检索结果-内蒙古大学图书馆

37th Australasian Joint Conference on artificial intelligence, AJCAI 2024

作者： Fang, Zhengxin Ma, Hui Chen, Gang Hartmann, Sven Wang, Chen Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany National Institute of Water and Atmospheric Research Wellington New Zealand

ISBN: (纸本)9789819603473

Microservice deployment in cloud computing is a challenging combinatorial optimization problem due to the complex dependencies among microservices and the intricate trade-offs among different QoS requirements, e.g., minimizing Energy Consumption (EC) vs. minimizing Communication Overhead (CO). Recently, some hyper-heuristics methods, particularly Genetic Programming Hyper-Heuristics (GPHH), have been proposed to automatically generate heuristics for solving dynamic microservice deployment problems. Meanwhile, Large Language Models (LLMs) are becoming popular for solving various domain-specific problems thanks to their strong ability to learn problem-related knowledge. However, hybridizing GPHH with LLM by combining their abilities in solving complex optimization problems remains unexplored. In this paper, we propose an LLM-enhanced Genetic Programming Hyper-Heuristic (LLM-GPHH) algorithm to evolve heuristics for the dynamic deployment of applications composed of microservices, to jointly optimize EC and CO. Our experiments on real-world datasets demonstrate the effectiveness of the newly proposed LLM-GPHH. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Efficient Canine Vision: Accurate Dog Breed Classification with EfficientNet 2

Efficient Canine Vision: Accurate Dog Breed Classification w...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Godwin James, T. Prabahar Poonguzhali, C. Selvakumaran, S. Malathi, G. Kaliappan, S. Venu, Nookala Department of Computer Science and Engineering Sri Sairam Institute of Technology India Department of Electronics and Communication Engineering S.A. Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Electrical and Electronics Engineering Kumaraguru College of Technology Saravanampatti Coimbatore India Madhya Pradesh Gwalior India

ISBN: (纸本)9798350384277

Understanding and classifying dog breeds is a fascinating yet challenging task due to the vast diversity within the canine species. In this project, we present a novel approach to dog breed classification utilizing the state-of-the-art Efficient Net architecture. Leveraging a comprehensive dataset comprising 133 distinct breeds, our method aims to accurately identify and categorize each breed with high precision. Efficient Net's innovative scaling method allows us to strike a balance between model complexity and computational efficiency, enabling robust classification performance even with limited computational resources. Through meticulous preprocessing techniques and data augmentation strategies, we enhance the model's ability to generalize across diverse breed characteristics, minimizing the risk of overfitting. Our experimental results demonstrate the efficacy of the proposed approach, achieving impressive classification accuracy on the challenging dog breed dataset. We conduct extensive evaluations and comparisons with existing methodologies, showcasing the superiority of Efficient Net in handling complex classification tasks with large-scale image datasets. Furthermore, we provide insights into the interpretability of the model's predictions, shedding light on the learned representations and key features contributing to breed classification. This project not only advances the state-of-the-art in dog breed classification but also contributes to our understanding of deep learning techniques applied to animal recognition tasks. In sum up, our work highlights the potential of leveraging advanced neural network architectures like Efficient Net for comprehensive and accurate dog breed classification, paving the way for applications in veterinary medicine, pet care, and animal welfare. © 2024 IEEE.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal Large Language Models 31

StoryLLaVA: Enhancing Visual Storytelling with Multi-Modal L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Yang, Li Xiao, Zhiding Huang, Wenxin Zhong, Xian Hubei Key Laboratory of Big Data Intelligent Analysis and Application School of Computer Science and Information Engineering Hubei University China Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798891761964

The rapid development of multi-modal large language models (MLLMs) has positioned visual storytelling as a crucial area in content creation. However, existing models often struggle to maintain temporal, spatial, and narrative coherence across image sequences and frequently lack the depth and engagement of human-authored stories. To address these challenges, we propose Story with Large Language and Vision Assistant (StoryLLaVA), a novel framework for enhancing visual storytelling. Our approach introduces a Topic-Driven Narrative Optimizer (TDNO) that improves both the training data and MLLM models by integrating image descriptions, topic generation, and GPT-4-based refinements. Furthermore, we employ a preference-based ranked story sampling method that aligns model outputs with human storytelling preferences through positive-negative pairing. These two phases of the framework differ in their training methods: the former uses supervised fine-tuning, while the latter incorporates reinforcement learning with positive and negative sample pairs. Experimental results demonstrate that StoryLLaVA outperforms current models in visual relevance, coherence, and fluency, with LLM-based evaluations confirming the generation of richer and more engaging narratives. The enhanced dataset and model are available at https://***/XxxZzD/StoryLLaVA. © 2025 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Using Wavelet Transformation and XGboost Algorithm

