检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Gadekallu, Thippa Reddy Dev, Kapal Khowaja, Sunder Ali Wang, Weizheng Feng, Hailin Fang, Kai Pandya, Sharnil Wang, Wei College of Mathematics and Computer Science Zhejiang A&F University Hangzhou311300 China Department of Computer Science ADAPT Centre Munster Technological University Bishopstown CorkT12 P928 Ireland School of Computing Faculty of Engineering and Computing Dublin City University Glasnevin Campus DublinD09 V209 Ireland Department of Computer Science City University of Hong Kong Hong Kong Department of Computer and Information Sciences Faculty of Engineering and Environment Northumbria University Newcastle upon TyneNE1 8ST United Kingdom Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen518172 China School of Medical Technology Beijing Institute of Technology Beijing100081 China

Responsible Artificial Intelligence (RAI) is a combination of ethics associated with the usage of artificial intelligence aligned with the common and standard frameworks. This survey paper extensively discusses the global and national standards, applications of RAI, current technology and ongoing projects using RAI, and possible challenges in implementing and designing RAI in the industries and projects based on AI. Currently, ethical standards and implementation of RAI are decoupled which caters each industry to follow their own standards to use AI ethically. Many global firms and government organizations are taking necessary initiatives to design a common and standard framework. Social pressure and unethical way of using AI forces the RAI design rather than implementation. © 2025, CC BY.

关键词： Ethical technology

来源：评论

学校读者我要写书评

暂无评论

Highly Stable 3d-Printed Monolithic Structured Al2o3-Supported Ni-Based Catalysts for Dry Reforming of Methane

SSRN

引用

SSRN 2023年

作者： Zhang, Guangcai Zhang, Jinjin Song, Jian Yu, Fangyong Wong, Ngie Hing Sunarso, Jaka Yang, Naitao Meng, Bo Tan, Xiaoyao Liu, Shaomin School of Chemistry and Chemical Engineering Shandong University of Technology Zibo255000 China Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga Sarawak Kuching93350 Malaysia State Key Laboratory of Separation Membranes and Membrane Processes Department of Chemical Engineering Tiangong University Tianjin300387 China

Nickel (Ni)-based powder catalysts with poor stability used in dry reforming of methane (DRM) suffer from severe coking and high bed pressure drop. We successfully prepared a monolithic structured NiAl2O4/Al2O3 catalyst using 3D printed α-Al2O3 topological support followed by Ni impregnation and calcination at 1,400 oC to improve the stability and decrease the pressure drop. The presence of Ni with strong metal-carrier binding in Ni/NiAl2O4/Al2O3 catalyst reduced from NiAl2O4/Al2O3 could inhibit coke accumulation effectively and exhibit excellent catalytic performance and stability. During the 750-h stability test, Ni/NiAl2O4/Al2O3 catalyst exhibited 3% CH4 conversion degradation and 0.37 mgC h-1 gcat-1 coke accumulation rate. The formation mechanisms of two different types of cokes were proposed to explain the performance. This work serves as a guide for preparing the monolithic structured Ni-based catalyst with outstanding stability and low pressure drop for practical application in DRM. © 2023, The Authors. All rights reserved.

关键词： Coke

来源：评论

学校读者我要写书评

暂无评论

CAE-ResVGG FusionNet: A Feature Extraction Framework Integrating Convolutional Autoencoders and Transfer Learning for Immature White Blood Cells in Acute Myeloid Leukemia

引用

Heliyon 2024年第19期10卷 e37745页

作者： Elhassan, Tusneem Osman, Ahmed Hamza Mohd Rahim, Mohd Shafry Mohd Hashim, Siti Zaiton Ali, Abdulalem Elhassan, Esmaeil Elkamali, Yusra Aljurf, Mahmoud Cancer Center of Excellence King Faisal Specialist Hospital and Research Center Riyadh 11564 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Rabigh Saudi Arabia School of Computing Universiti Teknologi Malaysia Johor Johor Bahru 81310 Malaysia Faculty of Computer & Information Technology Sohar University Sohar Oman Institute of Computer Science and Digital Innovation UCSI University Federal Territory of Kuala Lumpur Faculty of mathematical science university of Khartoum Sudan Dept of Hematology Stem Cell Transplantation and Cellular Therapy King Faisal Specialist Hospital & Research Centre Riyadh Saudi Arabia

