检索结果-内蒙古大学图书馆

5th International Conference on Emerging Systems and Intelligent Computing, ESIC 2025

作者： Devi, K. Sumithra Contractor, Dipenkumar Deepa, V. Lakshmi, T.K. Santhikala, M. Mounika, Kamati Kcg College of Technology Department of Computer Science and Engineering Chennai India Government Engineering College Department of Computer Engineering Dahod India Sri Ramakrishna College of Arts and Science Department of Information Technology Tamil Nadu Coimbatore India Malla Reddy University Department of Computer Science and Engineering Telangana Hyderabad India Ramco Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Rajapalayam India Mb School of Pharmaceutical Sciences Mohan Babu University Department of Pharmacy Practice Andhra Pradesh Tirupathi India

ISBN: (纸本)9798331522100

The application of big data analytics to improve energy usage efficiency in smart grids has been prompted by the rising need for power management. Adding to the above, it poses a big data solution for demand prediction, load consolidation, and fault diagnosis. Establishing the new and state-of-the-art innovative LSTM network that was employed in the forecast yielded a higher demand forecast accuracy of 94.2% compared to the previous systems. The load balancing index achieved 92% with an accuracy of 93.7% in fault detection, thus minimizing maintenance cost by 14.7% while improving grid reliability. The proposed model was found to give better results than previous conventional machine learning techniques and even modern ones which are more complex, especially for an ever-changing grid environment. Overall, these findings show the promise of big data solutions for handling the challenges of the contemporary smart grid while improving its efficiency through energy optimization. Consequently, this work lays a framework for subsequent studies on the remaining applications of advanced analytics in energy management systems. © 2025 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Leveraging CNN-Transformer Hybrid Architecture for Accurate Breast Tumor Segmentation in Mammograms

Leveraging CNN-Transformer Hybrid Architecture for Accurate ...

引用

Women in data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Mudassar Ali Muhammad Zeeshan Tahir Iqra Mariam Khadija Nawaz Tariq Mahmood Samia Allaoua Chelloug College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Computer Science and Technology Zhejiang University Hangzhou China School of Electronics and Information Engineering Liaoning University of Technology Jinzhou China Faculty of Information Sciences University of Education Vehari Pakistan Artificial Intelligence and Data Analytics Lab CCIS PSU Riyadh SA Department of Information Technology CCIS PNU Riyadh SA

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Breast cancer detection through mammograms is very crucial for early diagnosis, and tumor segmentation is an important step in treatment planning. This paper proposes a novel approach by combining CNNs with transformers, which we call the Hybrid CNN + Transformer model, for the task of breast tumor segmentation. It leverages the strengths of CNN s in local feature extraction to capture fine details, such as tumor boundaries, and combines them with transformers that model long-range dependencies and contextual relationships across images for the exact delineation of tumor regions in complex tissue structures. Our methodology will be tested on the high-quality mammog-raphy dataset annotated with both benign and malignant lesions, the so-called INbreast dataset. Herein, the CNN backbone-first for instance, ResNet or EfficientNet-extracts the input mammo-gram hierarchically; features are fed into a transformer layer in order to capture global dependencies, after which the final segmentation mask is generated by using a U-Net style decoder for a pixel-wise tumor classification. The segmentation accuracies of our models demonstrated the significant improvement achieved in tumor segmentation, using Hybrid CNN + Transformer when compared with tra-ditional CNN-based models on challenging tumor boundaries and complex tissue patterns. An accurate, robust, completely automatic method for tumor segmentation will thus enable improved diagnostic feasibility on clinical grounds. Furthermore, the combination of learning at both local and global features improved generalizability to previously unseen mammogram images and therefore strengthened clinical applicability.

关键词： Image segmentation Adaptation models Accuracy Breast tumors Computational modeling Transformers Mammography Breast cancer Convolutional neural networks Tumors

来源：评论

学校读者我要写书评

暂无评论

Dipper Throated Optimization Algorithm for Unconstrained Function and Feature Selection

引用

computers, Materials & Continua 2022年第7期72卷 1465-1481页

作者： Ali E.Takieldeen El-Sayed M.El-kenawy Mohammed Hadwan Rokaia M.Zaki Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaizYemen Intelligent Analytics Group(IAG) College of ComputerQassim UniversityBuraydahSaudi Arabia Higher Institute of Engineering and Technology KafrelsheikhEgypt Department of Electrical Engineering Shoubra Faculty of EngineeringBenha UniversityEgypt

