检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Ke Liu Feng Liu Haishuai Wang Ning Ma Jiajun Bu Bo Han Zhejiang Provincial Key Laboratory of Service Robot College of Computer Science Zhejiang University Hangzhou China School of Computing and Information Systems The University of Melbourne Australia Department of Computer Science Hong Kong Baptist University Hong Kong SAR China

Implicit neural representations (INRs) aim to learn a continuous function (i.e., a neural network) to represent an image, where the input and output of the function are pixel coordinates and RGB/Gray values, respectively. However, images tend to consist of many objects whose colors are not perfectly consistent, resulting in the challenge that image is actually a discontinuous piecewise function and cannot be well estimated by a continuous function. In this paper, we empirically investigate that if a neural network is enforced to fit a discontinuous piecewise function to reach a fixed small error, the time costs will increase exponentially with respect to the boundaries in the spatial domain of the target signal. We name this phenomenon the exponential-increase hypothesis. Under the exponential-increase hypothesis, learning INRs for images with many objects will converge very slowly. To address this issue, we first prove that partitioning a complex signal into several sub-regions and utilizing piecewise INRs to fit that signal can significantly speed up the convergence. Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs. In both cases, we partition an image into different sub-regions and dedicate smaller networks for each part. In addition, we further propose two partition rules based on regular grids and semantic segmentation maps, respectively. Extensive experiments validate the effectiveness of the proposed partitioning methods in terms of learning INR for a single image (ordinary learning framework) and the learning-to-learn framework. Code is released here.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyclone Center Identification in Radar Images through Deep Learning and Match Recognition

Enhancing Cyclone Center Identification in Radar Images thro...

引用

International Conference on computing and Networking Technology (ICCNT)

作者： Thirumurugan Shanmugam Chirag Chandrashekar Maheswari Subburaj Arun Kumar Sivaraman Ajmery Sultana Senthil Kumar Thangavel College of Computing and Information Sciences University of Technology and Applied Sciences Suhar Oman School of Computer Science and Engineering Vellore Institute of Technology Chennai India Digital Engineering Solution Center Photon Interactive Inc Ontario Canada School of Computer Science and Technology Algoma University Brampton Ontario Canada Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This research focuses on improving the identification of cyclone centers using deep learning and match recognition applied to radar images. Accurately pinpointing the cyclone’s center is vital for predicting its intensity and trajectory. However, challenges persist in automatically locating the center due to the diverse nature of cyclone morphology and structure. To address this, the deep convolutional network’s capability is leveraged to capture various structural features in images by proposing two-step approach for cyclone center localization. Initially, a pre-trained EfficientDet model is employed using transfer learning to obtain weights. Subsequently, these weights, along with the data, are utilized in a deep learning model to provide precise coordinates of the cyclone center in the respective image. The effectiveness of existing deep learning and machine learning models show that the cyclone prediction systems have an accuracy ranging from $86 \%$ to $92 \%$ or better, and cyclone eye detection accuracy surpassing 87%. Experiment outcomes indicate that the proposed methodology outperforms conventional methods and existing works, showcasing its potential for enhancing cyclone monitoring and forecasting.

关键词： Deep learning YOLO Training Adaptation models Accuracy Machine learning algorithms Transfer learning Radar Radar imaging Cyclones

来源：评论

学校读者我要写书评

暂无评论

Crude Palm Oil Price Forecasting Based on ECoS-MARS: in Data science Models

Crude Palm Oil Price Forecasting Based on ECoS-MARS: in Data...

