检索结果-内蒙古大学图书馆

Drone-assisted adaptive object detection and privacy-preserving surveillance in smart cities using whale-optimized deep reinforcement learning techniques

引用

Scientific Reports 2025年第1期15卷 1-20页

作者： Abu-Khadrah, Ahmed Al-Qerem, Ahmad Hassan, Mohammad R. Ali, Ali Mohd Jarrah, Muath Department of Electrical Engineering College of Engineering Technology Al-Balqa Applied University Amman Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa 13132 Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Amman Jordan School of Computing Skyline University College Sharjah United Arab Emirates

Drone/ unmanned aerial vehicles (UAV) surveillance for object/ human detection is familiar in large gatherings in the modern cities era. Artificial intelligence algorithms and computer-aided processing will handle the images extracted from the surveillance videos to reveal the object. This article proposes a novel object detection technique (ODT) that assimilates whale optimization algorithms and deep reinforcement learning. The optimization algorithm detects spreading image features from the origin to the end of x×y pixels. This feature extraction is performed until the complete image pixels are covered to identify their existence in the least position. The forging behaviour of the whales is implied to identify highly overlapping features for object/ human detection/ classification. If the overlapping features increase, the whale’s movement is updated from the last-known highest pixel position. The reinforcement learning recommends that new whale agents validate the low overlapping features, such that the forging whale agent moves towards the large overlapping feature. Therefore, the highest overlapping feature-based pixel differentiation is pursued using forging and searching whales to identify objects through collated pixels. © The Author(s) 2025.

关键词： DRL Feature overlap Object detection Whale optimization

来源：评论

学校读者我要写书评

暂无评论

Dual Fuel-Based Multi-Energy System for Australian Renewable Energy Zones at Country Scale

SSRN

引用

SSRN 2025年

作者： Tariq, Abdul Haseeb Amin, Uzma Shafie-Khan, Miadreza Dehghanian, Payman Senjyu, Tomonobu National University of Sciences and Technology Pakistan School of Electrical Engineering Computing and Mathematical Sciences Curtin University Australia Research and Innovation Division Nowocert Dublin Ireland School of Engineering and Applied Science The George Washington University United States Faculty of Engineering University of the Ryukyus Japan University of Vaasa Finland

The multi-energy system (MES) is an attractive option for producing multi-energy for remote areas. This paper aims to optimize dual-fuel green hydrogen and blended natural gas (BNG) facilitated heterogeneous off-/on-grid MES integrated with renewable sources for different Renewable Energy Zones (REZs) of Australia at the country scale. The main objective is to develop a novel MES for green hydrogen production and BNG for remote housing applications, like combi boilers and gas stoves. The proposed study generates green hydrogen via a proton exchange membrane (PEM) electrolyzer and blends it with natural gas (NG). The blending process involves 20% hydrogen and 80% NG in the overall volume. The optimal sizing of the components, economic-energy-environmental, and performance analyses are performed to examine a feasible solution for each REZ. The results indicate that the North Queensland REZs have the lowest levelized cost of energy (LCE) of 1.28 A$/kWh and 0.1003 A$/kWh, and the net present cost (NPC) of A$0.311 million and A$0.219 million for off-grid and on-grid configurations. The off-grid system has 99.99% and the on-grid system has 95.27% fewer carbon emissions than the NG-fuelled combustion energy system. Therefore, the proposed on-grid dual-fuel-based MES is both more reliably feasible and economically beneficial. © 2025, The Authors. All rights reserved.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained Deep-Learning Scheme 3

Glioma/Glioblastoma Detection in Brain MRI using Pre-trained...

