检索结果-内蒙古大学图书馆

Semantic Segmentation of Areal Images using Pixel Wise Segmentation

Procedia computer science 2025年 259卷 463-472页

作者： Swathi Gowroju V. Swathi Narsimhulu K. Shilpa Choudhary Associate Professor Department of Artificial Intelligence & Machine Learning Sreyas Institute of Engineering and Technology Hyderabad Telangana Assistant Professor Department of Computer Science Sreyas Institute of Engineering and Technology Hyderabad Telangana Assistant Professor Department of Computer Science Matrusri Engineering College Hyderabad Telangana Associate Professor Department of Computer Science NGIT Hyderabad Telangana

Particularly in regions hit by flooding, precise semantic segmentation of aerial photographs is essential for post-disaster evaluation and urban planning. The high-resolution aerial photography collection FloodNet, created for pixel-by-pixel segmentation of flooded and non-flooded landscapes, is presented in this work. Aerial photos taken from various geographic regions make up the collection, and segmentation masks are used to detect flooded roads, houses, cars, plants, and other vital infrastructure. In order to conduct semantic segmentation on aerial photos and capture the fine-grained information necessary for flood damage assessments, the suggested model makes use of a U-Net architecture. Morphological post-processing is also used to improve object delineation and smooth segmentation borders. The model showed consistent performance with little overfitting, achieving training accuracy of 84% and validation accuracy of 81% over 200 epochs. Effective generalization to unknown data was demonstrated by the validation loss stabilizing at 0.55 and the training loss declining from 1.1 to 0.45. The findings show that the suggested method can reliably identify and categorize areas damaged by flooding from aerial photos, enabling automated flood assessment and speeding up disaster relief activities. There is a lot of promise for integrating this model and dataset combination into real-time catastrophe monitoring, urban planning, and geospatial analytic pipelines.

关键词： Satellite images areal images semantic segmentation UNet using morphology Pixel wise segmentation

来源：评论

学校读者我要写书评

暂无评论

Optic disc pallor diagnosis using ROMF based optic disc segmentation in fundus images

引用

Multimedia Tools and Applications 2025年第2期84卷 517-546页

作者： Jency, J. Shunmugan, S. Research Scholar Department of Computer Science S. T. Hindu College Nagercoil Affiliated to Manonmaniam Sundaranar University Tirunelveli India Associate Professor Department of Computer Science & Applications S.T. Hindu College Nagercoil. Affiliated to Manonmaniam Sundaranar University Tirunelveli India

Disc pallor is a pale yellow discoloration of the optic disc (OD) that causes irreversible damage to the fiber of the retina's anterior visual pathway. Automatic disc pallor diagnosis has obstacles such as increased time consumption and reduced accuracy due to less powerful OD segmentation algorithms. Hence, a new development for pallor diagnosis through the enhanced version of OD segmentation, namely, 'Optic Disc Pallor Diagnosis using ROMF-based OD segmentation in fundus images (ODPD_ROMF)', is proposed. Herein, the essential contribution is a new OD segmentation method, namely 'Optic disc segmentation using Retinex and ONH structure-specific Membership based FCM method (ROMF)’. The ROMF method is constituted based on a new variant of Fuzzy C Means (FCM), namely 'Optic Nerve Head (ONH) structure-influenced Fuzzy C Means (FCM)', where the membership function and the objective function are redefined to calibrate according to the refined or updated ONH structure, which results in fast and accurate OD segmentation. The second-best approach has an average classification accuracy of 93.00, while the proposed ODPD_ROMF method has an average accuracy of 96.17. The suggested ROMF method's average segmentation accuracy in OD segmentation is 97.52, while the second-best method's average segmentation accuracy is 96.66. Because of its great competence, the proposed ODPD_ROMF method can be utilized to identify disc pallor more effectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Membership functions

来源：评论

学校读者我要写书评

暂无评论

Unleashing Facial Expression Recognition for Stress Detection Using Deep CNN Model.