Dipper throated optimization(DTO)algorithm is a novel with a very efficient metaheuristic inspired by the dipper throated *** has its unique hunting technique by performing rapid bowing *** show the efficiency of the proposed algorithm,DTO is tested and compared to the algorithms of Particle Swarm Optimization(PSO),Whale Optimization Algorithm(WOA),Grey Wolf Optimizer(GWO),and Genetic Algorithm(GA)based on the seven unimodal benchmark ***,ANOVA and Wilcoxon rank-sum tests are performed to confirm the effectiveness of the DTO compared to other optimization ***,to demonstrate the proposed algorithm’s suitability for solving complex realworld issues,DTO is used to solve the feature selection *** strategy of using DTOs as feature selection is evaluated using commonly used data sets from the University of California at Irvine(UCI)*** findings indicate that the DTO outperforms all other algorithms in addressing feature selection issues,demonstrating the proposed algorithm’s capabilities to solve complex real-world situations.

关键词： Metaheuristic optimization swarmoptimization feature selection function optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Cutting-Edge Machine Learning and data Mining Techniques for Enhancing Big data Management with Advanced Algorithmic Strategies for Optimal data Processing and Analysis 2

Exploring Cutting-Edge Machine Learning and Data Mining Tech...

引用

2nd IEEE International Conference on Advances in information Technology, ICAIT 2024

作者： Anitha, M. Kumari, V. Sheeja Pillai, N. Muthuvairavan Jayarin, P. Jesu David, D. Beulah Department of Artificial Intelligence & Data Science CARE College of Engineering Tamil Nadu Trichy India Department of Computational Intelligence Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Thandalam Chennai India Department of Computer Science and O. Business Systems R.M.D Engineering College Tamil Nadu Thiruvallur India Department of Information Technology Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Thandalam Chennai India

ISBN: (纸本)9798350383867

This work focuses on diverse machine learning methods for big data analytics, which works to leverage predictive performance. The techniques like data preprocessing, dimensionality reduction, feature selection, model selection, hyperparameter tuning, and model evaluation are a focus. A number of algorithms including Random Forests, SVM (Support Vector Machines) Gradient Boosting Machines (GBM), Neural Networks, and ensemble methods (Bagging and Boosting) have their performance evaluated. Hyperparameter tuning applies the Grid Search and Random Search algorithms while model evaluation is done by the K-fold Cross-validation. Fleiss' kappa provide differing levels of accuracy, precision, recall, and F1-score for different models and techniques. Ensemble methods actually show how they have all the necessary qualities to win and perform better than individual models. repeatedly testing improve the models' reliability and effectiveness for practical use. The study highlights the crucial significance of choices on the methods and algorithms that suit the peculiarities of the dataset and problem domain. Capitalizing on the machine learning techniques and in-depth evaluation methods, organizations can get the actionable insights from the big data that will ensure the headquarters' decision-making process and accomplish the meaningful outcomes. Future research could instead be exploring new algorithms and techniques to improve the prediction and scalability in big data analytics setting. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Food Recommendations: A Machine Learning Model for Enhanced Dining Choices

Personalized Food Recommendations: A Machine Learning Model ...

引用

IEEE International Conference on Control System, Computing and Engineering (ICCSCE)

作者： Mohammed Al-Hubaishi Musab A. M. Ali Nooritawati Md Tahir Department of Computer Engineering Halic University Istanbul Turkey College of Computing and Information Sciences University of Technology and Applied Sciences Sultanate of Oman Department of Computer Engineering and Information Security International Information Technology University Kazakhstan Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Malaysia College of Engineering Universiti Teknologi MARA Malaysia Applied College Princess Nourah Bint Abdul Rahman University (PNU) Riyadh Saudi Arabia

ISBN: (数字)9798350364507

ISBN: (纸本)9798350364514

This research introduces an innovative approach to enhance dining experiences through a personalized meal suggestion system. Our method leverages decision tree-based machine learning to predict user preferences by analyzing various attributes. The aim is to assist individuals in making optimal food choices at restaurants, thereby enriching their culinary journey. QR codes are integrated into an Android restaurant application, facilitating convenient access to the food menu. User inquiries are efficiently managed through a MySQL database accessible across multiple platforms, including a Java GUI, an Android app, and a dedicated website catering to both user and administrator roles.

