检索结果-内蒙古大学图书馆

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Kasarapu Ramani Maddireddy Srilekha Reddy Kelavathi Bhavani Syed Feeza Vellampalli Sai Bavesh Dept. of Data Science Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupati India Department of CSSE Sree Vidyanikethan Engineering College Tirupati India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

In recent years, non-periodic rainfall has increased globally. The importance of accurate rainfall prediction model is increased in order to reduce the losses due to floods and drought. Rainfall prediction plays a crucial role in decision-making, flood and drought risk assessment and management. In agriculture, it guides many farmers in optimizing crop planting schedules and irrigation. It ensures better yields and reduces losses from droughts and floods. Accurate rainfall prediction benefits us in effective water resource management and energy sector planning. In India, the rainfall varies rapidly due to the vast geography. There are many factors which effects rainfall like distance from the sea, seasons, the presence of mountains, prevailing winds and precipitation. This research work mainly focuses on developing an efficient ensemble-based Machine Learning Techniques such as Extreme Gradient boosting algorithm (XG Boost) and Logistic Regression (LR) for predicting rainfall in different regions of India using satellite data and comparing results with the deep learning algorithms such as Convolutional Neural Network (CNN), Multiple Layer Perceptron (MLP), Long Short-Term Memory (LSTM), and Radial Basis Function Network (RBF). The aim of this paper is to overcome the drawbacks of existing systems and build improved prediction model with accuracy more than 90% in order to enhance water resource management, early warning systems, improved urban planning, agriculture, and climate change studies.

关键词： Deep learning Rain Accuracy Satellites Machine learning algorithms Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-Based Pothole Detection for Autonomous Driving Safety

YOLOv8-Based Pothole Detection for Autonomous Driving Safety

引用

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Poongothai P Sabareswari T C R Ramesh Veeramalai Sankaradass R. Ponnusamy Dept of Mathematics Chennai Institute of Technology Tamil Nadu India Dept of Electronics and Communication Engineering Chennai Institute of Technology Tamil Nadu India Dept. of Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India Dept of Computer Science and Engineering Chennai Institute of Technology Tamil Nadu India Dept. of Artificial Intelligence and Data Science Madha Engineering College Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Undeniably, autonomous vehicles are the most dramatic evolution of transportation yet. They offer new safety, efficiency, and convenience levels that have never been seen before. Still, some natural and unexpected conditions continually strike a blow against the safety of self-driving systems, such as potholes on roads. This paper introduces a new, cloud-based safety solution for autonomous vehicles through artificial intelligence and implementation with the YOLOv8 object detection model, coupled with the deep learning platform Weights & Biases, or wandb. As the real-time pothole-detecting system is developed, issues related to navigation appear while increasing the safety level. This work adopts the YOLOv8 object detection model in the use case due to its higher accuracy and much faster object detection rate. This can classify and predict the object boundaries of a single network, thus being a good fit for quick and accurate detection. Upgrades will be made in sync with new conditions in roads and types of potholes as the right solution gains ready to change the future of transportation about autonomous transportation, paving the path for safer and more reliable self-driving vehicles. It directly addresses the acute challenge of pothole-related hazards. It builds the way to an even safer and more efficient future for autonomous mobility, thus showing tremendous potential for transforming advanced AI technologies.

关键词： Accuracy Navigation Roads Transportation Object detection Real-time systems Safety Reliability Artificial intelligence Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Integrating Spatial and Frequency Information for Under-Display Camera Image Restoration

arXiv

引用

arXiv 2025年

作者： Ahn, Kyusu Kim, Jinpyo Park, Chanwoo Kim, JiSoo Lee, Jaejin Dept. of Data Science Seoul National University Seoul Korea Republic of Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of Research Center Samsung Display Co. Ltd. Yongin Korea Republic of

Under-Display Camera (UDC) houses a digital camera lens under a display panel. However, UDC introduces complex degradations such as noise, blur, decrease in transmittance, and flare. Despite the remarkable progress, previous research on UDC mainly focuses on eliminating diffraction in the spatial domain and rarely explores its potential in the frequency domain. It is essential to consider both the spatial and frequency domains effectively. For example, degradations, such as noise and blur, can be addressed by local information (e.g., CNN kernels in the spatial domain). At the same time, tackling flares may require leveraging global information (e.g., the frequency domain). In this paper, we revisit the UDC degradations in the Fourier space and figure out intrinsic frequency priors that imply the presence of the flares. Based on this observation, we propose a novel multi-level DNN architecture called SFIM. It efficiently restores UDC-distorted images by integrating local and global (the collective contribution of all points in the image) information. The architecture exploits CNNs to capture local information and FFT-based models to capture global information. SFIM comprises a spatial domain block (SDB), a Frequency Domain Block (FDB), and an Attention-based Multi-level Integration Block (AMIB). Specifically, SDB focuses more on detailed textures such as noise and blur, FDB emphasizes irregular texture loss in extensive areas such as flare, and AMIB enables effective cross-domain interaction. SFIM’s superior performance over state-of-the-art approaches is demonstrated through rigorous quantitative and qualitative assessments across three UDC benchmarks. © 2025, CC BY-NC-SA.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Silent Skies: Machine Learning for Aircraft Noise Reduction Strategies

Silent Skies: Machine Learning for Aircraft Noise Reduction ...

