检索结果-内蒙古大学图书馆

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Snitsar, Liliya L.N. Gumilyov Eurasian National University Dept. Of 'Computer And Software Engineering' Nur-Sultan Kazakhstan

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

In this paper, theoretical and experimental studies were carried out on the diagnostics of building structures, namely, piles using the pile diagnostics device (PDS-MG4). The task of the study is to determine the dept. of pile driving and identify defects in piles to localize them. A technical problem and a methodology for solving the problem are formulated based on engineering and technical methods for interpreting the data of the device used. A technique for solving one-dimensional inverse problems for the propagation equations of acoustic and seismic waves is presented. © 2022 IEEE.

关键词： Piles

来源：评论

学校读者我要写书评

暂无评论

Aerial Vehicle Detection and Classification Through Fusion of Multi-Domain Features of Acoustic Signals

Aerial Vehicle Detection and Classification Through Fusion o...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Sumble, Malaika Aziz, Sumair Khan, Muhammad Umar Iqtidar, Khushbakht Fernandez-Rojas, Raul University of Engg. and Tech. Taxila Department of Electronics Engineering Taxila Pakistan University of Canberra Faculty of Science and Technology CanberraACT Australia National University of Sciences & Tech. Dept. of Computer and Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350349719

Detection of aerial vehicles is a challenging task. Over time, the significance of developing such vehicles has increased rapidly. However, an utmost concern arises from the potential misuse of these small-sized vehicles in illicit activities such as unauthorized surveillance, smuggling contraband, or disrupting critical infrastructure significant security threats. Recognizing the gravity of this issue, we have opted to introduce an innovative approach to automate the detection processes for aerial vehicles. This initiative aims to deploy effective drone detection systems to mitigate risks and safeguard against illegal activities. We put use to two datasets from GitHub depot. Cepstral, spectral, and time domain features were extracted from the data, followed by classification. We conducted two experiments, with the first (Drone, No-Drone) yielding 98.6% accuracy, using the Ensemble (Bagged Trees) classifier. The second set of experimentation addressed five classes: Background Noises, Bebop Drone, Drone, Helicopter, and Mambo Drone. Ensemble (Bagged trees) again outperformed all other classifiers and achieved 98.3% accuracy. The results highlight that our proposed framework gives effective results based on audio signals of different aerial vehicles. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Optimization of Processing Power by Improving the Performance of Application Service 23

Optimization of Processing Power by Improving the Performanc...

引用

23rd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2022

作者： Tileubergenov, Nurken Romanchikova, Svetlana N. Zhumadillayeva, Ainur K. L.N. Gumilyov Eurasian National University Dept. of 'Computer and Software Engineering' Nur-Sultan Kazakhstan

ISBN: (纸本)9781665498043

This article discusses the problems of optimizing computing power by improving the performance of web applications. The shared responsibility model for the Azure cloud is considered and the area of responsibility of the user and the provider of cloud services for such models as IaaS, PaaS and SaaS is shown. The article discusses methods for optimizing loops and provides the results of performance tests in Microsoft Visual Studio using Performance Profiler and C# language. Methods for optimizing such constructs as algebraic expressions are described and ways to increase performance from caching are considered. Optimization methods are described when using the String type. The article also looks at how boxing/unboxing objects of reference and value types improve application performance. The practical steps given in the article are aimed at writing safe and efficient code. Please, note that the tests and optimization designs carried out and described in the article will help to write code that will not cause poor application performance in the future. These steps will help to avoid buying software to detect optimization problems and, accordingly, significantly reduce material costs for the entire project as a whole. © 2022 IEEE.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

EvoSL: A Large Open-Source Corpus of Changes in Simulink Models & Projects 26

EvoSL: A Large Open-Source Corpus of Changes in Simulink Mod...

引用

26th ACM/IEEE International Conference on Model Driven engineering Languages and Systems, MODELS 2023

作者： Shrestha, Sohil Lal Boll, Alexander Chowdhury, Shafiul Azam Kehrer, Timo Csallner, Christoph University of Texas at Arlington Computer Science & Eng. Dept. ArlingtonTX76019 United States University of Bern Software Engineering Group Bern3012 Switzerland

ISBN: (纸本)9798350324808

Having readily available corpora is crucial for performing replication, reproduction, extension, and verification studies of existing research tools and techniques. MAT-LAB/Simulink is a de-facto standard tool in several safety-critical industries for system modeling and analysis, compiling models to code, and deploying code to embedded hardware. There is no commonly used corpus for large-scale model change studies because there is no readily available corpus. EvoSL is the first large corpus of Simulink projects that includes model and project changes and allows redistribution. EvoSL is available under a permissive open-source license and contains its collection and analysis tools. Using a subset of EvoSL, we replicated a case study of model changes on a single closed-source industrial project. © 2023 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Explainable Multiclass Blood Cell Classification: Combining Custom CNNs with SHAP

