检索结果-内蒙古大学图书馆

21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022

作者： Zhang, Yi Rayz, Julia Taylor Purdue University Computer and Information Technology West LafayetteIN United States

ISBN: (纸本)9781665490849

Empowering machines to understand our physical world should go beyond models with only natural language and models with only vision. Vision and language comprise a growing field of study that attempts to bridge the gap between natural language processing and computer vision communities by enabling models to learn visually grounded language. However, as an increasing number of pre-Trained visual linguistic models focus on the alignment between visual regions and natural language, it is difficult to claim that these models capture certain properties of objects in their latent space, such as size. Inspired by recent trends in prompt learning, this study designed a prompt learning framework for two visual linguistic models, ViLBERT and ViLT, and used manually crafted prompt templates to evaluate the consistency of performance of these models in comparing the size of objects. © 2022 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Prediction based Auto-Pilot Interface for Drone to Object Chasing using Historical TSPI Data 23

Prediction based Auto-Pilot Interface for Drone to Object Ch...

引用

23rd International Conference on Control, Automation and Systems, ICCAS 2023

作者： Jang, Shinhyoung Park, Byeonghwi Jeong, Juheon Mahedy, Jack Gebreslassie, Nebey Lee, Minji Matson, Eric T. Chungnam National University Department of Computer Science and Engineering Daejeon34134 Korea Republic of Purdue University Department of Computer and Information Technology West LafayetteIN47906 United States Purdue University Department of Technology West LafayetteIN47906 United States

ISBN: (纸本)9788993215274

Replacing military aircraft with Unmanned Aerial Vehicles (UAV) offers advantages such as reducing costs and risks associated with conventional military aircraft. To defend against enemy UAV attacks, anti-drone systems are used. While most technologies focus on drone detection, this paper proposes a process of tracking targets using arbitrary UAV to enhance camera data quality or directly engage and neutralize targets. The system comprises drone detection, movement prediction, and chasing. Devices such as radar are used to detect drones, and they provide Time-Space-Position information (TSPI) using suitable data formats. Using Machine Learning (ML) techniques make it feasible to predict an object's future location, represented with equations. Utilizing trained machine learning models, the Auto-pilot Application Programming Interface (API) of the drone is employed to track based on the predicted results. Through experiments, the feasibility of predicting an object's future location using various ML techniques has been confirmed. Furthermore, verification has been conducted to establish the attainability of implementing the Auto-pilot API through the utilization of DJI's API. © 2023 ICROS.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Prediction Using CNN-Based Decision Fusion with Dermoscopic Images

Skin Cancer Prediction Using CNN-Based Decision Fusion with ...

引用

2023 Congress in computer Science, computer Engineering, and Applied Computing, CSCE 2023

作者： Rahman, Saeka Vhaduri, Sudip Rahman, Asheka Faezipour, Miad School of Engineering Technology Electrical and Computer Engineering Technology Purdue University West LafayetteIN47907 United States Purdue University Department of Computer and Information Technology West LafayetteIN47907 United States Central Connecticut State University Department of Computer Electronics and Graphic Technology New BritainCT06050 United States

ISBN: (纸本)9798350327595

Skin cancer is a type of cancer that develops in the cells of the skin and can affect any part of the body. Early-stage detection is crucial for the effective treatment and curability of this cancer. Skin cancer diagnosis includes visual screening, dermoscopic image analysis, biopsy, and histopathological examination. The accuracies of these diagnostic procedures are highly dependent on the experience of dermatologists. However, the number of experts in this field is limited. Therefore, automatic skin cancer detection from skin lesion images is an increasingly important field that can aid in medical research. This research proposes a Convolutional Neural Network (CNN) architecture-based decision-level fusion model to predict skin cancer from dermoscopic images with improved accuracy. In so doing, the research uses majority voting decision fusion to combine three individual CNN models. The models are validated using the International Skin Imaging Collaboration (ISIC) 2018 challenges dataset available in the ISIC archive to predict binary and multiclass skin cancer with validation accuracy of 0.83±0.01 and 0.91±0.01, respectively. Paired t-tests are conducted to test the difference in mean accuracies between the fused and best-performing individual models. The test results show that the fused models' mean accuracy is significantly better at a 5% significance level than the best individual models for both cases. The performance of the binary fused model is further compared to several state-of-the-art models and is found to outperform most of them, suggesting the considerable clinical significance. © 2023 IEEE.

关键词： CNN decision fusion Dermoscopic image majority voting melanoma detection paired t-test

来源：评论

学校读者我要写书评

暂无评论

No Filters: A Deep Dive into Photo Sharing Apps on Android and iOS

No Filters: A Deep Dive into Photo Sharing Apps on Android a...