引用

Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications (COSMIC), International Conference on

作者： Nageshwar Singh Kunal Pawar Syed Afnan Nashath Hurthivk Ramakrishna N Hegde Prashanth Kannadaguli dept. Aeronautical engineering Srinivas institute of technology Mangalore India Senior Data Science Trainer Dhaarini Academy of Technical Education Bengaluru India

ISBN: (数字)9798331517892

ISBN: (纸本)9798331517908

Aircraft noise pollution poses a significant challenge to communities near airports, impacting their health, well-being, and overall quality of life. Traditional noise mitigation approaches have predominantly focused on physical modifications to aircraft design and flight procedures. However, the emergence of machine learning (ML) techniques offers promising avenues for innovative noise reduction strategies. This paper introduces “Silent Skies,” a groundbreaking framework utilizing machine learning algorithms to address aircraft noise. Silent Skies integrates diverse data sources, including aircraft telemetry, weather conditions, airport infrastructure, and community feedback, to train predictive models for accurately estimating noise levels. These models inform decision-making processes, optimizing flight paths, engine settings, and airport operations to minimize noise emissions. Key components of the Silent Skies framework include data preprocessing techniques for handling heterogeneous and noisy data, feature engineering methods for extracting relevant information from raw data sources, and ensemble learning approaches to enhance prediction accuracy. Additionally, the framework incorporates real-time monitoring and feedback mechanisms to continually refine noise reduction strategies in response to evolving conditions. To demonstrate the effectiveness of Silent Skies, we present case studies conducted at major airports, showcasing significant reductions in noise pollution while maintaining operational efficiency. These case studies underscore the framework's adaptability across diverse airport configurations, airspace constraints, and environmental contexts. In summary, Silent Skies represents a significant advancement in aircraft noise mitigation, offering scalable and adaptive solutions that prioritize community well-being without compromising aviation safety or efficiency. Through the integration of machine learning techniques, airports can transition towards q

关键词： Adaptation models Accuracy Atmospheric modeling Noise Noise reduction Machine learning Airports Feature extraction Aircraft Noise level

来源：评论

学校读者我要写书评

暂无评论

A Big data Analytic and IoT-Based Approach for Addressing Water Scarcity in Jordan

A Big Data Analytic and IoT-Based Approach for Addressing Wa...

引用

computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Abdelraouf Ishtaiwi Nuha El-Khalili May Alnashashibi Mohammad Abu Arqoub Dept. of Data Science and Artificial Intelligence University of Petra Amman Jordan Department of Software Engineering University of Petra Amman Jordan Department of Computer Science University of Petra Amman Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Water scarcity critically threatens agricultural sus-tainability in Jordan, necessitating innovative technological solutions. This study presents a comprehensive framework that integrates Internet of Things (IoT) sensors with Big data Analytics to optimize water usage in agriculture. Employing a multi-stage approach, we conducted real-time data acquisition from diverse farms, processed the data using clustering algorithms, and implemented intelligent decision-making systems. Our analysis focused on key parameters such as soil moisture, temperature, rainfall, and wind speed across various farming locations. The methodology encompassed extensive field data collection, advanced analytics, and the deployment of smart irrigation systems. Results demonstrated a significant 25 % reduction in water consumption while maintaining optimal crop yields. Additionally, clustering identified three distinct farm categories, each requiring tailored water management strategies. This research contributes to the field of smart agriculture by providing practical, scalable solutions for regions facing severe water scarcity. The findings highlight the potential of advanced technologies to enhance agricultural sustainability and address critical water management challenges.

