检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Priya, S. Padma Pavalarajan, S. Abarna, P.S. Manjula devi, C. Abinaya, B. Sukaina, S. Department of Computer Science and Business Systems PSNA College of Engineering and Technology Dindigul India Department of Information Technology Velammal college of Engineering and Technology Madurai India

ISBN: (纸本)9798331522667

An Internet of Things based smart irrigation system for terrace plants is a cutting-edge solution designed to automate and optimize the watering process, ensuring efficient use of water and promoting healthier plant growthSmart irrigation system may vary from field with crops of same variety to terrace plantation with plants of different varieties. As the water requirement may vary based on plant type, environmental condition, growth stage, it is intelligent to provide varying water supply. This Smart irrigation system employs soil moisture to monitor the water content of the terrace garden in real time. Some variety of plants may require minimum quantity of water. The sensors continuously collect data and send it to a central IoT platform or a cloud-based server, where intelligent algorithms analyse the data and determine the precise amount of water needed by the plants. Based on this analysis, the system automatically activates the irrigation mechanism whether it's a drip system, sprinklers, or any other appropriate watering method only when required, thus preventing water wastage and avoiding overwatering or underwatering. © 2025 IEEE.

关键词： Sprinkler systems (irrigation)

来源：评论

学校读者我要写书评

暂无评论

An effective object detection via BS2ResNet and LTK-Bi-LSTM

引用

Multimedia Tools and Applications 2025年 1-20页

作者： V, Arulalan V, Premanand Kumar, Dhananjay Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering Vellore Institute Technology Chennai Campus Tamil Nadu Chennai India Department of Information Technology Anna University MIT Campus Tamil Nadu Chennai India

Video analytics faces complex challenges in object detection and classification. Deep learning based approaches have achieved remarkable success in past decade. However, existing object identification models that utilize backbone’s core features still present challenges due to their lack of semantic information. To address these issues, a novel object detection and classification framework utilizing Batch normalization and Softswish activation adapted ResNet (BS2ResNet) and Logistic Tanh Kaiming Bi-directional Long Short Term Memory (LTK-Bi-LSTM) techniques was proposed. The framework employs frame conversion, noise removal, and contrast elevation during frame pre-processing, followed by background subtraction using the Supreme Distance-centered Fuzzy C-Means (SD-FCM) clustering algorithm, and edge detection using the Hyperbolic Tangent Kernel Canny Edge Detector (HTKCED). BS2ResNet is then used for object detection, and features are extracted and passed to the LTK-Bi-LSTM neural network for object classification. The proposed system was found to improve object detection and classification accuracy, outperforming existing techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Federated Knowledge Distillation With 3D Transformer Adaptation for Weakly Labeled Multi-Organ Medical Image Segmentation

引用

IEEE Access 2025年 13卷 83619-83642页

作者： AlZubi, Tareq Mahmod Mukhtar, Hamza Al-Balqa Applied University Prince Abdullah bin Ghazi Faculty of Information and Communication Technology Department of Computer Science As-Salt 19117 Jordan Department of Computer Science University of Engineering and Technology Lahore (UET Lahore) Lahore 39161 Pakistan Al-Khawarizmi Institute of Computer Science UET Lahore Intelligent Criminology Laboratory National Center of Artificial Intelligence Lahore 39161 Pakistan

The increasing reliance on medical image segmentation for disease diagnosis, treatment planning, and therapeutic assessment has highlighted the need for robust and generalized deep learning (DL)-based segmentation frameworks. However, existing models often suffer from task-specific limitations, catastrophic forgetting, and poor scalability due to their dependency on narrowly annotated datasets. This creates a significant gap in developing unified, multi-organ segmentation systems that leverage distributed and partially labeled datasets across diverse clinical institutions. To address these challenges, we propose the Federated 3D Knowledge Distillation Network (Fed3D-KDNet), a hybrid federated learning (FL) framework that integrates both global and local knowledge distillation mechanisms. Our model adapts the Segment Anything Model (SAM) for volumetric medical imaging by introducing architectural enhancements, including 3D spatial feature adapters and an Auto Prompt Generator (APG), to optimize spatial representation and reduce reliance on manually crafted prompts. Fed3D-KDNet employs a dual knowledge distillation strategy to mitigate catastrophic forgetting and improve cross-client knowledge transfer, ensuring robust generalization across heterogeneous datasets. The proposed methodology was evaluated on multi-organ CT datasets, including the BTCV benchmark, under centralized and federated settings. Experimental results demonstrate that Fed3D-KDNet achieves state-of-the-art performance with an average Dice score of 80.53% and an average Hausdorff Distance (HD) of 11.43 voxels in federated experiments involving seven clients, showing 5.04% improvement in Dice accuracy and a 4.35 voxel reduction in HD. Moreover, our model demonstrates superior efficiency with a computational cost of 371.3 GFLOPs, 26.53 million tuned parameters, and an inference time of 0.058 seconds per iteration. These results validate the efficacy, scalability, and computational efficiency of Fed3D-K