引用

International Conference on Cyber and IT Service Management (CITSM)

作者： Al-Khowarizmi Fitria Wulandari Ramlan Syahril Efendi Arif Ridho Lubis Ferdy Riza Amrullah Yoshida Sary Department of Information Technology Universitas Muhammadiyah Sumatera Utara Medan Indonesia College of Engineering and Informatics National University ireland Galway Ireland Department of Computer Science Universitas Sumatera Utara Medan Indonesia Department of Computer Engineering & Informatics Politeknik Negeri Medan Medan Indonesia Department of Information System Universitas Muhammadiyah Sumatera Utara Medan Indonesia

The crude palm oil (CPO) industry is highly competitive due to fluctuating and unpredictable prices. To accurately predict future CPO prices, a forecasting technique is necessary. This can be achieved through various regression techniques and data mining approaches. This paper proposes a Multivariate Adaptive Regression Splines (MARS) model, which utilizes the ECoS machine learning algorithm to obtain optimal forecasting values. This research mainly focuses on forecasting CPO prices using the ECoS-MARS approach. The functional basis (BF) validation has yielded an accuracy of 0.0532%. Furthermore, validation has been conducted to achieve accurate forecasting values, resulting in an accuracy of 0.11714%. The best parameter combination for this forecasting model consists of a learning rate of 0.6 for both learning rates 1 and 2, a sensitivity threshold of 0.3, and an error threshold of 0.05.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Navigating the Blockchain Landscape: Role, Challenges, Risks, and Issues in the Banking and Finance Sector

Navigating the Blockchain Landscape: Role, Challenges, Risks...

引用

Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), IEEE International Conference on

作者： Rajiv Kumar Manisha Saini Ajeet Kumar Vishwakarm Ruby Faizan Divya Rawat Deepak Negi Department of Computer Science and Engineering Shivalik College of Engineering Dehradun Uttarakhand Uttaranchal School of Computing Sciences Uttaranchal University Dehradun Uttarakhand Department of Computer Science and Engineering Dev Bhoomi Uttarakhand University Dehradun Amrapali Institutes of Technology and Sciences (AITS) Haldwani UK India

Due to its potential to fundamentally alter a number of sectors of the financial services industry, blockchain technology has been attracting a lot of attention. However, several obstacles prevent its widespread adoption and application. Scalability is one of the biggest issues with blockchain technology. Traditional block chains, like those used by Bitcoin and Ethereum, have capacity and processing speed restrictions. For many large-scale applications, their low transactional capacity per second is insufficient. Their modest transactional throughput per second is insufficient for many large-scale applications. The complexity of blockchain protocols makes it more difficult for developers who may not be familiar with them to create blockchain apps because they need specialized knowledge and abilities. Considering the autonomous and international nature of blockchain networks, it can be difficult for organizations to traverse complex legal frameworks and maintain compliance with existing legislation. The blockchain business needs standardized frameworks and protocols, which causes complexity and restricts compatibility. Cryptocurrency-related negative instances including fraud, scams, and unlawful activity have stoked fears and stoked skepticism about the technology. Financial institutions, technology providers, regulators, and standardization bodies must work together to address these issues. To get over these barriers and realize the full potential of blockchain technology in the financial services industry, continued research and development activities are essential, as well as regulatory certainty. In this article, we conducted a methodical analysis of the blockchain technology, its use in the financial and economic sector, the current situation, and the difficulties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

New Recommender System for Online Courses Using Knowledge Graph Modeling

New Recommender System for Online Courses Using Knowledge Gr...

引用

International Conference on computer Communication and informatics (ICCCI)

作者： S. Bhaskaran N. Bharathiraja K Pradeepa M Vinoth Kumar N V Ravindhar Raja Marappan School of Computing SASTRA Deemed University Thanjavur India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering St. Michael College of Engineering and Technology India Department of Computer Science and Engineering Dmi-St.Eugene University Great North Road Chibombo District Zambia Department of Computer Science and Engineering Saveetha Engineering College(Autonomous) Chennai

Nowadays, customers can get recommendations for products and services that fit their anticipated needs in the context of a large body of data. Advances in this area provide novel concepts and enable technology for use in e-learning settings. The existing recommendation systems typically focus on improving the item side, but they don’t consider the user characteristics in the recommendation. Thus, they’re ineffective and hence not a good fit for a virtual classroom setting. This research focuses on applying semantics-based knowledge graph modeling with collaborative filtering (CF) to solve these issues. This proposed framework applies the users’ static features to aid in cold start issues for potential new users. The proposed framework significantly outperforms the existing models and helps maintain acceptable performance using better user-item interactions.