引用

3rd International Conference on Intelligent computing, Instrumentation and Control Technologies, ICICICT 2022

作者： Rajinikanth, Venkatesan Kadry, Seifedine Damasevicius, Robertas Sujitha, R. Angel Balaji, Gangadharam Mohammed, Mazin Abed Noroff University College Faculty of Applied Computing and Technology Kristiansand94612 Norway Vytautas Magnus University Department of Applied Informatics Kaunas44404 Lithuania St. Joseph's College of Engineering Department of Electronics and Instrumentation Engineering Omr Chennai600119 India M/S Tata Consultancy Services Limited Tcsl Siruseri Sez Unit Sipcot I.T. Park TN Chennai603103 India University of Anbar College of Computer Science and Information Technology Ramadi31001 Iraq

ISBN: (数字)9781665410052

ISBN: (纸本)9781665410052

Convolutional Neural Network (CNN) supported medicinal image examination is extensively accepted due to its reputation and improved accuracy. The investigational outcome obtained with DLS along with a chosen classifier helps to achieve better detection results than the traditional and machine-learning methods. The proposed research examines the performance of pre-trained VGG16 and VGG19 schemes in detecting the brain tumour (Glioma/Glioblastoma) grade using different pooling methods. The classification is performed using SoftMax with five-fold cross-validation, and the products are compared and presented. The brain tumour images considered in this study are collected from The Cancer Imaging Archive (TCIA) dataset. This work considered 2000 images (1000 Glioma and 1000 Glioblastoma) of axial-plane with dimension of 224×224×3 pixels for the assessment, and the attained results are compared. The experimental outcome achieved with Python® confirms that the VGG16 with average-pooling provides a better classification accuracy (>99%) with Decision Tree (DT) compared with other methods considered. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Applications in Home Improvement Retailer, Koctas 2

Applications in Home Improvement Retailer, Koctas

引用

2nd International Conference on Business Analytics for technology and Security, ICBATS 2023

作者： Mourad, Nahia Raza, Hammad Amjad, Muhamamd Ullah, Muhammed Ubaid Sabri Elmitwally, Nouh University in Dubai College of Engineering & IT British Dubai United Arab Emirates College of Business Administration and Economics Department of Computer Science National Lahore Pakistan NCBA&E Lahore School of Computer Science Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan Minhaj University Lahore Pakistan Birmingham City University School of Computing and Digital Technology BirminghamB4 7XG United Kingdom Cairo University Faculty of Computers and Artifcial Intelligence Department of Computer Science Giza12613 Egypt

ISBN: (纸本)9798350335644

It sounds like Koçtaş is a leader in the home improvement sector in Turkey, and they are focused on providing the best service and customer experience possible. They are also actively working to accelerate their digital investments and use their vast amount of customer data to innovate in the industry. One way they are using this data is by collecting and analyzing video camera images using AI. This allows them to detect humans and identify which products and shelves are most viewed in their stores. This information can then be used to optimize store layout and product placement for a better customer experience. Another way Koçtaş is innovating is through the implementation of kiosks that use Natural Language Processing (NLP) to interact with customers. These kiosks can understand and respond to questions asked by customers using AI, providing a more personalized and human-like ***, Koçtaş is using Dynamic Creative Optimization to create personalized advertisements for their customers. This method allows them to optimize the content and format of their ads based on the individual preferences and behavior of their customers, leading to more effective ***, Koçtaş is using technology and data to drive innovation and provide a better customer experience in the home improvement industry. © 2023 IEEE.

关键词： Video cameras

来源：评论

学校读者我要写书评

暂无评论

Risk-Based Inspection for Ammonia Storage Unit by Using PRIMS: A Case Study 3

Risk-Based Inspection for Ammonia Storage Unit by Using PRIM...

引用

3rd Innovative Manufacturing, Mechatronics and Materials Forum 2022, iM3F 2022

作者： Omar, Marzuki Ramli, Azizan Johari, Kharul Anwar Saeid, Mohammed Faraj Faculty of Chemical and Process Engineering Technology College of Engineering Technology Universiti Malaysia Pahang Lebuhraya Tun Abdul Razak Gambang Pahang Kuantan26300 Malaysia Faculty of Industrial Sciences and Technology College of Computing and Applied Sciences Universiti Malaysia Pahang Lebuhraya Tun Abdul Razak Gambang Pahang Kuantan26300 Malaysia Aid Station Heavy Oil Depot and Oil Berth Brega Petroleum Marketing Company Tobruk Libya General Registrar Management United Libyan European University Salama Cross corner Ring Road Tobruk Libya

