检索结果-内蒙古大学图书馆

Hybrid feature selection to identify important single nucleotide polymorphism for asthma classification

AIP Conference Proceedings 2024年第1期2991卷

作者： Wan Ni Wong Weng Howe Chan Hui Wen Nies Kauthar Mohd Daud Artificial Intelligence and Bioinformatics Group School of Computing Faculty of Engineering Universiti Teknologi Malaysia 81310 Skudai Johor Malaysia UTM Big Data Centre Ibnu Sina Institute for Scientific and Industrial Research Universiti Teknologi Malaysia 81310 Skudai Johor Malaysia Center for Artificial Intelligence Technology Faculty of Information Science & Technology Universiti Kebangsaan Malaysia 43600 UKM Bangi Selangor Malaysia

Single nucleotide polymorphism (SNP), being the most common genetic variation, is found to be responsible for traits and complex diseases such as asthma. Polygenic risk scoring (PRS) and machine learning (ML) are the current two common types of genetic risk prediction models. PRS employs statistical association testing to identify alleles with risk. However, it was found not performing well in unraveling the SNP-SNP interactions and attaining low predictive value. In contrast, ML algorithms are more robust in detecting disease associated SNPs, resulting in an improvement in prediction performance. The challenge remains as the high dimensionality nature of SNP tends to cause overfitting problems and impact the classifier performance. This paper introduces a two-stage hybrid feature selection that integrates Mutual Information and Random Forest Recursive Feature Elimination for identifying informative SNPs from 176,287 SNPs in a dataset of 128 asthmatic and non-asthmatic samples. The reduced samples based on the identified informative SNPs are then used with Support Vector Machine to train a classification model. The model from this paper outperforms other ML models with an average accuracy, precision, recall and area under the curve of 98.91%, 98.36%, 99.72% and 0.99 respectively. Additional analysis shows that the genes associated with the top selected SNPs, namely Ring Finger Protein 217 (RNF217) and A-kinase-anchoring protein 6 (AKAP6) are correlated with respiratory diseases. This shows that the proposed method can identify important SNPs that are able to differentiate between asthmatic and non-asthmatic samples.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic Controlled Photovoltaic system with IoT technology

Fuzzy Logic Controlled Photovoltaic system with IoT Technolo...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： L. M. Merlin Livingston Elangovan Guruva Reddy K S Rajesh M. Muthulekshmi E. N. Ganesh Professor Department of Electronics and Communication Engineering Jeppiaar Institute of Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Assistant Professor Department of Electrical and Electronics Engineering Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Adjunct Professor Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Director R&D Department of Electronics and Communication Engineering St. Peters Institute of Higher Education and Research (SPIHER) Avadi Chennai Tamil Nadu India

Due to its affordability and environmental sustainability, solar photovoltaic (PV) systems are gaining popularity as a source of renewable energy. These types of systems, however, deal with a number of issues, such as insufficient energy efficiency, unstable systems, and poor weather adaptation. Conventional control techniques, which are employed to monitor and manage PV systems, have drawbacks, including inadequate data processing capacity and not enough scalability. The Internet of Things (IoT) and fuzzy logic control (FLC) are used in this paper's unique technique to improve PV system monitoring and control in order to meet these difficulties. The FLC technique enhances the PV system output voltage and attains the maximum power point (MPP). Using FLC method, PV systems can be controlled more precisely and effectively, which boosts system stability and energy efficiency. Benefits of the suggested approach include increased flexibility and scalability to various PV system configurations, decreased energy costs, and decreased carbon emissions. This method could assist with the design of more environmentally friendly and energy-efficient systems and has potential uses in commercial as well as residential PV systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

引用

Telecommunications and Intelligent Systems (ICTIS), International Conference on

作者： Mohamed Rafik Aymene Berkani Ammar Chouchane Yassine Himeur Anes Abdennebi Seref Sagiroglu Abbes Amira Research Laboratory in Advanced Electronics Systems (LSEA) University Yahia Fares of Medea Medea Algeria Laboratory of LI3C University Biskra University Center of Barika Barika Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Software and Information Technology Engineering École de Technologie Supérieure Montréal Canada Artificial Intelligence and Big Data Analytics Security R&D Center Gazi University Ankara Turkey Department of Computer Science University of Sharjah Sharjah United Arab Emirates

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments.