引用

2023 International Symposium on Networks, computers and Communications, ISNCC 2023

作者： Mirza, Mohammad Meraj Hutchinson, Shinelle Gee, Rebecca Karabiyik, Umit College of Computers and Information Technology Department of Computer Science Taif University P.O. Box 11099 Taif21944 Saudi Arabia Purdue University Department of Computer and Information Technology West LafayetteIN47907 United States

ISBN: (纸本)9798350335590

Photo and video-sharing applications have gained popularity among all age groups. These applications allow users to create, share, and interact with multimedia content. Unfortunately, some of these applications have been used to harass, exploit, cyberbully, solicit/groom minors, or track any users' physical location. Consequently, they have become a significant source of evidence in digital investigations. In this paper, we conduct a comprehensive forensic investigation of two relatively new and highly popular photo-sharing applications on both Android and iOS devices. Our goals are to (1) provide a forensic roadmap for forensic investigators who may encounter these or similar applications during a case, (2) highlight the privacy concerns that these applications' users should be made aware of, and (3) discuss the implications of not using multiple tools for artifact validation. Our findings illustrate the lack of privacy and security measures in place for these applications' users, which are location-specific artifacts that can be easily recovered along with plaintext chat messages. Additionally, our findings highlight the inability of commercial tools to uncover pertinent evidence and thus reinforce the need for investigators to use multiple tools during a forensic investigation. © 2023 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

DynADL - Dynamic Architecture Description Language for System of Systems

DynADL - Dynamic Architecture Description Language for Syste...

引用

Annual IEEE Systems Conference

作者： Anton D. Hristozov Eric T. Matson Purdue University Computer and Information Technology West Lafayette In

ISBN: (数字)9798350358803

ISBN: (纸本)9798350358810

Architecture description languages (ADL), many of them well-established, are popular in the systems and software engineering fields. They all exhibit different strengths, weaknesses, and specializations. Many of them are targeting static architectures with some limited support for dynamic changes of the architecture during run-time. The proposed Architecture Description Language in this paper targets the definition of architectures for system of systems (SoS) that can allow for dynamic changes in each system through manipulation of components during run-time and, therefore, dynamic reconfiguration. The existing modeling tools do not target dynamic reconfiguration of systems and, especially system of systems and could be used through possible extensions or annexes. Examples of such existing languages are SysML and AADL. These capabilities allow for improved system maintenance and adaptive behavior at run-time. The main contribution of this work is achieving these goals through the development of a new specialized language. dynADL and its environment have been developed using Antlr and C++ and have been tested for generating systems in POSIX environments. It is an architecture definition language that is extensible and flexible and has an experimental git repository with C++ source code for the implementation of the tools. The proposed tools allow for code generation of skeleton code for systems of systems that have dynamic behavior.

关键词： Adaptation models Codes Source coding computer architecture C++ languages Maintenance Architecture description languages

来源：评论

学校读者我要写书评

暂无评论

EXAMPLE-BASED EXPLANATIONS FOR RANDOM FORESTS USING MACHINE UNLEARNING

arXiv

引用

arXiv 2024年

作者： Surve, Tanmay Pradhan, Romila Computer and Information Technology Purdue University United States

Tree-based machine learning models, such as decision trees and random forests, have been hugely successful in classification tasks primarily because of their predictive power in supervised learning tasks and ease of interpretation. Despite their popularity and power, these models have been found to produce unexpected or discriminatory outcomes. Given their overwhelming success for most tasks, it is of interest to identify sources of their unexpected and discriminatory behavior. However, there has not been much work on understanding and debugging tree-based classifiers in the context of fairness. We introduce FAIRDEBUGGER, a system that utilizes recent advances in machine unlearning research to identify training data subsets responsible for instances of fairness violations in the outcomes of a random forest classifier. FAIRDEBUGGER generates top-k explanations (in the form of coherent training data subsets) for model unfairness. Toward this goal, FAIRDEBUGGER first utilizes machine unlearning to estimate the change in the tree structures of the random forest when parts of the underlying training data are removed, and then leverages the apriori algorithm from frequent itemset mining to reduce the subset search space. We empirically evaluate our approach on three real-world datasets, and demonstrate that the explanations generated by FAIRDEBUGGER are consistent with insights from prior studies on these datasets. © 2024, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Answer Comments As Reviews: Predicting Acceptance By Measuring Valence On Stack Exchange

Answer Comments As Reviews: Predicting Acceptance By Measuri...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Ledbetter, William Springer, John Purdue University Department of Computer and Information Technology West LafayetteIN United States

ISBN: (纸本)9781665480451

Online communication has increased the need to interpret complex emotions rapidly;due to the volatility of the data involved, machine learning tasks that process text aim to address the related challenges. Exploring text in comments that supports ideas through computational methods is a logical next step considering similar research for these question-and-answer sites. A lack of current algorithms that can accurately predict accepted answers with equal votes suggests a gap in this knowledge. Measuring collaborative signals in comments finds common keywords to move a problem toward a *** a dataset from questions posted to Stack Exchange on the subject area of machine learning, the researchers constructed a model using the comments of posts made on accepted answers. Intending to discover whether predictions of marked solutions are accurate by treating the comments as reviews, the researchers find a reduction in error by incorporating reviews of answers as a feature in the predictive algorithm. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Automating the Competence Matrix of a Quality Control Laboratory with the Relational Database Management Framework—A Case Study with the Analytical Chemistry Unit of a National Regulatory Agency