Acute myeloid leukemia (AML) is a highly aggressive cancer form that affects myeloid cells, leading to the excessive growth of immature white blood cells (WBCs) in both bone marrow and peripheral blood. Timely AML detection is crucial for effective treatment and patient well-being. Currently, AML diagnosis relies on the manual recognition of immature WBCs through peripheral blood smear analysis, which is time-consuming, prone to errors, and subject to inter-observers’ variation. This study aimed to develop a computer-aided diagnostic framework for AML, called "CAE-ResVGG FusionNet", that precisely identifies and classifies immature WBCs into their respective subtypes. The proposed framework leverages an integrated approach, by combining a convolutional autoencoder (CAE) with finely tuned adaptations of the VGG19 and ResNet50 architectures to extract features from CAE-derived embeddings. The process begins with a binary classification model distinguishing between mature and immature WBCs followed by a multiclassifier further classifying immature cells into four subtypes: myeloblasts, monoblasts, erythroblasts, and promyelocytes. The CAE-ResVGG FusionNet workflow comprises four primary stages, including data preprocessing, feature extraction, classification, and validation. The preprocessing phase involves applying data augmentation methods using geometric transformations and synthetic image generation using the CAE to address imbalance in the WBC distribution. Feature extraction involves image embedding and transfer learning, where CAE-derived image representations are used by a custom integrated model of VGG19 and ResNet50 pretrained models. The classification phase employs a weighted ensemble approach that leverages VGG19 and ResNet50, where the optimal weighting parameters are selected using a grid search. The model performance was assessed during the validation phase using the overall accuracy, precision, and sensitivity, while the area under the receiver charact

关键词： Acute myeloid leukemia Autoencoder blood smear microscopic images Cancer Computer-aided diagnosis model image classification Immature white blood cells ResNet VGG19

来源：评论

学校读者我要写书评

暂无评论

Cognitive-inspired Post-processing of optical character recognition for Swedish addresses

Cognitive-inspired Post-processing of optical character reco...

引用

IEEE International Conference on Cognitive Informatics

作者： Moa Andersson Summrina Kanwal Faiza Khan School of Electrical Engineering and Computer Science Kth Royal Institute of Technology in Stockholm Sweden School of Electrical Engineering and Computer Science Kth Royal Institute of Technology in Stockholm Centre for Applied Intelligent Systems Research Halmstad University Sweden Faculty of Computing Riphah International University Islamabad Pakistan

Optical character recognition (OCR) has many ap-plications, such as digitizing historical documents, automating processes, and helping visually impaired people read. However, extracting text from images into a digital format is not an easy problem to solve, and the outputs from the OCR frameworks often include errors. The complexity comes from the many variations in (digital) fonts, handwriting, lighting, etc. To tackle this problem, this thesis investigates two different methods for correcting the errors in OCR output. The used dataset consists of Swedish addresses. The methods are therefore applied to postal automation to investigate the usage of these methods for further automating postal work by automatically reading addresses on parcels using OCR. The first method, the lexical implementation, uses a dataset of Swedish addresses so that any valid address should be in this dataset (hence there is a known and limited vocabulary), and misspelled addresses are corrected to the address in the lexicon with the smallest Levenshtein distance. The second approach uses the same dataset, but with artificial errors, or artificial noise, added. The addresses with this artificial noise are then used together with their correct spelling to train a machine learning model based on Neural machine translation (NMT) to automatically correct errors in OCR read addresses. The results from this study could contribute by defining in what direction future work connected to OCR and postal addresses should go. The results were that the lexical implementation outperformed the NMT model. However, more experiments including real data would be required to draw definitive conclusions as to how the methods would work in real-life applications.