关键词： Java Codes databases Machine learning QR codes Control systems Decision trees Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Spiking Transformer with Experts Mixture 38

Spiking Transformer with Experts Mixture

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Zhou, Zhaokun Lu, Yijie Jia, Yanhao Che, Kaiwei Niu, Jun Huang, Liwei Shi, Xinyu Zhu, Yuesheng Li, Guoqi Yu, Zhaofei Yuan, Li School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China Peng Cheng Laboratory China College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science Peking University China Institute for Artificial Intelligence Peking University China Institute of Automation Chinese Academy of Sciences China Deep NeuroCognition Lab I2R and CFAR Agency for Science Technology and Research Singapore

Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing model capacity and conditional computation. In this work, we consider how to incorporate SNNs' spike-driven and MoE's conditional computation into a unified framework. However, MoE uses softmax to get the dense conditional weights for each expert and TopK to hard-sparsify the network, which does not fit the properties of SNNs. To address this issue, we reformulate MoE in SNNs and introduce the Spiking Experts Mixture Mechanism (SEMM) from the perspective of sparse spiking activation. Both the experts and the router output spiking sequences, and their element-wise operation makes SEMM computation spike-driven and dynamic sparse-conditional. By developing SEMM into Spiking Transformer, the Experts Mixture Spiking Attention (EMSA) and the Experts Mixture Spiking Perceptron (EMSP) are proposed, which performs routing allocation for head-wise and channel-wise spiking experts, respectively. Experiments show that SEMM realizes sparse conditional computation and obtains a stable improvement on neuromorphic and static datasets with approximate computational overhead based on the Spiking Transformer baselines. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COVID-19 artificial intelligence Based Surveillance Applications in The Kingdom of Saudi Arabia

COVID-19 Artificial Intelligence Based Surveillance Applicat...

引用

artificial intelligence and data analytics (CAIDA), International Conference on

作者： Safia Dawood Aisha Dawood Hind Alaskar Tanzila Saba Artificial Intelligence and Data Analytics (AIDA) Lab College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia

ISBN: (纸本)9781665415118;9781665430418

COVID-19 imposed huge burdens and obligations on public health and epidemiology centers to elevate the role of periodic surveillance and case tracing in order to cease the spread of the pandemic. As a result, nations globally are developing various digital solutions for accurate surveillance, reporting of new cases, tracing contacts, and monitoring public health. Traditional tracking and reporting methods have been replaced by intelligent solutions for accurate and efficient reporting. Tools such smart phones, portable devices, and drones have been incorporated in these solutions. These devices produce large amount of data on daily basis and need to be processed instantly to battle the spread of the virus and this is where AI is needed. While the need for AI in disease control and surveillance is clear, the application of AI methods and machine learning algorithms in this field needs further studies. This paper is a systematic review of using AI in COVID-19 surveillance literature to answer the following questions: 1. What AI-based methods are used globally for COVID-19 surveillance? 2. How effective are these methods, and 3. What are the methods used in the Kingdom of Saudi Arabia.

关键词： COVID-19 Systematics Pandemics Surveillance data collection Tools Security

来源：评论

学校读者我要写书评

暂无评论

Human Brain Stroke Prediction using Machine Learning Methods with Synthetic Minority Oversampling Approach

Human Brain Stroke Prediction using Machine Learning Methods...

引用

Women in data Science at Prince Sultan University (WiDS PSU), International Conference of

作者： Muhammad Mujahid Noor Ayesha Ahmad Taher Azar Tanzila Saba Zeeshan Haider Artificial Intelligence and Data Analytics (AIDA) Lab CCIS Prince Sultan University Riyadh School of Clinical Medicine Zhengzhou University Zhengzhou China College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia

ISBN: (数字)9798350395839

ISBN: (纸本)9798350395846

The brain is considered to be the principal anatomical component of the human body. A stroke is a medical condition defined by cerebral injury that occurs as a consequence of blood vessel rupture within the brain. Symptoms might become apparent when there is an interruption in the brain circulation of blood and other vital chemicals. Stroke is widely acknowledged as a significant medical disorder because to its elevated mortality rates, enduring cognitive impairments, and concomitant comorbidities. The timely recognition of the numerous prodromal manifestations linked to a stroke has the capacity to attenuate its magnitude. The primary objective of this study is to utilize machine learning methodologies in order to predict the likelihood of an early-stage occurrence of a cerebral stroke. In order to assess the efficacy of the algorithm, a dataset for stroke prediction was acquired via the Kaggle platform. Various preprocessing techniques are applied to normalize and clean the dataset for stroke prediction. This research utilized many classification models including Random Forest, Ada Boost, LightGBM,, Decision Tree (DT), Logistic Regression (LR),and Support vector machine (SVM) to perform classification tasks. The Random Forest classifier has a higher level of classification accuracy in comparison to alternative machine learning classifiers, obtaining an impressive accuracy rate of 99.45%. The results of the investigation revealed that machine learning approaches demonstrated a higher level of performance in comparison to alternative methods.