ISBN: (数字)9781839537813

ISBN: (纸本)9781839538063

Risk-based inspection (RBI) is a method that applies risk analysis as its foundation. In this study, RBI methodology is applied on an ammonia storage unit in a specialized bioprocess facility. A liquid ammonia is stored in two pressure vessels. This study aims to determine the level of risk posed by the storage unit and decide the right inspection method and timeframe to conduct the inspection on the unit. The methodology used is based on PRIMS-RBI software with reference to American Petroleum Institute, API 581 Risk-based inspection methodology. This study is the first application of RBI for ammonia storage tank in bio-processing facilities in Malaysia. Based on the analysis performed, the most credible damage mechanism experienced by the unit is identified as internal and external wall thinning. Also, based on the analysis, the probability of failure of this unit is identified as "Low", and the consequences of failure is identified as "Catastrophic". Based on the risk analysis, the risk level of this unit is categorised as "Medium-High" level. This "medium-high risk" is caused by the property of the fluid stored in this device, which is toxic in nature and may potentially cause serious safety and health impact to the surrounding population. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Swallowing Assessment using High-Resolution Cervical Auscultations and Transformer-based Neural Networks

Swallowing Assessment using High-Resolution Cervical Auscult...

引用

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

作者： Ayman Anwar Yassin Khalifa Erin Lucatorto James L. Coyle Ervin Sejdic Department of Electrical and Computer Engineering Faculty of Applied Science & Engineering University of Toronto Toronto Canada Center for Research Computing and Information Technology Analytics University of Pittsburgh Pittsburgh PA USA Systems and Biomedical Engineering Department Faculty of Engineering Cairo University Giza Egypt Department of Communication Science and Disorders School of Health and Rehabilitation Sciences University of Pittsburgh Pittsburgh PA USA Department of Electrical and Computer Engineering Faculty of Applied Science & Engineering University of Toronto and North York General Hospital Toronto Canada

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Swallowing assessment is a crucial task to reveal swallowing abnormalities. There are multiple modalities to analyze swallowing kinematics, such as videofluoroscopic swallow studies (VFSS), which is the gold standard method, and high-resolution cervical auscultation (HRCA), which is a noninvasive technique that uses a triaxial accelerometer attached to the patient’s neck. Deep learning models play an essential role in data driven analysis of swallowing landmarks using VFSS and/or HRCA as input data. Most of these models utilize convolutional and recurrent neural networks. Here, we investigate the ability of transformers to analyze swallowing kinematics; specifically upper esophageal sphincter opening and laryngeal vestibule closure using HRCA signals. We tested the model using an independent test dataset to assess the generalizability of the proposed network. The proposed network achieved an average detection accuracy higher than 90% and 85% for both segmentation tasks, which outperform the hybrid neural networks from the literature, and the model obtained high-performance measures for the independent dataset, showing the transformers’ ability to generalize on unseen data.

关键词： Accuracy Sensitivity Recurrent neural networks Convolution Kinematics Transformers Feature extraction Solids Data models Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Machine learning for Autopsy reports Forensic using Text Classification Techniques 2

Machine learning for Autopsy reports Forensic using Text Cla...

引用

2nd International Conference on computing and Information technology, ICCIT 2022

作者： Shahid, Muhammad Rehman Munir, Asim Ifraheem, Layeba Aldabbas, Hamza Wadood, Abdul Alwada'n, Tariq University of Faisalabad Departmental of Computational Sciences Faislabad Pakistan International Islamic University Department of Computer Science and Software Engineering Islamabad Pakistan Al-Balqa Applied University Prince Abdullah Bin Ghazi Faculty of Information and Communication Technology Al-Salt Jordan School of Computing Engineering Digital Technologies Teesside University Middlesbrough United Kingdom

ISBN: (纸本)9781665436052

A forensic autopsy is a surgical process in which experts collect a deceased body's internal and external information. These death certificates are the source of timely warnings of an increase in disease activity. It's only helpful if accurate and quantitative data is available. Therefore, the Classification of plain text medical autopsy reports reduces the time consumption and irregularities. The motive is to design an automatic text classification system that classifies plain text autopsy reports. Therefore, a methodology proposes using different Automatic Text Classification Techniques (ATC). This technique has embedded Feature Extraction, Feature Representation, and Feature Reduction techniques. These techniques use for the construction of classification models that classify the text of autopsy reports. Data sets collected from these types will be helpful in future experiments. Finally, the performance of the classifier measures by using different Evaluation parameters. These Evaluation Measures are Precision, Recall, Accuracy, and F-measure. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Gene Regulatory Network Construction of Ovarian Cancer Based on Passing Attributes between Network for Data Assimilation 8

Gene Regulatory Network Construction of Ovarian Cancer Based...