关键词： Vocabulary Automation Computational modeling Optical character recognition Lighting Machine learning Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Development of a techno-economic framework for natural gas dehydration via absorption using tri-ethylene glycol: A comparative study between DRIZO and other dehydration processes

引用

South African Journal of Chemical Engineering 2020年 31卷 17-24页

作者： Kong, Zong Yang Melvin Wee, Xin Jie Mahmoud, Ahmed Yu, Aimin Liu, Shaomin Sunarso, Jaka Research Centre for Sustainable Technologies Faculty of Engineering Computing and Science Swinburne University of Technology Jalan Simpang Tiga Kuching 93350 Sarawak Malaysia Faculty of Science Engineering and Technology Swinburne University of Technology Hawthorn 3122 Victoria Australia Department of Chemical Engineering Curtin University Perth 6845 WA Australia

In this work, the previously developed techno-economic framework in Kong et al. (2018) is extended to evaluate three different configurations of DRIZO process for natural gas dehydration: Case (i) – recycling of the regenerator overhead, Case (ii) – recycling of the flash vapour, and Case (iii) – recycling of both the flash vapour and the regenerator overhead into the dehydration system. The best configuration of DRIZO process is Case (iii), which is used as a representative case for subsequent comparison against other dehydration processes evaluated in our previous work. Our techno-economic analysis reveals that Case (iii) can regenerate tri-ethylene glycol (TEG) with the highest purity and the lowest TEG loss rate and volatile organic compound (VOC) emission. This translates to the lower water content in the dry product gas and also the higher HHV relative to Case (i) and Case (ii). A higher HHV generally signifies a higher gross profit margin. Nevertheless, DRIZO process is not economically feasible in comparison to the other dehydration processes from our previous work, mainly because of the high capital expenditure and the associated operating cost. Relative to the other dehydration processes, although the gross profit margin for DRIZO process is about $100,000 higher, it is not sufficient to compensate the high capital and operating expenses due to the high TCOP of about $500,000 to $600,000. Therefore, our analysis recommends the use of stripping gas dehydration process that consumes a portion of dry product gas to achieve the desired water dew point specification for its highest gross profit margin. © 2019 The Author(s)

关键词： Aspen HYSYS Dehydration Glycol regeneration Natural gas Techno-economic analysis Tri-ethylene glycol

来源：评论

学校读者我要写书评

暂无评论

Continuous Human Activity Recognition using Radar Imagery and Dynamic Time Warping

Continuous Human Activity Recognition using Radar Imagery an...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Ruchita Mehta Vasile Palade Sara Sharifzadeh Bo Tan Yordanka Karayaneva Centre for Computational Science and Mathematical Modelling Coventry University Coventry UK Department of Computer Science Swansea University Swansea UK Faculty of Technology and Communication Sciences Tampere University Finland School of Computing Engineering & Digital Technologies Teesside University Middlesbrough UK

Remote Human Activity Recognition (HAR) in a private residential area has a beneficial influence on the elderly population's life, since this group of people require regular monitoring of health conditions. This paper addresses the problem of continuous detection of daily human activities using mm-wave Doppler radar. Unlike most previous research, this work records the data in terms of continuous series of activities rather than individual activities. These series of activities are similar to real-life activity patterns. The Dynamic Time Warping (DTW) algorithm is used for the detection of human activities in the recorded time series of data and compared to other time-series classification methods. DTW requires less amount of labelled data. The input for DTW was provided using three strategies, and the obtained results were compared against each other. The first approach uses the pixel-level data of frames (named UnSup-PLevel). In the other two strategies, a Convolutional Variational Autoencoder (CVAE) is used to extract Un-Supervised Encoded features (UnSup-EnLevel) and Supervised Encoded features (Sup-EnLevel) from the series of Doppler frames. Results demonstrates the superiority of the Sup-EnLevel features over UnSup-EnLevel and UnSup-PLevel strategies. However, the performance of the UnSup-PLevel strategy worked surprisingly well without using annotations.

