检索结果-内蒙古大学图书馆

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

Application of VGIS Digital Twin Platform for Enhanced Oilfield Disaster Management and Environmental Protection

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第14期48卷 27-42页

作者： Alabbasi, Awab Aljabery, Maalim A. Bölük, Pınar Sarısaray Faculty of Engineering and Natural Sciences Electrical and Computer Engineering Dept. Bahcesehir University Istanbul34353 Turkey Faculty of Computer Science and Information Technology Computer Science Dept. University of Basrah Basrah61004 Iraq Faculty of Engineering and Natural Sciences Software Engineering Dept. Bahçeşehir University Istanbul34353 Turkey

VGIS (Virtual Geographic Information System) Platform is a unified oilfield operations management platform based on MaaS (Management as a Service) that integrates advanced technologies such as AIoT (Artificial Intelligence & Internet of Things), GIS (Geographic Information System), Digital Twin, and AR (Augmented Reality)/ VR (Virtual Reality). The VGIS platform connects, collects, integrates, analyses, and acts on disparate data sources to provide the oilfield with a centralized view to help make informed decisions fast, bring operational visibility across all assets to improve safety and operational efficiency, reduce costs and improve margins, provide comprehensive analytics and decision support, increase business agility, and reduce management complexity. This is a case study of the application of the VGIS platform Majnoon oilfield, Basrah, Iraq. VGIS digital transformation, production process, and KPIs (Key performance indicators) are highly managed taking oilfield management to a higher level globally, in this study, the objective is to address and resolve the issue of high costs associated with using cloud services by utilising a local Data Center (a large group of networked computer servers typically used by organizations for the remote storage, processing, or distribution of large amounts of data). This approach involves directly uploading 3D maps to ensure faster service on the intranet, eliminating the need to pay for cloud *** aims providing a platform for researching and implementing monitoring and controlling processes in a more convenient and remote manner. The vGIS platform has emerged as a crucial instrument in the realm of disaster response and crisis management. This technology enables responders to rapidly evaluate, analyse, and respond to crucial information in real-time. This research examined the application of vGIS technology in disaster response and analyse the potential advantages and obstacles associated with its utilisation. © 2

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection with Region-of-Interest Selection Based Spatio-Temporal Deep Convolutional-LSTM 16

Driver Drowsiness Detection with Region-of-Interest Selectio...

引用

16th International Conference on Open Source Systems and Technologies, ICOSST 2022

作者： Basit, Muhammad Saif Ahmad, Usman Ahmad, Jameel Ijaz, Khalid Ali, Syed Farooq Sst Umt Dept. of Computer Science Lahore Pakistan Sen Umt Dept. of Electrical Engineering Lahore Pakistan Sst Umt Dept. of Software Engineering Lahore Pakistan

ISBN: (纸本)9781665464772

Driver fatigue and drowsiness instigate road traffic accidents while driving throughout the years. to reduce road traffic injuries and fatality cases, a real-time drowsiness detection system is needed by using artificial intelligence algorithms to detect drivers' tiredness and drowsiness at an early stage. This study proposes an automatic region-of-interest selection based stacked spatio-temporal convolution-long short-term memory (ConvLSTM) drowsiness detection neural network for an in-vehicle surveillance and security system. Haar Cascade classifiers are used to select the region-of-interest on the human face. A ConvLSTM model is implemented to extract spatio-temporal features from the selected region-of-interest and to predict the drowsiness state of the driver. The performance of the proposed model is compared with various pre-trained deep learning models such as CNN, VGG-16, VGG-19, ResNet-50 and MobileNet. The proposed model is trained on the Yawn Eye and MRL benchmarked image datasets. The proposed approach achieves an accuracy of 99.44% on the Yawn Eye dataset and 90.12% on the MRL dataset. The model is further tested and validated using a live feed camera. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Three Levels of Agile Planning in a software Vendor Environment 32

Three Levels of Agile Planning in a Software Vendor Environm...

引用

32nd Australasian Conference on Information Systems: Information Systems for a Sustainable Future, Connectedness, and Social Good, ACIS 2021

作者： Lal, Ramesh Clear, Tony Dept. of Computer Science and Software Engineering Auckland University of Technology Auckland New Zealand Dept. of Computer Science and Software Engineering University of Technology Auckland New Zealand

There is a misconception that agile development requires minimal planning effort. In reality, an agile approach for market-driven software development requires highly disciplined, reliable, and accurate planning practices to swiftly plan and develop high-value innovations in a software vendor environment. This study investigated a highly successful international software vendor in Melbourne, Australia, to provide a case study on agile planning practices. Five planning practices were identified which underly successful agile software development for software vendors. These planning practices were driven by agile concepts such as adaptation, self-organizing, cross-functional collaboration, and empowerment/delegation. We constructed a conceptual framework for agile planning practices, the APP (Agile Planning Practices) Framework illustrating the three levels of agile planning. Copyright © 2021 authors.

关键词： software design

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

A Preliminary Result of Food Object Detection using Swin Transformer 22

A Preliminary Result of Food Object Detection using Swin Tra...

