检索结果-内蒙古大学图书馆

Detecting and localizing multiple forgeries with TransGAN

Iran Journal of computer Science 2025年 1-17页

作者： Singh, Upasana Rathor, Sandeep Kumar, Manoj Department of Computer Engineering and Applications GLA University U.P. Mathura India Department of Information Technology GGV University Chhattisgarh Bilaspur India

The rapid rise of manipulated videos in the digital era necessitates advanced forgery detection and localization techniques. This study presents a novel approach using a GAN-based framework integrated with a 3D Swin-B Transformer Encoder–Decoder architecture for future frame prediction. A ConvLSTM-based Siamese network serves as a discriminator, capturing spatiotemporal inconsistencies, while forgery localization is enhanced through attention maps and a patch-based strategy. Experimental validation on diverse datasets demonstrates the effectiveness of the proposed method, achieving 98.97% detection accuracy and 100% localization accuracy, surpassing existing techniques. The results highlight the robustness of the approach in identifying and localizing various types of video forgeries, making a significant contribution to digital content forensics. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial training Forgery detection Forgery localization GAN-based framework Multimedia forensics Spatiotemporal forgery

来源：评论

学校读者我要写书评

暂无评论

Adaptive Treatment Planning via Multi-class Segmentation of GI Tract Tumours 6th

Adaptive Treatment Planning via Multi-class Segmentation of ...

引用

6th International conference on communication and computational technologies, ICCCT 2024

作者： Jain, Samyak Pal, Aarush Andrew, J. Maheshwari, Saatvik Department of Computer Science and Engineering and Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

ISBN: (纸本)9789819774258

This study addresses gastrointestinal cancer radiation therapy challenges by implementing advanced deep learning techniques. We focus on automating manual segmentation tasks during treatment planning to enhance efficiency and patient tolerance. Our methodology uses a diverse 3D MRI scan dataset to employ image analysis, Convolutional Neural Networks (CNNs), and Image Segmentation. The primary architectural choices involve the U-Net and InceptionResNetv2 models, contributing to developing a predictive segmentation model. This substantial result underscores the effectiveness of our approach in achieving accurate segmentations in the clinical setting. The overarching objective of our project is to automate the segmentation of the stomach and intestines in MRI scans, thereby streamlining radiation therapy planning for improved efficiency and patient care. In our evaluations, the implemented model demonstrates a commendable dice coefficient of 0.7, as indicated by metrics such as dice loss. Anticipated outcomes encompass reduced treatment times, enhanced patient comfort, and optimised tumour radiation doses while minimising healthy tissue exposure. The successful implementation of this advanced model holds the potential to revolutionise current radiation therapy practices, significantly elevating cancer treatment outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MACPGANA: design of a highly efficient multimodal agriculture commodity price prediction model via generative adversarial networks & autoencoders

引用

International Journal of Information technology (Singapore) 2025年第4期17卷 2355-2368页

作者： kambo, Rubi Pillai, Jyothi Soni, Sunita Urkude, Giridhar Department of Computer Science and Engineering Bhilai Institute Technology Chhattisgarh Durg India Department of Computer Science and Engineering Rungta College of Engineering and Technology Chhattisgarh Bhilai India Symbiosis Institute of Technology Nagpur Campus Symbiosis International(Deemed University) Pune India Department of Computer Applications Bhilai Institute of Technology Durg Chhattisgarh India

This paper presents MACPGANA, a novel multimodal agriculture commodity price prediction model leveraging Generative Adversarial Networks (GAN) and Autoencoders (AEs). The model integrates multimodal data to extract and represent features efficiently, employs GAN for feature selection, and uses predictive autoencoders to estimate inter-day price movements. A Q-Learning-based feedback loop ensures continuous optimization of prediction performance. MACPGANA achieves high accuracy, precision, and recall while maintaining low computational complexity, making it suitable for real-time and large-scale applications. The model’s effectiveness is demonstrated across diverse commodities, highlighting its potential for scalable and efficient agricultural price prediction. © Bharati Vidyapeeth's Institute of computer applications and Management 2025.

关键词： Agriculture commodity price prediction Autoencoders (AE) Generative adversarial networks (GAN) Multimodal feature extraction Q-learning optimization Real-time price forecasting

来源：评论

学校读者我要写书评

暂无评论

An Effort Toward Localization and Recognition of Elevation Values in a Topographic Sheet 7th

An Effort Toward Localization and Recognition of Elevation V...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： Pradhan, Ashis Supriya, Sneha Pradhan, Mohan P. Pradhan, Ratika Department of Computer Science and Engineering Sikkim Manipal Institute of Technology Sikkim Manipal University Gangtok India Department of Computer Applications Sikkim University Sikkim India

ISBN: (纸本)9789819764648

This study focuses on efficient elevation value localization and recognition in topographic sheets (TS) through morphological operations and YOLO-based deep learning. The aim is to enhance the digitization process, crucial for creating Digital Elevation Models (DEMs) widely used in various applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