引用

Computers, Materials & Continua 2024年第4期79卷 801-817页

作者： Shahid Naseem Tariq Mahmood Amjad Rehman Khan Umer Farooq Samra Nawazish Faten S.Alamri Tanzila Saba Department of Information Sciences Division of S&TUniversity of EducationLahore54770Pakistan Artificial Intelligence and Data Analytics(AIDA)Lab CCIS Prince Sultan UniversityRiyadh11586Saudi Arabia Faculty of Information Sciences University of EducationVehari CampusVehari61100Pakistan Department of Computer Science University of Engineering and TechnologyTaxila47050Pakistan Department of Mathematical Sciences College of SciencePrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia

Recently,there have been several uses for digital image *** fusion has become a prominent application in the domain of imaging *** create one final image that provesmore informative and helpful compared to the original input images,image fusion merges two or more initial images of the same *** fusion aims to produce,enhance,and transform significant elements of the source images into combined images for the sake of human visual *** fusion is commonly employed for feature extraction in smart robots,clinical imaging,audiovisual camera integration,manufacturing process monitoring,electronic circuit design,advanced device diagnostics,and intelligent assembly line robots,with image quality varying depending on *** research paper presents various methods for merging images in spatial and frequency domains,including a blend of stable and curvelet transformations,everageMax-Min,weighted principal component analysis(PCA),HIS(Hue,Intensity,Saturation),wavelet transform,discrete cosine transform(DCT),dual-tree Complex Wavelet Transform(CWT),and multiple wavelet *** fusion methods integrate data from several source images of an identical target,thereby enhancing information in an extremely efficient *** precisely,in imaging techniques,the depth of field constraint precludes images from focusing on every object,leading to the exclusion of certain *** tackle thess challanges,a very efficient multi-focus wavelet decomposition and recompositionmethod is *** use of these wavelet decomposition and recomposition techniques enables this method to make use of existing optimized wavelet code and filter *** simulated outcomes provide evidence that the suggested approach initially extracts particular characteristics from images in order to accurately reflect the level of clarity portrayed in the original *** study enhances the performance of the eXtreme Gradient Boosting(XGBoos

关键词： Image fusion max-min average CWT XGBoost DCT inclusive innovations spatial and frequency domain

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Alzheimer’s Disease Based on Laplacian Re-Decomposition and XGBoosting

引用

Computer Systems science & engineering 2023年第9期46卷 2773-2795页

作者： Hala Ahmed Hassan Soliman Shaker El-Sappagh Tamer Abuhmed Mohammed Elmogy Information Technology Department Faculty of Computers and InformationMansoura UniversityMansoura35511Egypt Faculty of Computer Science and Engineering Galala UniversitySuez435611Egypt Faculty of Computers and Artificial Intelligence Benha UniversityBanha13518Egypt College of Computing and Informatics Sungkyunkwan UniversitySuwonKorea

The precise diagnosis of Alzheimer’s disease is critical for patient treatment,especially at the early stage,because awareness of the severity and progression risks lets patients take preventative actions before irreversible brain damage *** is possible to gain a holistic view of Alzheimer’s disease staging by combining multiple data modalities,known as image *** this paper,the study proposes the early detection of Alzheimer’s disease using different modalities of Alzheimer’s disease brain ***,the preprocessing was performed on the ***,the data augmentation techniques are used to handle ***,the skull is removed to lead to good *** the second phase,two fusion stages are used:pixel level(early fusion)and feature level(late fusion).We fused magnetic resonance imaging and positron emission tomography images using early fusion(Laplacian Re-Decomposition)and late fusion(Canonical Correlation Analysis).The proposed system used magnetic resonance imaging and positron emission tomography to take advantage of *** resonance imaging system’s primary benefits are providing images with excellent spatial resolution and structural information for specific *** emission tomography images can provide functional information and the metabolisms of particular *** characteristic helps clinicians detect diseases and tumor progression at an early ***,the feature extraction of fused images is extracted using a convolutional neural *** the case of late fusion,the features are extracted first and then ***,the proposed system performs XGB to classify Alzheimer’s *** system’s performance was evaluated using accuracy,specificity,and *** medical data were retrieved in the 2D format of 256×256 *** classifiers were optimized to achieve the final results:for the decision tree,the maximum depth of a tree was *** best number of trees for the random forest was 60;for