引用

8th International Conference on computer Technology Applications, ICCTA 2022

作者： Jung, Daeil Shim, Simon Choo, Charles Hwang, Doosung Nah, Yunmook Oh, Sejong Dept. of Computer Science Dankook University Korea Republic of Dept. of Computer Engineering San Jose State University United States Dept. of Electrical Engineering San Jose State University United States Dept. of Software Science Dankook University Korea Republic of Dept. of Applied Computer Engineering Dankook University Korea Republic of

ISBN: (纸本)9781450396226

An inappropriate diet is one of the main causes of poor health. However, it is difficult to sustain a quantitative diet assessment in the general living environment. Food object detection is a key method for solving this problem;still, it is difficult to find studies that apply recent object detection techniques. In addition, the currently used high-performance food object detection models have a special architecture that combines two deep learning models-food localization and food classification-in series to achieve high accuracy. The disadvantage of this architecture is that it is difficult to predict the scalability of a model. In this study, we built an end-to-end food object detection model using the Swin Transformer, which is one of the latest backbone models. The experiment was conducted to compare the performance of the UECFOOD dataset with other food object detection studies. For the UECFOOD-100 dataset, a mAP(mean Average Precision) of 0.522 was obtained;also, a mAP of 0.52 was obtained for the UECFOOD-256 dataset. The findings show that the proposed model that uses only end-to-end object detection produces better performance than previous studies using a combination of food localization and food classification. © 2022 ACM.

关键词： Object detection

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

Hybrid Deep Learning Approach for Nonfunctional software Requirements Classifications 3

Hybrid Deep Learning Approach for Nonfunctional Software Req...

引用

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Rahman, Kiramat Ghani, Anwar Ahmad, Rashid Sajjad, Syed Haseeb International Islamic University Dept. of Software Engineering Islamabad Pakistan Big Data Research Center Jeju National University Jeju Korea Republic of Inernational Islamic University Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350332391

This paper explores the concept of algorithmic hybridization, which involves combining various machine learning (ML) algorithms to enhance performance by utilizing the benefits of both simultaneously. This study presents a framework that utilizes a combination of long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) with artificial neural networks (ANN) to classify non-functional requirements (NFR). The task of NFR classification is challenging due to the scarcity of supervised learning data. The effectiveness of the proposed approach was assessed by comparing the performance of our integrated model with that of single LSTM and BiLSTM models. To conduct this evaluation, we combined two datasets consisting of 1000 non-functional requirements (NFR). The experimental findings revealed that the proposed approach is effective as the hybrid models exhibited better precision, recall, and F-1 score compared to its counterparts. © 2023 IEEE.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Using a Multi-Agent System to Better Simultaneous Collaboration software Systems 2

Using a Multi-Agent System to Better Simultaneous Collaborat...

引用

2nd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2022

作者： Abd Alati Elfargane, Rabeia N. Yousef, Khamisa. A. Saleh, Eiman M. Abd Elati, Naeima N Benghazi University Dept. Computer Science Benghazi Libya University of Tobruk Dept. Computer Science Tobruk Libya Benghazi University Dept. Software Engineering Benghazi Libya Benghazi University Dept. Statistics Benghazi Libya

ISBN: (数字)9781665479189

ISBN: (纸本)9781665479189

In each field, there is a need for better collaborative efforts among team members. The software development community is currently concentrating its efforts on developing tools that will make this endeavor easier. As a result, the two major purposes of a collaborative system are to solve the lack of community consciousness (since group members must be aware of one another) and to maintain flooring directive (i.e. provide means to manage access to shared resource in synchronous groupware systems). The goal of this study is to design a dynamic, extendable, and adaptable framework capable of handling challenges in synchronous community consciousness systems in order to solve these concerns. The major purpose of this study is to improve Simultaneous Collaboration software Systems utilizing the structure analysis real-Time approach (SART), which is based on a multiagent system (MAS)). © 2022 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Validation and evaluation of models in the study of characteristic descriptors based on patients' gender

Validation and evaluation of models in the study of characte...

引用

2022 International Conference Automatics and Informatics, ICAI 2022

作者： Marinova, Ginka Todorova, Maya Technical University of Varna Dept. of Computer Science and Engineering Varna Bulgaria Technical University of Varna Dept. of Software and Internet Technologies Varna Bulgaria

ISBN: (数字)9781665476256

ISBN: (纸本)9781665476256

Cancer-related distress is the result of the psyche's reaction to the diagnosis given and to the various stressors in the development of the type of malignant disease. The spreading of the psychological distress and depression may change depending on the stage, gender, and age of the patient. Identifying gender-based distress is important for improving the work of health professionals. The results of the study of models of characteristic descriptors based on patients' sex evaluated distress by applying three methods of machine learning. This report evaluates the effectiveness of the metrics accuracy and classification error. It implemented validation of models of descriptors and the calculated correlation coefficients. The results obtained for the two metrics - accuracy and classification error - were high. © 2022 IEEE.

关键词： Machine learning

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：