关键词： Heuristic algorithms Time series analysis Pipelines Radar detection Streaming media Radar imaging Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Machine Learning Techniques for Prediction of Breast Cancer

Evaluation of Machine Learning Techniques for Prediction of ...

引用

International Colloquium on Signal Processing & Its Applications, CSPA

作者： Jared Tan Yi Hoong Samuel-Soma M. Ajibade Muhammed Basheer Jasser Anwar P.P. Abdul Majeed David Olayemi Alebiosu Bayan Issa Anthonia Oluwatosin Adediran Charis Shwu Chen Kwan Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia Faculty of Informatics Engineering University of Aleppo Syria Department of Real Estate Faculty of Built Environment Universiti Malaya Kuala Lumpur Malaysia Department of Smart Computing and Cyber Resilience School of Engineering and Technology Sunway University No.5 Jalan Universiti Selangor Darul Ehsan Malaysia

ISBN: (数字)9798331522193

ISBN: (纸本)9798331522209

The prediction of breast cancer prognosis has been a significant challenge in medical research due to the complex nature of cancer progression and the variability in patient-specific factors. Machine learning techniques have emerged as powerful tools for enhancing prediction accuracy in cancer diagnosis and prognosis. This study evaluates the performance of three widely used machine learning classifiers—Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM)—in predicting breast cancer outcomes using the Wisconsin Breast Cancer Database. A robust framework was designed to preprocess the dataset, scale features, and assess the classifiers using key evaluation metrics, including accuracy, precision, recall, F1-score, and Matthews Correlation Coefficient (MCC). The results reveal that all classifiers demonstrated high predictive accuracy, with SVM achieving the highest accuracy of 97.08%, followed by RF and ANN with 96.67%. While RF recorded superior precision (95.40%), SVM outperformed others in recall (97.70%) and F1-score (96.05%), showcasing its ability to balance prediction precision and sensitivity. These findings underscore the potential of machine learning to augment traditional cancer prognosis methods, providing healthcare professionals with data-driven insights for personalized treatment strategies. This research highlights the critical role of machine learning in transforming cancer care and lays the groundwork for future studies focused on hybrid models and real-world implementation.

关键词： Support vector machines Accuracy Machine learning Medical services Artificial neural networks Breast cancer Prognostics and health management Random forests Medical diagnostic imaging Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Dynamic AI-Driven Network Slicing with O-RAN for Continuous Connectivity in Connected Vehicles and Onboard Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shah, Syed Danial Ali Bashir, Ali Kashif Al-Otaibi, Yasser D. Dabel, Maryam M. Al Ali, Farman University of Leeds School of Electronic and Electrical Engineering LeedsLS2 9JT United Kingdom Manchester Metropolitan University Department of Computing and Mathematics M15 6BH United Kingdom Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Punjab Rajpura140401 India King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Jeddah21589 Saudi Arabia University of Hafr Al Department of Computer Science and Engineering Batin Saudi Arabia Sungkyunkwan University School of Convergence Seoul Korea Republic of

The rise of connected and autonomous vehicles signifies an era of intelligent transportation systems, where robust and continued network connectivity is essential for critical applications and enhanced in-vehicle Consumer Electronics (CE) experiences. Slicing at the network's edge offers tailored and dedicated logical networks for diverse and low-latency vehicular demands, including Advanced Driver Assistance Systems (ADAS) and in-car infotainment. However, seamless migration of network slices as vehicles traverse coverage areas of different network operators presents formidable challenges, such as ensuring continuous connectivity and uninterrupted service for both safety-critical systems and consumer-oriented services. In this paper, we introduced dynamic network slicing for continuous connectivity in connected vehicles and onboard CE using the Open Radio Access Network (O-RAN) framework in a highly dynamic and mobile environment. We implemented an xAPP within O-RAN that enables Deep Reinforcement Learning (DRL) agent to learn optimal policies through interaction with the network, guiding intelligent decisions on slice migration, resource allocation, and handover optimization. We conducted simulations and evaluations to demonstrate the effectiveness of the proposed xAPP in maintaining optimal Quality of Service (QoS), ensuring efficient RAN resource utilization, minimizing service interruptions, and prioritizing safety-critical slices, all while supporting seamless operation of CE within vehicles during mobility. © 1975-2011 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Laser-Directed Energy Deposition of Bioactive Glass on Ti-6Al-7Nb Titanium Alloy Substrate with Highly Refined Grain Structure