关键词： Alzheimer’s disease(AD) machine learning(ML) image fusion Laplacian Re-decomposition(LRD) XGBoosting

来源：评论

学校读者我要写书评

暂无评论

Parasitized Malarial Infected Cell Detection through Variance Scaling Kernel Initializer Conv2D 4

Parasitized Malarial Infected Cell Detection through Varianc...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Devi, M. Shyamala Umanandhini, D. Joshi, Aparna Dontamsetti, Gowtham Shreyas, S. Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Computer Science and Engineering Tamilnadu Chennai India Pimpri Chinchwad College of Engineering Computer Science and Engineering Pune India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Artificial Intelligence and Data Science Tamilnadu Chennai India

ISBN: (纸本)9798350343670

Medical pathologists physically examine Plasmodium falciparum parasites infected blood cells that have been infected through a magnifying glass as part of the traditional diagnostic process, which is time-consuming and liable to mistakes. CNN and advanced technology have recently been used to conduct research on optimizing this procedure to identify orientation and geometrical information from blood sample particle images. With this view, this research recommends Variance Scaling Kernel Initializer Conv2D (VSKIC) Sequential model for predicting the infected malaria cell. The Malaria Cell Images dataset from KAGGLE, which contains 27,558 visuals of plasmodium parasites has been used for execution in the suggested VSKIC model. For the purpose of predicting a malarial cell infection, images are preprocessed and fitted using the VSKIC model. Three convolutional layers merged with max pooling layer, and three dense layers that are weight initialized with variance scaling kernel initializer are used as preprocessing steps on the malaria cell images for the purpose of identifying the presence of affected malarial tissue. The picture files were separated into training and evaluation images, and the training Malaria Cell images were used to evaluate the effectiveness of the VSKIC model along with the standard conV2D paradigms. While comparing the suggested model with the available CNN methods, the execution observations made with Python on a V100 Nvidia GPU workstation using 64 and 250 training intervals demonstrates that the proposed VSKIC model predicts with the higher accuracy of 98.96% and Area under curve of 97.8%. © 2024 IEEE.

关键词： accuracy AUC ConV2D initializer kernel

来源：评论

学校读者我要写书评

暂无评论

A Novel Inception Deep Learning model for Mobile AI Stroke Prediction system: AI Research and Industry Perspectives for Connected Health 6

A Novel Inception Deep Learning model for Mobile AI Stroke P...

引用

6th International Conference on Computing and Informatics, ICCI 2024

作者： Elbagoury, Bassant M. Maskeliuans, Rytis Zaghow, Marwa Kamel, Nabil Faculty of Computer and Information Sciences Ain Shams University Computer Science and Artificial Intelligence Programs Egypt Faculty of Computer Science and Engineering King Salman International University KSIU Egypt Kaunas University of Technology Faculty of Informatics Department of Multimedia Engineering Lithuania Dell Technologies EMEA Egypt

ISBN: (纸本)9798350373875

artificial intelligence technologies for the mobile health and smart hospitals are important, by applying predictive Analytics and Deep Learning algorithms and developing new models. The main objective is applying artificial intelligence methods in the medical field, especially for heart/brain stroke diseases diagnosis and prediction for emergency patients' cases. Thus, to save patients' lives, also through the integration with IoT and wearable technologies, which are integrated with AI and DL algorithms that help to make sense of bio signals predictive analytics such as biomedical sensors processing. and complex diseases predictions and early detection like heart and stroke diseases. Also dealing with EMG sensors for stroke prediction. Moreover, Intelligent Mobile Health based on our previously introduced project of AI smart hospital and Mobile AI stroke prediction system for connected health and stroke emergencies. In this paper, a new deep learning model has been built and tested for Stroke EMG signal prediction by modifying the Inception-v3 architecture and other deep learning models. Also, this paper compares current results of Mobile AI health Inception model with our previous developed Mobile AI stroke engine that depends on hybrid LSTM deep learning for EMG signals prediction. Both models have achieved high accuracies. Moreover, the inception model is more stable and higher average accuracies that reaches 98%. Moreover, AI research and future industry implementations for Generative AI Dell Technologies servers is discussed. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Earthquake Prediction through Hybrid Deep Learning Approach 2