关键词： Privacy Smart buildings Costs Federated learning Atmospheric modeling data models Convolutional neural networks Wearable sensors Monitoring Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Orientation and Context Entangled Network for Retinal Vessel Segmentation

arXiv

引用

arXiv 2022年

作者： Wei, Xinxu Yang, Kaifu Bzdok, Danilo Li, Yongjie MOE Key Lab for Neuroinformation School of Life Sciences and Technology University of Electronic Science and Technology of China China McGill University MontrealQC Canada Department of Biomedical Engineering Faculty of Medicine McGill University MontrealQC Canada Mila - Quebec Artificial Intelligence Institute MontrealQC Canada

Most of the existing deep learning based methods for vessel segmentation neglect two important aspects of retinal vessels, one is the orientation information of vessels, and the other is the contextual information of the whole fundus region. In this paper, we propose a robust Orientation and Context Entangled Network (denoted as OCE-Net), which has the capability of extracting complex orientation and context information of the blood vessels. To achieve complex orientation aware, a Dynamic Complex Orientation Aware Convolution (DCOA Conv) is proposed to extract complex vessels with multiple orientations for improving the vessel continuity. To simultaneously capture the global context information and emphasize the important local information, a Global and Local Fusion Module (GLFM) is developed to simultaneously model the long-range dependency of vessels and focus sufficient attention on local thin vessels. A novel Orientation and Context Entangled Non-local (OCE-NL) module is proposed to entangle the orientation and context information together. In addition, an Unbalanced Attention Refining Module (UARM) is proposed to deal with the unbalanced pixel numbers of background, thick and thin vessels. Extensive experiments were performed on several commonly used datasets (DRIVE, STARE and CHASEDB1) and some more challenging datasets (AV-WIDE, UoA-DR, RFMiD and UK Biobank). The ablation study shows that the proposed method achieves promising performance on maintaining the continuity of thin vessels and the comparative experiments demonstrate that our OCE-Net can achieve state-of-the-art performance on retinal vessel segmentation. © 2022, CC BY-NC-SA.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Pay-per-flight dynamic pricing of UAV operations 1

Pay-per-flight dynamic pricing of UAV operations

引用

1st International Conference on artificial intelligence and data Analytics for Air Transportation, AIDA-AT 2020

作者： Rubio-Hervas, Jaime Gupta, Abhishek Ong, Yew-Soon Reyhanoglu, Mahmut Data Science and Artificial Intelligence Research Centre Nanyang Technological University Singapore Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research Singapore Singapore School of Computer Science and Engineering Nanyang Technological University Singapore Singapore University of North Carolina at Asheville Department of Engineering Asheville United States

ISBN: (纸本)9781728153803

Insuring unmanned aerial vehicles (UAVs) is a relatively new concept, where not much data is available yet. We propose the combination of available data from different sources, other than past accident rates, to stochastically model the operational environment by using Gaussian process-based function approximations. A data-driven risk measure is then derived through such stochastic formulation accounting for both aleatoric uncertainties of the considered environmental factors as well as epistemic uncertainties originating from the geographical sparsity of data collection sources. The risk measure is obtained in a path-integral form which represents the operational risk associated with a defined operation in partially unknown environments. A novel pay-per-flight dynamic pricing scheme is derived from such risk measure. © 2020 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Lung and Colon Cancer Detection using Deep Feature Extraction and Ensemble Learning

arXiv

引用

arXiv 2022年

作者： Talukder, Md Alamin Islam, Md Manowarul Uddin, Md Ashraf Akhter, Arnisha Hasan, Khondokar Fida Moni, Mohammad Ali Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Centre for Cyber Security Research & Innovation RMIT University 124 La Trobe Street MelbourneVIC3000 Australia Artificial Intelligence & Data Science School of Health and Rehabilitation Sciences Faculty of Health and Behavioural Sciences The University of Queensland St LuciaQLD4072 Australia

Cancer is a fatal disease caused by a combination of genetic diseases and a variety of biochemical abnormalities. Lung and colon cancer have emerged as two of the leading causes of death and disability in humans. The histopathological detection of such malignancies is usually the most important component in determining the best course of action. Early detection of the ailment on either front considerably decreases the likelihood of mortality. Machine learning and deep learning techniques can be utilized to speed up such cancer detection, allowing researchers to study a large number of patients in a much shorter amount of time and at a lower cost. In this research work, we introduced a hybrid ensemble feature extraction model to efficiently identify lung and colon cancer. It integrates deep feature extraction and ensemble learning with high-performance filtering for cancer image datasets. The model is evaluated on histopathological (LC25000) lung and colon datasets. According to the study findings, our hybrid model can detect lung, colon, and (lung and colon) cancer with accuracy rates of 99.05%, 100%, and 99.30%, respectively. The study's findings show that our proposed strategy outperforms existing models significantly. Thus, these models could be applicable in clinics to support the doctor in the diagnosis of cancers. © 2022, CC BY.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An integrated GIS-based multivariate adaptive regression splines-cat swarm optimization for improving the accuracy of wildfire susceptibility mapping