IoT Based Agricultural Monitoring and Alert System 4

IoT Based Agricultural Monitoring and Alert System

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Priya, V Vishnu Nisanth, G. Dhanushree, D. Sindhu, M. Varshini, T. Preteka, A.T. Kongu Engineering College Department of Computer Science and Engineering Perundurai India Kongu Engineering College Department of Computer Applications Perundurai India Kongu Engineering College Department of Computer Technology Perundurai India

ISBN: (纸本)9798331523923

The goal of this project is to implement an Internet of Things (IoT)-based Agricultural Monitoring & Alert System (AMAS) that will integrate multiple sensors to continuously monitor agricultural parameters, such as soil moisture levels, soil temperature, water levels, irrigation pump operation status, and water quality, to improve precision farming practices. Enabling farmers to make well-informed decisions, maximize resources, and enhance crop output in real time is the primary objective of the AMAS system. The challenges of using IoT for agricultural monitoring, include issues with adoption among farmers, dependable technology, efficient data administration, and connectivity. Small-scale farmers' financial hardship and rural areas' restricted access to technology. Many obstacles stand in the way of the widespread adoption of IoT-based agricultural monitoring systems, such as smallscale farmers' limited financial resources, rural communities' restricted access to technology, and problems with connectivity, dependable data handling, and system scalability. Machine learning-based prediction models and IoT-integrated smart irrigation are two recent approaches that have showed promise in tackling these issues, but they still face obstacles such high implementation costs, technical complexity, and infrastructure dependence. By improving yields, increasing output, and facilitating remote monitoring, the AMAS system seeks to overcome these limits while taking into account the unique requirements and limitations of farmers. This study plan to enhance productivity, optimize yield, and implement remote monitoring. © 2025 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

A holistic securing approach to speech steganography system with message embedding and pause optimization

引用

Multimedia Tools and applications 2025年 1-27页

作者： Kumar, Surendra Yadav, Arun Singh Dwivedi, Mridula Kumar, Mohit Department of Computer Engineering and Applications GLA University Uttar Pradesh Mathura281401 India Department of Computer Science University of Lucknow Uttar Pradesh Lucknow226007 India Lucknow India Department of IT Dr. B.R. Ambedkar National Institute of Technology Jalandhar India

Nowadays, prevention control of message sharing as well as security enhancement in speech transmission which occurs due to users having a passion for novel inventions, communication system benefits. In this paper, the main objective is to design a speech steganography framework with covert message data transmission including speech. The secret message data is encrypted with the help of the Hyperelliptic Curve Cryptography (HECC) algorithm to provide a maximum security environment. The designed speech steganography framework is integrated with the pause removal mechanism respectively. Since, the Stegospeech is sent into the channel, as the Stegospeech as of now obtained the secret Message data its transfer speed will increment. Then at that point, it needs high bandwidth for transmission as well as needs higher energy utilization. In this manner, to decrease the data transfer speed, the best procedure is to eliminate the undesirable pause in the speech, the pause removal strategy carried out utilizing the combinations of Ensemble Empirical Mode Decomposition (EEMD) with Hilbert-Huang Transform (HHT). Then, some techniques are used to embed the message into the speech like 4-level Discrete Wavelet Transformation (DWT), Matrix definition, and Single Value Decomposition (SVD). They are likewise utilized for the secret message extraction from speech signal as well as message information from the Stegospeech signal. The presented strategy is carried out and analyzed towards the different invasions in the output. The Correlation Coefficient (CC), the Peak Signal-To-Noise Ratio (PSNR), the Signal-To-Noise Ratio (SNR), the Number of Pixels Changing Rate (NPCR), and the Unified Average Changing Intensity (UACI) are some of the popular standards that are utilised when comparing two encrypted voice signals. The numbers 33.3% and 100%, respectively, for UACI and NPCR are considered to be optimum states. It is noticed that the presented technique provides better Statistical resul

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

South Indian agricultural crop yield prediction using deep learning and transfer learning models

引用

Theoretical and Applied Climatology 2025年第5期156卷 1-16页

作者： Anandavalli, R. Karthigadevi, K. Rani, G. Elizabeth Department of Computer Applications Kalasalingam Academy of Research and Education Krishnankoil India Department of Artificial Intelligence and Data Science Kalaingar Karunanidhi Institute of Technology Coimbatore India

Agriculture is an essential part of the Indian economy, so crop yield (CY) prediction is vital to help farmers and their businesses understand when to plant a crop and when to harvest based on seasons for better CY. This study proposes a deep learning model called Mish Activation-based Bidirectional Gated Recurrent Unit (MABGRU) to forecast CYs primarily grown throughout India. The system comprises the following steps: preprocessing, deep feature extraction, feature selection, and CY prediction. Initially, the system performs preprocessing steps such as imputation and normalization to handle the missing values and standardize the dataset. Then, deep features are learned using the Deformable Attention-based Residual Network-50 (DARN50). Then, the best features are chosen from the extracted feature set using the Tent chaotic map and phasor operator, including the Sparrow search algorithm (TPSSA). Finally, MABGRU is employed for CY prediction. The result of the system is compared with the existing systems, and our model outperforms the previous techniques by achieving a maximum accuracy of 98.88% with less computational time (15.9 ms). © The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2025.