关键词： Temperature sensors Smart agriculture Irrigation Wind speed Soil moisture Big data Real-time systems Internet of Things Sustainable development Water resources

来源：评论

学校读者我要写书评

暂无评论

PATIENT-ADAPTIVE AND LEARNED MRI data UNDERSAMPLING USING NEIGHBORHOOD CLUSTERING

arXiv

引用

arXiv 2023年

作者： Gautam, Siddhant Li, Angqi Ravishankar, Saiprasad Dept. of Computational Mathematics Science and Engineering Michigan State University East LansingMI United States Dept. of Biomedical Engineering Michigan State University East LansingMI United States

There has been much recent interest in adapting undersampled trajectories in MRI based on training data. In this work, we propose a novel patient-adaptive MRI sampling algorithm based on grouping scans within a training set. Scan-adaptive sampling patterns are optimized together with an image reconstruction network for the training scans. The training optimization alternates between determining the best sampling pattern for each scan (based on a greedy search or iterative coordinate descent (ICD)) and training a reconstructor across the dataset. The eventual scan-adaptive sampling patterns on the training set are used as labels to predict sampling design using nearest neighbor search at test time. The proposed algorithm is applied to the fastMRI knee multicoil dataset and demonstrates improved performance over several baselines. © 2023, CC BY.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Segmentation with Advanced Superpixel Techniques in Conjunction with Deep Learning Methods

Optimizing Brain Tumor Segmentation with Advanced Superpixel...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Chythanya, Kanegonda Ravi Aruna, S. Karuppaiah, Jayakumar Arul, S. Benjamin Kumar Pareek, Piyush Sr University School of Computer Science & Artificial Intelligence Warangal India Srmist Dept. of Computational Intelligence Chennai India KIT- Kalaignarkarunanidhi Institute of Technology Department of Biomedical Engineering Coimbatore India School of Engineering and Technology Jeppiaar University Chennai India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

Brain tumor segmentation in medical imaging is crucial for precise diagnosis and treatment planning. To address these issues, our research leverages deep learning techniques and introduces an innovative approach that combines various key components. Our methodology includes preprocessing, superpixel segmentation, feature extraction, and the use of a Convolutional Neural Network (CNN) to achieve precise brain tumor segmentation. This approach is driven by the necessity for improved accuracy and efficiency, especially with diverse clinical data and tumor types, like the challenging BraTS 2018 dataset, consisting of 1070 T1W-CE MRI images. This approach using metrics such as the Dice score, sensitivity, and specificity, which demonstrate the superior performance of our superpixel model in brain tumor segmentation. This proposed method yields exceptional results, with a Dice score of 97.06%, sensitivity of 99.05%, and specificity of 99.83%, highlighting its accuracy and effectiveness in tumor segmentation when compared to existing methods such as UNet, Kapur entropy, and rough set theory. This research significantly advances the state of the art and offers great promise for enhancing medical image analysis in this critical field. © 2023 IEEE.

关键词： Brain tumor Convolutional Neural Network Deep Learning Superpixel technique Tumor segmentation

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Image Identify and Categorization using Artificial Neural Networks

Lung Cancer Image Identify and Categorization using Artifici...

引用

computational Intelligence for Green and Sustainable Technologies (ICCIGST), International Conference on

作者： Ediga Lingappa D Jareena Begum Priya Pachouri Kuderu Rashmi Thokala Tharuna Varalakshmi Anoop Kumar Dept of Computer Science and Engineering Mallareddy College of Engineering Maisammaguda Secunderabad TS INDIA Dept. of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Dept of Cyber Security Malla Reddy University Hyderabad India

ISBN: (数字)9798350381887

ISBN: (纸本)9798350381894

Lung cancer that is made up of small cells is called small cell lung cancer (SCLC). Smoking tobacco in any form-cigarettes, cigars, or pipes-is by far the most significant risk factor for developing lung cancer, though it is only one of many. Cancer of the lungs is known as lung cancer. When cells in the body multiply uncontrollably, cancer develops. If cancer cells enter the lymphatic system or the bloodstream, they can travel to other organs and spread the disease. Cheap and fast cancer diagnostics could save millions. Latestage cancer treatment is hard. Lung cancer is diagnosed non-invasively. Biopsy requires careful ANN architecture selection. This study proposes a diagnosis ANN model. ANN research is “hot” in cardiology, cancer, and radiology. Medical research uses ANNs. Lung cancer diagnosis was tested. MR images assess lung health for the neural network. MATLAB created ANNs and processed images. Training data was extracted from MR images using Harlick texture features. MATLAB made ANNs. Elman Network exceeds ANNs with 90.30 %. Lung cancer can develop. MRIs detect lung cancer. MRIs show lung development. Many lung tumour detection research use machine learning and deep learning. MRI algorithms swiftly detect lung malignancies, improving patient therapy. Radiologists use these forecasts. The study evaluates a self-defined ANN for lung tumour identification. The radiologist needs time to find and remove the cancer from the MR. Technology improves performance and segmentation. Machines always predict and detect. Neural networks outperformed SVM, Random forest, regression, and others.

