检索结果-内蒙古大学图书馆

A hybrid of an automated multi-filter with a spatial bound particle swarm optimization for gene selection and cancer classification

引用

Heliyon 2025年第5期11卷

作者： Arram, Anas Ayob, Masri Albadr, Musatafa Abbas Abbood Albashish, Dheeb Sulaiman, Alaa Department of Computer Science Birzeit University Birzeit Palestine CAIT Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Selangor Bangi Malaysia Department of Petroleum Project Management College of Industrial Management of Oil and Gas Basrah University for Oil and Gas Al-Basrah Al-Basrah Iraq Computer Science Department Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Al-Balqa Applied University Salt Jordan

Cancer is one of the most dangerous diseases and a leading cause of death globally. Therefore, early detection of cancer is critical for effective treatments. However, the main challenge in disease identification and classification, such as cancer microarray dataset, is the large number of genes. Extracting meaningful information from these genes is a challenging task. This study proposes a new hybrid gene selection approach for cancer classification that combines three multi-filters in an automated manner with the proposed spatial bound particle swarm optimization (AMF-SBPSO) to effectively select the most important genes. The proposed AMF-SBPSO selects genes through two phases. In the first phase, the method uses three multi-filters to remove the most irrelevant and noisy genes in an automated manner. This process combines multiple filters based on various metrics and filter size ratios, then votes for the best one. This phase aims to select the best filter type and optimal ratio size for each dataset, taking into account that each dataset has unique gene sizes and characteristics. What may work for one dataset might not be effective for others. This phase makes the filtering process more robust. In the second phase, a new variant of particle swarm optimization (PSO), called spatial bound PSO (SBPSO), based on a spatial bounding strategy is proposed to reduce the remaining number of genes without losing the classifier's performance. The proposed AMF-SBPSO's performance was evaluated through experimental studies on nine microarray gene datasets. The results demonstrate that AMF-SBPSO yields a 100% classification accuracy on all tested datasets, outperforming state-of-the-art methods. These findings indicate the superiority of the proposed method in reducing the number of genes and achieving the highest accuracy for cancer classification. © 2025

关键词： Cancer classification Gene selection Microarray Particle swarm optimization Spatial bound particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Performances of Deep Neural Networks with Ensemble Learning Methods for Complex Human Activity Recognition Using Wearable Sensors

Enhancing Performances of Deep Neural Networks with Ensemble...

引用

International ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

Sensor-based human activity recognition (HAR) is a widely explored research area focused on identifying human behaviors by analyzing sensor-generated data, particularly one-dimensional time series signals. Such HAR systems have many real-world applications, including elderly health monitoring and athlete performance evaluation. This paper presents Ens-DeepNet, a novel ensemble learning approach designed for recognizing complex human activities using data from wearable sensors. While deep neural networks have proven effective for HAR tasks, their performance can be further improved through ensemble strategies. To this end, we propose an ensemble architecture that combines five distinct deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and bidirectional GRU (BiGRU). These models are integrated using a majority voting scheme to boost classification accuracy. The proposed method is evaluated using the UTwente dataset, which includes sensor data collected from ten individuals via tri-axial accelerometers and gyroscopes. Experimental findings demonstrate that the ensemble model achieves an impressive accuracy of 99.28%, surpassing the performance of each standalone model, whose accuracies range from 92.77%to 97.34%. This performance gain is particularly notable in recognizing complex activities such as eating, drinking coffee, smoking, and conversing.

关键词： Deep learning Performance evaluation Accuracy Time series analysis Bidirectional long short term memory Performance gain Human activity recognition Ensemble learning Older adults Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Consumer Technology in Task Offloading and Edge Resource Allocation: AIoT and Edge Computing for Next-Generation Communication

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Byeon, Haewon Alsaadi, Mahmood Quraishi, Aadam Alghamdi, Azzah Ahanger, Tariq Ahamed Keshta, Ismail Xalikovich, Pardayev Abdunabi Soni, Mukesh Bhatt, Mohammed Wasim Convergence Department Korea University of Technology and Education Cheonan Korea Republic of Department of Computer Sciences College of Science University of Al Maarif Al Anbar31001 Iraq M.D. Research Intervention Treatment Institute HoustonTX United States Computer Information Systems Department College of Computer Science and Information Technology Imam Abdalrhman Bin Faisal University Khobar Saudi Arabia Department of Management Information Systems CoBA Prince Sattam Bin Abdulaziz University Saudi Arabia Computer Science and Information Systems Department College of Applied Sciences AlMaarefa University Riyadh Saudi Arabia The Department of Accounting and Reporting Tashkent State University of Economics Tashkent Uzbekistan Division of Research and Development Lovely Professional University Phagwara India Dr. D. Y. Patil Vidyapeeth Dr. D. Y. Patil School of Science & Technology Pune Tathawade Pune India Model Institute of Engineering and Technology J&K Jammu India