Enhancing Earthquake Prediction through Hybrid Deep Learning...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Kandan, M. Sarkar, Swagata Sharma, Meenakshi Rajeswari, V. Poonkuzhali, P. Srimathi, S. SRM Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computing Technologies Kattankulathur India Sri Sairam Engineering College Artificial Intelligence and Data Science Chennai India Global Group of Institute Department of CSE Amritsar India Panimalar Engineering College Information Technology India R.M.D Engineering College Kavaraipettai India Saveetha School of Engineering SIMATS Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350317558

Earthquakes, one of the greatest natural catastrophes, kill people and harm the economy. Heavy earthquakes and tsunamis may kill thousands and cost millions. Globally, predicting major earthquakes is important. Because earthquake prediction is difficult, researchers employ machine learning to improve forecasts. Many countries have early earthquake warning systems to save lives. Temporal rather than geographical characteristics dominated previous research. A similarity between earthquake and non-seismic signals makes real-time earthquake detection with cellphones or IoT devices problematic. This system may change entity interactions using ML and an IoT network. EEWS metrics are tracked using IoT. However, ML can assess these actions and determine smart city risk reduction and catastrophe management strategies. A deep learning approach for continuous earthquake forecasting utilising past seismic events is proposed. This research predicts earthquakes by position and depth using machine learning and deep learning. ConvLSTM, a Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), extracts important waveform elements to make the classifier reliable in earthquake parameters. © 2024 IEEE.

关键词： Convolutional Neural Network Deep Learning Earthquake LSTM Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A BPNN-Based Method for Regional Competitiveness: Taking the Guangdong-Hong Kong-Macau Greater Bay Area as an Example 2nd

A BPNN-Based Method for Regional Competitiveness: Taking the...

引用

2nd World Conference on Intelligent and 3D Technologies, WCI3DT 2023

作者： Wang, Mini Han Li, Pengsheng Wang, Fengling Zhou, Xiaoshu Wu, Qing Chen, Guoqiang Lin, Zhiyuan Zeng, Peijin Xiao, Qide Beijing Institute of Technology Zhuhai China Faculty of Data Science City University of Macau Macau China Department of Big Data and Artificial Intelligence Zhuhai Institute of Advanced Technology Chinese Academy of Sciences Zhuhai China Hezhou University Hezhou China Gree Polytechnic Zhuhai China Zhuhai Science and Technology Development Promotion Association Zhuhai China

ISBN: (纸本)9789819721436

Guangdong-Hong Kong-Macau Greater Bay Area (GBA) reveals a significant opportunity for self-developing and regional competition since China’s government regards it as one of the most significant developing strategies. However, cities in this area are enhancing comprehensive competitiveness at different levels. This paper proposed a competitiveness evaluation model based on the entropy approach and built a competitiveness measuring and predictive model based on the BPNN machine learning algorithm. The research results illustrate that comprehensive competitiveness is approximately increasing over time, which shows a trend of eastward development. Hong Kong, Guangzhou, Shenzhen, Macau, and Dongguan are the top-5 cities during the three years. On the contrary, Zhongshan is the least competitive city, however, Zhongshan‘s comprehensive competitiveness emerges at the highest increasing rate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimized Ensemble Model Towards Secured Industrial IoT Devices

arXiv

引用

arXiv 2024年

作者： Injadat, MohammadNoor Data Science and Artificial Intelligence Department Faculty of Information Technology Zarqa University Zarqa Jordan

The continued growth in the deployment of Internet-of-Things (IoT) devices has been fueled by the increased connectivity demand, particularly in industrial environments. However, this has led to an increase in the number of network related attacks due to the increased number of potential attack surfaces. Industrial IoT (IIoT) devices are prone to various network related attacks that can have severe consequences on the manufacturing process as well as on the safety of the workers in the manufacturing plant. One promising solution that has emerged in recent years for attack detection is Machine learning (ML). More specifically, ensemble learning models have shown great promise in improving the performance of the underlying ML models. Accordingly, this paper proposes a framework based on the combined use of Bayesian Optimization-Gaussian Process (BO-GP) with an ensemble tree-based learning model to improve the performance of intrusion and attack detection in IIoT environments. The proposed framework's performance is evaluated using the Windows 10 dataset collected by the Cyber Range and IoT labs at University of New South Wales. Experimental results illustrate the improvement in detection accuracy, precision, and F-score when compared to standard tree and ensemble tree models. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning systems

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：