SSRN

引用

SSRN 2024年

作者： Bajda, Szymon Cholewa-Kowalska, Katarzyna Krzyzanowski, Michal Dziadek, Michal Kopyscianski, Mateusz Liu, Yijun Rai, Adarsh Faculty of Metals Engineering and Industrial Computer Science AGH University of Krakow Mickiewicza 30 Krakow30-059 Poland Manufacturing Technology Centre Ansty Park CoventryCV7 9JU United Kingdom Faculty of Materials Science and Ceramics AGH University of Krakow Mickiewicza 30 Krakow30-059 Poland Birmingham City University Faculty Computing Engineering & the Built Environment Millenium Point Curzon Street BirminghamB4 7XG United Kingdom Faculty of Chemistry Jagiellonian University Golebia 24 Krakow31-007 Poland

The bioactive glass S520 was applied to an ultrafine-grained Ti-6Al-7Nb titanium alloy by a laser-directed energy deposition (LDED) process, in order to create a biocompatible material without potentially toxic vanadium for use in load bearing biomedical implants. The laser cladding process influenced the substrate's structure by melting the metallic material at the surface and infusing it with bioactive glass. Subsequently, the melted titanium alloy crystallised, resulting in the formation of relatively large grains. Deeper into the material, laser-induced heat triggered martensitic transformation, leading to the formation of α’ acicular martensite. In the lower regions of the HAZ, a distinctive band with refined grains was identified. Detection of certain amounts of Al directly in the bioactive glass raises concerns about potential toxicity as the glass dissolves in the human body. The nearly complete reduction in P concentration after 14 days highlights the high bioactivity of the material produced. © 2024, The Authors. All rights reserved.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Application of NOMA for cellular-connected UAVs:opportunities and challenges

引用

science China(Information sciences) 2021年第4期64卷 26-39页

作者： Wee Kiat NEW Chee Yen LEOW Keivan NAVAIE Yanshi SUN Zhiguo DING Wireless Communication Centre School of Electrical Engineering Faculty of EngineeringUniversiti Teknologi Malaysia School of Computing and Communications Lancaster University Key Laboratory of Wireless-Optical Communications Chinese Academy of SciencesSchool of Information Science and Technology University of Science and Technology of China School of Electrical and Electronic Engineering The University of Manchester

Unmanned aerial vehicles(UAVs) have gained considerable interests in numerous civil applications. To push forward its potentials, cellular-connected UAVs have been introduced. Nevertheless, cellular networks face several bottlenecks such as spectrum scarcity and limited concurrent connectivity. To address these issues, non-orthogonal multiple access(NOMA) can be adopted. NOMA provides several opportunities for cellular-connected UAVs such as larger rate region, balanced performance between system throughput and fairness, and reduced delay. In this paper, we review important findings of the related studies, and outline new opportunities and challenges in NOMA for cellular-connected UAVs. Monte-Carlo simulations are then performed to analyze the new aerial user's(AU)'s signal characteristics and evaluate the NOMA performance for co-existence of AU and terrestrial user(TU). Our preliminary results show that NOMA is a promising strategy for cellular-connected UAVs.

关键词： cellular-connected UAVs non-orthogonal multiple access signal characteristics aerial user rate terrestrial user rate

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：