引用

Procedia computer science 2025年 259卷 306-315页

作者： Geethu S Kumar Jo Cheriyan Aparna N Swathy J Research Scholar Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai- 600 119 Tamilnadu India Assistant Professor Department of Information Science and Engineering Cambridge Institute of Technology Bangalore-560 036 Karnataka India Assistant Professor Department of Computer Science and Engineering Saintgits College of Engineering Kottayam- 686 532 Kerala India Assistant Professor Department of Computer Science and Engineering Cambridge Institute of Technology Bangalore-560 036 Karnataka India

The technology and field of study known as Facial Emotion Recognition (FER) focuses on recognising and deciphering human facial expressions to ascertain emotions. It incorporates aspects of psychology, machine learning, and computer vision. Considering its ability to analyse facial expressions and spot signs of stress or emotional distress, FER plays a vital role in the detection of stress. Microexpressions are fleeting, uncontrollably expressed facial expressions that convey true feelings. These ephemeral expressions, which are frequently linked to stress, can be captured by FER systems. With its capacity to manage intricate patterns and variances in face expressions, FER utilising deep learning has grown in popularity. A novel FER system was designed to overcome issues that plague current FER systems, such as imbalanced datasets and robustness to noisy inputs. Large datasets are handled effectively by FER employing Deep CNN because of its architecture, which is built for high-dimensional input like images. Leveraging FER using Deep CNN achieves notable performance improvements, attaining an accuracy of 95.65 % and F1 score of 94.02%. Deep learning-based FER marks a substantial advancement in our ability to recognize and decipher facial expressions that convey emotions. FER technology has the ability to revolutionize several fields by improving intuition and sensitivity to human emotions through further development and thoughtful assessment of ethical ramifications. FER systems will advance in sophistication as science and technology develop, offering more profound understanding of human emotional states and promoting improved human-machine interactions.

关键词： Stress PPG Conv-XGBoost deep learning mental health

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology for Secure Smart Grid Access Control

Blockchain Technology for Secure Smart Grid Access Control

引用

International Conference on Power Engineering and Intelligent Systems, PEIS 2023

作者： Maurya, Vijendra Kumar Kothari, Rakshit Sachdev, Payal Rathore, Narendra Singh Associate Professor Department of Computer Science and Engineering Geetanjali Institute of Technical Studies Dabok Udaipur India Assistant Professor Department of Computer Science and Engineering Geetanjali Institute of Technical Studies Dabok Udaipur India Campus Director Geetanjali Institute of Technical Studies Dabok Udaipur India

ISBN: (纸本)9789819972159

The use of smart grid technologies, in the energy sector has brought about upgrade, such as high efficiency, lower operating costs and better energy management. However, it has also established security aspects. Safeguarding the smart grid is of importance due to its role as essential infrastructure. The innovative potential of blockchain holds promise in enhancing the security of the grid. This paper aims to explore how blockchain technology can be utilized for protecting the grid. It delves into the security issues associated with grids and investigates how blockchain can address them. Additionally, it provides an analysis of studies on blockchain and its application, in grid protection while considering the pros and cons of utilizing blockchain based solutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Gated Recurrent Unit with Attention Mechanism for IC50 Prediction Model Using Amyotrophic Lateral Sclerosis Related Proteins 1

引用

International Conference on Power Engineering and Intelligent Systems, PEIS 2024

作者： Devipriya, S. Vijaya, M.S. Research Scholar Department of Computer Science PSGR Krishnammal College for Women Coimbatore India Associate Professor & Head Department of Computer Science PSGR Krishnammal College for Women Coimbatore India