引用

E-Health Telecommunication Systems and Networks 2023年第2期12卷 15-33页

作者： Marcel Okezue Eric Dietz Computer and Information Technology Purdue University West Lafayette USA

This study analyzed the concept of time efficiency in the data management process associated with the personnel training and competence assessments in one of the quality control (QC) laboratories of Nigeria’s Foods and Drugs Authority (NAFDAC). The laboratory administrators were burdened with a lot of mental and paper-based record keeping because the personnel training’s data were managed manually, hence not efficiently processed. The Excel spreadsheet provided by a purdue doctoral dissertation as a remedial to this challenge was found to be deficient in handling operations in database tables, and therefore did not appropriately address the inefficiencies. Purpose: This study aimed to reduce the time it essentially takes to generate, obtain, manipulate, exchange, and securely store data that are associated with personnel competence training and assessments. Method: The study developed a software system that was integrated with a relational database management system (RDBMS) to improve manual/Excel-based data management procedures. To validate the efficiency of the software the mean operational times in using the Excel-based format were compared with that of the “New” software system. The data were obtained by performing four predefined core tasks for five hypothetical subjects using Excel and the “New” system (the model system) respectively. Results: It was verified that the average time to accomplish the specified tasks using the “New” system (37.08 seconds) was significantly (p = 0.00191, α = 0.05) lower than the time measurements for the Excel system (77.39 seconds) in the ANACHEM laboratory. The RDBMS-based “New” system provided operational (time) efficiency in the personnel training and competence assessment process in the QC laboratory and reduced human errors.

关键词： Data Management RDBMS NAFDAC Personnel Assessment SOP Proficiency

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Intent-Based Generation of Cloud-Native Configurations 18

Leveraging Large Language Models for Intent-Based Generation...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Dubey, Anuj Singh, Charu Priya Nadig, Deepak Purdue University Dept. of Computer and Information Technology West LafayetteIN47907 United States Northeastern University College of Professional Studies BostonMA02115 United States

ISBN: (纸本)9798350391725

Cloud-native systems have revolutionized the development, deployment, and management of modern applications, enabling organizations to achieve unprecedented scalability and resilience. However, the complexity of configuring and managing these systems remains a significant barrier, particularly for users lacking deep technical expertise. In this paper, we present an intent-based framework that leverages large language models (LLMs) to automate the generation of configurations within cloud-native environments, focusing on Kubernetes deployment workloads as a use case. The framework offers a practical toolkit for users who lack deep technical expertise, helping them manage Kubernetes configurations by converting user intents into workable, deployable configurations. Our evaluations demonstrate that our proposed framework achieves a 100% success rate in schema validation through kubectl using few-shot prompting, compared to {9 7. 1 8 %} with zero-shot prompting and {9 5. 7 7} % with human-generated configurations. In semantic validation using Kubeval, our framework performed well, achieving a success rate of {9 1. 5 5 %} with both few-shot and zero-shot prompting, compared to 87.32% with human-generated configurations. These results highlight our framework's potential to enhance both the accessibility and efficiency of cloud-native technologies, making complex deployment tasks more approachable for a broader range of users. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Toward Mitigating Sex Bias in Pilot Trainees' Stress and Fatigue Modeling

Toward Mitigating Sex Bias in Pilot Trainees' Stress and Fat...

引用

International Workshop on Wearable and Implantable Body Sensor Networks (BSN)

作者： Rachel Pfeifer Sudip Vhaduri Mark Wilson Julius Keller Computer Science Department Purdue University IN Computer and Information Technology Department Purdue University IN School of Health Sciences Purdue University IN School of Aviation and Transportation Technology Purdue University IN

ISBN: (数字)9798331530143

ISBN: (纸本)9798331530150

While researchers have been trying to understand the stress and fatigue among pilots, especially pilot trainees, and to develop stress/fatigue models to automate the process of detecting stress/fatigue, they often do not consider biases such as sex in those models. However, in a critical profession like aviation, where the demographic distribution is disproportionately skewed to one sex, it is urgent to mitigate biases for fair and safe model predictions. In this work, we investigate the perceived stress/fatigue of 69 college students, including 40 pilot trainees with around 63% male. We construct models with decision trees first without bias mitigation and then with bias mitigation using a threshold optimizer with demographic parity and equalized odds constraints 30 times with random instances. Using bias mitigation, we achieve improvements of 88.31% (demographic parity difference) and 54.26% (equalized odds difference), which are also found to be statistically significant.

关键词： Body sensor networks Prevention and mitigation Predictive models Fatigue Decision feedback equalizers Time factors Decision trees Stress

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：