Artificial Intelligence of Things (AIoT) edge computing has emerged as a critical enabler for consumer technology, easing the load on distribution grid networks through enhanced data transmission and processing capabilities. The Internet of Things (IoT), a modern network paradigm, connects devices using sensors and communication mediums to enable seamless information exchange. However, the limited computational capacity of edge nodes poses challenges in optimizing AIoT edge resources compared to cloud computing. To address this, a cloud-edge three-layer framework for task offloading and edge resource allocation is proposed in the context of consumer technology and distribution grids. This model incorporates random tasks, limited resources, unequal processing power, and high latency requirements. It features two key phases: a resource auction using a multi-round iterative process and compute offloading managed by a Deep Reinforcement Learning (DRL) approach. Enhanced algorithms such as Double DQN and Dueling DQN are integrated into the job offloading process to improve performance. Simulations validate the convergence of the task offloading algorithm and demonstrate that the proposed methods significantly enhance computational efficiency and resource utilization for edge nodes. These advancements offer promising solutions for the dynamic needs of consumer technology and future communication networks. © 2025 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

SmarTeeth: Augmenting Manual Toothbrushing with In-ear Microphones 25

SmarTeeth: Augmenting Manual Toothbrushing with In-ear Micro...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing systems

作者： Qiang Yang Yang Liu Jake Stuchbury-Wass Kayla-Jade Butkow Emeli Panariti Dong Ma Cecilia Mascolo Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Faculty of Dentistry Oral and Craniofacial Sciences King's College London London United Kingdom School of Computing and Information Systems Singapore Management University Singapore Singapore

来源：评论

学校读者我要写书评

暂无评论

Towards Improved Cervical Cancer Screening: Vision Transformer-Based Classification and Interpretability

Towards Improved Cervical Cancer Screening: Vision Transform...

引用

IEEE International Symposium on Biomedical Imaging

作者： Khoa Tuan Nguyen Ho-Min Park Gaeun Oh Joris Vankerschaver Wesley De Neve Department of Environmental Technology Food Technology and Molecular Biotechnology Center for Biosystems and Biotech Data Science Ghent University Global Campus Incheon Korea Department of Electronics and Information Systems IDLab Ghent University Ghent Belgium Department of Applied Mathematics Computer Science and Statistics Ghent University Ghent Belgium

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

We propose a novel approach to cervical cell image classification for cervical cancer screening using the EVA-02 transformer model. We developed a four-step pipeline: fine-tuning EVA-02, feature extraction, selecting important features through multiple machine learning models, and training a new artificial neural network with optional loss weighting for improved generalization. With this design, our best model achieved an F1-score of 0.85227, outperforming the baseline EVA-02 model (0.84878). We also utilized Kernel SHAP analysis and identified key features correlating with cell morphology and staining characteristics, providing interpretable insights into the decision-making process of the fine-tuned model. Our code is available at https://***/Khoa-NT/isbi2025_ps3c.

关键词： Training Pipelines Decision making Artificial neural networks Feature extraction Transformers Kernel Cervical cancer Image classification Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

The potential for electrifying industrial utility systems in existing chemical plants

引用

applied Energy 2025年 392卷

作者： Bielefeld, Svenja Cvetković, Miloš Ramírez, Andrea Engineering Systems and Services Department Faculty of Technology Policy and Management Delft University of Technology Delft Netherlands Electrical Sustainable Energy Department Faculty of Electrical Engineering Mathematics & Computer Science Delft University of Technology Delft Netherlands Department of Chemical Engineering Faculty of Applied Science Delft University of Technology Delft Netherlands

The electrification of utility systems in energy-intensive plants is a promising measure for decarbonising the chemical industry in the short term. However, with the increasing deployment of renewable energy sources, the variability of electricity prices will become a challenge for plants with continuous and constant energy demand. It is thus uncertain whether electrification can become financially viable. This work models the electrification of utility systems in combination with storage technologies for five chemical plants with existing fossil fuel-based utility generation and uses historical data as energy price scenarios. The results show that partial electrification is cost-effective when using electricity is cheaper than natural gas for more than 600 h. Regarding the portfolio of technologies, electric boilers are installed first, followed by thermal energy storage and batteries. Hydrogen is not cost-effective in any of the scenarios explored. This is independent of the type of plant, the available grid connection capacity, and the minimal load of existing fossil fuel-based utility generation. This work thus highlights the potential for electrifying industrial utility systems and the role that electric boilers and energy storage units can play in electrification. © 2025 The Author(s)

关键词： Chemical plants

来源：评论

学校读者我要写书评

暂无评论

SETS OF EQUIANGULAR LINES IN DIMENSION 18 CONSTRUCTED FROM A9 ⊕ A9 ⊕ A1

arXiv

引用

arXiv 2025年

作者： Lin, Yen-Chi Roger Munemasa, Akihiro Taniguchi, Tetsuji Yoshino, Kiyoto Department of Mathematis National Taiwan Normal University Taipei City11677 Taiwan Graduate School of Information Sciences Tohoku University Aoba Ward Sendai980-8579 Japan Department of Electronics and Computer Hiroshima Institute of Technology Saeki Ward Hiroshima731-5143 Japan Department of Computer Science Faculty of Applied Information Science Hiroshima Institute of Technology Saeki Ward Hiroshima731-5143 Japan