引用

Geocarto International 2023年第1期38卷

作者： Hai, Tao Theruvil Sayed, Biju Majdi, Ali Zhou, Jincheng Sagban, Rafid Band, Shahab S. Mosavi, Amir School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Computer Science Dhofar University Salalah Oman Department of Building and Construction Technologies Engineering Al-Mustaqbal University College Hilla Iraq Department of Computer Technology Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan John von Neumann Faculty of Informatics Obuda University Budapest Hungary German Research Center for Artificial Intelligence Oldenburg Germany Institute of the Information Society University of Public Service Budapest Hungary

A hybrid machine learning method is proposed for wildfire susceptibility mapping. For modeling a geographical information system (GIS) database including 11 influencing factors and 262 fire locations from 2013 to 2018 is used for developing an integrated multivariate adaptive regression splines (MARS). The cat swarm optimization (CSO) algorithm tunes the parameters of the MARS in order to generate accurate susceptibility maps. From the Pearson correlation results, it is observed that land use, temperature, and slope angle have strong correlation with the fire severity. The results demonstrate that the prediction capability of the MARS-CSO model outperforms model tree, reduced error pruning tree and MARS. The resulting wildfire risk map using MARS-CSO reveals that 20% of the study areas is categorized in the very low wildfire risk class, whereas 40% is under the very high class of fire hazard. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence cat swarm optimization geospatial machine learning natural hazard Wildfire susceptibility

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional (3d) and Two-Dimensional (2d) Lead Iodide-Based Perovskite Materials: A Comparison of Material Stability and Ammonia Gas Detection

SSRN

引用

SSRN 2022年

作者： Adenam, Norfatihah Mohd Mat Yunin, Muhamad Yuzaini Azrai Khairul, Wan M. Yusoff, Abdul Hafidz Adli, Hasyiya Karimah Faculty of Bioengineering and Technology Universiti Malaysia Kelantan Kelantan Jeli17600 Malaysia Research Group Faculty of Science and Marine Environment Universiti Malaysia Terengganu Terengganu Kuala Nerus21030 Malaysia Department of Data Science Universiti Malaysia Kelantan City Campus Pengkalan Chepa Kelantan Kota Bharu16100 Malaysia Institute for Artificial Intelligence and Big Data Universiti Malaysia Kelantan City Campus Pengkalan Chepa Kelantan Kota Bharu16100 Malaysia

Despite enormous attention on lead halide perovskite, the stability of material is of major concern that is in critical needs of attention. Lead iodide-based CH3NH3PbI3 (3D) perovskite (MIP) and (H2C=C(CH3)CO2CH2CH2NH3)2PbI2Cl2 (2D) perovskite (AMP) were synthesised and investigated for different days under various storage conditions. After few days, the original surface morphology of both samples changed and small scattered particles were found. RMS (roughness) of MIP decreased from 51.78 to 18.00 nm, while AMP showed otherwise (from 37.70 to 95.52 nm). The increase in roughness favours the diffusion of ammonia gas molecules into perovskite and consequently increases gas response properties. Based on roughness, FWHM, crystallite size, crystallinity and lattice strain parameters, it can be concluded that 2D AMP exhibited better sensing properties than 3D MIP although the finding shows superior stability of 3D over 2D due to the self-crystallization of 3D perovskite materials. © 2022, The Authors. All rights reserved.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Framework, Standards, Applications and Best practices of Responsible AI: A Comprehensive Survey

arXiv

引用

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

Domain-Adversarial Transformer Network for Multiphase Liver Tumor Segmentation

Domain-Adversarial Transformer Network for Multiphase Liver ...

引用

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

作者： Yangfan Ni Geng Chen Zhan Feng Heng Cui Dimitris Metaxas Shaoting Zhang Wentao Zhu Zhejiang Lab Hangzhou China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi’an China Department of Radiology College of Medicine The First Affiliated Hospital Zhejiang University Hangzhou China Department of Computer Science Rutgers University Piscataway NJ USA Shanghai Artificial Intelligence Laboratory SenseTime Research Shanghai China

Accurate liver tumor segmentation is a prerequisite for data-driven tumor analysis. Multiphase computed tomography (CT) with extensive liver tumor characteristics is typically used as the most crucial diagnostic basis. However, the large variations in contrast, texture, and tumor structure between CT phases limit the generalization capabilities of the associated segmentation algorithms. Inadequate feature integration across phases might also lead to a performance decrease. To address these issues, we present a domain-adversarial transformer (DA-Tran) network for segmenting liver tumors from multiphase CT images. A DA module is designed to generate domain-adapted feature maps from the non-contrast-enhanced (NC) phase, arterial (ART) phase, portal venous (PV) phase, and delay phase (DP) images. These domain-adapted feature maps are then combined with 3D transformer blocks to capture patch-structured similarity and global context attention. The experimental findings show that DA-Tran produces cutting-edge tumor segmentation outcomes, making it an ideal candidate for this co-segmentation challenge.

关键词：

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：