ISBN: (数字)9789819767144

ISBN: (纸本)9789819767137

Amyotrophic Lateral Sclerosis is a common neurodegenerative disease that weakens the brain and spinal cord myelin nerves. Two protein targets of Amyotrophic Lateral Sclerosis are used in this study. The protein targets selected are SOD1 and TBK1. Numerous SOD1 mutations in the genome have been linked to ALS. The inhibition of the harmful effects of the defective SOD1 protein aids in ALS treatment. ALS has been linked to variations in the TBK1 gene. Modulating the immune system and neural inflammation is achieved through inhibition of TBK1. IC50 prediction is an important strategy for selecting drugs during Drug discovery. In this paper, Deep Learning models are built using a Gated Recurrent Unit (GRU) that accepts SMILES (Simplified Molecular Input Line Entry System) representation of active molecules as input. The key novelty in the proposed research is a customized GRU IC50 prediction model with attention mechanism. A new GRU model with an attention mechanism is implemented. Drug molecules and their features are collected from the ChEMBL database. More than 500 ligands are used and converted to SMILES one hot encoding for training the models. The prediction results of models are found using important metrics and observed more accurate predictions of IC50. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Autism Spectrum Disorder from Functional MRI Using Deep Learning 4th

Identification of Autism Spectrum Disorder from Functional M...

引用

4th International Conference on Advances in Information Communication Technology and Computing, AICTC 2022

作者： Pavithra, R. Abirami, S.P. Krithika, S. Sabitha, S. Tharanidharan, P. Assistant Professor Department of Computer Science and Engineering Coimbatore Institute of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Coimbatore Institute of Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9789811998874

Autism spectrum disorder (ASD) is a collection of a way of continuing neurodevelopment illnesses identified by limited and repetitive behavioral patterns, as well as social and communication impairments. Despite the fact that symptoms are most common in childhood, diagnosis is sometimes delayed. Because the current ASD diagnostic technique is solely uncertain and questionnaire, requiring the physician to review the behavior and developmental history of a child. It's been suggested that behavioral symptoms in ASD are linked to brain findings of increased short-distance and diminished long-distance connections. The suggested approach makes use of brain imaging data from Autism Brain Imaging Data Exchange (ABIDE), a global multi-site database. For ASD identification, the proposed approach uses functional connectivity characteristics extracted from resting state functional MRI data. ASD patients’ brain connections could be disturbed. The presented method extracts time series from 122 regions of interest defined by the Bootstrap Analysis of Stable Clusters (BASC) and also extracts time series from 48 regions of interest defined by the Harvard Oxford (HO) brain atlas to create an efficient functional connectivity matrix for all individuals. Synthetic Minority Over-sampling Technique (SMOTE) an oversampling procedure employed for artificial data generation. The classification challenge is carried out using a Recurrent Convolutional Neural Network (RCNN) and Convolutional Neural Network (CNN) and results were compared. In both models, fivefold Cross-Validation is applied. The model performed better in the modified experiment, with RCNN achieving an accuracy of nearly 85%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Text Steganography in Statistically Clustered Iris Image

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2021年第33期8卷 1-7页

作者： Neamah, Irtefaa A. Mohammed, Hind Rustum Assistant Professor Department of Mathematics Faculty of Computer Science and Mathematics University of Kufa Iraq Professor Department of Computer Science Faculty of Computer Science and Mathematics University of Kufa Iraq

The hiding text within the iris to increase the data protection method is discussed in this work. It is impossible to distinguish between the iris image before and after concealment, and the difference between the two images only after using statistical measures such as PSNR and MSR to compare them. The proposed database consists of 500 images with different formats (tif, gif, png, jpg, .bmp) selected for analysis. The proposed method is shown with more accurate results, stronger image encoding, and high-efficiency text protection using performance evaluation factors to assess business standards. The success of hiding high-text ratios proved successful. Experimental results were shown based on a statistical strategy, and that the text was converted into two random variables, X and Y, which were distributed to Asia. Then, the random variables’ data were included in the iris segment, cut-off, and iris’ clustered image. It appears that the use of our proposed scheme can include sufficient data in the image of the iris that maintains the accuracy of the identification. Copyright © 2020 Irtefaa A. Neamah et al., licensed to EAI. This is an open access article distributed under the terms of the Creative Commons Attribution license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection Using Convolution Neural Network 2

Plant Disease Detection Using Convolution Neural Network

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Rani, K. Pushpa Lavanya, G. Madhuri, K. Sai Vamsinath, J. Sabitha, Ch. Rao, K. Srinivas Department of Computer Science and Engineering MLR Institute of Technology Dundigal Hyderabad 500043 Assistant Professor Department of CSE VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Guntur 522302