In 2023, Greaves et al. constructed several sets of 57 equiangular lines in dimension 18. Using the concept of switching root introduced by Cao et al. in 2021, these sets of equiangular lines are embedded in a lattice of rank 19 spanned by norm 3 vectors together with a switching root. We characterize this lattice as an overlattice of the root lattice A9 ⊕ A9 ⊕ A1, and show that there are at least 246896 sets of 57 equiangular lines in dimension 18 arising in this way, up to isometry. Additionally, we prove that all of these sets of equiangular lines are strongly maximal. Here, a set of equiangular lines is said to be strongly maximal if there is no set of equiangular lines properly containing it even if the dimension of the underlying space is increased. Among these sets, there are ones with only six distinct Seidel *** Codes 05B40, 05B20, 05C50, 05C70 © 2025, CC BY.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Exploring digital interventions for business resilience during crisis-a systematic literature review 16

Exploring digital interventions for business resilience duri...

引用

16th International Conference on ENTERprise information systems, CENTERIS 2024 - 12th International Conference on Project MANagement, ProjMAN 2024 - 14th International Conference on Health and Social Care information systems and Technologies, HCist 2024

作者： Dzandu, Michael D. De Cesare, Sergio Evans, Richard Tang, Yinshan School of Applied Management Westminster Business School University of Westminster 35 Marylebone Road LondonNW1 5LS United Kingdom Faculty of Computer Science Dalhousie University 6050 University Avenue HalifaxB3H 4R2 Canada Business Informatics Systems and Accounting Henley Business School University of Reading ReadingRG6 6UD United Kingdom

Enterprises responded to the COVID-19 outbreak by deploying various digital technology interventions to achieve business resilience. However, little is known about the nature of enterprise digital technology resilience that emerged during the pandemic and how these can inform businesses to build resilience for future pandemics. The purpose of this study therefore is to explore digital technology interventions and enterprise resilience during the pandemic to inform the development of a pandemic resilience framework for future pandemics. A systematic literature review is being conducted on twenty-three relevant articles sourced from the Scopus database on digital technology intervention and resilience during the COVID-19 pandemic. The analysis of the relevant articles using VOSviewer visualisation revealed five key thematic areas namely information systems, digital health, digital intervention and social media;COVID-19 and wellbeing, and digital resilience. The nature, scope and type of digital technology interventions were mainly data resources, information systems and online platforms. Generally, businesses faced technical, motivational and governance challenges deploying digital technology intervention to emerge resilient from the pandemic. The study concluded that the need for future pandemic preparedness is now, and the lessons learned from businesses in using digital interventions during the recent pandemic are useful. The implications of the study for businesses, policymaking and theorizing in the area of digital intervention and resilience have been highlighted. © 2025 The Author(s).

关键词： business digital technologies Enterprises interventions pandemic resilience

来源：评论

学校读者我要写书评

暂无评论

High-Performance Biomedical Antenna for Early and Non-Invasive Breast Cancer Detection

High-Performance Biomedical Antenna for Early and Non-Invasi...

引用

Innovative Research in applied science, Engineering and Technology (IRASET),Conference on

作者： Abdelmouttalib Bousrout Asma Khabba Saida Ibnyaich Tomader Mazri Mohamed Habibi Advanced Systems Engineering Laboratory National School of Applied Sciences Ibn Tofail University Kenitra Morocco Laboratory LAMIGEP EMSI Marrakech Marrakech Morocco Instrumentation Signals and Physical Systems (I2SP) Team Faculty of Sciences SEMLALIA Cadi Ayyad University Marrakesh Morocco Laboratory of Electronic Systems Information Processing Mechanics and Energetics Faculty of Science Ibn Tofail University Kenitra Morocco

ISBN: (数字)9798331532970

ISBN: (纸本)9798331532987

This article presents a novel microstrip antenna design for early breast cancer detection, featuring enhanced bandwidth. Designed using HFSS software, the antenna employs edge feeding with a feed line measuring 3.6 mm in length and 3 mm in width. The 70 × 70 mm substrate, with a thickness of 1.6 mm, is fabricated using FR-4 Epoxy, characterized by a relative permittivity of 4.4 and a 50 Ω impedance. The antenna achieves a maximum gain of 4.431 dBi and operates around 2.4 GHz, offering a 100 MHz bandwidth and an average return loss of –32 dB. A breast phantom model with an embedded tumor was developed to evaluate performance, enabling detection based on the specific absorption rate (SAR), which quantifies the energy absorbed by the tissue. The SAR results, peaking at coordinates (0.035, 0.0325, 0.0325), closely align with the tumor's actual location (0, 0, 0). These findings demonstrate the antenna's effectiveness in accurately locating the tumor while adhering to SAR safety standards.

关键词： Patch antennas Phantoms Microstrip antennas Bandwidth Specific absorption rate Breast cancer Microwave antenna arrays Microstrip Permittivity Substrates

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

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：