引用

8th International Conference on Information technology and Multimedia, ICIMU 2020

作者： Ern Isaac, Yeo Zhu Moorthy, Kohbalan MacHap, Logenthiran Mohamad, Mohd Saberi Sallim, Jamaludin College of Computing and Applied Sciences Faculty of Computing Universiti Malaysia Pahang Pahang26300 Malaysia School of Computing Faculty of Engineering Universiti Teknologi Malaysia Skudai81310 Malaysia Faculty of Bioengineering and Technology Universiti Malaysia Kelantan Kelantan17600 Malaysia

ISBN: (纸本)9781728173108

In the field of cancer informatics, there are computational methods or approach exists to share the same goal, which is to unravel the interactions between genes through the effort of gene regulatory network (GRN) inference and construction. Even now, such a complex task has always been challenging and at the same time, this challenge becomes a motivation for new methods to be invented. Hence, the development of PYPANDA, which is a new method for applying the assimilation of several different datasets input for the construction of the gene regulatory network. Moreover, this integration model is capable of redeeming information that was lost when using other methods that only utilize a single dataset, thus having an innate capacity of predicting a more accurate interaction between genes. The proposed improvement of PYPANDA in this article has been able to filter and determine the most informative or significant genes for the construction of the GRN. With this, the differences between the prior network and the improved PYPANDA network can be specified. As such, two new relationships between the highly informative genes that have not been identified before were successfully identified. © 2020 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: Pedestrian identification using motion-controlled deep neural network in real-time visual surveillance (Soft computing, (2023), 27, 1, (453-469), 10.1007/s00500-021-05701-9)

引用

Soft computing 2024年第2期28卷 1029-1029页

作者： Zahid, Muhammad Khan, Muhammad Attique Azam, Faisal Sharif, Muhammad Kadry, Seifedine Mohanty, Jnyana Ranjan Department of Computer Science COMSATS University Islamabad Wah Campus Islamabad Pakistan Department of Computer Science HITEC University Museum Road Taxila Pakistan Faculty of Applied Computing and Technology Noroff University College Kristiansand Norway School of Computer Applications KIIT Deemed to be University Bhubaneswar India

The publisher has retracted this article in agreement with the Editor-in-Chief. The article was submitted to be part of a guest-edited issue. An investigation by the publisher found a number of articles, including this one, with a number of concerns, including but not limited to compromised editorial handling and peer review process, inappropriate or irrelevant references or not being in scope of the journal or guest-edited issue. Based on the investigation’s findings the publisher no longer has confidence in the results and conclusions of this article. Muhammad Attique Khan, Muhammad Sharif, Seifedine Kadry, and Jnyana Ranjan Mohanty disagree with this retraction. Faisal Azam did not explicitly state whether they agree or disagree with this retraction. Muhammad Zahid has not responded to correspondence regarding this retraction. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction to: A comprehensive performance evaluation of container migration strategies

引用

computing 2025年第4期107卷 1-2页

作者： Feitosa, Leonel Barbosa, Vandirleya Sabino, Arthur Lima, Luiz Nelson Fé, Iure Silva, Luis Guilherme Callou, Gustavo Carvalho, Juliana Leão, Erico Nguyen, Tuan Anh Rego, Paulo Silva, Francisco Airton Laboratory of Applied Research to Distributed Systems (PASID) Federal University of Piauí (UFPI) Picos Brazil Department of Computing Federal Rural University of Pernambuco (UFRPE) Recife Brazil Department of Software Engineering Faculty of Information Technology University of Industry and Trade (HUIT) Ho Chi Minh City Vietnam Department of Computer Science Federal University of Ceará (UFC) Fortaleza Brazil

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：