ISBN: (纸本)9798350370188

Today the persistence of plant and plant diseases is a substantial problem for cultivators, disease diagnosis is important in the farm. To preserve the production of crops, adequate consideration is a must. To isolate and detect infections in conventional situation, a lot of workforce, time, and frequent surveillance of the farm is involved. If no proper safety measures are not taken in protecting the crops, then it may damage the production often diseases make the plants weak by interrupting the photosynthesis. This paper shows in-depth study methods used in disease diagnosing. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

GS-FFO Based Meta-Heuristic Clustering for Discovering Colossal Patterns in High-Dimensional Data 2nd

GS-FFO Based Meta-Heuristic Clustering for Discovering Colos...

引用

2nd Congress on Control, Robotics, and Mechatronics, CRM 2024

作者： Reddy, T. Sreenivasula Sathya, R. Nuka, Mallikharjuna Rao Research Scholar Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Assistant Professor Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Professor Department of Computer Applications Annamacharya Institute of Technology & Sciences YSR Kadapa Andhra Pradesh Rajampet516115 India

ISBN: (纸本)9789819768097

Colossal pattern mining, which involves deriving important relationships and insights from large and complex datasets, is an essential part of data analysis. Extracting association rules that satisfy preset minimum support and confidence criteria from a given database is the aim of association rule mining (ARM). Nevertheless, ARM often generates an unusually large number of association rules that are hard for end users to comprehend or validate, which lessens the significance of data mining discoveries. Based on the clustering methodology, this research study presents a new mining strategy. The process begins with a method called the Expressed Data Matrix (EDM), which transforms unstructured data into a structured format and enhances the quality and organisation of the information. Primary data cleaning processes are used to eliminate noise and inconsistencies from the data in order to further improve it. To address high-dimensionality issues and boost mining productivity, dimensionality reduction—which lowers the dataset to its most valuable features—is accomplished using Eigen-Principal Component Analysis (PCA). The core of this study is the hybridised clustering approach, or GS-FFO, which combines the Fruit Fly Optimisation technique (FOA) with Glow Swarm Optimisation (GSO). This technique improves the quality of clustering and reduces the probability of local optima convergence by integrating the benefits of both approaches. The suggested GS-FFO model outperforms with four datasets, including accident, pumbs*, retail, and yeast, with an accuracy of up to 98.5%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Precaution Chatbot for Epilepsy Patients using Natural Language Processing and Deep Learning Sequential Model

引用

Procedia computer science 2024年 233卷 537-546页

作者： E Kasthuri S. Subbulakshmi Rajasree Sreedharan Research Scholar Department of Computer Science and Engineering Assistant Professor Department of Computer Science and Applications Amrita School of Computing Amritapuri India Associate Professor Division of Nephrology Department of Pediatrics Medical College of Wisconsin Milwaukee Wisconsin USA

Epilepsy is a brain disorder that can affect people of all ages which is one of the most common neurological disorders affecting around 50 million individuals. Healthcare Chatbots schedule appointments, respond to patient inquiries, and offer relevant information, freeing medical staff to handle life crises. This paper implements a chatbot for epilepsy patients to increase awareness about epilepsy. Patients may easily access this AI-based healthcare chatbot whenever they have queries regarding precautions to be taken by epilepsy patients. Chatbot uses a rich set of epilepsy-related datasets collected from trusted websites which are preprocessed with NLP techniques to prepare the data for model ***, LSTM, and RNN models are created and evaluated to produce answers to user queries related to possible precautions to avoid seizures, safety measures to be taken by patients with seizure history, etc. Evaluation of models shows that the RNN model generates more accurate answers with 94% accuracy. Finally, the epilepsy question answering Chatbot for precaution is concluded with the RNN model.

关键词： Epilepsy Seizure Chatbot Natutal Language Processing LSTM Long short-term memory Recurrent neural network Deep neural network

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：