关键词： Federated learning knowledge distillation medical image segmentation transformer

来源：评论

学校读者我要写书评

暂无评论

Document Summarizer: A Machine Learning approach to PDF summarization 4

Document Summarizer: A Machine Learning approach to PDF summ...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Peddarapu, Rama Krishna Anogna, Sudagoni Harshini, M.N.S. Sri Sireesha, J. Rathna, K. Guna Department of Computer Science and Engineering Faculty of Computer Sciences and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India

To address the need for summarizing and extracting information efficiently, this paper highlights the growing challenge posed by the increasing number of PDF files. Reading lengthy documents is a tedious and time-consuming task. To save time and quickly comprehend the key points of a PDF, a PDF summarizer tool has been developed to tackle these issues. In today's professional environments, gathering and managing data from documents is critical. This article introduces an innovative solution called DocSum, which automates the process of summarizing extracted data. Powered by *** Core, the DocSum system allows users to upload PDF documents for processing and receive concise summaries in return. The system features a user-friendly interface that encourages interaction and engagement, utilizing AI and machine learning techniques to streamline document handling. Users can request specific summaries, enabling efficient document management workflows. By empowering users to seamlessly interact with vast amounts of information, DocSum enhances productivity and explores new ways to optimize document management. This solution is ideal for professionals seeking to stay informed and manage data effectively, while also keeping track of advancements in document handling technologies across multiple industries. It is not only helpful for professionals but also helpful for students who need quick revision or examinations, teachers to gain brief knowledge on the concepts. © 2025 The Authors. Published by Elsevier B.V.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

An optimal feature selection-based deep learning approach for wheat disease identification

引用

Multimedia Tools and Applications 2025年第14期84卷 12855-12876页

作者： Raja, S. M. Naveen Nargunam, A. Shajin Department of Information Technology Noorul Islam Centre for Higher Education Thuckalay Kumaracoil India Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Thuckalay Kumaracoil India

Globally, wheat is a staple food crop, which plays a vital role in food security and sustenance for millions of people. However, the diseases in wheat crops affect their growth, productivity, and crop quality. Hence, early and timely disease detection is significant to prevent the loss of productivity and the economy. This article introduces an innovative hybrid model combining Moth Flame Optimization (MFO) and Radial Basis Functional Neural Network (RBFNN) for the prediction of disease wheat leaves from healthy ones. Initially, the wheat leaf image containing the normal and diseased leaves is collected and utilized as input for the system. Then, the dataset was filtered and related leaf attributes are tracked using the Histogram of Oriented Gradients. Subsequently, MFO fitness was employed to select the most informative leaf images from the extracted feature set. By utilizing these selected features, the RBFNN was trained to classify the normal and healthy leaves accurately. This model was evaluated with the wheat leaf dataset and the performances are evaluated. The presented model achieved greater accuracy 99.32%, recall of 99.33%, f-measure of 99.33%, and precision of 99.33%. The implementation outcomes exhibit that the designed framework has great potential for practical application in agriculture. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Approach to Predict Heart Diseases Using Fused Dataset 3rd

Machine Learning-Based Approach to Predict Heart Diseases Us...

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Uddin, Khandaker Mohammad Mohi Mohamed, Abdirahman Biswas, Nitish Mostafiz, Rafid Department of Computer Science and Engineering Southeast University Dhaka1208 Bangladesh Department of Computer Science and Engineering Dhaka International University Dhaka1205 Bangladesh Institute of Information Technology Noakhali Science and Technology University Noakhali Bangladesh

ISBN: (纸本)9789819739363

Cardiovascular disease is currently a prominent sickness that kills the majority of sufferers. The medical evaluation of cardiac disease presents significant problems. This diagnostic method is complex, requiring precision and efficiency. Early detection of heart disease can significantly lower the chance of death. In light of the high occurrence of cardiac issues in contemporary times, the prediction of heart disease has emerged as one of the most challenging endeavors within the medical field in recent years. Scientists examined a plethora of closely related characteristics to identify the most trustworthy predictors of these diseases. In this work, we use Machine Learning (ML) approaches to detect the existence of cardiac problems. The suggested method predicts the likelihood of heart disease and classifies people into risk categories. This is performed by utilizing several machine learning algorithms such as Support Vector Machine (SVM), Gradient Boosting, Random Forest (RF), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Logistic Regression (LR). The developed system is trained and evaluated using a composite dataset derived from two separate sources. The results of the experiments show that, when compared to other machine learning algorithms, the Random Forest approach achieves the greatest accuracy rate, achieving an amazing 99.99%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CMV2U-Net: A U-shaped network with edge-weighted features for detecting and localizing image splicing

引用

Journal of Forensic sciences 2025年第0期70卷 2025 Apr 3页

作者： Akram, Arslan Jaffar, Muhammad Arfan Rashid, Javed Boulaaras, Salah Mahmoud Faheem, Muhammad Faculty of Computer Science and Information Technology The Superior University Lahore Pakistan Information Technology Services University of Okara Okara Pakistan Department of Mathematics College of Science Qassim University Buraydah Saudi Arabia VTT Technical Research Centre of Finland Espoo Finland

The practice of cutting and pasting portions of one image into another, known as “image splicing,” is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U-Net, an edge-weighted U-shaped network-based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U-Net provides high AUC and F₁ in localizing tampered regions, outperforming state-of-the-art techniques. Noise, Gaussian blur, and JPEG compression are post-processing threats that CMV2U-Net has successfully resisted. © 2025 American Academy of Forensic sciences.