Explainable Multiclass Blood Cell Classification: Combining ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Ismiel Hossen Abir Shantanu Dey Anik Hasibul Islam Peyal Dept. of Computer Science & Engineering International Standard University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Birulia Savar Dhaka Bangladesh Dept. of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Blood cell classification is a crucial task in medical diagnostics. This work can identify different blood cell types that play essential roles in the immune system and overall body function. This research introduces a custom Convolutional Neural Network (CNN) model with SHAP for explainable multiclass classification of blood cell images. We classify eight types of blood cells—basophil, eosinophil, erythroblast, immunoglobulin (Ig), lymphocyte, monocyte, neutrophil, and platelet. An ablation study was conducted to optimize the CNN architecture. We compared its performance with eleven transfer learning models, including VGG16, ResNet101, and EfficientNet variants. Our model achieved 92.60% accuracy while maintaining lower complexity. The use of SHAP provides transparency by highlighting crucial features in the model’s decision-making process.

关键词： Training Accuracy Microprocessors Transfer learning Lymphocytes computer architecture Convolutional neural networks Medical diagnosis Blood Testing

来源：评论

学校读者我要写书评

暂无评论

Embodied AI in Mobile Robots: Coverage Path Planning with Large Language Models

arXiv

引用

arXiv 2024年

作者： Kong, Xiangrui Zhang, Wenxiao Hong, Jin Braunl, Thomas Dept. of Electrical Electronic and Computer Engineering The University of Western Australia Perth Australia Dept. of Computer Science and Software Engineering The University of Western Australia Perth Australia

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and solving mathematical problems, leading to advancements in various fields. We propose an LLM-embodied path planning framework for mobile agents, focusing on solving high-level coverage path planning issues and low-level control. Our proposed multilayer architecture uses prompted LLMs in the path planning phase and integrates them with the mobile agents' low-level actuators. To evaluate the performance of various LLMs, we propose a coverage-weighted path planning metric to assess the performance of the embodied models. Our experiments show that the proposed framework improves LLMs' spatial inference abilities. We demonstrate that the proposed multi-layer framework significantly enhances the efficiency and accuracy of these tasks by leveraging the natural language understanding and generative capabilities of LLMs. Our experiments show that this framework can improve LLMs' 2D plane reasoning abilities and complete coverage path planning tasks. We also tested three LLM kernels: gpt-4o, gemini-1.5-flash, and claude- 3.5-sonnet. The experimental results show that claude-3.5 can complete the coverage planning task in different scenarios, and its indicators are better than those of the other models. © 2024, CC BY-NC-SA.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Identifying COVID-19 through X-ray and CT scan images using Machine Learning 18

Identifying COVID-19 through X-ray and CT scan images using ...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Shehzadi, Maham Arshad, Usama Abideen, Zainul Ali, Raja Hashim Khan, Ammad Aslam Ijaz, Ali Zeeshan BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Virtual University of Pakistan Dept. of Biological Sciences Rawalpindi Pakistan National University of Computer & Emerging Sciences Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350328172

In the current global scenario, marked by the COVID-19 pandemic, it has become imperative for healthcare systems around the globe to swiftly and accurately diagnose the disease. This is where cutting-edge approaches such as machine learning (ML) come into play, specifically, ML-based identification of COVID-19 from chest X-ray and CT-Scan imagery. Our research collective is devotedly working towards devising a robust, accurate ML model capable of deciphering these images to identify COVID-19 effectively. This involves the application of a variety of AI algorithms and vast data resources. Our work is grounded on a large, annotated image dataset that aids in training and refining the model. Our findings indicate that ML methodologies can discern COVID-19 from chest X-ray and CT scan images with a mean accuracy of 90%. Such a tool holds promise in aiding medical practitioners in prompt and precise patient diagnosis, thereby improving patient prognosis. The most notable contribution of our study lies in the creation of an ML model that can accurately detect COVID-19 in chest X-ray and CT-Scan images, potentially aiding in early disease detection and management. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

AMN: Attention-based Multimodal Network for Android Malware Classification

AMN: Attention-based Multimodal Network for Android Malware ...