关键词： Support vector machines Deep learning Accuracy Machine learning algorithms Computed tomography Stroke (medical condition) Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Ethanol Production in Escherichia Coli Using a Hybrid of Particle Swarm Optimization and artificial Bee Colony 22

Optimizing Ethanol Production in Escherichia Coli Using a Hy...

引用

Proceedings of the 6th International Conference on Advances in artificial intelligence

作者： Mohamad Faiz Dzulkalnine Mohd Saberi Mohamad Yee Wen Choon Muhammad Akmal Remli Hany Alashwal Artificial Intelligence and Bioinformatics Research Group Faculty of Computing Universiti Teknologi Malaysia Malaysia Health Data Science Lab Department of Genetics and Genomics College of Medical and Health Sciences United Arab Emirates University UAE and Big Data Analytics Center United Arab Emirates University UAE Institute for Artificial Intelligence and Big Data Universiti Malaysia Kelantan Malaysia and Department of Data Science Universiti Malaysia Kelantan Malaysia Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University UAE and Big Data Analytics Center United Arab Emirates University UAE

ISBN: (纸本)9781450396943

Metabolic engineering for biomass production using microorganisms’ cell has received considerable attention in recent years. This is due to the biomass products being extensively used in the field of food additives, supplements, pharmaceuticals, and polymer materials. In this paper, ethanol production in Escherichia coli (E. coli) is the desired product. Sugarcane and corn are often used to produce ethanol. However, one of the problems to produce adequate amounts of ethanol is that large areas are needed to plant sugarcane and corn. Furthermore, the amount of time for the process of dry milling and wet milling is high, which are 40 to 50 hours and 24 to 48 hours, respectively. The wet laboratory is also having limitation on the production of ethanol in microorganisms because the amount of the ethanol produced is not satisfying. Hence, a lot of metabolic engineering techniques is introduced to enhance the production of ethanol in E. coli, such as gene knockout strategy, but the production is yet to meet the demand. Therefore, this paper proposes a hybrid algorithm of Particle Swarm Optimization with the artificial Bee Colony algorithm (PSOABC) to identify the optimal set of gene knockout strategy to improve the ethanol production in E. coli. A list of genes to knockout, production of the desired product, and growth rate are presented in this paper. PSOABC has shown better performance in terms of production, growth rate and accuracy.

关键词： Gene Knockouts Particle Swarm Optimization artificial Bee Colony Ethanol Flux Balance Analysis

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review to Build a Smart Guide for the Government E-services in Oman

Comprehensive Review to Build a Smart Guide for the Governme...

引用

IEEE International Conference on Control System, Computing and Engineering (ICCSCE)

作者： Sana Fathima Amal Al Abri Fatma Al Shamli Sara Shukaili Moza Al Balushi Mastan Vali Shaik Nooritawati Md Tahir College of Computing and Information Sciences University of Technology and Applied Sciences-Ibri Ibri Sultanate of Oman College of Engineering Universiti Teknologi MARA (UiTM) Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Malaysia Applied College Princess Nourah Bint Abdul Rahman University (PNU) Riyadh Saudi Arabia

ISBN: (数字)9798350364507

ISBN: (纸本)9798350364514

In the modern age, the idea of the E-government has attained a lot of attention due to its impactful benefits and advantages in achieving the significant goals of the country. The E-government systems play a vital role in facilitating the government’s duties and responsibilities along with the citizen’s interaction and participation. Despite the availabilities of the various studies on the E government, there is still a need to review the previous related literature and combine the issues emerging out of it such that an appropriate system is built incorporating the right blend of AI, social media, and public dissemination of the services. This type of guidance is required in many countries including Oman. The aim of this review is to provide the recent studies that have been done in similar areas focusing on providing the approach and the framework deployed to help build a model for Oman’s e-government systems endorsing social media in its delivery.

关键词： Deep learning Reviews Social networking (online) Buildings Focusing Control systems Rendering (computer graphics) Market research artificial intelligence Electronic government

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：