关键词： digital forensics feature fusion image authentication image forgery localization image splicing detection U-shaped network

来源：评论

学校读者我要写书评

暂无评论

Developing a Translation Model to Bridge ASL and Indian Regional Languages Using Neural Networks

Developing a Translation Model to Bridge ASL and Indian Regi...

引用

2025 International Conference on Computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Swetha, M.S. Muneshwara, M.S. Venkatesh, Varnitha Kudremane, Shreyaa S. M. Nair, Ritika S Vismitha, H. Bms Institute of Technology & Management Department of Information Science and Engineering Bengaluru India Bms Institute of Technology & Management Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331538538

In this resarch work, a real-time hand gesture detection system for Ame rican Sign Language (ASL) that enables the deaf-dumb co mmun ity to interact with others by translating sign language into text. The current methods for translating ASL to English primarily use computer vision tools like Media Pipe and OpenPose to recognise hand landma rks and motions. To tackle this issue, we provide a novel convolutional neural network (CNN) architecture that removes the need for manual feature engineering by automatically obtaining discriminative spatial-temporal characteristics from raw video streams. CNNs are more suited to handle the dynamic and highly changeable nature of hand movements because they are very good in simu Itaneously recording spatial and temporal informat ion, unlike LSTM (Long Short-Term Memory) networks, which are frequently emp loyed for sequential data. CNNs are perfect for rea l-t ime applications because they provide more efficient processing and faster inference time. By using multilingual language translators and advanced CNNbased deep learning models, we aim to reduce the communication gaps across India's diverse linguistic minorities. To ensure accurate performance evaluation and successful model learning, the dataset was divided into 70 % for tra inin g and 30 % for testing. Compared to tradit ional methods, the proposed approach has a 95% accuracy rate. With potential uses in public services, healthcare, and education, this program encourages assistive technology by offering a practical tool to improve communicat ion between sign language users and the general public. Through encouraging interlanguage contact, the system helps create a society that is more inclusive. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Image Caption Generation Using Deep Learning 12th

Image Caption Generation Using Deep Learning

引用

12th International Conference on Big Data Analytics, BDA 2024

作者： Mehta, Shikha Baranwal, Honey Saxena, Sarvagya Department of Computer Science and Engineering Jaypee Institute of Information Technology Uttar Pradesh Noida100190 India

ISBN: (纸本)9783031861925

Artificial intelligence (AI) often lacks cultural diversity with limited representation of non-Western contexts which results in biased outputs. Addressing this gap, this paper presents a deep learning-based image captioning system specifically for Indian deities, a culturally rich but underrepresented subject in AI research. Due to the lack of benchmark datasets for such a culturally significant imagery, this work introduces the DIVINE 1K dataset. This dataset contains 1,000 images of Indian deities, each annotated with five manually curated captions. To develop an accurate caption model we evaluated several deep learning architectures such as VGG16, ResNet50, ResNet152, InceptionV3, MobileNetV2, and DenseNet201 for feature extraction. Performance is assessed through BLEU, ROUGE, and METEOR scores, with DenseNet201 emerging as the most effective model. This optimized model is subsequently deployed within a mobile application, enabling real-time caption generation for images of Indian deities. This work not only contributes a specialized dataset but also advances culturally inclusive AI by pioneering automated image captioning tailored to Indian iconography, thus bridging a critical gap in AI cultural representation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Boundary Extraction for Unseen Entities Prediction Using Bidirectional Long Short-Term Memory 17th

Boundary Extraction for Unseen Entities Prediction Using Bid...

引用

17th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2024

作者： Kuntichod, Watcharet Lee, Wilaiporn Prayote, Akara Department of Computer and Information Science King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok10800 Thailand

ISBN: (纸本)9789819606917

Named Entities Recognition (NER), which is a task to identify and classify named entities within text, has gained significant popularity in recent years. This task often requires pre-labeled data and large datasets to achieve high accuracy. A key challenge in NER is extracting unseen entities that have not been previously labeled or are new terms, posing difficulties in adapting to rapidly changing data and the emergence of new vocabularies. In this article, we propose a model utilizing Bidirectional Long Short-Term Memory (Bi-LSTM) for boundary extraction. The model aims to enhance the detection and labeling of unseen entities by leveraging Bi-LSTM's strengths in capturing contextual information and accurately identifying entities boundaries. The model demonstrates high potential in identifying unseen names without pre-labeling. Our study demonstrates the model's showcasing its effectiveness in discovering unlabeled words and unseen entities in Thai language datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Labeled data

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：