引用

IEEE Conference on Cybernetics and Intelligent Systems

作者： Yi Yang Huyu Wu Yanzhe Wang Peng Wang Dept. Software Engineering Sichuan University Chengdu China Dept. Computer Science Sichuan University Chengdu China

ISBN: (数字)9798350364194

ISBN: (纸本)9798350364200

With the rapid evolution of malware, android malware classification has become increasingly important and remains an active area of research. Traditional machine learning methods rely heavily on hand-crafted features based on expert domain knowledge, making the feature engineering process time-consuming. In recent years, deep learning-based Android malware classification has attracted considerable attention, inspired by the remarkable success of deep learning techniques in the fields of vision and natural language processing. Deep learning methods replace the manual process of feature engineering with a framework capable of simultaneous feature extraction and classification directly from raw data. However, existing approaches do not fully exploit hybrid and multimodal features, which limits their ability to consider multiple disparate sources of information during classification. In this paper, we present attention-based multimodal network(AMN), a multimodal approach to malware classification based on the attention mechanism. AMN combines two modalities of data: 1) grayscale images generated by malware binary files, and 2) network traffic feature sequences. The model employs a cross-modal attention mechanism that combines the features of both modalities by compensating for their limitations. Furthermore, a transfer learning method is proposed to improve the generalization performance of the model, especially in scenarios with limited sample size. The proposed solution surpasses the state-of-the-art precision, achieving 97.73%, along with a recall of 96.51%, as demonstrated through experiments conducted on the CICInvesAndMal2017 dataset. Additionally, to show the effectiveness of our model, ablation experiments were conducted.

关键词： Deep learning Attention mechanisms Mechatronics Transfer learning Random access memory Telecommunication traffic Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Using LLMs for Annotation and ML Methods for Comparative Analysis of Large-Scale Turkish Sentiment Datasets

Using LLMs for Annotation and ML Methods for Comparative Ana...

引用

International Conference on computer Science and engineering (UBMK)

作者： Ercan Ezin Rukiye Savran Kiziltepe Murat Karakus Dept. of Computer Engineering Harran University Şanlıurfa Türkiye Dept. of Software Engineering Karadeniz Tech. University Trabzon Türkiye Dept. of Software Engineering Ankara University Ankara Türkiye

ISBN: (数字)9798350365887

ISBN: (纸本)9798350365894

With the increasing prevalence of e-commerce plat-forms, understanding customer sentiments expressed in product reviews is crucial for assessing platform and product performance. However, traditional sentiment analysis (SA) models often struggle with low-resource languages such as Turkish, particularly due to the language's agglutinative nature and morphological complexity. To address this, several public datasets are now available online. However, these datasets are often annotated using rule-based methods, resulting in poor accuracy for Machine Learning (ML) models. This study addresses these challenges by employing two large Turkish datasets, TRSAv1 and VSCR, and improving their sentiment annotations through advanced Large Language Models (LLMs) such as ChatGPT4o-mini. The reannotation significantly enhanced the performance of traditional ML models-Logistic Regression, Naive Bayes, Random Forest, and Support Vector Machine-especially in the neutral and negative sentiment classes, as evidenced by increased precision, recall, and F1-scores. The findings underscore the importance of thorough data preparation and demonstrate that utilizing LLMs for sentiment annotation in Turkish can lead to more reliable SA, providing a stronger foundation for developing advanced SA tailored to low-resource languages. This study is the first to employ recent LLM for relabelling Turkish customer reviews, highlighting the potential for improved accuracy in SA for low-resource languages.

关键词： Analytical models Accuracy Systematics Annotations Reviews Computational modeling Transfer learning Transformers Vectors Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems

arXiv

引用

arXiv 2024年

作者： Zhang, Wenxiao Kong, Xiangrui Braunl, Thomas Hong, Jin B. Dept. of Computer Science and Software Engineering The University of Western Australia Perth Australia Dept. of Electrical Electronic and Computer Engineering The University of Western Australia Perth Australia

Embodied AI systems, including AI-powered robots that autonomously interact with the physical world, stand to be significantly advanced by Large Language Models (LLMs), which enable robots to better understand complex language commands and perform advanced tasks with enhanced comprehension and adaptability, highlighting their potential to improve embodied AI capabilities. However, this advancement also introduces safety challenges, particularly in robotic navigation tasks. Improper safety management can lead to failures in complex environments and make the system vulnerable to malicious command injections, resulting in unsafe behaviours such as detours or collisions. To address these issues, we propose SafeEmbodAI, a safety framework for integrating mobile robots into embodied AI systems. SafeEmbodAI incorporates secure prompting, state management, and safety validation mechanisms to secure and assist LLMs in reasoning through multi-modal data and validating responses. We designed a metric to evaluate mission-oriented exploration, and evaluations in simulated environments demonstrate that our framework effectively mitigates threats from malicious commands and improves performance in various environment settings, ensuring the safety of embodied AI systems. Notably, In complex environments with mixed obstacles, our method demonstrates a significant performance increase of 267% compared to the baseline in attack scenarios, highlighting its robustness in challenging conditions. © 2024, CC BY.

关键词： Mobile robots

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：