关键词： Training Machine learning algorithms Magnetic resonance imaging Lung cancer Lung Artificial neural networks Feature extraction MATLAB Tumors Testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Flutter App Development: Addressing Configuration and Compatibility Bugs Using Large Language Models

Enhancing Flutter App Development: Addressing Configuration ...

引用

International Research Conference on Smart Computing and Systems engineering (SCSE)

作者： Supun Rajaguru Lohara Chathumini Samantha Kumara Ashansa Wijerathna Dept. of Computing and Information Systems Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka Dept. of Data Science Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka Dept. of Software Engineering Sabaragamuwa University of Sri Lanka Belihuloya Sri Lanka

ISBN: (数字)9798331523268

ISBN: (纸本)9798331523275

In today’s world, there are cross-platform frameworks are widely available, The frameworks like Flutter, allow the developer to develop an app from a single codebase. But there are some major issues like debugging and compatibility finding in Flutter framework. These issues lead to prolonged debugging and lesser app reliability. The proposed model will lead to overcome those mentioned challenges. The proposed model used advanced LLMs including GPT-4o, Claude Sonnet 3.5, and Gemini 2.0 Flash, combined with RAG capabilities. The data was collected from multiple sources like Stack Overflow, GitHub, and Flutter documentation. The dataset was cleaned and preprocessed by removing low-scoring answers, filtering incomplete questions, and applying text sanitization techniques to ensure structured and relevant inputs for analysis. A fixed set of prompt templates to 350 Stack Overflow questions across all the LLMs were applied to commence the evaluation process. The 25 most important questions were identified through verification via cosine similarity and precision correction between its responses. It was able to determine the two models’ efficacy in finding configuration bugs and addressing those bugs. The current work involves integrating an RAG pipeline and using a vector database for better retrieval and response generation. Early evidence hints at the enhanced accuracy/precision of an RAG-enhanced LLM when that LLM is a standalone model for better Flutter configuration. In conclusion this proposed model presents a modular framework to integrate RAG-enhanced LLMs for bug detection and fixing. The framework requires much lesser debugging efforts along with more reliability of the app. Additionally, it can also adopt the fast-evolving Flutter framework. By filling a significant gap in cross-platform development literature, it helps advance AI-assisted debugging and improve the development workflows of Flutter apps.

关键词： Large language models Computer bugs Pipelines Debugging Documentation Vectors Software Software reliability Modeling Software development management

来源：评论

学校读者我要写书评

暂无评论

PrecisionStroke: Optimized Stroke Risk Prediction through Advanced Hyperparameter Tuning and Machine Learning Techniques

PrecisionStroke: Optimized Stroke Risk Prediction through Ad...

引用

Computer Applications (ICCA), IEEE Conference on

作者： Mithila Arman Saroar Jahan Shuba Md. Mahfuzur Rhaman Sumaya Binte Zilani Choya Md Ashfaqul Azam Chowdhury Mahamudul Islam Intezab Alam Sheikh Md. Khurshid Jahan Dept. of CSE BRAC University Dhaka Bangladesh Dept. of MSCQM Lamar University Texas USA Dept. of Computational Data Science George Mason University Fairfax Virginia USA Dept. of IST George Mason University Fairfax Virginia USA Dept. of CSE Ahsanullah University of Science & Technology Dhaka Bangladesh Anwer Khan Modern Medical College Hospital Dhaka Bangladesh Dhaka Residential Model College Dhaka Bangladesh Dept. of ECE North South University Dhaka Bangladesh

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

Stroke prediction is a challenging problem in the healthcare domain, especially due to high class imbalance in datasets where data about stroke cases is a very small portion. In this study we develop a machine learning based framework for stroke prediction that tackles through powerful data preprocessing methods, such as Synthetic Minority Oversampling Technique (SMOTE) for balancing the classes. (Situated within the entire framework of a comparative evaluation of the Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), CatBoost, XGBoost, LightGBM, and Multi-Layer Perceptron (MLP) and TabNet machine learning classifiers as per unique designs. In conclusion, the Random Forest classifier proved to be the best performing model with an accuracy of 99.38%, followed closely by LightGBM and CatBoost. A detailed analysis including KP song metrics including precision, F1 score, and confusion matrices were carried out to ensure thorough evaluation. The study also emphasizes the importance of explainable AI tools which improve the explainability of predictions. This framework shows that machine learning has the potential to assist with early detection of stroke and may ultimately be integrated into clinical decision-making systems.

关键词： Support vector machines Measurement Accuracy Explainable AI Decision making data preprocessing Medical services Nearest neighbor methods Random forests Tuning

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：