately deleted media. Despite our focus on media, we scrutinized the applications' log files and databases, uncovering potentially valuable information relevant to investigations, including details on Wi-Fi connections and user interactions.

关键词： Pediatrics Law enforcement Soft sensors Focusing Media Cameras Object recognition Internet of Things Wireless fidelity Monitoring

来源：评论

学校读者我要写书评

暂无评论

Forensic Intelligence Derived from Crime Scene Evidence Using Text Embeddings

Forensic Intelligence Derived from Crime Scene Evidence Usin...

引用

IEEE International Conference on Big Data

作者： Vinicius Lima Umit Karabiyik Computer and Information Technology Purdue University West Lafayette USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Forensic Intelligence and Crime Linkage are fields dedicated to studying patterns in criminal behavior to provide actionable insights for investigations. Despite their potential, both fields have seen limited advancements in leveraging recent developments in Artificial Intelligence. This study introduces a novel model that utilizes Natural Language Processing techniques to analyze criminal behavior patterns based on crime scene evidence. Our methodology involves transforming detailed crime scene narratives into a vectorized format, creating a multidimensional space that encapsulates the modus operandi of individual cases. When applied to a real-world dataset, preliminary results demonstrate the effectiveness of this approach in grouping similar crimes, including known serial offenses, and distinguishing unrelated cases based on location and forensic evidence analysis. This research aims to benefit both the academic and law enforcement communities, providing a tool that uncovers insights into criminal behavior patterns and potential case linkages.

关键词： Couplings Analytical models Translation Law enforcement Forensics Big Data Natural language processing Data models Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

QoE-Aware Airborne Communication Infrastructure for Surveillance in Wildfires

QoE-Aware Airborne Communication Infrastructure for Surveill...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Praveen Fernando Jin Wei-Kocsis Department of Computer and Information Technology Purdue University West Lafayette IN

ISBN: (数字)9798350370997

ISBN: (纸本)9798350371000

Global warming is one of the fundamental threats to all living beings today. Various side effects are triggered as a consequence of global warming. Frequent wildfires are one of the side effects causing the loss of lives, vegetation, and economies on a significant scale each year. Therefore, sophisticated mechanisms for surveilling wildfires, including communication systems that are resilient enough to transmit surveillance information to first responders even in the presence of wildfires are urgent. In this work, we leverage unmanned aerial vehicles (UAVs), cognitive radio (CR), and deep reinforcement learning (DRL) technologies to propose a Quality of Experience (QoE)–aware airborne communication infrastructure that can deliver surveillance video streams to a destination in a disaster such as wildfire. In our simulation results, we evaluate the performance of our proposed communication infrastructure by considering different scenarios.

关键词： Wildfires Surveillance Simulation Vegetation mapping Streaming media Routing Climate change Airborne radar Global warming Deep reinforcement learning Environmental monitoring Hazardous areas

来源：评论

学校读者我要写书评

暂无评论

SemiCon: A Semi-supervised Learning for Industrial Image Inspection 9

SemiCon: A Semi-supervised Learning for Industrial Image Ins...

引用

9th IEEE International Conference on Cyber Security and Cloud Computing and 8th IEEE International Conference on Edge Computing and Scalable Cloud, CSCloud-EdgeCom 2022

作者： Tang, Weitao Zhang, Tonglin Yang, Baijian Purdue University Computer and Information Technology West Lafayette United States Purdue University Statistics West Lafayette United States

ISBN: (数字)9781665480666

ISBN: (纸本)9781665480666

Automatic visual inspection system through computer vision has been studied for decades. Traditional methods are often based on image processing techniques, which require individual design for each product and show unsatisfying performance. Recently, deep learning algorithms have significantly promoted the capability of computer vision in various tasks and provided new prospect in automatic inspection system. Numerous studies applied supervised deep learning to inspect industrial images and reported promising results. However, the methods employed in these studies are often in supervised fashion where heavy manual annotation are required. This may not be realistic in many manufacturing scenarios because products are constantly updating. Data collection, annotation and algorithm training can only be proceeded after the completion of the manufacturing process, causing a significant delay to train the models to establish the inspection system. This research aims to tackle the problem using semi-supervised manner such that these computer vision-based machine learning approaches can be rapidly deployed in real-life scenarios. Specifically, this paper proposed SemiCon: a semi-supervised contrastive learning method to identify defective products from industrial images. The proposed method was tested on two open-source industrial images inspection datasets. Results demonstrated that SemiCon achieved better results in several occasions than state-of-the-art approaches. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Mitigating Sex Bias in Audio Data-driven COPD and COVID-19 Breathing Pattern Detection Models

arXiv

引用

arXiv 2024年

作者： Pfeifer, Rachel Vhaduri, Sudip Dietz, James Eric Computer Science Department Purdue University 47907 India Computer and Information Technology Department Purdue University 47907 India

In the healthcare industry, researchers have been developing machine learning models to automate diagnosing patients with respiratory illnesses based on their breathing patterns. However, these models do not consider the demographic biases, particularly sex bias, that often occur when models are trained with a skewed patient dataset. Hence, it is essential in such an important industry to reduce this bias so that models can make fair diagnoses. In this work, we examine the bias in models used to detect breathing patterns of two major respiratory diseases, i.e., chronic obstructive pulmonary disease (COPD) and COVID-19. Using decision tree models trained with audio recordings of breathing patterns obtained from two open-source datasets consisting of 29 COPD and 680 COVID-19-positive patients, we analyze the effect of sex bias on the models. With a threshold optimizer and two constraints (demographic parity and equalized odds) to mitigate the bias, we witness 81.43% (demographic parity difference) and 71.81% (equalized odds difference) improvements. These findings are statistically significant. © 2024, CC BY.

关键词： COVID-19

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：