关键词： Crop yield prediction Deep feature extraction Deep learning Feature selection Preprocessing Texture feature extraction Transfer learning

来源：评论

学校读者我要写书评

暂无评论

GraphXAI: a survey of graph neural networks (GNNs) for explainable AI (XAI)

引用

Neural Computing and applications 2025年 1-52页

作者： Nandan, Mauparna Mitra, Soma De, Debashis Department of Computer Applications Techno Main Salt Lake West Bengal Kolkata India Department of Computational Science Brainware University West Bengal Barasat India Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology West Bengal West Bengal Kolkata India

Graphs find wide applications in numerous domains, ranging from simulating physical systems to learning molecular fingerprints, predicting protein interfaces, diagnosing diseases, etc. These applications encompass simulations in non-Euclidean space, in which a graph serves as an ideal representation, and are also an indispensable means of illustrating the connections and interdependencies among its various constituents. Graph neural networks (GNNs) are specific types of neural networks that are specifically built to handle data possessing a graph structure. They are highly effective at capturing intricate relationships among different entities. Nonetheless, their "black-box" characteristics pose difficulties in transparency, trust, and interpretability, especially in critical sectors like heath care, banking, and autonomous systems. Explainable artificial intelligence (XAI) has emerged to clarify these obscure decision-making processes, thus enhancing trust and accountability in AI systems. This survey paper delves into the intricate interplay between GNNs and XAI, including an exhaustive taxonomy of the various explainability methods designed for graph-structured data. It classifies the existing explainability methods into post hoc and self-interpretable models. The paper analyzes their practical applications in diversified fields, highlighting the significance of transparent GNNs in essential sectors such as fraud detection, drug development, and network security. The survey also delineates evaluation parameters for assessing explainability along with addressing persistent issues in scalability and fairness. The paper concludes by addressing prospective advancements in the subject, including the creation of innovative XAI methodologies tailored for GNN architectures, integration with federated learning, and utilization of these models in interdisciplinary fields. This study bridges the gap between GNNs and XAI, providing an essential resource for researchers and p

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A study on Electronic Health Records (EHR) in India: Security challenges, initiatives and blockchain integration 4th

A study on Electronic Health Records (EHR) in India: Securit...

引用

4th International Conference on Computational Methods in Science and technology, ICCMST 2024

作者： Bhargava, Misha Mahi, Samarjit Rao, Vidya Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal India

ISBN: (纸本)9781032911571

With its vast population and extensive healthcare requirements, India is moving toward digitalizing its health records. Safeguarding Electronic Health Records (EHRs) is crucial given the increase in security breaches and attacks, with India’s healthcare sector at the forefront. This study provides an overview of EHR security in India by exploring the EHR adoption rate in India and the barriers to its use. It focuses on the significant security challenges they bring, and the initiatives currently being implemented in India, such as the Ayushman Bharat Digital Mission (ABDM) and the recently released National Accreditation Board for Hospitals (NABH) Digital Health Standards. Integrating Blockchain in current EHR systems to resolve the observed challenges is then explored. The findings of this study show the urgency of integrating emerging technologies such as blockchain which have the potential for patient-controlled data sharing and data immutability possibly within the framework of the ABDM. This study aims to serve as a valuable resource for healthcare professionals, researchers and other regions seeking to understand and improve EHR security. © 2025 the Author(s).

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Accessing Deep Learning Techniques for Commodity Price Prediction: A Comparative Assessment Across Energy, Precious Metal, and Agricultural Futures

Accessing Deep Learning Techniques for Commodity Price Predi...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Nandeshwar, Tushar Babulal Sharma, Akanksha Verma, Chandan Kumar Maulana Azad National Institute of Technology Department of Mathematics Bioinformatics and Computer Applications M.P. Bhopal India

ISBN: (纸本)9798331512965

This study performs an in-depth comparison of deep learning approaches - CNN, LSTM, GRU, and their bidirectional variants (BiLSTM and BiGRU) - to anticipate commodity futures prices, particularly in the crude oil, gold, and corn markets. The approach used in our study combines fundamental and technical factors with thorough variable selection to establish the most effective predictors. The Grid Search Cross-Validation approach is employed for optimizing the hyperparameters of deep learning architectures. The efficacy of applied models is evaluated using common evaluation indicators: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Coefficient of Determination(R2), and Adjusted R2. The results presented enhance the existing research on AI applications in financial markets, providing recommendations for the development of more precise forecasting techniques for researchers. © 2025 IEEE.

关键词： Crude oil price

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：