关键词： Electronic learning Computational modeling Collaborative filtering Knowledge graphs informatics Recommender systems

来源：评论

学校读者我要写书评

暂无评论

MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL

arXiv

引用

arXiv 2023年

作者： Ni, Fei Hao, Jianye Mu, Yao Yuan, Yifu Zheng, Yan Wang, Bin Liang, Zhixuan College of Intelligence and Computing Tianjin University Tianjin China Huawei Noah’s Ark Lab Beijing China Department of Computer Science The University of Hong Kong Hong Kong

Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning (RL). However, these works mostly lack the generalization ability across tasks with reward or dynamics change. To tackle this challenge, in this paper we propose a task-oriented conditioned diffusion planner for offline meta-RL (MetaDiffuser), which considers the generalization problem as conditional trajectory generation task with contextual representation. The key is to learn a context conditioned diffusion model which can generate task-oriented trajectories for planning across diverse tasks. To enhance the dynamics consistency of the generated trajectories while encouraging trajectories to achieve high returns, we further design a dual-guided module in the sampling process of the diffusion model. The proposed framework enjoys the robustness to the quality of collected warm-start data from the testing task and the flexibility to incorporate with different task representation method. The experiment results on MuJoCo benchmarks show that MetaDiffuser outperforms other strong offline meta-RL baselines, demonstrating the outstanding conditional generation ability of diffusion architecture. More visualization results are released on project page. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Clinical Decision Support System for Diabetic Patients by Predicting Type 2 Diabetes Using Machine Learning Algorithms

引用

Journal of Healthcare Engineering 2023年第1期2023卷

作者： Islam, Rakibul Sultana, Azrin Tuhin, Md. Nuruzzaman Saikat, Md. Sazzad Hossain Islam, Mohammad Rashedul Department of Computer Science American International University-Bangladesh Dhaka1229 Bangladesh Department of Research & Training Monitoring Bangladesh College of Physicians and Surgeons Dhaka1212 Bangladesh Department of Health Informatics Bangladesh University of Health Sciences Dhaka1216 Bangladesh

Diabetes is one of the most serious chronic diseases that result in high blood sugar levels. Early prediction can significantly diminish the potential jeopardy and severity of diabetes. In this study, different machine learning (ML) algorithms were applied to predict whether an unknown sample had diabetes or not. However, the main significance of this research was to provide a clinical decision support system (CDSS) by predicting type 2 diabetes using different ML algorithms. For the research purpose, the publicly available Pima Indian Diabetes (PID) dataset was used. Data preprocessing, K-fold cross-validation, hyperparameter tuning, and various ML classifiers such as K-nearest neighbor (KNN), decision tree (DT), random forest (RF), Naïve Bayes (NB), support vector machine (SVM), and histogram-based gradient boosting (HBGB) were used. Several scaling methods were also used to improve the accuracy of the result. For further research, a rule-based approach was used to escalate the effectiveness of the system. After that, the accuracy of DT and HBGB was above 90%. Based on this result, the CDSS was implemented where users can give the required input parameters through a web-based user interface to get decision support with some analytical results for the individual patient. The CDSS, which was implemented, will be beneficial for physicians and patients to make decisions about diabetes diagnosis and offer real-time analysis-based suggestions to improve medical quality. For future work, if daily data of a diabetic patient can be put together, then a better clinical support system can be implemented for daily decision support for patients worldwide. © 2023 Rakibul Islam et al.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Autonomous Multi-Objective Optimization Using Large Language Model

arXiv

引用

arXiv 2024年

作者： Huang, Yuxiao Wu, Shenghao Zhang, Wenjie Wu, Jibin Feng, Liang Tan, Kay Chen The Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Elctronics Engineering The Hong Kong Polytechnic University Hong Kong The Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University Chongqing400044 China

Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evolutionary algorithms (EAs), though effective, often rely on domain-specific expertise and iterative fine-tuning, hindering adaptability to unseen MOPs. In recent years, the advent of Large Language Models (LLMs) has revolutionized software engineering by enabling the autonomous generation and refinement of programs. Leveraging this breakthrough, we propose a new LLM-based framework that autonomously designs EA operators for solving MOPs. The proposed framework includes a robust testing module to refine the generated EA operator through error-driven dialogue with LLMs, a dynamic selection strategy along with informative prompting-based crossover and mutation to fit textual optimization pipeline. Our approach facilitates the design of EA operators without the extensive demands for expert intervention, thereby speeding up the innovation of EA operators. Empirical studies across various MOP categories validate the robustness and superior performance of our proposed framework. © 2024, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

A New Phylogeny-Driven Random Forest-Based Classification Approach for Functional Metagenomics

A New Phylogeny-Driven Random Forest-Based Classification Ap...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jyotsna Talreja Wassan Haiying Wang Huiru Zheng School of Computing Ulster University Belfast United Kingdom Department of Computer Science Maitreyi College University of Delhi INDIA

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Classifying microbial genes into their functional repertoire is an important task for metagenomic studies, where the research community is trying to develop Machine Learning (ML) based methods to achieve good classification performance. Random Forest (RF) has been proposed as one of the most favorable methods for such supervised analysis when applied over the abundance profiles of microbial genes mapping them to functional phenotypes. To further explore and make optimization in the existing RF model (based on the biological relationships between microbial features), a new classification method based on RF as guided by the evolutionary ancestry of microbial phylogeny, i.e. Phylogeny-RF, has been developed in this paper. This method facilitates to capture the effects of phylogenetic relatedness in a ML classifier itself. Closely related microbes by phylogeny are highly correlated and tend to have similar genetic and phenotypic traits. Such microbes behave similarly; and hence tend to be selected together or one of these could be dropped from the analysis, to make the ML process better. The proposed Phylogeny-RF algorithm has been compared with state-of-the-art classification methods including RF and the phylogeny-aware method of MetaPhyl, using 2 real-world 16S rRNA metagenomic data sets. It is observed that the proposed method performed better than the other phylogeny-driven benchmarks. For example, Phylogeny-RF attained a high AUC of 0.949 over soil microbiomes in comparison to other benchmarks.

关键词： Microorganisms Forestry Benchmark testing Soil Genetics Phylogeny Task analysis

来源：评论

学校读者我要写书评

暂无评论

Enhanced Investment Decision Making with a Reinforcement Learning-Based Multi-Agent Portfolio Management System

Enhanced Investment Decision Making with a Reinforcement Lea...

引用

Data science and Network Security (ICDSNS), International Conference on

作者： Kottooru Saaketh Raja Ram Selvaganapathy M Nandhini I Tamilselvi M Kalaivani M Natarajan B Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Amrita School of Computing Chennai India Department of Electroncis and Communication Engineering C. K. College of Engineering and Technology Cuddalore India Department of Electron cis and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Computer Science and Engineering Roever Engineering College Perambalur Tamilnadu India Department of Electron cis and Communication Engineering K. Ramakrishnan College of Engineering Trichy India School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamilnadu India

ISBN: (数字)9798350373110

ISBN: (纸本)9798350373127

The portfolio management system using traditional machine learning approaches struggles with data quality and interpretability of models, while needing to adapt to constantly evolving market dynamics. The Reinforcement Learning (RL) algorithms have proven to be a promising approach in handling diverse datasets with unpredictable performance. The proposed approach utilizes multiple RL alogrithms such as Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimisation (PPO), and Advantage Actor-Critic (A2C) to improve investment decision-making, historical data from the Yahoo Finance Dataset. This system incorporates three well-established reinforcement learning algorithms to dynamically adjust portfolio allocations. The A2C algorithm combines actor-critic techniques to optimize long-term portfolio performance, while the PPO algorithm maintains a balance between exploration and exploitation, enhancing returns stability. The proposed DDPG algorithm utilizes a deep neural network to determine the optimal action-value function, enabling informed investment decisions. Tested across various assets in the Yahoo Finance Dataset, it consistently outperforms traditional portfolio management methods. This flexible system can be tailored to suit different investment objectives and risk tolerances.

关键词： Heuristic algorithms Decision making Finance Reinforcement learning Network security Stability analysis Resource management Portfolios Optimization Investment

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：